diff --git a/.agents/notes/README.i18n.yaml b/.agents/notes/README.i18n.yaml index 7f5b16b9b8..b33a36665d 100644 --- a/.agents/notes/README.i18n.yaml +++ b/.agents/notes/README.i18n.yaml @@ -3,4 +3,4 @@ # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/README.md README.md: 3cfbb5154713046846a3bfcb2ccea62c0e4cb6c0 -README.zh.md: a3369a94c6761e27567b1408d98a81665443f2ef +README.zh.md: 4b3a1ee57ea61a8e8ba4d01cf7c719bbf8440e30 diff --git a/.agents/notes/README.zh.md b/.agents/notes/README.zh.md index a3369a94c6..4b3a1ee57e 100644 --- a/.agents/notes/README.zh.md +++ b/.agents/notes/README.zh.md @@ -2,7 +2,7 @@ [English](README.md) | 中文 -这里存放一类设计文档。**Agent Note(agent 决策记录)** 记录塑造本代码库的决策或提案:代码和文档无法承载的*为什么*以及*放弃了什么*。本文件是入口和契约:Agent Note 存放在哪里、何时需要写一份,以及[文件内格式](#the-file-format)。 +这里存放一类设计文档。**Agent Note** 记录塑造本代码库的决策或提案:代码和文档无法承载的*为什么*以及*放弃了什么*。本文件是入口和约定:Agent Note 存放在哪里、何时需要写一份,以及[文件内格式](#the-file-format)。 ## 布局与命名 @@ -10,7 +10,7 @@ - **生命周期**(顶层文件夹)是 Agent Note 的状态,Agent Note 随状态变化在文件夹之间移动: - **`proposed/`**:实施前评审的提案;尚未构建(或仅部分构建)。 - - **`implemented/`**:决策已交付。文件记录做了什么决定、否决了什么,并**与实际交付的内容保持同步**:当代码后续移动文件、重命名包(package)或更改键名/默认值时,Agent Note 在同一个变更中同步更新(仅限事实——路径、名称、结构——而非决策本身)。见 [implemented/AGENTS.md](implemented/AGENTS.md)。 + - **`implemented/`**:决策已交付。文件记录做了什么决定、否决了什么,并**与实际交付的内容保持同步**:当代码后续移动文件、重命名包或更改键名/默认值时,Agent Note 在同一个变更中同步更新(仅限事实——路径、名称、结构——而非决策本身)。见 [implemented/AGENTS.md](implemented/AGENTS.md)。 - **`rejected/`**:提案经过讨论后被否决。仅当其决策依据仍能避免一种诱人且影响重大的错误时保留;否则删除完整的英文、中文和伴随记录三文件组。 - **类别**(嵌套文件夹)是决策的*种类*——见下方[分类](#classification)。 @@ -45,13 +45,13 @@ ## 何时需要写一份 -每个非平凡变更都必须在同一 PR(Pull Request)中新增或更新至少一份 Agent Note。如果变更修改了行为、架构、跨文件或跨包契约、流程或工具、测试策略、磁盘存储格式、协议格式(wire format)或配置格式,或者其他维护者可能合理重新审视的决策,就属于非平凡变更。对未来重大工作的提案从 `proposed/` 开始;已经做出的决策从 `implemented/` 开始。选择与决策匹配的类别文件夹(见[分类](#classification))。 +每个非平凡变更都必须在同一 PR(Pull Request)中新增或更新至少一份 Agent Note。如果变更修改了行为、架构、跨文件或跨包约定、流程或工具、测试策略、磁盘存储格式、协议格式(wire format)或配置格式,或者其他维护者可能合理重新审视的决策,就属于非平凡变更。对未来重大工作的提案从 `proposed/` 开始;已经做出的决策从 `implemented/` 开始。选择与决策匹配的类别文件夹(见[分类](#classification))。 -更新已经拥有该决策的 Agent Note 即可满足规则;不要创建重复记录。只有不涉及行为、契约、结构、流程或理由变化的纯机械性或局部编辑才可豁免。Agent Note 永远不会被编辑为一个*不同的决策*:用新 Agent Note 取代旧记录,并让两个记录保持互相链接,除非后续依据下方规则完全合并旧记录。编辑 `implemented/` Agent Note 以跟踪其现有决策的所在位置是必需的,而非禁止的;见 [implemented/AGENTS.md](implemented/AGENTS.md)。 +更新已经拥有该决策的 Agent Note 即可满足规则;不要创建重复记录。只有不涉及行为、约定、结构、流程或理由变化的纯机械性或局部编辑才可豁免。Agent Note 永远不会被编辑为一个*不同的决策*:用新 Agent Note 取代旧记录,并让两个记录保持互相链接,除非后续依据下方规则完全合并旧记录。编辑 `implemented/` Agent Note 以跟踪其现有决策的所在位置是必需的,而非禁止的;见 [implemented/AGENTS.md](implemented/AGENTS.md)。 -被完全取代的 implemented Agent Note 可以合并到当前持有该决策的记录中,并删除原文件。删除前,当前记录必须保存所有独有的决策依据、备选方案、影响、验证契约和明确指出的覆盖缺口;修复所有入站链接;并在同一变更中删除中文对侧文件和一致性记录。仅部分被取代的记录不符合此条件:保留两个记录并让它们互相链接,同时更新所有仍然适用的事实。合并不得将旧文件改写成与其相反的决策,也不得让 git 历史成为决策依据的唯一副本。 +被完全取代的 implemented Agent Note 可以合并到当前持有该决策的记录中,并删除原文件。删除前,当前记录必须保存所有独有的决策依据、备选方案、影响、验证约定和明确指出的覆盖缺口;修复所有入站链接;并在同一变更中删除中文对侧文件和一致性记录。仅部分被取代的记录不符合此条件:保留两个记录并让它们互相链接,同时更新所有仍然适用的事实。合并不得将旧文件改写成与其相反的决策,也不得让 git 历史成为决策依据的唯一副本。 -只有当一项功能已从生产代码、配置、schema、持久化格式或协议格式、迁移和兼容行为中完全消失,当前文档不再将其描述为可用,且没有测试把它作为受支持行为来执行时,新增该功能的 Agent Note 才可合并进后续的移除记录。移除决策的依据和验证该功能已不存在的测试可以保留。移除决策的持有记录必须保留最初动机、为什么该动机已不足以证明保留该功能的合理性、完全移除之外的备选方案、放弃的能力、重新引入的条件,以及证明已彻底移除的验证。过时的实现清单和只验证已删除行为的测试不属于当前验证契约。仅移除一种传输、默认值、实现或展示属于部分取代;仍有任何持久数据或兼容处理也同样如此。 +只有当一项功能已从生产代码、配置、schema、持久化格式或协议格式、迁移和兼容行为中完全消失,当前文档不再将其描述为可用,且没有测试把它作为受支持行为来执行时,新增该功能的 Agent Note 才可合并进后续的移除记录。移除决策的依据和验证该功能已不存在的测试可以保留。移除决策的持有记录必须保留最初动机、为什么该动机已不足以证明保留该功能的合理性、完全移除之外的备选方案、放弃的能力、重新引入的条件,以及证明已彻底移除的验证。过时的实现清单和只验证已删除行为的测试不属于当前验证约定。仅移除一种传输、默认值、实现或展示属于部分取代;仍有任何持久数据或兼容处理也同样如此。 @@ -79,7 +79,7 @@ Status: ### 正文骨架 -每份 Agent Note 的正文以 `## Problem` 开头:动机,写法上不依赖解决方案即可独立成文。后续内容取决于生命周期;固定章节使用以下规范名称且仅限这些名称,而真正独特的技术章节(包拓扑、协议契约、schema 等)在必需章节之间可自由组织。 +每份 Agent Note 的正文以 `## Problem` 开头:动机,写法上不依赖解决方案即可独立成文。后续内容取决于生命周期;固定章节使用以下规范名称且仅限这些名称,而真正独特的技术章节(包拓扑、协议约定、schema 等)在必需章节之间可自由组织。 #### `proposed/` @@ -126,4 +126,4 @@ Status: ### 中文对侧文件 -`.zh.md` 对侧文件按 [i18n 契约](../../docs/i18n/README.md)逐章节镜像其英文对侧文件的结构;机器检查的头部标记(`# Agent Note: ` 和 `Status:` 行)保持英文原样不翻译。格式门禁跳过 `.zh.md` 文件——配对门禁负责它们的一致性。 +`.zh.md` 对侧文件按 [i18n 约定](../../docs/i18n/README.md)逐章节镜像其英文对侧文件的结构;机器检查的头部标记(`# Agent Note: ` 和 `Status:` 行)保持英文原样不翻译。格式门禁跳过 `.zh.md` 文件——配对门禁负责它们的一致性。 diff --git a/.agents/notes/archived/architecture/2026-07-22-tui-interactive-extension-service.i18n.yaml b/.agents/notes/archived/architecture/2026-07-22-tui-interactive-extension-service.i18n.yaml new file mode 100644 index 0000000000..f64a48f00f --- /dev/null +++ b/.agents/notes/archived/architecture/2026-07-22-tui-interactive-extension-service.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write .agents/notes/archived/architecture/2026-07-22-tui-interactive-extension-service.md +2026-07-22-tui-interactive-extension-service.md: e523361ceb920d2848369d7d3cf1093765d296d4 +2026-07-22-tui-interactive-extension-service.zh.md: 23c46f6bc18d576912aaa648b26877873ea60eda diff --git a/.agents/notes/implemented/architecture/2026-07-22-tui-interactive-extension-service.md b/.agents/notes/archived/architecture/2026-07-22-tui-interactive-extension-service.md similarity index 99% rename from .agents/notes/implemented/architecture/2026-07-22-tui-interactive-extension-service.md rename to .agents/notes/archived/architecture/2026-07-22-tui-interactive-extension-service.md index 86cb397483..e523361ceb 100644 --- a/.agents/notes/implemented/architecture/2026-07-22-tui-interactive-extension-service.md +++ b/.agents/notes/archived/architecture/2026-07-22-tui-interactive-extension-service.md @@ -1,6 +1,7 @@ # Agent Note: Effect-owned TUI interactive extensions Status: implemented +Archived: 2026-08-04 English | [中文](2026-07-22-tui-interactive-extension-service.zh.md) diff --git a/.agents/notes/implemented/architecture/2026-07-22-tui-interactive-extension-service.zh.md b/.agents/notes/archived/architecture/2026-07-22-tui-interactive-extension-service.zh.md similarity index 99% rename from .agents/notes/implemented/architecture/2026-07-22-tui-interactive-extension-service.zh.md rename to .agents/notes/archived/architecture/2026-07-22-tui-interactive-extension-service.zh.md index d53f526a07..23c46f6bc1 100644 --- a/.agents/notes/implemented/architecture/2026-07-22-tui-interactive-extension-service.zh.md +++ b/.agents/notes/archived/architecture/2026-07-22-tui-interactive-extension-service.zh.md @@ -1,6 +1,7 @@ # Agent Note: 由 effect 持有的 TUI 交互扩展 Status: implemented +Archived: 2026-08-04 [English](2026-07-22-tui-interactive-extension-service.md) | 中文 diff --git a/.agents/notes/archived/architecture/2026-07-27-tui-chat-channel-module-split.i18n.yaml b/.agents/notes/archived/architecture/2026-07-27-tui-chat-channel-module-split.i18n.yaml new file mode 100644 index 0000000000..0d20a831f8 --- /dev/null +++ b/.agents/notes/archived/architecture/2026-07-27-tui-chat-channel-module-split.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write .agents/notes/archived/architecture/2026-07-27-tui-chat-channel-module-split.md +2026-07-27-tui-chat-channel-module-split.md: 3cf9548d4d9d1b845bee5f7137d79a490827b082 +2026-07-27-tui-chat-channel-module-split.zh.md: d5de02bd0f7090c24ccfc5dabbbadff9ff42174e diff --git a/.agents/notes/implemented/architecture/2026-07-27-tui-chat-channel-module-split.md b/.agents/notes/archived/architecture/2026-07-27-tui-chat-channel-module-split.md similarity index 99% rename from .agents/notes/implemented/architecture/2026-07-27-tui-chat-channel-module-split.md rename to .agents/notes/archived/architecture/2026-07-27-tui-chat-channel-module-split.md index 56b345b670..3cf9548d4d 100644 --- a/.agents/notes/implemented/architecture/2026-07-27-tui-chat-channel-module-split.md +++ b/.agents/notes/archived/architecture/2026-07-27-tui-chat-channel-module-split.md @@ -1,6 +1,7 @@ # Agent Note: dsh-tui chat channel module split Status: implemented +Archived: 2026-08-04 English | [中文](2026-07-27-tui-chat-channel-module-split.zh.md) diff --git a/.agents/notes/implemented/architecture/2026-07-27-tui-chat-channel-module-split.zh.md b/.agents/notes/archived/architecture/2026-07-27-tui-chat-channel-module-split.zh.md similarity index 99% rename from .agents/notes/implemented/architecture/2026-07-27-tui-chat-channel-module-split.zh.md rename to .agents/notes/archived/architecture/2026-07-27-tui-chat-channel-module-split.zh.md index d74844a762..d5de02bd0f 100644 --- a/.agents/notes/implemented/architecture/2026-07-27-tui-chat-channel-module-split.zh.md +++ b/.agents/notes/archived/architecture/2026-07-27-tui-chat-channel-module-split.zh.md @@ -1,6 +1,7 @@ # Agent Note: dsh-tui 聊天通道模块拆分 Status: implemented +Archived: 2026-08-04 [English](2026-07-27-tui-chat-channel-module-split.md) | 中文 diff --git a/.agents/notes/archived/architecture/2026-07-28-consolidated-tui-presentation.i18n.yaml b/.agents/notes/archived/architecture/2026-07-28-consolidated-tui-presentation.i18n.yaml new file mode 100644 index 0000000000..135a8442d2 --- /dev/null +++ b/.agents/notes/archived/architecture/2026-07-28-consolidated-tui-presentation.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write .agents/notes/archived/architecture/2026-07-28-consolidated-tui-presentation.md +2026-07-28-consolidated-tui-presentation.md: c772985a11bc61c2bfcbb4422cae219966246163 +2026-07-28-consolidated-tui-presentation.zh.md: c96fd105bc4ff6632017b16a8b7a0e8f448449bd diff --git a/.agents/notes/implemented/architecture/2026-07-28-consolidated-tui-presentation.md b/.agents/notes/archived/architecture/2026-07-28-consolidated-tui-presentation.md similarity index 99% rename from .agents/notes/implemented/architecture/2026-07-28-consolidated-tui-presentation.md rename to .agents/notes/archived/architecture/2026-07-28-consolidated-tui-presentation.md index 8200c8e96c..c772985a11 100644 --- a/.agents/notes/implemented/architecture/2026-07-28-consolidated-tui-presentation.md +++ b/.agents/notes/archived/architecture/2026-07-28-consolidated-tui-presentation.md @@ -1,6 +1,7 @@ # Agent Note: Consolidated TUI presentation and navigation Status: implemented +Archived: 2026-08-04 English | [中文](2026-07-28-consolidated-tui-presentation.zh.md) diff --git a/.agents/notes/implemented/architecture/2026-07-28-consolidated-tui-presentation.zh.md b/.agents/notes/archived/architecture/2026-07-28-consolidated-tui-presentation.zh.md similarity index 99% rename from .agents/notes/implemented/architecture/2026-07-28-consolidated-tui-presentation.zh.md rename to .agents/notes/archived/architecture/2026-07-28-consolidated-tui-presentation.zh.md index 852bd413b2..c96fd105bc 100644 --- a/.agents/notes/implemented/architecture/2026-07-28-consolidated-tui-presentation.zh.md +++ b/.agents/notes/archived/architecture/2026-07-28-consolidated-tui-presentation.zh.md @@ -1,6 +1,7 @@ # Agent Note: 统一的 TUI 呈现与导航 Status: implemented +Archived: 2026-08-04 [English](2026-07-28-consolidated-tui-presentation.md) | 中文 diff --git a/.agents/notes/archived/architecture/2026-07-28-dsh-native-typescript-source-launch.i18n.yaml b/.agents/notes/archived/architecture/2026-07-28-dsh-native-typescript-source-launch.i18n.yaml new file mode 100644 index 0000000000..c0fcdd30f9 --- /dev/null +++ b/.agents/notes/archived/architecture/2026-07-28-dsh-native-typescript-source-launch.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write .agents/notes/archived/architecture/2026-07-28-dsh-native-typescript-source-launch.md +2026-07-28-dsh-native-typescript-source-launch.md: b5e8ed2a18bb0cbb3ab54cf5ed4a427efaa9dfeb +2026-07-28-dsh-native-typescript-source-launch.zh.md: 05a4f92d2d3be553bb9ca363bf08e3ebf8e3f5b8 diff --git a/.agents/notes/implemented/architecture/2026-07-28-dsh-native-typescript-source-launch.md b/.agents/notes/archived/architecture/2026-07-28-dsh-native-typescript-source-launch.md similarity index 99% rename from .agents/notes/implemented/architecture/2026-07-28-dsh-native-typescript-source-launch.md rename to .agents/notes/archived/architecture/2026-07-28-dsh-native-typescript-source-launch.md index 773f831ec2..b5e8ed2a18 100644 --- a/.agents/notes/implemented/architecture/2026-07-28-dsh-native-typescript-source-launch.md +++ b/.agents/notes/archived/architecture/2026-07-28-dsh-native-typescript-source-launch.md @@ -1,6 +1,7 @@ # Agent Note: Native TypeScript source launch for dsh Status: implemented +Archived: 2026-08-07 English | [中文](2026-07-28-dsh-native-typescript-source-launch.zh.md) diff --git a/.agents/notes/implemented/architecture/2026-07-28-dsh-native-typescript-source-launch.zh.md b/.agents/notes/archived/architecture/2026-07-28-dsh-native-typescript-source-launch.zh.md similarity index 63% rename from .agents/notes/implemented/architecture/2026-07-28-dsh-native-typescript-source-launch.zh.md rename to .agents/notes/archived/architecture/2026-07-28-dsh-native-typescript-source-launch.zh.md index 0602aa1ba0..05a4f92d2d 100644 --- a/.agents/notes/implemented/architecture/2026-07-28-dsh-native-typescript-source-launch.zh.md +++ b/.agents/notes/archived/architecture/2026-07-28-dsh-native-typescript-source-launch.zh.md @@ -1,30 +1,31 @@ # Agent Note: dsh 原生 TypeScript 源码启动 Status: implemented +Archived: 2026-08-07 [English](2026-07-28-dsh-native-typescript-source-launch.md) | 中文 -> Node 原生启动向量已被 [dsh 通过 tsx ESM hook 源码启动](2026-07-29-dsh-source-launch-tsx-esm.md) 取代:Node 26.0.0 移除了 `--experimental-transform-types`,本文描述的 paths loader 已删除。Cordis 配置声明门禁(`verify-cordis-config`)、app-boot 的 fail-loud 插件诊断以及 vendor 中的 `import type` 标注仍然有效。 +> Node 原生启动方案已被 [dsh 通过 tsx ESM hook 源码启动](2026-07-29-dsh-source-launch-tsx-esm.md) 取代:Node 26.0.0 移除了 `--experimental-transform-types`,本文描述的 paths loader 已删除。Cordis 配置声明门禁(`verify-cordis-config`)、app-boot 的显式失败插件诊断以及 vendor 中的 `import type` 标注仍然有效。 ## 问题 `dsh` 源码入口原本使用 `tsx` 运行 `apps/cli/src/bin.ts`,TypeScript 转换和根 tsconfig 的 `paths` 解析都由同一个第三方 loader 隐式处理。改由 Node 原生处理 TypeScript 后,Node 不会应用 tsconfig 路径映射;如果改为通过包导出解析,源码启动会混入可能陈旧或不存在的 `lib/` 产物。 -Node 的转换也不执行类型分析。通过普通值 import 导入的类型会保留为运行时 ESM 请求,而 TypeScript 的 `export =` 会变成 CommonJS 赋值,而不是 ESM default export。因此,源码图必须显式使用仅类型导入和原生 ESM 导出;resolve hook 无法修复不兼容的源码语法。 +Node 的转换也不执行类型分析。通过普通值 import 导入的类型会保留为运行时 ESM 请求,而 TypeScript 的 `export =` 会转换成 CommonJS 赋值,而不是 ESM default export。因此,源码图必须显式使用仅类型导入和原生 ESM 导出;resolve hook 无法修复不兼容的源码语法。 -Cordis 配置还引入了另一条解析边界。`cordis.yml` 中的 bare plugin 不经过 TypeScript import 分析,其解析方 manifest 可能漏掉所需依赖。Cordis Loader 会记录插件 import 错误,并留下没有 fiber 的 entry,但不会让启动本身失败;配置中的拼写错误因此可能得到退出码为 0 的残缺应用。 +Cordis 配置还引入了另一条解析边界。`cordis.yml` 中的 bare plugin 不经过 TypeScript import 分析,其解析方的 manifest(元数据清单)可能漏掉所需依赖。Cordis Loader 会记录插件 import 错误,并留下没有 fiber 的 entry,但不会让启动本身失败;配置中的拼写错误因此可能得到退出码为 0 的残缺应用。 ## 决策 `dsh` 的 TUI、Web 和无头源码启动使用 `node --experimental-transform-types`,由 Node 完成 TypeScript 转换,不加载 `tsx` 或 esbuild。`bin/dsh`、根级 `dsh`/TUI/Web demo 以及 Code Mode TUI 都进入同一条 `apps/cli/src/bin.ts` 启动链路。测试与 e2e 启动器保留各自现有策略,构建后的 `lib/bin.js` 继续由普通 Node 运行。 -`scripts/tspath-loader.ts` 只注册一个模块 resolve hook。设置 `TSX_TSCONFIG_PATH` 时,它会使用该路径(相对路径从调用方的 cwd 解析),否则读取根 `tsconfig.json`;`TsconfigPathsResolver` 使用仓库已有的 TypeScript 开发工具沿该配置的 `extends` 链解析,按 tsconfig 规则选择精确或 wildcard `paths` 条目,并将命中的 workspace bare specifier 映射到 `.ts`/`.mts`/`.cts` 源文件或目录 index 文件。代码转换始终只由 Node 负责。该源码专用 loader 不属于构建后的 CLI,`apps/cli` 也不会把 `typescript` 声明为运行时依赖。 +`scripts/tspath-loader.ts` 只注册一个模块解析钩子。设置 `TSX_TSCONFIG_PATH` 时,它会使用该路径(相对路径从调用方的 cwd 解析),否则读取根 `tsconfig.json`;`TsconfigPathsResolver` 使用仓库已有的 TypeScript 开发工具沿该配置的 `extends` 链解析,按 tsconfig 规则选择精确或 wildcard `paths` 条目,并将命中的 workspace bare specifier 映射到 `.ts`/`.mts`/`.cts` 源文件或目录 index 文件。代码转换始终只由 Node 负责。该源码专用 loader 不属于构建后的 CLI,`apps/cli` 也不会把 `typescript` 声明为运行时依赖。 -只有当目标包是最近 package manifest 的自身名称或其已声明的运行时依赖时,源码 import 才会重定向。Cordis Loader 使用配置目录 URL 作为 import parent;此时 resolver 会向上查找声明该插件的 workspace manifest。因此,已交付的 `apps/cli/config/base.cordis.yml` 及其界面覆盖层所需依赖由 `apps/cli/package.json` 持有。未命中 tsconfig paths、引用未声明依赖或不是 bare specifier 的说明符全部交回 Node 默认解析。 +只有当目标包是最近一层包 manifest 的自身名称或该 manifest 已声明的运行时依赖时,源码 import 才会重定向。Cordis Loader 使用配置目录 URL 作为 import parent;此时 resolver 会向上查找声明该插件的 workspace manifest。因此,已交付的 `apps/cli/config/base.cordis.yml` 及其界面覆盖层所需依赖由 `apps/cli/package.json` 持有。未命中 tsconfig paths、引用未声明依赖或不是 bare specifier 的说明符全部交回 Node 默认解析。 `verify-cordis-config` 对该解析方 manifest 执行单向完整性检查:配置中的每个 bare plugin package 都必须出现在对应 manifest 的 `dependencies` 中,manifest 可以包含该配置未引用的额外依赖。根 `AGENTS.md` 将同步更新配置和依赖定为常驻规则。 -Loader 完成结算后,共享的 `dsh-app-boot` 会检查每个已启用但没有 fiber 的 entry,并以 `plugin(s) failed to load: ...; Cordis startup failed because these plugin(s) could not be resolved` 拒绝启动,同时列出全部加载失败的插件。该诊断位于应用层,不改变 vendor 中 Loader 的启动行为。 +Loader 完全停稳后,共享的 `dsh-app-boot` 会检查每个已启用但没有 fiber 的 entry,并拒绝启动,报错为 `plugin(s) failed to load: ...; Cordis startup failed because these plugin(s) could not be resolved`,同时列出全部加载失败的插件。该诊断位于应用层,不改变 vendor 中 Loader 的启动行为。 Node-compatible TypeScript 是这项源码启动契约的一部分。vendor 中的 Cordis、Loader、Include、HMR(热模块替换)和 Schemastery 使用 `import type` 标记会被擦除的导入。Schemastery 使用原生 ESM default export 并声明 `type: module`;其 `.mjs` 和 `.cjs` 构建产物分别保留现有的 ESM default export 行为和 `require()` 返回可调用值的行为。这些差异记录在 `vendor/README.md` 中;没有为 vendor 中的框架新增运行时行为。 @@ -32,7 +33,7 @@ Node-compatible TypeScript 是这项源码启动契约的一部分。vendor 中 **继续使用 `tsx`。** 不采用,因为 `tsx`/esbuild 会继续负责 TypeScript 转换,本启动链路无法因此证明 Node 原生转换可用。 -**让源码入口通过包导出加载构建后的 `lib/`。** 不采用,因为这会混合 source plane 与 artifact plane;零构建开发启动可能读取陈旧产物或直接失败。 +**让源码入口通过包导出加载构建后的 `lib/`。** 不采用,因为这会混合 source plane 与 artifact plane;无需预先构建的开发启动可能读取陈旧产物或直接失败。 **无条件应用根 tsconfig `paths`。** 不采用,因为这会让未声明的跨包 import 和 Cordis 插件继续成功解析,从而掩盖 manifest 与实际运行图之间的不一致。 diff --git a/.agents/notes/archived/bug-fix/2026-07-23-tui-generic-card-markdown.i18n.yaml b/.agents/notes/archived/bug-fix/2026-07-23-tui-generic-card-markdown.i18n.yaml new file mode 100644 index 0000000000..05d62eea95 --- /dev/null +++ b/.agents/notes/archived/bug-fix/2026-07-23-tui-generic-card-markdown.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write .agents/notes/archived/bug-fix/2026-07-23-tui-generic-card-markdown.md +2026-07-23-tui-generic-card-markdown.md: 5c092c4d5ffbc566074f9b280d3fbc207d645ec7 +2026-07-23-tui-generic-card-markdown.zh.md: 93e6388c64e69d9028822ce65f9eda368ed26e7d diff --git a/.agents/notes/implemented/bug-fix/2026-07-23-tui-generic-card-markdown.md b/.agents/notes/archived/bug-fix/2026-07-23-tui-generic-card-markdown.md similarity index 98% rename from .agents/notes/implemented/bug-fix/2026-07-23-tui-generic-card-markdown.md rename to .agents/notes/archived/bug-fix/2026-07-23-tui-generic-card-markdown.md index 494ba58048..5c092c4d5f 100644 --- a/.agents/notes/implemented/bug-fix/2026-07-23-tui-generic-card-markdown.md +++ b/.agents/notes/archived/bug-fix/2026-07-23-tui-generic-card-markdown.md @@ -1,6 +1,7 @@ # Agent Note: TUI generic-card Markdown rendering Status: implemented +Archived: 2026-08-04 English | [中文](2026-07-23-tui-generic-card-markdown.zh.md) diff --git a/.agents/notes/implemented/bug-fix/2026-07-23-tui-generic-card-markdown.zh.md b/.agents/notes/archived/bug-fix/2026-07-23-tui-generic-card-markdown.zh.md similarity index 98% rename from .agents/notes/implemented/bug-fix/2026-07-23-tui-generic-card-markdown.zh.md rename to .agents/notes/archived/bug-fix/2026-07-23-tui-generic-card-markdown.zh.md index 214edd00f5..93e6388c64 100644 --- a/.agents/notes/implemented/bug-fix/2026-07-23-tui-generic-card-markdown.zh.md +++ b/.agents/notes/archived/bug-fix/2026-07-23-tui-generic-card-markdown.zh.md @@ -1,6 +1,7 @@ # Agent Note: TUI 通用卡片的 Markdown 渲染 Status: implemented +Archived: 2026-08-04 [English](2026-07-23-tui-generic-card-markdown.md) | 中文 diff --git a/.agents/notes/archived/bug-fix/2026-07-24-tui-turn-end-stop-reason-notices.i18n.yaml b/.agents/notes/archived/bug-fix/2026-07-24-tui-turn-end-stop-reason-notices.i18n.yaml new file mode 100644 index 0000000000..2ac19448b5 --- /dev/null +++ b/.agents/notes/archived/bug-fix/2026-07-24-tui-turn-end-stop-reason-notices.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write .agents/notes/archived/bug-fix/2026-07-24-tui-turn-end-stop-reason-notices.md +2026-07-24-tui-turn-end-stop-reason-notices.md: 62784ed7cd085ada49b2e0e3d9d809c33a2af917 +2026-07-24-tui-turn-end-stop-reason-notices.zh.md: 162ba4ed44c98bfe00153b7acf69424784f92f5e diff --git a/.agents/notes/implemented/bug-fix/2026-07-24-tui-turn-end-stop-reason-notices.md b/.agents/notes/archived/bug-fix/2026-07-24-tui-turn-end-stop-reason-notices.md similarity index 99% rename from .agents/notes/implemented/bug-fix/2026-07-24-tui-turn-end-stop-reason-notices.md rename to .agents/notes/archived/bug-fix/2026-07-24-tui-turn-end-stop-reason-notices.md index 7c783ce5a3..62784ed7cd 100644 --- a/.agents/notes/implemented/bug-fix/2026-07-24-tui-turn-end-stop-reason-notices.md +++ b/.agents/notes/archived/bug-fix/2026-07-24-tui-turn-end-stop-reason-notices.md @@ -1,6 +1,7 @@ # Agent Note: TUI presents a reason for every turn-end kind Status: implemented +Archived: 2026-08-04 English | [中文](2026-07-24-tui-turn-end-stop-reason-notices.zh.md) diff --git a/.agents/notes/implemented/bug-fix/2026-07-24-tui-turn-end-stop-reason-notices.zh.md b/.agents/notes/archived/bug-fix/2026-07-24-tui-turn-end-stop-reason-notices.zh.md similarity index 99% rename from .agents/notes/implemented/bug-fix/2026-07-24-tui-turn-end-stop-reason-notices.zh.md rename to .agents/notes/archived/bug-fix/2026-07-24-tui-turn-end-stop-reason-notices.zh.md index 4a98352577..162ba4ed44 100644 --- a/.agents/notes/implemented/bug-fix/2026-07-24-tui-turn-end-stop-reason-notices.zh.md +++ b/.agents/notes/archived/bug-fix/2026-07-24-tui-turn-end-stop-reason-notices.zh.md @@ -1,6 +1,7 @@ # Agent Note: TUI 为每种轮次结束 kind 呈现原因 Status: implemented +Archived: 2026-08-04 [English](2026-07-24-tui-turn-end-stop-reason-notices.md) | 中文 diff --git a/.agents/notes/archived/bug-fix/2026-07-27-question-composer-rows-do-not-shrink.i18n.yaml b/.agents/notes/archived/bug-fix/2026-07-27-question-composer-rows-do-not-shrink.i18n.yaml new file mode 100644 index 0000000000..3520cf4974 --- /dev/null +++ b/.agents/notes/archived/bug-fix/2026-07-27-question-composer-rows-do-not-shrink.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write .agents/notes/archived/bug-fix/2026-07-27-question-composer-rows-do-not-shrink.md +2026-07-27-question-composer-rows-do-not-shrink.md: 47e581a23caaeb9368b075fa84a01d2bc945ab46 +2026-07-27-question-composer-rows-do-not-shrink.zh.md: a1b72cab41c51c268540dcec60e85a0edf2fe9bc diff --git a/.agents/notes/implemented/bug-fix/2026-07-27-question-composer-rows-do-not-shrink.md b/.agents/notes/archived/bug-fix/2026-07-27-question-composer-rows-do-not-shrink.md similarity index 99% rename from .agents/notes/implemented/bug-fix/2026-07-27-question-composer-rows-do-not-shrink.md rename to .agents/notes/archived/bug-fix/2026-07-27-question-composer-rows-do-not-shrink.md index 2e0e9b9ca6..47e581a23c 100644 --- a/.agents/notes/implemented/bug-fix/2026-07-27-question-composer-rows-do-not-shrink.md +++ b/.agents/notes/archived/bug-fix/2026-07-27-question-composer-rows-do-not-shrink.md @@ -1,6 +1,7 @@ # Agent Note: Question-composer option rows are scroll content, not the slack absorber Status: implemented +Archived: 2026-08-07 English | [中文](2026-07-27-question-composer-rows-do-not-shrink.zh.md) diff --git a/.agents/notes/implemented/bug-fix/2026-07-27-question-composer-rows-do-not-shrink.zh.md b/.agents/notes/archived/bug-fix/2026-07-27-question-composer-rows-do-not-shrink.zh.md similarity index 76% rename from .agents/notes/implemented/bug-fix/2026-07-27-question-composer-rows-do-not-shrink.zh.md rename to .agents/notes/archived/bug-fix/2026-07-27-question-composer-rows-do-not-shrink.zh.md index 845d9ee883..a1b72cab41 100644 --- a/.agents/notes/implemented/bug-fix/2026-07-27-question-composer-rows-do-not-shrink.zh.md +++ b/.agents/notes/archived/bug-fix/2026-07-27-question-composer-rows-do-not-shrink.zh.md @@ -1,12 +1,13 @@ # Agent Note: 提问 composer 的选项行是滚动内容,而非空间不足时的吸收方 Status: implemented +Archived: 2026-08-07 [English](2026-07-27-question-composer-rows-do-not-shrink.md) | 中文 ## 问题 -提问 composer 的卡片会按视口设上限(`max-height: min(60vh, 520px)`),并让选项列表自行滚动,这样在成批提问时标题和底部操作按钮始终可达。但当 composer 的容器变矮时(窗口较小,或视口偏矮且详情面板处于展开状态),选项行会互相叠在一起,也会叠到问题标题上。 +提问 composer 的卡片会按视口设上限(`max-height: min(60vh, 520px)`),并让选项列表自行滚动,这样在成批提问时头部和底部操作按钮始终可达。但当 composer 的可用区域变矮时(窗口较小,或视口偏矮且详情面板处于展开状态),选项行会互相叠在一起,也会叠到问题标题上。 缺陷不在这个高度上限,而在高度不足时由谁来吸收。`.options` 是一个 `flex-direction: column` 的盒子,其子元素默认取 `flex-shrink: 1`,因此空间不足时首先被压缩的是各个选项行,而不是让滚动容器产生溢出。一行会被压到它的 `min-height: 42px`,而 `.optionCopy` 仍保持文案折行后所需的更大固有高度(带描述的选项会占两行)。由于 `align-items: center`,文案于是以一个比自身更矮的盒子为基准居中,并向上下两个方向画到该行边框盒之外——向上盖住标题,向下盖住下一行。在实际发布的客户端上于 900x440 处实测:文案有 6.5px 落在行盒之外,视口高度降到 380px 时增至 10px,而 `.options` 报告的 `scrollHeight` 等于 `clientHeight`,因此始终不会给出滚动条。 @@ -26,25 +27,25 @@ Status: implemented **把 `align-items: center` 改为 `align-items: flex-start`。** 文案就只会向下生长,因此不再向上盖住标题。但这什么也没修好:被压缩的行依然会溢出到下一行上,而且这一改动会在所有尺寸下(包括常见尺寸)无声改变每个选项行的垂直对齐。 -**移除卡片的 `max-height` 上限,使其永远不会被压缩。** 没有高度不足,就没有分配问题。之所以否决:正是这个上限保证成批提问时标题和底部操作按钮留在屏幕内;移除它会重新引入该上限本就为之存在的失败(composer 所处的容器是一个固定高度、`overflow: hidden` 的会话列,因此不设上限的卡片会连自己的提交按钮一起丢掉)。 +**移除卡片的 `max-height` 上限,使其永远不会被压缩。** 没有高度不足,就没有分配问题。之所以否决:正是这个上限保证成批提问时头部和底部操作按钮留在屏幕内;移除它会重新引入该上限本就为之存在的失败(composer 所处的容器是一个固定高度、`overflow: hidden` 的会话列,因此不设上限的卡片会连自己的提交按钮一起丢掉)。 **把折行文案限制为单行(对 `.description` 设 `white-space: nowrap` 加省略号)。** 行永远不会折行,因此被压缩时也永远不会溢出。否决理由与裁剪相同,此外它还为了修一个窄视口缺陷,而牺牲了空间充裕的宽视口渲染效果。 ## 后果 -- 被压缩的 composer 会滚动其选项列表,而不是让它互相重叠:在 900x380 处,该列表报告 `scrollHeight` 为 200、`clientHeight` 为 114,并给出滚动条;此前两者相等,不给滚动条。 +- 被压缩的 composer 会滚动其选项列表,而不是让选项行互相重叠:在 900x380 处,该列表报告 `scrollHeight` 为 200、`clientHeight` 为 114,并给出滚动条;此前两者相等,不给滚动条。 - 选项行在任何视口尺寸下都保留完整的折行文案。不裁剪、不加省略号,宽视口下的渲染保持不变(该规则仅在 flex 盒子空间不足时才生效)。 -- 由于高度不足不再被行部分吸收,卡片现在更早进入滚动状态。这正是该高度上限想要的行为,也意味着在此前只会无声画错列表的情形下,矮容器现在会显示滚动条。 +- 由于高度不足不再被行部分吸收,卡片现在更早进入滚动状态。这正是该高度上限想要的行为,也意味着在此前只会无声画错列表的情形下,较矮的可用区域现在会显示滚动条。 - 该场景录制的问题,比它主要测试的那次往返所需的长度更长。这个代价是有意付出的:没有折行文案,该布局不变式无法被证伪,而为一条 CSS 规则再加一份 fixture 会更糟。 ## 验证 -Web e2e 的 composer 场景会在三个被压缩的容器高度(900x520/440/380)上,对活动的 composer 断言该运行时不变式:每个选项行的子元素都留在该行的边框盒之内。两道守卫防止该断言空洞地成立——必须至少有一行处于折行状态(这是唯一会溢出的形态),且 `.options` 必须确实处在滚动状态(证明容器确实触及了高度上限)。该场景录制的问题现在带有较长的选项描述,正是为此;没有折行文案,这条断言不可能失败。 +Web e2e 的 composer 场景会在三个受挤压的可用区域高度下(900x520/440/380),在实际运行的 composer 上断言该不变式:每个选项行的子元素都留在该行的边框盒之内。两道守卫防止该断言空洞地成立——必须至少有一行处于折行状态(这是唯一会溢出的形态),且 `.options` 必须确实处在滚动状态(证明可用区域确实受到了高度上限约束)。该场景录制的问题现在带有较长的选项描述,正是为此;没有折行文案,这条断言不可能失败。 在构建产物客户端上双向确认过:撤销 `flex-shrink: 0` 后该场景失败(`scrolls: false`,6.5px 溢出),恢复后通过。一次覆盖 340 种视口尺寸(420-1600 x 320-960)的独立几何遍历,从 86 种尺寸存在文案落在行盒之外,降到 0 种。 -该断言仅在回放模式下执行:录制模式必须走到写入 fixture 那一步,而不是在布局检查处中断。另需注意,composer 以客户端模组包的形式发布,因此单跑 `pnpm run build:web` 不会带上对 `QuestionComposer.module.css` 的改动——必须执行包构建,浏览器测试通道才能看到它。 +该断言仅在回放模式下执行:录制模式必须走到写入 fixture 那一步,而不是在布局检查处中断。另需注意,composer 以客户端模块包的形式发布,因此单跑 `pnpm run build:web` 不会带上对 `QuestionComposer.module.css` 的改动——必须执行包构建,浏览器测试通道才能看到它。 要复现这种空间不足,需要的是矮视口,而不是矮容器。高度上限为 `min(60vh, 520px)`,因此把会话列压到比卡片自身高度更矮,只会裁剪卡片,而不会让它空间不足——各行仍保持完整高度,也不会有任何溢出。凡是在 e2e 场景之外演示或测量该缺陷的手段,都必须改变视口。 -`lib/` 陈旧会让浏览器测试通道对着一个比工作树更旧的客户端做断言,而中途失败的 `pnpm run build` 留下的正是这种状态:失败之前构建的那些包是新的,其余不是。在这种状态下刷新 golden,记录下来的是旧客户端的界面。抓取之前先确认构建以 0 退出;另需注意 `packages/` 下的未跟踪目录同样会被编译——来自另一个分支的遗留物可能以 diff 无法解释的原因让构建失败。 +`lib/` 陈旧会让浏览器测试通道对着一个比工作树更旧的客户端做断言,而中途失败的 `pnpm run build` 留下的正是这种状态:失败之前构建的那些包是新的,其余不是。在这种状态下刷新预期输出,记录下来的是旧客户端的界面。抓取之前先确认构建以 0 退出;另需注意 `packages/` 下的未跟踪目录同样会被编译——来自另一个分支的遗留物可能以 diff 无法解释的原因让构建失败。 diff --git a/.agents/notes/archived/bug-fix/2026-07-27-tool-card-single-row-fields-inline.i18n.yaml b/.agents/notes/archived/bug-fix/2026-07-27-tool-card-single-row-fields-inline.i18n.yaml new file mode 100644 index 0000000000..c7d248fb65 --- /dev/null +++ b/.agents/notes/archived/bug-fix/2026-07-27-tool-card-single-row-fields-inline.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write .agents/notes/archived/bug-fix/2026-07-27-tool-card-single-row-fields-inline.md +2026-07-27-tool-card-single-row-fields-inline.md: 23989e08ac7e32097212bf951461ca1d4213f729 +2026-07-27-tool-card-single-row-fields-inline.zh.md: 8358f7b8dff67c0d3f459d08bf37e3a47f276107 diff --git a/.agents/notes/implemented/bug-fix/2026-07-27-tool-card-single-row-fields-inline.md b/.agents/notes/archived/bug-fix/2026-07-27-tool-card-single-row-fields-inline.md similarity index 99% rename from .agents/notes/implemented/bug-fix/2026-07-27-tool-card-single-row-fields-inline.md rename to .agents/notes/archived/bug-fix/2026-07-27-tool-card-single-row-fields-inline.md index e04110ed74..23989e08ac 100644 --- a/.agents/notes/implemented/bug-fix/2026-07-27-tool-card-single-row-fields-inline.md +++ b/.agents/notes/archived/bug-fix/2026-07-27-tool-card-single-row-fields-inline.md @@ -1,6 +1,7 @@ # Agent Note: Tool-card single-row fields render inline Status: implemented +Archived: 2026-08-04 English | [中文](2026-07-27-tool-card-single-row-fields-inline.zh.md) diff --git a/.agents/notes/implemented/bug-fix/2026-07-27-tool-card-single-row-fields-inline.zh.md b/.agents/notes/archived/bug-fix/2026-07-27-tool-card-single-row-fields-inline.zh.md similarity index 99% rename from .agents/notes/implemented/bug-fix/2026-07-27-tool-card-single-row-fields-inline.zh.md rename to .agents/notes/archived/bug-fix/2026-07-27-tool-card-single-row-fields-inline.zh.md index ac532ec6eb..8358f7b8df 100644 --- a/.agents/notes/implemented/bug-fix/2026-07-27-tool-card-single-row-fields-inline.zh.md +++ b/.agents/notes/archived/bug-fix/2026-07-27-tool-card-single-row-fields-inline.zh.md @@ -1,6 +1,7 @@ # Agent Note: 工具卡片的单行字段以内联方式渲染 Status: implemented +Archived: 2026-08-04 [English](2026-07-27-tool-card-single-row-fields-inline.md) | 中文 diff --git a/.agents/notes/archived/bug-fix/2026-07-27-tui-step-timing-trails-tool-cards.i18n.yaml b/.agents/notes/archived/bug-fix/2026-07-27-tui-step-timing-trails-tool-cards.i18n.yaml new file mode 100644 index 0000000000..e230947bf4 --- /dev/null +++ b/.agents/notes/archived/bug-fix/2026-07-27-tui-step-timing-trails-tool-cards.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write .agents/notes/archived/bug-fix/2026-07-27-tui-step-timing-trails-tool-cards.md +2026-07-27-tui-step-timing-trails-tool-cards.md: 00256fc0f1c0e9469d0dd4e8567fdbc4a48dcaff +2026-07-27-tui-step-timing-trails-tool-cards.zh.md: a566b521923fecb47c721617ac1b4a5fffce7a0f diff --git a/.agents/notes/implemented/bug-fix/2026-07-27-tui-step-timing-trails-tool-cards.md b/.agents/notes/archived/bug-fix/2026-07-27-tui-step-timing-trails-tool-cards.md similarity index 99% rename from .agents/notes/implemented/bug-fix/2026-07-27-tui-step-timing-trails-tool-cards.md rename to .agents/notes/archived/bug-fix/2026-07-27-tui-step-timing-trails-tool-cards.md index 82f46b44d3..00256fc0f1 100644 --- a/.agents/notes/implemented/bug-fix/2026-07-27-tui-step-timing-trails-tool-cards.md +++ b/.agents/notes/archived/bug-fix/2026-07-27-tui-step-timing-trails-tool-cards.md @@ -1,6 +1,7 @@ # Agent Note: TUI step timing trails the step's last message Status: implemented +Archived: 2026-08-04 English | [中文](2026-07-27-tui-step-timing-trails-tool-cards.zh.md) diff --git a/.agents/notes/implemented/bug-fix/2026-07-27-tui-step-timing-trails-tool-cards.zh.md b/.agents/notes/archived/bug-fix/2026-07-27-tui-step-timing-trails-tool-cards.zh.md similarity index 99% rename from .agents/notes/implemented/bug-fix/2026-07-27-tui-step-timing-trails-tool-cards.zh.md rename to .agents/notes/archived/bug-fix/2026-07-27-tui-step-timing-trails-tool-cards.zh.md index 885b232973..a566b52192 100644 --- a/.agents/notes/implemented/bug-fix/2026-07-27-tui-step-timing-trails-tool-cards.zh.md +++ b/.agents/notes/archived/bug-fix/2026-07-27-tui-step-timing-trails-tool-cards.zh.md @@ -1,6 +1,7 @@ # Agent Note: TUI 步骤计时跟在该步骤最后一条消息之后 Status: implemented +Archived: 2026-08-04 [English](2026-07-27-tui-step-timing-trails-tool-cards.md) | 中文 diff --git a/.agents/notes/archived/bug-fix/2026-07-28-web-conversation-polish-sweep.i18n.yaml b/.agents/notes/archived/bug-fix/2026-07-28-web-conversation-polish-sweep.i18n.yaml new file mode 100644 index 0000000000..e77beba866 --- /dev/null +++ b/.agents/notes/archived/bug-fix/2026-07-28-web-conversation-polish-sweep.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write .agents/notes/archived/bug-fix/2026-07-28-web-conversation-polish-sweep.md +2026-07-28-web-conversation-polish-sweep.md: 338b687c041c585c1d490fdad9b8bbcf88fc3912 +2026-07-28-web-conversation-polish-sweep.zh.md: 166662070b67837b9f4755e6457578f74af771ed diff --git a/.agents/notes/implemented/bug-fix/2026-07-28-web-conversation-polish-sweep.md b/.agents/notes/archived/bug-fix/2026-07-28-web-conversation-polish-sweep.md similarity index 99% rename from .agents/notes/implemented/bug-fix/2026-07-28-web-conversation-polish-sweep.md rename to .agents/notes/archived/bug-fix/2026-07-28-web-conversation-polish-sweep.md index cae52217d6..338b687c04 100644 --- a/.agents/notes/implemented/bug-fix/2026-07-28-web-conversation-polish-sweep.md +++ b/.agents/notes/archived/bug-fix/2026-07-28-web-conversation-polish-sweep.md @@ -1,6 +1,7 @@ # Agent Note: Web conversation UI polish sweep Status: implemented +Archived: 2026-08-07 English | [中文](2026-07-28-web-conversation-polish-sweep.zh.md) diff --git a/.agents/notes/implemented/bug-fix/2026-07-28-web-conversation-polish-sweep.zh.md b/.agents/notes/archived/bug-fix/2026-07-28-web-conversation-polish-sweep.zh.md similarity index 80% rename from .agents/notes/implemented/bug-fix/2026-07-28-web-conversation-polish-sweep.zh.md rename to .agents/notes/archived/bug-fix/2026-07-28-web-conversation-polish-sweep.zh.md index d19a5f7593..166662070b 100644 --- a/.agents/notes/implemented/bug-fix/2026-07-28-web-conversation-polish-sweep.zh.md +++ b/.agents/notes/archived/bug-fix/2026-07-28-web-conversation-polish-sweep.zh.md @@ -1,37 +1,38 @@ -# Agent Note: Web conversation UI polish sweep +# Agent Note: Web 对话 UI 视觉优化 Status: implemented +Archived: 2026-08-07 [English](2026-07-28-web-conversation-polish-sweep.md) | 中文 -## Problem +## 问题 一次针对 web GUI 对话界面的设计评审发现了一批视觉呈现缺陷:portal 菜单在重新定位前会先在错误位置绘制一帧(打开时可见跳动);只要某条步骤消息只携带工具调用头,聊天列就会把一次工具运行拆成好几组;工具行摘要打印以工作区为根的绝对路径,占掉行内大部分空间;运行中行的扫光效果用 alpha 遮罩实现,把整行都压暗;hero 区的工作区 chip 会从会话 cwd 里复现已删除工作区的文件夹名;标题栏还在 13px 的标题旁显示一个没人需要的轮次计数。 -## Decision +## 决策 -本次修复全部为纯展示侧改动落地;不会有任何内容进入会话日志。 +本次修复仅改动展示层;不会有任何内容进入会话日志。 - **Portal 菜单先隐藏预渲染,绘制前完成测量。**菜单列表以 `visibility: hidden` 挂载在 (0,0),在 `useLayoutEffect` 中测量,显示时已处于最终位置。菜单与视口保持 12px 间距并支持内部滚动;工作区创建操作固定在不滚动的页脚区。 - **聊天流跳过不渲染任何内容的助手节点。**已定稿的助手节点若其块仅含工具调用头和空白的文本/推理(reasoning)内容,就会从流推导中剔除,于是连续的工具结果合并为一组。被中断的节点始终渲染(它们携带「已停止」标记)。 - **工具行摘要把以工作区为根的路径转为相对路径。**会话 cwd 经由 toolview 插槽契约(`ToolRowOwnerProps.cwd`)逐层传递,`toolRowModel` 从以其开头的摘要中剥去该前缀;工作区之外的路径保持原样。这只影响显示:工具参数与日志均不受影响。 - **运行中的扫光效果改为高光带叠加层。**一条固定宽度的 `::after` 渐变光带横向扫过整行(即 deepsuite 的 ShimmerText 模式),取代先前的 `mask-image` 方案,ToolRow 与 Bash toolview 两处均已替换。 -- **hero 区的工作区 chip 是选择器,而非回显。**没有有效选中项时(冷启动,或列表稳定后工作区被删除),它显示「Choose workspace」占位文案;由 cwd 推导的名称只用于衔接列表的首次加载,待定选择对应的工作区从已就绪的列表中消失时,该陈旧选择会被清除。 +- **hero 区的工作区 chip 是选择器,而非回显。**没有有效选中项时(冷启动,或列表稳定后工作区被删除),它显示「Choose workspace」占位文案;由 cwd 推导的名称只用于衔接列表的首次加载,尚待确认的选择所对应的工作区从已就绪的列表中消失时,该陈旧选择会被清除。 - **统一为 16px 的纵向节奏。**聊天列间距与分组内工具行间距统一为 16px,取代原先「分组内 10px 间距加跨分组负外边距」的做法。 -- **标题栏标题改为 14/20,去掉轮次计数**;StateDot 的进行中状态与轮次尾部采用逐格推进的像素追逐式加载视觉语言;`body` 启用灰度抗锯齿(`-webkit-font-smoothing` 及 Firefox 在 macOS 上的等价设置)。 +- **标题文字改为 14/20,标题栏去掉轮次计数**;StateDot 的进行中状态与轮次尾部采用逐格推进的像素追逐式加载视觉语言;`body` 启用灰度抗锯齿(`-webkit-font-smoothing` 及 Firefox 在 macOS 上的等价设置)。 -## Alternatives considered +## 考虑过的替代方案 - **挂载前根据锚点矩形同步定位菜单。**不予采纳:列表自身尺寸在布局完成前无从得知,向视口内收拢仍然需要布局后测量;对已挂载的隐藏节点做测量正是 React 与 Floating UI 文档记载的模式。 - **在宿主侧过滤空的助手消息。**不予采纳:该节点是真实的模型输出,Trajectory 与回放都必须保留它;只有聊天展示应当跳过它,且按契约 web 层只负责呈现。 -- **在每个工具各自的展示器中做路径相对化。**不予采纳:这种冗余是所有输出路径摘要的工具共有的;在 `toolRowModel` 里做一次仅影响显示的处理即可覆盖全部工具,非聊天消费方仍拿到绝对路径。 +- **在每个工具各自的 presenter 中做路径相对化。**不予采纳:这种冗余是所有输出路径摘要的工具共有的;在 `toolRowModel` 里做一次仅影响显示的处理即可覆盖全部工具,非聊天消费方仍拿到绝对路径。 - **保留基于遮罩的扫光。**不予采纳:遮罩会把包括状态圆点在内的整行内容压暗,其退出过渡还与悬停图标的交叉淡入淡出相互冲突;叠加光带在内容之上合成,完全不触碰内容的 alpha。 - **让 chip 继续显示已删除工作区的名称。**不予采纳:chip 是为*下一个*会话服务的选择器;用户刚删掉某个工作区,还回显它的 cwd,就是在错误呈现当前的选择。 -## Consequences +## 后果 聊天渲染出的流条目数少于快照中的节点数:凡是拿渲染出的块与节点数对账的人,都必须把被跳过的「不渲染任何内容」的助手节点计算在内(chat-view 规格测试固定了这一点)。路径相对化只是针对会话 cwd 的前缀检查,因此会话中途重命名工作区后,摘要在重新推导前会显示绝对路径,这被接受为仅影响显示的陈旧状态。统一的 16px 节奏淘汰了原先更紧凑的 10px 工具运行外观;将来若要更紧凑的布局,应当有意识地重新引入第二个常量。菜单预渲染让每次打开多一次隐藏布局计算,在菜单的尺寸量级下开销可忽略。 -## Testing +## 测试 -`chat-view.spec.tsx` 固定了「不渲染任何内容」节点的分组行为(含被中断节点这一例外);`chat-tool-row.spec.tsx` 固定了工作区内、工作区外以及 cwd 为空时的 cwd 相对化行为;`atoms.spec.tsx` 与 `workspace-picker.spec.tsx` 覆盖菜单与 chip 的各种状态;ui-conversation、ui-primitives 与 ui-workspace 的全量测试套件通过。 +`chat-view.spec.tsx` 锁定了「不渲染任何内容」节点的分组行为(含被中断节点这一例外);`chat-tool-row.spec.tsx` 锁定了工作区内、工作区外以及 cwd 为空时的 cwd 相对化行为;`atoms.spec.tsx` 与 `workspace-picker.spec.tsx` 覆盖菜单与 chip 的各种状态;ui-conversation、ui-primitives 与 ui-workspace 的全量测试套件通过。 diff --git a/.agents/notes/archived/bug-fix/2026-07-30-tui-adapter-registration-race.i18n.yaml b/.agents/notes/archived/bug-fix/2026-07-30-tui-adapter-registration-race.i18n.yaml new file mode 100644 index 0000000000..025b6610a9 --- /dev/null +++ b/.agents/notes/archived/bug-fix/2026-07-30-tui-adapter-registration-race.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write .agents/notes/archived/bug-fix/2026-07-30-tui-adapter-registration-race.md +2026-07-30-tui-adapter-registration-race.md: 051f5e6af5d7fd6c0096c84af064d065dd6f8983 +2026-07-30-tui-adapter-registration-race.zh.md: 1706acb1d23bab987333a7ac0b5e2695226c1af5 diff --git a/.agents/notes/implemented/bug-fix/2026-07-30-tui-adapter-registration-race.md b/.agents/notes/archived/bug-fix/2026-07-30-tui-adapter-registration-race.md similarity index 99% rename from .agents/notes/implemented/bug-fix/2026-07-30-tui-adapter-registration-race.md rename to .agents/notes/archived/bug-fix/2026-07-30-tui-adapter-registration-race.md index fd08e7b613..051f5e6af5 100644 --- a/.agents/notes/implemented/bug-fix/2026-07-30-tui-adapter-registration-race.md +++ b/.agents/notes/archived/bug-fix/2026-07-30-tui-adapter-registration-race.md @@ -1,6 +1,7 @@ # Agent Note: TUI model-context resolution defers on the adapter-registration race Status: implemented +Archived: 2026-08-04 English | [中文](2026-07-30-tui-adapter-registration-race.zh.md) diff --git a/.agents/notes/implemented/bug-fix/2026-07-30-tui-adapter-registration-race.zh.md b/.agents/notes/archived/bug-fix/2026-07-30-tui-adapter-registration-race.zh.md similarity index 99% rename from .agents/notes/implemented/bug-fix/2026-07-30-tui-adapter-registration-race.zh.md rename to .agents/notes/archived/bug-fix/2026-07-30-tui-adapter-registration-race.zh.md index 0c6bba4bbc..1706acb1d2 100644 --- a/.agents/notes/implemented/bug-fix/2026-07-30-tui-adapter-registration-race.zh.md +++ b/.agents/notes/archived/bug-fix/2026-07-30-tui-adapter-registration-race.zh.md @@ -1,6 +1,7 @@ # Agent Note: TUI 模型上下文解析在适配器注册竞争时延后重试 Status: implemented +Archived: 2026-08-04 [English](2026-07-30-tui-adapter-registration-race.md) | 中文 diff --git a/.agents/notes/archived/bug-fix/2026-07-30-web-details-default-closed.i18n.yaml b/.agents/notes/archived/bug-fix/2026-07-30-web-details-default-closed.i18n.yaml new file mode 100644 index 0000000000..286ed2a62e --- /dev/null +++ b/.agents/notes/archived/bug-fix/2026-07-30-web-details-default-closed.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write .agents/notes/archived/bug-fix/2026-07-30-web-details-default-closed.md +2026-07-30-web-details-default-closed.md: e4271917b998c9a916d8c67b30627022587547b8 +2026-07-30-web-details-default-closed.zh.md: 3b9432067c944ea604e039ee1b305a927a1c206e diff --git a/.agents/notes/implemented/bug-fix/2026-07-30-web-details-default-closed.md b/.agents/notes/archived/bug-fix/2026-07-30-web-details-default-closed.md similarity index 99% rename from .agents/notes/implemented/bug-fix/2026-07-30-web-details-default-closed.md rename to .agents/notes/archived/bug-fix/2026-07-30-web-details-default-closed.md index 658b6fc2c1..e4271917b9 100644 --- a/.agents/notes/implemented/bug-fix/2026-07-30-web-details-default-closed.md +++ b/.agents/notes/archived/bug-fix/2026-07-30-web-details-default-closed.md @@ -1,6 +1,7 @@ # Agent Note: Web details default closed Status: implemented +Archived: 2026-08-07 English | [中文](2026-07-30-web-details-default-closed.zh.md) diff --git a/.agents/notes/implemented/bug-fix/2026-07-30-web-details-default-closed.zh.md b/.agents/notes/archived/bug-fix/2026-07-30-web-details-default-closed.zh.md similarity index 99% rename from .agents/notes/implemented/bug-fix/2026-07-30-web-details-default-closed.zh.md rename to .agents/notes/archived/bug-fix/2026-07-30-web-details-default-closed.zh.md index 5a1d0e4713..3b9432067c 100644 --- a/.agents/notes/implemented/bug-fix/2026-07-30-web-details-default-closed.zh.md +++ b/.agents/notes/archived/bug-fix/2026-07-30-web-details-default-closed.zh.md @@ -1,6 +1,7 @@ # Agent Note: Web 详情栏默认关闭 Status: implemented +Archived: 2026-08-07 [English](2026-07-30-web-details-default-closed.md) | 中文 diff --git a/.agents/notes/archived/bug-fix/2026-07-31-hero-visible-while-blank-session-opens.i18n.yaml b/.agents/notes/archived/bug-fix/2026-07-31-hero-visible-while-blank-session-opens.i18n.yaml new file mode 100644 index 0000000000..0cc1847c1a --- /dev/null +++ b/.agents/notes/archived/bug-fix/2026-07-31-hero-visible-while-blank-session-opens.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write .agents/notes/archived/bug-fix/2026-07-31-hero-visible-while-blank-session-opens.md +2026-07-31-hero-visible-while-blank-session-opens.md: 1b1f35d82731675978585d718e4ef837f0c78aa5 +2026-07-31-hero-visible-while-blank-session-opens.zh.md: 91c1a372ebc6341632820450d9e54d58c9d36916 diff --git a/.agents/notes/implemented/bug-fix/2026-07-31-hero-visible-while-blank-session-opens.md b/.agents/notes/archived/bug-fix/2026-07-31-hero-visible-while-blank-session-opens.md similarity index 80% rename from .agents/notes/implemented/bug-fix/2026-07-31-hero-visible-while-blank-session-opens.md rename to .agents/notes/archived/bug-fix/2026-07-31-hero-visible-while-blank-session-opens.md index b39963beff..1b1f35d827 100644 --- a/.agents/notes/implemented/bug-fix/2026-07-31-hero-visible-while-blank-session-opens.md +++ b/.agents/notes/archived/bug-fix/2026-07-31-hero-visible-while-blank-session-opens.md @@ -1,6 +1,7 @@ # Agent Note: Hero stays visible while a blank session opens Status: implemented +Archived: 2026-08-07 English | [中文](2026-07-31-hero-visible-while-blank-session-opens.zh.md) @@ -24,12 +25,10 @@ The summary flag and the snapshot's own `blank` are distinct sources: the snapsh ## Deferred -The no-session→session tree relocation in `ConversationRoot` (the hero/composer subtree moves into the `conversation.session` outlet) still rebuilds the composer DOM on the same transition; removing it means moving `conversation.session` to `session-maybe` scope, a slot-contract change that needs its own proposal. - Object-layer reference churn found while diagnosing this — no-op projections minting fresh snapshots, the create path projecting twice, `select()` using `notifyNow` from async continuations — is real but independent of the visible flash. ## Consequences Startup auto-selection renders the hero immediately and keeps the composer seat and header visible through the history round-trip, so launching into a recent workspace no longer looks like a page reload. Sessions whose summary does not prove them blank keep the previous settling behavior, so the guard still covers the case it was written for. Skeleton tests pin all three summary shapes: a row reporting `blank: false` settles, an absent row settles, and a summary-proven blank session opening under `loading` renders hero chrome with a live textarea. -The assembled coverage is `apps/web/tests/startup-auto-selection.e2e.ts` (keyless web browser lane): it registers a workspace, holds the `session.history` response open at the browser's network boundary, and asserts the visible frame while the auto-selected open is in flight — hero phase, hero title, painted composer — plus a recorded phase timeline of exactly `['hero']` for the whole load. Holding the round-trip is what makes it a regression test rather than a race: against a loopback host the open settles too fast to sample, and with the exemption reverted the held window is precisely when the root reports `settling`. +The assembled coverage is `apps/web/tests/startup-auto-selection.e2e.ts` (keyless web browser lane). Its first Workspace connection asserts that the Hero root, Workspace chip, scroll body, composer seat, and textarea remain the same DOM nodes when the blank Session appears. It then holds the `session.history` response open at the browser's network boundary and asserts the visible frame while the auto-selected open is in flight — hero phase, hero title, painted composer — plus a recorded phase timeline of exactly `['hero']` for the whole load. Holding the round-trip is what makes the second case a regression test rather than a race: against a loopback host the open settles too fast to sample, and with the exemption reverted the held window is precisely when the root reports `settling`. diff --git a/.agents/notes/implemented/bug-fix/2026-07-31-hero-visible-while-blank-session-opens.zh.md b/.agents/notes/archived/bug-fix/2026-07-31-hero-visible-while-blank-session-opens.zh.md similarity index 80% rename from .agents/notes/implemented/bug-fix/2026-07-31-hero-visible-while-blank-session-opens.zh.md rename to .agents/notes/archived/bug-fix/2026-07-31-hero-visible-while-blank-session-opens.zh.md index b451d7c00e..91c1a372eb 100644 --- a/.agents/notes/implemented/bug-fix/2026-07-31-hero-visible-while-blank-session-opens.zh.md +++ b/.agents/notes/archived/bug-fix/2026-07-31-hero-visible-while-blank-session-opens.zh.md @@ -1,6 +1,7 @@ # Agent Note: 空白会话打开期间保持 hero 可见 Status: implemented +Archived: 2026-08-07 [English](2026-07-31-hero-visible-while-blank-session-opens.md) | 中文 @@ -24,12 +25,10 @@ Status: implemented ## 推迟事项 -`ConversationRoot` 中"无会话→有会话"的树位置迁移(hero/composer 子树移入 `conversation.session` 出口)仍会在同一次转换中重建 composer 的 DOM;消除它意味着把 `conversation.session` 移到 `session-maybe` 作用域,这是一次插槽契约变更,需要单独立项。 - 诊断期间发现的对象层引用抖动——空操作投影铸造出新的快照、创建路径重复投影一次、`select()` 在异步续体中使用 `notifyNow`——确实存在,但与这次可见闪烁相互独立。 ## 影响 启动自动选择会立即渲染 hero,并在整个历史往返期间保持 composer 座位与 header 可见,因此启动进入最近工作区不再像页面重载。摘要未证明为空白的会话保持原有的 settling 行为,这道防护仍覆盖它当初针对的场景。骨架测试固定了摘要的三种形态:报告 `blank: false` 的行进入 settling;根本没有该行同样进入 settling;摘要已证明为空白的会话在 `loading` 期间渲染 hero 外壳与可用的文本框。 -组装级覆盖是 `apps/web/tests/startup-auto-selection.e2e.ts`(无密钥的 Web 浏览器泳道):它注册一个工作区,在浏览器网络边界上扣住 `session.history` 的响应,并在自动选择的打开仍在飞行途中断言可见画面——hero 阶段、hero 标题、已绘制的 composer——外加整次加载记录到的阶段时间线恰好为 `['hero']`。扣住这次往返正是它成为回归测试而非竞态的原因:对着回环主机,打开会快到无从采样;而一旦回退这条豁免,被扣住的这段窗口恰恰就是根节点报告 `settling` 的时刻。 +组装级覆盖是 `apps/web/tests/startup-auto-selection.e2e.ts`(无密钥的 Web 浏览器泳道)。首次连接 Workspace 时,它断言 blank Session 出现前后 Hero root、Workspace chip、滚动主体、composer seat 与 textarea 都是同一 DOM 节点。随后它在浏览器网络边界上扣住 `session.history` 的响应,并在自动选择的打开仍在飞行途中断言可见画面——hero 阶段、hero 标题、已绘制的 composer——外加整次加载记录到的阶段时间线恰好为 `['hero']`。扣住这次往返正是第二个用例成为回归测试而非竞态的原因:对着回环主机,打开会快到无从采样;而一旦回退这条豁免,被扣住的这段窗口恰恰就是根节点报告 `settling` 的时刻。 diff --git a/.agents/notes/archived/bug-fix/2026-07-31-tui-diff-context-line-accounting.i18n.yaml b/.agents/notes/archived/bug-fix/2026-07-31-tui-diff-context-line-accounting.i18n.yaml new file mode 100644 index 0000000000..b3414c0f98 --- /dev/null +++ b/.agents/notes/archived/bug-fix/2026-07-31-tui-diff-context-line-accounting.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write .agents/notes/archived/bug-fix/2026-07-31-tui-diff-context-line-accounting.md +2026-07-31-tui-diff-context-line-accounting.md: 5172069c7def39808b018030b630ea4313bd7038 +2026-07-31-tui-diff-context-line-accounting.zh.md: b9a9863f05d1c5b829facdc850eccc7a321a76ab diff --git a/.agents/notes/implemented/bug-fix/2026-07-31-tui-diff-context-line-accounting.md b/.agents/notes/archived/bug-fix/2026-07-31-tui-diff-context-line-accounting.md similarity index 99% rename from .agents/notes/implemented/bug-fix/2026-07-31-tui-diff-context-line-accounting.md rename to .agents/notes/archived/bug-fix/2026-07-31-tui-diff-context-line-accounting.md index d465568d5f..5172069c7d 100644 --- a/.agents/notes/implemented/bug-fix/2026-07-31-tui-diff-context-line-accounting.md +++ b/.agents/notes/archived/bug-fix/2026-07-31-tui-diff-context-line-accounting.md @@ -1,6 +1,7 @@ # Agent Note: TUI diff context lines stay neutral Status: implemented +Archived: 2026-08-04 English | [中文](2026-07-31-tui-diff-context-line-accounting.zh.md) diff --git a/.agents/notes/implemented/bug-fix/2026-07-31-tui-diff-context-line-accounting.zh.md b/.agents/notes/archived/bug-fix/2026-07-31-tui-diff-context-line-accounting.zh.md similarity index 99% rename from .agents/notes/implemented/bug-fix/2026-07-31-tui-diff-context-line-accounting.zh.md rename to .agents/notes/archived/bug-fix/2026-07-31-tui-diff-context-line-accounting.zh.md index dd1a3eb1ac..b9a9863f05 100644 --- a/.agents/notes/implemented/bug-fix/2026-07-31-tui-diff-context-line-accounting.zh.md +++ b/.agents/notes/archived/bug-fix/2026-07-31-tui-diff-context-line-accounting.zh.md @@ -1,6 +1,7 @@ # Agent Note: TUI diff 上下文行保持中性 Status: implemented +Archived: 2026-08-04 [English](2026-07-31-tui-diff-context-line-accounting.md) | 中文 diff --git a/.agents/notes/archived/bug-fix/2026-08-03-tui-long-session-render-costs.i18n.yaml b/.agents/notes/archived/bug-fix/2026-08-03-tui-long-session-render-costs.i18n.yaml new file mode 100644 index 0000000000..f5b795742e --- /dev/null +++ b/.agents/notes/archived/bug-fix/2026-08-03-tui-long-session-render-costs.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write .agents/notes/archived/bug-fix/2026-08-03-tui-long-session-render-costs.md +2026-08-03-tui-long-session-render-costs.md: 2f6e909aa280cf72cd15a635a64c80aee6cd0cf1 +2026-08-03-tui-long-session-render-costs.zh.md: eeff7bc33df1f6e69d749c590953a42675a4d688 diff --git a/.agents/notes/implemented/bug-fix/2026-08-03-tui-long-session-render-costs.md b/.agents/notes/archived/bug-fix/2026-08-03-tui-long-session-render-costs.md similarity index 99% rename from .agents/notes/implemented/bug-fix/2026-08-03-tui-long-session-render-costs.md rename to .agents/notes/archived/bug-fix/2026-08-03-tui-long-session-render-costs.md index c5b03960b6..2f6e909aa2 100644 --- a/.agents/notes/implemented/bug-fix/2026-08-03-tui-long-session-render-costs.md +++ b/.agents/notes/archived/bug-fix/2026-08-03-tui-long-session-render-costs.md @@ -1,6 +1,7 @@ # Agent Note: TUI long-session render costs — shared step-timing scan and card line caches Status: implemented +Archived: 2026-08-04 English | [中文](2026-08-03-tui-long-session-render-costs.zh.md) diff --git a/.agents/notes/implemented/bug-fix/2026-08-03-tui-long-session-render-costs.zh.md b/.agents/notes/archived/bug-fix/2026-08-03-tui-long-session-render-costs.zh.md similarity index 99% rename from .agents/notes/implemented/bug-fix/2026-08-03-tui-long-session-render-costs.zh.md rename to .agents/notes/archived/bug-fix/2026-08-03-tui-long-session-render-costs.zh.md index b41c5a8c54..eeff7bc33d 100644 --- a/.agents/notes/implemented/bug-fix/2026-08-03-tui-long-session-render-costs.zh.md +++ b/.agents/notes/archived/bug-fix/2026-08-03-tui-long-session-render-costs.zh.md @@ -1,6 +1,7 @@ # Agent Note: TUI 长会话渲染开销:共享步骤耗时扫描与卡片行缓存 Status: implemented +Archived: 2026-08-04 [English](2026-08-03-tui-long-session-render-costs.md) | 中文 diff --git a/.agents/notes/archived/feature/2026-07-17-dedicated-full-screen-tui-front-door.i18n.yaml b/.agents/notes/archived/feature/2026-07-17-dedicated-full-screen-tui-front-door.i18n.yaml new file mode 100644 index 0000000000..c44bf6e177 --- /dev/null +++ b/.agents/notes/archived/feature/2026-07-17-dedicated-full-screen-tui-front-door.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write .agents/notes/archived/feature/2026-07-17-dedicated-full-screen-tui-front-door.md +2026-07-17-dedicated-full-screen-tui-front-door.md: 1a04e738a2810abdb4bac81aebe9b23db404879e +2026-07-17-dedicated-full-screen-tui-front-door.zh.md: 75fc3d47aa258fa6db767b1049194663148d1afa diff --git a/.agents/notes/implemented/feature/2026-07-17-dedicated-full-screen-tui-front-door.md b/.agents/notes/archived/feature/2026-07-17-dedicated-full-screen-tui-front-door.md similarity index 79% rename from .agents/notes/implemented/feature/2026-07-17-dedicated-full-screen-tui-front-door.md rename to .agents/notes/archived/feature/2026-07-17-dedicated-full-screen-tui-front-door.md index c011a0284e..1a04e738a2 100644 --- a/.agents/notes/implemented/feature/2026-07-17-dedicated-full-screen-tui-front-door.md +++ b/.agents/notes/archived/feature/2026-07-17-dedicated-full-screen-tui-front-door.md @@ -1,11 +1,14 @@ # Agent Note: Dedicated full-screen TUI front door Status: implemented +Archived: 2026-08-04 English | [中文](2026-07-17-dedicated-full-screen-tui-front-door.zh.md) ## Problem +The reusable TUI package remains implemented, but [`dsh` no longer ships it as an application entrypoint](../simplification/2026-08-03-explicit-config-dsh-entrypoint.md). This note continues to own the package boundary and terminal behavior; the later note owns product composition. + At the time this front door was introduced, the line-oriented agent handled pipes and ordinary terminals, but a full-screen coding interface had to own raw input, differential screen drawing, cursor state, overlays, and terminal restoration. Combining those contracts in one UI plugin would have coupled a stream-oriented path to a TTY-only lifecycle. The later [redundant-agent removal](../simplification/2026-07-20-remove-stdio-and-echo-agents.md) removes that line agent; this Note continues to own the TUI design. The interactive channel must remain a Cordis plugin over the same agent, session, tool, and user-interaction services as every other front door. It needs to resume durable history, follow compaction replacements, display tool-owned presentation, and restore the terminal on startup failure and disposal. A standalone chat application or a second agent composition would duplicate behavior outside the plugin graph. @@ -14,9 +17,9 @@ The interactive channel must remain a Cordis plugin over the same agent, session DeepSeek Harness ships [`@deepseek-ai/dsh-tui`](../../../../packages/ui/tui/README.md) as a dedicated Cordis plugin. It owns terminal input and presentation only; agent lifecycle, session persistence, tool execution, and the model-facing question tool remain separate composition entries. The plugin requires both stdin and stdout to be TTYs and fails instead of silently changing to line-oriented behavior. -There is one terminal front door. `@deepseek-ai/dsh-tui` mounts before the configured agent, and `apps/cli/config/tui.cordis.yml` — an overlay over the shared `base.cordis.yml` — owns the interactive coding composition. Non-interactive tasks use the official headless surface; ACP remains a separate automation protocol and owns the supported Code Mode demo. +The package is a terminal front door, not a complete application. A host mounts `@deepseek-ai/dsh-tui` before its configured agent and composes the backends, tools, and policies around it. The product CLI currently ships no terminal composition; non-interactive tasks use headless mode, Web owns the installed human surface, and ACP remains a separate automation protocol. -The selected front door receives the exact generated or resumed `SessionId` used by the pre-created agent. It mounts before the agent composition, waits for the matching root agent, and enters full-screen mode only after that agent exists. A matching `agent-loop/config-start-failed` event is therefore reported before screen takeover and exits with status 1. +The host supplies the exact generated or resumed `SessionId` used by its pre-created agent. The TUI waits for the matching root agent and enters full-screen mode only after that agent exists. A matching `agent-loop/config-start-failed` event is therefore reported before screen takeover. ### Session projection and interaction @@ -34,18 +37,18 @@ The built-in palette uses standard 16-color ANSI foregrounds and SGR attributes, ## Verification -The implemented [TUI terminal-state snapshot Agent Note](../testing/2026-07-18-tui-terminal-state-snapshots.md) owns the four-layer verification contract: direct behavior tests, transient semantic terminal snapshots, recorded JSONL journeys through production tools, and Loader/PTY smoke tests. The package README owns configuration, commands, model-visible effects, and current limitations. +The implemented [TUI terminal-state snapshot Agent Note](../testing/2026-07-18-tui-terminal-state-snapshots.md) owns the package verification contract: direct behavior tests and semantic terminal snapshots. A deployment shipping this front door owns its assembled transcript and process/PTY acceptance. The package README owns configuration, commands, model-visible effects, and current limitations. ## Alternatives considered - **Keep readline and full-screen modes inside `@deepseek-ai/dsh-stdio`** — rejected because line-oriented output and differential TTY rendering have different dependencies, input rules, logging ownership, and teardown obligations. Separate packages keep the pipe-safe contract small and explicit. -- **Let the TUI plugin silently downgrade when either stream is not a TTY** — rejected because a fallback hides deployment mistakes and changes interaction semantics. The app bundle may select a front door with `auto`; an explicitly mounted TUI fails loud. -- **Keep TUI wiring and tests under the readline `repl-agent` leaf** — rejected because one leaf would represent two distinct front doors and break symmetry with `acp-agent`. A dedicated `tui-agent` leaf owns TUI overlays and tests while reusing the repl-agent backend composition. +- **Let the TUI plugin silently downgrade when either stream is not a TTY** — rejected because a fallback hides deployment mistakes and changes interaction semantics. A host may select a different front door; an explicitly mounted TUI fails loud. +- **Keep TUI wiring and tests under the readline `repl-agent` leaf** — rejected at the time because one leaf would represent two distinct front doors. The later product-entrypoint removal deleted that application wiring while retaining the package boundary. - **Mutate `agent.options` when `/model` runs** — rejected because creation options do not provide an atomic boundary between asynchronous prompt assembly and request routing. Agent-scoped waterfalls preserve immutable creation input and snapshot the selected pair for each step. ## Consequences -- Interactive terminal work has a stateful Markdown, card, plan, and question interface with no second terminal protocol to keep aligned. +- Deployments that mount the TUI gain a stateful Markdown, card, plan, and question interface with no second terminal protocol to keep aligned. - The TUI carries a pi-tui dependency and a strict TTY requirement; non-TTY deployments use the Headless app or a structured protocol. - Session projection makes resume consistent with the durable conversation, but one configured session owns the transcript and editor. - Tool packages extend terminal cards through their existing presentation methods without adding tool-specific branches to the TUI. diff --git a/.agents/notes/implemented/feature/2026-07-17-dedicated-full-screen-tui-front-door.zh.md b/.agents/notes/archived/feature/2026-07-17-dedicated-full-screen-tui-front-door.zh.md similarity index 81% rename from .agents/notes/implemented/feature/2026-07-17-dedicated-full-screen-tui-front-door.zh.md rename to .agents/notes/archived/feature/2026-07-17-dedicated-full-screen-tui-front-door.zh.md index 5aea4ac0c5..75fc3d47aa 100644 --- a/.agents/notes/implemented/feature/2026-07-17-dedicated-full-screen-tui-front-door.zh.md +++ b/.agents/notes/archived/feature/2026-07-17-dedicated-full-screen-tui-front-door.zh.md @@ -1,11 +1,14 @@ # Agent Note: 独立的全屏 TUI 入口 Status: implemented +Archived: 2026-08-04 [English](2026-07-17-dedicated-full-screen-tui-front-door.md) | 中文 ## 问题 +可复用的 TUI 包(package)仍然保留实现,但 [`dsh` 不再将其作为应用入口交付](../simplification/2026-08-03-explicit-config-dsh-entrypoint.md)。本记录继续负责包边界和终端行为;后续记录负责产品组合。 + 在本入口引入时,面向行的 agent 负责 pipe 与普通终端,但全屏 coding 界面必须负责原始输入、差分绘制、光标状态、浮层和终端恢复。把这两类契约合并到一个 UI 插件中,会迫使面向 stream 的路径依赖仅适用于 TTY 的生命周期。后续的[移除重复 agent 决策](../simplification/2026-07-20-remove-stdio-and-echo-agents.md)移除了这个面向行 agent;本 Note 继续负责 TUI 设计。 交互通道必须继续作为 Cordis 插件,使用与其他入口相同的 agent(智能体)、会话、工具和用户交互服务。它需要恢复持久历史、跟随压缩替换、显示工具自有的呈现内容,并在启动失败和资源释放时恢复终端。独立聊天应用或第二套 agent 组合会在插件图之外重复实现这些行为。 @@ -14,9 +17,9 @@ Status: implemented DeepSeek Harness 将 [`@deepseek-ai/dsh-tui`](../../../../packages/ui/tui/README.md) 作为独立的 Cordis 插件交付。该插件只负责终端输入与呈现;agent 生命周期、会话持久化、工具执行以及模型可见的提问工具仍由不同组合项负责。插件要求 stdin 和 stdout 均为 TTY;条件不满足时会失败,不会静默切换为逐行输出。 -只有一个终端入口。`@deepseek-ai/dsh-tui` 在已配置 agent 之前挂载,而 `apps/cli/config/tui.cordis.yml`——叠加在共享 `base.cordis.yml` 之上的 overlay——拥有交互式 coding 组装。非交互任务使用官方 headless 界面;ACP 仍是独立的自动化协议,并拥有受支持的 Code Mode demo。 +该包是终端入口,而不是完整应用。宿主在已配置 agent 之前挂载 `@deepseek-ai/dsh-tui`,并围绕它组合后端、工具和策略。产品 CLI 目前不交付终端组合;非交互任务使用 headless 模式,Web 是已安装产品中面向人的界面,而 ACP 仍是独立的自动化协议。 -所选入口接收预创建 agent 使用的同一个新建或恢复 `SessionId`。入口先于 agent 组合挂载,等待相符的根 agent 出现,然后才进入全屏模式。因此,相符的 `agent-loop/config-start-failed` 事件会在接管屏幕前报告,并以状态码 1 退出。 +宿主提供其预创建 agent 使用的同一个新建或恢复 `SessionId`。TUI 等待相符的根 agent 出现,然后才进入全屏模式。因此,相符的 `agent-loop/config-start-failed` 事件会在接管屏幕前报告。 ### 会话投影与交互 @@ -34,18 +37,18 @@ agent 空闲时,编辑器输入调用 `agent.send()`;轮次运行中则调 ## 验证 -已实现的 [TUI 终端状态快照 Agent Note](../testing/2026-07-18-tui-terminal-state-snapshots.md) 规定四层验证契约:直接行为测试、瞬态语义终端快照、通过生产工具执行的已录制 JSONL 流程,以及 Loader/PTY 冒烟测试。包(package)README 负责记录配置、命令、模型可见效果和当前限制。 +已实现的 [TUI 终端状态快照 Agent Note](../testing/2026-07-18-tui-terminal-state-snapshots.md) 规定包验证契约:直接行为测试和语义终端快照。交付该入口的部署负责其组装后 transcript 和进程/PTY 验收。包 README 负责记录配置、命令、模型可见效果和当前限制。 ## 曾考虑的替代方案 - **把 readline 与全屏模式都保留在 `@deepseek-ai/dsh-stdio` 中**:不予采纳,因为逐行输出和差分 TTY 渲染具有不同的依赖、输入规则、日志所有权和资源清理义务。拆分为独立包可以让管道安全契约保持精简、明确。 -- **当任一进程流不是 TTY 时,让 TUI 插件静默降级**:不予采纳,因为回退会掩盖部署错误并改变交互语义。应用包可以通过 `auto` 选择入口;明确挂载的 TUI 会快速失败。 -- **把 TUI 接线与测试保留在 readline `repl-agent` 叶节点下**:不予采纳,因为一个叶节点会代表两个不同入口,也会破坏它与 `acp-agent` 的对称性。独立的 `tui-agent` 叶节点负责 TUI 浮层和测试,同时复用 repl-agent 的后端组合。 +- **当任一进程流不是 TTY 时,让 TUI 插件静默降级**:不予采纳,因为回退会掩盖部署错误并改变交互语义。宿主可以选择其他入口;明确挂载的 TUI 会快速失败。 +- **把 TUI 接线与测试保留在 readline `repl-agent` 叶节点下**:当时不予采纳,因为一个叶节点会代表两个不同入口。后续移除产品入口时删除了该应用接线,但保留了包边界。 - **在 `/model` 运行时修改 `agent.options`**:不予采纳,因为创建选项无法在异步 prompt 组装与请求路由之间提供原子边界。agent 作用域内的 waterfall 会在保持创建输入不可变的同时,为每个 step 快照一次选中的字段组合。 ## 后果 -- 交互式终端拥有带状态的 Markdown、卡片、计划和提问界面,无需再对齐第二套终端协议。 +- 挂载 TUI 的部署会获得带状态的 Markdown、卡片、计划和提问界面,无需再对齐第二套终端协议。 - TUI 会引入 pi-tui 依赖并严格要求 TTY;非 TTY 部署使用 Headless app 或结构化协议。 - 会话投影使恢复与持久会话保持一致,但只有一个已配置会话拥有 transcript 和编辑器。 - 工具包通过既有呈现方法扩展终端卡片,无需在 TUI 中增加工具专用分支。 diff --git a/.agents/notes/archived/feature/2026-07-20-windows-tui-support.i18n.yaml b/.agents/notes/archived/feature/2026-07-20-windows-tui-support.i18n.yaml new file mode 100644 index 0000000000..52f5e24a1b --- /dev/null +++ b/.agents/notes/archived/feature/2026-07-20-windows-tui-support.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write .agents/notes/archived/feature/2026-07-20-windows-tui-support.md +2026-07-20-windows-tui-support.md: 9308df7fb43378610cb2d480324c55bff07ea108 +2026-07-20-windows-tui-support.zh.md: 8b4a1eb4cef3056b47b911a07ed62202b52d1f73 diff --git a/.agents/notes/implemented/feature/2026-07-20-windows-tui-support.md b/.agents/notes/archived/feature/2026-07-20-windows-tui-support.md similarity index 99% rename from .agents/notes/implemented/feature/2026-07-20-windows-tui-support.md rename to .agents/notes/archived/feature/2026-07-20-windows-tui-support.md index 6b728486dd..9308df7fb4 100644 --- a/.agents/notes/implemented/feature/2026-07-20-windows-tui-support.md +++ b/.agents/notes/archived/feature/2026-07-20-windows-tui-support.md @@ -1,6 +1,7 @@ # Agent Note: Support the TUI on Windows Status: implemented +Archived: 2026-08-04 English | [中文](2026-07-20-windows-tui-support.zh.md) diff --git a/.agents/notes/implemented/feature/2026-07-20-windows-tui-support.zh.md b/.agents/notes/archived/feature/2026-07-20-windows-tui-support.zh.md similarity index 99% rename from .agents/notes/implemented/feature/2026-07-20-windows-tui-support.zh.md rename to .agents/notes/archived/feature/2026-07-20-windows-tui-support.zh.md index 2b53b05ff6..8b4a1eb4ce 100644 --- a/.agents/notes/implemented/feature/2026-07-20-windows-tui-support.zh.md +++ b/.agents/notes/archived/feature/2026-07-20-windows-tui-support.zh.md @@ -1,6 +1,7 @@ # Agent Note: 在 Windows 上支持 TUI Status: implemented +Archived: 2026-08-04 [English](2026-07-20-windows-tui-support.md) | 中文 diff --git a/.agents/notes/archived/feature/2026-07-21-tui-resume-command.i18n.yaml b/.agents/notes/archived/feature/2026-07-21-tui-resume-command.i18n.yaml new file mode 100644 index 0000000000..e6628da8c3 --- /dev/null +++ b/.agents/notes/archived/feature/2026-07-21-tui-resume-command.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write .agents/notes/archived/feature/2026-07-21-tui-resume-command.md +2026-07-21-tui-resume-command.md: de6c488b51b300705b33db13b8959b8114fdd025 +2026-07-21-tui-resume-command.zh.md: d7639c7a51fc5c35f10c514356ceb79d9c1ca76a diff --git a/.agents/notes/implemented/feature/2026-07-21-tui-resume-command.md b/.agents/notes/archived/feature/2026-07-21-tui-resume-command.md similarity index 87% rename from .agents/notes/implemented/feature/2026-07-21-tui-resume-command.md rename to .agents/notes/archived/feature/2026-07-21-tui-resume-command.md index c8cb855378..de6c488b51 100644 --- a/.agents/notes/implemented/feature/2026-07-21-tui-resume-command.md +++ b/.agents/notes/archived/feature/2026-07-21-tui-resume-command.md @@ -1,6 +1,7 @@ # Agent Note: Product-level TUI session resume Status: implemented +Archived: 2026-08-04 English | [中文](2026-07-21-tui-resume-command.zh.md) @@ -36,4 +37,4 @@ The exit line is a launcher-owned context slot rather than a config template, an ## Testing -TUI tests cover keyboard navigation, title/id search, search-clear/cancel behavior, running-agent refusal, refusal of the current session and sessions already live in this runtime, route absence, corrupt rows, preflight revalidation, the no-host warning, and stop-before-handoff ordering. Session-query tests pin detached full-log validation. Agent-loop resume tests pin exact identity and history; title, todo, and goal replay suites pin restored projections and disarmed goal activation. The keyless TUI snapshot owns the full-viewport selector and its IME cursor anchor, and a real PTY smoke covers search plus handoff. +TUI package tests cover keyboard navigation, title/id search, search-clear/cancel behavior, running-agent refusal, refusal of the current session and sessions already live in this runtime, route absence, corrupt rows, preflight revalidation, the no-host warning, and stop-before-handoff ordering. Session-query tests pin detached full-log validation. Agent-loop resume tests pin exact identity and history; title, todo, and goal replay suites pin restored projections and disarmed goal activation. The package semantic snapshot owns the full-viewport selector and its IME cursor anchor; a deployment shipping the TUI owns its process and PTY handoff acceptance. diff --git a/.agents/notes/implemented/feature/2026-07-21-tui-resume-command.zh.md b/.agents/notes/archived/feature/2026-07-21-tui-resume-command.zh.md similarity index 86% rename from .agents/notes/implemented/feature/2026-07-21-tui-resume-command.zh.md rename to .agents/notes/archived/feature/2026-07-21-tui-resume-command.zh.md index 2a7e74d110..d7639c7a51 100644 --- a/.agents/notes/implemented/feature/2026-07-21-tui-resume-command.zh.md +++ b/.agents/notes/archived/feature/2026-07-21-tui-resume-command.zh.md @@ -1,6 +1,7 @@ # Agent Note: 产品级 TUI 会话恢复 Status: implemented +Archived: 2026-08-04 [English](2026-07-21-tui-resume-command.md) | 中文 @@ -36,4 +37,4 @@ Status: implemented ## Testing -TUI 测试覆盖键盘导航、标题/id 搜索、清空搜索后再取消、agent 运行期间拒绝恢复、拒绝恢复当前会话和已在本运行时中处于活跃状态的会话、路由缺失、损坏的候选行、预检复查、无宿主时的告警,以及停止终端先于宿主交接的顺序。session-query 测试固定脱离运行时的完整日志验证。agent-loop 恢复测试固定会话身份和历史完全一致;标题、待办事项和目标回放测试套件固定这些投影均可恢复,且目标激活状态已经解除。无密钥 TUI 快照固定全屏选择页和输入法光标锚点,真实 PTY smoke 则覆盖搜索与交接。 +TUI 包(package)测试覆盖键盘导航、标题/id 搜索、清空搜索后再取消、agent 运行期间拒绝恢复、拒绝恢复当前会话和已在本运行时中处于活跃状态的会话、路由缺失、损坏的候选行、预检复查、无宿主时的告警,以及停止终端先于宿主交接的顺序。session-query 测试固定脱离运行时的完整日志验证。agent-loop 恢复测试固定会话身份和历史完全一致;标题、待办事项和目标回放测试套件固定这些投影均可恢复,且目标激活状态已经解除。包级语义快照固定全屏选择页和输入法光标锚点;交付 TUI 的部署负责其进程与 PTY 交接验收。 diff --git a/.agents/notes/archived/feature/2026-07-21-tui-skill-slash-command.i18n.yaml b/.agents/notes/archived/feature/2026-07-21-tui-skill-slash-command.i18n.yaml new file mode 100644 index 0000000000..a8a6577e01 --- /dev/null +++ b/.agents/notes/archived/feature/2026-07-21-tui-skill-slash-command.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write .agents/notes/archived/feature/2026-07-21-tui-skill-slash-command.md +2026-07-21-tui-skill-slash-command.md: e151f92d0d9eb1486bcf21498fb73ba156edd861 +2026-07-21-tui-skill-slash-command.zh.md: ac1c4da948dcbd6b01bdb6e62d66d5f704c0b132 diff --git a/.agents/notes/implemented/feature/2026-07-21-tui-skill-slash-command.md b/.agents/notes/archived/feature/2026-07-21-tui-skill-slash-command.md similarity index 82% rename from .agents/notes/implemented/feature/2026-07-21-tui-skill-slash-command.md rename to .agents/notes/archived/feature/2026-07-21-tui-skill-slash-command.md index 872e1f1097..e151f92d0d 100644 --- a/.agents/notes/implemented/feature/2026-07-21-tui-skill-slash-command.md +++ b/.agents/notes/archived/feature/2026-07-21-tui-skill-slash-command.md @@ -1,6 +1,7 @@ # Agent Note: TUI skill slash command Status: implemented +Archived: 2026-08-04 English | [中文](2026-07-21-tui-skill-slash-command.zh.md) @@ -30,4 +31,4 @@ Autocomplete filters the invocation-neutral `list()` result with `isUserInvocabl ## Consequences -Manual invocation always reloads the full skill body: the TUI does not detect a skill already present in the conversation, so a repeated `/skill:` appends its instructions again — acceptable because re-injection is sometimes the intent, and documented under the package README's Known Limitations. The two-renderer duplication is a standing maintenance cost accepted above. The `` wrapper is stable model-visible text and is pinned verbatim in unit tests against a real `SkillService`; the help-panel line is pinned by the `errors-and-help` terminal snapshot. Autocomplete population and the disposed-lookup and failed-lookup branches are covered by unit tests that mount the real registry or a controllable service. End-to-end delivery is proven by a dedicated real-composition test: the `examples/tui-agent` keyless PTY smoke (`tui-keyless-smoke.e2e.ts`) boots the production TUI/agent/skill stack through the Loader under a genuine pseudo-terminal with only the model scripted, drops a fixture skill under the agents-home `skills/` root, types `/skill:` as live keystrokes, and asserts the scripted adapter echoes the fixture's body marker only when the rendered `` block arrives — exercising `ctx.get('skills')` resolution in the shipped tree, the client-side parse, the local provider load, and the user turn reaching the model together. That fixture's frontmatter description avoids a `: ` colon-space so its YAML stays a plain scalar; an invalid-frontmatter skill is silently dropped during discovery. +Manual invocation always reloads the full skill body: the TUI does not detect a skill already present in the conversation, so a repeated `/skill:` appends its instructions again — acceptable because re-injection is sometimes the intent, and documented under the package README's Known Limitations. The two-renderer duplication is a standing maintenance cost accepted above. The `` wrapper is stable model-visible text and is pinned verbatim in package tests against a real `SkillService`; the package semantic matrix pins the help-panel line. Autocomplete population, user-only discovery, delivery to idle and running agents, and the disposed-lookup and failed-lookup branches are covered by package tests that mount the real registry or a controllable service. The removed product TUI's keyless PTY smoke formerly covered the assembled Loader path; a future terminal deployment owns that application-level scenario. diff --git a/.agents/notes/implemented/feature/2026-07-21-tui-skill-slash-command.zh.md b/.agents/notes/archived/feature/2026-07-21-tui-skill-slash-command.zh.md similarity index 80% rename from .agents/notes/implemented/feature/2026-07-21-tui-skill-slash-command.zh.md rename to .agents/notes/archived/feature/2026-07-21-tui-skill-slash-command.zh.md index 772e25745e..ac1c4da948 100644 --- a/.agents/notes/implemented/feature/2026-07-21-tui-skill-slash-command.zh.md +++ b/.agents/notes/archived/feature/2026-07-21-tui-skill-slash-command.zh.md @@ -1,6 +1,7 @@ # Agent Note: TUI skill slash command Status: implemented +Archived: 2026-08-04 [English](2026-07-21-tui-skill-slash-command.md) | 中文 @@ -30,4 +31,4 @@ TUI 通过 `ctx.get('skills')` 读取 skill 服务,而非声明式注入,因 ## Consequences -手动调用总是重新加载完整的 skill 正文:TUI 不会检测某个 skill 是否已在对话中出现,因此重复的 `/skill:` 会再次追加其指令——这可以接受,因为重新注入有时正是意图所在,且已在本包 README 的已知限制中说明。上文接受的双渲染器重复是一项长期维护成本。`` 包裹是稳定的、模型可见的文本,并在单元测试中针对一个真实的 `SkillService` 逐字固定;帮助面板那一行由 `errors-and-help` 终端快照固定。自动补全的填充、dispose 后查找分支、以及查找失败分支,都由挂载真实注册表或可控服务的单元测试覆盖。端到端的投递由一项专门的真实组合测试证明:`examples/tui-agent` 的无密钥 PTY 冒烟测试(`tui-keyless-smoke.e2e.ts`)在真实伪终端下经由 loader 引导生产环境的 TUI/agent/skill 栈,仅对模型进行脚本化,把一个夹具 skill 放入 agents home 的 `skills/` 根下,以真实按键输入 `/skill:`,并断言:只有当渲染出的 `` 文本块抵达时,脚本化适配器才会回显该夹具的正文标记——从而一并演练了 `ctx.get('skills')` 在发布树中的解析、客户端解析、本地 provider 的加载,以及用户回合抵达模型。该夹具的 frontmatter 描述避免出现 `: ` 冒号加空格,使其 YAML 保持为纯标量;frontmatter 无效的 skill 会在发现阶段被静默丢弃。 +手动调用总是重新加载完整的 skill 正文:TUI 不会检测某个 skill 是否已在对话中出现,因此重复的 `/skill:` 会再次追加其指令——这可以接受,因为重新注入有时正是意图所在,且已在本包 README 的已知限制中说明。上文接受的双渲染器重复是一项长期维护成本。`` 包装层是稳定的、模型可见的文本,并在包测试中针对一个真实的 `SkillService` 逐字固定;包语义矩阵固定帮助面板中的这一行。自动补全填充、仅限用户的发现、向空闲及运行中 agent 投递,以及 dispose 后查找和查找失败分支,都由挂载真实注册表或可控服务的包测试覆盖。已移除的产品 TUI 的无密钥 PTY 冒烟测试过去覆盖组装后的 Loader 路径;未来的终端部署负责该应用级场景。 diff --git a/.agents/notes/archived/feature/2026-07-22-docked-web-goal-bar.i18n.yaml b/.agents/notes/archived/feature/2026-07-22-docked-web-goal-bar.i18n.yaml new file mode 100644 index 0000000000..535a0a8ff3 --- /dev/null +++ b/.agents/notes/archived/feature/2026-07-22-docked-web-goal-bar.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write .agents/notes/archived/feature/2026-07-22-docked-web-goal-bar.md +2026-07-22-docked-web-goal-bar.md: decf40996b51a0f2358a943bbb928f00d4db2026 +2026-07-22-docked-web-goal-bar.zh.md: 8ebb106b260a6107084c07b51b1763adb1df2da8 diff --git a/.agents/notes/implemented/feature/2026-07-22-docked-web-goal-bar.md b/.agents/notes/archived/feature/2026-07-22-docked-web-goal-bar.md similarity index 84% rename from .agents/notes/implemented/feature/2026-07-22-docked-web-goal-bar.md rename to .agents/notes/archived/feature/2026-07-22-docked-web-goal-bar.md index 21f200f165..decf40996b 100644 --- a/.agents/notes/implemented/feature/2026-07-22-docked-web-goal-bar.md +++ b/.agents/notes/archived/feature/2026-07-22-docked-web-goal-bar.md @@ -1,6 +1,7 @@ # Agent Note: Docked web goal bar Status: implemented +Archived: 2026-08-07 English | [中文](2026-07-22-docked-web-goal-bar.zh.md) @@ -16,13 +17,13 @@ Visibility drives the label and actions: active shows "Ongoing Goal" with pause/ `GoalBarActions` lives in ui-goal's slot contract (`packages/client/ui-goal/src/client/slots.ts`) and carries exactly the rendered verbs: `onEdit`/`onPause`/`onResume`/`onClear`. Each callback asynchronously returns an explicit success/failure result so `GoalBar` owns its transitions and error display. `apply.ts` wires them to the runtime session methods; the runtime session resolves the current goal's compare-and-set ref internally, so the UI passes no ref. -The runtime session gains the goal surface the strip (and future UI) needs: `fetchGoal` populates the snapshot on open, and a live `context/message` carrying `goal/change` meta triggers a coalesced refetch — concurrent triggers share the in-flight `goal.get`, while a trigger received during that read schedules one coalesced trailing read so independently ordered notifications and GET responses cannot leave stale state. Window replays never refetch, and matching the meta kind (rather than a goal key) also catches clear tombstones written by other clients. The six mutation verbs fold transport failures into `{ ok: false }` results like every sibling session method, and a get result older than a mutation response that landed mid-flight is dropped. +The runtime session gains the goal surface the strip (and future UI) needs through the host-computed `goal` projection. The history tail seeds its whole current value, and `session/projection` frames update it when durable `agent/inbox/spliced` insertions commit goal snapshots or clear tombstones; later context admission is irrelevant to UI freshness. The four rendered mutation verbs fold transport failures into `{ ok: false }` results like every sibling session method. The strip's background is `--dsw-alias-interactive-bg-hover` rather than the mock's literal `#F5F6F7`: the translucent hover gray resolves to that value over the white light-theme base and lifts the strip off the composer card in dark mode, where a static light token would sink. All colors are `--dsw-*` tokens. ## Testing -`packages/client/ui-goal/tests/goalbar.spec.tsx` pins the behavior through props alone: loading/absent/complete render nothing, the active strip renders label/objective and fires clear, rapid same-frame clear clicks dispatch once and a successful clear hides before projection convergence, the edit form prefills, rejects empty, saves on Enter, cancels on Esc, and resets when the goal's identity changes, the active strip fires pause, the paused strip fires resume, and the blocked strip exposes the reason tooltip. Component failure-path cases prove that a failed edit preserves its draft and that edit/resume/clear errors remain visible and retryable in the bar. The skeleton specs mount `ConversationRoot` with and without `goalActions`; the undefined case is seeded with an active goal, so the missing gate — not the missing goal — is what hides the strip. Runtime session specs pin the folded-error results, the live-only in-flight-plus-trailing refetch, and the stale-read guard. A keyless real-browser smoke boots the assembled application through `boot → RPC → runtime → GoalBar` and records an inline snapshot of the rendered label, objective, and actions. +`packages/client/ui-goal/tests/goalbar.spec.tsx` pins the behavior through props alone: loading/absent/complete render nothing, the active strip renders label/objective and fires clear, rapid same-frame clear clicks dispatch once and a successful clear hides before projection convergence, the edit form prefills, rejects empty, saves on Enter, cancels on Esc, and resets when the goal's identity changes, the active strip fires pause, the paused strip fires resume, and the blocked strip exposes the reason tooltip. Component failure-path cases prove that a failed edit preserves its draft and that edit/resume/clear errors remain visible and retryable in the bar. The skeleton specs mount `ConversationRoot` with and without `goalActions`; the undefined case is seeded with an active goal, so the missing gate — not the missing goal — is what hides the strip. Runtime session specs pin folded-error results and projection updates. A keyless real-browser smoke boots the assembled application through `boot → RPC → runtime → GoalBar` and records an inline snapshot of the rendered label, objective, and actions. ## Alternatives considered @@ -35,6 +36,6 @@ The strip's background is `--dsw-alias-interactive-bg-hover` rather than the moc - Goal presence in the web UI is a standalone composer-context strip: sparkle, phase label, truncated objective, and pause/edit/clear (resume replacing pause when paused) — the browser client's first goal surface. - Goal mutations are single-flight within the component; a successful clear hides its exact goal immediately while projection delivery converges, preventing duplicate CAS errors without making transient UI state authoritative. -- The runtime session exposes the goal verbs over RPC with folded transport errors, and refreshes the snapshot's goal on open and on live goal-change meta (coalesced, guarded against stale reads). +- The runtime session exposes the goal verbs over RPC with folded transport errors and consumes the host's durable whole-goal projection on open and live updates. - Objective editing is reachable from the UI for the first time, through `goal.edit` with the runtime-owned ref; complete remains available to other surfaces (`/goal`, model tools). - `goal === null` renders nothing; the composer carries no persistent create affordance — creation is the `/goal` command's job. diff --git a/.agents/notes/implemented/feature/2026-07-22-docked-web-goal-bar.zh.md b/.agents/notes/archived/feature/2026-07-22-docked-web-goal-bar.zh.md similarity index 83% rename from .agents/notes/implemented/feature/2026-07-22-docked-web-goal-bar.zh.md rename to .agents/notes/archived/feature/2026-07-22-docked-web-goal-bar.zh.md index eb8e3edda5..8ebb106b26 100644 --- a/.agents/notes/implemented/feature/2026-07-22-docked-web-goal-bar.zh.md +++ b/.agents/notes/archived/feature/2026-07-22-docked-web-goal-bar.zh.md @@ -1,6 +1,7 @@ # Agent Note: 停靠式 Web 目标条 Status: implemented +Archived: 2026-08-07 [English](2026-07-22-docked-web-goal-bar.md) | 中文 @@ -16,13 +17,13 @@ Web UI 此前没有任何目标相关的界面:目标栈已随模型工具、T `GoalBarActions` 位于 ui-goal 的槽位契约(`packages/client/ui-goal/src/client/slots.ts`),只携带实际渲染的动词:`onEdit`/`onPause`/`onResume`/`onClear`。每个回调都会异步返回显式成功/失败结果,因此 `GoalBar` 自行负责界面转换和错误显示。`apply.ts` 把它们接到运行时会话方法上;运行时会话在内部解析当前目标的 compare-and-set ref,因此 UI 不传 ref。 -运行时会话获得了横条(以及未来 UI)所需的目标表面:`fetchGoal` 在打开时填充快照;携带 `goal/change` 元数据的 live `context/message` 触发合并重新拉取——并发触发器共享正在执行的 `goal.get`,读取期间收到的触发器会安排一次合并后的尾随读取,避免彼此独立排序的通知和 GET 响应留下陈旧状态。窗口重放绝不触发重新拉取,且匹配元数据 kind(而不是 goal 键)还能捕获其他客户端写入的清除墓碑。六个变更动词与所有同类会话方法一样,把传输层失败折叠为 `{ ok: false }` 结果;比在拉取途中落地的变更响应更旧的 get 结果会被丢弃。 +运行时会话通过由 host 计算的 `goal` 投影获得横条(以及未来 UI)所需的 goal 表面。历史尾页会提供完整当前值作为初始状态;持久 `agent/inbox/spliced` 插入项提交 goal 快照或 clear 墓碑时,`session/projection` 帧会更新该值,后续上下文准入与 UI 新鲜度无关。4 个实际渲染的变更动词与所有同类会话方法一样,把传输层失败折叠为 `{ ok: false }` 结果。 横条的背景色用 `--dsw-alias-interactive-bg-hover`,而不是设计稿里的字面值 `#F5F6F7`:这个半透明的悬浮灰在浅色主题的白色底上正好解析为该值,而在深色模式下能把横条从输入框卡片上衬托出来,静态的浅色 token 在深色模式下会沉进去。所有颜色都是 `--dsw-*` token。 ## 测试 -`packages/client/ui-goal/tests/goalbar.spec.tsx` 仅通过 props 固定这些行为:加载中/无目标/已完成时不渲染;active 横条渲染标签和目标内容并触发清除;同一帧内快速连续点击清除只会分发一次,清除成功后横条会在投影收敛前隐藏;编辑表单预填内容、拒绝空值、按 Enter 保存、按 Esc 取消,并在目标身份变化时重置;active 横条触发暂停;paused 横条触发恢复;blocked 横条暴露原因悬浮提示。组件失败路径用例证明编辑失败时保留草稿,并且编辑/恢复/清除错误持续显示在横条中且可重试。skeleton 规格测试分别挂载带与不带 `goalActions` 的 `ConversationRoot`;未定义的情形预置了一个 active 目标,因此隐藏横条的是缺失的挂载门,而不是缺失的目标。运行时会话规格测试固定了折叠错误结果、仅 live 的执行中读取加尾随读取,以及陈旧读取守卫。一个无密钥真实浏览器冒烟测试通过 `boot → RPC → runtime → GoalBar` 启动组装后的应用,并以内联快照记录渲染出的标签、目标内容和操作。 +`packages/client/ui-goal/tests/goalbar.spec.tsx` 仅通过 props 固定这些行为:加载中/无目标/已完成时不渲染;active 横条渲染标签和目标内容并触发清除;同一帧内快速连续点击清除只会分发一次,清除成功后横条会在投影收敛前隐藏;编辑表单预填内容、拒绝空值、按 Enter 保存、按 Esc 取消,并在目标身份变化时重置;active 横条触发暂停;paused 横条触发恢复;blocked 横条暴露原因悬浮提示。组件失败路径用例证明编辑失败时保留草稿,并且编辑/恢复/清除错误持续显示在横条中且可重试。skeleton 规格测试分别挂载带与不带 `goalActions` 的 `ConversationRoot`;未定义的情形预置了一个 active 目标,因此隐藏横条的是缺失的挂载门,而不是缺失的目标。运行时会话规格测试固定折叠错误结果和投影更新。一个无密钥真实浏览器冒烟测试通过 `boot → RPC → runtime → GoalBar` 启动组装后的应用,并以内联快照记录渲染出的标签、目标内容和操作。 ## 考虑过的替代方案 @@ -35,6 +36,6 @@ Web UI 此前没有任何目标相关的界面:目标栈已随模型工具、T - Web UI 中目标的存在形式是独立的 composer 上下文横条:闪光图标、阶段标签、截断的目标内容,以及暂停/编辑/清除(暂停时恢复取代暂停)——这是浏览器客户端的第一个目标界面。 - 目标变更在组件内走 single-flight;清除成功后会在投影投递收敛期间立即隐藏与其 id 完全匹配的目标,既防止重复 CAS 错误,又不会把瞬态 UI 状态视为权威。 -- 运行时会话通过 RPC 暴露目标动词并折叠传输层错误,且在打开时和 live 目标变更元数据到达时刷新快照中的目标(合并拉取,带陈旧读取守卫)。 +- 运行时会话通过 RPC 暴露 goal 动词并折叠传输层错误,在打开时和 live 更新时消费 host 的持久完整 goal 投影。 - 目标内容首次可以从 UI 编辑,经由 `goal.edit`,ref 由运行时持有;完成对其他界面(`/goal`、模型工具)照常可用。 - `goal === null` 时不渲染任何内容;输入框不提供常驻的创建入口,创建是 `/goal` 命令的职责。 diff --git a/.agents/notes/archived/feature/2026-07-23-tui-file-reference-autocomplete.i18n.yaml b/.agents/notes/archived/feature/2026-07-23-tui-file-reference-autocomplete.i18n.yaml new file mode 100644 index 0000000000..5e79c40332 --- /dev/null +++ b/.agents/notes/archived/feature/2026-07-23-tui-file-reference-autocomplete.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write .agents/notes/archived/feature/2026-07-23-tui-file-reference-autocomplete.md +2026-07-23-tui-file-reference-autocomplete.md: 3ceda81858bc3364a2c4ac5b91d599b23479412a +2026-07-23-tui-file-reference-autocomplete.zh.md: c0b947edf6df42d27f5fee40d95eb073029e32b1 diff --git a/.agents/notes/implemented/feature/2026-07-23-tui-file-reference-autocomplete.md b/.agents/notes/archived/feature/2026-07-23-tui-file-reference-autocomplete.md similarity index 96% rename from .agents/notes/implemented/feature/2026-07-23-tui-file-reference-autocomplete.md rename to .agents/notes/archived/feature/2026-07-23-tui-file-reference-autocomplete.md index 1a13600921..3ceda81858 100644 --- a/.agents/notes/implemented/feature/2026-07-23-tui-file-reference-autocomplete.md +++ b/.agents/notes/archived/feature/2026-07-23-tui-file-reference-autocomplete.md @@ -1,6 +1,7 @@ # Agent Note: TUI file-reference autocomplete Status: implemented +Archived: 2026-08-04 English | [中文](2026-07-23-tui-file-reference-autocomplete.zh.md) @@ -30,4 +31,4 @@ Structured session mentions keep their existing snapshot preparation. Unlike fil Users can discover and insert paths without making selection itself expensive or model-visible beyond the path. The model preserves agency over whether to inspect a file, and any inspection remains reconstructable through the logged tool transcript. The fixed instruction slightly enlarges TUI system prompts when `read` is present, and content-requiring requests take an additional tool round trip. -Completion is deliberately bounded and advisory: very large workspaces may omit paths beyond the configured index cap, ignored files may still appear, and remote or virtual filesystem deployments must align the TUI host working directory with the `read` namespace or supply a different completion surface. Package tests pin token grammar, ranking, bounds, cancellation, invalidation, and path-only submission; terminal snapshots and the real Loader PTY smoke pin the visible menu and keyboard completion. +Completion is deliberately bounded and advisory: very large workspaces may omit paths beyond the configured index cap, ignored files may still appear, and remote or virtual filesystem deployments must align the TUI host working directory with the `read` namespace or supply a different completion surface. Package tests pin token grammar, ranking, bounds, cancellation, invalidation, path-only submission, the visible menu, and keyboard completion; a deployment shipping the TUI owns its Loader and PTY acceptance. diff --git a/.agents/notes/implemented/feature/2026-07-23-tui-file-reference-autocomplete.zh.md b/.agents/notes/archived/feature/2026-07-23-tui-file-reference-autocomplete.zh.md similarity index 95% rename from .agents/notes/implemented/feature/2026-07-23-tui-file-reference-autocomplete.zh.md rename to .agents/notes/archived/feature/2026-07-23-tui-file-reference-autocomplete.zh.md index 410f0d49db..c0b947edf6 100644 --- a/.agents/notes/implemented/feature/2026-07-23-tui-file-reference-autocomplete.zh.md +++ b/.agents/notes/archived/feature/2026-07-23-tui-file-reference-autocomplete.zh.md @@ -1,6 +1,7 @@ # Agent Note: TUI 文件引用自动补全 Status: implemented +Archived: 2026-08-04 [English](2026-07-23-tui-file-reference-autocomplete.md) | 中文 @@ -30,4 +31,4 @@ TUI 维护一个有容量上限且可取消的主机工作区路径索引,以 用户可以发现并插入路径,而选择操作本身不会带来高开销,对模型可见的内容也仅限路径。模型仍可自行决定是否检查文件,任何检查都能通过已记录的工具 transcript 重建。存在 `read` 时,固定指令会略微增大 TUI 系统提示词;需要文件内容的请求还会增加一次工具往返。 -补全有意采用有界的提示性设计:超大型工作区可能省略超过配置索引上限的路径,被忽略的文件仍可能出现,远程或虚拟文件系统部署必须让 TUI 的主机工作目录与 `read` 命名空间对齐,否则需要提供不同的补全接口。包(package)测试固定 token 语法、排序、边界、取消、失效和仅提交路径的行为;终端快照与真实 Loader PTY 冒烟测试固定可见菜单和键盘补全。 +补全有意采用有界的提示性设计:超大型工作区可能省略超过配置索引上限的路径,被忽略的文件仍可能出现,远程或虚拟文件系统部署必须让 TUI 的主机工作目录与 `read` 命名空间对齐,否则需要提供不同的补全接口。包(package)测试固定 token 语法、排序、边界、取消、失效、仅提交路径的行为、可见菜单和键盘补全;交付 TUI 的部署负责其 Loader 与 PTY 验收。 diff --git a/.agents/notes/archived/feature/2026-07-23-tui-status-prompt-tools.i18n.yaml b/.agents/notes/archived/feature/2026-07-23-tui-status-prompt-tools.i18n.yaml new file mode 100644 index 0000000000..0322b85af5 --- /dev/null +++ b/.agents/notes/archived/feature/2026-07-23-tui-status-prompt-tools.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write .agents/notes/archived/feature/2026-07-23-tui-status-prompt-tools.md +2026-07-23-tui-status-prompt-tools.md: b8e5e9fc4fd8f9d6dafa689512ef991ee1013b39 +2026-07-23-tui-status-prompt-tools.zh.md: 3d10073b4332609371fdd1ebed7486970b439251 diff --git a/.agents/notes/implemented/feature/2026-07-23-tui-status-prompt-tools.md b/.agents/notes/archived/feature/2026-07-23-tui-status-prompt-tools.md similarity index 87% rename from .agents/notes/implemented/feature/2026-07-23-tui-status-prompt-tools.md rename to .agents/notes/archived/feature/2026-07-23-tui-status-prompt-tools.md index 42524d021d..b8e5e9fc4f 100644 --- a/.agents/notes/implemented/feature/2026-07-23-tui-status-prompt-tools.md +++ b/.agents/notes/archived/feature/2026-07-23-tui-status-prompt-tools.md @@ -1,6 +1,7 @@ # Agent Note: TUI status inspects model request inputs Status: implemented +Archived: 2026-08-04 English | [中文](2026-07-23-tui-status-prompt-tools.zh.md) @@ -26,4 +27,4 @@ The command can run prompt providers and assembly listeners, just like request p ## Testing -Unit coverage pins scoped assembly output, ordered tool names, empty labels, and terminal-control escaping. The keyless TUI smoke and terminal snapshot exercise `/status` through the assembled application. +Package behavior tests pin scoped assembly output, ordered tool names, empty labels, and terminal-control escaping. The package semantic snapshots exercise `/status` at normal and narrow widths; a deployment shipping the TUI owns its assembled process acceptance. diff --git a/.agents/notes/implemented/feature/2026-07-23-tui-status-prompt-tools.zh.md b/.agents/notes/archived/feature/2026-07-23-tui-status-prompt-tools.zh.md similarity index 87% rename from .agents/notes/implemented/feature/2026-07-23-tui-status-prompt-tools.zh.md rename to .agents/notes/archived/feature/2026-07-23-tui-status-prompt-tools.zh.md index 5a33e19e97..3d10073b43 100644 --- a/.agents/notes/implemented/feature/2026-07-23-tui-status-prompt-tools.zh.md +++ b/.agents/notes/archived/feature/2026-07-23-tui-status-prompt-tools.zh.md @@ -1,6 +1,7 @@ # Agent Note: TUI 状态检查模型请求输入 Status: implemented +Archived: 2026-08-04 [English](2026-07-23-tui-status-prompt-tools.md) | 中文 @@ -26,4 +27,4 @@ Status: implemented ## 测试 -单元测试固定按作用域组装的输出、工具名称顺序、空值标签和终端控制字符转义。无密钥 TUI 冒烟测试与终端快照通过完整组装的应用执行 `/status`。 +包(package)行为测试固定按作用域组装的输出、工具名称顺序、空值标签和终端控制字符转义。包级语义快照在正常宽度和窄宽度下执行 `/status`;交付 TUI 的部署负责其组装后的进程验收。 diff --git a/.agents/notes/implemented/feature/2026-07-29-tui-hidden-mode-assistant-fold.i18n.yaml b/.agents/notes/archived/feature/2026-07-24-configurable-tui-prompt-theme.i18n.yaml similarity index 56% rename from .agents/notes/implemented/feature/2026-07-29-tui-hidden-mode-assistant-fold.i18n.yaml rename to .agents/notes/archived/feature/2026-07-24-configurable-tui-prompt-theme.i18n.yaml index 338f90664d..29edf8a739 100644 --- a/.agents/notes/implemented/feature/2026-07-29-tui-hidden-mode-assistant-fold.i18n.yaml +++ b/.agents/notes/archived/feature/2026-07-24-configurable-tui-prompt-theme.i18n.yaml @@ -1,6 +1,6 @@ # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: -# pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-29-tui-hidden-mode-assistant-fold.md -2026-07-29-tui-hidden-mode-assistant-fold.md: e2bae1d4669fd0a4c8f9278c58f641704b425109 -2026-07-29-tui-hidden-mode-assistant-fold.zh.md: 583d6099f9cd5edfc592a9d510d260d7a4172013 +# pnpm run verify-translation-pairing --write .agents/notes/archived/feature/2026-07-24-configurable-tui-prompt-theme.md +2026-07-24-configurable-tui-prompt-theme.md: 918eaa617811049a5caa4b9f43a8cc12854471c3 +2026-07-24-configurable-tui-prompt-theme.zh.md: eccfed00c3fe866291d2f18bd7cecf117296bd58 diff --git a/.agents/notes/implemented/feature/2026-07-24-configurable-tui-prompt-theme.md b/.agents/notes/archived/feature/2026-07-24-configurable-tui-prompt-theme.md similarity index 93% rename from .agents/notes/implemented/feature/2026-07-24-configurable-tui-prompt-theme.md rename to .agents/notes/archived/feature/2026-07-24-configurable-tui-prompt-theme.md index f8815c6c19..918eaa6178 100644 --- a/.agents/notes/implemented/feature/2026-07-24-configurable-tui-prompt-theme.md +++ b/.agents/notes/archived/feature/2026-07-24-configurable-tui-prompt-theme.md @@ -1,6 +1,7 @@ # Agent Note: TUI prompt themes compose mutable plugin values Status: implemented +Archived: 2026-08-04 English | [中文](2026-07-24-configurable-tui-prompt-theme.zh.md) @@ -36,4 +37,4 @@ Changing `inputPrompt` through a registered value preserves editor text, cursor, ## Testing -Registry tests pin validation, duplicate rejection, updates, unavailable values, coalesced-notification containment, unsubscribe, disposal, interpolation, trailing-literal retention, whitespace cleanup, and ANSI preservation. TUI tests pin nested theme defaults, custom templates, out-of-band value redraw, mutable redraw, Powerline-capable fragments, dynamic input-prefix width, and the static running placeholder. The assembled TUI demo test pins service load order and config forwarding. +Registry tests pin validation, duplicate rejection, updates, unavailable values, coalesced-notification containment, unsubscribe, disposal, interpolation, trailing-literal retention, whitespace cleanup, and ANSI preservation. TUI package tests pin service availability, nested theme defaults, config forwarding, custom templates, out-of-band value redraw, mutable redraw, Powerline-capable fragments, dynamic input-prefix width, and the static running placeholder. A deployment shipping the TUI owns assembled load-order acceptance. diff --git a/.agents/notes/implemented/feature/2026-07-24-configurable-tui-prompt-theme.zh.md b/.agents/notes/archived/feature/2026-07-24-configurable-tui-prompt-theme.zh.md similarity index 92% rename from .agents/notes/implemented/feature/2026-07-24-configurable-tui-prompt-theme.zh.md rename to .agents/notes/archived/feature/2026-07-24-configurable-tui-prompt-theme.zh.md index 831471860a..eccfed00c3 100644 --- a/.agents/notes/implemented/feature/2026-07-24-configurable-tui-prompt-theme.zh.md +++ b/.agents/notes/archived/feature/2026-07-24-configurable-tui-prompt-theme.zh.md @@ -1,6 +1,7 @@ # Agent Note: TUI 提示符主题组合可变的插件值 Status: implemented +Archived: 2026-08-04 [English](2026-07-24-configurable-tui-prompt-theme.md) | 中文 @@ -36,4 +37,4 @@ TUI 主题把 `color`、`truecolor`、`leftPrompt`、`rightPrompt`、`inputPromp ## 测试 -注册表测试固定校验、重名拒绝、更新、不可用值、合并通知的容错、取消订阅、dispose、插值、尾随字面保留、空白清理与 ANSI 保留等行为。TUI 测试固定嵌套主题默认值、自定义模板、带外值重绘、可变重绘、支持 Powerline 的片段、动态输入前缀宽度以及运行状态下的静态占位文本。组装后的 TUI 演示测试固定服务加载顺序与配置转发。 +注册表测试固定校验、重名拒绝、更新、不可用值、合并通知的容错、取消订阅、dispose、插值、尾随字面保留、空白清理与 ANSI 保留等行为。TUI 包(package)测试固定服务可用性、嵌套主题默认值、配置转发、自定义模板、带外值重绘、可变重绘、支持 Powerline 的片段、动态输入前缀宽度以及运行状态下的静态占位文本。交付 TUI 的部署负责组装后的加载顺序验收。 diff --git a/.agents/notes/archived/feature/2026-07-24-tui-question-dialog-multiline.i18n.yaml b/.agents/notes/archived/feature/2026-07-24-tui-question-dialog-multiline.i18n.yaml new file mode 100644 index 0000000000..90558a3d22 --- /dev/null +++ b/.agents/notes/archived/feature/2026-07-24-tui-question-dialog-multiline.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write .agents/notes/archived/feature/2026-07-24-tui-question-dialog-multiline.md +2026-07-24-tui-question-dialog-multiline.md: 9f1e75325942f28d69d9cadadf938c0f0b5e3ae5 +2026-07-24-tui-question-dialog-multiline.zh.md: bd112898367e7a7dd940f2b5fa76e531029ab803 diff --git a/.agents/notes/implemented/feature/2026-07-24-tui-question-dialog-multiline.md b/.agents/notes/archived/feature/2026-07-24-tui-question-dialog-multiline.md similarity index 99% rename from .agents/notes/implemented/feature/2026-07-24-tui-question-dialog-multiline.md rename to .agents/notes/archived/feature/2026-07-24-tui-question-dialog-multiline.md index fc6e9bceee..9f1e753259 100644 --- a/.agents/notes/implemented/feature/2026-07-24-tui-question-dialog-multiline.md +++ b/.agents/notes/archived/feature/2026-07-24-tui-question-dialog-multiline.md @@ -1,6 +1,7 @@ # Agent Note: TUI QuestionDialog renders options across multiple lines Status: implemented +Archived: 2026-08-04 English | [中文](2026-07-24-tui-question-dialog-multiline.zh.md) diff --git a/.agents/notes/implemented/feature/2026-07-24-tui-question-dialog-multiline.zh.md b/.agents/notes/archived/feature/2026-07-24-tui-question-dialog-multiline.zh.md similarity index 99% rename from .agents/notes/implemented/feature/2026-07-24-tui-question-dialog-multiline.zh.md rename to .agents/notes/archived/feature/2026-07-24-tui-question-dialog-multiline.zh.md index a56821921b..bd11289836 100644 --- a/.agents/notes/implemented/feature/2026-07-24-tui-question-dialog-multiline.zh.md +++ b/.agents/notes/archived/feature/2026-07-24-tui-question-dialog-multiline.zh.md @@ -1,6 +1,7 @@ # Agent Note: TUI QuestionDialog 以多行方式渲染选项 Status: implemented +Archived: 2026-08-04 [English](2026-07-24-tui-question-dialog-multiline.md) | 中文 diff --git a/.agents/notes/archived/feature/2026-07-24-tui-shell-prompt-editor.i18n.yaml b/.agents/notes/archived/feature/2026-07-24-tui-shell-prompt-editor.i18n.yaml new file mode 100644 index 0000000000..a78bd1a593 --- /dev/null +++ b/.agents/notes/archived/feature/2026-07-24-tui-shell-prompt-editor.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write .agents/notes/archived/feature/2026-07-24-tui-shell-prompt-editor.md +2026-07-24-tui-shell-prompt-editor.md: a3707d3fcd0ae30517083ed388eb38cb3b92cad7 +2026-07-24-tui-shell-prompt-editor.zh.md: ca050e2000ff772389086b5023935c816ec1154e diff --git a/.agents/notes/implemented/feature/2026-07-24-tui-shell-prompt-editor.md b/.agents/notes/archived/feature/2026-07-24-tui-shell-prompt-editor.md similarity index 99% rename from .agents/notes/implemented/feature/2026-07-24-tui-shell-prompt-editor.md rename to .agents/notes/archived/feature/2026-07-24-tui-shell-prompt-editor.md index bba03e788b..a3707d3fcd 100644 --- a/.agents/notes/implemented/feature/2026-07-24-tui-shell-prompt-editor.md +++ b/.agents/notes/archived/feature/2026-07-24-tui-shell-prompt-editor.md @@ -1,6 +1,7 @@ # Agent Note: TUI shell-prompt editor Status: implemented +Archived: 2026-08-04 English | [中文](2026-07-24-tui-shell-prompt-editor.zh.md) diff --git a/.agents/notes/implemented/feature/2026-07-24-tui-shell-prompt-editor.zh.md b/.agents/notes/archived/feature/2026-07-24-tui-shell-prompt-editor.zh.md similarity index 99% rename from .agents/notes/implemented/feature/2026-07-24-tui-shell-prompt-editor.zh.md rename to .agents/notes/archived/feature/2026-07-24-tui-shell-prompt-editor.zh.md index 1897d11292..ca050e2000 100644 --- a/.agents/notes/implemented/feature/2026-07-24-tui-shell-prompt-editor.zh.md +++ b/.agents/notes/archived/feature/2026-07-24-tui-shell-prompt-editor.zh.md @@ -1,6 +1,7 @@ # Agent Note: TUI shell 提示符编辑器 Status: implemented +Archived: 2026-08-04 [English](2026-07-24-tui-shell-prompt-editor.md) | 中文 diff --git a/.agents/notes/archived/feature/2026-07-27-assistant-timing-header-trailing.i18n.yaml b/.agents/notes/archived/feature/2026-07-27-assistant-timing-header-trailing.i18n.yaml new file mode 100644 index 0000000000..2d8d84405a --- /dev/null +++ b/.agents/notes/archived/feature/2026-07-27-assistant-timing-header-trailing.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write .agents/notes/archived/feature/2026-07-27-assistant-timing-header-trailing.md +2026-07-27-assistant-timing-header-trailing.md: 2ef926cff989499aa05ebfa781eea10399c69d18 +2026-07-27-assistant-timing-header-trailing.zh.md: 282ac1e65b3c4e185839d3c6b70a085f685e8013 diff --git a/.agents/notes/implemented/feature/2026-07-27-assistant-timing-header-trailing.md b/.agents/notes/archived/feature/2026-07-27-assistant-timing-header-trailing.md similarity index 98% rename from .agents/notes/implemented/feature/2026-07-27-assistant-timing-header-trailing.md rename to .agents/notes/archived/feature/2026-07-27-assistant-timing-header-trailing.md index a315a0620c..2ef926cff9 100644 --- a/.agents/notes/implemented/feature/2026-07-27-assistant-timing-header-trailing.md +++ b/.agents/notes/archived/feature/2026-07-27-assistant-timing-header-trailing.md @@ -1,6 +1,7 @@ # Agent Note: Assistant timing line renders after the message body Status: implemented +Archived: 2026-08-04 English | [中文](2026-07-27-assistant-timing-header-trailing.zh.md) diff --git a/.agents/notes/implemented/feature/2026-07-27-assistant-timing-header-trailing.zh.md b/.agents/notes/archived/feature/2026-07-27-assistant-timing-header-trailing.zh.md similarity index 98% rename from .agents/notes/implemented/feature/2026-07-27-assistant-timing-header-trailing.zh.md rename to .agents/notes/archived/feature/2026-07-27-assistant-timing-header-trailing.zh.md index 84b8612337..282ac1e65b 100644 --- a/.agents/notes/implemented/feature/2026-07-27-assistant-timing-header-trailing.zh.md +++ b/.agents/notes/archived/feature/2026-07-27-assistant-timing-header-trailing.zh.md @@ -1,6 +1,7 @@ # Agent Note: Assistant timing line renders after the message body Status: implemented +Archived: 2026-08-04 [English](2026-07-27-assistant-timing-header-trailing.md) | 中文 diff --git a/.agents/notes/archived/feature/2026-07-27-tui-running-glyph-smooth-fade.i18n.yaml b/.agents/notes/archived/feature/2026-07-27-tui-running-glyph-smooth-fade.i18n.yaml new file mode 100644 index 0000000000..0ceac7c49a --- /dev/null +++ b/.agents/notes/archived/feature/2026-07-27-tui-running-glyph-smooth-fade.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write .agents/notes/archived/feature/2026-07-27-tui-running-glyph-smooth-fade.md +2026-07-27-tui-running-glyph-smooth-fade.md: 09a944a5e39d407713da5665a3dd32a171a04bc1 +2026-07-27-tui-running-glyph-smooth-fade.zh.md: 5fc6a7e490670ce02d011651741a952cfb97dcce diff --git a/.agents/notes/implemented/feature/2026-07-27-tui-running-glyph-smooth-fade.md b/.agents/notes/archived/feature/2026-07-27-tui-running-glyph-smooth-fade.md similarity index 99% rename from .agents/notes/implemented/feature/2026-07-27-tui-running-glyph-smooth-fade.md rename to .agents/notes/archived/feature/2026-07-27-tui-running-glyph-smooth-fade.md index e4c8fee399..09a944a5e3 100644 --- a/.agents/notes/implemented/feature/2026-07-27-tui-running-glyph-smooth-fade.md +++ b/.agents/notes/archived/feature/2026-07-27-tui-running-glyph-smooth-fade.md @@ -1,6 +1,7 @@ # Agent Note: Dim-gray pulse for the running prompt glyph Status: implemented +Archived: 2026-08-04 English | [中文](2026-07-27-tui-running-glyph-smooth-fade.zh.md) diff --git a/.agents/notes/implemented/feature/2026-07-27-tui-running-glyph-smooth-fade.zh.md b/.agents/notes/archived/feature/2026-07-27-tui-running-glyph-smooth-fade.zh.md similarity index 99% rename from .agents/notes/implemented/feature/2026-07-27-tui-running-glyph-smooth-fade.zh.md rename to .agents/notes/archived/feature/2026-07-27-tui-running-glyph-smooth-fade.zh.md index 25bda3d549..5fc6a7e490 100644 --- a/.agents/notes/implemented/feature/2026-07-27-tui-running-glyph-smooth-fade.zh.md +++ b/.agents/notes/archived/feature/2026-07-27-tui-running-glyph-smooth-fade.zh.md @@ -1,6 +1,7 @@ # Agent Note: Dim-gray pulse for the running prompt glyph Status: implemented +Archived: 2026-08-04 [English](2026-07-27-tui-running-glyph-smooth-fade.md) | 中文 diff --git a/.agents/notes/archived/feature/2026-07-27-tui-tool-card-header.i18n.yaml b/.agents/notes/archived/feature/2026-07-27-tui-tool-card-header.i18n.yaml new file mode 100644 index 0000000000..8653f43d71 --- /dev/null +++ b/.agents/notes/archived/feature/2026-07-27-tui-tool-card-header.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write .agents/notes/archived/feature/2026-07-27-tui-tool-card-header.md +2026-07-27-tui-tool-card-header.md: f054ca378481be477ac2d261423c3e6af2035b2a +2026-07-27-tui-tool-card-header.zh.md: bf3bf39662f8cc04a28d8f5ea411077bb190c59a diff --git a/.agents/notes/implemented/feature/2026-07-27-tui-tool-card-header.md b/.agents/notes/archived/feature/2026-07-27-tui-tool-card-header.md similarity index 93% rename from .agents/notes/implemented/feature/2026-07-27-tui-tool-card-header.md rename to .agents/notes/archived/feature/2026-07-27-tui-tool-card-header.md index 13f5e7fec1..f054ca3784 100644 --- a/.agents/notes/implemented/feature/2026-07-27-tui-tool-card-header.md +++ b/.agents/notes/archived/feature/2026-07-27-tui-tool-card-header.md @@ -1,6 +1,7 @@ # Agent Note: Fixed `Tool / ` header for tool-call cards Status: implemented +Archived: 2026-08-04 English | [中文](2026-07-27-tui-tool-card-header.zh.md) @@ -32,4 +33,4 @@ A tool call now shows its identity in one stable place, and status reads as one ## Testing -`packages/ui/tui/tests/tui.spec.ts` pins the new header (`Tool / `), the dropped diff title, the relocated generic title, and the `· N file(s)` footer. The keyless terminal snapshots under `packages/ui/tui/tests/snapshots/` and `examples/tui-agent/tests/snapshots/` — rendered through the real assembled TUI and a pseudo-terminal — were re-recorded and show the new cards for read, bash (described and undescribed), edit, and the other tools. +`packages/ui/tui/tests/tui.spec.ts` pins the new header (`Tool / `), the dropped diff title, the relocated generic title, and the `· N file(s)` footer. Package semantic snapshots cover the card families in a headless terminal. The deleted application journeys formerly supplied assembled tool executions; a future terminal deployment owns equivalent transcript coverage. diff --git a/.agents/notes/implemented/feature/2026-07-27-tui-tool-card-header.zh.md b/.agents/notes/archived/feature/2026-07-27-tui-tool-card-header.zh.md similarity index 93% rename from .agents/notes/implemented/feature/2026-07-27-tui-tool-card-header.zh.md rename to .agents/notes/archived/feature/2026-07-27-tui-tool-card-header.zh.md index 85f9f1244a..bf3bf39662 100644 --- a/.agents/notes/implemented/feature/2026-07-27-tui-tool-card-header.zh.md +++ b/.agents/notes/archived/feature/2026-07-27-tui-tool-card-header.zh.md @@ -1,6 +1,7 @@ # Agent Note: Fixed `Tool / ` header for tool-call cards Status: implemented +Archived: 2026-08-04 [English](2026-07-27-tui-tool-card-header.md) | 中文 @@ -32,4 +33,4 @@ TUI 曾把每次工具调用渲染为 `{glyph} {title}`,其中 `title` 是 pre ## Testing -`packages/ui/tui/tests/tui.spec.ts` 固定了新表头(`Tool / `)、弃用的 diff 标题、迁移后的 generic 标题以及 `· N file(s)` 页脚。`packages/ui/tui/tests/snapshots/` 与 `examples/tui-agent/tests/snapshots/` 下的无密钥终端快照——经由真实组装的 TUI 与伪终端渲染——已重新录制,展示了 read、bash(有描述与无描述)、edit 及其他工具的新卡片。 +`packages/ui/tui/tests/tui.spec.ts` 固定了新表头(`Tool / `)、弃用的 diff 标题、迁移后的 generic 标题以及 `· N file(s)` 页脚。包级语义快照在无界面终端中覆盖各类卡片。已删除的应用流程此前提供组装后的工具执行;未来的终端部署负责提供等价的 transcript 覆盖。 diff --git a/.agents/notes/implemented/feature/2026-07-28-dsh-guided-skill-session-commands.i18n.yaml b/.agents/notes/archived/feature/2026-07-28-dsh-guided-skill-session-commands.i18n.yaml similarity index 67% rename from .agents/notes/implemented/feature/2026-07-28-dsh-guided-skill-session-commands.i18n.yaml rename to .agents/notes/archived/feature/2026-07-28-dsh-guided-skill-session-commands.i18n.yaml index cd0da77981..8feded0ad4 100644 --- a/.agents/notes/implemented/feature/2026-07-28-dsh-guided-skill-session-commands.i18n.yaml +++ b/.agents/notes/archived/feature/2026-07-28-dsh-guided-skill-session-commands.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-28-dsh-guided-skill-session-commands.md -2026-07-28-dsh-guided-skill-session-commands.md: 8a091f7a03c85b0723d96b4fc546875a4e6c0f95 -2026-07-28-dsh-guided-skill-session-commands.zh.md: 861e6cf6cf07c41fde4f78b0833e3f8eb9508767 +2026-07-28-dsh-guided-skill-session-commands.md: 454d090a55db8987f8e4987aba67deff1b21b1a0 +2026-07-28-dsh-guided-skill-session-commands.zh.md: 64dad4e39c6fd3e3341313c3f8dd2b04947695cf diff --git a/.agents/notes/implemented/feature/2026-07-28-dsh-guided-skill-session-commands.md b/.agents/notes/archived/feature/2026-07-28-dsh-guided-skill-session-commands.md similarity index 99% rename from .agents/notes/implemented/feature/2026-07-28-dsh-guided-skill-session-commands.md rename to .agents/notes/archived/feature/2026-07-28-dsh-guided-skill-session-commands.md index 8a091f7a03..454d090a55 100644 --- a/.agents/notes/implemented/feature/2026-07-28-dsh-guided-skill-session-commands.md +++ b/.agents/notes/archived/feature/2026-07-28-dsh-guided-skill-session-commands.md @@ -1,6 +1,7 @@ # Agent Note: `dsh migrate`/`dsh upgrade` seed the first turn with a skill Status: implemented +Archived: 2026-08-03 English | [中文](2026-07-28-dsh-guided-skill-session-commands.zh.md) diff --git a/.agents/notes/implemented/feature/2026-07-28-dsh-guided-skill-session-commands.zh.md b/.agents/notes/archived/feature/2026-07-28-dsh-guided-skill-session-commands.zh.md similarity index 98% rename from .agents/notes/implemented/feature/2026-07-28-dsh-guided-skill-session-commands.zh.md rename to .agents/notes/archived/feature/2026-07-28-dsh-guided-skill-session-commands.zh.md index 861e6cf6cf..64dad4e39c 100644 --- a/.agents/notes/implemented/feature/2026-07-28-dsh-guided-skill-session-commands.zh.md +++ b/.agents/notes/archived/feature/2026-07-28-dsh-guided-skill-session-commands.zh.md @@ -1,6 +1,7 @@ -# Agent Note:`dsh migrate`/`dsh upgrade` 以 skill 播种首轮 +# Agent Note: `dsh migrate`/`dsh upgrade` 以 skill 播种首轮 Status: implemented +Archived: 2026-08-03 [English](2026-07-28-dsh-guided-skill-session-commands.md) | 中文 diff --git a/.agents/notes/implemented/feature/2026-07-28-dsh-meta-source-workspace.i18n.yaml b/.agents/notes/archived/feature/2026-07-28-dsh-meta-source-workspace.i18n.yaml similarity index 68% rename from .agents/notes/implemented/feature/2026-07-28-dsh-meta-source-workspace.i18n.yaml rename to .agents/notes/archived/feature/2026-07-28-dsh-meta-source-workspace.i18n.yaml index 72c62d1e60..1df1788849 100644 --- a/.agents/notes/implemented/feature/2026-07-28-dsh-meta-source-workspace.i18n.yaml +++ b/.agents/notes/archived/feature/2026-07-28-dsh-meta-source-workspace.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-28-dsh-meta-source-workspace.md -2026-07-28-dsh-meta-source-workspace.md: 95270a276cd5df03ffd2dfb419a33289d7b5b901 -2026-07-28-dsh-meta-source-workspace.zh.md: 645b20705386a3501d026fb58ca224c49cc69a17 +2026-07-28-dsh-meta-source-workspace.md: 1e433bb50ae5cd5cc893e867d0f4b6edce2bf168 +2026-07-28-dsh-meta-source-workspace.zh.md: 95b1edabbbac2e78d09097db614ee4e5d1b33bf7 diff --git a/.agents/notes/implemented/feature/2026-07-28-dsh-meta-source-workspace.md b/.agents/notes/archived/feature/2026-07-28-dsh-meta-source-workspace.md similarity index 99% rename from .agents/notes/implemented/feature/2026-07-28-dsh-meta-source-workspace.md rename to .agents/notes/archived/feature/2026-07-28-dsh-meta-source-workspace.md index 95270a276c..1e433bb50a 100644 --- a/.agents/notes/implemented/feature/2026-07-28-dsh-meta-source-workspace.md +++ b/.agents/notes/archived/feature/2026-07-28-dsh-meta-source-workspace.md @@ -1,6 +1,7 @@ # Agent Note: `dsh meta` boots the TUI over the harness checkout Status: implemented +Archived: 2026-08-03 English | [中文](2026-07-28-dsh-meta-source-workspace.zh.md) diff --git a/.agents/notes/implemented/feature/2026-07-28-dsh-meta-source-workspace.zh.md b/.agents/notes/archived/feature/2026-07-28-dsh-meta-source-workspace.zh.md similarity index 98% rename from .agents/notes/implemented/feature/2026-07-28-dsh-meta-source-workspace.zh.md rename to .agents/notes/archived/feature/2026-07-28-dsh-meta-source-workspace.zh.md index 645b207053..95b1edabbb 100644 --- a/.agents/notes/implemented/feature/2026-07-28-dsh-meta-source-workspace.zh.md +++ b/.agents/notes/archived/feature/2026-07-28-dsh-meta-source-workspace.zh.md @@ -1,6 +1,7 @@ -# Agent Note:`dsh meta` 以 harness 检出为 workspace 启动 TUI +# Agent Note: `dsh meta` 以 harness 检出为 workspace 启动 TUI Status: implemented +Archived: 2026-08-03 [English](2026-07-28-dsh-meta-source-workspace.md) | 中文 diff --git a/.agents/notes/implemented/feature/2026-07-20-windows-tui-support.i18n.yaml b/.agents/notes/archived/feature/2026-07-29-addressable-queue-operations.i18n.yaml similarity index 62% rename from .agents/notes/implemented/feature/2026-07-20-windows-tui-support.i18n.yaml rename to .agents/notes/archived/feature/2026-07-29-addressable-queue-operations.i18n.yaml index 4edd7b7223..88f510a4b0 100644 --- a/.agents/notes/implemented/feature/2026-07-20-windows-tui-support.i18n.yaml +++ b/.agents/notes/archived/feature/2026-07-29-addressable-queue-operations.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -2026-07-20-windows-tui-support.md: 6b728486dd50faac067933ce06f883447aae821f -2026-07-20-windows-tui-support.zh.md: 2b53b05ff6231361d79b4304181dc0e6d8e24e68 +2026-07-29-addressable-queue-operations.md: 258e4e4e50a4c6386a2e8c28402fe32cb8870e1a +2026-07-29-addressable-queue-operations.zh.md: b4370d87892df2e0477c0897b45b4c7a1030978e diff --git a/.agents/notes/archived/feature/2026-07-29-addressable-queue-operations.md b/.agents/notes/archived/feature/2026-07-29-addressable-queue-operations.md new file mode 100644 index 0000000000..258e4e4e50 --- /dev/null +++ b/.agents/notes/archived/feature/2026-07-29-addressable-queue-operations.md @@ -0,0 +1,44 @@ +# Agent Note: Address pending queue occurrences for edit and removal + +Status: implemented +Archived: 2026-07-31 + +English | [中文](2026-07-29-addressable-queue-operations.zh.md) + +## Problem + +The Web queue rendered pending messages but could not edit or delete one row. `MessageId` was insufficient as an address because callers may enqueue the same immutable message more than once. The browser also inferred queue retirement from turn and status events, so a row operation racing with driver claim had no authoritative outcome. + +## Decision + +**Each accepted FIFO occurrence has its own identity.** AgentLoop mints an opaque `InboxItemId` and publishes an `InboxItem` containing that id, the identified `UserMessage`, and its acceptance-time `queued | steering` placement. Reusing one `MessageId` creates distinct inbox identities. Injection bypasses the FIFOs and receives no inbox identity. + +**Mutation ends at driver claim.** `Agent.updateInbox(id, action)` synchronously searches the pending queued FIFO. Edit replaces frozen content while preserving `InboxItemId`, `MessageId`, source, wake policy, and position. Remove emits the occurrence’s terminal discard. Steering and driver-claimed occurrences return `not-found`, so queue operations never rewrite active-turn input or durable history. + +**The live ledger is authoritative.** `agent/inbox/enqueue`, `update`, `dequeue`, and `discard` maintain a Host mirror of queued occurrences. A synchronously re-entrant update or terminal event may reach the mirror before its outer enqueue listener; the mirror retains that unseen outcome for the current dispatch and folds it into the enqueue, so listener registration order cannot publish stale content or a ghost row. The wire sends complete `session/queue` snapshots rather than incremental guesses. Reconnect sends the current baseline, and every queued mutation or terminal event replaces it. The client applies no optimistic edit and never retires a row from durable turn events or status changes. + +**Queue addresses require a live Agent.** `session.updateQueue` queries only the mounted Agent registry and never resumes a cold session: an `InboxItemId` is process-local and cannot name work after restart or disposal. A missing Agent and a driver-claimed occurrence both return `queue-item-not-found`. + +**Web actions address Queue only.** The Host excludes pending steering from `session/queue`; steering retains its existing durable transcript path after consumption. QueueDock hides while empty, renders one pending occurrence directly, and defaults two or more occurrences to a collapsed `" 条排队消息"` header that expands or collapses the complete list. The header exposes `aria-expanded` and `aria-controls`; the expanded list scrolls within a 180px height bound. An active edit or mutation keeps its rows visible, and emptying the queue restores the collapsed default for the next queue. Visible rows expose edit and delete, but no send-now control. The UI derives queue row and mutation types from the runtime `SessionFace` contract rather than importing the connection plugin, so plugin cooperation continues through services and snapshots. Edit is available only when all content blocks are text; the editor cannot silently drop non-text blocks. An editing row exposes only save and cancel, with Enter and Escape as their keyboard equivalents. Delete removes the exact occurrence. + +## Alternatives considered + +**Address rows by `MessageId`.** Rejected because one immutable message may be sent repeatedly; editing or deleting by message identity would affect an ambiguous occurrence. + +**Apply optimistic browser mutations.** Rejected because driver claim and another client can win before the Host action. Waiting for the authoritative snapshot makes the ownership boundary visible and lets `queue-item-not-found` report a real race. + +**Include pending steering in the queue mutation protocol.** Rejected because QueueDock has no steering interaction, and editing or deleting active-turn input would widen this feature beyond its current consumer. A dedicated steering interaction owns that delivery contract. + +**Expose a protocol-only promotion operation.** Rejected because no product interaction reorders Queue. A public operation without a current consumer would add ordering semantics and tests for speculative use. + +**Resume a cold Agent for a queue operation.** Rejected because durable session identity does not preserve the process-local inbox capability. Resuming can only produce `not-found` after creating unrelated live state. + +## Verification + +AgentLoop contract tests hold prompt admission while editing and removing exact queued occurrences, reject mutations of steering occurrences, and verify the resulting independent turn and terminal lifecycle events. Host schema and proxy tests cover queued-only authoritative snapshots, synchronous re-entrant mutation order, reconnect, cold-Agent rejection, typed not-found errors, and the RPC transport. Client runtime and QueueDock tests cover non-optimistic projection, single-row presentation, default multi-row collapse, interaction-forced visibility, reset after emptying, expansion, text-only editing, save and cancel affordances, removal, retirement races, and disabled mixed-content editing. Keyless browser scenarios capture the default collapsed header before expanding the queue and driving its exposed edit and delete actions through the built Web composition and real HTTP/SSE wire. + +## Consequences + +Queued work gains precise row operations without becoming durable session history. Occurrence identity is a live process-local capability and disappears at claim, cancellation, disposal, or restart; reconnect recovers only queued items still held by the live Agent. Editing excludes mixed content until an editor can preserve every block, while pending steering remains outside this operation surface. + +The protocol now carries full queue snapshots on each change. Queues are expected to remain short, so deterministic recovery and multi-client convergence are preferred over an incremental mutation protocol. diff --git a/.agents/notes/archived/feature/2026-07-29-addressable-queue-operations.zh.md b/.agents/notes/archived/feature/2026-07-29-addressable-queue-operations.zh.md new file mode 100644 index 0000000000..b4370d8789 --- /dev/null +++ b/.agents/notes/archived/feature/2026-07-29-addressable-queue-operations.zh.md @@ -0,0 +1,44 @@ +# Agent Note: 为待处理队列项提供编辑与移除操作 + +Status: implemented +Archived: 2026-07-31 + +[English](2026-07-29-addressable-queue-operations.md) | 中文 + +## 问题 + +Web 队列能够渲染待处理消息,但无法编辑或删除其中某一行。`MessageId` 不足以充当寻址标识,因为调用方可以多次将同一条不可变消息加入队列。浏览器还会根据轮次和状态事件推断队列项已退役,因此当行操作与驱动器认领发生竞态时,系统无法给出权威结果。 + +## 决策 + +**每次获准进入 FIFO 的项都有独立标识。** AgentLoop 会铸造不透明的 `InboxItemId`,并发布一个 `InboxItem`,其中包含该 id、已有标识的 `UserMessage`,以及接受时确定的 `queued | steering` 放置方式。复用同一个 `MessageId` 会创建不同的 inbox 标识。注入绕过 FIFO,因此不会获得 inbox 标识。 + +**变更边界止于驱动器认领。** `Agent.updateInbox(id, action)` 会同步搜索待处理的 queued FIFO。编辑会替换已冻结的内容,同时保留 `InboxItemId`、`MessageId`、来源、唤醒策略和位置。移除会发出该次入队项的终态 discard。steering(中途引导)项和已被驱动器认领的项会返回 `not-found`,因此队列操作绝不会改写活动轮次输入或持久历史。 + +**实时账本是权威状态。** `agent/inbox/enqueue`、`update`、`dequeue` 和 `discard` 共同维护 queued 入队项的 Host 镜像。同步可重入的 update 或终态事件可能先于外层 enqueue 监听器到达镜像;镜像会在当前分发期间保留这一尚不可见的结果,并在处理 enqueue 时把它合并进去,因此监听器注册顺序不会导致系统发布陈旧内容或不存在的行。协议发送完整的 `session/queue` 快照,而非增量猜测。重连会发送当前基线,每次 queued 变更或终态事件都会整体替换它。客户端不会进行乐观编辑,也绝不根据持久轮次事件或状态变化退役队列行。 + +**Queue 寻址要求 Agent 存活。** `session.updateQueue` 只查询已挂载的 Agent 注册表,绝不恢复冷会话:`InboxItemId` 属于进程本地标识,无法在重启或资源释放后继续指向工作。Agent 缺失和单次入队项已被驱动器认领这两种情况都返回 `queue-item-not-found`。 + +**Web 操作只面向 Queue。** Host 从 `session/queue` 中排除待处理 steering;steering 消费后仍沿用既有的持久 transcript(文本记录)路径。QueueDock 在队列为空时隐藏,只有一个待处理项时直接渲染该行,存在两个或更多待处理项时则默认收起为可展开或收起完整列表的 `" 条排队消息"` 表头。表头暴露 `aria-expanded` 和 `aria-controls`;展开后的列表以 180px 为高度上限,并可滚动。存在进行中的编辑或变更时,列表行会保持可见;队列清空后,下一次出现队列时会恢复默认收起状态。可见行暴露编辑和删除操作,不提供立即发送控件。UI 从运行时 `SessionFace` 契约派生队列行与变更类型,而不是导入连接插件,因此插件仍通过服务和快照协作。仅当所有内容块都是文本时才提供编辑功能;编辑器不能静默丢弃非文本块。编辑中的行只展示保存和取消操作,对应的键盘操作分别是 Enter 和 Escape。删除会移除对应的精确入队项。 + +## 考虑过的替代方案 + +**通过 `MessageId` 寻址行。** 不予采纳,因为同一条不可变消息可以重复发送;按消息标识编辑或删除会无法确定应操作哪一次入队。 + +**在浏览器中进行乐观变更。** 不予采纳,因为驱动器认领或另一个客户端可能先于 Host 操作完成。等待权威快照可以显式呈现所有权边界,并让 `queue-item-not-found` 报告真实竞态。 + +**将待处理 steering 纳入队列变更协议。** 不予采纳,因为 QueueDock 没有 steering 交互,而编辑或删除活动轮次输入会把此功能扩展到当前消费方之外。应由专用 steering 交互负责该投递契约。 + +**暴露仅协议层的前移操作。** 不予采纳,因为当前没有产品交互会重新排序 Queue。公开一个没有当前消费方的操作,会为了推测性用途引入排序语义和测试。 + +**为队列操作恢复冷 Agent。** 不予采纳,因为持久会话标识不会保留进程本地的 inbox 寻址凭据。恢复只能在创建无关的实时状态后得到 `not-found`。 + +## 验证 + +AgentLoop 契约测试会在编辑和移除精确 queued 入队项时阻塞提示词接纳,拒绝对 steering 入队项的变更,并验证所得独立轮次及终态生命周期事件。Host schema 与代理测试覆盖仅含 queued 项的权威快照、同步可重入变更顺序、重连、拒绝冷 Agent、类型化 not-found 错误和 RPC 传输。客户端运行时和 QueueDock 测试覆盖非乐观投影、单行呈现、多行默认收起、交互期间强制保持可见、清空后重置、展开、仅文本编辑、保存与取消入口、移除、退役竞态,以及禁用混合内容编辑。无密钥浏览器场景会先捕获默认收起的表头,再展开队列,并通过构建后的 Web 组合和真实 HTTP/SSE 协议操作其公开的编辑和删除。 + +## 后果 + +queued 工作获得精确的行操作,但不会因此成为持久会话历史。单次入队标识是进程本地的实时寻址凭据,会在认领、取消、dispose 或重启时消失;重连只能恢复仍由活跃 Agent 持有的 queued 项。编辑会排除混合内容,直至编辑器能够保留每个块;待处理 steering 则不属于此操作接口。 + +现在,协议会在每次变更时携带完整队列快照。队列预期保持较短,因此系统优先选择确定性恢复和多客户端收敛,而非增量变更协议。 diff --git a/.agents/notes/archived/feature/2026-07-29-tui-hidden-mode-assistant-fold.i18n.yaml b/.agents/notes/archived/feature/2026-07-29-tui-hidden-mode-assistant-fold.i18n.yaml new file mode 100644 index 0000000000..4c92c6521f --- /dev/null +++ b/.agents/notes/archived/feature/2026-07-29-tui-hidden-mode-assistant-fold.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write .agents/notes/archived/feature/2026-07-29-tui-hidden-mode-assistant-fold.md +2026-07-29-tui-hidden-mode-assistant-fold.md: 53cd3d812212f8a72c56165c37b806cae58f37f6 +2026-07-29-tui-hidden-mode-assistant-fold.zh.md: cf3644478588bbba955fb6539dd99744ef6eb84c diff --git a/.agents/notes/implemented/feature/2026-07-29-tui-hidden-mode-assistant-fold.md b/.agents/notes/archived/feature/2026-07-29-tui-hidden-mode-assistant-fold.md similarity index 99% rename from .agents/notes/implemented/feature/2026-07-29-tui-hidden-mode-assistant-fold.md rename to .agents/notes/archived/feature/2026-07-29-tui-hidden-mode-assistant-fold.md index e2bae1d466..53cd3d8122 100644 --- a/.agents/notes/implemented/feature/2026-07-29-tui-hidden-mode-assistant-fold.md +++ b/.agents/notes/archived/feature/2026-07-29-tui-hidden-mode-assistant-fold.md @@ -1,6 +1,7 @@ # Agent Note: TUI hidden mode folds a turn's assistant steps into one message Status: implemented +Archived: 2026-08-04 English | [中文](2026-07-29-tui-hidden-mode-assistant-fold.zh.md) diff --git a/.agents/notes/implemented/feature/2026-07-29-tui-hidden-mode-assistant-fold.zh.md b/.agents/notes/archived/feature/2026-07-29-tui-hidden-mode-assistant-fold.zh.md similarity index 99% rename from .agents/notes/implemented/feature/2026-07-29-tui-hidden-mode-assistant-fold.zh.md rename to .agents/notes/archived/feature/2026-07-29-tui-hidden-mode-assistant-fold.zh.md index 583d6099f9..cf36444785 100644 --- a/.agents/notes/implemented/feature/2026-07-29-tui-hidden-mode-assistant-fold.zh.md +++ b/.agents/notes/archived/feature/2026-07-29-tui-hidden-mode-assistant-fold.zh.md @@ -1,6 +1,7 @@ # Agent Note: TUI 隐藏模式把一个轮次的 assistant 步骤折叠为一条消息 Status: implemented +Archived: 2026-08-04 [English](2026-07-29-tui-hidden-mode-assistant-fold.md) | 中文 diff --git a/.agents/notes/archived/feature/2026-07-29-web-message-icon-actions-and-clock.i18n.yaml b/.agents/notes/archived/feature/2026-07-29-web-message-icon-actions-and-clock.i18n.yaml new file mode 100644 index 0000000000..47400cc87e --- /dev/null +++ b/.agents/notes/archived/feature/2026-07-29-web-message-icon-actions-and-clock.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write .agents/notes/archived/feature/2026-07-29-web-message-icon-actions-and-clock.md +2026-07-29-web-message-icon-actions-and-clock.md: a95c7d33a917026c882f17d30264cf9ec743dee5 +2026-07-29-web-message-icon-actions-and-clock.zh.md: b64c14aaa7056e19ccc4d512db3d24714e11a309 diff --git a/.agents/notes/implemented/feature/2026-07-29-web-message-icon-actions-and-clock.md b/.agents/notes/archived/feature/2026-07-29-web-message-icon-actions-and-clock.md similarity index 90% rename from .agents/notes/implemented/feature/2026-07-29-web-message-icon-actions-and-clock.md rename to .agents/notes/archived/feature/2026-07-29-web-message-icon-actions-and-clock.md index f43f7f9c96..a95c7d33a9 100644 --- a/.agents/notes/implemented/feature/2026-07-29-web-message-icon-actions-and-clock.md +++ b/.agents/notes/archived/feature/2026-07-29-web-message-icon-actions-and-clock.md @@ -1,6 +1,7 @@ # Agent Note: Web message IconActions and clocks Status: implemented +Archived: 2026-08-07 English | [中文](2026-07-29-web-message-icon-actions-and-clock.zh.md) @@ -12,6 +13,8 @@ The web chat user bubble already had copy / branch / edit IconActions but no clo **User bubbles prepend a date-aware local clock to the existing IconActions row; the last content-text assistant of each turn appends a copy / branch / clock row with `margin-top: 16px`; both seats stay visible whenever mounted and re-format at the next local midnight.** +The assistant seat is narrowed by the [completed-turn decision](../bug-fix/2026-08-05-turn-tail-actions-require-a-completed-turn.md): only a turn with a `turn/end` grants it, so a turn still producing steps hands the row to nothing. The user seat's branch control is removed outright by the [user-bubble branch removal](../simplification/2026-08-06-user-bubbles-drop-the-branch-action.md); a user row's IconActions are clock and copy. + Both seats format `node.time` through `formatMessageClock`: same calendar day → `HH:mm`, earlier this year → `M月D日 HH:mm`, other years → `YYYY年M月D日 HH:mm`. `useCalendarDay` is a component-local day tick (timeout to the next local midnight) so memoized rows re-render when the calendar day changes without a new framework hook. `MessageItem` places the label before copy (figma `388:20051`). `ChatView` derives turn-tail seqs via `assistantActionsSeqs` and withholds `time` for mid-turn content; `AssistantMarkdown` places the row after branch (figma `43:32997`) only when `streaming` is false, the event time is known, and the node has non-empty text content. Think-only nodes, mid-turn narration, and the streaming tail omit the row. Copy writes joined text blocks. Both message rows pass their event's `seq` to the same fork callback; [Web session fork actions](2026-07-27-web-session-fork-actions.md) define the real mutation contract. Clipboard write and the clock helpers live in `message-chrome.ts`. The assembled surface is pinned by `apps/web/tests/message-actions.e2e.ts` (cold-seeded history + aria golden); aria normalization collapses every clock shape to `{{clock}}`. ## Alternatives considered diff --git a/.agents/notes/archived/feature/2026-07-29-web-message-icon-actions-and-clock.zh.md b/.agents/notes/archived/feature/2026-07-29-web-message-icon-actions-and-clock.zh.md new file mode 100644 index 0000000000..b64c14aaa7 --- /dev/null +++ b/.agents/notes/archived/feature/2026-07-29-web-message-icon-actions-and-clock.zh.md @@ -0,0 +1,36 @@ +# Agent Note: Web 消息 IconActions 与时钟 + +Status: implemented +Archived: 2026-08-07 + +[English](2026-07-29-web-message-icon-actions-and-clock.md) | 中文 + +## 问题 + +Web 聊天的用户气泡已有复制、分支、编辑 IconActions,但没有时钟。已定稿的 assistant 叙述下方完全没有操作栏,尽管 harness 设计稿在回答结束后展示复制、分支、时钟。流式回复不得在逐 token 输出期间闪现该操作栏。经 memo 优化的行在跨午夜时仍保持稳定 props,因此一次性的 `Date.now()` 会让昨日消息一直卡在 `HH:mm`。 + +## 决策 + +**用户气泡在既有 IconActions 行的开头添加感知日期的本地时钟;每个轮次中最后一条带 text 内容的 assistant 在正文下追加带 `margin-top: 16px` 的复制、分支、时钟;两边只要挂载就保持可见,并在下一个本地午夜重新格式化。** + +assistant 一侧的座位由[已完成轮次决策](../bug-fix/2026-08-05-turn-tail-actions-require-a-completed-turn.md)收紧:只有存在 `turn/end` 的轮次才授予该行,仍在产出步骤的轮次不把该行交给任何节点。user 一侧的分支控件被 [user 气泡分支移除决策](../simplification/2026-08-06-user-bubbles-drop-the-branch-action.md)直接移除;user 行的 IconActions 只有时钟与复制。 + +两边都通过 `formatMessageClock` 格式化 `node.time`:同一日历日 → `HH:mm`,同年更早 → `M月D日 HH:mm`,跨年 → `YYYY年M月D日 HH:mm`。`useCalendarDay` 是组件本地的日刻度(定时到下一个本地午夜),因此 memo 行在日历日变化时会重渲染,且不新增框架钩子。`MessageItem` 把标签放在复制之前(figma `388:20051`)。`ChatView` 通过 `assistantActionsSeqs` 推导轮次尾部的 seq,并不为轮次中间的内容传入 `time`;`AssistantMarkdown` 把该行放在分支之后(figma `43:32997`),且仅在 `streaming` 为 false、已知事件时间、且节点含非空 text 内容时渲染。纯 Think 节点、轮次中间的叙述与流式尾部省略该行。复制写入拼接后的 text 块。两种消息行都把自己的事件 `seq` 交给同一个 fork 回调;真实 mutation 契约由 [Web session fork 操作](2026-07-27-web-session-fork-actions.md)定义。剪贴板写入与时钟辅助函数放在 `message-chrome.ts`。组装后的界面由 `apps/web/tests/message-actions.e2e.ts`(冷 seed 历史 + aria golden)钉住;aria 归一化把每种时钟形态折叠为 `{{clock}}`。 + +## 曾考虑的方案 + +**在流式过程中展示 assistant IconActions。** 否决:需求是输出完成后才展示该行;中途 chrome 会闪烁,并诱使复制半截回答。 + +**给每个已定稿 assistant 节点(含纯 Think)都挂 IconActions。** 否决:没有 text 内容时复制没有可写内容,且在每一步/Think 下重复 chrome 会打乱流程;只有内容输出拥有该座位。 + +**给多步骤轮次中的每一条带 text 内容的 assistant 都挂 IconActions。** 否决:轮次中间的叙述(工具调用前的 text)不是已定稿答案;在每一步下重复复制、分支、时钟会打乱流程。只有该轮次中最后一条内容 assistant 拥有该座位。 + +**在具备 hover 能力的指针上用 hover 才揭示操作行。** 否决:行一旦存在就应保持可发现;用 opacity 隐藏容易漏看,且需要父级 hover 选择器重复挂载门控。 + +**由 IconActions 决策同时定义 session fork 语义。** 否决:本笔记只拥有消息 chrome、时钟与挂载门控;边界选择、失败行为和切换语义属于独立的 [Web session fork 操作](2026-07-27-web-session-fork-actions.md),避免展示组件成为 session mutation 的第二正家。 + +**通过 chat store 或 inject 钩子发布日历日。** 否决:日刻度只是展示层本地状态,没有跨入口消费方;组件本地 timeout 符合「行为钩子可拥有不订阅外部源的状态」这一客户端规则。 + +## 后果 + +每个轮次中最后一条已定稿的内容回答在行挂载后立刻暴露复制、分支与事件时钟;轮次中间的内容与纯 Think 节点不带 chrome。用户与 assistant 时钟共用同一套跨天、跨年加宽规则,并在午夜后无需消息变更即可刷新。逐消息分页仍是包 README 中记录的暂缓 footer 功能位。包级测试钉住三种时钟形态、午夜加宽、assistant 仅内容门控、轮次尾部 seq 门控,以及 user/assistant 分支按钮各自传递的事件 `seq`;Web e2e 场景钉住组装后的 IconActions chrome。 diff --git a/.agents/notes/implemented/feature/2026-07-30-compaction-progress-visibility.i18n.yaml b/.agents/notes/archived/feature/2026-07-30-compaction-progress-visibility.i18n.yaml similarity index 67% rename from .agents/notes/implemented/feature/2026-07-30-compaction-progress-visibility.i18n.yaml rename to .agents/notes/archived/feature/2026-07-30-compaction-progress-visibility.i18n.yaml index c922eb5a91..aad3f3c42f 100644 --- a/.agents/notes/implemented/feature/2026-07-30-compaction-progress-visibility.i18n.yaml +++ b/.agents/notes/archived/feature/2026-07-30-compaction-progress-visibility.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-30-compaction-progress-visibility.md -2026-07-30-compaction-progress-visibility.md: b4d95d4bc645924b96eab6a36ee7b8f36b76a2c6 -2026-07-30-compaction-progress-visibility.zh.md: e444fbdfbf1c865a5bb3b6675a5ff318c5cef9e7 +2026-07-30-compaction-progress-visibility.md: e0d44c8616661161f6a99b54e3fe75a75dd5b9ad +2026-07-30-compaction-progress-visibility.zh.md: 5b181da16280393db9da5bc00127e71de1d9341a diff --git a/.agents/notes/implemented/feature/2026-07-30-compaction-progress-visibility.md b/.agents/notes/archived/feature/2026-07-30-compaction-progress-visibility.md similarity index 95% rename from .agents/notes/implemented/feature/2026-07-30-compaction-progress-visibility.md rename to .agents/notes/archived/feature/2026-07-30-compaction-progress-visibility.md index b4d95d4bc6..e0d44c8616 100644 --- a/.agents/notes/implemented/feature/2026-07-30-compaction-progress-visibility.md +++ b/.agents/notes/archived/feature/2026-07-30-compaction-progress-visibility.md @@ -1,6 +1,7 @@ # Agent Note: Live standalone compaction progress in the terminal Status: implemented +Archived: 2026-08-04 English | [中文](2026-07-30-compaction-progress-visibility.zh.md) @@ -46,4 +47,4 @@ Manual compaction has a named elapsed-time display above the prompt while the ag The live cell and timer are additional process-local state, cleared on both bracket close and TUI teardown. This is intentionally not reconstructible presentation state: durable history supplies the successful marker and timing facts, while current-process observation alone supplies liveness. -The package-level TUI tests pin standalone start, elapsed-time refresh, single-indicator presentation, numbered-start exclusion, fade-out, failure warning, idle-status preservation, running-turn precedence, orphaned resume, and timer disposal. The assembled `queued-manual-compact` terminal scenario observes `Context being compacted 1.0s` and `dsh ⊙` while the real summary boundary is held. +The package-level TUI tests pin standalone start, elapsed-time refresh, single-indicator presentation, numbered-start exclusion, fade-out, failure warning, idle-status preservation, running-turn precedence, orphaned resume, and timer disposal. The removed product TUI scenario formerly observed `Context being compacted 1.0s` and `dsh ⊙` across a held real summary boundary; a future terminal deployment owns that assembled journey. diff --git a/.agents/notes/implemented/feature/2026-07-30-compaction-progress-visibility.zh.md b/.agents/notes/archived/feature/2026-07-30-compaction-progress-visibility.zh.md similarity index 96% rename from .agents/notes/implemented/feature/2026-07-30-compaction-progress-visibility.zh.md rename to .agents/notes/archived/feature/2026-07-30-compaction-progress-visibility.zh.md index e444fbdfbf..5b181da162 100644 --- a/.agents/notes/implemented/feature/2026-07-30-compaction-progress-visibility.zh.md +++ b/.agents/notes/archived/feature/2026-07-30-compaction-progress-visibility.zh.md @@ -1,6 +1,7 @@ # Agent Note: 终端中的实时独立压缩进度 Status: implemented +Archived: 2026-08-04 [English](2026-07-30-compaction-progress-visibility.md) | 中文 @@ -46,4 +47,4 @@ TUI 将实时独立的 `compact/start { turn: null }` 与匹配的 `compact/end` 实时状态及其定时器是额外的进程局部状态,在标记对闭合和 TUI 清理这两种情况下都会清除。按设计,这种显示状态不可重建:持久历史提供成功标记与计时事实,只有当前进程的观察才能提供运行中状态。 -包(package)级 TUI 测试固定了以下行为:独立开始事件、已用时间刷新、单指示器呈现、排除带编号的开始事件、淡出、失败警告、保留空闲状态、运行轮次优先级、存在未匹配标记时的恢复,以及定时器释放。组装后的 `queued-manual-compact` 终端场景会在真实摘要边界保持开放期间观察到 `Context being compacted 1.0s` 和 `dsh ⊙`。 +包(package)级 TUI 测试固定了以下行为:独立开始事件、已用时间刷新、单指示器呈现、排除带编号的开始事件、淡出、失败警告、保留空闲状态、运行轮次优先级、存在未匹配标记时的恢复,以及定时器释放。已移除的产品 TUI 场景此前会在真实摘要边界保持开放期间观察到 `Context being compacted 1.0s` 和 `dsh ⊙`;未来的终端部署负责该组装流程。 diff --git a/.agents/notes/archived/feature/2026-07-30-dsh-dump-config.i18n.yaml b/.agents/notes/archived/feature/2026-07-30-dsh-dump-config.i18n.yaml new file mode 100644 index 0000000000..1e8be61bca --- /dev/null +++ b/.agents/notes/archived/feature/2026-07-30-dsh-dump-config.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write .agents/notes/archived/feature/2026-07-30-dsh-dump-config.md +2026-07-30-dsh-dump-config.md: cc16f11d79b536a661d67811c6fd50705f6009e3 +2026-07-30-dsh-dump-config.zh.md: 185a2b8f37cef102b48d4dea1b3ed0a96958d220 diff --git a/.agents/notes/implemented/feature/2026-07-30-dsh-dump-config.md b/.agents/notes/archived/feature/2026-07-30-dsh-dump-config.md similarity index 99% rename from .agents/notes/implemented/feature/2026-07-30-dsh-dump-config.md rename to .agents/notes/archived/feature/2026-07-30-dsh-dump-config.md index bc6504541c..cc16f11d79 100644 --- a/.agents/notes/implemented/feature/2026-07-30-dsh-dump-config.md +++ b/.agents/notes/archived/feature/2026-07-30-dsh-dump-config.md @@ -1,6 +1,7 @@ # Agent Note: dsh --dump-config prints the composed config tree Status: implemented +Archived: 2026-08-07 English | [中文](2026-07-30-dsh-dump-config.zh.md) diff --git a/.agents/notes/implemented/feature/2026-07-30-dsh-dump-config.zh.md b/.agents/notes/archived/feature/2026-07-30-dsh-dump-config.zh.md similarity index 99% rename from .agents/notes/implemented/feature/2026-07-30-dsh-dump-config.zh.md rename to .agents/notes/archived/feature/2026-07-30-dsh-dump-config.zh.md index 5e173305a6..185a2b8f37 100644 --- a/.agents/notes/implemented/feature/2026-07-30-dsh-dump-config.zh.md +++ b/.agents/notes/archived/feature/2026-07-30-dsh-dump-config.zh.md @@ -1,6 +1,7 @@ # Agent Note: dsh --dump-config 打印合成后的配置树 Status: implemented +Archived: 2026-08-07 [English](2026-07-30-dsh-dump-config.md) | 中文 diff --git a/.agents/notes/archived/feature/2026-07-30-tui-details-command.i18n.yaml b/.agents/notes/archived/feature/2026-07-30-tui-details-command.i18n.yaml new file mode 100644 index 0000000000..f3b185bbde --- /dev/null +++ b/.agents/notes/archived/feature/2026-07-30-tui-details-command.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write .agents/notes/archived/feature/2026-07-30-tui-details-command.md +2026-07-30-tui-details-command.md: b17cd493fc0c47d7484714f72f418266cd006353 +2026-07-30-tui-details-command.zh.md: ef2a682db1248dfc97fd6ccaa4260b4b9d1a0861 diff --git a/.agents/notes/implemented/feature/2026-07-30-tui-details-command.md b/.agents/notes/archived/feature/2026-07-30-tui-details-command.md similarity index 99% rename from .agents/notes/implemented/feature/2026-07-30-tui-details-command.md rename to .agents/notes/archived/feature/2026-07-30-tui-details-command.md index fb7c4dfaed..b17cd493fc 100644 --- a/.agents/notes/implemented/feature/2026-07-30-tui-details-command.md +++ b/.agents/notes/archived/feature/2026-07-30-tui-details-command.md @@ -1,6 +1,7 @@ # Agent Note: /details command for transcript detail state Status: implemented +Archived: 2026-08-04 English | [中文](2026-07-30-tui-details-command.zh.md) diff --git a/.agents/notes/implemented/feature/2026-07-30-tui-details-command.zh.md b/.agents/notes/archived/feature/2026-07-30-tui-details-command.zh.md similarity index 99% rename from .agents/notes/implemented/feature/2026-07-30-tui-details-command.zh.md rename to .agents/notes/archived/feature/2026-07-30-tui-details-command.zh.md index 5f9e033311..ef2a682db1 100644 --- a/.agents/notes/implemented/feature/2026-07-30-tui-details-command.zh.md +++ b/.agents/notes/archived/feature/2026-07-30-tui-details-command.zh.md @@ -1,6 +1,7 @@ # Agent Note: 用于 transcript 细节状态的 /details 命令 Status: implemented +Archived: 2026-08-04 [English](2026-07-30-tui-details-command.md) | 中文 diff --git a/.agents/notes/implemented/feature/2026-07-30-versioned-tui-first-run-welcome.i18n.yaml b/.agents/notes/archived/feature/2026-07-30-versioned-tui-first-run-welcome.i18n.yaml similarity index 67% rename from .agents/notes/implemented/feature/2026-07-30-versioned-tui-first-run-welcome.i18n.yaml rename to .agents/notes/archived/feature/2026-07-30-versioned-tui-first-run-welcome.i18n.yaml index 5a414af614..d73372fda8 100644 --- a/.agents/notes/implemented/feature/2026-07-30-versioned-tui-first-run-welcome.i18n.yaml +++ b/.agents/notes/archived/feature/2026-07-30-versioned-tui-first-run-welcome.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-30-versioned-tui-first-run-welcome.md -2026-07-30-versioned-tui-first-run-welcome.md: 5270c239f0bccbf58e68364e195ff2175355a816 -2026-07-30-versioned-tui-first-run-welcome.zh.md: cd132fde5ff0601cef6cd3cd433fdd15dc05f7f0 +2026-07-30-versioned-tui-first-run-welcome.md: c032785a34455e868c2643bc58aafcb0e4916592 +2026-07-30-versioned-tui-first-run-welcome.zh.md: 0f3e684baeaed178ce3d7590590d0086f345e461 diff --git a/.agents/notes/implemented/feature/2026-07-30-versioned-tui-first-run-welcome.md b/.agents/notes/archived/feature/2026-07-30-versioned-tui-first-run-welcome.md similarity index 99% rename from .agents/notes/implemented/feature/2026-07-30-versioned-tui-first-run-welcome.md rename to .agents/notes/archived/feature/2026-07-30-versioned-tui-first-run-welcome.md index 5270c239f0..c032785a34 100644 --- a/.agents/notes/implemented/feature/2026-07-30-versioned-tui-first-run-welcome.md +++ b/.agents/notes/archived/feature/2026-07-30-versioned-tui-first-run-welcome.md @@ -1,6 +1,7 @@ # Agent Note: Versioned TUI first-run welcome Status: implemented +Archived: 2026-08-03 English | [中文](2026-07-30-versioned-tui-first-run-welcome.zh.md) diff --git a/.agents/notes/implemented/feature/2026-07-30-versioned-tui-first-run-welcome.zh.md b/.agents/notes/archived/feature/2026-07-30-versioned-tui-first-run-welcome.zh.md similarity index 99% rename from .agents/notes/implemented/feature/2026-07-30-versioned-tui-first-run-welcome.zh.md rename to .agents/notes/archived/feature/2026-07-30-versioned-tui-first-run-welcome.zh.md index cd132fde5f..0f3e684bae 100644 --- a/.agents/notes/implemented/feature/2026-07-30-versioned-tui-first-run-welcome.zh.md +++ b/.agents/notes/archived/feature/2026-07-30-versioned-tui-first-run-welcome.zh.md @@ -1,6 +1,7 @@ # Agent Note: 版本化 TUI 首次运行欢迎页 Status: implemented +Archived: 2026-08-03 [English](2026-07-30-versioned-tui-first-run-welcome.md) | 中文 diff --git a/.agents/notes/archived/feature/2026-07-30-web-composer-stats-and-input-polish.i18n.yaml b/.agents/notes/archived/feature/2026-07-30-web-composer-stats-and-input-polish.i18n.yaml new file mode 100644 index 0000000000..5105501452 --- /dev/null +++ b/.agents/notes/archived/feature/2026-07-30-web-composer-stats-and-input-polish.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write .agents/notes/archived/feature/2026-07-30-web-composer-stats-and-input-polish.md +2026-07-30-web-composer-stats-and-input-polish.md: 3c80b74c564a1779c69ef525f8d1f194e8915f6b +2026-07-30-web-composer-stats-and-input-polish.zh.md: eabb174e78f3171997b9103650c7fe326793ce1b diff --git a/.agents/notes/implemented/feature/2026-07-30-web-composer-stats-and-input-polish.md b/.agents/notes/archived/feature/2026-07-30-web-composer-stats-and-input-polish.md similarity index 99% rename from .agents/notes/implemented/feature/2026-07-30-web-composer-stats-and-input-polish.md rename to .agents/notes/archived/feature/2026-07-30-web-composer-stats-and-input-polish.md index 78f286cb0e..3c80b74c56 100644 --- a/.agents/notes/implemented/feature/2026-07-30-web-composer-stats-and-input-polish.md +++ b/.agents/notes/archived/feature/2026-07-30-web-composer-stats-and-input-polish.md @@ -1,6 +1,7 @@ # Agent Note: Web composer stats detail and input-zone polish Status: implemented +Archived: 2026-08-07 English | [中文](2026-07-30-web-composer-stats-and-input-polish.zh.md) diff --git a/.agents/notes/implemented/feature/2026-07-30-web-composer-stats-and-input-polish.zh.md b/.agents/notes/archived/feature/2026-07-30-web-composer-stats-and-input-polish.zh.md similarity index 99% rename from .agents/notes/implemented/feature/2026-07-30-web-composer-stats-and-input-polish.zh.md rename to .agents/notes/archived/feature/2026-07-30-web-composer-stats-and-input-polish.zh.md index eeba56d9f3..eabb174e78 100644 --- a/.agents/notes/implemented/feature/2026-07-30-web-composer-stats-and-input-polish.zh.md +++ b/.agents/notes/archived/feature/2026-07-30-web-composer-stats-and-input-polish.zh.md @@ -1,6 +1,7 @@ # Agent Note: Web composer stats detail and input-zone polish Status: implemented +Archived: 2026-08-07 [English](2026-07-30-web-composer-stats-and-input-polish.md) | 中文 diff --git a/.agents/notes/archived/feature/2026-07-30-web-context-injection-disclosure.i18n.yaml b/.agents/notes/archived/feature/2026-07-30-web-context-injection-disclosure.i18n.yaml new file mode 100644 index 0000000000..09f2268a0f --- /dev/null +++ b/.agents/notes/archived/feature/2026-07-30-web-context-injection-disclosure.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write .agents/notes/archived/feature/2026-07-30-web-context-injection-disclosure.md +2026-07-30-web-context-injection-disclosure.md: e9551cacdcd5b3e45ba35eeb76db6c70e5bbe368 +2026-07-30-web-context-injection-disclosure.zh.md: a4937ba880df30b911f7c8a1eceaab7e2bb74026 diff --git a/.agents/notes/implemented/feature/2026-07-30-web-context-injection-disclosure.md b/.agents/notes/archived/feature/2026-07-30-web-context-injection-disclosure.md similarity index 99% rename from .agents/notes/implemented/feature/2026-07-30-web-context-injection-disclosure.md rename to .agents/notes/archived/feature/2026-07-30-web-context-injection-disclosure.md index 84c3259f3f..e9551cacdc 100644 --- a/.agents/notes/implemented/feature/2026-07-30-web-context-injection-disclosure.md +++ b/.agents/notes/archived/feature/2026-07-30-web-context-injection-disclosure.md @@ -1,6 +1,7 @@ # Agent Note: Web context injection disclosure Status: implemented +Archived: 2026-08-07 English | [中文](2026-07-30-web-context-injection-disclosure.zh.md) diff --git a/.agents/notes/implemented/feature/2026-07-30-web-context-injection-disclosure.zh.md b/.agents/notes/archived/feature/2026-07-30-web-context-injection-disclosure.zh.md similarity index 99% rename from .agents/notes/implemented/feature/2026-07-30-web-context-injection-disclosure.zh.md rename to .agents/notes/archived/feature/2026-07-30-web-context-injection-disclosure.zh.md index 4d77e06e27..a4937ba880 100644 --- a/.agents/notes/implemented/feature/2026-07-30-web-context-injection-disclosure.zh.md +++ b/.agents/notes/archived/feature/2026-07-30-web-context-injection-disclosure.zh.md @@ -1,6 +1,7 @@ # Agent Note: Web 上下文注入展开项 Status: implemented +Archived: 2026-08-07 [English](2026-07-30-web-context-injection-disclosure.md) | 中文 diff --git a/.agents/notes/implemented/feature/2026-07-31-experimental-subcommand-gate.i18n.yaml b/.agents/notes/archived/feature/2026-07-31-experimental-subcommand-gate.i18n.yaml similarity index 68% rename from .agents/notes/implemented/feature/2026-07-31-experimental-subcommand-gate.i18n.yaml rename to .agents/notes/archived/feature/2026-07-31-experimental-subcommand-gate.i18n.yaml index 8d925d4eee..5db76248b3 100644 --- a/.agents/notes/implemented/feature/2026-07-31-experimental-subcommand-gate.i18n.yaml +++ b/.agents/notes/archived/feature/2026-07-31-experimental-subcommand-gate.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-31-experimental-subcommand-gate.md -2026-07-31-experimental-subcommand-gate.md: 41447c2d23bc71964f990298de3c48b2fe7ef309 -2026-07-31-experimental-subcommand-gate.zh.md: 35598a61d98ff7490b34d175fc915043f5b5236a +2026-07-31-experimental-subcommand-gate.md: a12c93935805a9ab19d4a15905f90783851eabba +2026-07-31-experimental-subcommand-gate.zh.md: ee05ec2c1c488e9d815bc150135202963f030ae7 diff --git a/.agents/notes/implemented/feature/2026-07-31-experimental-subcommand-gate.md b/.agents/notes/archived/feature/2026-07-31-experimental-subcommand-gate.md similarity index 99% rename from .agents/notes/implemented/feature/2026-07-31-experimental-subcommand-gate.md rename to .agents/notes/archived/feature/2026-07-31-experimental-subcommand-gate.md index 41447c2d23..a12c939358 100644 --- a/.agents/notes/implemented/feature/2026-07-31-experimental-subcommand-gate.md +++ b/.agents/notes/archived/feature/2026-07-31-experimental-subcommand-gate.md @@ -1,6 +1,7 @@ # Agent Note: experimental subcommands gate behind `--experimental` or `DSH_EXPERIMENTAL=1` Status: implemented +Archived: 2026-08-03 English | [中文](2026-07-31-experimental-subcommand-gate.zh.md) diff --git a/.agents/notes/implemented/feature/2026-07-31-experimental-subcommand-gate.zh.md b/.agents/notes/archived/feature/2026-07-31-experimental-subcommand-gate.zh.md similarity index 97% rename from .agents/notes/implemented/feature/2026-07-31-experimental-subcommand-gate.zh.md rename to .agents/notes/archived/feature/2026-07-31-experimental-subcommand-gate.zh.md index 35598a61d9..ee05ec2c1c 100644 --- a/.agents/notes/implemented/feature/2026-07-31-experimental-subcommand-gate.zh.md +++ b/.agents/notes/archived/feature/2026-07-31-experimental-subcommand-gate.zh.md @@ -1,6 +1,7 @@ -# Agent Note:实验性子命令由 `--experimental` 或 `DSH_EXPERIMENTAL=1` 把守 +# Agent Note: 实验性子命令由 `--experimental` 或 `DSH_EXPERIMENTAL=1` 把守 Status: implemented +Archived: 2026-08-03 [English](2026-07-31-experimental-subcommand-gate.md) | 中文 diff --git a/.agents/notes/archived/feature/2026-07-31-hover-card-click-copy.i18n.yaml b/.agents/notes/archived/feature/2026-07-31-hover-card-click-copy.i18n.yaml new file mode 100644 index 0000000000..d0bc2ac45e --- /dev/null +++ b/.agents/notes/archived/feature/2026-07-31-hover-card-click-copy.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write .agents/notes/archived/feature/2026-07-31-hover-card-click-copy.md +2026-07-31-hover-card-click-copy.md: 906f64129ee9ba767859260a3288faada21ea4de +2026-07-31-hover-card-click-copy.zh.md: 0359b2edacde9e048db900d315b6a7befd361075 diff --git a/.agents/notes/implemented/feature/2026-07-31-hover-card-click-copy.md b/.agents/notes/archived/feature/2026-07-31-hover-card-click-copy.md similarity index 99% rename from .agents/notes/implemented/feature/2026-07-31-hover-card-click-copy.md rename to .agents/notes/archived/feature/2026-07-31-hover-card-click-copy.md index c87734fe32..906f64129e 100644 --- a/.agents/notes/implemented/feature/2026-07-31-hover-card-click-copy.md +++ b/.agents/notes/archived/feature/2026-07-31-hover-card-click-copy.md @@ -1,6 +1,7 @@ # Agent Note: Hover cards copy their primary value on activation Status: implemented +Archived: 2026-08-07 English | [中文](2026-07-31-hover-card-click-copy.zh.md) diff --git a/.agents/notes/implemented/feature/2026-07-31-hover-card-click-copy.zh.md b/.agents/notes/archived/feature/2026-07-31-hover-card-click-copy.zh.md similarity index 97% rename from .agents/notes/implemented/feature/2026-07-31-hover-card-click-copy.zh.md rename to .agents/notes/archived/feature/2026-07-31-hover-card-click-copy.zh.md index a57b5238b0..0359b2edac 100644 --- a/.agents/notes/implemented/feature/2026-07-31-hover-card-click-copy.zh.md +++ b/.agents/notes/archived/feature/2026-07-31-hover-card-click-copy.zh.md @@ -1,6 +1,7 @@ -# Agent Note(agent 决策记录):悬浮卡片激活时复制主要值 +# Agent Note: 悬浮卡片激活时复制主要值 Status: implemented +Archived: 2026-08-07 [English](2026-07-31-hover-card-click-copy.md) | 中文 diff --git a/.agents/notes/archived/feature/2026-07-31-web-cards-toolrow.i18n.yaml b/.agents/notes/archived/feature/2026-07-31-web-cards-toolrow.i18n.yaml new file mode 100644 index 0000000000..fcd4878180 --- /dev/null +++ b/.agents/notes/archived/feature/2026-07-31-web-cards-toolrow.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write .agents/notes/archived/feature/2026-07-31-web-cards-toolrow.md +2026-07-31-web-cards-toolrow.md: 9bdf5d4e8917178ec27ea5f5d24af753c0d10eab +2026-07-31-web-cards-toolrow.zh.md: ce473a8a34ba8b1bb022d681244508c56a1084f3 diff --git a/.agents/notes/implemented/feature/2026-07-31-web-cards-toolrow.md b/.agents/notes/archived/feature/2026-07-31-web-cards-toolrow.md similarity index 99% rename from .agents/notes/implemented/feature/2026-07-31-web-cards-toolrow.md rename to .agents/notes/archived/feature/2026-07-31-web-cards-toolrow.md index caa18563a9..9bdf5d4e89 100644 --- a/.agents/notes/implemented/feature/2026-07-31-web-cards-toolrow.md +++ b/.agents/notes/archived/feature/2026-07-31-web-cards-toolrow.md @@ -1,6 +1,7 @@ # Agent Note: Card tool rows collapse through one ToolRow Status: implemented +Archived: 2026-08-07 English | [中文](2026-07-31-web-cards-toolrow.zh.md) diff --git a/.agents/notes/implemented/feature/2026-07-31-web-cards-toolrow.zh.md b/.agents/notes/archived/feature/2026-07-31-web-cards-toolrow.zh.md similarity index 97% rename from .agents/notes/implemented/feature/2026-07-31-web-cards-toolrow.zh.md rename to .agents/notes/archived/feature/2026-07-31-web-cards-toolrow.zh.md index 4e9c429497..ce473a8a34 100644 --- a/.agents/notes/implemented/feature/2026-07-31-web-cards-toolrow.zh.md +++ b/.agents/notes/archived/feature/2026-07-31-web-cards-toolrow.zh.md @@ -1,6 +1,7 @@ -# Agent Note:卡片工具行通过同一个 ToolRow 折叠 +# Agent Note: 卡片工具行通过同一个 ToolRow 折叠 Status: implemented +Archived: 2026-08-07 [English](2026-07-31-web-cards-toolrow.md) | 中文 diff --git a/.agents/notes/archived/manifest.json b/.agents/notes/archived/manifest.json index 1ed77225ae..1adde54c7b 100644 --- a/.agents/notes/archived/manifest.json +++ b/.agents/notes/archived/manifest.json @@ -25,12 +25,24 @@ "architecture/2026-07-05-windows-fs-permissions.i18n.yaml": "sha256:7e61ee9bbd9de4bf3285a6f250d9625bd062e5fb90279dbffd64c820f1f7fe6b", "architecture/2026-07-05-windows-fs-permissions.md": "sha256:03734da511eae3b0736f7cad73d9da76ae2f69f9d5ed09089b0121ccb135a861", "architecture/2026-07-05-windows-fs-permissions.zh.md": "sha256:454848057ea905fe76c88d17264e71e71fb685f08f82088de6976878372865c3", + "architecture/2026-07-22-tui-interactive-extension-service.i18n.yaml": "sha256:1b4822af5c8d642b73e3a0b04fb0a1dea9f50d0147046fbef53f5e49c030fb91", + "architecture/2026-07-22-tui-interactive-extension-service.md": "sha256:ca6b2774f4821e66f7c8397f20fcd34926728ded853fa48cbe451db7a8d2f883", + "architecture/2026-07-22-tui-interactive-extension-service.zh.md": "sha256:5b060c7626ee796c27108be7467a5e4be0677d7525d383336e7ec31ddce5c303", "architecture/2026-07-23-unified-session-query-service.i18n.yaml": "sha256:e8733b6543d9602ec206a087d9e89815f041f60fb57e93bee80e1309b9f03067", "architecture/2026-07-23-unified-session-query-service.md": "sha256:28d003686f29ec5e072e51e73da353575bcdcba5af20fefdfad88340e1ddd32c", "architecture/2026-07-23-unified-session-query-service.zh.md": "sha256:cfbe6525bc3b072fbc6db6bdca7a4d8cb4fc5507b1655bebc6af0589ed29ed31", "architecture/2026-07-24-dsh-commander-argument-adapter.i18n.yaml": "sha256:cf99eda0e58b49630d5f95792459d7095666fafbef61f614165d5cdd031b7118", "architecture/2026-07-24-dsh-commander-argument-adapter.md": "sha256:705654c8a43bcd199f72c21a77d24ca8bfa02447aff1c7f3e4e820be61dcd562", "architecture/2026-07-24-dsh-commander-argument-adapter.zh.md": "sha256:3844f02d7659d18caf5d39e1131ed775c789cbf92dc44b4a446c7d6468aa5d00", + "architecture/2026-07-27-tui-chat-channel-module-split.i18n.yaml": "sha256:7b9dbe8b4a340640610abe7e54fb29492d77a187c176996a53d0e1fc7c8e1945", + "architecture/2026-07-27-tui-chat-channel-module-split.md": "sha256:3e2cd43f306a18b3eaf9bac23e6bdc3a5dbdc7388b7c399ce71e4f71b8f71d2a", + "architecture/2026-07-27-tui-chat-channel-module-split.zh.md": "sha256:d6b84fdcd91a2693b72cf6884b3a0c39e56e571b2b694f630805d894a6ba292f", + "architecture/2026-07-28-consolidated-tui-presentation.i18n.yaml": "sha256:1eb43c420a21b7a3adf0aa5274d9aa597187630a29d7e535c5e266f82e803665", + "architecture/2026-07-28-consolidated-tui-presentation.md": "sha256:e6fa4ea0c9d1d94942ab98de47c554f4e8aa3b639a1cce52113107b1dbb0f4b0", + "architecture/2026-07-28-consolidated-tui-presentation.zh.md": "sha256:01814434482a84ebd7f672eb5c26fc468b568e773452563bf39ba52ad25d054a", + "architecture/2026-07-28-dsh-native-typescript-source-launch.i18n.yaml": "sha256:af071e07bce5d9bc8f3df65fed9dcd9b3779a98c5864badbd530363bda021b55", + "architecture/2026-07-28-dsh-native-typescript-source-launch.md": "sha256:1b56e3454277ace713e2a01c4da538c756c45bf633fd24d7b16443d584afac5d", + "architecture/2026-07-28-dsh-native-typescript-source-launch.zh.md": "sha256:8c0f97472c2c89d2c19ae5cfa68c6e67f32b50960b08b60b46496f78ea6ffad1", "bug-fix/2026-07-20-code-mode-result-card-completeness.i18n.yaml": "sha256:1035dae11d049d32ab09fd7d4f950eceae44bf46ba498b3cfaf3c75102b9fb64", "bug-fix/2026-07-20-code-mode-result-card-completeness.md": "sha256:6ca2c9d4df98be18813ef38b7462db880900b5bcd6944fbcd1b8f2258006b93e", "bug-fix/2026-07-20-code-mode-result-card-completeness.zh.md": "sha256:ed85fa7f935e5f525d566bc37a92014614983e649c75de9a9f244939097a7991", @@ -43,12 +55,45 @@ "bug-fix/2026-07-23-thinking-row-disclosure-target.i18n.yaml": "sha256:fd926967311f30ea4a222e88b845f95d74af75d1e94b24ebef59186593b9ca78", "bug-fix/2026-07-23-thinking-row-disclosure-target.md": "sha256:92815c170972b1b91c3d75dd0c846c070805ec1e99ce368b6aae37b048e19869", "bug-fix/2026-07-23-thinking-row-disclosure-target.zh.md": "sha256:0e09f5f5e14d74214e5157ceb5859c866bab6de701c47e2ce5c450866d75aecf", + "bug-fix/2026-07-23-tui-generic-card-markdown.i18n.yaml": "sha256:51fec8e6d7a998fd6189e70d32a6be293500abc8435b23257449e6f6d15a0053", + "bug-fix/2026-07-23-tui-generic-card-markdown.md": "sha256:7dda1114a392737465837e014059c1049da37330e3069b74f6e2ea34eccbce6e", + "bug-fix/2026-07-23-tui-generic-card-markdown.zh.md": "sha256:5040a1aaa8ff9dddeeb572a628410a79d870a90f84be00bf421e4b63e1974a4b", + "bug-fix/2026-07-24-tui-turn-end-stop-reason-notices.i18n.yaml": "sha256:8ac9e40a4a7ac1f526b5a23656579414322bd947d991cfc02c0be0e1aacf2d68", + "bug-fix/2026-07-24-tui-turn-end-stop-reason-notices.md": "sha256:5a1f6ba4baf25ad412eda3601ee074aeb607388da0375979797797a81eeba9da", + "bug-fix/2026-07-24-tui-turn-end-stop-reason-notices.zh.md": "sha256:a7bbc530b9fc5e31ceb0f72d87edc720a0bd04ce7613b2ca9f9704cd5e7f682e", "bug-fix/2026-07-26-intent-draft-same-tick-echo.i18n.yaml": "sha256:c623947c4fa00e6d4b51792c7972ba09582bbcb7605beb373725c0dd666f2c81", "bug-fix/2026-07-26-intent-draft-same-tick-echo.md": "sha256:fa8b1417b2cdd3deecbf8e55bdddd73dd3a8c6e3486fd399b0b8bdf317e56373", "bug-fix/2026-07-26-intent-draft-same-tick-echo.zh.md": "sha256:00ce72552dbaa11562fbc541343a5d33f9449edabbe6dd354eb879a7d4d530f8", + "bug-fix/2026-07-27-question-composer-rows-do-not-shrink.i18n.yaml": "sha256:9b8fd6c3fc5f6527890d74a70372de90ade6db5fa957246d4bbdc06ee06e072c", + "bug-fix/2026-07-27-question-composer-rows-do-not-shrink.md": "sha256:0411033becc2835ce53cd268c9fa149830274c9f61016514087bea89562cfbb8", + "bug-fix/2026-07-27-question-composer-rows-do-not-shrink.zh.md": "sha256:41f024f8b7a4587a92026b4d36d77879086bc86716b0b28bf2131b85db35ee75", + "bug-fix/2026-07-27-tool-card-single-row-fields-inline.i18n.yaml": "sha256:4b94aded16c60628d22414dce524e8a98a8af4fff298805ee7efc63cae02c90d", + "bug-fix/2026-07-27-tool-card-single-row-fields-inline.md": "sha256:40adcd522a9a2eeacc6f2b0196d1f24888a4f57830b7490a3be3d78c86c4e968", + "bug-fix/2026-07-27-tool-card-single-row-fields-inline.zh.md": "sha256:a79d56c9b781442ee596b47707d1a8c80abcd6466094b01802189c8e55f16da7", "bug-fix/2026-07-27-tui-diff-card-redundant-path-header.i18n.yaml": "sha256:8613a1cfcf4b9c7fafa78a8d8565e2a65ef0335b7b826af9b2bb32097836af55", "bug-fix/2026-07-27-tui-diff-card-redundant-path-header.md": "sha256:1bd344aec5454d2a2d6e1e6a32eff035c4a99c3df409f2624b39fd32e23ee402", "bug-fix/2026-07-27-tui-diff-card-redundant-path-header.zh.md": "sha256:0a1747006efb1a4b67feceb9b627a437a0f023158e90ae86e1fe8aef76485384", + "bug-fix/2026-07-27-tui-step-timing-trails-tool-cards.i18n.yaml": "sha256:280b93ece72662501f65edd58a00cdafb5b5941e4ef1314d7198fab18950cb03", + "bug-fix/2026-07-27-tui-step-timing-trails-tool-cards.md": "sha256:112bdbde16b6023eeb5b8a79cd2a711385e7198d51bbfc0520e9612acaa95c8a", + "bug-fix/2026-07-27-tui-step-timing-trails-tool-cards.zh.md": "sha256:fc4e7f778ea63c4583cf81132c264cf6c4b9cc3e1818778061b0497ff16b8ef6", + "bug-fix/2026-07-28-web-conversation-polish-sweep.i18n.yaml": "sha256:27e60a7d822b201dee65eebc8335da8edd416ee19b9b89c056302bae69c830fd", + "bug-fix/2026-07-28-web-conversation-polish-sweep.md": "sha256:92647f06202f8711107918da9d9947767385a8b6307e772b1e868b0b1cb07412", + "bug-fix/2026-07-28-web-conversation-polish-sweep.zh.md": "sha256:95ccc18f4b35396bdcabee8b8745e75008f6c07f829fd8719bbb35d77ac0fd95", + "bug-fix/2026-07-30-tui-adapter-registration-race.i18n.yaml": "sha256:50b7a32e11591719c249258ecc2ec0f45e58f1a04050d2e53f6e2650f58ba137", + "bug-fix/2026-07-30-tui-adapter-registration-race.md": "sha256:7e17eb1dd8f92e1efb7a18477df277b13580840b473ffe8a5309fc70ec3cfa3e", + "bug-fix/2026-07-30-tui-adapter-registration-race.zh.md": "sha256:efcbd3d82af6a58677efe1a0580edd715945b6a93418fde47badac9c01a29866", + "bug-fix/2026-07-30-web-details-default-closed.i18n.yaml": "sha256:2af5559d727f3e4afdd4946eaf89ac212c81db611db78dbd9bfabb1c4661db17", + "bug-fix/2026-07-30-web-details-default-closed.md": "sha256:27a280a817c8048718bb22927e7d9572cf99ffd0c044631e99e0fd6ea236876f", + "bug-fix/2026-07-30-web-details-default-closed.zh.md": "sha256:e047c7d02cf4b95b0c7f78f4b79af254091294b05cc75e98a8bb860ae2074189", + "bug-fix/2026-07-31-hero-visible-while-blank-session-opens.i18n.yaml": "sha256:42218a762ce0141d3cb43deb6c688d3705cdc4405e03851d486c78f3d25b70ef", + "bug-fix/2026-07-31-hero-visible-while-blank-session-opens.md": "sha256:a40992e89736131f5c487e5357848f14accd06e135dbec9ce242c968a5b11d43", + "bug-fix/2026-07-31-hero-visible-while-blank-session-opens.zh.md": "sha256:e0cc576bc1c196affc9220ddabf15d735c347029c530c56454f0e585979101e1", + "bug-fix/2026-07-31-tui-diff-context-line-accounting.i18n.yaml": "sha256:cd39ae2646fdc6827bf29a63953b5463faa37d5b404ae8cc3c0913c47bc92d0c", + "bug-fix/2026-07-31-tui-diff-context-line-accounting.md": "sha256:57066bccd22c2dc2c3546b363de73d13b55ff8683ee12b17a81ed2bcf536645b", + "bug-fix/2026-07-31-tui-diff-context-line-accounting.zh.md": "sha256:a658d886c5eb203f5f30a6fac70ad18e4a24cf756746254723d8f1d144653c04", + "bug-fix/2026-08-03-tui-long-session-render-costs.i18n.yaml": "sha256:f65f7bf8fc84c7a1f022ee393c8d969c06d9bde8bed3a0206de86fb35b246ac6", + "bug-fix/2026-08-03-tui-long-session-render-costs.md": "sha256:6ecf2ef831f527f361ade18a882d79bc6eccf15cc676d05728e7753f41cde051", + "bug-fix/2026-08-03-tui-long-session-render-costs.zh.md": "sha256:5f44e707b332e13fa06d625212173ea055c1c3c0aee60888435a0ff099ec6037", "feature/2026-06-14-acp-agent-client-protocol.i18n.yaml": "sha256:006795baa43ae962a8d125cc0f1e9f134bc2ee9fb758b6e7669e3fa0126e1918", "feature/2026-06-14-acp-agent-client-protocol.md": "sha256:6828c0af74bb3fb96206ca6b21c0e56a000b50e4744aad4bc2c05092f3a5a31b", "feature/2026-06-14-acp-agent-client-protocol.zh.md": "sha256:ba104e841a1fb84edbd3b6c8119d50445b7785255a7a8d13bb9ac8a2cb4d2e69", @@ -79,9 +124,15 @@ "feature/2026-07-14-time-context-plugin.i18n.yaml": "sha256:670c093817c77e093562e02f43984d42ed44ebcced7c91d09366839e412d05e1", "feature/2026-07-14-time-context-plugin.md": "sha256:618b121da38a8b610bcadaecf121ca823b2c8c13598c012b350c214b82fd238f", "feature/2026-07-14-time-context-plugin.zh.md": "sha256:1e9eee8ba427a6f2ee08c79e2fcb33c0948e67a80758fdf9f8c9f7dff9aea361", + "feature/2026-07-17-dedicated-full-screen-tui-front-door.i18n.yaml": "sha256:c04ec462f846887f349ffeb48aef8febf50f06903e7177ffd7679a694f6c1a57", + "feature/2026-07-17-dedicated-full-screen-tui-front-door.md": "sha256:feb70faaad016965e8cc1bd7339947e48937fb3e8ea1425dada581073396f50c", + "feature/2026-07-17-dedicated-full-screen-tui-front-door.zh.md": "sha256:71e4a4abf01e5fc46f7da60e0a66bca659c1ee3c4ea2c4bc20587844f33920fe", "feature/2026-07-20-tui-startup-slogans.i18n.yaml": "sha256:265d1fd79dae6c785201c81ffe2de3baa9fe9e3b6c0f84aac79c90f4040ced15", "feature/2026-07-20-tui-startup-slogans.md": "sha256:aaaab4b419d35ce24317b7730f15af0029878bf3d17c6f184b05138c2cd44930", "feature/2026-07-20-tui-startup-slogans.zh.md": "sha256:01fba568cd92e9c54857f6dba1a3a5a6a4d0e906f36915d7e64682e67d456708", + "feature/2026-07-20-windows-tui-support.i18n.yaml": "sha256:fa7253a8e20308b216c21d201720a4b7d6b74ccc9a650c0d30081c9e5b6bf04c", + "feature/2026-07-20-windows-tui-support.md": "sha256:abf80ade38ec4d9e558c0fa9b0ecc8877acc18442f4ed945ebc2f4b153d85087", + "feature/2026-07-20-windows-tui-support.zh.md": "sha256:6690a7693b8a4c8ce495c13ae84d9dc81f41c691d217db3152ea0d926dffa0f8", "feature/2026-07-21-dsh-system-prompt-source-path.i18n.yaml": "sha256:22efaf3237425fecbac1b40a444454e0fc244a3c85c2f6a14535de22ea777719", "feature/2026-07-21-dsh-system-prompt-source-path.md": "sha256:5fa554932c62a8bbd5a619581710d7f8b6b65d79ec1e340129cda96d279c5ae3", "feature/2026-07-21-dsh-system-prompt-source-path.zh.md": "sha256:995cd593074881c72510a6af3ba80108bbf986d49508cce9f698c2fcb493fd23", @@ -109,30 +160,108 @@ "feature/2026-07-21-tui-reload-command.i18n.yaml": "sha256:9be416ccd681aed0781fdfd2c44c4821c1e45f2a0deccb1f2b47d46163bde488", "feature/2026-07-21-tui-reload-command.md": "sha256:b8616457822ae87c90062308bc8c0d2badd5f368092ec65847d0d9520b1ac372", "feature/2026-07-21-tui-reload-command.zh.md": "sha256:c24bfcb0df13977a9c11c4d0fe433169e535b5f764995b668430dbb14a8e6b33", + "feature/2026-07-21-tui-resume-command.i18n.yaml": "sha256:50526c2ec1bf5fe4f2f912e70fc8145f6978907f80f9d716ca3bcb17cd028933", + "feature/2026-07-21-tui-resume-command.md": "sha256:821cfee22ff6ed491807ecca492538e2dd18ce4b00e7c09b6f4e8604cb02b97b", + "feature/2026-07-21-tui-resume-command.zh.md": "sha256:7fe8e638df0f1977bb93a9efd973d4f69a19ad48e43dae6b1bc8eb70758a561b", + "feature/2026-07-21-tui-skill-slash-command.i18n.yaml": "sha256:c711fd237649c81705a6bc5b20d7b4585ced3166acbc8cc3c2877d97bb386edf", + "feature/2026-07-21-tui-skill-slash-command.md": "sha256:b2904829540a1801852e072937dc259830e93f0c719590da0a189879aca1d7a6", + "feature/2026-07-21-tui-skill-slash-command.zh.md": "sha256:350ed930218b5c4dfb721ebaceac419f4cb2c73f047c004747ba01535a77cab5", "feature/2026-07-21-tui-steering-queue-badge.i18n.yaml": "sha256:a029da558a6e14e1f13269960b98273ca9af0141579967acfbc19b656775f4a5", "feature/2026-07-21-tui-steering-queue-badge.md": "sha256:9aabd68c8910fdc7e7b05674492ddb8dc9285dd691fe554adcb84026fb846cc8", "feature/2026-07-21-tui-steering-queue-badge.zh.md": "sha256:919fd737866c3700f945751628071dab89eabdbf8f809deab93b9e6fbe2c8c59", "feature/2026-07-21-tui-verbose-status-line.i18n.yaml": "sha256:4371b9a46d713d4180aa5d0b1ecde1ff3cae948380a8f56474c895e6113d7824", "feature/2026-07-21-tui-verbose-status-line.md": "sha256:9dcba19ee725b1593e9413a1da5398c205a258aff2e384acd406bb618e86c7f0", "feature/2026-07-21-tui-verbose-status-line.zh.md": "sha256:203c2abac99cedf7afa2540c925367ba66f00b61b926d1cc86472a603ad2bb07", + "feature/2026-07-22-docked-web-goal-bar.i18n.yaml": "sha256:4fae22f5b921ae37feda632addace14bab8d1578c861228dd1df89a7b579f057", + "feature/2026-07-22-docked-web-goal-bar.md": "sha256:94a4b00afc231eddd0fdcf6a494157d12a12b3ae40e8d732c3c05c6811b1c1f8", + "feature/2026-07-22-docked-web-goal-bar.zh.md": "sha256:90dfa4f855a810bce6d57157049eacd6b0d9aa45e99fc296d9024adae4ebac7a", "feature/2026-07-23-trajectory-step-cell.i18n.yaml": "sha256:fe2e935a0affdef877902a40d9861ef5f55b30f40650469f6a52a4d45a92793f", "feature/2026-07-23-trajectory-step-cell.md": "sha256:185e3b87174cb6d2f2d2271fd2a74b1517d03e8570be602570d027bf6002d106", "feature/2026-07-23-trajectory-step-cell.zh.md": "sha256:51f46be43d2f5c4f78a05ed9aeec92d1f33ac988f45cf24d35528e9c43828ef3", + "feature/2026-07-23-tui-file-reference-autocomplete.i18n.yaml": "sha256:f95d9b37369ca8a0eecb07784759e94b5e0e85b7565c7256008c2f9db0d0c157", + "feature/2026-07-23-tui-file-reference-autocomplete.md": "sha256:5a6fd182d9080d757b4ad565e98233b0f128589cbfa6d741dc76a7cc0f41b5c6", + "feature/2026-07-23-tui-file-reference-autocomplete.zh.md": "sha256:8676fd1f57fd705c25f8c37fbfd91126a85387d5b6261d22470b035723a6ad73", + "feature/2026-07-23-tui-status-prompt-tools.i18n.yaml": "sha256:e8072d6661c91b43d13ef88b69fc49b9a312a7b5cb0b6f0171c0fdafc36b0435", + "feature/2026-07-23-tui-status-prompt-tools.md": "sha256:0dd669c70ac34024b389d76c81dcf4f1d5b747f56b7d6d82587c8c15a421c0a2", + "feature/2026-07-23-tui-status-prompt-tools.zh.md": "sha256:6a488b18e1516887d6073375651fba59c3a266b888f9ca2d4804f6681838059b", + "feature/2026-07-24-configurable-tui-prompt-theme.i18n.yaml": "sha256:694de3851ca1e3de76c4f4fb7f3581ad0df568a99046c905f56d24a54407a5ba", + "feature/2026-07-24-configurable-tui-prompt-theme.md": "sha256:694136b6d9bf7de25c240c373cb268cf798f8617c206d53c1d0ef7443e75adeb", + "feature/2026-07-24-configurable-tui-prompt-theme.zh.md": "sha256:ee083f864bf6915a887b7883d14a6662ff6ecb4e702f4ac0f583d0c8f823bf50", "feature/2026-07-24-new-session-clears-to-empty-state.i18n.yaml": "sha256:978638cbf18bc6dce9fea0817654f41cc307f99004a637b85a63ae2208fe9095", "feature/2026-07-24-new-session-clears-to-empty-state.md": "sha256:b6b71d3883a167056070713e3dffb5046de953bdd218074d17c88e7690e03d83", "feature/2026-07-24-new-session-clears-to-empty-state.zh.md": "sha256:82a80b48337487029acd05a0137d268f0850f46801fa44a0e62733cacd00d5e9", + "feature/2026-07-24-tui-question-dialog-multiline.i18n.yaml": "sha256:b8a90f13f579c17476e94740079ac2e058f2a97ec4d723fe2841398426129858", + "feature/2026-07-24-tui-question-dialog-multiline.md": "sha256:0bf07eb8731cf6928db275f160ba36b07ce93d53873eec2fb6dcaabaa0c57f76", + "feature/2026-07-24-tui-question-dialog-multiline.zh.md": "sha256:85f5dedc794014152792557158b826650b147fe6d439e71ea23c115d2c2c84de", + "feature/2026-07-24-tui-shell-prompt-editor.i18n.yaml": "sha256:f40b5ba2d22e3a52fea2d3d0f3f481ef710764c3ec4379e7c859f52c61434b1b", + "feature/2026-07-24-tui-shell-prompt-editor.md": "sha256:7bbb99108a7dfe219c031f77cafa5bbcfacd1dd05080822fe11e0ca58da4b3f5", + "feature/2026-07-24-tui-shell-prompt-editor.zh.md": "sha256:6e20225724941290bbdc9af86d4f91e1beb93bde5c2d67144f0a32c4abb30e7b", "feature/2026-07-26-code-mode-trajectory-waterfall-spans.i18n.yaml": "sha256:916525fdc3a12061928380fd8f7b81cd9763a7873663aad564843fccab0ccedc", "feature/2026-07-26-code-mode-trajectory-waterfall-spans.md": "sha256:a822963e4c34c9737681d6d70d8167731d4350e66ef7f356684ad096c04fa7ab", "feature/2026-07-26-code-mode-trajectory-waterfall-spans.zh.md": "sha256:ef01163adf1245f75cc8291db70d389314dee43b6bff958a9da49b097531218d", + "feature/2026-07-27-assistant-timing-header-trailing.i18n.yaml": "sha256:e5a8aa9e5194dae6f4369299a64acae2c751d7f85e457e8dec1c14e1dbcee3e9", + "feature/2026-07-27-assistant-timing-header-trailing.md": "sha256:85fac4a712ac5b4d61c224eddede08edb27db2e3718321c094a55034c75ce984", + "feature/2026-07-27-assistant-timing-header-trailing.zh.md": "sha256:260d115d2da429eeac73b7256944e60cb03a93714f5d13b5e219dff316f5a958", + "feature/2026-07-27-tui-running-glyph-smooth-fade.i18n.yaml": "sha256:e440b7f4800f722f1a0f9d089081ac19a7fbf809cb75136566ae363b4aa0aab9", + "feature/2026-07-27-tui-running-glyph-smooth-fade.md": "sha256:cc58dce4788c8478c97ce589e4519cfb1b6a6cc3ec46d263f3038823231e5ae5", + "feature/2026-07-27-tui-running-glyph-smooth-fade.zh.md": "sha256:c1735d5bd4b5e75989a9aead8af29136e7fadc01e79fb8c8cc68601a31fbf94a", + "feature/2026-07-27-tui-tool-card-header.i18n.yaml": "sha256:1ed2c377f6d2c589195a00e84f92e6511b9a0793a2684a75ec3a0ca1f2b98670", + "feature/2026-07-27-tui-tool-card-header.md": "sha256:ebb3d913960cdb0949a753c5811bd7d68a96f64f3b0549cd2ab7e4997b6b2d28", + "feature/2026-07-27-tui-tool-card-header.zh.md": "sha256:402a619dce15534fbf88a59361b693eeb2121584fbb2e7af4e93eeaccaf2d0ea", "feature/2026-07-27-user-message-icon-actions.i18n.yaml": "sha256:b33e480f19ec58c8c60417a6c03999953d463ca54606a5ac80ec528edf57c49b", "feature/2026-07-27-user-message-icon-actions.md": "sha256:b6332e67c6dad0a3fcdb597cec9e4dc32b44ad33665f39c1a50501cf38d3f5ad", "feature/2026-07-27-user-message-icon-actions.zh.md": "sha256:0fc824eac66a18063f7098e1c395c09b580d5a30b96f2b856608c084212c2ac2", + "feature/2026-07-28-dsh-guided-skill-session-commands.i18n.yaml": "sha256:cf56e0ff7f2af7a5b50b27818fddb66a0c5300de98fc5733673ce094cd14bb22", + "feature/2026-07-28-dsh-guided-skill-session-commands.md": "sha256:9234465259f89fbedd5dfc07f26acbc9e48e16ce829cc6ada672c4d597b0b255", + "feature/2026-07-28-dsh-guided-skill-session-commands.zh.md": "sha256:57ee966476f755c1a6832d35d5f045f9d9e63a97a824e8a3723ba914502ade7f", + "feature/2026-07-28-dsh-meta-source-workspace.i18n.yaml": "sha256:f7c6b5db53c32c7475f4f6bb3ae189ed8d67f2163196ab315d6f81fde3aa37d9", + "feature/2026-07-28-dsh-meta-source-workspace.md": "sha256:ee8b2f6055b27957fa27258f26a07183b7102933af68c64d0df418e32d3d8754", + "feature/2026-07-28-dsh-meta-source-workspace.zh.md": "sha256:0b10db368e04c24be03569a56ec4b69fed66b70c39a3c4f168b5f1c912efcd96", + "feature/2026-07-29-addressable-queue-operations.i18n.yaml": "sha256:0a067b38dd3c02ac41148ed03a7a6fa4c3dee88d5a4b9bad325ff76ebc03c443", + "feature/2026-07-29-addressable-queue-operations.md": "sha256:f4d38d6cc49ad23cda2a287ba7ea5ce0e5fdb0edd41f33e68633f439654ca9fa", + "feature/2026-07-29-addressable-queue-operations.zh.md": "sha256:9aedd7e241cf46ec7a78ae999a7fb105d73da4baf57c9ecf7ae745ee9b98182b", + "feature/2026-07-29-tui-hidden-mode-assistant-fold.i18n.yaml": "sha256:0865835802348b730542adbe6b7db613750f3786993c6a14dbb2f47686c13c70", + "feature/2026-07-29-tui-hidden-mode-assistant-fold.md": "sha256:a5fefebd802e2d9c3c79c7852c1c34c7bbef3f2ac2150d224608b9ec44e966ad", + "feature/2026-07-29-tui-hidden-mode-assistant-fold.zh.md": "sha256:21bccd1e07ec8dc73b618f428461848bb90b6235afe0b842afb0afab2d5cc575", + "feature/2026-07-29-web-message-icon-actions-and-clock.i18n.yaml": "sha256:59b09ed3c94f9b706b5ba8b567e264d9a6f4ff396245a8f4435ddfe5f4af3620", + "feature/2026-07-29-web-message-icon-actions-and-clock.md": "sha256:c4f56f6681f7fa5fdef5354cdd1d0d00ae7e77f4ebcfae6015579b8a4e9ad712", + "feature/2026-07-29-web-message-icon-actions-and-clock.zh.md": "sha256:6f8522382f644467ba39c7c0f15583de30a79ac17305cdba94c4195169cb0dc3", + "feature/2026-07-30-compaction-progress-visibility.i18n.yaml": "sha256:4c2267054ad5d73aecc8d39d138a0cb532981b33175252e67252d07c3314b0f5", + "feature/2026-07-30-compaction-progress-visibility.md": "sha256:2dfe07244cd784f27a9e5850801d40e96eae21a20ba10aaf56f9a793cdf5b505", + "feature/2026-07-30-compaction-progress-visibility.zh.md": "sha256:6180b8aff0536147ab6ed6a78ecdbe1448fd12d89407746ecb1c7c05c73d4d60", + "feature/2026-07-30-dsh-dump-config.i18n.yaml": "sha256:b400c8cce902328989e5493301f66451de7a36e966d69c43b20935fc635aca0f", + "feature/2026-07-30-dsh-dump-config.md": "sha256:85b81dd517aaa6bb7510780acd961739c6da223bf2ddf6747d62f7a74e652d1f", + "feature/2026-07-30-dsh-dump-config.zh.md": "sha256:d0d55947bcb0ef53d534844c15928ae26eebe3fb6d43f98ab176ec36a8eac640", + "feature/2026-07-30-tui-details-command.i18n.yaml": "sha256:033cea6df0a16fc68cbdb435babdc6e75c1199a8e70e1a71d87c800c40f5a044", + "feature/2026-07-30-tui-details-command.md": "sha256:a13478d4e55ec6d358209b51b541413ec75d0e20dfc22196ace28020f03f0c2d", + "feature/2026-07-30-tui-details-command.zh.md": "sha256:de9c449b98468cef34ce4f9a9d2a854a5d8905eecd61f80e27a9a0e4495e9901", + "feature/2026-07-30-versioned-tui-first-run-welcome.i18n.yaml": "sha256:4c3fc380b0512ad7c00baacd0ac610e1a78ae45374311d9bd43bab6b5e29e630", + "feature/2026-07-30-versioned-tui-first-run-welcome.md": "sha256:296f153e6c839f3743078e4f5aab3b2befc211c934835238668c57bdeae52231", + "feature/2026-07-30-versioned-tui-first-run-welcome.zh.md": "sha256:82871a9cca1fec46bb08a5b39daad28a44bb2419dea367b4ae41af3cf07bfa65", + "feature/2026-07-30-web-composer-stats-and-input-polish.i18n.yaml": "sha256:eb0f02b1e15cb127618c82871fcea1b3ba4a9a5db670615072f15c71864729ea", + "feature/2026-07-30-web-composer-stats-and-input-polish.md": "sha256:68d0c0486219d8e886db07c4cde2285e515adf9756c1e4bc94e4bbd5cbcc2c93", + "feature/2026-07-30-web-composer-stats-and-input-polish.zh.md": "sha256:679565f7a2e183ac71132bd1cbd9d2418d77fe0e5472224b15bd310dd3931f4b", + "feature/2026-07-30-web-context-injection-disclosure.i18n.yaml": "sha256:83a8b78b0140afc8f18034674b594b998099c162ed9b9d939cb99e49cea2272b", + "feature/2026-07-30-web-context-injection-disclosure.md": "sha256:00f869b29861ff8f30e64ea3ca65aa9f8a06b33be205453ea3b679e5dfe05c4d", + "feature/2026-07-30-web-context-injection-disclosure.zh.md": "sha256:9bca10469e4d77b20c3785ce7ab6cbc628a03b8919de8a47c14466c1dbc94d36", + "feature/2026-07-31-experimental-subcommand-gate.i18n.yaml": "sha256:d223669bebbf6ea65b4ec636e8e7ed618eff389117335946be713897151c6968", + "feature/2026-07-31-experimental-subcommand-gate.md": "sha256:8fdee37340f7e72397cf2f440a2ca70639a987d07f0c2102e02e79c0fec4bfeb", + "feature/2026-07-31-experimental-subcommand-gate.zh.md": "sha256:bcdec0f82319670a1d1de54a27b103b5e2d86306b884a5f9f415b89cd5a373f4", + "feature/2026-07-31-hover-card-click-copy.i18n.yaml": "sha256:2b95987c23e13a4499f5f3851770e8f97aa6f6df457a36b6aa818a8db08785c9", + "feature/2026-07-31-hover-card-click-copy.md": "sha256:f9a85c1603dcbdd36d26f730bf2a1f7bfaaa2267c7c30bee08cb9a94a7ce774e", + "feature/2026-07-31-hover-card-click-copy.zh.md": "sha256:b01e6edda5c6b031b5265ca0d868583fecce04cbc817fa7e8cc4433d10056e64", + "feature/2026-07-31-web-cards-toolrow.i18n.yaml": "sha256:f9a6ab72a77934cdcc02167c7313f08d7e9925362017b34bed7ad56c8c70fbaa", + "feature/2026-07-31-web-cards-toolrow.md": "sha256:5058f7cec4497d1cb0a5c8e77b88fddacac6eead034f3edec88e8514919b8a3e", + "feature/2026-07-31-web-cards-toolrow.zh.md": "sha256:ba84ef2e1be61211ab5ba6950b78ede3d3a979f252bc068d3e04e2c025f7bc03", "process/2026-06-11-doc-sync-enforcement.i18n.yaml": "sha256:33b6d5874427bd7a2bd82e7e2f4f482b12448b2464aef15a9c57975edb48554d", "process/2026-06-11-doc-sync-enforcement.md": "sha256:aa2fe83d519fc30d48dff19e596e83c8922aacc9e063e14fe2cc35b769b9100e", "process/2026-06-11-doc-sync-enforcement.zh.md": "sha256:698017bd35f030fdea3eac51df9e43138c48140f504739d687b7251d13fced2b", "process/2026-06-11-tsdown-over-dumble.i18n.yaml": "sha256:22791adb84a4b6c545173d4f1708eea51151d57e426d875e0e5423be9b6e0212", "process/2026-06-11-tsdown-over-dumble.md": "sha256:8d3c35dddd8869cc3361059dfe4b7b8ab6716d29dda232c97c2f37e92c841dc0", "process/2026-06-11-tsdown-over-dumble.zh.md": "sha256:cf11c651c13f5ffef5474e7795006ba3653c5eb08eae75a879be6499353455dc", + "process/2026-06-20-generated-cordis-catalog.i18n.yaml": "sha256:5250aaec698b25bdf5e3a02f67e531793fc968f9c38348f0c8bd11418571967f", + "process/2026-06-20-generated-cordis-catalog.md": "sha256:1f3190b759bf1445b35f25f2f18ac1c8b16d7f2e9263e2627bf3c94fac54d275", + "process/2026-06-20-generated-cordis-catalog.zh.md": "sha256:5d46da71bd73bba62ba15a9f11b21da422dbecc8ed68b6f530ceb302e1935ddb", "process/2026-07-03-documentation-graph-atlas.i18n.yaml": "sha256:b1e1ed4b7865d87f939dbf8c94c0ea1069fdf7af6fa68f695e6c9d6eccbeb123", "process/2026-07-03-documentation-graph-atlas.md": "sha256:b62e92bb12123bfa4c4dac806f584aabb6b60af4c5a6a4ab88f84bb9153e766d", "process/2026-07-03-documentation-graph-atlas.zh.md": "sha256:3485ede4a5e695643bcf9e744a62f8914cff788ae35717dac5eb6bf77e0d65cf", @@ -232,6 +361,24 @@ "simplification/2026-07-26-consolidate-gate-scripts-on-existing-deps.i18n.yaml": "sha256:7acf002ea8c1533f052c7bfc0c4e3da013ecf43c5872866a3ee4a8c2691c5e33", "simplification/2026-07-26-consolidate-gate-scripts-on-existing-deps.md": "sha256:f18a913096b7defd2192c4bac888a33f68075c3662703a0e28a6146897d17777", "simplification/2026-07-26-consolidate-gate-scripts-on-existing-deps.zh.md": "sha256:ff48a37673c97059536fe5b61aff746133eac682145550badb049eb5c83b097c", + "simplification/2026-07-26-eventsource-parser-for-deepseek-sse.i18n.yaml": "sha256:534abd90ddde9ccd35ab7e595de4242d8fa30a75908a638e5b3290f749553e5a", + "simplification/2026-07-26-eventsource-parser-for-deepseek-sse.md": "sha256:ce449c72ed09238ba5dbe6068689db13bd33225694b2ad2c7696541f32dc0eec", + "simplification/2026-07-26-eventsource-parser-for-deepseek-sse.zh.md": "sha256:2f66b407b626f1f8c661d849b3b359c959e690715e0ac3f61f7e3d57d59e89c3", + "simplification/2026-07-26-turndown-for-tool-web-html-markdown.i18n.yaml": "sha256:6df56f5f5639847f0fac445abb5fea8a07f3cf9a0703d9022e50728c8f5055ca", + "simplification/2026-07-26-turndown-for-tool-web-html-markdown.md": "sha256:344c5cc2a1e79287eeda6996ae417dd2e02a7545987df0f2c9016b20ae094d93", + "simplification/2026-07-26-turndown-for-tool-web-html-markdown.zh.md": "sha256:8c4f2ac12ccd23f7ada90694502f5da689344e6bba72080a89672aa9b4f1903a", + "simplification/2026-07-27-copyable-transcript-no-gutter-bar.i18n.yaml": "sha256:821f96f3e203e03b80553c07b10a511926bb5014be95c7df6bffb30c8e226d31", + "simplification/2026-07-27-copyable-transcript-no-gutter-bar.md": "sha256:4b6aa150bbc8a4da0acac4d20f5fb8c2b77fef7e9c4c4dba8fd8e84dec36d619", + "simplification/2026-07-27-copyable-transcript-no-gutter-bar.zh.md": "sha256:5225e627ff301be171434a5b9f18905fe1578f50eb2d4bf9998e126aba6cc3e3", + "simplification/2026-07-30-sidebar-resize-without-visible-pill.i18n.yaml": "sha256:ad42430fef4a5db610f8c56acfcda79b40396418694f664a5b0fb093bff1f114", + "simplification/2026-07-30-sidebar-resize-without-visible-pill.md": "sha256:6f2cfc5121371ec19c7178b31777c223e16bebdc9b63b7654a61cadc4a765b63", + "simplification/2026-07-30-sidebar-resize-without-visible-pill.zh.md": "sha256:ab859eeb12c6a74da3c37d411af52fce37bed3195941570b2f23ccd9a00d55fe", + "simplification/2026-07-31-web-ui-no-steer-entry-or-interjection-chrome.i18n.yaml": "sha256:531c446f0e95054f8ced17be9a180f8b0a823f7e9d5ce466c94c2f9cff90a111", + "simplification/2026-07-31-web-ui-no-steer-entry-or-interjection-chrome.md": "sha256:a35a6372aabdf7cbc211f1bd5820d85d3467c9ed50f84e05caa3339382379ce7", + "simplification/2026-07-31-web-ui-no-steer-entry-or-interjection-chrome.zh.md": "sha256:a6ed9530289a783c3d7a1ddb038fba6b7daf7feb773298a57e811791e354d438", + "simplification/2026-08-03-explicit-config-dsh-entrypoint.i18n.yaml": "sha256:5466161f3fb8f2e8117fe8ff242675cc9fe9ef264d1e29b9bc586891c73c051a", + "simplification/2026-08-03-explicit-config-dsh-entrypoint.md": "sha256:f23accae7d05c2e75cb73ec69b492307f1ce7526ecfa9f6b12a621e02fd1a0c3", + "simplification/2026-08-03-explicit-config-dsh-entrypoint.zh.md": "sha256:a32d2c6ecf748a16a2c35b59cd2da2fda75769e3ab24be6a2e026d8655466db4", "testing/2026-06-20-remove-redundant-snapshot-log-expected-output.i18n.yaml": "sha256:4177012c0821a8c22499852ecdf096af56d7263cb91c5d9d1bcd552cc26a3e00", "testing/2026-06-20-remove-redundant-snapshot-log-expected-output.md": "sha256:45234e7cc04b6010c6141f8d5924c04547300098f96262d423c50108e7c7011a", "testing/2026-06-20-remove-redundant-snapshot-log-expected-output.zh.md": "sha256:15e5a4ad3dee0bb711480cabe45cd97ec37bbdba19c2c2b47d1e9c203b07a48b", @@ -249,6 +396,12 @@ "testing/2026-07-06-pin-request-header-content-in-one-scenario.zh.md": "sha256:cac75d4475666239bbe0030b90c0fa7cc66024af5b9f8ef217e53018be64890e", "testing/2026-07-08-shared-acp-snapshot-package.i18n.yaml": "sha256:fc37fcdfe8744f8c8f39eda3f494eed25ee8c4d5322d1f3f671eabd2c5d7026e", "testing/2026-07-08-shared-acp-snapshot-package.md": "sha256:285b4a3c0b1ef7a837e6713cf0192ddc8a26101f6737fa3923682a9e91350c50", - "testing/2026-07-08-shared-acp-snapshot-package.zh.md": "sha256:02da3f910c2060f70038a0d86a7ddae4a8890905600440e1373412f54fbdcea8" + "testing/2026-07-08-shared-acp-snapshot-package.zh.md": "sha256:02da3f910c2060f70038a0d86a7ddae4a8890905600440e1373412f54fbdcea8", + "testing/2026-07-18-tui-terminal-state-snapshots.i18n.yaml": "sha256:c1a22174274b9f34ef4368039b3547f221507b040bd51b87af73a2722ee6b4d2", + "testing/2026-07-18-tui-terminal-state-snapshots.md": "sha256:9a7fdcbeafc34376cb049b9668e0f4e9e541f523116fb11c3af9d35c2963e908", + "testing/2026-07-18-tui-terminal-state-snapshots.zh.md": "sha256:26750f240f6c8a7b28746f62fe161b357e9c5dd52867cc7037399f1ed6ff37fa", + "testing/2026-07-26-execa-for-test-subprocess-plumbing.i18n.yaml": "sha256:dd45cddb591b892739b75b0c180bde7f14008f4769227b863571475be295e1e0", + "testing/2026-07-26-execa-for-test-subprocess-plumbing.md": "sha256:1f45a69d0a7367ec5afbf112a77b355339b35270af8ff52696bee879cdf770d3", + "testing/2026-07-26-execa-for-test-subprocess-plumbing.zh.md": "sha256:8a24bdc8376373d7a97f65cefc07078824bf918d6a9934056a025ecfafe8634b" } } diff --git a/.agents/notes/archived/process/2026-06-20-generated-cordis-catalog.i18n.yaml b/.agents/notes/archived/process/2026-06-20-generated-cordis-catalog.i18n.yaml new file mode 100644 index 0000000000..3eb6be2fb1 --- /dev/null +++ b/.agents/notes/archived/process/2026-06-20-generated-cordis-catalog.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write .agents/notes/archived/process/2026-06-20-generated-cordis-catalog.md +2026-06-20-generated-cordis-catalog.md: 8d013a5b0c7e1b8df9f607215384f6c26a83b5b8 +2026-06-20-generated-cordis-catalog.zh.md: 2550bc805db7bea95106d444ecf9b0ad75ef91cc diff --git a/.agents/notes/implemented/process/2026-06-20-generated-cordis-catalog.md b/.agents/notes/archived/process/2026-06-20-generated-cordis-catalog.md similarity index 99% rename from .agents/notes/implemented/process/2026-06-20-generated-cordis-catalog.md rename to .agents/notes/archived/process/2026-06-20-generated-cordis-catalog.md index 5005e50a2e..8d013a5b0c 100644 --- a/.agents/notes/implemented/process/2026-06-20-generated-cordis-catalog.md +++ b/.agents/notes/archived/process/2026-06-20-generated-cordis-catalog.md @@ -1,6 +1,7 @@ # Agent Note: Generated cordis events + services catalog Status: implemented +Archived: 2026-08-07 English | [中文](2026-06-20-generated-cordis-catalog.zh.md) diff --git a/.agents/notes/archived/process/2026-06-20-generated-cordis-catalog.zh.md b/.agents/notes/archived/process/2026-06-20-generated-cordis-catalog.zh.md new file mode 100644 index 0000000000..2550bc805d --- /dev/null +++ b/.agents/notes/archived/process/2026-06-20-generated-cordis-catalog.zh.md @@ -0,0 +1,42 @@ +# Agent Note: 生成的 Cordis 事件与服务目录 + +Status: implemented +Archived: 2026-08-07 + +[English](2026-06-20-generated-cordis-catalog.md) | 中文 + +## 问题 + +插件作者需要两类此前没有任何单一文档能同时提供的参考信息:他们可以监听的每一个 Cordis **事件**(含精确签名与分发模式),以及他们可以调用的每一个 `ctx.` **服务**(含精确接口)。相关信息虽然存在,但散落各处:`docs/architecture.md` 中一张手工维护的事件分类体系*表格*(名称 + 行文描述的 Mode/Purpose,由 `verify-event-taxonomy` 做名称集合校验)、一张服务映射表(8 行角色描述),以及 `interface Events` / `interface Context` 声明本身。分类体系表格还有一个盲区:它无法捕获全新的*未记录*事件——名称集合校验器只检查两侧已有的名称。 + +这是对[核心数据结构目录](../../../../docs/core-data-structures/core.md)([其 Agent Note](2026-06-20-core-data-structures-catalog.md))在接线维度上的补充:前者对循环传递的*数据结构*编目(经验证的手工粘贴),本文则对传递它们的*事件和服务*编目。 + +## 决策 + +从源码生成目录,取代手工维护表格并校验子集的方式。 + +`scripts/gen-cordis-catalog.ts` 使用 TypeScript 编译器 API,根据声明和源码 JSDoc 分别生成事件与服务参考。事件包含分派模式及其原始成员 JSDoc;服务包含公共签名及各方法的原始 JSDoc。确定性的 `--write` 和 `--check` 模式使两个页面成为生成产物,并由 `doc-sync` 强制检查新鲜度。 + +完全通过生成来构建目录在此处是正确的,因为代码库足够规范,AST 包含全部事实:每个事件/服务名称都是字符串字面量,可以往返映射到静态声明——不存在动态命名的事件,也不存在仅运行时的服务。因此生成的文档不可能出错,且从结构上消除了未记录事件的缺口(生成器枚举源码,而非校验手写子集)。 + +具体选择: + +- **`@mode` 标签,交叉校验。** 每个 harness 事件的 JSDoc 携带一个显式的 `@mode emit|waterfall|parallel|serial` 标签;缺少标签时生成器直接报错。当签名形状具有决定性时——尾部参数为 `next: () => …` 在结构上即为 waterfall(瀑布式事件)——生成器断言标签与之一致,矛盾时直接报错。emit/parallel/serial 的区别在结构上不可见(`session/flush` 返回 `Promise | void` 且无 `next`,有序的 `agent/pre-step` 检查点亦然),因此信任标签。编写规则见 [AGENTS.md](../../../../AGENTS.md)。 +- **分层范围。** harness 层(8 个 `@deepseek-ai/dsh-*` 服务及其事件)从源码完整渲染。继承层(cordis-core 的 `ctx.on/emit/effect/provide/…` + `internal/*` 事件 + loader/hmr/timer)是插件同样可见的固定版本的 vendor 源码;它从生成器中一张人工维护的表格简洁渲染(名称 + 一行描述 + 源码位置),而非遍历 vendor AST。原因是 cordis-core 的 `Context` 混合了真正的 ctx 成员与非服务字段(`root`、`baseUrl`、`logger`),且 vendor 接口仅在有意的 vendor 同步时才变化。 +- **指向数据结构目录的交叉链接。** 签名中由仓库拥有的每个类型名(`GenerateOptions`、`StreamChunk`、`ToolDefinition`……)都会通过人工维护的映射链接到其主要核心数据结构页面。AST 遍历采用默认拒绝放行的策略:每个参数、泛型约束/默认值和返回类型引用都必须已映射、是签名自身的类型参数、是点名的 TypeScript/Cordis 基础类型,或带有点名的例外及其非目录文档归属。违规会连同源码位置汇总报告,并点明相应的归属列表。该映射不会复用 `type-equiv.manifest.json`,因为后者记录 `…Map` 符号,而签名引用派生的联合类型名,并且会在多个页面列出某些符号。 +- **专用围栏。** 签名块使用 ` ```ts cordis-catalog ` 信息字符串,并把原始事件或公共方法 JSDoc 直接放在其声明之前。`doc-typecheck` 会识别并跳过这些裸片段,将其排除在 opt-out 比例之外——与 `type-equiv` 块的处理相同。 + +本决策**取代** [doc-sync 强制](../../archived/process/2026-06-11-doc-sync-enforcement.md)中事件分类体系的那一半:`verify-event-taxonomy` 及其 `docs/architecture.md` 表格退役(architecture.md 的标题保留,正文改为指向目录;服务映射的角色表格作为人工行文保留)。doc-typecheck、verify-md-wrap、verify-md-links 和 verify-type-equiv 不受影响。 + +## 曾考虑的替代方案 + +- **校验而非生成(退役的分类体系检查所做的事)**:*仅对本参考面*反转了这一策略。此处的数据可以机械地完整获取,因此生成严格强于对手工表格做名称集合校验(完整签名、不会漂移、能捕获未记录事件)。 +- **遍历 vendor AST 以获取继承层**:否决,改用人工维护表格。cordis-core 的 `Context` 混合了真正的 ctx 成员与非服务字段,且固定的 vendor 接口仅在有意同步时才变化。 +- **复用 `type-equiv.manifest.json` 作为签名交叉链接映射**:否决,改用完整的人工维护常量和默认拒绝放行的覆盖检查。manifest 记录 `…Map` 符号,而签名引用派生的联合类型名,并且会在多个页面列出某些符号。显式映射让每个渲染目标和每个非目录例外都成为可评审的决策。 + +## 后果 + +- 目录不会发生漂移:提交文件未反映的源码变化会使 `doc-sync` 和 CI 中的 `verify-cordis-catalog` 失败。新事件缺少 `@mode` 标签、标签与其签名冲突,或签名类型未分类,都会直接使生成器失败。 +- 事件与服务方法契约只有一个归属——声明处的 JSDoc。目录会在生成的签名块中重复该原始 JSDoc,并使用其描述部分作为条目正文,因此单薄的源码文档只会生成单薄的目录条目。 +- 继承层是手工摘要,因此 vendor 同步若新增或重命名了 cordis-core 事件或 `ctx` 成员,需要同步编辑 `gen-cordis-catalog.ts` 中的人工维护表格。这是不遍历固定版本的 vendor 源码的有意代价;它很少变化,且在生成器中有明确标注。 +- `verify-event-taxonomy.ts` 被删除,`docs/architecture.md` 的事件表格也已移除;之前链接到特定表格行的人现在会落在生成目录上。 diff --git a/.agents/notes/archived/simplification/2026-07-26-eventsource-parser-for-deepseek-sse.i18n.yaml b/.agents/notes/archived/simplification/2026-07-26-eventsource-parser-for-deepseek-sse.i18n.yaml new file mode 100644 index 0000000000..cfb5b17afd --- /dev/null +++ b/.agents/notes/archived/simplification/2026-07-26-eventsource-parser-for-deepseek-sse.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write .agents/notes/archived/simplification/2026-07-26-eventsource-parser-for-deepseek-sse.md +2026-07-26-eventsource-parser-for-deepseek-sse.md: 9e716cf9556c9c2d8cdf6cb85c6908d45a127a0f +2026-07-26-eventsource-parser-for-deepseek-sse.zh.md: 16c63ddc9646f6309654910bd80801bd20005545 diff --git a/.agents/notes/implemented/simplification/2026-07-26-eventsource-parser-for-deepseek-sse.md b/.agents/notes/archived/simplification/2026-07-26-eventsource-parser-for-deepseek-sse.md similarity index 99% rename from .agents/notes/implemented/simplification/2026-07-26-eventsource-parser-for-deepseek-sse.md rename to .agents/notes/archived/simplification/2026-07-26-eventsource-parser-for-deepseek-sse.md index e7835bc738..9e716cf955 100644 --- a/.agents/notes/implemented/simplification/2026-07-26-eventsource-parser-for-deepseek-sse.md +++ b/.agents/notes/archived/simplification/2026-07-26-eventsource-parser-for-deepseek-sse.md @@ -1,6 +1,7 @@ # Agent Note: Replace the hand-rolled SSE parser in llm-deepseek with eventsource-parser Status: implemented +Archived: 2026-08-07 English | [中文](2026-07-26-eventsource-parser-for-deepseek-sse.zh.md) diff --git a/.agents/notes/implemented/simplification/2026-07-26-eventsource-parser-for-deepseek-sse.zh.md b/.agents/notes/archived/simplification/2026-07-26-eventsource-parser-for-deepseek-sse.zh.md similarity index 95% rename from .agents/notes/implemented/simplification/2026-07-26-eventsource-parser-for-deepseek-sse.zh.md rename to .agents/notes/archived/simplification/2026-07-26-eventsource-parser-for-deepseek-sse.zh.md index 933b993d47..16c63ddc96 100644 --- a/.agents/notes/implemented/simplification/2026-07-26-eventsource-parser-for-deepseek-sse.zh.md +++ b/.agents/notes/archived/simplification/2026-07-26-eventsource-parser-for-deepseek-sse.zh.md @@ -1,6 +1,7 @@ # Agent Note: 用 eventsource-parser 替换 llm-deepseek 中手写的 SSE 解析器 Status: implemented +Archived: 2026-08-07 [English](2026-07-26-eventsource-parser-for-deepseek-sse.md) | 中文 @@ -12,7 +13,7 @@ Status: implemented ## 决策 -`sse.ts` 将 SSE 分帧委托给 `eventsource-parser/stream` 的 `EventSourceParserStream`:`parseSse` 把响应 body 依次管道接入 `new TextDecoderStream()` 和 `new EventSourceParserStream()`,只保留 DeepSeek 协议垫层——逐个产出事件的 `data`,遇到 `[DONE]` 终止,流在未见哨兵时结束则抛出 `LlmError('STREAM_CLOSED')`。所需的全部内置能力(`TextDecoderStream`、`pipeThrough`、可异步迭代的 `ReadableStream`)在 Node ^22.19 引擎下限即已存在。规范符合性测试已删除;`tests/sse.spec.ts` 只固定 `[DONE]`/`STREAM_CLOSED`/EOF 契约。`eventsource-parser` 是 `llm-deepseek` 继 schemastery 之后的第二个运行时依赖。曾把该适配器标为「手写 fetch + SSE 解析」的[孪生适配器 Agent Note(agent 决策记录)](../architecture/2026-06-13-twin-llm-adapters.md)与 `dsh-llm` JSDoc,现在将其描述为直接 fetch 加库分帧的 SSE。 +`sse.ts` 将 SSE 分帧委托给 `eventsource-parser/stream` 的 `EventSourceParserStream`:`parseSse` 把响应 body 依次管道接入 `new TextDecoderStream()` 和 `new EventSourceParserStream()`,只保留 DeepSeek 协议垫层——逐个产出事件的 `data`,遇到 `[DONE]` 终止,流在未见哨兵时结束则抛出 `LlmError('STREAM_CLOSED')`。所需的全部内置能力(`TextDecoderStream`、`pipeThrough`、可异步迭代的 `ReadableStream`)在 Node ^22.19 引擎下限即已存在。规范符合性测试已删除;`tests/sse.spec.ts` 只固定 `[DONE]`/`STREAM_CLOSED`/EOF 契约。`eventsource-parser` 是 `llm-deepseek` 继 schemastery 之后的第二个运行时依赖。曾把该适配器标为「手写 fetch + SSE 解析」的[孪生适配器 Agent Note](../architecture/2026-06-13-twin-llm-adapters.md)与 `dsh-llm` JSDoc,现在将其描述为直接 fetch 加库分帧的 SSE。 该库还会剥离开头的 BOM(手写解析器在 BOM 之后会无法匹配 `data:`),并提供手写解析器缺少的 `maxBufferSize` 加固能力。 diff --git a/.agents/notes/archived/simplification/2026-07-26-turndown-for-tool-web-html-markdown.i18n.yaml b/.agents/notes/archived/simplification/2026-07-26-turndown-for-tool-web-html-markdown.i18n.yaml new file mode 100644 index 0000000000..f79936b9fa --- /dev/null +++ b/.agents/notes/archived/simplification/2026-07-26-turndown-for-tool-web-html-markdown.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write .agents/notes/archived/simplification/2026-07-26-turndown-for-tool-web-html-markdown.md +2026-07-26-turndown-for-tool-web-html-markdown.md: 46c4eba12c782146aa32df245c5f69567723935a +2026-07-26-turndown-for-tool-web-html-markdown.zh.md: 077ea89c54c63e41bec2aabd15e744b7b8a764da diff --git a/.agents/notes/implemented/simplification/2026-07-26-turndown-for-tool-web-html-markdown.md b/.agents/notes/archived/simplification/2026-07-26-turndown-for-tool-web-html-markdown.md similarity index 99% rename from .agents/notes/implemented/simplification/2026-07-26-turndown-for-tool-web-html-markdown.md rename to .agents/notes/archived/simplification/2026-07-26-turndown-for-tool-web-html-markdown.md index 0e387021e3..46c4eba12c 100644 --- a/.agents/notes/implemented/simplification/2026-07-26-turndown-for-tool-web-html-markdown.md +++ b/.agents/notes/archived/simplification/2026-07-26-turndown-for-tool-web-html-markdown.md @@ -1,6 +1,7 @@ # Agent Note: Replace tool-web's regex HTML-to-markdown converter with turndown Status: implemented +Archived: 2026-08-07 English | [中文](2026-07-26-turndown-for-tool-web-html-markdown.zh.md) diff --git a/.agents/notes/implemented/simplification/2026-07-26-turndown-for-tool-web-html-markdown.zh.md b/.agents/notes/archived/simplification/2026-07-26-turndown-for-tool-web-html-markdown.zh.md similarity index 90% rename from .agents/notes/implemented/simplification/2026-07-26-turndown-for-tool-web-html-markdown.zh.md rename to .agents/notes/archived/simplification/2026-07-26-turndown-for-tool-web-html-markdown.zh.md index 44e7d08c1d..077ea89c54 100644 --- a/.agents/notes/implemented/simplification/2026-07-26-turndown-for-tool-web-html-markdown.zh.md +++ b/.agents/notes/archived/simplification/2026-07-26-turndown-for-tool-web-html-markdown.zh.md @@ -1,12 +1,13 @@ # Agent Note: 用 turndown 替换 tool-web 的正则 HTML 转 markdown 转换器 Status: implemented +Archived: 2026-08-07 [English](2026-07-26-turndown-for-tool-web-html-markdown.md) | 中文 ## 问题 -`dsh-tool-web` 的 `src/html.ts`(约 86 行,另有约 40 行专属测试;已由本变更删除)曾用正则表达式把抓取到的 HTML 转成 markdown:剥离 script、style、noscript 标签与注释,转换 ``/``/`
  • `,解码数字实体外加一张 12 项的命名实体表,并折叠空白。该模块自身的 JSDoc 写明「A richer converter can replace it without changing the seam or tool schema」,README 的 Known Limitations 章节也把它记载为「a minimal regex converter, not an HTML parser — tables, images, and nested formatting are lost」。[web 能力 seam 决策记录](../architecture/2026-06-24-web-capability-seam.md)把 HTML 转 markdown 作为呈现职责划归本包(package),因此替换点恰好就在这里。每个抓取到的 HTML 页面上,该转换器的输出都对模型可见;此前没有任何无密钥快照执行到 `web_fetch`,因此没有预期输出固定它的行为。 +`dsh-tool-web` 的 `src/html.ts`(约 86 行,另有约 40 行专属测试;已由本变更删除)曾用正则表达式把抓取到的 HTML 转成 markdown:剥离 script、style、noscript 标签与注释,转换 ``/``/`
  • `,解码数字实体外加一张 12 项的命名实体表,并折叠空白。该模块自身的 JSDoc 写明「A richer converter can replace it without changing the seam or tool schema」,README 的 Known Limitations 章节也把它记载为「a minimal regex converter, not an HTML parser — tables, images, and nested formatting are lost」。[web 能力 seam 决策记录](../architecture/2026-06-24-web-capability-seam.md)把 HTML 转 markdown 作为呈现职责划归本包,因此替换点恰好就在这里。每个抓取到的 HTML 页面上,该转换器的输出都对模型可见;此前没有任何无密钥快照执行到 `web_fetch`,因此没有预期输出固定它的行为。 ## 决策 @@ -16,7 +17,7 @@ Status: implemented ## 快照覆盖 -此前缺失的无密钥 `web_fetch` 快照随本变更以 acp-agent 场景 `web-fetch` 落地:`examples/acp-agent/web.cordis.yml` 组合了 web seam、真实的 `dsh-web-fetch-local` 提供方、`search: false` 的 `tool-web`,以及 `web-fetch-fixture-server.mjs`——一个固定端口(抓取的 URL 是录制 transcript(文本记录)的一部分)上的回环 HTTP fixture,提供包含命名实体、GFM 表格与嵌套格式的确定性 HTML。录制与无密钥回放都驱动真实的 HTTP 抓取与转换;固定住的工具结果就是 turndown 的输出,该场景同时固定 `web` header 类(`web_fetch` 的 schema 与指引)。 +此前缺失的无密钥 `web_fetch` 快照随本变更以 acp-agent 场景 `web-fetch` 落地:`examples/acp-agent/web.cordis.yml` 组合了 web seam、真实的 `dsh-web-fetch-local` 提供方、`search: false` 的 `tool-web`,以及 `web-fetch-fixture-server.mjs`——一个固定端口(抓取的 URL 是录制 transcript(文本记录)的一部分)上的回环 HTTP fixture(测试前置数据),提供包含命名实体、GFM 表格与嵌套格式的确定性 HTML。录制与无密钥回放都驱动真实的 HTTP 抓取与转换;固定住的工具结果就是 turndown 的输出,该场景同时固定 `web` header 类(`web_fetch` 的 schema 与指引)。 ## 曾考虑的替代方案 diff --git a/.agents/notes/archived/simplification/2026-07-27-copyable-transcript-no-gutter-bar.i18n.yaml b/.agents/notes/archived/simplification/2026-07-27-copyable-transcript-no-gutter-bar.i18n.yaml new file mode 100644 index 0000000000..c7ce910e5f --- /dev/null +++ b/.agents/notes/archived/simplification/2026-07-27-copyable-transcript-no-gutter-bar.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write .agents/notes/archived/simplification/2026-07-27-copyable-transcript-no-gutter-bar.md +2026-07-27-copyable-transcript-no-gutter-bar.md: a4eca191d28a834b05a6839997aab602852912c0 +2026-07-27-copyable-transcript-no-gutter-bar.zh.md: b1f661cb76bb879e414a0dcfd08fc9349ae070c7 diff --git a/.agents/notes/implemented/simplification/2026-07-27-copyable-transcript-no-gutter-bar.md b/.agents/notes/archived/simplification/2026-07-27-copyable-transcript-no-gutter-bar.md similarity index 99% rename from .agents/notes/implemented/simplification/2026-07-27-copyable-transcript-no-gutter-bar.md rename to .agents/notes/archived/simplification/2026-07-27-copyable-transcript-no-gutter-bar.md index 659b7d2f2f..a4eca191d2 100644 --- a/.agents/notes/implemented/simplification/2026-07-27-copyable-transcript-no-gutter-bar.md +++ b/.agents/notes/archived/simplification/2026-07-27-copyable-transcript-no-gutter-bar.md @@ -1,6 +1,7 @@ # Agent Note: Copyable TUI transcript without gutter bars Status: implemented +Archived: 2026-08-04 English | [中文](2026-07-27-copyable-transcript-no-gutter-bar.zh.md) diff --git a/.agents/notes/implemented/simplification/2026-07-27-copyable-transcript-no-gutter-bar.zh.md b/.agents/notes/archived/simplification/2026-07-27-copyable-transcript-no-gutter-bar.zh.md similarity index 99% rename from .agents/notes/implemented/simplification/2026-07-27-copyable-transcript-no-gutter-bar.zh.md rename to .agents/notes/archived/simplification/2026-07-27-copyable-transcript-no-gutter-bar.zh.md index 5c43169ba3..b1f661cb76 100644 --- a/.agents/notes/implemented/simplification/2026-07-27-copyable-transcript-no-gutter-bar.zh.md +++ b/.agents/notes/archived/simplification/2026-07-27-copyable-transcript-no-gutter-bar.zh.md @@ -1,6 +1,7 @@ # Agent Note: 无 gutter bar 的可复制 TUI transcript Status: implemented +Archived: 2026-08-04 [English](2026-07-27-copyable-transcript-no-gutter-bar.md) | 中文 diff --git a/.agents/notes/archived/simplification/2026-07-30-sidebar-resize-without-visible-pill.i18n.yaml b/.agents/notes/archived/simplification/2026-07-30-sidebar-resize-without-visible-pill.i18n.yaml new file mode 100644 index 0000000000..4f211e5ed8 --- /dev/null +++ b/.agents/notes/archived/simplification/2026-07-30-sidebar-resize-without-visible-pill.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write .agents/notes/archived/simplification/2026-07-30-sidebar-resize-without-visible-pill.md +2026-07-30-sidebar-resize-without-visible-pill.md: 50bf43564675540df2db8e88530a82177f551407 +2026-07-30-sidebar-resize-without-visible-pill.zh.md: 41a33e039aaa29813d4232e5a6d36141b55ce947 diff --git a/.agents/notes/implemented/simplification/2026-07-30-sidebar-resize-without-visible-pill.md b/.agents/notes/archived/simplification/2026-07-30-sidebar-resize-without-visible-pill.md similarity index 98% rename from .agents/notes/implemented/simplification/2026-07-30-sidebar-resize-without-visible-pill.md rename to .agents/notes/archived/simplification/2026-07-30-sidebar-resize-without-visible-pill.md index cc41898990..50bf435646 100644 --- a/.agents/notes/implemented/simplification/2026-07-30-sidebar-resize-without-visible-pill.md +++ b/.agents/notes/archived/simplification/2026-07-30-sidebar-resize-without-visible-pill.md @@ -1,6 +1,7 @@ # Agent Note: Sidebar resize without a visible pill Status: implemented +Archived: 2026-08-07 English | [中文](2026-07-30-sidebar-resize-without-visible-pill.zh.md) diff --git a/.agents/notes/implemented/simplification/2026-07-30-sidebar-resize-without-visible-pill.zh.md b/.agents/notes/archived/simplification/2026-07-30-sidebar-resize-without-visible-pill.zh.md similarity index 98% rename from .agents/notes/implemented/simplification/2026-07-30-sidebar-resize-without-visible-pill.zh.md rename to .agents/notes/archived/simplification/2026-07-30-sidebar-resize-without-visible-pill.zh.md index 9f1f521df2..41a33e039a 100644 --- a/.agents/notes/implemented/simplification/2026-07-30-sidebar-resize-without-visible-pill.zh.md +++ b/.agents/notes/archived/simplification/2026-07-30-sidebar-resize-without-visible-pill.zh.md @@ -1,6 +1,7 @@ # Agent Note: 侧边栏缩放不显示胶囊 Status: implemented +Archived: 2026-08-07 [English](2026-07-30-sidebar-resize-without-visible-pill.md) | 中文 diff --git a/.agents/notes/archived/simplification/2026-07-31-web-ui-no-steer-entry-or-interjection-chrome.i18n.yaml b/.agents/notes/archived/simplification/2026-07-31-web-ui-no-steer-entry-or-interjection-chrome.i18n.yaml new file mode 100644 index 0000000000..32c335c431 --- /dev/null +++ b/.agents/notes/archived/simplification/2026-07-31-web-ui-no-steer-entry-or-interjection-chrome.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write .agents/notes/archived/simplification/2026-07-31-web-ui-no-steer-entry-or-interjection-chrome.md +2026-07-31-web-ui-no-steer-entry-or-interjection-chrome.md: 8ef2b7deb103f2e2a9147b4b50c7d39936ed2381 +2026-07-31-web-ui-no-steer-entry-or-interjection-chrome.zh.md: 875e44a06e1cebf4f2b1731909c479b2f06fb06a diff --git a/.agents/notes/archived/simplification/2026-07-31-web-ui-no-steer-entry-or-interjection-chrome.md b/.agents/notes/archived/simplification/2026-07-31-web-ui-no-steer-entry-or-interjection-chrome.md new file mode 100644 index 0000000000..8ef2b7deb1 --- /dev/null +++ b/.agents/notes/archived/simplification/2026-07-31-web-ui-no-steer-entry-or-interjection-chrome.md @@ -0,0 +1,42 @@ +# Agent Note: Web UI drops steer entry and interjection chrome + +Status: implemented +Archived: 2026-08-07 + +English | [中文](2026-07-31-web-ui-no-steer-entry-or-interjection-chrome.zh.md) + +## Problem + +Mid-turn steering is a host/agent-loop capability (`mode:'steer'`, a durable `user/message`). The Web product already locked the composer while a turn runs and never shipped a queue/steer menu, yet the client still threaded `'queue' | 'steer'` through the input machine, `conversation.send`, and locale keys, and rendered consumed steering as a badged 「插话」/「Interjection」 bubble. That left a half-built UI surface: an unused submit mode, a product label for a gesture users cannot perform, and e2e goldens that pinned chrome the product does not own. + +## Decision + +Keep host and runtime steering intact. Remove only the Web UI entry and chrome: + +- `InputMachine` / `SessionInput` / `InputActions.submit` / hub `defaultSink` are queue-only; they always call `session.prompt(..., 'queue')`. +- `ConversationService.send(text)` drops its mode argument and always queues. +- Durable steer content renders as a plain right-aligned bubble (no badge, no user IconActions) so external/host steers stay visible on replay. +- Delete `message.steering` locale strings and the unused badge CSS. +- The web steering e2e still POSTs `mode:'steer'` over `/api/session.prompt` and asserts durable + model-visible obedience; it no longer expects interjection chrome. Update [web input machine note](../architecture/2026-07-25-web-input-machine-and-slash-pipeline.md) fact lines to match. + +## Alternatives considered + +**Delete host steering entirely.** Out of scope; the user asked only for Web UI display and entry. Agent-loop drain, session events, and the wire mode remain load-bearing for ACP/TUI/automation. + +**Hide durable steer `user/message` content from the transcript.** Would lie on replay when an external client steers; rejected in favor of a plain bubble. + +**Keep the mode parameter but only ever pass `'queue'`.** Leaves dead API surface and tests that invent `'steer'` paths the composer cannot reach. + +## Consequences + +- **Superseded in part.** Decision bullets 1 and 3 through 5 no longer describe master: composer steering shipped later, and the [context-source and steer marks decision](../feature/2026-08-04-web-context-source-and-steer-marks.md) owns its caption. The current facts follow. +- Host steering ownership is unchanged: agent-loop drain, session events, and the wire mode remain load-bearing for ACP, automation, and non-Web clients. +- `ConversationService.send(text)` still takes no mode and always queues; the composer's Steer gesture uses `session.prompt(mode: 'steer')` instead. +- Durable steer `user/message` content still folds into the transcript, so an externally submitted steer stays truthful on replay. It now carries the interjection caption instead of rendering as a bare bubble. +- Non-user next-step items (`agent.inject` context: approval notices, task completion, attached snapshots) broadcast with the `context` placement and never render as pending steering bubbles; they stay invisible until claimed as durable `user/message` context cards. + +## Testing + +- `packages/client/ui-conversation` unit/jsdom coverage: input machine enter/sink, ConversationService routing, the MessageItem steering arm, InputBar submit. +- `apps/web/tests/steering.e2e.ts` keyless replay plus its goldens, which pin the caption. +- `packages/host/apiproxy` `session/queue` projection test asserts user-origin next-step items stay `steering` while plugin-origin items land as `context`. diff --git a/.agents/notes/archived/simplification/2026-07-31-web-ui-no-steer-entry-or-interjection-chrome.zh.md b/.agents/notes/archived/simplification/2026-07-31-web-ui-no-steer-entry-or-interjection-chrome.zh.md new file mode 100644 index 0000000000..875e44a06e --- /dev/null +++ b/.agents/notes/archived/simplification/2026-07-31-web-ui-no-steer-entry-or-interjection-chrome.zh.md @@ -0,0 +1,42 @@ +# Agent Note: Web UI 去掉 steer 入口与插话 chrome + +Status: implemented +Archived: 2026-08-07 + +[English](2026-07-31-web-ui-no-steer-entry-or-interjection-chrome.md) | 中文 + +## 问题 + +中途 steering 是 host/agent-loop 能力(`mode:'steer'`、持久 `user/message`)。Web 产品已在 turn 运行中锁定 composer,且从未交付排队/steer 菜单,但客户端仍把 `'queue' | 'steer'` 穿进 input machine、`conversation.send` 与 locale 键,并把已消费的 steering 渲染成带「插话」/「Interjection」徽章的气泡。这留下半成品 UI:用不到的提交 mode、用户做不到的手势却有产品文案,以及把产品并不拥有的 chrome 钉死在 e2e golden 上。 + +## 决策 + +保留 host 与 runtime 的 steering。只去掉 Web UI 入口与 chrome: + +- `InputMachine`/`SessionInput`/`InputActions.submit`/hub `defaultSink` 仅 queue;始终调用 `session.prompt(..., 'queue')`。 +- `ConversationService.send(text)` 去掉 mode 参数,始终排队。 +- 持久 steer 内容渲染为右对齐普通气泡(无徽章、无用户 IconActions),以便外部/host steer 在回放时仍可见。 +- 删除 `message.steering` locale 字符串与未使用的徽章 CSS。 +- web steering e2e 仍通过 `/api/session.prompt` POST `mode:'steer'`,并断言持久化与模型可见服从;不再期望插话 chrome。同步更新 [web input machine note](../architecture/2026-07-25-web-input-machine-and-slash-pipeline.md) 中的事实行。 + +## 曾考虑的替代方案 + +**整段删除 host steering。** 超出范围;用户只要求清 Web UI 展示与入口。agent-loop 排空、session 事件与线缆 mode 对 ACP/TUI/自动化仍是承重能力。 + +**在 transcript 中隐藏持久 steer `user/message` 内容。** 外部客户端 steer 时回放会失真,因此改为普通气泡。 + +**保留 mode 参数但永远只传 `'queue'`。** 留下死 API 面与只会虚构 composer 到不了的 `'steer'` 路径的测试。 + +## 后果 + +- **部分被取代。** 决策中的第 1 条和第 3 至 5 条已经不再描述 master:composer steering 后来已经交付,[上下文来源与 steer 标识决策](../feature/2026-08-04-web-context-source-and-steer-marks.md)负责定义其标注。下面列出当前事实。 +- host 侧 steering 的归属未变:agent-loop 排空、session 事件与线缆 mode 对 ACP、自动化和非 Web 客户端仍然必要。 +- `ConversationService.send(text)` 仍然不接 mode,始终排队;composer 的 Steer 手势改走 `session.prompt(mode: 'steer')`。 +- 持久 steer `user/message` 内容仍然折叠进 transcript,因此外部提交的 steer 会如实出现在回放中。它现在带有插话标注,而不是无标识气泡。 +- 非用户来源的 next-step 项(`agent.inject` 上下文:审批通知、任务完成、附加快照)以 `context` placement 广播,绝不渲染为待处理 steering 气泡;领取为持久 `user/message` context card 前保持不可见。 + +## 测试 + +- `packages/client/ui-conversation` unit/jsdom 覆盖:input machine enter/sink、ConversationService 路由、MessageItem steering 分支、InputBar submit。 +- `apps/web/tests/steering.e2e.ts` 无密钥回放及其黄金基线,后者会检查插话标注。 +- `packages/host/apiproxy` 的 `session/queue` 投影测试断言用户来源的 next-step 项保持 `steering`,而插件来源的项落入 `context`。 diff --git a/.agents/notes/archived/simplification/2026-08-03-explicit-config-dsh-entrypoint.i18n.yaml b/.agents/notes/archived/simplification/2026-08-03-explicit-config-dsh-entrypoint.i18n.yaml new file mode 100644 index 0000000000..b699495f93 --- /dev/null +++ b/.agents/notes/archived/simplification/2026-08-03-explicit-config-dsh-entrypoint.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write .agents/notes/implemented/simplification/2026-08-03-explicit-config-dsh-entrypoint.md +2026-08-03-explicit-config-dsh-entrypoint.md: 4474e786b3a99ff0ee81ac54fcb6eb5aaff5ee04 +2026-08-03-explicit-config-dsh-entrypoint.zh.md: 11b7b27c7560aaa43a9fdcfb12a9a17f9433e619 diff --git a/.agents/notes/archived/simplification/2026-08-03-explicit-config-dsh-entrypoint.md b/.agents/notes/archived/simplification/2026-08-03-explicit-config-dsh-entrypoint.md new file mode 100644 index 0000000000..4474e786b3 --- /dev/null +++ b/.agents/notes/archived/simplification/2026-08-03-explicit-config-dsh-entrypoint.md @@ -0,0 +1,46 @@ +# Agent Note: Explicit-config dsh entrypoint + +Status: implemented +Archived: 2026-08-08 + +English | [中文](2026-08-03-explicit-config-dsh-entrypoint.zh.md) + +## Problem + +Bare `dsh` selected a product TUI implicitly. That made one command own terminal lifecycle, session identity and resume handoff, onboarding, source-workspace shortcuts, guided upgrade sessions, personal config watching, and a large app-level PTY and transcript snapshot suite. The default also hid the actual composition boundary: `--config` was an optional third layer over a TUI overlay rather than the deployment definition a raw launcher needs. + +The shared base is intentionally neutral: it provides capabilities but creates no startup agent or interaction front door. A neutral base paired with an implicit application made raw config composition less explicit and kept product policy in the CLI rather than in the caller-selected overlay. + +## Decision + +Raw executable use is `dsh --config `. The named file must be an Include patch list and is applied directly over `apps/cli/config/base.cordis.yml` at the same include level. It is required for boot, is not a complete replacement tree, and does not inherit `apps/cli/config/web.cordis.yml` or `$DSH_HOME/config.yaml`. Relative paths resolve from the invoking directory. Boot errors fail loud; SIGINT and SIGTERM dispose the root before exit. + +The raw diagnostic forms remain boot-free: `dsh --dump-default-config` prints the base, while `dsh --config --dump-config` prints base plus the required overlay. The dump uses the Include implementation's patch algorithm and YAML dialect. + +The CLI no longer ships a TUI application. Its TUI overlay, launcher, first-run onboarding assets, app-level TUI fixtures, PTY harness, terminal journeys, and snapshots are deleted. The `meta` and `upgrade` subcommands, their experimental gate, default-surface resume, and full-tree `--config-replace` path are deleted with that application. The installer builds and launches Web without an interface selector. + +`dsh web` retains the shared base plus Web overlay and personal-or-explicit user layer. `dsh -p` retains the one-shot Web/headless composition. The reusable TUI package initially remained after this entrypoint change, then [the package-wide removal decision](2026-08-04-remove-tui-package.md) deleted it and its SDK interface. + +This decision supersedes the `dsh`-specific parts of the [dedicated TUI front door](../../archived/feature/2026-07-17-dedicated-full-screen-tui-front-door.md), [personal config](../feature/2026-07-20-dsh-cli-personal-config.md), [guided skill commands](../../archived/feature/2026-07-28-dsh-guided-skill-session-commands.md), [meta workspace](../../archived/feature/2026-07-28-dsh-meta-source-workspace.md), [shared config overlays](2026-07-29-shared-base-config-overlays.md), [config dump](../../archived/feature/2026-07-30-dsh-dump-config.md), [first-run welcome](../../archived/feature/2026-07-30-versioned-tui-first-run-welcome.md), and [experimental subcommand gate](../../archived/feature/2026-07-31-experimental-subcommand-gate.md) notes. The later [package-wide removal decision](2026-08-04-remove-tui-package.md) supersedes their reusable-package decisions and consolidates the deleted launcher-identity record. + +## Verification + +Parser tests require `--config` for raw boot and reject the removed command names and incompatible option combinations. Built-bin acceptance runs the published JavaScript entry without tsx, checks base-only and base-plus-overlay dumps, and drives an invalid raw provider overlay to prove a boot failure settles and exits rather than hanging. Source-launch compatibility checks the same required-config diagnostic through `bin/dsh`. No `apps/cli` TUI demo or test remains. + +## Alternatives considered + +**Keep bare `dsh` as a TUI and add an explicit config subcommand.** Rejected because the CLI would still own two unrelated application policies and retain the TUI-only launcher, onboarding, and test infrastructure. + +**Allow bare `dsh` to boot the neutral base.** Rejected because the base creates no agent or interaction front door. A process that settles successfully but has no usable entry point hides a missing deployment decision. + +**Keep `--config-replace` for complete trees.** Rejected because raw execution now has one composition contract: a required overlay over the product base. Complete-tree deployments can use the generic Cordis loader or a dedicated application bin without adding a second meaning to `dsh --config`. + +**Delete the TUI package with the product entrypoint.** Initially rejected because removing one shipped application did not by itself require removing a reusable UI implementation. Once no shipped composition or independent consumer remained, [the package-wide removal decision](2026-08-04-remove-tui-package.md) accepted this alternative. + +## Consequences + +Invoking `dsh` without a mode or raw config is a usage error. Existing TUI startup, `meta`, `upgrade`, resume, and full-tree replacement invocations stop working without compatibility aliases. This is acceptable under the pre-release compatibility stance and keeps the supported grammar small. + +Raw deployments must state their agent and front-door rows in an overlay, which makes the application boundary reviewable and keeps base updates available underneath. They do not receive personal config implicitly; deployments that want that policy must compose it themselves. Web remains the installed interactive product surface, while headless and automation entries remain separate. + +Reintroducing a shipped terminal application requires a concrete product need, a named entry mode rather than an implicit raw default, and its own current snapshot and lifecycle acceptance surface. diff --git a/.agents/notes/archived/simplification/2026-08-03-explicit-config-dsh-entrypoint.zh.md b/.agents/notes/archived/simplification/2026-08-03-explicit-config-dsh-entrypoint.zh.md new file mode 100644 index 0000000000..11b7b27c75 --- /dev/null +++ b/.agents/notes/archived/simplification/2026-08-03-explicit-config-dsh-entrypoint.zh.md @@ -0,0 +1,46 @@ +# Agent Note: 显式配置的 dsh 入口 + +Status: implemented +Archived: 2026-08-08 + +[English](2026-08-03-explicit-config-dsh-entrypoint.md) | 中文 + +## 问题 + +裸 `dsh` 会隐式选择产品 TUI。这使一条命令负责终端生命周期、会话身份与恢复移交、onboarding、源码 workspace 快捷入口、引导式升级会话、个人配置监听,以及一整套规模庞大的应用级 PTY 和 transcript(文本记录)快照测试。该默认行为还隐藏了真实的组合边界:`--config` 是 TUI overlay 之上的可选第三层,而不是 raw 启动器所需的部署定义。 + +共享 base 有意保持中性:它提供各项能力,但不会创建启动 agent(智能体)或交互入口。将中性 base 与隐式应用配对,使 raw 配置组合缺乏明确边界,也使产品政策留在 CLI(命令行界面)中,而不是由调用方选定的 overlay 持有。 + +## 决策 + +raw 执行方式为 `dsh --config `。指定文件必须是一份 Include 补丁列表,并在同一 include 层级直接应用到 `apps/cli/config/base.cordis.yml` 之上。启动时必须提供该文件;它不是完整的替换配置树,也不会继承 `apps/cli/config/web.cordis.yml` 或 `$DSH_HOME/config.yaml`。相对路径从调用目录解析。启动错误会明确报错;SIGINT 和 SIGTERM 会先对根上下文执行 dispose(资源释放),再退出。 + +raw 诊断形式仍然无需启动:`dsh --dump-default-config` 打印 base,`dsh --config --dump-config` 则打印 base 与必需 overlay 的合成结果。转储过程使用 Include 实现的补丁算法和 YAML 方言。 + +CLI 不再交付 TUI 应用。TUI overlay、启动器、首次运行 onboarding 资产、应用级 TUI fixture(测试前置数据)、PTY harness、终端流程和快照均已删除。`meta` 与 `upgrade` 子命令、对应的实验功能门禁、默认 surface 恢复入口,以及整棵配置树的 `--config-replace` 路径也随该应用一并删除。安装器不再提供界面选择器,只构建并启动 Web。 + +`dsh web` 保留共享 base、Web overlay 与个人或显式用户层。`dsh -p` 保留一次性 Web/headless 组合。可复用 TUI 包(package)在本入口变更后起初保留,随后[全包移除决策](2026-08-04-remove-tui-package.md)将其及 SDK 接口删除。 + +本决策取代以下记录中专用于 `dsh` 的部分:[独立 TUI 入口](../../archived/feature/2026-07-17-dedicated-full-screen-tui-front-door.md)、[个人配置](../feature/2026-07-20-dsh-cli-personal-config.md)、[引导式 skill 命令](../../archived/feature/2026-07-28-dsh-guided-skill-session-commands.md)、[meta workspace](../../archived/feature/2026-07-28-dsh-meta-source-workspace.md)、[共享配置 overlay](2026-07-29-shared-base-config-overlays.md)、[配置转储](../../archived/feature/2026-07-30-dsh-dump-config.md)、[首次运行欢迎页](../../archived/feature/2026-07-30-versioned-tui-first-run-welcome.md)和[实验性子命令门禁](../../archived/feature/2026-07-31-experimental-subcommand-gate.md)。后续的[全包移除决策](2026-08-04-remove-tui-package.md)取代了其中关于可复用包的决策,并整合了已删除的启动器身份记录。 + +## 验证 + +解析器测试要求 raw 启动提供 `--config`,并拒绝已删除的命令名和不兼容的选项组合。构建后二进制验收测试在不使用 tsx 的情况下运行已发布的 JavaScript 入口,检查仅含 base 及 base 加 overlay 的转储,并传入无效的 raw 提供方 overlay,以证明启动失败能够结束并退出,而不会挂起。源码启动兼容性测试通过 `bin/dsh` 检查同一条缺少必需配置的诊断。`apps/cli` 不再包含任何 TUI demo 或测试。 + +## 曾考虑的替代方案 + +**保留裸 `dsh` 作为 TUI,并新增显式配置子命令。** 不予采纳,因为 CLI 仍需持有两套互不相关的应用政策,并保留仅供 TUI 使用的启动器、onboarding 和测试基础设施。 + +**允许裸 `dsh` 启动中性 base。** 不予采纳,因为 base 不会创建 agent 或交互入口。进程成功结束启动但没有可用入口,会掩盖缺失的部署决策。 + +**保留 `--config-replace` 以支持完整配置树。** 不予采纳,因为 raw 执行现在只有一份组合契约:在产品 base 之上施加一份必需的 overlay。完整配置树部署可以使用通用 Cordis loader 或专用应用二进制文件,无需为 `dsh --config` 增加第二种含义。 + +**随产品入口一并删除 TUI 包。** 最初不予采纳,因为仅移除一项已交付应用本身并不要求移除可复用 UI 实现。当已交付组合与独立消费方均不复存在后,[全包移除决策](2026-08-04-remove-tui-package.md)采纳了这一方案。 + +## 后果 + +调用 `dsh` 时如果既不指定模式,也不提供 raw 配置,将产生用法错误。既有的 TUI 启动、`meta`、`upgrade`、恢复和整棵配置树替换调用会停止工作,且不提供兼容别名。根据发布前兼容性立场,这是可以接受的,并能使支持的命令语法保持精简。 + +raw 部署必须在 overlay 中声明 agent 和入口配置项,使应用边界可供评审,并能继续吸收底层 base 的更新。它们不会隐式接收个人配置;需要该政策的部署必须自行组合。Web 仍是安装后提供的交互式产品 surface,headless 与自动化入口仍保持独立。 + +重新引入已交付的终端应用,需要有具体产品需求,采用具名入口模式而非隐式 raw 默认值,并建立自身当前有效的快照与生命周期验收面。 diff --git a/.agents/notes/archived/testing/2026-07-18-tui-terminal-state-snapshots.i18n.yaml b/.agents/notes/archived/testing/2026-07-18-tui-terminal-state-snapshots.i18n.yaml new file mode 100644 index 0000000000..4d5f9581c3 --- /dev/null +++ b/.agents/notes/archived/testing/2026-07-18-tui-terminal-state-snapshots.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write .agents/notes/archived/testing/2026-07-18-tui-terminal-state-snapshots.md +2026-07-18-tui-terminal-state-snapshots.md: eef9777c1f3d19c03985c0d105223960dd7d4878 +2026-07-18-tui-terminal-state-snapshots.zh.md: 50d2e1b81762538a08abda5608a7d26f2dd0b841 diff --git a/.agents/notes/implemented/testing/2026-07-18-tui-terminal-state-snapshots.md b/.agents/notes/archived/testing/2026-07-18-tui-terminal-state-snapshots.md similarity index 55% rename from .agents/notes/implemented/testing/2026-07-18-tui-terminal-state-snapshots.md rename to .agents/notes/archived/testing/2026-07-18-tui-terminal-state-snapshots.md index b8e6f77d96..eef9777c1f 100644 --- a/.agents/notes/implemented/testing/2026-07-18-tui-terminal-state-snapshots.md +++ b/.agents/notes/archived/testing/2026-07-18-tui-terminal-state-snapshots.md @@ -1,6 +1,7 @@ # Agent Note: Snapshot semantic terminal state for the TUI Status: implemented +Archived: 2026-08-04 English | [中文](2026-07-18-tui-terminal-state-snapshots.zh.md) @@ -10,26 +11,24 @@ The TUI is a stateful renderer. Its user-visible result depends on ANSI parsing, Component-line snapshots stop before ANSI reaches a terminal and miss cursor movement, clearing, styling, overlay composition, and reflow. Raster screenshots include font and platform rendering noise that is unrelated to the TUI contract. A completed flow built by directly appending plausible session events has another blind spot: it proves the renderer accepts those shapes, not that the production agent loop and tool implementations produce them. -The TUI therefore needs a deterministic, reviewable representation of terminal state, recorded model journeys that execute the real downstream stack, and a smaller test at the real process and PTY boundary. +The reusable TUI therefore needs a deterministic, reviewable representation of terminal state. A product deployment that ships it additionally needs recorded model journeys through the assembled stack and a smaller test at the real process and PTY boundary. ## Decision -TUI coverage has four complementary layers: +Reusable TUI coverage has two complementary package layers: 1. `packages/ui/tui/tests/tui.spec.ts` tests event mapping, input routing, disposal, and error behavior directly. 2. `packages/ui/tui/tests/tui.snapshot.ts` mounts the production TUI against a headless terminal emulator for transient states that a completed session log cannot retain: in-flight streaming, pending tool calls, overlays, expansion, compaction reflow, errors, and shutdown. -3. `examples/tui-agent/tests/tui.snapshot.ts` replays committed JSONL session logs through the production agent loop and real tools, then compares the resulting semantic terminal state. -4. `examples/tui-agent/tests/tui-keyless-smoke.e2e.ts` boots the real Loader composition in a PTY, drives a scripted conversation through streaming and `ask_user_question`, and verifies startup, input, exit, failure reporting, and terminal restoration. -The runnable TUI is the shipped `apps/cli` composition: the shared `base.cordis.yml` plus the `tui.cordis.yml` overlay, which owns the interactive coding backends, tools, and front door. TUI snapshots and PTY tests live in `apps/cli/tests/`. The [redundant-agent removal](../simplification/2026-07-20-remove-stdio-and-echo-agents.md) owns this consolidation. +The [explicit-config entrypoint decision](../simplification/2026-08-03-explicit-config-dsh-entrypoint.md) removed the product TUI composition, recorded application journeys, and PTY suite. A deployment shipping a terminal front door owns those assembled-application layers; package tests do not claim that product coverage. -### Recorded-session replay +### Removed application replay -Each example-level scenario directory owns `session.jsonl`, optional child logs `session..jsonl`, and `terminal.expected.txt`. The primary log supplies user-authored `user/message` prompts and the recorded `assistant/chunk` sequence. `dsh-llm-replay` derives one model-call script per session, binds child logs to fresh child sessions, and is the only mocked boundary. The agent loop, bash and filesystem implementations, Code Mode worker, subagent provider, workflow worker, Cordis tools, presenters, and TUI are production implementations. +The deleted application suite gave each scenario `session.jsonl`, optional child logs `session..jsonl`, and `terminal.expected.txt`. The primary log supplied user-authored `user/message` prompts and the recorded `assistant/chunk` sequence. `dsh-llm-replay` derived one model-call script per session and was the only mocked boundary; the agent loop, tools, workers, presenters, and TUI were production implementations. -The suite rejects a journey when its tool-call sequence differs, an expected event count is missing, a tool result is an error, a turn ends in error, a workflow lifecycle is incomplete, or the live child-session count differs from the fixture set. These assertions prevent an attractive terminal expected output from hiding a failed or bypassed production path. +That suite rejected a journey when its tool-call sequence differed, an expected event count was missing, a tool result was an error, a turn ended in error, a workflow lifecycle was incomplete, or the live child-session count differed from the fixture set. These checks remain the acceptance pattern for any future terminal deployment; they are no longer shipped fixtures. -The live-model fixtures use `DSH_SNAPSHOT=record`; record mode rewrites their primary and child JSONL logs and terminal expected outputs. The deterministic Cordis toolchain keeps an authored complete JSONL script because reliably coercing a live model through five exact tool boundaries and two children is not a stable recording contract. `DSH_SNAPSHOT=refresh` replays every committed script keylessly and rewrites only derived terminal expected outputs. Plain replay compares without writing, and unknown mode values fail loud. +The removed recording workflow used `DSH_SNAPSHOT=record` for model journeys and `DSH_SNAPSHOT=refresh` for derived terminal output. Removing the product entrypoint also removed those modes from the repository snapshot lane; reusable TUI snapshots are authored directly from package scenarios. ### Semantic terminal projection @@ -43,13 +42,6 @@ Every checkpoint enforces theme independence across the complete terminal state: | Layer | Scenario | Contract pinned | |---|---|---| -| Recorded journey | Multi-turn conversation | Recorded reasoning/text chunks, two input turns, retained history, token totals, and idle editor state | -| Recorded journey | Todo plan | Real `todo_write` execution, result card, and persistent plan rendering | -| Recorded journey | Bash terminal card | Real local executor output, description, exit status, and completed terminal card | -| Recorded journey | Parallel filesystem reads | Two calls from one assistant message, real file contents, ordering, and separate completed cards | -| Recorded journey | Code Mode | Real `run_code` worker execution, two `tool/code-dispatch` events, captured program output, and completed card | -| Recorded journey | Dynamic workflow | Real workflow worker, phase lifecycle, replayed child session, structured return value, and completed card | -| Recorded journey | Cordis dynamic toolchain | Real mount, Code Mode inspect, direct subagent, workflow child, unmount, and all production presenters | | Transient state | Streaming and pending advanced calls | In-flight reasoning/text plus pending Code Mode, workflow, and Cordis cards that disappear from completed logs | | Transient state | Cards, interaction, layout, failure, and shutdown | Collapsed/expanded card families, question validation, compaction replacement, resize reflow, help/errors, cursor restoration, and terminal stop | @@ -58,13 +50,13 @@ Every checkpoint enforces theme independence across the complete terminal state: - **Snapshot raw terminal writes** — rejected because differential rendering may change write boundaries without changing the screen, while cursor and clear sequences are unreadable in review. - **Snapshot component render lines before terminal output** — rejected because it does not test ANSI parsing, cursor movement, overlays, viewport behavior, or independent components in one frame. - **Build every completed flow by appending session events** — rejected because a hand-authored event sequence can drift from the agent loop, tool execution, child-session binding, or worker behavior while its presentation test stays green. Direct event construction remains limited to transient renderer states. -- **Reuse ACP stdout expected outputs as the TUI oracle** — rejected because a recorded model journey is transport-neutral but its presentation is not. TUI scenarios own terminal expected outputs while using the same JSONL replay vocabulary. +- **Reuse ACP stdout expected outputs as the TUI oracle** — rejected because a recorded model journey is transport-neutral but its presentation is not. A terminal deployment owns its expected output while it may reuse the same JSONL replay vocabulary. - **Commit raster screenshots** — rejected because fonts, glyph metrics, antialiasing, and host terminal themes make them platform-sensitive and make semantic style changes difficult to review. - **Use only PTY end-to-end tests** — rejected because raw PTY output is a stream of historical drawing operations, not queryable final state. PTY tests retain the real Loader/input/teardown boundary, while the emulator owns broad state coverage. ## Consequences -- Completed advanced snapshots now fail when the real Code Mode, workflow, subagent, filesystem, bash, or Cordis path breaks, rather than accepting a fabricated result event. +- Package snapshots fail when TUI event mapping or presentation breaks; they do not substitute for an assembled application's tool-path transcript. - TUI visual regressions produce readable cell-and-style diffs, while JSONL fixtures retain the exact model chunks that made the production path execute. -- The emulator uses xterm's proposed buffer API. An xterm upgrade requires rerunning and reviewing the semantic projection; terminal-specific behavior still needs the PTY smoke. -- Expected outputs deliberately encode wrapping and viewport behavior at fixed sizes. Intentional layout changes use keyless refresh, while model-journey changes use record mode and review both JSONL and terminal diffs. +- The emulator uses xterm's proposed buffer API. An xterm upgrade requires rerunning and reviewing the semantic projection; terminal-specific behavior still needs a PTY smoke owned by the deployment that ships it. +- Expected outputs deliberately encode wrapping and viewport behavior at fixed sizes. Intentional layout changes update and review the package semantic snapshots. diff --git a/.agents/notes/implemented/testing/2026-07-18-tui-terminal-state-snapshots.zh.md b/.agents/notes/archived/testing/2026-07-18-tui-terminal-state-snapshots.zh.md similarity index 56% rename from .agents/notes/implemented/testing/2026-07-18-tui-terminal-state-snapshots.zh.md rename to .agents/notes/archived/testing/2026-07-18-tui-terminal-state-snapshots.zh.md index 1b2f6b58e5..50d2e1b817 100644 --- a/.agents/notes/implemented/testing/2026-07-18-tui-terminal-state-snapshots.zh.md +++ b/.agents/notes/archived/testing/2026-07-18-tui-terminal-state-snapshots.zh.md @@ -1,6 +1,7 @@ # Agent Note: TUI 语义终端状态快照 Status: implemented +Archived: 2026-08-04 [English](2026-07-18-tui-terminal-state-snapshots.md) | 中文 @@ -10,26 +11,24 @@ TUI 是有状态的渲染器。用户最终看到的结果取决于 ANSI 解析 组件行快照止于 ANSI 进入终端之前,无法覆盖光标移动、清屏、样式、浮层组合和重排。栅格截图会带入与 TUI 契约无关的字体和平台渲染噪声。直接追加看似合理的会话事件来构造完整流程还存在另一处盲区:这种测试只能证明渲染器接受这些数据形态,无法证明生产环境的 agent loop(智能体循环)和工具实现会生成这些事件。 -因此,TUI 既需要确定、便于评审的终端状态表示,也需要通过已录制模型流程执行真实下游组件,并保留一项范围更小、覆盖真实进程与 PTY 边界的测试。 +因此,可复用 TUI 需要确定、便于评审的终端状态表示。交付它的产品部署还需要通过组装后的技术栈运行已录制模型流程,并保留一项范围更小、覆盖真实进程与 PTY 边界的测试。 ## 决策 -TUI 覆盖分为四个互补层次: +可复用 TUI 的覆盖分为两个互补的包级层次: 1. `packages/ui/tui/tests/tui.spec.ts` 直接测试事件映射、输入路由、资源释放和错误行为。 2. `packages/ui/tui/tests/tui.snapshot.ts` 将生产 TUI 挂载到无界面终端模拟器,覆盖完整会话日志无法保留的瞬态:进行中的流式输出、待完成工具调用、浮层、展开状态、压缩重排、错误和关闭过程。 -3. `examples/tui-agent/tests/tui.snapshot.ts` 通过生产 agent loop 和真实工具回放已提交的 JSONL 会话日志,再比较生成的语义终端状态。 -4. `examples/tui-agent/tests/tui-keyless-smoke.e2e.ts` 在 PTY 中启动真实 Loader 组合,驱动一段经过流式输出和 `ask_user_question` 的脚本化会话,并验证启动、输入、退出、失败报告和终端恢复。 -可运行 TUI 就是交付的 `apps/cli` 组合:共享的 `base.cordis.yml` 加 `tui.cordis.yml` overlay,后者拥有交互式 coding 后端、工具与前端入口。TUI 快照和 PTY 测试位于 `apps/cli/tests/`。[移除重复 agent 的决策](../simplification/2026-07-20-remove-stdio-and-echo-agents.md)负责此次整合。 +[显式配置入口决策](../simplification/2026-08-03-explicit-config-dsh-entrypoint.md)移除了产品 TUI 组合、已录制应用流程和 PTY 测试套件。交付终端入口的部署负责这些组装应用层;包测试不声称提供产品覆盖。 -### 已录制会话回放 +### 已移除的应用回放 -每个示例级场景目录都包含 `session.jsonl`、可选的子会话日志 `session..jsonl`,以及 `terminal.expected.txt`。主日志提供用户来源的 `user/message` 提示词和已录制的 `assistant/chunk` 序列。`dsh-llm-replay` 为每个会话派生一份模型调用脚本,并将子日志绑定到新建的子会话;这是测试中唯一的 mock 边界。agent loop、bash 与文件系统实现、Code Mode worker、subagent 提供方、工作流 worker、Cordis 工具、呈现器和 TUI 都使用生产实现。 +已删除的应用测试套件为每个场景提供 `session.jsonl`、可选的子会话日志 `session..jsonl`,以及 `terminal.expected.txt`。主日志提供用户来源的 `user/message` 提示词和已录制的 `assistant/chunk` 序列。`dsh-llm-replay` 为每个会话派生一份模型调用脚本,并且是测试中唯一的 mock 边界;agent loop、工具、worker、呈现器和 TUI 都使用生产实现。 -如果工具调用顺序不符、预期事件数量不足、工具结果报错、轮次以错误结束、工作流生命周期不完整,或者实时子会话数量与 fixture(测试前置数据)集合不一致,测试都会失败。即使终端预期输出表面正确,这些断言也能阻止失败或被绕过的生产路径混入结果。 +如果工具调用顺序不符、预期事件数量不足、工具结果报错、轮次以错误结束、工作流生命周期不完整,或者实时子会话数量与 fixture(测试前置数据)集合不一致,该测试套件都会拒绝流程。这些检查仍是未来任何终端部署的验收模式;它们已不再作为 fixture 交付。 -真实模型 fixture 通过 `DSH_SNAPSHOT=record` 更新;录制模式会重写其主会话与子会话 JSONL 日志以及终端预期输出。确定性的 Cordis 工具链保留一份人工编写的完整 JSONL 脚本,因为要求真实模型稳定经过五个指定工具边界和两个子会话并不是可靠的录制契约。`DSH_SNAPSHOT=refresh` 会无密钥回放所有已提交脚本,并且只重写派生的终端预期输出。普通回放只比较而不写入,未知模式值会快速失败。 +已移除的录制工作流使用 `DSH_SNAPSHOT=record` 录制模型流程,使用 `DSH_SNAPSHOT=refresh` 更新派生的终端输出。移除产品入口时也从仓库快照通道中移除了这些模式;可复用 TUI 快照直接由包级场景编写。 ### 语义终端投影 @@ -43,13 +42,6 @@ TUI 覆盖分为四个互补层次: | 层次 | 场景 | 固定的契约 | |---|---|---| -| 已录制流程 | 多轮会话 | 已录制的推理与文本分片、两轮输入、保留历史、token 总量和空闲编辑器状态 | -| 已录制流程 | Todo 计划 | 真实 `todo_write` 执行、结果卡片和持久计划渲染 | -| 已录制流程 | Bash 终端卡片 | 真实本地执行器输出、说明、退出状态和已完成终端卡片 | -| 已录制流程 | 并行文件读取 | 同一条 assistant 消息中的两次调用、真实文件内容、顺序和两个独立完成卡片 | -| 已录制流程 | Code Mode | 真实 `run_code` worker 执行、两条 `tool/code-dispatch` 事件、捕获的程序输出和已完成卡片 | -| 已录制流程 | 动态工作流 | 真实工作流 worker、阶段生命周期、回放的子会话、结构化返回值和已完成卡片 | -| 已录制流程 | Cordis 动态工具链 | 真实挂载、Code Mode 检查、直接 subagent、工作流子会话、卸载和全部生产呈现器 | | 瞬态 | 流式输出与待完成高级调用 | 进行中的推理和文本,以及完整日志中不会保留的待完成 Code Mode、工作流和 Cordis 卡片 | | 瞬态 | 卡片、交互、布局、失败和关闭 | 折叠与展开的卡片族、问题校验、压缩替换、尺寸重排、帮助与错误、光标恢复和终端停止 | @@ -58,13 +50,13 @@ TUI 覆盖分为四个互补层次: - **快照原始终端写入**:不予采纳,因为差分渲染可能在画面不变时改变写入边界,而且光标与清屏序列难以评审。 - **快照进入终端输出之前的组件渲染行**:不予采纳,因为它无法测试 ANSI 解析、光标移动、浮层、视口行为,也无法测试独立组件在同一帧中的相互作用。 - **通过追加会话事件构造所有完整流程**:不予采纳,因为人工编写的事件序列可能与 agent loop、工具执行、子会话绑定或 worker 行为发生偏差,但呈现测试仍然保持绿色。直接构造事件只用于渲染器瞬态。 -- **复用 ACP stdout 预期输出作为 TUI 判定依据**:不予采纳,因为已录制模型流程与传输方式无关,其呈现方式却并非如此。TUI 场景使用同一套 JSONL 回放词汇,但拥有独立的终端预期输出。 +- **复用 ACP stdout 预期输出作为 TUI 判定依据**:不予采纳,因为已录制模型流程与传输方式无关,其呈现方式却并非如此。终端部署拥有自己的预期输出,同时可以复用同一套 JSONL 回放词汇。 - **提交栅格截图**:不予采纳,因为字体、字形度量、抗锯齿和宿主终端主题会使结果依赖平台,也会增加语义样式变更的评审难度。 - **只使用 PTY 端到端测试**:不予采纳,因为原始 PTY 输出是一系列历史绘制操作,而不是可查询的最终状态。PTY 测试保留真实 Loader、输入与清理边界,模拟器负责广泛的状态覆盖。 ## 后果 -- 当真实 Code Mode、工作流、subagent、文件系统、bash 或 Cordis 路径损坏时,已完成高级快照会失败,不会继续接受伪造的结果事件。 +- 当 TUI 事件映射或呈现损坏时,包快照会失败;它们不能代替组装应用的工具路径 transcript。 - TUI 视觉回归会产生便于阅读的单元格和样式 diff,而 JSONL fixture 会保留触发生产路径的确切模型分片。 -- 模拟器使用 xterm 的拟议缓冲区 API。升级 xterm 时必须重新运行并评审语义投影;终端特有行为仍需由 PTY 冒烟测试覆盖。 -- 预期输出有意固定指定尺寸下的换行与视口行为。预期布局变更使用无密钥刷新;模型流程变更使用录制模式,并同时评审 JSONL 与终端 diff。 +- 模拟器使用 xterm 的拟议缓冲区 API。升级 xterm 时必须重新运行并评审语义投影;终端特有行为仍需由交付该终端的部署所拥有的 PTY 冒烟测试覆盖。 +- 预期输出有意固定指定尺寸下的换行与视口行为。预期布局变更会更新并评审包级语义快照。 diff --git a/.agents/notes/archived/testing/2026-07-26-execa-for-test-subprocess-plumbing.i18n.yaml b/.agents/notes/archived/testing/2026-07-26-execa-for-test-subprocess-plumbing.i18n.yaml new file mode 100644 index 0000000000..2fb23f6ad5 --- /dev/null +++ b/.agents/notes/archived/testing/2026-07-26-execa-for-test-subprocess-plumbing.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write .agents/notes/archived/testing/2026-07-26-execa-for-test-subprocess-plumbing.md +2026-07-26-execa-for-test-subprocess-plumbing.md: ca5edc50bf17a34809037462f8e9603b8ed28e74 +2026-07-26-execa-for-test-subprocess-plumbing.zh.md: 186e5cd560b6500364c855438d6c3ff18206b52b diff --git a/.agents/notes/implemented/testing/2026-07-26-execa-for-test-subprocess-plumbing.md b/.agents/notes/archived/testing/2026-07-26-execa-for-test-subprocess-plumbing.md similarity index 99% rename from .agents/notes/implemented/testing/2026-07-26-execa-for-test-subprocess-plumbing.md rename to .agents/notes/archived/testing/2026-07-26-execa-for-test-subprocess-plumbing.md index 958abc4aee..ca5edc50bf 100644 --- a/.agents/notes/implemented/testing/2026-07-26-execa-for-test-subprocess-plumbing.md +++ b/.agents/notes/archived/testing/2026-07-26-execa-for-test-subprocess-plumbing.md @@ -1,6 +1,7 @@ # Agent Note: Adopt execa for hand-rolled test subprocess plumbing Status: implemented +Archived: 2026-08-07 English | [中文](2026-07-26-execa-for-test-subprocess-plumbing.zh.md) diff --git a/.agents/notes/implemented/testing/2026-07-26-execa-for-test-subprocess-plumbing.zh.md b/.agents/notes/archived/testing/2026-07-26-execa-for-test-subprocess-plumbing.zh.md similarity index 91% rename from .agents/notes/implemented/testing/2026-07-26-execa-for-test-subprocess-plumbing.zh.md rename to .agents/notes/archived/testing/2026-07-26-execa-for-test-subprocess-plumbing.zh.md index 7027a8bde5..186e5cd560 100644 --- a/.agents/notes/implemented/testing/2026-07-26-execa-for-test-subprocess-plumbing.zh.md +++ b/.agents/notes/archived/testing/2026-07-26-execa-for-test-subprocess-plumbing.zh.md @@ -1,6 +1,7 @@ # Agent Note: 采用 execa 替换手写的测试子进程管道代码 Status: implemented +Archived: 2026-08-07 [English](2026-07-26-execa-for-test-subprocess-plumbing.md) | 中文 @@ -16,11 +17,11 @@ Status: implemented ## 决定 -- `execa` 是根 devDependency,同时是 `@deepseek-ai/dsh-loader-smoke`(唯一的 `src/` 消费者)的运行时依赖。上述 spawn、收集、超时的代码位置统一经由 `await execa(cmd, args, { cwd, env, timeout, killSignal: 'SIGKILL', reject: false })` 运行:其结果以相互独立的字段报告 `{ stdout, stderr, exitCode, signal, timedOut, failed }`,与本仓库防御模式中「正交的子进程结果各自独立上报」的规则一致。`runLoaderSmoke` 传 `input: ''` 以兑现其 stdin 关闭契约;断言固定精确流字节的位置传 `stripFinalNewline: false`。 -- 真正定制的部分继续保持定制,只是架在 execa 拥有的子进程之上:cli-demo 在流中遇到标记即中断的逻辑、jsonrpc 基于行谓词的协议驱动,以及 crash-recovery 在故障点发送 SIGKILL 的编排。`smoke-real.e2e.ts` 的三个长驻交互式服务器保留原生 `spawn`——跨双流监听就绪行加上分级的 SIGTERM→等待→SIGKILL 拆除就是该处的全部内容,execa 在那里删不掉任何东西;它在本 note 中的份额是那份死的 `.env` 解析器。 -- `llm-mock-server` 的 CLI 经由 `parseArgs` 切分(strict、不允许位置参数);数值转换、边界检查与跨选项约束仍手工实现,被固定的错误消息测试改为携带 `parseArgs` 自己的切分器文本。 +- `execa` 是根 devDependency,同时是 `@deepseek-ai/dsh-loader-smoke`(唯一的 `src/` 消费方)的运行时依赖。上述 spawn、收集、超时的代码位置统一经由 `await execa(cmd, args, { cwd, env, timeout, killSignal: 'SIGKILL', reject: false })` 运行:其结果以相互独立的字段报告 `{ stdout, stderr, exitCode, signal, timedOut, failed }`,与本仓库防御模式中「正交的子进程结果各自独立上报」的规则一致。`runLoaderSmoke` 传 `input: ''` 以兑现其 stdin 关闭契约;断言固定精确流字节的位置传 `stripFinalNewline: false`。 +- 真正定制的部分继续保持定制,只是架在 execa 拥有的子进程之上:cli-demo 在流中遇到标记即中断的逻辑、jsonrpc 基于行谓词的协议驱动,以及 crash-recovery 在故障点发送 SIGKILL 的编排。`smoke-real.e2e.ts` 的三个长驻交互式服务器保留原生 `spawn`——跨双流监听就绪行加上分级的 SIGTERM→等待→SIGKILL 拆除就是该处的全部内容,execa 在那里删不掉任何东西;本 Agent Note 涉及该文件的部分,仅是那份已成为死代码的 `.env` 解析器。 +- `llm-mock-server` 的 CLI(命令行界面)经由 `parseArgs` 切分(strict、不允许位置参数);数值转换、边界检查与跨选项约束仍手工实现,固定错误消息的测试改为采用 `parseArgs` 自己的切分器文本。 - 两份 `loadRootEnv` 拷贝被整体删除:拥有它们的 vitest 配置(`vitest.web.config.ts` 无条件、`vitest.snapshot.config.ts` 在 record 模式下)在这些文件运行之前就加载了仓库根部的 `.env`。 -- 那四个轮询循环改乘 `vi.waitFor`,显式传入 `{ interval, timeout }`,并在回调中抛出带描述信息的错误;`waitForPersistedTurnStart` 把「持久化记录格式非法」的校验错误捕获到重试循环之外,使其立即让运行失败,而不是被重试到截止时间。 +- 那四个轮询循环改用 `vi.waitFor`,显式传入 `{ interval, timeout }`,并在回调中抛出带描述信息的错误;`waitForPersistedTurnStart` 把「持久化记录格式非法」的校验错误捕获到重试循环之外,使其立即让运行失败,而不是被重试到截止时间。 ## 曾考虑的替代方案 @@ -32,6 +33,6 @@ Status: implemented - 手写的收集/超时代码块全部移除,包括 `loader-smoke` 中两个标注 `/* v8 ignore */`、无法人为诱发的 OS 错误分支:spawn 与流故障如今经由 execa 的结果字段结算,这个 `src/` 文件不再携带任何覆盖率豁免,逐文件门禁覆盖其余全部分支。 - 捕获的输出如今受 execa 默认 100 MB `maxBuffer` 约束(溢出即终止子进程),此前是无界的;`loader-smoke` README 的局限条目反映了这一点。 -- 直接子进程的超时终止以及退出/信号结果规范化均由 execa 跨平台负责,不再逐处手写;如 `loader-smoke` README 所述,这些辅助函数依然不负责终止进程树。每个改写后的套件在本次变更中已在 POSIX 上重新运行,另一平台由 Windows CI 车道负责。 +- 直接子进程的超时终止以及退出/信号结果规范化均由 execa 跨平台负责,不再逐处手写;如 `loader-smoke` README 所述,这些辅助函数依然不负责终止进程树。每个改写后的套件在本次变更中已在 POSIX 上重新运行,另一平台由 Windows CI 通道负责。 - execa 是新增的根 devDependency(此前完全不存在于 lockfile 中);它是 npm 上被依赖最多的包之一且维护活跃,exe/运行时闭包不受影响(仅测试使用)。 - mock-server CLI 切分器层面的错误文本不再由本仓库决定:未知选项、缺失取值与多余位置参数报告 `parseArgs` 的措辞,并在 `tests/cli.spec.ts` 中如此固定。 diff --git a/.agents/notes/implemented/architecture/2026-06-11-content-block-vocabulary.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-11-content-block-vocabulary.i18n.yaml index b8d807098d..0b150d8090 100644 --- a/.agents/notes/implemented/architecture/2026-06-11-content-block-vocabulary.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-06-11-content-block-vocabulary.i18n.yaml @@ -1,6 +1,6 @@ # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: -# pnpm run verify-translation-pairing --write -2026-06-11-content-block-vocabulary.md: d926c28e7e197aff28c7b1c09d085febf866832b -2026-06-11-content-block-vocabulary.zh.md: 6361f00abe109bffdb5bd3ff5652df67d6b3c8a1 +# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-06-11-content-block-vocabulary.md +2026-06-11-content-block-vocabulary.md: 5228724bb9101307db9929aaf7831b477c2a6022 +2026-06-11-content-block-vocabulary.zh.md: b43de335917c6b5304a94b296fcb8253827b0600 diff --git a/.agents/notes/implemented/architecture/2026-06-11-content-block-vocabulary.md b/.agents/notes/implemented/architecture/2026-06-11-content-block-vocabulary.md index d926c28e7e..5228724bb9 100644 --- a/.agents/notes/implemented/architecture/2026-06-11-content-block-vocabulary.md +++ b/.agents/notes/implemented/architecture/2026-06-11-content-block-vocabulary.md @@ -12,7 +12,7 @@ The harness needs one internal language for messages that the loop, session log, Own the vocabulary: messages are arrays of typed content blocks (`text`, `reasoning`, `tool-call`, `tool-result`), with the union derived from the merge-extensible `ContentBlockMap` so plugins add block types via declaration merging. The same merge-extensible-map pattern types every "stringly" field (`MessageSource`, `FinishReason`, `TurnTrigger`, `TurnEndReason`). Streaming is a raw chunk protocol; `BlockAssembler` is the single shared assembly implementation. Adapters translate to provider wire formats — mapping cost lives in adapters, where it belongs. -In-session context injection (`context/message`) and mid-turn steering (`steering/message`) originally rendered as tagged user-role envelopes (the system-reminder pattern) rather than a new role, so adapters carry zero burden. Both now project as plain user content with no wrapper; see [the injected-content-envelope Agent Note](../simplification/2026-07-20-unwrap-injected-content-envelopes.md). Live-adapter validation confirms this rendering for current DeepSeek behavior; a future provider-specific mismatch belongs in that adapter rather than a new canonical role. +In-session context injection (`context/message`) and mid-turn steering originally rendered as tagged user-role envelopes (the system-reminder pattern) rather than a new role, so adapters carry zero burden. Both now project as plain user content with no wrapper; see [the injected-content-envelope Agent Note](../simplification/2026-07-20-unwrap-injected-content-envelopes.md). Live-adapter validation confirms this rendering for current DeepSeek behavior; a future provider-specific mismatch belongs in that adapter rather than a new canonical role. ## Alternatives considered diff --git a/.agents/notes/implemented/architecture/2026-06-11-content-block-vocabulary.zh.md b/.agents/notes/implemented/architecture/2026-06-11-content-block-vocabulary.zh.md index 6361f00abe..b43de33591 100644 --- a/.agents/notes/implemented/architecture/2026-06-11-content-block-vocabulary.zh.md +++ b/.agents/notes/implemented/architecture/2026-06-11-content-block-vocabulary.zh.md @@ -12,7 +12,7 @@ harness 需要一套统一的内部消息语言,供 agent loop(智能体循 自主拥有词汇:消息是类型化内容块的数组(`text`、`reasoning`、`tool-call`、`tool-result`),其联合类型派生自可合并扩展的 `ContentBlockMap`,插件通过声明合并添加新的块类型。同一可合并扩展映射模式为所有「字符串化」字段提供类型(`MessageSource`、`FinishReason`、`TurnTrigger`、`TurnEndReason`)。流式输出采用原始分片协议;`BlockAssembler` 是唯一的共享组装实现。适配器负责转换为提供方的协议格式(wire format)——映射成本留在适配器中,正是它该在的地方。 -会话内上下文注入(`context/message`)和轮次中途 steering(`steering/message`)最初渲染为带标签的 user-role 信封(system-reminder 模式),而非引入新角色,因此适配器无需承担额外负担。如今两者都投影为无包装的普通用户内容;见[注入内容信封 Agent Note](../simplification/2026-07-20-unwrap-injected-content-envelopes.md)。实际适配器验证已确认此渲染方式符合当前 DeepSeek 的行为;如果未来某提供方出现不兼容,应在该适配器内处理,而非引入新的规范角色。 +会话内上下文注入(`context/message`)和轮次中途 steering(中途引导)最初渲染为带标签的 user-role 信封(system-reminder 模式),而非引入新角色,因此适配器无需承担额外负担。如今两者都投影为无包装的普通用户内容;见[注入内容信封 Agent Note](../simplification/2026-07-20-unwrap-injected-content-envelopes.md)。实际适配器验证已确认此渲染方式符合当前 DeepSeek 的行为;如果未来某提供方出现不兼容,应在该适配器内处理,而非引入新的规范角色。 ## 曾考虑的替代方案 @@ -25,4 +25,4 @@ harness 需要一套统一的内部消息语言,供 agent loop(智能体循 - 多模态块只有在适配器、UI 和上下文压缩(context compaction)三方协同支持后才会回归;见 [drop-image Agent Note](../simplification/2026-07-04-drop-image-content-block.md)。 - 缓存提示与 assistant prefill 在有实际适配器能兑现之前保持缺席;见[无生产者的词汇变体](../../archived/simplification/2026-07-04-prune-producerless-vocabulary-variants.md)与[无端到端可用路径的请求旋钮](../../archived/simplification/2026-07-04-drop-inert-request-knobs.md) Agent Note。 - 每个适配器都需承担翻译成本;首批真实适配器已验证了流式输出协议,新适配器应继续在适配器本地测试中验证其提供方特有的映射。 -- 跨包(package)边界的 ID 使用品牌类型(`CallId`、agent 与会话共享的 `SessionId`)——零运行时开销的名义类型。 +- 跨包边界的 ID 使用品牌类型(`CallId`、agent 与会话共享的 `SessionId`)——零运行时开销的名义类型。 diff --git a/.agents/notes/implemented/architecture/2026-06-11-dev-invariants-over-deep-readonly.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-11-dev-invariants-over-deep-readonly.i18n.yaml index d5b172cb13..f89d1da013 100644 --- a/.agents/notes/implemented/architecture/2026-06-11-dev-invariants-over-deep-readonly.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-06-11-dev-invariants-over-deep-readonly.i18n.yaml @@ -3,4 +3,4 @@ # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-06-11-dev-invariants-over-deep-readonly.md 2026-06-11-dev-invariants-over-deep-readonly.md: f1a741927cf63b43b1aaf558efc148ff80d2d881 -2026-06-11-dev-invariants-over-deep-readonly.zh.md: 67439c674f5a77112fc0619c774f7897cf49e835 +2026-06-11-dev-invariants-over-deep-readonly.zh.md: ade3e20adb8f5301adb87130d42c2bd7a37f8a47 diff --git a/.agents/notes/implemented/architecture/2026-06-11-dev-invariants-over-deep-readonly.zh.md b/.agents/notes/implemented/architecture/2026-06-11-dev-invariants-over-deep-readonly.zh.md index 67439c674f..ade3e20adb 100644 --- a/.agents/notes/implemented/architecture/2026-06-11-dev-invariants-over-deep-readonly.zh.md +++ b/.agents/notes/implemented/architecture/2026-06-11-dev-invariants-over-deep-readonly.zh.md @@ -8,9 +8,9 @@ Status: implemented 会话日志需要两种不同的保护:对每条已存储事实的不可变所有权,以及对跨时间和服务 seam 的事实之间关系的检查。如果将二者混为一个可选的开发插件,生产环境的历史记录将失去保护;如果试图通过 TypeScript readonly 类型同时表达两者,既无法建立运行时边界,也无法描述关系规则。 -会话日志是回放、请求重建、持久化与用户可见历史的持久真源。会话包(package)外部的代码必须能检视历史,但不能保留一个可在之后改写历史的引用;从调用方接受的输入也不能继续连接到调用方拥有的可变对象。 +会话日志是回放、请求重建、持久化与用户可见历史的持久真源。会话包外部的代码必须能检视历史,但不能保留一个可在之后改写历史的引用;从调用方接受的输入也不能继续连接到调用方拥有的可变对象。 -单个值的不可变性只是契约的一半。一份日志可以包含完全不可变的记录,但其序列、轮次/步骤嵌套、工具调用配对、作用域分发或重建的模型请求是错误的。这些规则涉及多条记录或多个服务,无法通过冻结单个对象来建立。 +单个值的不可变性只是约定的一半。一份日志可以包含完全不可变的记录,但其序列、轮次/步骤嵌套、工具调用配对、作用域分发或重建的模型请求是错误的。这些规则涉及多条记录或多个服务,无法通过冻结单个对象来建立。 TypeScript readonly 类型不是充分的运行时边界。它们在程序运行时消失,类型转换可以绕过它们,而递归的 `DeepReadonly` 会扩散到每个日志和消息消费方,尽管某些下游请求处理 API 有意使用可变值。 @@ -22,7 +22,7 @@ TypeScript readonly 类型不是充分的运行时边界。它们在程序运行 `Session` 仅在一次递归遍历完成无损 JSON 快照的物化之后才接受事件。该遍历拒绝不支持的值,并产出进入日志的确切分离记录,因此验证与存储不会从有状态的 getter 观察到不同的值,也不会保留调用方拥有的嵌套引用。 -被接受的事件及其所有后代在发布前被深度冻结。`append()` 返回该拥有的冻结事件,`session/event` 观察者接收同一记录,`session.events` 返回冻结的数组快照。先前返回的数组不会因后续 append 而增长。种子记录在构造成功前经过相同的验证、快照与冻结边界。 +被接受的事件及其所有后代在发布前被深度冻结。`append()` 返回由 Session 拥有的冻结事件,`session/event` 观察者接收同一记录,`session.events` 返回冻结的数组快照。先前返回的数组不会因后续 append 而增长。种子记录在构造成功前经过相同的验证、快照与冻结边界。 此保证属于 `Session` 而非可选监听器,因为每种组合都依赖可信的历史。无论是否注册了开发支持插件,生产部署、聚焦测试或自定义嵌入都获得相同的存储语义。 @@ -32,15 +32,15 @@ TypeScript readonly 类型不是充分的运行时边界。它们在程序运行 ### 包拥有的不变式配套插件检查关系 -`dsh-invariants` 注册可配置的 `ctx.invariants` 服务,本身不包含产品检查。每个包发布一个 `./invariant` 所有权配套插件;`dsh-session`、`dsh-agent`、`dsh-scope` 和 `dsh-agent-loop` 目前添加需要 trace 状态或观察另一个 seam 的规则:单调递增的序列号、轮次与步骤嵌套、工具调用/结果配对、合法的 agent(智能体)状态转换、主体正确的作用域分发,以及循环构建的请求与从其会话日志前缀重建的请求之间的等价性。全局启用和包名 regex 过滤器归该服务所有(见[包拥有的不变式服务](2026-07-19-package-owned-invariant-service.md))。 +`dsh-invariants` 注册可配置的 `ctx.invariants` 服务,本身不包含产品检查。每个包发布一个 `./invariant` 所有权配套插件;`dsh-session`、`dsh-agent`、`dsh-scope` 和 `dsh-agent-loop` 目前添加需要 trace 状态或观察另一个 seam 的规则:单调递增的序列号、轮次与步骤嵌套、工具调用/结果配对、合法的 agent(智能体)状态转换、主体正确的作用域分发,以及循环构建的请求与从其会话日志前缀重建的请求之间的相等性。全局启用和包名 regex 过滤器归该服务所有(见[包拥有的不变式服务](2026-07-19-package-owned-invariant-service.md))。 -当会话配套插件附加到已有或已播种的会话时,它回放不可变日志以重建跟踪状态。服务为每项贡献提供一个可 dispose(资源释放)的子 fiber,因此轮次中途热重载是安全的,同时不赋予诊断逻辑对会话存储的所有权。 +当会话配套插件附加到已有会话或以种子记录初始化的会话时,它回放不可变日志以重建跟踪状态。服务为每项贡献提供一个可 dispose(资源释放)的子 fiber,因此轮次中途热重载是安全的,同时不赋予诊断逻辑对会话存储的所有权。 ## 曾考虑的替代方案 ### 全面的 deep-readonly 类型 -一个被否决的姊妹提案会在公共日志和消息表面上应用递归 `DeepReadonly` 类型,将会话读取路径(`events`、`session/event` 监听器、`deriveMessages()`)翻转为深只读,同时保持进行中的 waterfall 可变。这能提供编辑器反馈,但无法提供运行时保证:TypeScript 类型在运行时被擦除,插件代码可以通过类型转换绕过。它还会将 readonly 类型推入有意进行修改的消费方。在 `Session` 边界处的运行时所有权保护所有调用方,无需这种类型传播。 +一个被否决的配套提案会在公开的日志与消息接口上应用递归 `DeepReadonly` 类型,将会话读取路径(`events`、`session/event` 监听器、`deriveMessages()`)改为深只读,同时保持进行中的 waterfall(瀑布式事件)可变。这能提供编辑器反馈,但无法提供运行时保证:TypeScript 类型在运行时被擦除,插件代码可以通过类型转换绕过。它还会将 readonly 类型推入有意进行修改的消费方。在 `Session` 边界处的运行时所有权保护所有调用方,无需这种类型传播。 ### 仅在开发模式冻结 diff --git a/.agents/notes/implemented/architecture/2026-06-11-event-sourced-sessions.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-11-event-sourced-sessions.i18n.yaml index 6ea6fce11e..0eb64b3107 100644 --- a/.agents/notes/implemented/architecture/2026-06-11-event-sourced-sessions.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-06-11-event-sourced-sessions.i18n.yaml @@ -1,6 +1,6 @@ # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: -# pnpm run verify-translation-pairing --write -2026-06-11-event-sourced-sessions.md: 15ba7b23d5eae48e7dee2328b5924493d54aeeb0 -2026-06-11-event-sourced-sessions.zh.md: da3be5965a6900076f253cad065b847c6f5ce17e +# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-06-11-event-sourced-sessions.md +2026-06-11-event-sourced-sessions.md: 01f9628c1cfc000aca8654caf5edeff09411fdcc +2026-06-11-event-sourced-sessions.zh.md: 5de230de9e9f1303943b43f6fdeefaf8264aa3bf diff --git a/.agents/notes/implemented/architecture/2026-06-11-event-sourced-sessions.md b/.agents/notes/implemented/architecture/2026-06-11-event-sourced-sessions.md index 15ba7b23d5..01f9628c1c 100644 --- a/.agents/notes/implemented/architecture/2026-06-11-event-sourced-sessions.md +++ b/.agents/notes/implemented/architecture/2026-06-11-event-sourced-sessions.md @@ -14,7 +14,7 @@ A `Session` is an append-only log of typed `SessionEvent`s — the single source Appends are synchronous (the hot path never blocks on I/O); `session/event` is a sync notification; persistence plugins buffer write-behind and drain at the awaited `session/flush` checkpoint fired at every turn end. -Ordering contract: the loop appends to the session *before* emitting the corresponding Cordis event, and the `agent/step-result` waterfall runs before the `assistant/message` append so the log records the message tool dispatch actually used. Regression tests pin that ordering. +Ordering contract: the loop claims inbox messages before `agent/pre-step`, opens `step/start` only after an enter decision, then appends the returned `user/message` batch before request derivation. Provider output is assembled and appended as `assistant/message` before tool dispatch, so the durable log records the exact message the tools follow. Regression tests pin that ordering. ## Alternatives considered diff --git a/.agents/notes/implemented/architecture/2026-06-11-event-sourced-sessions.zh.md b/.agents/notes/implemented/architecture/2026-06-11-event-sourced-sessions.zh.md index da3be5965a..5de230de9e 100644 --- a/.agents/notes/implemented/architecture/2026-06-11-event-sourced-sessions.zh.md +++ b/.agents/notes/implemented/architecture/2026-06-11-event-sourced-sessions.zh.md @@ -14,7 +14,7 @@ MVP 要求严格的基于事件的追踪,以及完全可回放的会话(严 追加操作是同步的(热路径从不阻塞于 I/O);`session/event` 是同步通知;持久化插件在后台缓冲写入,并在每个轮次结束时触发的 `session/flush` 检查点处等待排空。 -顺序契约:agent loop(智能体循环)*先*追加到会话,再发出对应的 Cordis 事件;`agent/step-result` waterfall(瀑布式事件)在 `assistant/message` 追加之前运行,因此日志记录的是工具调度实际使用的消息。回归测试固定了这一顺序。 +顺序约定:agent loop(智能体循环)先领取 inbox 消息,再运行 `agent/pre-step`;只有 enter 决策才打开 `step/start`,随后在请求派生前追加返回的 `user/message` 批次。提供方输出组装并以 `assistant/message` 追加后才分派工具,因此持久日志记录工具实际遵循的确切消息。回归测试固定了这一顺序。 ## 曾考虑的替代方案 @@ -24,5 +24,5 @@ MVP 要求严格的基于事件的追踪,以及完全可回放的会话(严 - 回放、追踪与遥测在结构上得到保证,而非事后附加。 - 持久化仍是插件关注点;内存存储随 dsh-session 一起提供。 -- 事件词汇可通过合并扩展(插件可添加如压缩(compaction)事件);[会话持久化](2026-06-14-session-persistence.md)在日志变为持久后冻结了其形状。 +- 事件词汇可通过合并扩展(插件可添加如压缩(compaction)事件);[会话持久化](2026-06-14-session-persistence.md)在日志具备持久性后固定了其结构。 - 派生成本随日志长度增长,压缩(未来插件)是预期的缓解手段,而非日志变更。 diff --git a/.agents/notes/implemented/architecture/2026-06-11-microkernel-event-taxonomy.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-11-microkernel-event-taxonomy.i18n.yaml index a15ebcfddf..5a5aa0eaea 100644 --- a/.agents/notes/implemented/architecture/2026-06-11-microkernel-event-taxonomy.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-06-11-microkernel-event-taxonomy.i18n.yaml @@ -1,6 +1,6 @@ # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: -# pnpm run verify-translation-pairing --write -2026-06-11-microkernel-event-taxonomy.md: 8bf05b7deba5f054d4ec8ecf104c3b8798e42d4e -2026-06-11-microkernel-event-taxonomy.zh.md: 4ff2ab632ca02e98137a15f19a7996a740a519b0 +# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-06-11-microkernel-event-taxonomy.md +2026-06-11-microkernel-event-taxonomy.md: fe6c242acbc0b64123711a17a528f35c02d91087 +2026-06-11-microkernel-event-taxonomy.zh.md: aa3db53d640145836817f9835a30c69815f70d23 diff --git a/.agents/notes/implemented/architecture/2026-06-11-microkernel-event-taxonomy.md b/.agents/notes/implemented/architecture/2026-06-11-microkernel-event-taxonomy.md index 8bf05b7deb..fe6c242acb 100644 --- a/.agents/notes/implemented/architecture/2026-06-11-microkernel-event-taxonomy.md +++ b/.agents/notes/implemented/architecture/2026-06-11-microkernel-event-taxonomy.md @@ -12,10 +12,10 @@ The product principle is "everything is a plugin": hooks, /goal, /loop, dynamic Pure Cordis event taxonomy. The loop's extension seams are typed events with deliberate dispatch modes: -- **waterfall** (around-middleware) where plugins transform, veto, recover, or wrap: `agent/prompt-submit`, `agent/request`, `agent/request-error`, `agent/step-result`, `agent/turn-continuation`, `tools/pre-execute`, `tools/execute`, `tools/post-execute`, `llm/stream`, `system-prompt/assemble`. -- **serial** (awaited in listener order; a bail value stops later listeners) for ordered checkpoints: every `agent/pre-step` and `agent/post-step` listener runs when all abstain, while the first stop returned from `agent/turn-stop` makes the terminal decision final. +- **waterfall** (around-middleware) where plugins transform, short-circuit, recover, or wrap: `agent/pre-step`, `agent/request`, `agent/request-error`, `tools/pre-execute`, `tools/execute`, `tools/post-execute`, `llm/stream`, `system-prompt/assemble`. +- **serial** (awaited in listener order) for ordered checkpoints such as `agent/turn-stopping`. - **parallel** (awaited fan-out) where every listener must get an independent chance: the `session/flush` durability checkpoint. -- **emit** (synchronous fire-and-forget) for notifications: turn/step boundaries, stream chunks, lifecycle, errors, and the contained immutable `tools/result` observation. +- **emit** (synchronous fire-and-forget) for notifications: inbox transitions, lifecycle, errors, and the contained immutable `tools/result` observation. Durable session events own turn and step boundaries. The event vocabulary lives in interface packages (dsh-agent declares the agent/* events); `@deepseek-ai/dsh-agent-loop` is the only concrete loop plugin and is itself swappable — nothing outside it may depend on it. diff --git a/.agents/notes/implemented/architecture/2026-06-11-microkernel-event-taxonomy.zh.md b/.agents/notes/implemented/architecture/2026-06-11-microkernel-event-taxonomy.zh.md index 4ff2ab632c..aa3db53d64 100644 --- a/.agents/notes/implemented/architecture/2026-06-11-microkernel-event-taxonomy.zh.md +++ b/.agents/notes/implemented/architecture/2026-06-11-microkernel-event-taxonomy.zh.md @@ -12,10 +12,10 @@ Status: implemented 纯 Cordis 事件分类体系。agent loop(智能体循环)的扩展 seam 是带类型的事件,具有明确的分发模式: -- **waterfall(瀑布式事件)**(around-middleware):插件可变换、否决、恢复或包装:`agent/prompt-submit`、`agent/request`、`agent/request-error`、`agent/step-result`、`agent/turn-continuation`、`tools/pre-execute`、`tools/execute`、`tools/post-execute`、`llm/stream`、`system-prompt/assemble`。 -- **serial**(按监听器顺序依次 await;bail 值会阻止后续监听器执行):用于有序检查点。所有 `agent/pre-step` 和 `agent/post-step` 监听器在全部弃权时才继续运行,而 `agent/turn-stop` 返回的第一个 stop 值即为最终的终止决策。 +- **waterfall(瀑布式事件)**(around-middleware):插件可变换、短路、恢复或包装:`agent/pre-step`、`agent/request`、`agent/request-error`、`tools/pre-execute`、`tools/execute`、`tools/post-execute`、`llm/stream`、`system-prompt/assemble`。 +- **serial**(按监听器顺序依次 await):用于 `agent/turn-stopping` 等有序检查点。 - **parallel**(await 扇出):每个监听器都必须获得独立执行的机会:`session/flush` 持久性检查点。 -- **emit**(同步 fire-and-forget):用于通知:轮次/步骤边界、流分片、生命周期、错误,以及包含不可变 `tools/result` 观测的事件。 +- **emit**(同步 fire-and-forget):用于通知:inbox 转换、生命周期、错误,以及受错误隔离的 `tools/result` 观测;该观测接收不可变的最终结果。轮次与步骤边界由持久会话事件拥有。 事件词汇定义在接口包中(dsh-agent 声明 agent/* 事件);`@deepseek-ai/dsh-agent-loop` 是唯一的具体循环插件,且自身可替换——外部不得依赖它。 diff --git a/.agents/notes/implemented/architecture/2026-06-11-structured-error-taxonomy.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-11-structured-error-taxonomy.i18n.yaml index ca9d2117ec..c878105c4b 100644 --- a/.agents/notes/implemented/architecture/2026-06-11-structured-error-taxonomy.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-06-11-structured-error-taxonomy.i18n.yaml @@ -1,6 +1,6 @@ # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: -# pnpm run verify-translation-pairing --write +# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-06-11-structured-error-taxonomy.md 2026-06-11-structured-error-taxonomy.md: 9122193b3d01cf5a4c315e6f7a7218153fd4a60a -2026-06-11-structured-error-taxonomy.zh.md: 56a196ccd10a81b51953887f18e522412cd9463b +2026-06-11-structured-error-taxonomy.zh.md: 71814954bdadae575cdfa63d399f7b5b37da19e4 diff --git a/.agents/notes/implemented/architecture/2026-06-11-structured-error-taxonomy.zh.md b/.agents/notes/implemented/architecture/2026-06-11-structured-error-taxonomy.zh.md index 56a196ccd1..71814954bd 100644 --- a/.agents/notes/implemented/architecture/2026-06-11-structured-error-taxonomy.zh.md +++ b/.agents/notes/implemented/architecture/2026-06-11-structured-error-taxonomy.zh.md @@ -6,14 +6,14 @@ Status: implemented ## 问题 -故障跨越 seam 时只是裸字符串。工具错误被扁平化为一个文本块(name、code 和 stack 全部丢失),导致未来的沙箱/重试插件无法区分 ENOENT 和 EACCES,模型得到的反馈也不如本可以那样具有可操作性。非 Error 的 throw 退化更严重:agent loop(智能体循环)将其包装为 `new Error(String(x))`,丢弃了所有 code。而 `LlmError` 是系统中唯一的类型化错误,没有共享基类,消费方无法对其进行通用的 `instanceof` 判断。 +故障跨越 seam 时只是裸字符串。工具错误被扁平化为一个文本块(name、code 和 stack 全部丢失),导致未来的沙箱/重试插件无法区分 ENOENT 和 EACCES,模型也未能获得本可提供的更具可操作性的反馈。非 Error 的 throw 退化更严重:agent loop(智能体循环)将其包装为 `new Error(String(x))`,丢弃了所有 code。而 `LlmError` 是系统中唯一的类型化错误,没有共享基类,消费方无法对其进行通用的 `instanceof` 判断。 ## 决策 在 `dsh-llm`(叶子包,所有其他包都已依赖它,不引入新的依赖边)中引入一个 `HarnessError extends Error` 基类:稳定的 `code`(与 `message` 分离)、通过 `ErrorOptions` 进行 `cause` 链接、`name` 默认为子类名。`isHarnessError` 在 seam 处做类型收窄。 - `LlmError` 和 `ToolArgsError`(dsh-tools)继承该基类,保留各自既有的 code。 -- `ToolExecutionResult` 新增可选字段 `error: { name, code }`,在注册表的 catch 中当抛出值为 `HarnessError` 时填充。agent loop 将其转发到 `tool/result` 会话事件(该事件也新增了同一可选字段),使结构化的失败信息存活到日志中,供重试/沙箱插件和回放使用。面向模型的文本块保持不变。 +- `ToolExecutionResult` 新增可选字段 `error: { name, code }`,在注册表的 catch 中当抛出值为 `HarnessError` 时填充。agent loop 将其转发到 `tool/result` 会话事件(该事件也新增了同一可选字段),使结构化的失败信息保留在日志中,供重试/沙箱插件和回放使用。面向模型的文本块保持不变。 - agent loop 的 `toError` 将非 Error 的 throw 包装为 `HarnessError`(`code: 'UNKNOWN'`,原始值作为 `cause` 链接),而非裸 `Error`;这样即使是不规范的 throw 也能携带可路由的 code 进入会话的 `error` 事件(该事件此前已暴露 `code`)。 ## 后果 diff --git a/.agents/notes/implemented/architecture/2026-06-13-capability-seams.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-13-capability-seams.i18n.yaml index 63063f8d5f..2a310c8172 100644 --- a/.agents/notes/implemented/architecture/2026-06-13-capability-seams.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-06-13-capability-seams.i18n.yaml @@ -1,6 +1,6 @@ # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: -# pnpm run verify-translation-pairing --write +# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-06-13-capability-seams.md 2026-06-13-capability-seams.md: 7c755dced7825d2831acc0901f6412b8e5afe95a -2026-06-13-capability-seams.zh.md: 4148c79cb5e1930dca77eaf3afd2024f508275b5 +2026-06-13-capability-seams.zh.md: 31d20bb15f91533ab3c09d337a3cb11f812dbeb4 diff --git a/.agents/notes/implemented/architecture/2026-06-13-capability-seams.zh.md b/.agents/notes/implemented/architecture/2026-06-13-capability-seams.zh.md index 4148c79cb5..31d20bb15f 100644 --- a/.agents/notes/implemented/architecture/2026-06-13-capability-seams.zh.md +++ b/.agents/notes/implemented/architecture/2026-06-13-capability-seams.zh.md @@ -6,7 +6,7 @@ Status: implemented ## 问题 -harness 具有可替换的能力:当前是 bash 执行,未来会有沙箱化/远程执行器和替代模型提供方。一项能力涉及三个关注点,它们以不同速率、因不同原因变化:*契约*(这项能力是什么)、*实现*(它如何运行)、*消费方接口*(模型和其他插件面向什么编程)。将三者捆绑在一个包(package)中会耦合这些变化速率——把本地执行器换成沙箱化执行器时,模型看到的工具 schema 也会被搅动,尽管面向模型的契约从未改变。 +harness 具有可替换的能力:当前是 bash 执行,未来会有沙箱化/远程执行器和替代模型提供方。一项能力涉及三个关注点,它们以不同速率、因不同原因变化:*约定*(这项能力是什么)、*实现*(它如何运行)、*消费方接口*(模型和其他插件面向什么编程)。将三者捆绑在一个包中会耦合这些变化速率——把本地执行器换成沙箱化执行器时,模型看到的工具 schema 也会被搅动,尽管面向模型的约定从未改变。 这与「谁在运行时提供、谁需要一项能力」是不同的问题,后者 Cordis 已通过服务 + `inject` 解决(提供方注册 `ctx.bash`;消费方声明 `inject: ['bash']`,其 fiber 挂起直到服务存在)。该机制是必要的,但不决定包的边界;本 Agent Note 决定的是包的边界。 @@ -15,12 +15,12 @@ harness 具有可替换的能力:当前是 bash 执行,未来会有沙箱化 一项可替换的能力由**三个包**构成: 1. **接口**——一个抽象服务加词汇类型,拥有 `ctx.`,仅依赖其词汇依赖(例如 `dsh-bash`:`BashExecutor`、`BashRunResult`、`BashProcess`)。 -2. **实现**——一个具体子类,以插件形式加载(例如 `dsh-bash-local`:子进程、进程组 kill、溢出文件截断)。沙箱化/远程后端是实现同一接口的兄弟包。 +2. **实现**——一个具体子类,以插件形式加载(例如 `dsh-bash-local`:子进程、进程组 kill、spill 文件截断)。沙箱化/远程后端是实现同一接口的兄弟包。 3. **消费方**——模型和插件看到的内容(例如 `dsh-tool-bash`:`bash` schema,后台句柄注册到通用任务运行时)。消费方 `inject` 接口键,从不导入实现类型。 实现与消费方由此独立演进:沙箱化执行器替换 `dsh-bash-local` 时无需触碰任何工具 schema。 -当各部分确实属于同一个关注点时,三分并非强制:LLM(大语言模型) seam 将接口 + 消费方合并为 `dsh-llm`(消费方是 agent loop(智能体循环)本身,而非可替换的 schema 表面),适配器作为实现包。不要预防性地拆分——如果一项能力只有一种可设想的实现和一个消费方,就保持为一个包,直到第二种出现。 +当各部分确实属于同一个关注点时,三分并非强制:LLM(大语言模型) seam 将接口 + 消费方合并为 `dsh-llm`(消费方是 agent loop(智能体循环)本身,而非可替换的 schema 接口),适配器作为实现包。不要预防性地拆分——如果一项能力只有一种可设想的实现和一个消费方,就保持为一个包,直到出现第二种实现或第二个消费方。 ## 曾考虑的替代方案 @@ -29,4 +29,4 @@ harness 具有可替换的能力:当前是 bash 执行,未来会有沙箱化 ## 后果 -每项能力需要更多包和更多样板代码(一组 `package.json`/`tsconfig`/README,加上 inject 接线)。换来的是:实现与消费方独立发布和版本管理,新后端永远不会波及面向模型的契约。该规则记录在 [AGENTS.md](../../../../AGENTS.md) § Conventions(「Capability seams are three packages」)和 [architecture.md](../../../../docs/architecture.md) §「Capability seams」中;bash 三件套是参考模板。何时合并、何时拆分是一个判断问题,架构文档对此有详细说明——本 Agent Note 记录的是*为什么*默认选择拆分。 +每项能力需要更多包和更多样板代码(一组 `package.json`/`tsconfig`/README,加上 inject 接线)。换来的是:实现与消费方独立发布和版本管理,新后端永远不会波及面向模型的约定。该规则记录在 [AGENTS.md](../../../../AGENTS.md) § Conventions(「Capability seams are three packages」)和 [architecture.md](../../../../docs/architecture.md) §「Capability seams」中;bash 三件套是参考模板。何时合并、何时拆分是一个判断问题,架构文档对此有详细说明——本 Agent Note 记录的是*为什么*默认选择拆分。 diff --git a/.agents/notes/implemented/architecture/2026-06-13-twin-llm-adapters.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-13-twin-llm-adapters.i18n.yaml index dc88be13a2..d44279eb42 100644 --- a/.agents/notes/implemented/architecture/2026-06-13-twin-llm-adapters.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-06-13-twin-llm-adapters.i18n.yaml @@ -1,6 +1,6 @@ # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: -# pnpm run verify-translation-pairing --write -2026-06-13-twin-llm-adapters.md: b922891d4438553fd96a7f4f4226f378e66e8ad2 -2026-06-13-twin-llm-adapters.zh.md: d98b57a0a2e7c92453046022e8cb50aa52994c0f +# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-06-13-twin-llm-adapters.md +2026-06-13-twin-llm-adapters.md: a4c87325a0b0d1ebe6cf8f95672e5de74ef37d57 +2026-06-13-twin-llm-adapters.zh.md: 2af7e7cca4d4c40e18cece1a4dd5c9cdb11901c8 diff --git a/.agents/notes/implemented/architecture/2026-06-13-twin-llm-adapters.md b/.agents/notes/implemented/architecture/2026-06-13-twin-llm-adapters.md index b922891d44..a4c87325a0 100644 --- a/.agents/notes/implemented/architecture/2026-06-13-twin-llm-adapters.md +++ b/.agents/notes/implemented/architecture/2026-06-13-twin-llm-adapters.md @@ -12,7 +12,7 @@ English | [中文](2026-06-13-twin-llm-adapters.zh.md) Ship **two** adapters against the one contract from the start, deliberately built on different internals: -- `dsh-llm-deepseek` — direct `fetch` + in-repo translation against the DeepSeek API; SSE framing is delegated to `eventsource-parser` ([the SSE-parser swap](../simplification/2026-07-26-eventsource-parser-for-deepseek-sse.md)). The twin identity is owning the fetch/translate internals rather than delegating to a full provider SDK, not hand-rolling transport plumbing. +- `dsh-llm-deepseek` — direct `fetch` + in-repo translation against the DeepSeek API; SSE framing is delegated to `eventsource-parser` ([the archived SSE-parser swap](../../archived/simplification/2026-07-26-eventsource-parser-for-deepseek-sse.md)). The twin identity is owning the fetch/translate internals rather than delegating to a full provider SDK, not hand-rolling transport plumbing. - `dsh-llm-pi-ai` — the same endpoint through the `@earendil-works/pi-ai` library (its own event vocabulary). The rule they enforce: **anything the StreamChunk vocabulary cannot express for BOTH implementations is a core-vocabulary bug**, caught immediately rather than at the next provider. The pair pinned down conventions now documented on `StreamChunk` in `dsh-llm/src/types.ts`: usage emitted before finish, nothing after finish, tool-call `arguments` as raw JSON strings end-to-end, and the two sanctioned error paths (throw from `stream()` *or* end with `finish {kind:'error'|'aborted'}`) that a consumer must handle on both sides — a divergence the library-backed adapter surfaced that a single direct-fetch adapter would have hidden. diff --git a/.agents/notes/implemented/architecture/2026-06-13-twin-llm-adapters.zh.md b/.agents/notes/implemented/architecture/2026-06-13-twin-llm-adapters.zh.md index d98b57a0a2..2af7e7cca4 100644 --- a/.agents/notes/implemented/architecture/2026-06-13-twin-llm-adapters.zh.md +++ b/.agents/notes/implemented/architecture/2026-06-13-twin-llm-adapters.zh.md @@ -6,16 +6,16 @@ Status: implemented ## 问题 -`dsh-llm` 拥有一套提供方无关的流式词汇:`StreamChunk` 协议(`block-start`、`text-delta`、`reasoning-delta`、`tool-call-delta`、`block-end`、`usage`、`finish`)以及内容块类型([内容块词汇](2026-06-11-content-block-vocabulary.md))。如果词汇仅针对单个适配器定义,就有可能将该适配器的特异行为烘焙进「中立」契约:唯一实现碰巧做了什么,什么就成为事实上的规范;在第二个提供方到来之前,抽象层未经验证——而届时泄漏已代价高昂。 +`dsh-llm` 拥有一套提供方无关的流式词汇:`StreamChunk` 协议(`block-start`、`text-delta`、`reasoning-delta`、`tool-call-delta`、`block-end`、`usage`、`finish`)以及内容块类型([内容块词汇](2026-06-11-content-block-vocabulary.md))。如果词汇仅针对单个适配器定义,就有可能将该适配器的特异行为固化到「中立」约定中:唯一实现碰巧做了什么,什么就成为事实上的规范;在第二个提供方到来之前,抽象层未经验证——而届时修复这种泄漏的代价已经很高。 ## 决策 -从一开始就针对同一份契约交付**两个**适配器,刻意基于不同的内部实现构建: +从一开始就针对同一份约定交付**两个**适配器,刻意基于不同的内部实现构建: -- `dsh-llm-deepseek`:直接 `fetch` + 仓库内翻译逻辑对接 DeepSeek API;SSE(Server-Sent Events)分帧委托给 `eventsource-parser`([SSE 解析器替换](../simplification/2026-07-26-eventsource-parser-for-deepseek-sse.md))。孪生身份在于自行持有 fetch/translate 内部实现而非委托给完整的提供方 SDK,不在于手写传输层管道。 +- `dsh-llm-deepseek`:直接 `fetch` + 仓库内翻译逻辑对接 DeepSeek API;SSE(Server-Sent Events)分帧委托给 `eventsource-parser`([已归档的 SSE 解析器替换](../../archived/simplification/2026-07-26-eventsource-parser-for-deepseek-sse.md))。孪生身份在于自行持有 fetch/translate 内部实现而非委托给完整的提供方 SDK,不在于手写传输层管道。 - `dsh-llm-pi-ai`:通过 `@earendil-works/pi-ai` 库访问同一端点(该库有自己的事件词汇)。 -二者共同执行的规则是:**凡 StreamChunk 词汇无法为两个实现同时表达的内容,都是核心词汇的缺陷**——立即暴露,而非等到下一个提供方接入时才发现。这对孪生体确定了现已记录在 `dsh-llm/src/types.ts` 中 `StreamChunk` 上的约定:usage 在 finish 之前发出、finish 之后不再有任何事件、工具调用的 `arguments` 全程以原始 JSON 字符串传递,以及消费方必须在两侧都处理的两条合法错误路径(`stream()` 抛异常,*或者*以 `finish {kind:'error'|'aborted'}` 结束)。后一项分歧正是由基于库的适配器暴露出来的,单一直接 fetch 适配器会将其隐藏。 +二者共同执行的规则是:**凡 StreamChunk 词汇无法为两个实现同时表达的内容,都是核心词汇的缺陷**——立即暴露,而非等到下一个提供方接入时才发现。这对孪生适配器确立了现已记录在 `dsh-llm/src/types.ts` 中 `StreamChunk` 上的约定:usage 在 finish 之前发出、finish 之后不再有任何事件、工具调用的 `arguments` 全程以原始 JSON 字符串传递,以及消费方必须在两侧都处理的两条合法错误路径(`stream()` 抛异常,*或者*以 `finish {kind:'error'|'aborted'}` 结束)。这一分歧正是由基于库的适配器暴露出来的,单一直接 fetch 适配器会将其隐藏。 ## 曾考虑的替代方案 diff --git a/.agents/notes/implemented/architecture/2026-06-14-session-persistence.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-14-session-persistence.i18n.yaml index 5b70e37ebe..bead51ff09 100644 --- a/.agents/notes/implemented/architecture/2026-06-14-session-persistence.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-06-14-session-persistence.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-06-14-session-persistence.md -2026-06-14-session-persistence.md: 137b2b01126214629952812f3dd3b71985a3acda -2026-06-14-session-persistence.zh.md: 2846ee92349c297fb3a173ba9dd3e2ff3cd9ee1a +2026-06-14-session-persistence.md: 00e129e57c7144fd62eec26f5854ee21dec4e964 +2026-06-14-session-persistence.zh.md: df03dce6bd978f10deb64b8d75ae0685dabab7cd diff --git a/.agents/notes/implemented/architecture/2026-06-14-session-persistence.md b/.agents/notes/implemented/architecture/2026-06-14-session-persistence.md index 137b2b0112..00e129e57c 100644 --- a/.agents/notes/implemented/architecture/2026-06-14-session-persistence.md +++ b/.agents/notes/implemented/architecture/2026-06-14-session-persistence.md @@ -14,23 +14,23 @@ The [event-sourced model](2026-06-11-event-sourced-sessions.md) makes the append Persistence is an abstract **capability seam** ([capability seams](2026-06-13-capability-seams.md), the `dsh-bash` template), not loop or core logic: -1. **Interface** (`dsh-session-persistence`, `ctx.sessionPersistence`) — an abstract `SessionPersistence` service: `create`/`append`/`load`/`list`. Its persisted unit IS the existing `SessionEvent` (`{ type, seq, time, data }`), reused verbatim — no conversion type. +1. **Interface** (`dsh-session-persistence`, `ctx.sessionPersistence`) — an abstract `SessionPersistence` service: `locate`/`create`/`append`/`prepare`/`load`/`inspect`/`readFrom`/`list`/`listSnapshots`. Its persisted unit IS the existing `SessionEvent` (`{ type, seq, time, data }`), reused verbatim — no conversion type. 2. **Implementation** (`dsh-session-persistence-jsonl`) — an append-only logical JSONL log per session: a `SessionHeader` line followed by storage records that losslessly represent the contiguous `SessionEvent` stream. Eligible `assistant/chunk` delta runs use packed rows by default; [checksummed Zstandard frames](2026-07-19-zstandard-jsonl-session-logs.md) are the default physical encoding, with raw lines configurable. Key choices recorded here because they are durable, contested, and surprising: -- **The canonical durable log persists every `SessionEvent` losslessly, including `assistant/chunk`.** JSONL storage may encode a consecutive delta run as one packed row, but `load` reconstructs the exact event boundaries, sequence numbers, and timestamps. `deriveMessages()` skips chunks, and a chunk-filtered rollout (Codex's `policy.rs`) is tempting — but `seq = log.length` and the load-validation `events[i].seq === i` require a *contiguous* logical log; filtering chunks out would leave holes and break both the contract and resume. A chunk-filtered projection is possible later as a derived view with its own renumbering, but it is NOT the canonical log. -- **Append-only; a crashed turn is closed, never truncated.** Flushed events are never rewritten. The [semantic checkpoint policy](../bug-fix/2026-07-21-semantic-session-checkpoints.md) drains the request before model dispatch, a recorded top-level call before tool dispatch, and the complete response/result batch after a step; the loop drains the final turn boundary. Because one interrupted turn may contain substantial valid work, `load` preserves its contiguous, parseable events and appends risk-classified error results for unanswered assistant calls, a missing `step/end`, and `turn/end` with `{ kind: 'interrupted' }`. The synthetic results keep resumed provider transcripts valid. Only an incomplete final record is discarded; a parse error or sequence gap at or before the last real `turn/end` is corruption and makes the session unloadable. -- **File backend canonical, DB backend a proven drop-in.** `SessionEvent` maps 1:1 onto a row `(session_id, seq, type, time, data)` — `append` is INSERT (in a transaction asserting the contiguous-seq contract), `load` is SELECT … ORDER BY seq. `dsh-session-persistence-sqlite` is exactly this: a `SessionPersistence` subclass with no interface change (opencode runs this exact shape on SQLite/WAL), and it passes the same `runPersistenceContract` suite as the JSONL backend — so the contract holds both backends to identical semantics (lazy materialization, interrupted-turn close on load, contiguous-seq), expressed once over file bytes and once over rows. Its database carries a dedicated application id and monotonic schema version. A pristine file creates all tables and stamps both header values in one transaction; an unversioned file with any user-defined schema object or application identity, a foreign current-version identity, and every non-current version reject before journal-mode mutation. +- **The canonical durable log persists every `SessionEvent` losslessly, including `assistant/chunk`.** JSONL storage may encode a consecutive delta run as one packed row, but logical readers reconstruct the exact event boundaries, sequence numbers, and timestamps. `deriveMessages()` skips chunks, and a chunk-filtered rollout (Codex's `policy.rs`) is tempting — but `seq = log.length` and validation of `events[i].seq === i` require a *contiguous* logical log; filtering chunks out would leave holes and break both the contract and resume. A chunk-filtered projection is possible later as a derived view with its own renumbering, but it is NOT the canonical log. +- **Append-only; a crashed turn is closed, never truncated.** Flushed events are never rewritten. The [semantic checkpoint policy](../bug-fix/2026-07-21-semantic-session-checkpoints.md) drains the request before model dispatch, a recorded top-level call before tool dispatch, and the complete response/result batch after a step; the loop drains the final turn boundary. Because one interrupted turn may contain substantial valid work, cold inspection preserves its contiguous, parseable events and adds risk-classified error results for unanswered assistant calls, a missing `step/end`, and `turn/end` with `{ kind: 'interrupted' }` to the in-memory logical view. `prepare` or `load` commits those closers before returning a recoverable view; the synthetic results keep resumed provider transcripts valid. Only an incomplete final record is discarded during committed repair; a parse error or sequence gap at or before the last real `turn/end` is corruption and makes the session unloadable. +- **File backend canonical, DB backend a proven drop-in.** `SessionEvent` maps 1:1 onto a row `(session_id, seq, type, time, data)` — `append` is INSERT (in a transaction asserting the contiguous-seq contract), and reads use SELECT … ORDER BY seq. `dsh-session-persistence-sqlite` is exactly this: a `SessionPersistence` subclass with no interface change (opencode runs this exact shape on SQLite/WAL), and it passes the same `runPersistenceContract` suite as the JSONL backend — so the contract holds both backends to identical semantics (lazy materialization, logical interrupted-turn closure, single committed repair, contiguous-seq), expressed once over file bytes and once over rows. Its database carries a dedicated application id and monotonic schema version. A pristine file creates all tables and stamps both header values in one transaction; an unversioned file with any user-defined schema object or application identity, a foreign current-version identity, and every non-current version reject before journal-mode mutation. - **Metadata is out-of-log.** Format version, cwd, and lineage are storage concerns, not replayable conversation state, so they live in a `SessionHeader` owned by `dsh-session` and attached to a `Session` via a new readonly `session.header` — never in `SessionEventMap`, never reaching `deriveMessages()`. `createdAt` is non-negative safe-integer Unix epoch milliseconds: live creation and persistence registration reject fractional values, JSONL validates the decoded header, and SQLite stores it in a strict `INTEGER` column. The alternative (a merge-extensible `session/meta` event as log line 0) was rejected: an in-log event would ride along with a seeded/forked session for free, but metadata is not replayable state, so the explicit out-of-log header seam is the cleaner cost. (The header was originally split into an immutable `SessionHeader` plus a mutable `SessionSummary` whose union was `SessionMeta`; the mutable summary was later removed as dead state — see [Drop the mutable session summary](../simplification/2026-06-19-drop-mutable-session-summary.md).) -- **`ctx.agents.create()` and `ctx.agents.resume()` are async factories; resume additionally crosses the persistence boundary.** `ctx.agents.resume({ resumeSessionId })` awaits `ctx.sessionPersistence.load`, recreates the live session with the loaded events (so `lastTurnNumber`/`deriveMessages` continue), and registers the fresh agent under the exact resumed id. The agent-loop does NOT hard-inject `sessionPersistence` (that would pend non-persistent demos forever); `resume` rejects with a clear error when it is absent. +- **`ctx.agents.create()` and `ctx.agents.resume()` are async factories; resume additionally crosses the persistence boundary.** `ctx.agents.resume({ resumeSessionId })` obtains the exact unpublished Session through `ctx.sessionPersistence.prepare()`, publishes it under the persisted id, and continues its projections. The [Session preparation decision](2026-08-05-session-preparation.md) owns reuse between history inspection and resume. The agent-loop does NOT hard-inject `sessionPersistence` (that would pend non-persistent demos forever); `resume` rejects with a clear error when it is absent. ## Alternatives considered Each key choice above records its rejected alternative where the choice is stated: a **chunk-filtered canonical log** (Codex's `policy.rs` shape) — breaks the contiguous-seq contract; **truncating a crashed turn** — silently destroys a long autonomous run's real work; an **in-log `session/meta` event as line 0** — metadata is not replayable state; **finite fractional `createdAt` values** — have no producer and diverge from integer Unix-millisecond storage and query columns; **adopting a non-pristine unversioned SQLite file** — can overwrite unrelated objects or identity; **hard-injecting `sessionPersistence` into the loop** — would pend non-persistent demos forever. -Format versioning: the header carries a `version`; `load` rejects any non-current version. The pre-release session format stays pinned at `SESSION_FORMAT_VERSION = 0` and carries no broad compatibility promise, while the coordinator may own an explicit narrow import upgrade when persisted user data requires it ([pre-identity message recovery](../bug-fix/2026-07-28-load-pre-identity-session-messages.md)). Stated honestly: append-only + flush is robust to partial trailing writes (tolerated on load) but not to fsync-less power loss mid-line; a DB/WAL backend is the stronger option later. +Format versioning: the header carries a `version`; cold reads reject any non-current version. The pre-release session format stays pinned at `SESSION_FORMAT_VERSION = 0` and carries no broad compatibility promise, while the coordinator may own an explicit narrow import upgrade when persisted user data requires it ([pre-identity message recovery](../bug-fix/2026-07-28-load-pre-identity-session-messages.md)). Stated honestly: append-only + flush is robust to partial trailing writes (tolerated during cold preparation) but not to fsync-less power loss mid-line; a DB/WAL backend is the stronger option later. ## Consequences -Two new packages and the metadata seam in `dsh-session` (`session.header`, the `create(id?, options?)` signature). Bought: durable resume/fork, a read/replay path, crash tolerance, and host-side session access over the existing event-sourced log, with the backend swappable behind one interface. The reusable `runPersistenceContract` suite holds every backend to the same append-only, contiguous-seq, lazy-materialization, integer-metadata, and serializability semantics. Persisting the full logical log also settles event fidelity: every `assistant/chunk` survives exactly even when JSONL packs several into one storage row. SQLite initialization either commits its complete owned schema and header identity or leaves no partial schema to strand on the next open. +Two new packages and the metadata seam in `dsh-session` (`session.header`, the `create(id?, options?)` signature). Bought: durable resume/fork, a read/replay path, crash tolerance, and host-side session access over the existing event-sourced log, with the backend swappable behind one interface. The reusable `runPersistenceContract` suite holds every backend to the same append-only, contiguous-seq, lazy-materialization, logical-recovery, integer-metadata, and serializability semantics. Persisting the full logical log also settles event fidelity: every `assistant/chunk` survives exactly even when JSONL packs several into one storage row. SQLite initialization either commits its complete owned schema and header identity or leaves no partial schema to strand on the next open. diff --git a/.agents/notes/implemented/architecture/2026-06-14-session-persistence.zh.md b/.agents/notes/implemented/architecture/2026-06-14-session-persistence.zh.md index 2846ee9234..df03dce6bd 100644 --- a/.agents/notes/implemented/architecture/2026-06-14-session-persistence.zh.md +++ b/.agents/notes/implemented/architecture/2026-06-14-session-persistence.zh.md @@ -6,31 +6,31 @@ Status: implemented ## 问题 -会话此前仅存在于内存中。示例插件 `session-jsonl.ts`(在两个示例中逐字节重复)是只写的遥测:它缓冲 `session/event` 并追加 JSON 行,没有读取/回放路径,没有崩溃安全性(无 fsync、无原子写入、fire-and-forget 的 dispose 排空),没有列表功能,也没有格式版本控制。没有任何机制能将磁盘上的历史会话重新注入到活跃的 agent(智能体)中,因此持久恢复、持久 fork 以及宿主侧的会话浏览都无法实现。 +会话此前仅存在于内存中。示例插件 `session-jsonl.ts`(在两个示例中逐字节重复)是只写的遥测:它缓冲 `session/event` 并追加 JSON 行,没有读取/回放路径,没有崩溃安全性(无 fsync、无原子写入、dispose(资源释放)时采用 fire-and-forget 方式排空),没有列表功能,也没有格式版本控制。没有任何机制能将磁盘上的历史会话重新注入到活跃的 agent(智能体)中,因此持久恢复、持久 fork 以及宿主侧的会话浏览都无法实现。 -[事件溯源模型](2026-06-11-event-sourced-sessions.md)将仅追加日志作为唯一真源,并从中派生 LLM(大语言模型)历史。持久化必须忠实于这一设计:直接持久化现有的 `SessionEvent`,不引入需要来回转换的并行「持久化消息」类型。后端也必须可替换——当前用文件存储,以后用数据库存储——统一在一个接口之后。 +[事件溯源模型](2026-06-11-event-sourced-sessions.md)将仅追加日志作为唯一真源,并从中派生 LLM(大语言模型)历史。持久化必须忠实于这一设计:直接持久化现有的 `SessionEvent`,不引入需要来回转换的并行「持久化消息」类型。后端也必须可替换——当前用文件存储,以后用数据库存储——并由同一接口封装。 ## 决策 持久化是一个抽象的**能力 seam**([能力 seam](2026-06-13-capability-seams.md),`dsh-bash` 模板),而非循环或核心逻辑: -1. **接口**(`dsh-session-persistence`,`ctx.sessionPersistence`):一个抽象的 `SessionPersistence` 服务,提供 `create`/`append`/`load`/`list`。其持久化单元就是现有的 `SessionEvent`(`{ type, seq, time, data }`),原样复用,无转换类型。 +1. **接口**(`dsh-session-persistence`,`ctx.sessionPersistence`):一个抽象的 `SessionPersistence` 服务,提供 `locate`/`create`/`append`/`prepare`/`load`/`inspect`/`readFrom`/`list`/`listSnapshots`。其持久化单元就是现有的 `SessionEvent`(`{ type, seq, time, data }`),原样复用,无转换类型。 2. **实现**(`dsh-session-persistence-jsonl`):每个会话一个仅追加的逻辑 JSONL 日志:先是一行 `SessionHeader`,随后是无损表示连续 `SessionEvent` 流的存储记录。符合条件的 `assistant/chunk` 增量连续段默认使用打包行;[带校验和的 Zstandard 帧](2026-07-19-zstandard-jsonl-session-logs.md)是默认物理编码,也可通过配置使用原始行。 -以下关键选择记录于此,因为它们是持久性的、有争议的、且出人意料的: +以下关键选择记录于此,因为它们长期有效、存在争议且出人意料: -- **规范的持久日志无损保留每个 `SessionEvent`,包括 `assistant/chunk`。** JSONL 存储可以将一段连续的增量事件编码为一条打包行,但 `load` 会重建精确的事件边界、序号与时间戳。`deriveMessages()` 跳过分片,而过滤分片的方案(Codex 的 `policy.rs`)很有吸引力,但 `seq = log.length` 以及加载验证 `events[i].seq === i` 要求*连续*的逻辑日志;过滤掉分片会留下空洞,同时破坏契约和恢复功能。基于分片过滤的投影可以作为派生视图在后续实现(带有自己的重新编号),但它不是规范日志。 -- **仅追加;崩溃的轮次被关闭,而非截断。** 已刷写的事件永不被重写。[语义检查点策略](../bug-fix/2026-07-21-semantic-session-checkpoints.md)会在模型分发前排空请求、在工具分发前排空已记录的顶层调用,并在步骤结束后排空完整的响应/结果批次;循环则排空最终轮次边界。由于一个被中断的轮次可能包含大量有效工作,`load` 保留其连续、可解析的事件,并为未应答的 assistant 调用追加按风险分类的错误结果、补一个缺失的 `step/end`,以及带 `{ kind: 'interrupted' }` 的 `turn/end`。合成的结果保证恢复后的提供方 transcript(文本记录)仍然有效。只有不完整的最后一条记录会被丢弃;在最后一个真实 `turn/end` 处或之前出现解析错误或序号间隙,属于数据损坏,会使该会话不可加载。 -- **文件后端为规范实现,数据库后端为经过验证的直接替换。** `SessionEvent` 1:1 映射到一行 `(session_id, seq, type, time, data)`:`append` 是 INSERT(在一个断言连续 seq 契约的事务中),`load` 是 SELECT … ORDER BY seq。`dsh-session-persistence-sqlite` 正是如此:一个 `SessionPersistence` 子类,接口无变化(opencode 在 SQLite/WAL 上运行的正是这个形状),且通过与 JSONL 后端相同的 `runPersistenceContract` 测试套件。该契约以相同的语义约束两个后端(惰性物化、加载时关闭中断轮次、连续 seq),一次表达在文件字节上,一次表达在数据库行上。其数据库拥有专用的 application id 与单调递增的 schema 版本。系统会在一个事务中为全新文件创建所有表并写入这两个 header 值;未版本化文件若带有任何用户定义的 schema 对象或应用标识、当前版本文件若带有外部应用标识,以及任何非当前版本文件,都会在修改日志模式之前被拒绝。 -- **元数据在日志之外。** 格式版本、cwd 和谱系是存储关注点,不是可回放的对话状态,因此它们存放在 `dsh-session` 拥有的 `SessionHeader` 中,并通过新的只读属性 `session.header` 附加到 `Session` 上——永远不进入 `SessionEventMap`,永远不到达 `deriveMessages()`。`createdAt` 是以 Unix epoch 毫秒表示的非负安全整数:运行时创建和持久化注册会拒绝小数值,JSONL 会验证解码后的 header,SQLite 则将其存入严格的 `INTEGER` 列。替代方案(一个可合并扩展的 `session/meta` 事件作为日志第 0 行)被否决:日志内事件会随 seed/fork 的会话免费携带,但元数据不是可回放状态,因此显式的日志外 header seam 是更干净的代价。(header 最初被拆分为不可变的 `SessionHeader` 加可变的 `SessionSummary`,二者的联合类型为 `SessionMeta`;可变 summary 后来因属于死状态而被移除——见 [移除可变会话摘要](../simplification/2026-06-19-drop-mutable-session-summary.md)。) -- **`ctx.agents.create()` 和 `ctx.agents.resume()` 是异步工厂;恢复还跨越持久化边界。** `ctx.agents.resume({ resumeSessionId })` 等待 `ctx.sessionPersistence.load`,用加载的事件重建活跃会话(使 `lastTurnNumber`/`deriveMessages` 得以延续),并以原样恢复的 id 注册新 agent。agent loop(智能体循环)不会硬注入 `sessionPersistence`(那样会让非持久化的演示永远挂起);当它不存在时,`resume` 会以明确的错误拒绝。 +- **规范的持久日志无损保留每个 `SessionEvent`,包括 `assistant/chunk`。** JSONL 存储可以将一段连续的增量事件编码为一条打包行,但逻辑读取方会重建精确的事件边界、序号与时间戳。`deriveMessages()` 跳过分片,而过滤分片的方案(Codex 的 `policy.rs`)很有吸引力,但 `seq = log.length` 以及 `events[i].seq === i` 验证要求*连续*的逻辑日志;过滤掉分片会留下空洞,同时破坏约定和恢复功能。基于分片过滤的投影可以作为派生视图在后续实现(带有自己的重新编号),但它不是规范日志。 +- **仅追加;崩溃的轮次被关闭,而非截断。** 已刷写的事件永不被重写。[语义检查点策略](../bug-fix/2026-07-21-semantic-session-checkpoints.md)会在模型分发前排空请求、在工具分发前排空已记录的顶层调用,并在步骤结束后排空完整的响应/结果批次;循环则排空最终轮次边界。由于一个被中断的轮次可能包含大量有效工作,冷检查会保留其连续、可解析的事件,并在内存逻辑视图中为未应答的 assistant 调用添加按风险分类的错误结果、补一个缺失的 `step/end`,以及带 `{ kind: 'interrupted' }` 的 `turn/end`。`prepare` 或 `load` 在返回可恢复视图前提交这些收尾事件;合成结果保证恢复后的提供方 transcript(文本记录)仍然有效。只有不完整的最后一条记录会在提交修复时被丢弃;在最后一个真实 `turn/end` 处或之前出现解析错误或序号间隙,属于数据损坏,会使该会话不可加载。 +- **文件后端为规范实现,数据库后端为经过验证的直接替换。** `SessionEvent` 1:1 映射到一行 `(session_id, seq, type, time, data)`:`append` 是 INSERT(在一个断言连续 seq 约定成立的事务中),读取使用 SELECT … ORDER BY seq。`dsh-session-persistence-sqlite` 正是如此:一个 `SessionPersistence` 子类,接口无变化(opencode 在 SQLite/WAL 上运行的正是这个形状),且通过与 JSONL 后端相同的 `runPersistenceContract` 测试套件。该约定以相同的语义约束两个后端(惰性物化、逻辑关闭中断轮次、修复只提交一次、连续 seq),一次表达在文件字节上,一次表达在数据库行上。其数据库拥有专用的 application id 与单调递增的 schema 版本。系统会在一个事务中为全新文件创建所有表并写入这两个 header 值;未版本化文件若带有任何用户定义的 schema 对象或应用标识、当前版本文件若带有外部应用标识,以及任何非当前版本文件,都会在修改日志模式之前被拒绝。 +- **元数据在日志之外。** 格式版本、cwd 和谱系是存储关注点,不是可回放的对话状态,因此它们存放在 `dsh-session` 拥有的 `SessionHeader` 中,并通过新的只读属性 `session.header` 附加到 `Session` 上——永远不进入 `SessionEventMap`,永远不到达 `deriveMessages()`。`createdAt` 是以 Unix epoch 毫秒表示的非负安全整数:运行时创建和持久化注册会拒绝小数值,JSONL 会验证解码后的 header,SQLite 则将其存入严格的 `INTEGER` 列。替代方案(一个可合并扩展的 `session/meta` 事件作为日志第 0 行)被否决:日志内事件会自然随 seed/fork 的会话携带,但元数据不是可回放状态,因此显式的日志外 header seam 是更清晰的取舍。(header 最初被拆分为不可变的 `SessionHeader` 加可变的 `SessionSummary`,二者的联合类型为 `SessionMeta`;可变 summary 后来因属于死状态而被移除——见 [移除可变会话摘要](../simplification/2026-06-19-drop-mutable-session-summary.md)。) +- **`ctx.agents.create()` 和 `ctx.agents.resume()` 是异步工厂;恢复还跨越持久化边界。** `ctx.agents.resume({ resumeSessionId })` 通过 `ctx.sessionPersistence.prepare()` 取得原本那个尚未发布的会话,以持久化 id 发布该会话,并延续其投影。[会话准备决策](2026-08-05-session-preparation.md)负责历史检查与恢复之间的复用。agent loop(智能体循环)不会硬注入 `sessionPersistence`(那样会让非持久化的演示永远挂起);当它不存在时,`resume` 会以明确的错误拒绝。 ## 曾考虑的替代方案 -上述每个关键选择都在陈述处记录了被否决的替代方案:**过滤分片的规范日志**(Codex 的 `policy.rs` 形式)破坏连续 seq 契约;**截断崩溃的轮次**会静默销毁长时间自主运行中的真实工作;**日志内 `session/meta` 事件作为第 0 行**——元数据不是可回放状态;**有限的非整数 `createdAt` 值**没有生产方,且与整数 Unix 毫秒存储及查询列不一致;**接受非全新的未版本化 SQLite 文件**可能覆盖无关对象或应用标识;**将 `sessionPersistence` 硬注入循环**会让非持久化的演示永远挂起。 +上述每个关键选择都在陈述处记录了被否决的替代方案:**过滤分片的规范日志**(Codex 的 `policy.rs` 形式)破坏连续 seq 约定;**截断崩溃的轮次**会静默销毁长时间自主运行中的真实工作;**日志内 `session/meta` 事件作为第 0 行**——元数据不是可回放状态;**有限的非整数 `createdAt` 值**没有生产方,且与整数 Unix 毫秒存储及查询列不一致;**接受非全新的未版本化 SQLite 文件**可能覆盖无关对象或应用标识;**将 `sessionPersistence` 硬注入循环**会让非持久化的演示永远挂起。 -格式版本控制:header 携带一个 `version`;`load` 拒绝任何非当前版本。预发布阶段的会话格式仍固定为 `SESSION_FORMAT_VERSION = 0`,不承诺广泛兼容;当持久化用户数据确有需要时,协调器可以负责显式且范围受限的导入升级([消息标识机制引入前的消息恢复](../bug-fix/2026-07-28-load-pre-identity-session-messages.md))。坦率地说:仅追加 + 刷写对部分尾部写入是健壮的(加载时容忍),但对行写入中途的无 fsync 断电不健壮;数据库/WAL 后端是后续更强的选项。 +格式版本控制:header 携带一个 `version`;冷读取拒绝任何非当前版本。预发布阶段的会话格式仍固定为 `SESSION_FORMAT_VERSION = 0`,不承诺广泛兼容;当持久化用户数据确有需要时,协调器可以负责显式且范围受限的导入升级([消息标识机制引入前的消息恢复](../bug-fix/2026-07-28-load-pre-identity-session-messages.md))。坦率地说:仅追加 + 刷写对部分尾部写入是健壮的(冷准备时容忍),但对行写入中途的无 fsync 断电不健壮;数据库/WAL 后端是后续更强的选项。 ## 后果 -新增两个包(package),以及 `dsh-session` 中的元数据 seam(`session.header`,`create(id?, options?)` 签名)。收益:持久恢复/fork、读取/回放路径、崩溃容忍,以及基于现有事件溯源日志的宿主侧会话访问,后端在一个接口之后可替换。可复用的 `runPersistenceContract` 测试套件以相同的仅追加、连续 seq、惰性物化、整数元数据与可序列化语义约束每个后端。持久化完整的逻辑日志还确定了事件保真度:即使 JSONL 将多个 `assistant/chunk` 打包到一条存储行中,每个事件也会精确保留。SQLite 初始化要么提交完整的自有 schema 与 header 标识,要么不留下任何会使下次打开受阻的部分 schema。 +新增两个包,以及 `dsh-session` 中的元数据 seam(`session.header`,`create(id?, options?)` 签名)。收益:持久恢复/fork、读取/回放路径、崩溃容忍,以及基于现有事件溯源日志的宿主侧会话访问,后端可在同一接口下替换。可复用的 `runPersistenceContract` 测试套件以相同的仅追加、连续 seq、惰性物化、逻辑恢复、整数元数据与可序列化语义约束每个后端。持久化完整的逻辑日志还确定了事件保真度:即使 JSONL 将多个 `assistant/chunk` 打包到一条存储行中,每个事件也会精确保留。SQLite 初始化要么提交完整的自有 schema 与 header 标识,要么不留下任何会使下次打开受阻的部分 schema。 diff --git a/.agents/notes/implemented/architecture/2026-06-17-filesystem-capability-seam.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-17-filesystem-capability-seam.i18n.yaml index 530e207654..4511cefb31 100644 --- a/.agents/notes/implemented/architecture/2026-06-17-filesystem-capability-seam.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-06-17-filesystem-capability-seam.i18n.yaml @@ -1,6 +1,6 @@ # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: -# pnpm run verify-translation-pairing --write -2026-06-17-filesystem-capability-seam.md: fee0161e5e8397ac1d1c0e2850efad840c65d971 -2026-06-17-filesystem-capability-seam.zh.md: ee50b36d25315c3d8daed4502bc248977f9e6011 +# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-06-17-filesystem-capability-seam.md +2026-06-17-filesystem-capability-seam.md: 7436d2a9402c76f17c7d6571eb489a86e550ebfb +2026-06-17-filesystem-capability-seam.zh.md: a96d513d7f4fa793ebb3427e3f7b290862d0d5e9 diff --git a/.agents/notes/implemented/architecture/2026-06-17-filesystem-capability-seam.md b/.agents/notes/implemented/architecture/2026-06-17-filesystem-capability-seam.md index fee0161e5e..7436d2a940 100644 --- a/.agents/notes/implemented/architecture/2026-06-17-filesystem-capability-seam.md +++ b/.agents/notes/implemented/architecture/2026-06-17-filesystem-capability-seam.md @@ -62,8 +62,9 @@ The root `tool-fs` plugin registers the full filesystem tool suite (`read`, `wri The interface covers these semantic operations: - Resolve a model/plugin-supplied path into a backend-defined target. +- Convert a resolved target to the canonical process path or `file:` URI for the same execution world, and test containment without parsing its opaque key. - Stat target metadata without reading file contents. -- Read a bounded UTF-8 text page from a target. +- Read complete or streamed UTF-8 text; consumers apply their own view and retention limits. - Create or replace a UTF-8 text file. - Edit an existing UTF-8 text file by literal replacement. @@ -83,9 +84,11 @@ Resolved targets must expose at least three concepts: - An opaque `targetKey`, used for stale guards and file-state lookup. The local backend might use a realpath-like key; a remote backend might use a workspace URI or file id. Consumers must not parse or assume this is a local absolute path. - A `displayPath`, used for model/UI-facing output. It may be a local absolute path, workspace-relative path, or remote URI depending on the backend. +`targetKey` remains opaque even when another capability shares the provider's execution world. Such consumers ask the provider for `processPath(target)`, `fileUrl(target)`, or `contains(parent, child)`; the [portable execution-world decision](2026-07-28-portable-execution-world-consumers.md) owns why these facts sit on the filesystem seam. + Read and mutation results must include an opaque file `version`. The local backend derives its token from bigint stat metadata (`dev`, `ino`, `size`, `mtimeNs`, and `ctimeNs`) so same-size rewrites and inode replacement invalidate consumers reliably; a remote backend can use a revision id or hash-like token. The `dsh-fs-policy` plugin records versions for stale checks; consumers may display related metadata but must not interpret the version token. -The provider hands back decoded text: `readText` returns a whole regular text file, `streamText` streams the same text semantics for large files. Both own regular-file checks, bounded line/output handling is NOT theirs — line windowing, numbered-line rendering, and total-line accounting live in the executor (`dsh-tool-fs`), which reads through `ctx.fs` and renders the model-facing window. The provider owns UTF-8 decoding and binary/NUL rejection; it does not know about line windows or views. +The provider hands back decoded text: `readText` returns a whole regular text file and `streamText` streams the same text semantics for large files or consumer-owned retention limits. Line windowing, byte ceilings, numbered-line rendering, and total-line accounting live in consumers such as `dsh-tool-fs` and `dsh-lsp-local`. The provider owns regular-file checks, UTF-8 decoding, and binary/NUL rejection; it does not know about line windows, protocol limits, or views. Observed-state recording is not on `ctx.fs`: after a successful read the executor emits `fs/observed`, and the `dsh-fs-policy` plugin records `{ version }` for the deriving owner. There is no `full`/`partial` view — a read at any window records the version, and freshness (not view completeness) authorizes a later write/edit. diff --git a/.agents/notes/implemented/architecture/2026-06-17-filesystem-capability-seam.zh.md b/.agents/notes/implemented/architecture/2026-06-17-filesystem-capability-seam.zh.md index ee50b36d25..a96d513d7f 100644 --- a/.agents/notes/implemented/architecture/2026-06-17-filesystem-capability-seam.zh.md +++ b/.agents/notes/implemented/architecture/2026-06-17-filesystem-capability-seam.zh.md @@ -10,11 +10,11 @@ harness 已有一个具体的 `bash` 能力 seam(`dsh-bash` / `dsh-bash-local` 这把三个独立变化的关注点耦合在了一起: -1. 文件系统契约:插件可以请求哪些操作。 +1. 文件系统约定:插件可以请求哪些操作。 2. 后端:当前是本地磁盘,未来可能是沙箱/远程/项目作用域的文件系统。 3. 消费方接口:面向模型的 `read` / `write` / `edit` schema 与结果格式化。 -如果没有 `ctx.fs` 接口,将本地文件系统访问替换为沙箱或远程后端时,即使面向模型的契约应当保持稳定,工具 schema、演示和提示词引导也会被迫变动。这还使权限/沙箱边界更难推理:一个 `cwd` 选项看起来像沙箱,但除非有显式的后端或 `tools/execute` 策略强制隔离,否则它只是一个基础路径。 +如果没有 `ctx.fs` 接口,将本地文件系统访问替换为沙箱或远程后端时,即使面向模型的约定应当保持稳定,工具 schema、演示和提示词引导也会被迫变动。这还使权限/沙箱边界更难推理:一个 `cwd` 选项看起来像沙箱,但除非有显式的后端或 `tools/execute` 策略强制隔离,否则它只是一个基础路径。 我们需要文件系统工具在成为公开包(package)接口之前,以与 bash 相同的能力 seam 形态落地。 @@ -55,15 +55,16 @@ harness 已有一个具体的 `bash` 能力 seam(`dsh-bash` / `dsh-bash-local` 根 `tool-fs` 插件通过组合各工具的注册辅助函数来注册完整的文件系统工具套件(`read`、`write` 和 `edit`)。它注入 `fs`,从不导入实现包。 -## `ctx.fs` 契约 +## `ctx.fs` 约定 `@deepseek-ai/dsh-fs` 拥有一个语义文件系统服务。它比 `readFile` / `writeFile` 更高层,这样 `tool-fs` 就不必重新实现路径解析、版本管理、文本解码、二进制拒绝、分页、原子替换、符号链接行为或字面编辑语义。 该接口涵盖以下语义操作: - 将模型/插件提供的路径解析为后端定义的目标。 +- 将解析后的目标转换为同一执行环境的规范进程路径或 `file:` URI,并在不解析其不透明键的情况下检查包含关系。 - 获取目标元数据而不读取文件内容。 -- 从目标读取有界的 UTF-8 文本页。 +- 读取完整或流式 UTF-8 文本;消费方执行各自的视图与保留上限。 - 创建或替换一个 UTF-8 文本文件。 - 通过字面替换编辑一个已有的 UTF-8 文本文件。 @@ -83,9 +84,11 @@ harness 已有一个具体的 `bash` 能力 seam(`dsh-bash` / `dsh-bash-local` - 不透明的 `targetKey`,用于陈旧守护和文件状态查找。本地后端可能使用类似 realpath 的键;远程后端可能使用工作区 URI 或文件 id。消费方禁止解析或假设它是本地绝对路径。 - `displayPath`,用于面向模型/UI 的输出。根据后端不同,它可能是本地绝对路径、工作区相对路径或远程 URI。 +即使另一项能力共享提供方的执行环境,`targetKey` 仍保持不透明。这类消费方通过提供方的 `processPath(target)`、`fileUrl(target)` 或 `contains(parent, child)` 获取所需事实;[可移植执行环境决策](2026-07-28-portable-execution-world-consumers.md)说明这些事实为何属于文件系统 seam。 + 读取和变更结果必须包含不透明的文件 `version`。本地后端从 bigint stat 元数据(`dev`、`ino`、`size`、`mtimeNs` 和 `ctimeNs`)派生令牌,因此同大小重写和 inode 替换都会可靠地使消费方失效;远程后端可以使用 revision id 或类似 hash 的令牌。`dsh-fs-policy` 插件记录版本用于陈旧检查;消费方可以展示相关元数据但禁止解释版本令牌。 -提供方返回已解码的文本:`readText` 返回整个常规文本文件,`streamText` 为大文件流式传输相同的文本语义。两者负责常规文件检查;有界的行/输出处理不是它们的职责——行窗口化、带行号渲染和总行数统计位于执行器(`dsh-tool-fs`)中,执行器通过 `ctx.fs` 读取并渲染面向模型的窗口。提供方负责 UTF-8 解码和二进制/NUL 拒绝;它不知道行窗口或视图。 +提供方返回已解码的文本:`readText` 返回整个普通文本文件,`streamText` 为大文件或消费方自有的保留上限流式传输相同的文本语义。行窗口化、字节上限、带行号渲染和总行数统计归 `dsh-tool-fs`、`dsh-lsp-local` 等消费方所有。提供方负责普通文件检查、UTF-8 解码和二进制/NUL 拒绝;它不知道行窗口、协议上限或视图。 观测状态记录不在 `ctx.fs` 上:成功读取后,执行器发出 `fs/observed`,`dsh-fs-policy` 插件为推导出的 owner 记录 `{ version }`。没有 `full`/`partial` 视图——任何窗口的读取都记录版本,新鲜度(而非视图完整性)授权后续的写入/编辑。 @@ -95,7 +98,7 @@ harness 已有一个具体的 `bash` 能力 seam(`dsh-bash` / `dsh-bash-local` 策略插件(而非 `ctx.fs`)对先前观测进行门控:`edit` 要求 owner 有先前观测(否则报 `FS_NOT_OBSERVED`),记录的版本作为 CAS 基础传给 `editText`。在策略插件缺席时,`ctx.fs` 本身是一个完整的无约束 seam(无条件写入/编辑);工具从不与策略方法耦合。 -文件系统契约失败以 `FsError extends HarnessError` 抛出,工具注册表将其转换为带结构化 `{ name, code }` 元数据的 `isError` 工具结果。`dsh-fs` 拥有此词汇,而非由每个工具各自发明消息。错误码包括 `FS_NOT_FOUND`、`FS_NOT_TEXT`、`FS_STALE_VERSION`、`FS_NOT_OBSERVED`、`FS_NOT_REGULAR_FILE`、`FS_AMBIGUOUS_EDIT`、`FS_EDIT_NOT_FOUND` 和 `FS_ABORTED`。(早期草案包含 `FS_PARTIAL_OBSERVATION`;基于新鲜度的授权没有 partial/full 区分,因此已删除。目录列表相关的错误码后来由[为文件系统 seam 添加直接目录列举能力](../../archived/architecture/2026-07-03-filesystem-directory-listing-seam.md)添加。) +文件系统约定失败以 `FsError extends HarnessError` 抛出,工具注册表将其转换为带结构化 `{ name, code }` 元数据的 `isError` 工具结果。`dsh-fs` 拥有此词汇,而非由每个工具各自发明消息。错误码包括 `FS_NOT_FOUND`、`FS_NOT_TEXT`、`FS_STALE_VERSION`、`FS_NOT_OBSERVED`、`FS_NOT_REGULAR_FILE`、`FS_AMBIGUOUS_EDIT`、`FS_EDIT_NOT_FOUND` 和 `FS_ABORTED`。(早期草案包含 `FS_PARTIAL_OBSERVATION`;基于新鲜度的授权没有 partial/full 区分,因此已删除。目录列表相关的错误码后来由[为文件系统 seam 添加直接目录列举能力](../../archived/architecture/2026-07-03-filesystem-directory-listing-seam.md)添加。) ## 工具消费方行为 @@ -116,7 +119,7 @@ harness 已有一个具体的 `bash` 能力 seam(`dsh-bash` / `dsh-bash-local` 该包通过 `ctx.systemPrompt.section(...)` 注册提示词引导,通过 `ctx.tools.register(...)` 注册 schema。工具 schema 仍通过 `SystemPrompt.assemble()` 和 `ToolRegistry.schemas()` 流入正常的提示词组装路径;无需改动 agent loop(智能体循环)。 -工具包在后端变化时保持面向模型的契约稳定:本地后端和远程后端内部可能以不同方式解析路径,但 `read` / `write` / `edit` schema 不会仅因后端变化而改变。 +工具包在后端变化时保持面向模型的约定稳定:本地后端和远程后端内部可能以不同方式解析路径,但 `read` / `write` / `edit` schema 不会仅因后端变化而改变。 默认部署要求在用 `write` 或 `edit` 更新已有文件之前先 `read`。`tool-fs` 不通过检查是否运行过名为 `read` 的工具来实现这一点:它分发 `fs/write-intent`/`fs/edit-intent` 事件(将执行上下文作为不透明 actor 传递),`dsh-fs-policy` 插件推导 owner、对先前观测进行门控并提供版本期望。任何窗口化读取都能授权后续的写入/编辑,只要文件未变。用 `write` 创建新文件不要求先前观测。 @@ -141,9 +144,9 @@ harness 已有一个具体的 `bash` 能力 seam(`dsh-bash` / `dsh-bash-local` ## 后果 -**`cwd` 可能被误认为沙箱。** 本地后端的基目录是解析默认值,而非自动的隔离边界。如果需要隔离,必须由后端契约或 `tools/execute` 上的权限/沙箱插件强制执行。 +**`cwd` 可能被误认为沙箱。** 本地后端的基目录是解析默认值,而非自动的隔离边界。如果需要隔离,必须由后端约定或 `tools/execute` 上的权限/沙箱插件强制执行。 -**接口可能变得过于本地化。** 如果 `ctx.fs` 返回 `absolutePath` 之类的字段,远程、沙箱或虚拟后端会变得尴尬。契约应暴露显示元数据,而不要求消费方理解宿主路径。 +**接口可能变得过于本地化。** 如果 `ctx.fs` 返回 `absolutePath` 之类的字段,远程、沙箱或虚拟后端会变得尴尬。约定应暴露显示元数据,而不要求消费方理解宿主路径。 **接口可能变得过于薄。** 如果 `ctx.fs` 只镜像 `node:fs` 原语,`tool-fs` 将重新实现二进制检测、分页、原子写入和编辑语义,重新制造本 Agent Note 试图避免的耦合。 @@ -151,7 +154,7 @@ harness 已有一个具体的 `bash` 能力 seam(`dsh-bash` / `dsh-bash-local` **观测状态不属于 `ctx.fs`。** 记录执行上下文看到了什么是工作流策略,而非原始文件系统 I/O。本 Agent Note 最初将其放在文件系统 seam 内部;拆分文件系统 seam Agent Note 随后确立了沙箱/远程后端不应继承面向模型的观测策略,并将其移入 `dsh-fs-policy` 插件。提供方 seam 只保留写入/编辑安全在存储层真正需要的东西——后端铸造的版本令牌和可选的版本守护变更——而策略插件拥有 owner 推导、观测状态和基于 `fs/*` 事件的读后编辑门控。 -**`resolve` 然后操作的形态每次调用多一次往返。** 每个工具可能先将路径解析为 `FsTarget`,再以单独的 `ctx.fs` 调用发起读取/写入/编辑。对本地后端来说这可以忽略(解析是内存中的路径规范化),但远程/沙箱后端可能将每步变成独立请求,使单次 `read` 变为两次网络往返。往返开销重要的后端可以在内部缓存或折叠解析,同时保持可观测契约不变。 +**`resolve` 然后操作的形态每次调用多一次往返。** 每个工具可能先将路径解析为 `FsTarget`,再以单独的 `ctx.fs` 调用发起读取/写入/编辑。对本地后端来说这可以忽略(解析是内存中的路径规范化),但远程/沙箱后端可能将每步变成独立请求,使单次 `read` 变为两次网络往返。往返开销重要的后端可以在内部缓存或折叠解析,同时保持可观测约定不变。 **观测状态持久化被推迟。** 观测状态存在于内存中(`dsh-fs-policy` 内部的 `WeakMap`),因此恢复的会话保守地要求文件在写入/编辑前重新读取,直到未来的会话事件或持久化机制使观测可回放。 diff --git a/.agents/notes/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.i18n.yaml index 3b07958faa..70c9f791f4 100644 --- a/.agents/notes/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.i18n.yaml @@ -1,6 +1,6 @@ # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: -# pnpm run verify-translation-pairing --write -2026-06-18-agent-lifecycle-and-ownership-seams.md: f190b4ba2b7f22d29f473c8a2725401ff371488e -2026-06-18-agent-lifecycle-and-ownership-seams.zh.md: dcaa319232baa8951a4f515abc6bce5611da5576 +# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.md +2026-06-18-agent-lifecycle-and-ownership-seams.md: 93247a6da7446a5a67db33423d2b766ce4cf3308 +2026-06-18-agent-lifecycle-and-ownership-seams.zh.md: e17650c7789764dfb4240132f5903795e6f86381 diff --git a/.agents/notes/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.md b/.agents/notes/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.md index f190b4ba2b..93247a6da7 100644 --- a/.agents/notes/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.md +++ b/.agents/notes/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.md @@ -47,4 +47,4 @@ The bash owner-token comparison relies on the shared `Agent.id`/`SessionId` bein ## Consequences -This touched public interfaces (`Agent`, `AgentFactory`, the bash seam) deliberately, not as a local ACP patch. The simple synchronous `Agent.send()` ergonomics were preserved; the async lifecycle path is additive, for owners that need it. +This touched public interfaces (`Agent`, `AgentFactory`, the bash seam) deliberately, not as a local ACP patch. Synchronous agent delivery remains simple; the async lifecycle path is additive for owners that need it. diff --git a/.agents/notes/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.zh.md b/.agents/notes/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.zh.md index dcaa319232..e17650c778 100644 --- a/.agents/notes/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.zh.md +++ b/.agents/notes/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.zh.md @@ -14,17 +14,17 @@ ACP(Agent Client Protocol)与 tool-bash 的若干限制是同一个缺失 se ### 1. 队列感知的 `Agent.cancel(cause?)` -`Agent` 接口新增 `cancel()` 动词——唯一的公开停止原语。(它最初与范围更窄、仅作用于步骤的 `abort()` 一同交付;后者后来因无人使用而移除,使 `cancel()` 成为唯一公开的停止工作方式。)它清空 inbox 的 queued + steering FIFO,在存在活跃轮次时中止它,并保留一个不带 cause 的 pre-run 标记,使在取得所有权前被取消的提示词永不运行,而后来的提示词仍保持独立。有效调用会在清空或中止前发出 `agent/cancel-requested`,携带类型化的 `user | parent` cause;空闲取消不发出任何事件,也不会使下一条提示词搁浅。`whenIdle()` 会在取消后达到完全停稳,ACP 的 `session/cancel` 映射到 `user`。[显式轮次取消决策](2026-07-16-explicit-turn-cancellation.md)拥有当前的 cause、signal 生命周期与协作式结算契约。 +`Agent` 接口新增 `cancel()` 动词——唯一的公开停止原语。(它最初与范围更窄、仅作用于步骤的 `abort()` 一同交付;后者后来因无人使用而移除,使 `cancel()` 成为唯一公开的停止工作方式。)它清空 inbox 的 queued + steering FIFO,在存在活跃轮次时中止它,并保留一个不带 cause 的 pre-run 标记,使在被领取前被取消的提示词永不运行,而后来的提示词仍保持独立。有效调用会在清空或中止前发出 `agent/cancel-requested`,携带类型化的 `user | parent` cause;空闲取消不发出任何事件,也不会使下一条提示词搁浅。`whenIdle()` 会在取消后达到完全停稳,ACP 的 `session/cancel` 映射到 `user`。[显式轮次取消决策](2026-07-16-explicit-turn-cancellation.md)规定了当前的 cause、signal 生命周期与协作式结算约定。 ### 2. `AgentHandle` 异步释放器 -`ctx.agents.create`/`resume`(以及 `AgentFactory` 接口)返回 `AgentHandle = { agent: Agent; dispose(): Promise }`。释放器是一种**消费方能力**——仅持有裸 `Agent` 的注册表观察者无法将其拆除。调用方 fiber 和已注册的 factory 提供方是结构上的共同所有者:调用方卸载强制结构化所有权,而提供方卸载必须停止旧实例,因为其实例作用域的依赖 surface 通过该提供方解析。三条路径都会进入同一个 memoize 的拆除过程:停止循环、等待其退出与空闲刷写完成(完全停稳,而非仅把状态翻转为 `disposed`)、分离 agent、分离其会话,然后解除其 scope。每个公开 ID 在其精确注册表条目分离时变得可复用;不存在独立的保留释放阶段。由配置创建的 agent 已归 `AgentLoop` fiber 所有(handle 被丢弃)。ACP 在其 `SessionRecord` 中保存每个全新会话的释放器,并在断连或插件拆除时运行它,因此单纯的客户端断连不会留下已注册 agent 或会话存储条目。在与关闭的竞态中落败的创建流程会 dispose 其尚未发布的 handle。 +`ctx.agents.create`/`resume`(以及 `AgentFactory` 接口)返回 `AgentHandle = { agent: Agent; dispose(): Promise }`。释放器是一种**消费方能力**——仅持有裸 `Agent` 的注册表观察者无法将其拆除。调用方 fiber 和已注册的 factory 提供方是结构上的共同所有者:调用方卸载强制结构化所有权,而提供方卸载必须停止旧实例,因为其实例作用域的依赖 surface 通过该提供方解析。三条路径都会进入同一个记忆化的拆除过程:停止循环、等待其退出与空闲刷写完成(完全停稳,而非仅把状态翻转为 `disposed`)、分离 agent、分离其会话,然后解除其 scope。每个公开 ID 在其精确注册表条目分离时变得可复用;不存在独立的保留释放阶段。由配置创建的 agent 已归 `AgentLoop` fiber 所有(handle 被丢弃)。ACP 在其 `SessionRecord` 中保存每个全新会话的释放器,并在断连或插件拆除时运行它,因此单纯的客户端断连不会留下已注册 agent 或会话存储条目。在与关闭的竞态中落败的创建流程会 dispose 其尚未发布的 handle。 **拆除顺序对持久性至关重要**,实现将会话生命周期折叠进 agent 的单个复合 Cordis effect(`SessionStore.prepare`/`enter`/`announce`,取代兄弟 effect 拆分)。fiber 卸载会并发释放兄弟 effect(`Promise.all`),这会让会话存储的 append 发布钩子移除与循环关闭时的 `session/flush` 竞争,从而丢失关闭的 `turn/end`;在一个 effect 内,释放器作为有序的 LIFO 链运行(停止循环 + `await agent.done` 在会话分离之前),因此无论 handle 的 `dispose()` 还是 fiber 卸载,都会捕获循环的最终刷写。被隔离的 `agent/disposed` 和 `session/disposed` 通知无法拒绝该链或跳过后续拆除。 ### 3. Bash seam 中的所有者令牌 -后台任务所有权从 `tool-bash` 插件本地的 `Map` 移入执行器。`BashExecRequest` 新增可选的 `owner?: string`;解析后的 `BashExecSpec` 将其作为必需但可空的 `owner: string | undefined` 携带(被遗忘的 owner 是可见的 `undefined`,而非静默缺失的属性)。执行器把 token 存在任务上,并通过新的 `BashExecutor.ownerOf(id): string | undefined` seam 暴露它(不放在公开的 `BashTask` 上——只有一条读取路径,没有冗余 API)。`tool-bash` 完全删除其 `Map`:它在 `start` 时将 `exec.agent?.id`(共享的注册表/会话 id)盖章为 owner,`bash_output`/`bash_kill` 则以 `!== undefined` 语义把 `ctx.bash.ownerOf(id)` 与调用方 token 比较(空字符串 token 仍是真实 owner)。完成通知通过扫描 `ctx.get('agents')?.list()` 查找 `agent.id === ownerToken` 的存活 agent(经 `ctx.get` 读取——`onTaskDone` 运行在 bash fiber 这一外部 fiber 上,直接使用 `ctx.agents` proxy 会抛异常)。由于所有权现在存活在执行器的任务上(随 `dsh-bash` fiber dispose),它能跨越 `tool-bash` HMR 重载,关闭旧的 `XXX(tool-bash-owner-hmr)` 缺口。(`onTaskDone` 监听器仍受 `tool-bash` 的 `apply` effect 约束,因此落在重载间隙的完成仍会丢失一条通知——既有的重载间隙丢失——但所有权隔离本身已经不受 HMR 影响。) +后台任务所有权从 `tool-bash` 插件本地的 `Map` 移入执行器。`BashExecRequest` 新增可选的 `owner?: string`;解析后的 `BashExecSpec` 将其作为必需但可空的 `owner: string | undefined` 携带(被遗忘的 owner 是可见的 `undefined`,而非静默缺失的属性)。执行器把 token 存在任务上,并通过新的 `BashExecutor.ownerOf(id): string | undefined` seam 暴露它(不放在公开的 `BashTask` 上——只有一条读取路径,没有冗余 API)。`tool-bash` 完全删除其 `Map`:它在 `start` 时将 `exec.agent?.id`(共享的注册表/会话 id)盖章为 owner,`bash_output`/`bash_kill` 则以 `!== undefined` 语义把 `ctx.bash.ownerOf(id)` 与调用方 token 比较(空字符串 token 仍是真实 owner)。完成通知通过扫描 `ctx.get('agents')?.list()` 查找 `agent.id === ownerToken` 的存活 agent(经 `ctx.get` 读取——`onTaskDone` 运行在 bash fiber 这一外部 fiber 上,直接使用 `ctx.agents` proxy 会抛异常)。由于所有权现在保存在执行器的任务上(随 `dsh-bash` fiber dispose),它能跨越 `tool-bash` HMR 重载,关闭旧的 `XXX(tool-bash-owner-hmr)` 缺口。(`onTaskDone` 监听器仍受 `tool-bash` 的 `apply` effect 约束,因此落在重载间隙的完成仍会丢失一条通知——既有的重载间隙丢失——但所有权隔离本身已经不受 HMR 影响。) ## 验证 @@ -37,7 +37,7 @@ ACP(Agent Client Protocol)与 tool-bash 的若干限制是同一个缺失 se ## 会话所有者令牌在存活 agent 中唯一 -bash 所有者 token 比较依赖共享的 `Agent.id`/`SessionId` 在存活 agent 中唯一。并发的同 ID 操作可以都私下准备,但发布会依次进入会话和 agent;`SessionStore.enter()` 拒绝重复的存活会话 id,每个失败事务都回滚自己的私有状态。因此程序化调用方无法发布两个共享同一会话 token 的存活 agent。访问*策略*(token 比较)留在消费方 `tool-bash`;bash seam 只存储不透明的 `owner` 字符串且从不解释它——这是正确的接口/实现/消费方拆分。 +bash 所有者 token 比较依赖共享的 `Agent.id`/`SessionId` 在存活 agent 中唯一。并发的同 ID 操作可以都私下准备,但发布时会依次登记会话和 agent;`SessionStore.enter()` 拒绝重复的存活会话 id,每个失败事务都回滚自己的私有状态。因此程序化调用方无法发布两个共享同一会话 token 的存活 agent。访问*策略*(token 比较)留在消费方 `tool-bash`;bash seam 只存储不透明的 `owner` 字符串且从不解释它——这是正确的接口/实现/消费方拆分。 ## 曾考虑的替代方案 @@ -47,4 +47,4 @@ bash 所有者 token 比较依赖共享的 `Agent.id`/`SessionId` 在存活 agen ## 后果 -本变更有意触及公开接口(`Agent`、`AgentFactory`、bash seam),而非作为 ACP 的局部补丁。同步 `Agent.send()` 的简洁易用性得以保留;异步生命周期路径是增量添加的,供需要它的所有者使用。 +本变更有意触及公开接口(`Agent`、`AgentFactory`、bash seam),而非作为 ACP 的局部补丁。同步 agent 交付仍然简单;异步生命周期路径是增量添加的,供需要它的所有者使用。 diff --git a/.agents/notes/implemented/architecture/2026-06-18-session-surface.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-18-session-surface.i18n.yaml index 4946fc219a..ce26042716 100644 --- a/.agents/notes/implemented/architecture/2026-06-18-session-surface.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-06-18-session-surface.i18n.yaml @@ -1,6 +1,6 @@ # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: -# pnpm run verify-translation-pairing --write -2026-06-18-session-surface.md: 80034881d0112076759a68737b5931c8ff659d15 -2026-06-18-session-surface.zh.md: 26a3119faf0b6988049a7599ea9551a8ae65d63d +# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-06-18-session-surface.md +2026-06-18-session-surface.md: 1bb3baac5e9bea3f657cbd3be2623223bda78ce2 +2026-06-18-session-surface.zh.md: b967ad467e58ed4f4b4009fe4746f1b8b6b22f25 diff --git a/.agents/notes/implemented/architecture/2026-06-18-session-surface.md b/.agents/notes/implemented/architecture/2026-06-18-session-surface.md index 80034881d0..1bb3baac5e 100644 --- a/.agents/notes/implemented/architecture/2026-06-18-session-surface.md +++ b/.agents/notes/implemented/architecture/2026-06-18-session-surface.md @@ -27,7 +27,7 @@ export type SurfaceOp = | { op: 'replace'; start: number; end: number } // shadow [start, end] inclusive ``` -1. **Append** — add the new event seq to the tail. Used by `user/message`, `assistant/message`, `tool/result`, `context/message`, `steering/message`. The loop passes `surfaceOp: 'append'` on all such appends and records `sourceEventSeqs` where applicable: every successful `assistant/message` records its complete `assistant/chunk` source set, including `[]`, while `tool/result` records its `tool/call` source. +1. **Append** — add the new event seq to the tail. Used by `user/message`, `assistant/message`, `tool/result`, `context/message`. The loop passes `surfaceOp: 'append'` on all such appends and records `sourceEventSeqs` where applicable: every successful `assistant/message` records its complete `assistant/chunk` source set, including `[]`, while `tool/result` records its `tool/call` source. 2. **Replace** — remove entries from `start` through `end` (both inclusive) and insert the new event seq in their place. Both `start` and `end` must be present in the current surface; `start === end` replaces one entry. The event's `sourceEventSeqs` must contain every shadowed surface seq. The shadowed events remain in the log but are no longer on the surface. @@ -64,9 +64,9 @@ Every surface-eligible event must carry `surfaceOp` or it would disappear from d - **`packages/core/session`**: `surface.ts` (`SurfaceManager`) maintains one ordered seq array for candidate acceptance and live projection; `SessionSurface` is its readonly public view. `SurfaceOp`/`SurfaceIntent` and the top-level session-event fields record how entries join it. `append()` requires a `SurfaceIntent` for surface events, `deriveMessages()` walks the surface as the sole derivation path, and `repair.ts` emits surface-aware closers. The seed constructor rejects a surface-eligible seed event missing its `surfaceOp` marker (see § Invariants). - **`packages/core/agent-loop`**: All surface-capable appends pass surface opts. Chunk seqs are collected for `assistant/message` provenance; `tool/call` seqs are captured for `tool/result` provenance. -- **`packages/session-persistence/session-persistence-sqlite`**: Two new nullable TEXT columns (`source_event_seqs`, `surface_op`) on the `events` table; `SCHEMA_VERSION` bumped (bump-and-reject, no migration). -- **`packages/session-persistence/session-persistence-jsonl`**: No changes required. -- **`packages/session-persistence/session-persistence`**: Abstract interface unchanged. +- **`packages/session/session-persistence-sqlite`**: Two new nullable TEXT columns (`source_event_seqs`, `surface_op`) on the `events` table; `SCHEMA_VERSION` bumped (bump-and-reject, no migration). +- **`packages/session/session-persistence-jsonl`**: No changes required. +- **`packages/session/session-persistence`**: Abstract interface unchanged. The surface is the foundation for future history manipulation. A compaction or tool-result-prune plugin appends one of the existing message-producing event types (a `user/message` carrying the summary, say) with `surfaceOp: { op: 'replace', start, end }` and `sourceEventSeqs` covering the shadowed entries — the new event takes the range's place on the surface while the plugin's own trace events (e.g. `compaction/start`, `compaction/end`) stay off it. Replay preserves the decision deterministically. diff --git a/.agents/notes/implemented/architecture/2026-06-18-session-surface.zh.md b/.agents/notes/implemented/architecture/2026-06-18-session-surface.zh.md index 26a3119faf..b967ad467e 100644 --- a/.agents/notes/implemented/architecture/2026-06-18-session-surface.zh.md +++ b/.agents/notes/implemented/architecture/2026-06-18-session-surface.zh.md @@ -27,13 +27,13 @@ export type SurfaceOp = | { op: 'replace'; start: number; end: number } // shadow [start, end] inclusive ``` -1. **Append**:在尾部追加新事件的 seq。`user/message`、`assistant/message`、`tool/result`、`context/message`、`steering/message` 使用此操作。agent loop(智能体循环)在所有此类追加上传入 `surfaceOp: 'append'`,并在适用时记录 `sourceEventSeqs`:每个成功的 `assistant/message` 都记录完整的 `assistant/chunk` 来源集合(包括 `[]`),而 `tool/result` 记录其 `tool/call` 来源。 +1. **Append**:在尾部追加新事件的 seq。`user/message`、`assistant/message`、`tool/result`、`context/message` 使用此操作。agent loop(智能体循环)在所有此类追加上传入 `surfaceOp: 'append'`,并在适用时记录 `sourceEventSeqs`:每个成功的 `assistant/message` 都记录完整的 `assistant/chunk` 来源集合(包括 `[]`),而 `tool/result` 记录其 `tool/call` 来源。 2. **Replace**:移除从 `start` 到 `end`(两端包含)的条目,并在其位置插入新事件的 seq。`start` 和 `end` 都必须存在于当前 surface;`start === end` 表示替换单个条目。该事件的 `sourceEventSeqs` 必须包含所有被遮蔽的 surface seq。被遮蔽的事件仍留在日志中,但不再出现在 surface 上。 ### SurfaceManager:基于增量,而非全量重建 -一个 `Session` 拥有一个 `SurfaceManager`,后者维护事件 seq 的有序 `number[]`。管理器会在提交前校验每个种子或追加候选项而不应用它,然后只处理上次同步之后已经提交的事件,而不重新扫描整个日志。`Session.surface` 通过只读的 `SessionSurface` 契约暴露同一个管理器,因此接纳、派生历史、压缩与工作区上下文共享同一份增量状态。Replace 按数组位置找到两端都包含的端点,并把替换 seq splice 到该范围;不会用第二个管理器、链接对象或 seq 到节点的 map 来重复表达顺序。 +一个 `Session` 拥有一个 `SurfaceManager`,后者维护事件 seq 的有序 `number[]`。管理器会在提交前校验每个种子或追加候选项而不应用它,然后只处理上次同步之后已经提交的事件,而不重新扫描整个日志。`Session.surface` 通过只读的 `SessionSurface` 约定暴露同一个管理器,因此接纳、派生历史、压缩与工作区上下文共享同一份增量状态。Replace 按数组位置定位两个端点(均包含在范围内),并把替换 seq splice 到该范围;不会用第二个管理器、链接对象或 seq 到节点的 map 来重复表达顺序。 无新事件时增量处理为 O(1),有新事件到达时为 O(新事件数)。 @@ -49,9 +49,9 @@ export type SurfaceOp = ### 不变式 -`Session` 在始终启用的 seed/append 边界校验 `sourceEventSeqs` 与 `surfaceOp`:只有 `assistant/message` 可以使用空的溯源列表;引用必须唯一、更早且已知;替换端点必须存在于 surface 顺序中;溯源必须覆盖每个被遮蔽的节点。这些是单记录接纳与存储投影规则,不是可选的不变式服务贡献。 +`Session` 在始终启用的 seed/append 边界校验 `sourceEventSeqs` 与 `surfaceOp`:只有 `assistant/message` 可以使用空的溯源列表;引用必须唯一、更早且已知;替换端点必须存在于 surface 顺序中;溯源必须覆盖每个被遮蔽的节点。这些是单记录接纳与存储投影规则,不是由可选的不变式服务提供的规则。 -每个 surface 可达事件都必须携带 `surfaceOp`,否则它将从派生历史中消失。类型化的 `append` 重载对字面事件类型强制执行此规则;`append` 和种子构造函数中的运行时检查覆盖宽化联合类型和加载的日志。按照预发布格式策略,无效的种子被拒绝而非升级。 +每个可进入 surface 的事件都必须携带 `surfaceOp`,否则它将从派生历史中消失。类型化的 `append` 重载对字面事件类型强制执行此规则;`append` 和种子构造函数中的运行时检查覆盖宽化联合类型和加载的日志。按照预发布格式策略,无效的种子被拒绝而非升级。 ## 曾考虑的替代方案 @@ -62,11 +62,11 @@ export type SurfaceOp = ## 后果 -- **`packages/core/session`**:`surface.ts`(`SurfaceManager`)维护一个用于候选接纳和实时投影的有序 seq 数组;`SessionSurface` 是其只读公共视图。`SurfaceOp`/`SurfaceIntent` 与顶层会话事件字段记录条目如何加入它。`append()` 要求 surface 事件携带 `SurfaceIntent`,`deriveMessages()` 以遍历 surface 作为唯一派生路径,`repair.ts` 则发出 surface 感知的闭合事件。种子构造函数拒绝缺少 `surfaceOp` 标记的 surface 可达种子事件(见「不变式」一节)。 -- **`packages/core/agent-loop`**:所有 surface 可达的追加操作传入 surface 选项。收集分片 seq 用于 `assistant/message` 溯源;捕获 `tool/call` seq 用于 `tool/result` 溯源。 -- **`packages/session-persistence/session-persistence-sqlite`**:`events` 表新增两个可空 TEXT 列(`source_event_seqs`、`surface_op`);`SCHEMA_VERSION` 递增(bump-and-reject,无迁移)。 -- **`packages/session-persistence/session-persistence-jsonl`**:无需改动。 -- **`packages/session-persistence/session-persistence`**:抽象接口不变。 +- **`packages/core/session`**:`surface.ts`(`SurfaceManager`)维护一个用于候选接纳和实时投影的有序 seq 数组;`SessionSurface` 是其只读公共视图。`SurfaceOp`/`SurfaceIntent` 与顶层会话事件字段记录条目如何加入它。`append()` 要求 surface 事件携带 `SurfaceIntent`,`deriveMessages()` 以遍历 surface 作为唯一派生路径,`repair.ts` 则发出 surface 感知的闭合事件。种子构造函数拒绝缺少 `surfaceOp` 标记的可进入 surface 的种子事件(见「不变式」一节)。 +- **`packages/core/agent-loop`**:所有涉及 surface 事件的追加操作都传入 surface 选项。收集分片 seq 用于 `assistant/message` 溯源;捕获 `tool/call` seq 用于 `tool/result` 溯源。 +- **`packages/session/session-persistence-sqlite`**:`events` 表新增两个可空 TEXT 列(`source_event_seqs`、`surface_op`);`SCHEMA_VERSION` 递增(bump-and-reject,无迁移)。 +- **`packages/session/session-persistence-jsonl`**:无需改动。 +- **`packages/session/session-persistence`**:抽象接口不变。 Surface 是未来历史操纵的基础。压缩或 tool-result-prune 插件追加一个既有的消息产出事件类型(例如一条携带摘要的 `user/message`),附带 `surfaceOp: { op: 'replace', start, end }` 和覆盖被遮蔽条目的 `sourceEventSeqs`——新事件在 surface 上取代该范围的位置,而插件自身的 trace 事件(如 `compaction/start`、`compaction/end`)不进入 surface。回放以确定性方式保留该决策。 diff --git a/.agents/notes/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.i18n.yaml index d8dae837fe..84edacb9dc 100644 --- a/.agents/notes/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.i18n.yaml @@ -1,6 +1,6 @@ # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: -# pnpm run verify-translation-pairing --write -2026-06-18-shared-persistence-write-coordinator.md: 4632351a6f39c44c9ba8af58d508d4665b9e9279 -2026-06-18-shared-persistence-write-coordinator.zh.md: 40a7144038ac0db4ca6cac651c0a3cef5de4afa9 +# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.md +2026-06-18-shared-persistence-write-coordinator.md: 12131ebf8380fb8ba816618f0cbaf72cb004623a +2026-06-18-shared-persistence-write-coordinator.zh.md: 0a7fbf351171d305b3b6245832a0b35a283c7c1d diff --git a/.agents/notes/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.md b/.agents/notes/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.md index 4632351a6f..12131ebf83 100644 --- a/.agents/notes/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.md +++ b/.agents/notes/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.md @@ -10,11 +10,11 @@ English | [中文](2026-06-18-shared-persistence-write-coordinator.zh.md) ## Decision -Extract a backend-agnostic `PersistenceCoordinator` into `dsh-session-persistence`. The coordinator owns the orchestration once; each first-party backend composes one (`new PersistenceCoordinator(ctx, this)`), implements a small `PersistenceBackend` hook interface, and delegates its stateful public methods (`create`/`append`/`load`/`inspect`) to it. Backend-owned metadata and revision listing bypass the coordinator. +Extract a backend-agnostic `PersistenceCoordinator` into `dsh-session-persistence`. The coordinator owns the orchestration once; each first-party backend composes one (`new PersistenceCoordinator(ctx, this)`), implements a small `PersistenceBackend` hook interface, and delegates its stateful public methods (`create`/`append`/`prepare`/`load`/`inspect`/`readFrom`) to it. Backend-owned metadata and revision listing bypass the coordinator. -Composition, not inheritance. The coordinator is a concrete class the backend holds, not a base class the backend extends. The Agent Note's risk — "a coordinator must not make unusual backends fight an inheritance hierarchy" — is avoided: a backend exposes only the hooks and cannot reach the coordinator's private orchestration state. A third-party backend MAY still implement the abstract service directly without the coordinator, including the non-mutating `inspect` contract used by read models. +Composition, not inheritance. The coordinator is a concrete class the backend holds, not a base class the backend extends. The Agent Note's risk — "a coordinator must not make unusual backends fight an inheritance hierarchy" — is avoided: a backend exposes only the hooks and cannot reach the coordinator's private orchestration state. A third-party backend MAY still implement the abstract service directly without the coordinator, including immutable logical inspection and the default preparation fallback through `load`. -The coordinator holds one controller for each exact live `Session`; the controller combines initialization, pending events, and the shared flush promise. Each `session/event` starts an eager drain, and `session/flush` observes quiescence rather than initiating the ordinary write path. The [flush-controller simplification](../simplification/2026-07-23-collapse-persistence-flush-state.md) owns this lifecycle. +The coordinator holds one lifecycle entry for each exact live `Session`: initialization plus a package-private write controller that owns pending events, a fixed batching deadline, the active write, failure retention, and the shared flush barrier. Each `session/event` enters that bounded write path, and `session/flush` bypasses the wait to observe quiescence. The [flush-controller simplification](../simplification/2026-07-23-collapse-persistence-flush-state.md) owns controller consolidation; the [bounded batching decision](2026-08-08-bounded-session-persistence-write-batching.md) owns scheduling cadence. The coordinator retires a session from `session/disposed`: it waits for the controller's initialization and current flush, serializes a final drain, and removes the controller and owned per-id state only after success. A failure leaves the controller discoverable for backend teardown to retry. Settled per-id chain tails remove themselves only when they are still current, so a completion cannot erase a newer operation for the same id. Backend teardown unregisters write-path listeners, flushes every remaining controller, awaits per-id operations, and then closes the backend. @@ -23,9 +23,9 @@ The coordinator retires a session from `session/disposed`: it waits for the cont Five required members plus an optional lifecycle hook form the only boundary between the coordinator and storage: - `name` — backend label for the dispose-failure `AggregateError`. -- `loadStored(id)` — read one stored prefix by id across every storage scope (every JSONL project directory; SQLite's id is globally unique). Resume/load, non-mutating inspection, live adoption, and the create-collision probe share this lookup. The coordinator asserts the returned id and rejects a stored/live cwd mismatch before repair or state publication. +- `loadStored(id)` — read one stored prefix by id across every storage scope (every JSONL project directory; SQLite's id is globally unique). Preparation, logical load/inspection, physical suffix reads, live adoption, and the create-collision probe share this lookup. The coordinator asserts the returned id and rejects a stored/live cwd mismatch before repair or state publication. - `appendBatch(meta, events, isMaterialized)` — durably append a contiguous batch, lazily materializing the session ATOMICALLY when not yet materialized (the materialize-write and the first event batch must commit together — a crash between them must not leave a materialized-but-empty session; this is why there is no separate `materialize` hook). -- `commitRepair(meta, tornMarker, closers)` — make a crash repair durable: truncate the torn tail (iff `tornMarker !== undefined`) and append `closers`. **NOT required to be atomic** — JSONL legitimately truncates-then-appends in two fsync'd steps, SQLite does DELETE+INSERT in one transaction. Used by `load` (truncate + synthetic closers) and live-adoption (truncate only, `closers = []`). +- `commitRepair(meta, tornMarker, closers)` — make a crash repair durable: truncate the torn tail (iff `tornMarker !== undefined`) and append `closers`. **NOT required to be atomic** — JSONL legitimately truncates-then-appends in two fsync'd steps, SQLite does DELETE+INSERT in one transaction. Used by `prepare`/`load` (truncate + synthetic closers) and live-adoption (truncate only, `closers = []`). - `list()` — list all stored metadata. - `close?()` — optional lifecycle teardown (SQLite closes its db handle; JSONL omits it), awaited in the dispose effect AFTER the quiescence drain so a close failure never masks a drain error. @@ -35,7 +35,7 @@ The single design choice that keeps the seam clean: the crash-repair "where is t ## Testing -The shared `runPersistenceContract` (public-API contract) runs for every backend and proves that `inspect` leaves interrupted logs and revisions unchanged before `load` performs recovery. `runCoordinatorContract` (`tests/coordinator-contract.ts`) covers adoption, HMR, collision, session and backend disposal drains, and crash-tail repair through an in-memory reference, JSONL, and SQLite. Coordinator-specific tests cover eager follow-up batches, live-controller cleanup, same-id chain-tail races, failed-drain retry, and close ordering. The per-backend specs retain storage mechanics only. A through-coordinator torn-tail repair test per real backend keeps the opaque-marker branch covered because the contract crash case produces synthetic closers without a torn marker. +The shared `runPersistenceContract` (public-API contract) runs for every backend and proves that `inspect` balances an interrupted logical view without changing storage or revisions before `prepare` or `load` commits recovery. `runCoordinatorContract` (`tests/coordinator-contract.ts`) covers adoption, HMR, collision, session and backend disposal drains, and crash-tail repair through an in-memory reference, JSONL, and SQLite. `persistence.spec.ts`, `preparations.spec.ts`, and `write-behind.spec.ts` cover preparation reuse and reservation, bounded prepared-state eviction, fixed-window follow-up batches, live-controller cleanup, same-id chain-tail races, failed-batch retry, and close ordering. The per-backend specs retain storage mechanics only. A through-coordinator torn-tail repair test per real backend keeps the opaque-marker branch covered because the contract crash case produces synthetic closers without a torn marker. ## Alternatives considered @@ -44,4 +44,4 @@ The shared `runPersistenceContract` (public-API contract) runs for every backend ## Consequences -The coordinator adds one indirection, an opaque torn marker, and detached session-retirement tasks, but centralizes correctness-heavy orchestration previously duplicated by every backend. Session disposal remains an observe-only event, so the session owner does not await persistence retirement; the coordinator contains failures, preserves pending events in the live controller, and makes backend teardown the quiescence boundary. Its hook surface stays narrow: identity, adoption, collision checks, and non-mutating inspection reuse `loadStored`; materialization stays atomic inside `appendBatch`; and listing bypasses the coordinator. Read models use `inspect` rather than `load`, so observing a persisted open turn cannot race a new live owner by committing interruption closers. New backends implement storage primitives rather than copy the eager write lifecycle. +The coordinator adds one indirection, an opaque torn marker, detached session-retirement tasks, and bounded prepared Session state, but centralizes correctness-heavy orchestration previously duplicated by every backend. Session disposal remains an observe-only event, so the session owner does not await persistence retirement; the coordinator contains failures, preserves pending events in the live controller, and makes backend teardown the quiescence boundary. Its hook surface stays narrow: identity, adoption, collision checks, preparation, and immutable inspection reuse `loadStored`; materialization stays atomic inside `appendBatch`; and listing bypasses the coordinator. Read models use `inspect` rather than `load`, so observing a persisted open turn does not commit interruption closers; the [Session preparation decision](2026-08-05-session-preparation.md) owns reuse, reservation, and publication. New backends implement storage primitives rather than copy the bounded write lifecycle. diff --git a/.agents/notes/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.zh.md b/.agents/notes/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.zh.md index 40a7144038..0a7fbf3511 100644 --- a/.agents/notes/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.zh.md +++ b/.agents/notes/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.zh.md @@ -6,15 +6,15 @@ Status: implemented ## 问题 -`dsh-session-persistence-jsonl` 与 `dsh-session-persistence-sqlite` 有意在不同存储介质上证明同一份 `SessionPersistence` 契约,但它们重复实现了写入路径编排:每会话状态、`session/created` 接管、后端特定的前缀读取、write-behind 控制、按 id 串行执行操作、HMR(热模块替换)种子注入与 dispose(资源释放)排空。纯粹的种子前缀碰撞检查与可序列化守卫已迁入 seam 包;剩余的编排仍然对正确性要求很高,且同样的修复被应用了两次。唯一的差异在于存储原语(写字节 vs. INSERT 行)。 +`dsh-session-persistence-jsonl` 与 `dsh-session-persistence-sqlite` 有意在不同存储介质上证明同一份 `SessionPersistence` 约定,但它们重复实现了写入路径编排:每会话状态、`session/created` 接管、后端特定的前缀读取、write-behind 控制、按 id 串行执行操作、HMR(热模块替换)种子注入与 dispose(资源释放)排空。纯粹的种子前缀碰撞检查与可序列化守卫已迁入 seam 包;剩余的编排仍然对正确性要求很高,且同样的修复被应用了两次。唯一的差异在于存储原语(写字节 vs. INSERT 行)。 ## 决策 -将一个后端无关的 `PersistenceCoordinator` 提取到 `dsh-session-persistence` 中。协调器统一拥有编排逻辑;每个第一方后端组合一个协调器实例(`new PersistenceCoordinator(ctx, this)`),实现一个小型 `PersistenceBackend` 钩子接口,并将其有状态的公开方法(`create`/`append`/`load`/`inspect`)委托给协调器。由后端拥有的元数据与修订版本列举会绕过协调器。 +将一个后端无关的 `PersistenceCoordinator` 提取到 `dsh-session-persistence` 中。协调器统一拥有编排逻辑;每个第一方后端组合一个协调器实例(`new PersistenceCoordinator(ctx, this)`),实现一个小型 `PersistenceBackend` 钩子接口,并将其有状态的公开方法(`create`/`append`/`prepare`/`load`/`inspect`/`readFrom`)委托给协调器。由后端拥有的元数据与修订版本列举会绕过协调器。 -组合,而非继承。协调器是后端持有的具体类,不是后端继承的基类。本 Agent Note 的风险——「协调器不得让非常规后端与继承层级作斗争」——由此规避:后端只暴露钩子,无法触及协调器的私有编排状态。第三方后端仍然可以完全不使用协调器、直接实现抽象服务,包括供读模型使用、不修改状态的 `inspect` 契约。 +组合,而非继承。协调器是后端持有的具体类,不是后端继承的基类。本 Agent Note 的风险——「协调器不得让非常规后端与继承层级作斗争」——由此规避:后端只暴露钩子,无法触及协调器的私有编排状态。第三方后端仍然可以完全不使用协调器、直接实现抽象服务,包括不修改状态的逻辑检查,以及通过 `load` 实现的默认准备回退。 -协调器为每个确切的存活 `Session` 持有一个控制器;该控制器统合初始化、待处理事件与共享 flush promise。每个 `session/event` 都会立即启动排空,而 `session/flush` 只观察完全停稳,不会发起常规写入路径。[flush 控制器简化](../simplification/2026-07-23-collapse-persistence-flush-state.md)定义该生命周期。 +协调器为每个存活的 `Session` 实例持有一个生命周期条目:初始化,加上一个包私有写入控制器,后者负责待处理事件、固定批处理截止时间、活跃写入、失败保留和共享 flush 屏障。每个 `session/event` 都进入这条有界写入路径,`session/flush` 则绕过等待以观察完全停稳。控制器归并由 [flush 控制器简化](../simplification/2026-07-23-collapse-persistence-flush-state.md)定义;调度节奏由[有界批处理决策](2026-08-08-bounded-session-persistence-write-batching.md)定义。 协调器通过 `session/disposed` 退役会话:它等待控制器完成初始化和当前 flush,串行执行最后一次排空,且仅在成功后才移除控制器与其拥有的每 id 状态。失败时保持控制器可被找到,以供后端 teardown(拆除)重试。每个 id 的已结算链尾仅在其仍是当前链尾时才移除自身,因此旧操作完成后不会抹除同一 id 的新操作。后端 teardown 会注销写入路径监听器、flush 每个剩余的控制器、等待所有按 id 串行化的操作,最后关闭后端。 @@ -23,9 +23,9 @@ Status: implemented 五个必需成员加一个可选的生命周期钩子,构成协调器与存储之间唯一的边界: - `name`——后端标签,用于 dispose 失败时的 `AggregateError`。 -- `loadStored(id)`——按 id 跨所有存储范围读取一个已存储前缀(JSONL 的所有项目目录;SQLite 的 id 全局唯一)。恢复/加载、不修改状态的检查、存活会话接管与创建碰撞探测共用此查找。协调器会断言返回的 id,并在修复或发布状态之前拒绝已存储记录与存活会话的 cwd 不匹配。 -- `appendBatch(meta, events, isMaterialized)`——持久追加一个连续批次,在尚未物化时原子地惰性物化会话(物化写入与首批事件必须一起提交——崩溃不得留下一个已物化但为空的会话;这就是为什么没有单独的 `materialize` 钩子)。 -- `commitRepair(meta, tornMarker, closers)`——使崩溃修复持久化:截断损坏的尾部(当且仅当 `tornMarker !== undefined`)并追加 `closers`。**不要求原子性**——JSONL 合理地分两步 fsync(先截断再追加),SQLite 在一个事务中完成 DELETE+INSERT。用于 `load`(截断 + 合成 closers)和 live-adoption(仅截断,`closers = []`)。 +- `loadStored(id)`——按 id 跨所有存储范围读取一个已存储前缀(JSONL 的所有项目目录;SQLite 的 id 全局唯一)。准备、逻辑加载/检查、物理后缀读取、存活会话接管与创建碰撞探测共用此查找。协调器会断言返回的 id,并在修复或发布状态之前拒绝已存储记录与存活会话的 cwd 不匹配。 +- `appendBatch(meta, events, isMaterialized)`——持久追加一个连续批次,在尚未物化时原子地惰性物化会话(物化写入与首批事件必须一起提交——二者之间发生崩溃时,不得留下一个已物化但为空的会话;这就是为什么没有单独的 `materialize` 钩子)。 +- `commitRepair(meta, tornMarker, closers)`——使崩溃修复持久化:截断损坏的尾部(当且仅当 `tornMarker !== undefined`)并追加 `closers`。**不要求原子性**——JSONL 合理地分两步 fsync(先截断再追加),SQLite 在一个事务中完成 DELETE+INSERT。用于 `prepare`/`load`(截断 + 合成 closers)和 live-adoption(仅截断,`closers = []`)。 - `list()`——列出所有已存储的元数据。 - `close?()`——可选的生命周期清理(SQLite 关闭 db 句柄;JSONL 省略),在 dispose effect 中于排空至完全停稳之后被 await,因此 close 失败不会掩盖排空错误。 @@ -35,13 +35,13 @@ Status: implemented ## 测试 -共享的 `runPersistenceContract`(公开 API 契约)为每个后端运行,并证明在 `load` 执行恢复之前,`inspect` 会保持被中断的日志与修订版本不变。`runCoordinatorContract`(`tests/coordinator-contract.ts`)通过内存参考实现、JSONL 与 SQLite 覆盖接管、HMR、碰撞、会话与后端 dispose 排空,以及崩溃尾部修复。协调器专属测试覆盖立即执行的后续批次、存活控制器清理、同 id 链尾竞态、排空失败重试与关闭顺序。各后端自身的测试规格只保留存储机制。每个真实后端都有一个经由协调器的崩溃尾部修复测试,以覆盖不透明 marker 分支,因为契约中的崩溃用例会产生合成 closers,却不会产生 torn marker。 +共享的 `runPersistenceContract`(公开 API 约定)为每个后端运行,并证明 `inspect` 会配平被中断的逻辑视图但不改变存储或修订版本,随后由 `prepare` 或 `load` 提交恢复。`runCoordinatorContract`(`tests/coordinator-contract.ts`)通过内存参考实现、JSONL 与 SQLite 覆盖接管、HMR、碰撞、会话与后端 dispose 排空和崩溃尾部修复。`persistence.spec.ts`、`preparations.spec.ts` 与 `write-behind.spec.ts` 覆盖准备复用与预留、有界准备状态淘汰、固定窗口后续批次、存活控制器清理、同 id 链尾竞态、失败批次重试与关闭顺序。各后端自身的测试规格只保留存储机制。每个真实后端都有一个经由协调器的崩溃尾部修复测试,以覆盖不透明 marker 分支,因为约定中的崩溃用例会产生合成 closers,却不会产生 torn marker。 ## 曾考虑的替代方案 - **后端继承的基类**——否决,改用组合:后端只暴露钩子,无法触及协调器的私有编排状态,且第三方后端仍可完全不使用协调器、直接实现抽象服务。 -- **更宽的钩子面**——每个候选钩子都被折叠掉:没有限定存储范围的实时查找,因为 `loadStored` 加上协调器的 cwd 检查即可维持碰撞边界;没有存储定位器泛型,因为经验证的 JSONL 元数据可还原其路径,而 SQLite 已按 id 绑定;没有单独的 `materialize` 钩子,因为首批事件必须与物化原子提交;没有单独的创建碰撞探测,因为它就是 `loadStored(id) !== undefined`;`list()` 也不经由协调器透传,因为列举不需要任何编排。 +- **更宽的钩子面**——每个候选钩子都被折叠掉:没有限定存储范围的存活会话查找,因为 `loadStored` 加上协调器的 cwd 检查即可维持碰撞边界;没有存储定位器泛型,因为经验证的 JSONL 元数据可还原其路径,而 SQLite 已按 id 绑定;没有单独的 `materialize` 钩子,因为首批事件必须与物化原子提交;没有单独的创建碰撞探测,因为它就是 `loadStored(id) !== undefined`;`list()` 也不经由协调器透传,因为列举不需要任何编排。 ## 后果 -协调器增加了一层间接、一个不透明的 torn marker 和脱离会话生命周期的退役任务,但将此前每个后端重复的、对正确性要求很高的编排逻辑集中到一处。会话 dispose 仍是仅观察事件,因此会话所有者不会等待持久化退役;协调器会收容失败、在存活控制器中保留待处理事件,并以后端 teardown 为完全停稳边界。其钩子面保持窄小:标识校验、接管、碰撞检查与不修改状态的检查共用 `loadStored`;物化保持在 `appendBatch` 内原子完成;列举绕过协调器。读模型使用 `inspect` 而非 `load`,因此观察已持久化但仍开放的轮次时,不会因提交中断 closers 而与新的存活所有者产生竞态。新后端只需实现存储原语,而无需复制立即写入生命周期。 +协调器增加了一层间接、一个不透明的 torn marker、脱离会话生命周期的退役任务,以及有界的已准备 Session 状态,但将此前每个后端重复的、对正确性要求很高的编排逻辑集中到一处。会话 dispose 仍是仅观察事件,因此会话所有者不会等待持久化退役;协调器会收容失败、在存活控制器中保留待处理事件,并以后端 teardown 为完全停稳边界。其钩子面保持窄小:标识校验、接管、碰撞检查、准备与不修改状态的检查共用 `loadStored`;物化保持在 `appendBatch` 内原子完成;列举绕过协调器。读模型使用 `inspect` 而非 `load`,因此观察已持久化但仍开放的轮次时不会提交中断 closers;复用、预留与发布由 [Session 准备阶段决策](2026-08-05-session-preparation.md)定义。新后端只需实现存储原语,而无需复制有界写入生命周期。 diff --git a/.agents/notes/implemented/architecture/2026-06-20-branded-ids.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-20-branded-ids.i18n.yaml index 04f7dcb1a3..0af0c0038b 100644 --- a/.agents/notes/implemented/architecture/2026-06-20-branded-ids.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-06-20-branded-ids.i18n.yaml @@ -1,6 +1,6 @@ # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: -# pnpm run verify-translation-pairing --write +# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-06-20-branded-ids.md 2026-06-20-branded-ids.md: 7c0b7ca89418e8312ec728223dac519f70edc3ed -2026-06-20-branded-ids.zh.md: 8b41ad3c3c85690fb03b20a208f8460a1614477b +2026-06-20-branded-ids.zh.md: 039953754b184af97eb9b4ea3bbb1325d45eda25 diff --git a/.agents/notes/implemented/architecture/2026-06-20-branded-ids.zh.md b/.agents/notes/implemented/architecture/2026-06-20-branded-ids.zh.md index 8b41ad3c3c..039953754b 100644 --- a/.agents/notes/implemented/architecture/2026-06-20-branded-ids.zh.md +++ b/.agents/notes/implemented/architecture/2026-06-20-branded-ids.zh.md @@ -6,13 +6,13 @@ Status: implemented ## 问题 -harness 使用 `Branded = string & { readonly [BRAND]: B }` 机制,为 `CallId`(`packages/llm/llm/src/brand.ts`)和 agent/会话共享的 `SessionId`(`packages/core/session/src/types.ts`)做 brand 处理;该机制由纯类型包(package) `@deepseek-ai/dsh-brand` 拥有,位于 `packages/util/brand/`,见其 [README](../../../../packages/util/brand/README.md),并为每个类型提供零开销的 cast 工厂。`dsh-brand` 还声明了治理策略:*「Branding 用于跨包边界且可能被混淆的 id;不是每个 string 都需要 brand。」* 这条策略是正确的;问题在于它只落实了一半。两处缺口使得结构相同但语义错误的 string 今天仍能通过类型检查器。 +harness 使用 `Branded = string & { readonly [BRAND]: B }` 机制,为 `CallId`(`packages/llm/llm/src/brand.ts`)和 agent/会话共享的 `SessionId`(`packages/core/session/src/types.ts`)做 brand 处理;该机制由纯类型包 `@deepseek-ai/dsh-brand` 拥有,位于 `packages/util/brand/`,见其 [README](../../../../packages/util/brand/README.md),并为每个类型提供零开销的 cast 工厂。`dsh-brand` 还声明了治理策略:*「Branding 用于跨包边界且可能被混淆的 id;不是每个 string 都需要 brand。」* 这条策略是正确的;问题在于它只落实了一半。两处缺口使得结构相同但语义错误的 string 今天仍能通过类型检查器。 **缺口 1:bash seam 中未 brand 的跨边界 ID。** 后台 task id 是普通 `string`:`BashTask.id: string`(`packages/bash/bash/src/types.ts`),作为 `string` 贯穿整个执行器 seam(`packages/bash/bash/src/index.ts` 中的 `BashExecutor.get`/`ownerOf`/`readOutput`/`kill(id: string)`),再由面向模型的工具以 `string` 校验并传递(`validateTaskId`、`assertTaskAccess`、`packages/bash/tool-bash/src/index.ts` 中 `task_id` 的 schema 参数)。它由每执行器计数器生成——`packages/bash/bash-local/src/index.ts` 中的 `` `bash-${this.nextTaskId++}` ``——其形状与 `SessionId` 的默认值**完全相同,都是 `name-N`**(`packages/core/session/src/index.ts` 中的 `` `session-${++counter}` ``)。bash task id 和会话 id 在调用点轻易就能互换,而编译器毫无反应。这是用户询问的核心案例,并且它是面向模型的 id(模型会把 `task_id` 传回 `bash_output`/`bash_kill`),所以该混淆可由不受信任的输入触达。 bash **owner token** 是相关的子情形:`BashExecRequest.owner?: string` 和 `BashExecSpec.owner: string | undefined`(`packages/bash/bash/src/types.ts`)被文档描述为刻意*不透明*的隔离键,但在所有实际调用方中,该值就是所属 agent(智能体)共享的 `Agent.id`/`SessionId`(`callerToken = (exec) => exec.agent?.id`,位于 `packages/bash/tool-bash/src/index.ts`),只是披着另一个 seam 本地名称。它被用于访问控制比较(`owner !== callerToken(exec)`),因此一个不匹配但类型正确的 string 在此处就是跨会话隔离 bug,而当前类型系统无法捕获。这正是[统一 agent/session 标识决策](../simplification/2026-06-20-unify-agent-and-session-id.md)覆盖的共享 id 别名。 -**缺口 2:*已经 brand* 的 ID 在 seam 处被侵蚀。** 就连 `CallId` 和 `SessionId` 也恰好在最容易混淆的地方退化为裸 `string`:注册表/store 键类型和公开方法参数。代表性位置包括会话存储、agent 注册表(二者都以共享的 `SessionId` 为键)、工具展示层的 call-id map、ACP 的会话记录,以及持久化协调器。在集合键处丢弃 brand,会让既有 brand 在查找时毫无价值;它们的价值只实现了一部分。 +**缺口 2:*已经 brand* 的 ID 在 seam 处被侵蚀。** 就连 `CallId` 和 `SessionId` 也恰好在最容易混淆的地方退化为裸 `string`:注册表/store 键类型和公开方法参数。代表性位置包括会话存储、agent 注册表(二者都以共享的 `SessionId` 为键)、工具展示层的 call-id map、ACP(Agent Client Protocol)的会话记录,以及持久化协调器。在集合键处丢弃 brand,会让既有 brand 在查找时毫无价值;它们的价值只实现了一部分。 ## 决策 @@ -65,5 +65,5 @@ export function OwnerToken(id: string): OwnerToken { ## 后果 - **两个接口面的机械性改动。** 传播 brand 涉及 bash seam(接口 + 实现 + 消费方)以及 ACP 会话 id 接口和持久化协调器。改动面广但严重度低:遗漏的位置是编译错误而非静默 bug。变更可观察地为纯类型变更——无快照或 e2e 行为差异。它与[统一 agent/会话标识决策](../simplification/2026-06-20-unify-agent-and-session-id.md)相邻,因为二者都触及会话 id / owner-token 边界;`OwnerToken` 出于上述解耦理由仍与统一后的 id 保持独立。 -- **Brand 不做校验。** Brand 是混淆防护,不是正确性证明:一个*错误的* 会话 id 只要仍是合法的 string,就和以前一样能通过类型检查器。本 Agent Note 不关闭这个缺口(见「不在范围内」)——它只阻止这类*类别*错误:传入错误*种类*的 id。 +- **Brand 不做校验。** Brand 是混淆防护,不是正确性证明:一个*错误的*会话 id 只要仍是格式正确的 string,就和以前一样能通过类型检查器。本 Agent Note 不关闭这个缺口(见「不在范围内」)——它只阻止这类*类别*错误:传入错误*种类*的 id。 - **「在哪里停下」仍是判断题。** 为 `BashTaskId` 加 brand 但不为 `ToolName` 加,为 `OwnerToken` 加但不为 `ModelId` 加,是对哪些 string「可能被混淆」的品味判断。合理的评审者可能想要更多或更少;`brand.ts` 中的策略是裁决依据,本 Agent Note 倾向于面向模型或用于访问控制的 id。 diff --git a/.agents/notes/implemented/architecture/2026-06-20-generic-long-running-tool-runtime.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-20-generic-long-running-tool-runtime.i18n.yaml index 341ea482c0..ebabaccdbb 100644 --- a/.agents/notes/implemented/architecture/2026-06-20-generic-long-running-tool-runtime.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-06-20-generic-long-running-tool-runtime.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-06-20-generic-long-running-tool-runtime.md -2026-06-20-generic-long-running-tool-runtime.md: cb9d9487cd274696ae20dddab8c6888b4cf4b833 -2026-06-20-generic-long-running-tool-runtime.zh.md: 77538105ba2841479238045327de493c5a835b7f +2026-06-20-generic-long-running-tool-runtime.md: 8cf6a34c3e4fc042bd73c147d83838734dfc9585 +2026-06-20-generic-long-running-tool-runtime.zh.md: 44241321f6e4da428fe3a6402440af344fd69f10 diff --git a/.agents/notes/implemented/architecture/2026-06-20-generic-long-running-tool-runtime.md b/.agents/notes/implemented/architecture/2026-06-20-generic-long-running-tool-runtime.md index cb9d9487cd..8cf6a34c3e 100644 --- a/.agents/notes/implemented/architecture/2026-06-20-generic-long-running-tool-runtime.md +++ b/.agents/notes/implemented/architecture/2026-06-20-generic-long-running-tool-runtime.md @@ -23,7 +23,7 @@ Long-running tools are producers. `dsh-tool-bash` adapts a `BashProcess` into in ## Runtime contract -The literal types live in the [task data-structure catalog](../../../../docs/core-data-structures/tasks.md). A producer calls `ctx.tasks.start()` with a kind, label, optional owning `Agent`, optional positive `outputLimitBytes`, and a `run()` function. The runtime completes all failable preflight work before calling `run()` and invokes it once. After `run()` returns hooks, registration commits without another failable step; a producer cannot start work that lacks a collectable task id. +The literal types live on the [tasks subsystem page](../../../../docs/subsystems/tasks.md). A producer calls `ctx.tasks.start()` with a kind, label, optional owning `Agent`, optional positive `outputLimitBytes`, and a `run()` function. The runtime completes all failable preflight work before calling `run()` and invokes it once. After `run()` returns hooks, registration commits without another failable step; a producer cannot start work that lacks a collectable task id. `outputLimitBytes` is producer-owned presentation policy, not a registry buffer. The registry validates and projects it unchanged into `TaskSnapshot`; generic control surfaces apply the cap to complete model-facing output after adding their own status or notice metadata. Omitting it preserves the existing surface behavior, so the runtime does not impose a hidden default on unrelated producer families. diff --git a/.agents/notes/implemented/architecture/2026-06-20-generic-long-running-tool-runtime.zh.md b/.agents/notes/implemented/architecture/2026-06-20-generic-long-running-tool-runtime.zh.md index 77538105ba..44241321f6 100644 --- a/.agents/notes/implemented/architecture/2026-06-20-generic-long-running-tool-runtime.zh.md +++ b/.agents/notes/implemented/architecture/2026-06-20-generic-long-running-tool-runtime.zh.md @@ -6,7 +6,7 @@ Status: implemented ## 问题 -后台 bash 原本兼有两项职责:bash 执行器既运行进程,又管理 task id、所有权、增量读取、取消、完成监听器和面向模型的控制工具。新增后台 subagent 需要相同的生命周期与交互契约。如果每种长时间运行能力都独立实现该契约,就会重复隔离、清理、通知和提示词行为,还会让模型为每种生产方学习不同的收集与停止协议。 +后台 bash 原本兼有两项职责:bash 执行器既运行进程,又管理 task id、所有权、增量读取、取消、完成监听器和面向模型的控制工具。新增后台 subagent 需要相同的生命周期与交互约定。如果每种长时间运行能力都独立实现该约定,就会重复隔离、清理、通知和提示词行为,还会让模型为每种生产方学习不同的收集与停止协议。 任务注册表、控制工具与完成通知共同构成一项 harness 功能。bash 和 subagent 只提供执行专属的钩子,不拥有通用任务行为。 @@ -21,9 +21,9 @@ Status: implemented `TaskService` 是 `@deepseek-ai/dsh-tasks` 中的抽象 seam;进程内注册表是 `@deepseek-ai/dsh-tasks-local` 中的 `LocalTaskService`(该拆分记录在[任务注册表 seam Agent Note](2026-07-26-task-registry-seam.md)中)。 -## 运行时契约 +## 运行时约定 -字面类型见[任务数据结构目录](../../../../docs/core-data-structures/tasks.md)。生产方调用 `ctx.tasks.start()`,传入 kind、label、可选的所属 `Agent`、可选的正数 `outputLimitBytes` 与一个 `run()` 函数。运行时会在调用 `run()` 前完成所有可能失败的预检工作,并且只调用一次。`run()` 返回钩子后,注册过程不会再执行可能失败的步骤而直接提交;生产方无法启动没有可收集 task id 的工作。 +字面类型见[任务子系统页面](../../../../docs/subsystems/tasks.md)。生产方调用 `ctx.tasks.start()`,传入 kind、label、可选的所属 `Agent`、可选的正数 `outputLimitBytes` 与一个 `run()` 函数。运行时会在调用 `run()` 前完成所有可能失败的预检工作,并且只调用一次。`run()` 返回钩子后,注册过程不会再执行可能失败的步骤而直接提交;生产方无法启动没有可收集 task id 的工作。 `outputLimitBytes` 是生产方拥有的呈现策略,而非注册表缓冲区。注册表校验该值,并将其原样投影到 `TaskSnapshot`;通用控制接口添加自身的状态或通知元数据后,再将该上限应用于完整的面向模型输出。省略该值时保持现有接口行为,因此运行时不会向无关的生产方类别施加隐式默认值。 @@ -39,7 +39,7 @@ Status: implemented 运行时为 `done` 附加一个 continuation,记录第一个终止结果、解决等待方,并逐个调用完成监听器,同时隔离每个监听器的错误。首次结果优先的结算在资源销毁期间至关重要:如果 `cancel` 抛出,运行时会强制将记录标为失败,并警告工作可能遗留,而不是永远等待一个可能永不完成的 promise。后续生产方结果不能覆盖该诊断,也不能重复通知。`cancel` 返回后如果最终未使 `done` 完成,仍会阻塞资源销毁,因为运行时无法区分这种情况与缓慢但有效的停止。 -任务注册不是生产方工具 fiber 的 effect。因此,重新加载工具或控制接口插件不会终止由 agent(智能体)和后端拥有的工作。任务服务自身释放时会取消所有实时任务,并等待遵守契约的生产方。 +任务注册不是生产方工具 fiber 的 effect。因此,重新加载工具或控制接口插件不会终止由 agent(智能体)和后端拥有的工作。任务服务自身释放时会取消所有实时任务,并等待遵守约定的生产方。 ## 授权与所有者生命周期 @@ -49,7 +49,7 @@ task id 在运行时全局可见且可预测,因此注册表会授权每次访 某个所有者的第一个任务会向 `owner.ctx` 附加一个异步 effect。agent 作用域释放时会取消该所有者的实时任务、等待其终止记录,并移除其快照。该 effect 可跨生产方重载存续,并加入 agent 现有的完全停稳边界。任务服务保留 effect disposer,使服务重载可以在全局资源销毁后,从仍然存活的 agent 作用域中分离回调。 -对于遵守契约的生产方,`AgentHandle.dispose()` 只在所属后台工作停止后解决。需要比 agent 存活更久的工作必须以无所有者方式启动;要跨运行时重启存续,则需另行设计持久任务。 +对于遵守约定的生产方,`AgentHandle.dispose()` 只在所属后台工作停止后解决。需要比 agent 存活更久的工作必须以无所有者方式启动;要跨运行时重启存续,则需另行设计持久任务。 ## 服务接口 @@ -91,7 +91,7 @@ task id 在运行时全局可见且可预测,因此注册表会授权每次访 bash seam 暴露 `resolve`、`run` 和 `start`。`start(spec)` 返回一个 `BashProcess`,提供增量读取、取消、退出事实以及不拒绝的完全停稳 promise。本地执行器只为自身释放时能终止并等待进程而保留实时句柄。前台调用方继续直接使用 `resolve` 和 `run`。 -对于后台 bash,`dsh-tool-bash` 将调用方 agent 注册为所有者。其钩子将 `kill()` 映射为取消,将 `done` 映射为 completed 或 killed 的 `TaskOutcome`,并将 `readOutput()` 映射为进程的有界增量输出,以及溢出文件与沙箱通知。通用任务工具拥有 id、状态行、列表、等待和完成通知。 +对于后台 bash,`dsh-tool-bash` 将调用方 agent 注册为所有者。其钩子将 `kill()` 映射为取消,将 `done` 映射为 completed 或 killed 的 `TaskOutcome`,并将 `readOutput()` 映射为进程的有界增量输出,以及 spill 与沙箱通知。通用任务工具拥有 id、状态行、列表、等待和完成通知。 对于后台 subagent,`dsh-tool-subagent` 创建由任务拥有的 `AbortController`,并在任务 starter 内启动提供方。无论提供方发布前后,取消都会中止同一个 signal。`done` 同时等待子运行结果和子运行释放,将已完成输出映射为最终结果,将中止映射为 `killed`,并将其他停止原因或基础设施失败映射为 `failed`。中间子历史保留在子会话中,不通过 `readOutput()` 暴露。 @@ -103,7 +103,7 @@ bash seam 暴露 `resolve`、`run` 和 `start`。`start(spec)` 返回一个 `Bas ### 立即抽象任务运行时后端 -当前 `TaskStart.run()` 契约传入进程内回调与确切的 `Agent` 对象。持久化后端会改变身份、重启、所有权与观察语义,因此在引入之时注册表保持为单一具体服务,而非固化错误的边界。[任务注册表 seam Agent Note](2026-07-26-task-registry-seam.md)后来在不改变这些进程内语义的前提下,将契约与进程内实现分离。 +当前 `TaskStart.run()` 约定传入进程内回调与确切的 `Agent` 对象。持久化后端会改变身份、重启、所有权与观察语义,因此在引入之时注册表保持为单一具体服务,而非固化错误的边界。[任务注册表 seam Agent Note](2026-07-26-task-registry-seam.md)后来在不改变这些进程内语义的前提下,将约定与进程内实现分离。 ### 由消费方负责授权或清理事件 @@ -117,11 +117,11 @@ bash seam 暴露 `resolve`、`run` 和 `start`。`start(spec)` 返回一个 `Bas ### 由运行时拥有输出接收端 -推送式接收端可以集中缓冲,但 bash 已经在执行器 seam 后拥有有界缓冲、截断与溢出文件。拉取格式化增量能够保留这一所有权。拥有存储的持久化后端可能足以支持重新审视生产方接口。 +推送式接收端可以集中缓冲,但 bash 已经在执行器 seam 后拥有有界缓冲、截断与 spill 文件。拉取格式化增量能够保留这一所有权。拥有存储的持久化后端可能足以支持重新审视生产方接口。 ### 随机 id、提升或生命周期会话事件 -授权而非不可猜测性才是访问边界,并且 id 不用于派生文件系统路径;顺序生成的品牌化 id 可保持 transcript(文本记录)易读。将前台任务提升为后台任务需要 SDK 并未规定的用户交互契约。启动、读取和通知已作为工具与上下文事件记录,因此专用任务会话事件会重复面向模型的事实。 +授权而非不可猜测性才是访问边界,并且 id 不用于派生文件系统路径;顺序生成的品牌化 id 可保持 transcript(文本记录)易读。将前台任务提升为后台任务需要 SDK 并未规定的用户交互约定。启动、读取和通知已作为工具与上下文事件记录,因此专用任务会话事件会重复面向模型的事实。 ## 测试 @@ -129,6 +129,6 @@ bash seam 暴露 `resolve`、`run` 和 `start`。`start(spec)` 返回一个 `Bas ## 后果 -bash 命令与 subagent 共享一套 id 词汇、列表、通知格式、提示词习惯和控制工具。新的长时间运行生产方只需实现执行钩子,而不必再实现一套注册表与工具族。[工具实操手册](../../../../docs/cookbook/adding-a-tool.md)将生产方指向本契约。 +bash 命令与 subagent 共享一套 id 词汇、列表、通知格式、提示词习惯和控制工具。新的长时间运行生产方只需实现执行钩子,而不必再实现一套注册表与工具族。[工具实操手册](../../../../docs/cookbook/adding-a-tool.md)将生产方指向本约定。 有所属后台 bash 会随其 agent 一起停止,不再比 agent 存活更久。后台进程没有执行器超时;调用方必须终止无关工作,或依赖所有者/服务释放。流式读取只支持一个消费方,完成通知不会唤醒空闲 agent;生产方的 `cancel` 返回后如果未使 `done` 完成,仍可能阻塞资源销毁。持久任务、独立观察游标和前台提升仍属于单独设计。 diff --git a/.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.i18n.yaml index d527bb9e7b..faa51b3d21 100644 --- a/.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.md -2026-06-21-bounded-llm-request-recovery.md: 122f30118ebe3f213a887e56a9d3505e78b23070 -2026-06-21-bounded-llm-request-recovery.zh.md: 8af62cef952eba929dd770df15fdc0666f575666 +2026-06-21-bounded-llm-request-recovery.md: 013cf5d77b0cddc38af8bcf15f13142022cb3f75 +2026-06-21-bounded-llm-request-recovery.zh.md: 9b025eeed208d42b5ca14fdec33e45aade50f0d2 diff --git a/.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.md b/.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.md index 122f30118e..013cf5d77b 100644 --- a/.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.md +++ b/.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.md @@ -4,11 +4,11 @@ Status: implemented English | [中文](2026-06-21-bounded-llm-request-recovery.zh.md) -The [per-provider request retry policy](../feature/2026-07-24-provider-retry-policies.md) extends this foundation with exact-provider configuration and an explicit unbounded mode. This note continues to own structured failure facts, the closed-step recovery boundary, normal mode's transient defaults, visible single attempts, and durable retry status. +The [per-provider request retry policy](../feature/2026-07-24-provider-retry-policies.md) extends this foundation with exact-provider configuration and an explicit unbounded mode. This note continues to own structured failure facts, the closed-step recovery boundary, normal mode's transient defaults, visible single attempts, and durable retry status. [Terminal LLM stream failures](2026-07-29-terminal-llm-stream-failures.md) supersedes its thrown-error identity and stream-sidecar mechanism. ## Problem -`dsh-llm` can report provider failures either by throwing during adapter dispatch or iteration or by ending with `finish { kind: 'error' | 'aborted' }`. The final adapter boundary tags thrown failures so `dsh-agent-loop` can distinguish them from middleware and result-processing defects, and the loop normalizes both delivery forms into `agent/request-error` after closing the failed step. An unhandled failure is terminal; a handling listener repairs policy-owned state, returns `{ kind: 'retry' }`, and stops waterfall delegation. The [retry-action decision](../simplification/2026-07-27-request-error-retry-action.md) owns this return contract. +Provider adapters can fail by throwing during dispatch or iteration or by ending with `finish { kind: 'error' | 'aborted' }`. The final adapter boundary normalizes thrown values to that terminal finish protocol before `dsh-agent-loop` receives them; middleware and result-processing defects remain thrown. The loop offers a terminal model-request failure to `agent/request-error`. An unhandled failure is terminal; a handling listener repairs policy-owned state, returns `{ kind: 'retry' }`, and stops waterfall delegation. The [retry-action decision](../simplification/2026-07-27-request-error-retry-action.md) owns this return contract. That boundary is already safe for another request attempt. Raw `assistant/chunk` events carry the failed `turn` and `step`, message derivation ignores them unless a successful `assistant/message` cites them, tool calls are dispatched only after a successful terminal finish and assembly, and a retry opens a new numbered turn from the durable log. The harness therefore does not need a second response lifecycle or tentative-output protocol to keep two attempts separate. @@ -40,9 +40,9 @@ interface LlmFailure { `code` remains the provider-neutral machine-routing taxonomy established by `HarnessError`; the new fields are observations from the provider boundary. `ProviderRequestId` is owned and constructed by `dsh-llm`, then serializes as its provider-issued string. The payload deliberately has no `retryable`, `failover`, `partialOutput`, provider, model, phase, or route id fields. Retryability belongs to policy, provider/model are already in the durable request header, and partial output is derived from the failed step's `assistant/chunk` events. -`LlmError` carries `failure: LlmFailure` and preserves `failure.code === error.code`. `FinishReasonMap.error` and `FinishReasonMap.aborted` carry the same payload instead of parallel failure shapes. An adapter-thrown `Error` keeps its exact object identity: the final-adapter scope associates the normalized facts with that object in call-local sidecar state and rethrows it unchanged; a non-`Error` throw is wrapped as today. `llmFailureOf(stream, error)` retrieves those facts alongside the existing provenance check, while an in-band finish without an error object becomes a new `LlmError`. This preserves listeners that key on error type or identity while giving all final-adapter failures, including unknown SDK exceptions, an `UNKNOWN` terminal payload. +`LlmError` carries `failure: LlmFailure` and preserves `failure.code === error.code`. `FinishReasonMap.error` and `FinishReasonMap.aborted` carry the same payload instead of parallel failure shapes. The final adapter boundary detaches those facts from adapter-thrown values and emits the appropriate terminal finish; unknown SDK exceptions receive an `UNKNOWN` payload. Exact thrown-object identity does not cross the LLM stream seam. -The agent loop keeps `RequestError` as that exact error object and passes `LlmFailure` as a separate argument to `agent/request-error`; it does not mutate possibly frozen third-party errors. It also uses the payload when converting an in-band finish and when recording an unrecovered `turn/end.reason`. +The agent loop passes the terminal finish's `LlmFailure` to `agent/request-error` and uses the same payload when recording an unrecovered `turn/end.reason`. Adapters extract structured facts before falling back to message inspection. They validate HTTP status, parse `Retry-After` seconds or dates into a positive finite millisecond delay, brand the provider request id when exposed, and distinguish their own timeout from the caller's abort. Provider-specific codes and messages may refine a mapping, but no recovery listener parses them. @@ -106,8 +106,8 @@ If recovery is exhausted, the final failure is stored once on `turn/end.reason` ## Verification -- `LlmFailure` is the single serializable payload for thrown, error-finish, and aborted-finish final-adapter failures; normalization preserves stable code, status, retry delay, branded provider request id, error cause, and caller-abort versus adapter-timeout classification where available. -- An adapter-thrown `Error` reaches `agent/request-error` as the exact same object while its sidecar `LlmFailure` reaches the adjacent argument; tests retain the existing identity assertion for extensible and frozen third-party errors. +- `LlmFailure` is the single serializable payload for adapter throws, error finishes, and aborted finishes; normalization preserves stable code, status, retry delay, branded provider request id, and caller-abort versus adapter-timeout classification where available. +- Adapter throws become terminal failure chunks before reaching consumers; middleware and consumer exceptions remain thrown outside model-request recovery. - DeepSeek and pi-ai adapter tests cover representative 400, 401/403, 429, 5xx, connection, malformed/truncated stream, timeout, abort, retry-after seconds/date, request-id, and unknown-SDK-error paths without recovery policy parsing message text. - Pi-ai pins the SDK option to zero retries and performs one observed wire attempt for a retryable provider response; separate tests make removing either boundary fail. - `agent/request-error` carries current failure facts, immutable prior-retried failure facts, and the serving registration's immutable retry policy; a success clears the history, and alternating transient/context-overflow integration tests prove the two policies consume only their own finite budgets. diff --git a/.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.zh.md b/.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.zh.md index 8af62cef95..9b025eeed2 100644 --- a/.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.zh.md +++ b/.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.zh.md @@ -1,14 +1,14 @@ -# Agent Note: LLM(大语言模型)暂时性请求失败的有界恢复 +# Agent Note: LLM 暂时性请求失败的有界恢复 Status: implemented [English](2026-06-21-bounded-llm-request-recovery.md) | 中文 -[按提供方配置的请求重试策略](../feature/2026-07-24-provider-retry-policies.md)在此基础上增加了确切提供方配置与显式无界 mode。本说明继续负责结构化失败事实、已关闭步骤的恢复边界、normal mode 的暂时性默认值、可见的单次尝试和持久重试状态。 +[按提供方配置的请求重试策略](../feature/2026-07-24-provider-retry-policies.md)在此基础上增加了确切提供方配置与显式无界 mode。本说明继续负责结构化失败事实、已关闭步骤的恢复边界、normal mode 的暂时性默认值、可见的单次尝试和持久重试状态。[LLM 流的终止失败](2026-07-29-terminal-llm-stream-failures.md)取代了其中关于抛出错误身份和流伴随状态的机制。 ## 问题 -`dsh-llm` 可能在适配器分发或迭代时抛出异常,也可能以 `finish { kind: 'error' | 'aborted' }` 结束,以这两种形式报告提供方失败。最终适配器边界会标记抛出的失败,使 `dsh-agent-loop` 能将其与中间件和结果处理缺陷区分开。循环关闭失败步骤后,会把两种交付形式统一规范化为 `agent/request-error`。未被处理的失败是终态;处理失败的监听器修复策略自有状态,返回 `{ kind: 'retry' }`,并停止 waterfall 委托。[重试动作决策](../simplification/2026-07-27-request-error-retry-action.md)规定这一返回契约。 +提供方适配器可能在分发或迭代时抛出异常,也可能以 `finish { kind: 'error' | 'aborted' }` 结束。最终适配器边界会在 `dsh-agent-loop` 接收前把抛出值规范化为该终止 finish 协议;middleware 与结果处理缺陷仍会抛出。loop 会将终止模型请求失败交给 `agent/request-error`。未被处理的失败是终态;处理失败的监听器修复策略自有状态,返回 `{ kind: 'retry' }`,并停止 waterfall(瀑布式事件)委托。[重试动作决策](../simplification/2026-07-27-request-error-retry-action.md)规定这一返回约定。 该边界已能安全地再次发起请求。原始 `assistant/chunk` 事件携带失败的 `turn` 和 `step`;除非某条成功的 `assistant/message` 引用这些事件,否则消息派生会忽略它们。只有终止性 finish 成功且组装完成后,系统才会分发工具调用;重试则会从持久日志开启新的编号轮次。因此,harness 无需引入第二套响应生命周期或暂定输出协议,即可分隔两次尝试。 @@ -40,9 +40,9 @@ interface LlmFailure { `code` 仍是 `HarnessError` 建立的提供方无关机器路由分类体系;新字段是在提供方边界观测到的事实。`ProviderRequestId` 由 `dsh-llm` 拥有并构造,序列化后为提供方发放的字符串。该载荷有意不包含 `retryable`、`failover`、`partialOutput`、提供方、模型、阶段或路由 id 字段。是否可重试属于策略,提供方/模型已位于持久请求头中,部分输出则从失败步骤的 `assistant/chunk` 事件派生。 -`LlmError` 携带 `failure: LlmFailure`,并保持 `failure.code === error.code`。`FinishReasonMap.error` 和 `FinishReasonMap.aborted` 携带同一载荷,而不是并行的失败形状。适配器抛出的 `Error` 保留其精确的对象标识:最终适配器 scope 在调用局部的伴随状态中把规范化事实与该对象关联,然后原样重新抛出;非 `Error` 抛出值则依旧被包装。`llmFailureOf(stream, error)` 会在现有来源检查旁取回这些事实,而没有错误对象的带内 finish 则会成为新的 `LlmError`。这既保留了按错误类型或标识分流的监听器,又使所有最终适配器失败(包括未知 SDK 异常)都获得 `UNKNOWN` 终止载荷。 +`LlmError` 携带 `failure: LlmFailure`,并保持 `failure.code === error.code`。`FinishReasonMap.error` 和 `FinishReasonMap.aborted` 携带同一载荷,而不是并行的失败形状。最终适配器边界会从适配器抛出值中分离这些事实,并发出相应的终止 finish;未知 SDK 异常会获得 `UNKNOWN` 载荷。精确的抛出对象身份不会跨越 LLM 流 seam。 -agent loop(智能体循环)会保留 `RequestError` 作为该精确的错误对象,并将 `LlmFailure` 作为独立参数传给 `agent/request-error`;它不会改动可能已冻结的第三方错误。在转换带内 finish 以及记录未恢复的 `turn/end.reason` 时,循环也会使用该载荷。 +agent loop(智能体循环)会将终止 finish 的 `LlmFailure` 传给 `agent/request-error`,并在记录未恢复的 `turn/end.reason` 时使用同一载荷。 适配器会先提取结构化事实,再回退到消息检查。它们会验证 HTTP 状态,将 `Retry-After` 的秒数或日期解析为正的有限毫秒延迟,在提供方公开请求 id 时将其品牌化,并区分自身超时与调用方中止。提供方专用 code 和消息可以细化映射,但恢复监听器不会解析它们。 @@ -58,11 +58,11 @@ agent loop(智能体循环)会保留 `RequestError` 作为该精确的错误 对于预算未耗尽的合格失败,从 1 开始的暂时性重试计数使用有界指数退避。有效的 `providerRetryAfterMs` 只有在不超过 `maxDelayMs` 时才会取代指数退避;提供方延迟更长时,系统会委托给下一监听器,而不会违反提供方指令提前重试。本地退避乘以 `[1 - jitterRatio, 1 + jitterRatio]` 内的注入随机因子,并将最终值限制到 `maxDelayMs`;提供方延迟不加抖动。 -插件拥有一个全生命期 `AbortController`,并跟踪每个活跃的恢复回调,包括委托的 waterfall(瀑布式事件)工作与退避。effect 清理会先注销监听器,再中止并等待活跃回调;中止会胜过较晚到达的委托重试决策,被捕获的回调在插件释放后既不能重试,也不能进入其 waterfall 的剩余部分。尽管 Cordis 已捕获该监听器,此设计仍能使 HMR(热模块替换)释放达到完全停稳。 +插件拥有一个全生命期 `AbortController`,并跟踪每个活跃的恢复回调,包括委托的 waterfall 工作与退避。effect 的 dispose(资源释放)会先注销监听器,再中止并等待活跃回调;中止会胜过较晚到达的委托重试决策,被捕获的回调在插件 dispose 后既不能重试,也不能进入其 waterfall 的剩余部分。尽管 Cordis 已捕获该监听器,此设计仍能使 HMR(热模块替换)的 dispose 达到完全停稳。 -休眠前,`dsh-llm-retry` 会追加一条不进入表层的 `llm/retry` 会话事件,其中包含轮次、失败步骤、提供方、策略 mode、完整的解析策略 key、提供方策略重试编号、该 mode 存在时的有限上限、计划延迟和 `LlmFailure`。该 key 会对 code 集排序,并在提供方路由被行为不同但 mode 相同的策略替换时分隔重试历史。该插件拥有 `SessionEventMap` 声明合并,并通过其浏览器安全的 `./types` 子路径导出载荷;`dsh-session` 继续负责通用持久化,不会吸收可选策略的词汇。事件记录已安排的内容,而不是下一个请求已完成;延迟期间取消随后会在 `turn/end` 中可见。因为该事件的目的是表示运行状态,而不是收集跟踪数据,所以它会与生产渲染器及回放/快照覆盖一起交付。 +休眠前,`dsh-llm-retry` 会追加一条不进入表层的 `llm/retry` 会话事件,其中包含轮次、失败步骤、提供方、策略 mode、完整的解析后策略 key、提供方策略重试编号、特定于 mode 的有限上限(如有)、计划延迟和 `LlmFailure`。该 key 会对 code 集排序,并在提供方路由被行为不同但 mode 相同的策略替换时分隔重试历史。该插件拥有 `SessionEventMap` 声明合并,并通过其浏览器安全的 `./types` 子路径导出载荷;`dsh-session` 继续负责通用持久化,不会吸收可选策略的词汇。事件记录已安排的内容,而不是下一个请求已完成;延迟期间取消随后会在 `turn/end` 中可见。因为该事件的目的是表示运行状态,而不是收集跟踪数据,所以它会与生产渲染器及回放/快照覆盖一起交付。 -对非暂时性 code、耗尽的策略预算或超出上限的提供方延迟,监听器会调用 `next()`。这保留了与上下文溢出恢复及后续策略插件的组合能力。对自身处理的失败,它会记录并等待延迟,然后在不委托的情况下返回 `{ kind: 'retry' }`。轮次取消和插件释放会结束等待且不返回重试动作,此后仍以循环的取消/释放检查为准。 +对非暂时性 code、耗尽的策略预算或超出上限的提供方延迟,监听器会调用 `next()`。这保留了与上下文溢出恢复及后续策略插件的组合能力。对自身处理的失败,它会记录并等待延迟,然后在不委托的情况下返回 `{ kind: 'retry' }`。轮次取消和插件 dispose 会结束等待且不返回重试动作,此后仍以循环的取消/dispose 检查为准。 agent-spine 演示组合包加载该插件,因此共享的 stdio/TUI、一次性 CLI(命令行界面)、ACP(Agent Client Protocol)和 headless 示例组合使用同一套按提供方路由的策略。随产品交付的 Web 组合也会加载该插件,因此浏览器请求与命令行请求使用相同的提供方默认值。库消费方仍需显式组合插件:省略该插件时,请求失败保持终态。 @@ -70,7 +70,7 @@ agent-spine 演示组合包加载该插件,因此共享的 stdio/TUI、一次 适配器每次调用 `stream()` 只执行一次提供方请求。pi-ai 适配器移除公开的 `maxRetries` 和 `maxRetryDelayMs` profile 字段,并禁用库内部重试;手写适配器保持现有的单次尝试行为。这样既避免 SDK 预算成倍放大 agent 预算,又能确保每次暂时性重试都由一个已关闭的失败步骤加 `llm/retry` 表示。 -`ctx.llm.stream()` 仍是原始的单次尝试 waterfall。压缩摘要等直接调用方会收到结构化失败,但不会自动获得重试,因为它们没有 agent 步骤边界,也没有可供分隔尝试的通用持久位置。未来的直接调用消费方可能会需要一个缓冲辅助函数,仅在尚未发出任何分片时重试;本决策不增加此类辅助函数。 +`ctx.llm.stream()` 仍是原始的单次尝试 waterfall。压缩(compaction)摘要等直接调用方会收到结构化失败,但不会自动获得重试,因为它们没有 agent 步骤边界,也没有可供分隔尝试的通用持久位置。未来的直接调用消费方可能会需要一个缓冲辅助函数,仅在尚未发出任何分片时重试;本决策不增加此类辅助函数。 ### 在能够终止停滞流的位置施加边界 @@ -78,11 +78,11 @@ agent-spine 演示组合包加载该插件,因此共享的 stdio/TUI、一次 `@deepseek-ai/dsh-timeout` 公开一个可重新布防的空闲看门狗原语。一个稳定的局部 `AbortController` 会与调用方信号融合,并在整个适配器调用期间传给传输层;每个尚未完成的 `next()` 都会布防看门狗,该调用完成时解除布防,下一次请求数据时再重新布防。带外传输活动会调用 `pulse()`,在不产生值的情况下为尚未完成的需求重新布防。超时会使用能力自身拥有的 `TimeoutReason` 中止这个稳定控制器,`finally` 则会清除定时器。适配器将自身看门狗归类为 `TIMEOUT`,将更早发生的上游中止归类为 `ABORTED`。现有的一次性 `deadline()` 不会被描述为滑动计时器。 -边界测试证明两个实际传输层都能终止。手写适配器会中止其 fetch/reader,pi-ai 适配器会把稳定信号映射到 SDK,并证明 SDK 会关闭响应。如果定时器只拒绝消费方 promise,却让请求继续运行,就不满足此契约。 +边界测试证明两个实际传输层都能终止。手写适配器会中止其 fetch/reader,pi-ai 适配器会把稳定信号映射到 SDK,并证明 SDK 会关闭响应。如果定时器只拒绝消费方 promise,却让请求继续运行,就不满足此约定。 ### 在现有日志中分隔尝试 -一次失败尝试可以在已关闭的步骤中留下 `assistant/chunk` 事件,但绝不会追加 `assistant/message`,也不会分发工具。重试会关闭失败轮次,开启下一个编号轮次,从持久表层重建请求,并生成自己的分片。步骤仍处于打开状态时,UI 可以渲染实时分片;当 `llm/retry` 标识失败步骤,或 `turn/end` 记录失败时,UI 再标记或清除这份暂时视图。Web 会验证完整的重试载荷契约,在 `llm/retry` 到达时清除失败的部分输出,将连续重试轮次的事件投影为稳定的一行,并用最新一次尝试更新该行,再从后续轮次事实派生 scheduled、started 或 cancelled 状态。倒计时以浏览器收到事件的时刻为计划延迟的起点,而不是使用 Host 事件时钟;它按向上取整且不低于 1 秒的秒数显示,仅在重试尚未结束时显示动画,并把最近一次失败的准确详情折叠在该行之后。即使失败尝试没有 assistant 节点,重试节点也会锚定自身的轨迹轮次。消息派生仍会忽略失败分片;Web 在重建历史时也会应用同一投影,因此刷新页面不会让已丢弃的部分输出重新出现,也不会生成重复的重试行。 +一次失败尝试可以在已关闭的步骤中留下 `assistant/chunk` 事件,但绝不会追加 `assistant/message`,也不会分发工具。重试会关闭失败轮次,开启下一个编号轮次,从持久表层重建请求,并生成自己的分片。步骤仍处于打开状态时,UI 可以渲染实时分片;当 `llm/retry` 标识失败步骤,或 `turn/end` 记录失败时,UI 再标记或清除这份暂时视图。Web 会验证完整的重试载荷约定,在 `llm/retry` 到达时清除失败的部分输出,将连续重试轮次的事件投影为稳定的一行,并用最新一次尝试更新该行,再从后续轮次事实派生 scheduled、started 或 cancelled 状态。倒计时以浏览器收到事件的时刻为计划延迟的起点,而不是使用 Host 事件时钟;它按向上取整且不低于 1 秒的秒数显示,仅在重试尚未结束时显示动画,并把最近一次失败的准确详情折叠在该行之后。即使失败尝试没有 assistant 节点,重试节点也会锚定自身的轨迹轮次。消息派生仍会忽略失败分片;Web 在重建历史时也会应用同一投影,因此刷新页面不会让已丢弃的部分输出重新出现,也不会生成重复的重试行。 如果恢复预算耗尽,最终失败会连同结构化事实在 `turn/end.reason` 中存储一次。Web 会在该序列位置派生一个 `turn-error` 节点,并内联渲染适合展示的消息与可选错误码;AUTH 投影会把可能回显凭据片段的提供方文案替换为 `API key is invalid`,原始诊断仍保留在会话日志中。实时事件和历史回放使用同一套折叠逻辑。如果暂时性恢复继续,`llm/retry` 就是该次尝试的失败与延迟的持久归属位置,因此该失败轮次不会再获得终态错误行。本决策不增加独立的最终错误事件或响应 id 词汇。 @@ -106,13 +106,13 @@ agent-spine 演示组合包加载该插件,因此共享的 stdio/TUI、一次 ## 验证 -- `LlmFailure` 是最终适配器抛出失败、错误 finish 和中止 finish 使用的唯一可序列化载荷;在可用时,规范化保留稳定 code、状态、重试延迟、品牌化的提供方请求 id、错误原因,以及调用方中止与适配器超时之间的分类。 -- 适配器抛出的 `Error` 会以完全相同的对象抵达 `agent/request-error`,其伴随的 `LlmFailure` 则抵达相邻参数;测试保留针对可扩展及冻结第三方错误的现有对象标识断言。 +- `LlmFailure` 是适配器抛出、错误 finish 和中止 finish 使用的唯一可序列化载荷;在可用时,规范化保留稳定 code、状态、重试延迟、品牌化的提供方请求 id,以及调用方中止与适配器超时之间的分类。 +- 适配器抛出值会在抵达消费方前成为终止失败分片;middleware 与消费方异常仍在模型请求恢复之外抛出。 - DeepSeek 和 pi-ai 适配器测试覆盖具有代表性的 400、401/403、429、5xx、连接、格式错误/截断流、超时、中止、Retry-After 秒数/日期、请求 id 和未知 SDK 错误路径,恢复策略无需解析消息文本。 -- Pi 将 SDK 选项固定为零次重试,并针对可重试的提供方响应执行一次可观测的实际网络请求;独立测试确保移除任一边界都会失败。 +- pi-ai 将 SDK 选项固定为零次重试,并针对可重试的提供方响应执行一次可观测的线路请求尝试;独立测试确保移除任一边界都会失败。 - `agent/request-error` 携带当前失败事实、不可变的先前已重试失败事实,以及实际服务注册所对应的不可变重试策略;成功会清除历史,暂时性失败/上下文溢出交替发生的集成测试证明两种策略只消耗各自的有限预算。 - 每个提供方适配器都在 Loader 启动时验证其嵌套重试策略,`ctx.llm` 则将该策略与路由一同捕获;normal mode 会委托不合格路径,而且在没有其他策略时最多发起 `maxRetries + 1` 次提供方请求。 -- 退避期间执行 HMR 的测试证明:释放过程会注销监听器、中止并等待其捕获的回调,释放后不发出重试决策,也不留下存活的定时器或 promise。 +- 退避期间执行 HMR 的测试证明:dispose 过程会注销监听器、中止并等待其捕获的回调,dispose 后不发出重试决策,也不留下存活的定时器或 promise。 - 纯单元测试覆盖暂时性 code 选择、指数退避和抖动边界、有效及超出上限的 `Retry-After`、耗尽的预算、确定性定时器/随机数 seam,以及退避期间中止。 - 真实 agent-loop 测试覆盖分片前失败、部分分片后失败、抛出及带内失败、在新轮次中重试至成功、耗尽后写入结构化 `turn/end.reason`,以及与 `dsh-compact-basic` 上下文溢出恢复的组合。 - 部分分片集成测试证明:失败分片仍归属于失败步骤,该步骤不会提交 assistant 消息或工具副作用,成功的重试具有不同的来源信息。 @@ -126,7 +126,7 @@ agent-spine 演示组合包加载该插件,因此共享的 stdio/TUI、一次 - 提供方 SDK 可能隐藏状态或重试标头。适配器会保留 SDK 公开的稳定事实,否则使用粗粒度 code,而不会让恢复策略解析脆弱的文本。 - 持久重试事件扩展了会话协议和 UI 状态机。事件与其消费方一同交付,可避免产生无人使用的遥测词汇;但以后更改 schema 仍需要同步完成持久化和回放工作。 - 清除失败步骤的实时分片可能会明显撤回输出。与把丢弃的文本或不完整工具 JSON 呈现为已提交历史相比,这是更好的选择;快照固定这一转换。 -- 适配器局部的空闲强制机制可以终止停滞的传输,而不会计入消费方思考时间。每个传输边界的契约测试会防止 SDK 漂移。 +- 适配器局部的空闲强制机制可以终止停滞的传输,而不会计入消费方思考时间。每个传输边界的约定测试会防止 SDK 漂移。 - 多个 normal 恢复插件会叠加各自的有限预算。always mode 会先委托,再提供无界回退;重叠的分类器仍会形成依赖注册顺序的策略,必须由引入它们的插件记录并测试。 ## 相关资料 @@ -135,4 +135,4 @@ agent-spine 演示组合包加载该插件,因此共享的 stdio/TUI、一次 - [可重建请求](../../implemented/architecture/2026-07-05-reconstructable-requests.md)使提供方/模型和完整请求输入在分发前持久化。 - [超时 deadline 库](../../implemented/architecture/2026-07-06-timeout-deadline-library.md)将共享的 deadline 分类与能力自身拥有的终止操作分开。 - [调用后压缩压力与上下文溢出恢复](../../implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md)负责当前已关闭步骤的请求恢复 seam 与有界溢出重试。 -- [提供方路由的 LLM 适配器](../../implemented/architecture/2026-07-14-provider-routed-llm-adapters.md)负责显式提供方/模型路由与每个提供方仅有一个适配器的不变量。 +- [提供方路由的 LLM(大语言模型)适配器](../../implemented/architecture/2026-07-14-provider-routed-llm-adapters.md)负责显式提供方/模型路由与每个提供方仅有一个适配器的不变量。 diff --git a/.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.i18n.yaml index e72b100327..6303b1e77a 100644 --- a/.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.i18n.yaml @@ -1,6 +1,6 @@ # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: -# pnpm run verify-translation-pairing --write -2026-06-21-mandatory-app-attribution-headers.md: a8ffe91c431cdc7907626bbc3eaf8096035777de -2026-06-21-mandatory-app-attribution-headers.zh.md: 5529a42dddf4615ee1054b4d1dee36b077800d7d +# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.md +2026-06-21-mandatory-app-attribution-headers.md: de9125bc891cc62798480e2eccb2c90cb633de3a +2026-06-21-mandatory-app-attribution-headers.zh.md: 6f0d0199f859fd462fdecc24e4063cbd27311bab diff --git a/.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.md b/.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.md index a8ffe91c43..de9125bc89 100644 --- a/.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.md +++ b/.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.md @@ -32,7 +32,7 @@ The provider-neutral identity is owned by `dsh-llm` (`packages/llm/llm/src/attri - product token for `User-Agent`: `deepseek-harness` (continuity with the pre-Agent Note wire value and the repo/org identity) - version: read from the owning package's manifest via `createRequire`, never a hand-copied constant -- app URL: `https://github.com/deepseek-ai/deepseek-harness-sdk` - the planned public home; a `FIXME` in `attribution.ts` blocks release until that repository actually exists +- app URL: `https://github.com/deepseek-ai/deepseek-harness-sdk` - the planned public home, which must exist before release The default is mandatory and non-empty. White-label deployments pass their own `AppIdentity` to `attributionHeaders(identity)` - the override seam is the function parameter, with no deployment config plumbing until a consumer needs it - and omission falls back to the harness default rather than suppressing attribution. There is no per-request API for the model, user prompt, session id, cwd, user email, API key owner, or local machine identity to influence these fields. @@ -51,7 +51,7 @@ Endpoint detection is not part of this Agent Note because no endpoint-specific m The landed contract: -- `dsh-llm` documents the mandatory `User-Agent` attribution contract for `LlmAdapter` authors (`LlmAdapter` JSDoc, package README, and the adapter-contract section of `docs/core-data-structures/llm-streaming.md`). +- `dsh-llm` documents the mandatory `User-Agent` attribution contract for `LlmAdapter` authors (`LlmAdapter` JSDoc, package README, and the adapter-contract section of `docs/subsystems/llm-streaming.md`). - A shared helper (`attributionHeaders` / `userAgent`) constructs the app identity and the standard `User-Agent` value from package metadata, so adapters do not hand-copy version constants. - `dsh-llm-deepseek` sends the shared `User-Agent` on every request and its mock-server suite asserts the exact value. - `dsh-llm-pi-ai` sends the same `User-Agent` through pi-ai's `StreamOptions.headers` hook and its mock-server suite asserts the exact value. @@ -77,7 +77,7 @@ The landed contract: **Providers see that traffic comes from the harness.** That is the point, but it means deployments that previously blended into generic SDK traffic become identifiable. Mitigation: send only static public product data and let forks/white-label deployments pass their own `AppIdentity`. -**The app URL points at a repository that does not exist yet.** `deepseek-ai/deepseek-harness-sdk` is the planned public home; until it is created the URL is a dangling promise. The `FIXME` marker on the constant blocks a release from shipping with it unresolved (see `docs/development.md` marker semantics). +**The app URL points at a repository that does not exist yet.** `deepseek-ai/deepseek-harness-sdk` is the planned public home; until it is created the URL is a dangling promise that blocks release. **Header support differs by client library.** The hand-rolled adapter sets headers directly; the pi-ai-backed adapter depends on pi-ai continuing to honor `StreamOptions.headers` (merged last over provider defaults). The wire-level mock-server tests are the guard: if a pi-ai upgrade stops delivering the header, the suite goes red. This is useful pressure on the abstraction: a provider adapter that cannot set mandatory headers cannot fully implement the harness LLM contract. diff --git a/.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.zh.md b/.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.zh.md index 5529a42ddd..6f0d0199f8 100644 --- a/.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.zh.md +++ b/.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.zh.md @@ -12,27 +12,27 @@ LLM(大语言模型)提供方请求应当标识发出请求的产品。这 ## 调研 -- **OpenRouter 的机制是提供方特有的。** 其当前文档说明应用归属通过 `HTTP-Referer`(必需)、`X-OpenRouter-Title` 和 `X-OpenRouter-Categories` 来追踪;`X-Title` 仅为向后兼容而接受。其 API 参考称这些头部为可选,并说它们使应用在 OpenRouter 上可被发现。这是一份具体的 OpenRouter 契约,而非 IETF 或 OpenAI 兼容 API 标准。 -- **在 agent 工具生态中,`HTTP-Referer` 是一种 OpenRouter 感知的约定,而非通用 agent 约定。** 它足够常见,以至于 OpenRouter SDK 和示例直接暴露它,面向 OpenRouter 的框架通常需要一种方式来透传它。但 ACP(Agent Client Protocol)等 agent 协议在自己的 initialize 消息中协商名称、版本和能力,而模型提供方请求仍需 HTTP 层面的身份标识。因此「在 agent 世界中被接受」意味着「被 OpenRouter 集成所识别」,而非「可跨 agent 运行时或提供方移植」。 -- **编程 agent 在 `User-Agent` 中标识产品和版本。** 公开实现在环境细节和提供方特有的附加头部上各有不同,但产品身份是共同契约;不存在通用的精确格式。 +- **OpenRouter 的机制是提供方特有的。** 其当前文档说明应用归属通过 `HTTP-Referer`(必需)、`X-OpenRouter-Title` 和 `X-OpenRouter-Categories` 来追踪;`X-Title` 仅为向后兼容而接受。其 API 参考称这些头部为可选,并说它们使应用在 OpenRouter 上可被发现。这是一项具体的 OpenRouter 惯例,而非 IETF 或 OpenAI 兼容 API 标准。 +- **在 agent 工具生态中,`HTTP-Referer` 是一种 OpenRouter 感知的惯例,而非通用 agent 惯例。** 它足够常见,以至于 OpenRouter SDK 和示例直接暴露它,面向 OpenRouter 的框架通常需要一种方式来透传它。但 ACP(Agent Client Protocol)等 agent 协议在自己的 initialize 消息中协商名称、版本和能力,而模型提供方请求仍需 HTTP 层面的身份标识。因此「在 agent 世界中被接受」意味着「被 OpenRouter 集成所识别」,而非「可跨 agent 运行时或提供方移植」。 +- **编程 agent 在 `User-Agent` 中标识产品和版本。** 公开实现在环境细节和提供方特有的附加头部上各有不同,但产品身份是共同惯例;不存在通用的精确格式。 - **标准化的通用客户端身份头部是 `User-Agent`。** RFC 9110 第 10.1.5 节将 `User-Agent` 定义为用户代理软件身份,说明它用于互操作性报告和分析,并说用户代理应当在每个请求中发送它(除非被配置为不发送)。这是唯一直接对应「哪个产品在发出此 HTTP 请求」的标准头部。 - **`Referer` 是标准的,但 OpenRouter 的 `HTTP-Referer` 不是标准字段。** RFC 9110 第 10.1.3 节将 `Referer` 定义为获取目标 URI 的来源 URI,并用大量篇幅讨论隐私限制。OpenRouter 则要求 `HTTP-Referer`,将其用作应用 URL 标识符。该名称和含义是 OpenRouter 特有的,尽管它形似标准 `Referer` 头部的 CGI 环境变量形式。 - **`From` 是标准的,但不适合作为强制默认值。** RFC 9110 第 10.1.2 节将 `From` 定义为负责用户代理的人的电子邮件地址。机器人代理应当发送它以便服务器联系运营者,但非机器人代理出于隐私和安全策略考虑不应在未经用户显式配置的情况下发送。harness 可以后续支持运营者联系方式,但不得凭空捏造或全局强制要求。 - **请求体中的 `user` 或 `metadata` 字段不是应用归属。** 部分模型 API 暴露稳定的终端用户标识符、请求元数据、标签或项目/账户头部。这些对滥用监控、内部计费、仪表盘或链路追踪有用,但它们要么标识的是终端用户而非产品,要么是提供方特有的 body schema,要么不保证能通过 OpenAI 兼容网关透传。它们不能替代静态的应用身份头部。 - **SDK 遥测头部标识的是 SDK,而非应用。** 官方和第三方 SDK 常发送库/版本头部。这些帮助 SDK 维护者调试其客户端,但除非应用显式提供产品归属层,否则它们不能标识 harness 作为应用。 -- **pi-ai 有一流的头部钩子。** `@earendil-works/pi-ai` 的 `StreamOptions.headers` 将调用方头部最后合并(覆盖提供方默认值),因此基于库的适配器无需包装或上游改动即可满足与手写适配器相同的协议格式契约。mock 服务器测试套件对两个适配器都断言头部到达了线路。 +- **pi-ai 有原生支持的头部钩子。** `@earendil-works/pi-ai` 的 `StreamOptions.headers` 将调用方头部最后合并(覆盖提供方默认值),因此基于库的适配器无需包装或上游改动即可满足与手写适配器相同的线路约定。mock 服务器测试套件对两个适配器都断言头部到达了线路。 ## 决策 -在 LLM 适配器边界,提供方请求归属是强制的,且仅使用标准 `User-Agent` 头部。规则:每个生产 LLM 适配器在每个提供方 HTTP 请求上发送一个静态、非机密的应用身份,且每个适配器都有测试证明 `User-Agent` 到达了线路(mock 服务器断言收到的头部;对于基于库的适配器,通过库的头部钩子馈入同一个 mock 服务器断言)。 +在 LLM 适配器边界,提供方请求归属是强制的,且仅使用标准 `User-Agent` 头部。规则:每个产品级 LLM 适配器在每个提供方 HTTP 请求上发送一个静态、非机密的应用身份,且每个适配器都有测试证明 `User-Agent` 到达了线路(mock 服务器断言收到的头部;对于基于库的适配器,通过库的头部钩子馈入同一个 mock 服务器断言)。 本 Agent Note **不**实现 OpenRouter 应用归属。`HTTP-Referer`、`X-OpenRouter-Title`、`X-Title` 和 `X-OpenRouter-Categories` 是 OpenRouter 特有的产品展示头部,不是提供方无关的模型请求归属。它们可以后续由 OpenRouter 适配器或显式 OpenRouter 模式提出,附带自己的隐私/产品决策、测试和文档。在此之前,即使请求指向 OpenRouter,也只发送本 Agent Note 定义的共享 `User-Agent` 归属。 提供方无关的身份由 `dsh-llm`(`packages/llm/llm/src/attribution.ts`)拥有,而非各适配器。`AppIdentity` 仅包含构建 `User-Agent` 所需的公开产品事实,默认的 `APP_IDENTITY` 确定了提案中留待决定的值: - `User-Agent` 的产品 token:`deepseek-harness`(与 Agent Note 之前的线路值及仓库/组织身份保持连续性) -- 版本:通过 `createRequire` 从所属包的 manifest 读取,绝不手动复制常量 -- 应用 URL:`https://github.com/deepseek-ai/deepseek-harness-sdk`——计划中的公开主页;`attribution.ts` 中的 `FIXME` 标记在该仓库实际存在之前阻塞发布 +- 版本:通过 `createRequire` 从所属包的 manifest(元数据清单)读取,绝不手动复制常量 +- 应用 URL:`https://github.com/deepseek-ai/deepseek-harness-sdk`——计划中的公开主页,且必须在发布前实际存在 默认值是强制的且非空。白标部署通过向 `attributionHeaders(identity)` 传入自己的 `AppIdentity` 来覆盖——覆盖 seam 就是函数参数,在有消费方需要之前不做部署配置管道——省略时回退到 harness 默认值而非抑制归属。没有逐请求 API 允许模型、用户提示词、会话 id、cwd、用户邮箱、API key 所有者或本地机器身份影响这些字段。 @@ -41,7 +41,7 @@ LLM(大语言模型)提供方请求应当标识发出请求的产品。这 | 目标 | 映射 | |---|---| | 所有基于 HTTP 的适配器 | `User-Agent: {product}/{version} (+{url})`——括号中的 `+url` 注释符合 RFC 9110 保守的 product/comment 语法。 | -| 直连 DeepSeek 端点 | `User-Agent`;除非 DeepSeek 文档化了等效契约,否则不发送 OpenRouter 特有头部。 | +| 直连 DeepSeek 端点 | `User-Agent`;除非 DeepSeek 文档化了等效约定,否则不发送 OpenRouter 特有头部。 | | OpenRouter 端点 | 目前仅 `User-Agent`。本 Agent Note 下不发送 `HTTP-Referer`、`X-OpenRouter-Title`、`X-Title` 或 `X-OpenRouter-Categories`。 | | 未来提供方 | 仅 `User-Agent`,除非后续提供方特有的 Agent Note 接受额外头部。不要类比复用 `HTTP-Referer`。 | @@ -49,9 +49,9 @@ LLM(大语言模型)提供方请求应当标识发出请求的产品。这 ## 验证 -已落地的契约: +已落地的约定: -- `dsh-llm` 为 `LlmAdapter` 作者文档化了强制的 `User-Agent` 归属契约(`LlmAdapter` JSDoc、包 README,以及 `docs/core-data-structures/llm-streaming.md` 的适配器契约章节)。 +- `dsh-llm` 为 `LlmAdapter` 作者文档化了强制的 `User-Agent` 归属约定(`LlmAdapter` JSDoc、包 README,以及 `docs/subsystems/llm-streaming.md` 的适配器约定(adapter contract)章节)。 - 共享辅助函数(`attributionHeaders` / `userAgent`)从包元数据构建应用身份和标准 `User-Agent` 值,适配器无需手动复制版本常量。 - `dsh-llm-deepseek` 在每个请求上发送共享的 `User-Agent`,其 mock 服务器套件断言精确值。 - `dsh-llm-pi-ai` 通过 pi-ai 的 `StreamOptions.headers` 钩子发送相同的 `User-Agent`,其 mock 服务器套件断言精确值。 @@ -63,7 +63,7 @@ LLM(大语言模型)提供方请求应当标识发出请求的产品。这 **现在就实现 OpenRouter 应用归属。** 本 Agent Note 否决。发送 `HTTP-Referer` 加 `X-OpenRouter-Title` 可以满足 OpenRouter 排名,但这些头部是提供方特有的产品功能,不是本 Agent Note 试图标准化的提供方无关的模型请求归属。支持它们应当是后续显式的 OpenRouter 适配器/模式决策,而非隐藏在首个共享归属辅助函数中。 -**向所有提供方发送 OpenRouter 头部。** 否决。这会把一份自定义的 OpenRouter 契约当作通用标准,并向未要求这些字段的提供方发送语义误导的头部。还有风险将 `HTTP-Referer` 当作通用应用 URL 字段使用,尽管标准 HTTP 已有 `User-Agent` 用于产品身份、`Referer` 用于不同的浏览上下文概念。 +**向所有提供方发送 OpenRouter 头部。** 否决。这会把一项自定义的 OpenRouter 惯例当作通用标准,并向未要求这些字段的提供方发送语义误导的头部。还有风险将 `HTTP-Referer` 当作通用应用 URL 字段使用,尽管标准 HTTP 已有 `User-Agent` 用于产品身份、`Referer` 用于不同的浏览上下文概念。 **仅使用提供方账户/项目身份。** 否决。组织/项目头部、API key、云账户和计费项目标识的是谁付费或谁拥有请求,而非哪个应用在发送流量。它们也不暴露公开的应用标题/类别,无法帮助 OpenRouter 等网关构建应用排名。 @@ -77,8 +77,8 @@ LLM(大语言模型)提供方请求应当标识发出请求的产品。这 **提供方看到流量来自 harness。** 这正是目的,但意味着此前混在通用 SDK 流量中的部署变得可识别。缓解措施:仅发送静态公开产品数据,并允许 fork/白标部署传入自己的 `AppIdentity`。 -**应用 URL 指向一个尚不存在的仓库。** `deepseek-ai/deepseek-harness-sdk` 是计划中的公开主页;在它创建之前,该 URL 是一个悬空承诺。常量上的 `FIXME` 标记阻塞发布,不允许带着未解决的问题出门(见 `docs/development.md` 标记语义)。 +**应用 URL 指向一个尚不存在的仓库。** `deepseek-ai/deepseek-harness-sdk` 是计划中的公开主页;在它创建之前,该 URL 是一个阻塞发布的悬空承诺。 -**不同客户端库的头部支持有差异。** 手写适配器直接设置头部;基于 pi-ai 的适配器依赖 pi-ai 继续尊重 `StreamOptions.headers`(最后合并覆盖提供方默认值)。线路级 mock 服务器测试是守卫:如果 pi-ai 升级后不再投递该头部,套件会变红。这对抽象施加了有益的压力:一个无法设置强制头部的提供方适配器不能完整实现 harness 的 LLM 契约。 +**不同客户端库的头部支持有差异。** 手写适配器直接设置头部;基于 pi-ai 的适配器依赖 pi-ai 继续尊重 `StreamOptions.headers`(最后合并覆盖提供方默认值)。线路级 mock 服务器测试是守卫:如果 pi-ai 升级后不再投递该头部,套件会变红。这对抽象施加了有益的压力:一个无法设置强制头部的提供方适配器不能完整实现 harness 的 LLM 约定。 **OpenRouter 排名尚未受益。** `User-Agent` 是提供方无关的 HTTP 身份的正确基线,但它不会创建 OpenRouter 应用页面或排名,因为 OpenRouter 要求 `HTTP-Referer` 来实现该产品功能。这是有意为之:公开应用市场参与是一个独立的产品决策,不是强制请求归属的前提。 diff --git a/.agents/notes/implemented/architecture/2026-06-24-web-capability-seam.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-24-web-capability-seam.i18n.yaml index 2175305799..43259e19b2 100644 --- a/.agents/notes/implemented/architecture/2026-06-24-web-capability-seam.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-06-24-web-capability-seam.i18n.yaml @@ -1,6 +1,6 @@ # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: -# pnpm run verify-translation-pairing --write +# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-06-24-web-capability-seam.md 2026-06-24-web-capability-seam.md: b705236690859961ed69b307dbb59ebefcbd65ac -2026-06-24-web-capability-seam.zh.md: 9b6899c922524350d2eee62140480fd76a450baa +2026-06-24-web-capability-seam.zh.md: ea9261b4bc16cbd913c90f5ccb1aeebc1a0d8dea diff --git a/.agents/notes/implemented/architecture/2026-06-24-web-capability-seam.zh.md b/.agents/notes/implemented/architecture/2026-06-24-web-capability-seam.zh.md index 9b6899c922..ea9261b4bc 100644 --- a/.agents/notes/implemented/architecture/2026-06-24-web-capability-seam.zh.md +++ b/.agents/notes/implemented/architecture/2026-06-24-web-capability-seam.zh.md @@ -6,11 +6,11 @@ Status: implemented ## 问题 -harness 需要面向模型的 web 工具,但不能将模型契约绑定到某一家厂商的 API 形状上。搜索是当前的压力点:从一开始就同时支持 Exa 搜索和 Perplexity 搜索——两种刻意不同的提供方形状(Exa 返回扁平的 `results[]`,每项包含 `{title, url, highlights, publishedDate}`;Perplexity 返回一段生成式回答加引用列表)——正是用来证明归一化的 seam 并非只是镜像某一家厂商。Fetch 是另一项独立能力:匿名公开 HTTP(S) fetch 后端涉及传输、安全、重定向、解码和大小限制等关注点,与提供方支撑的搜索并不相同。 +harness 需要面向模型的 web 工具,但不能将模型约定绑定到某一家厂商的 API 形状上。搜索是当前的压力点:从一开始就同时支持 Exa 搜索和 Perplexity 搜索——两种刻意不同的提供方形状(Exa 返回扁平的 `results[]`,每项包含 `{title, url, highlights, publishedDate}`;Perplexity 返回一段生成式回答加引用列表)——正是用来证明归一化的 seam 并非只是镜像某一家厂商。Fetch 是另一项独立能力:匿名公开 HTTP(S) fetch 后端涉及传输、安全、重定向、解码和大小限制等关注点,与提供方支撑的搜索并不相同。 面向模型的接口必须保持稳定,而后端可以更换。更换搜索提供方不应改变模型发起查询的方式;更换 fetch 实现不应改变模型请求 URL 的方式。反过来,提供方包也不应仅仅因为自己有额外的提供方特有旋钮就暴露自己的面向模型工具 schema。 -如果把搜索和 fetch 直接放进 `dsh-tool-web`,面向模型的工具就要同时承担提供方选择、后端请求映射、传输策略、结果归一化、提示词引导、展示和 schema 注册。让每个提供方注册自己的工具则有相反的问题:工具的可用性、名称、描述和参数将取决于恰好加载了哪些提供方包,提供方特有字段会泄漏到模型契约中。 +如果把搜索和 fetch 直接放进 `dsh-tool-web`,面向模型的工具就要同时承担提供方选择、后端请求映射、传输策略、结果归一化、提示词引导、展示和 schema 注册。让每个提供方注册自己的工具则有相反的问题:工具的可用性、名称、描述和参数将取决于恰好加载了哪些提供方包,提供方特有字段会泄漏到模型约定中。 还有一个提供方选择的问题。现有的 `tool-bash` 和 `tool-fs` 可以依赖 Cordis 的 `inject`,因为只有一个后端服务键。Web 有两项独立能力(`search` 和 `fetch`),每项能力可能有多个提供方。`inject: ['web']` 能证明 seam 存在,但不能证明存在可用的搜索或 fetch 提供方,也无法定义多个提供方注册时谁胜出。 @@ -32,7 +32,7 @@ Web 访问是一个一等能力 seam,遵循[能力 seam Agent Note](2026-06-13 - 工具绝不会仅仅因为其选定的提供方缺失、配置错误、缺少凭证、存在歧义或暂时不可用就被注销。 - 提供方在执行时解析,当选定的能力无法运行时返回结构化的 `WebError`。 -这使模型 schema 保持稳定,而不将插件加载顺序、凭证状态或 HMR(热模块替换)时序纳入面向模型的契约。如果 web 搜索已启用但不存在可用的搜索提供方,`web_search` 仍然可见,执行时以结构化的 `WebError`(如 `WEB_PROVIDER_UNAVAILABLE` 或 `WEB_PROVIDER_CONFIGURED_UNAVAILABLE`)失败。如果某个提供方在 `dsh-tool-web` 之后出现,下一次执行即可使用它而无需更改 schema。如果某个提供方在调用过程中消失,执行以结构化的 `WebError` 失败,而不是静默选择另一个提供方或回退到 `UNKNOWN_TOOL`。 +这使模型 schema 保持稳定,而不将插件加载顺序、凭证状态或 HMR(热模块替换)时序纳入面向模型的约定。如果 web 搜索已启用但不存在可用的搜索提供方,`web_search` 仍然可见,执行时以结构化的 `WebError`(如 `WEB_PROVIDER_UNAVAILABLE` 或 `WEB_PROVIDER_CONFIGURED_UNAVAILABLE`)失败。如果某个提供方在 `dsh-tool-web` 之后出现,下一次执行即可使用它而无需更改 schema。如果某个提供方在调用过程中消失,执行以结构化的 `WebError` 失败,而不是静默选择另一个提供方或回退到 `UNKNOWN_TOOL`。 该 seam 刻意不暴露任何观察面——没有注册表变更事件,也没有聚合的能力状态查询。不可用性是调用方通过执行观察到的事实:`search()`/`fetch()` 在调用时解析提供方,并抛出命名了失败原因的结构化 `WebError`。[观察面 Agent Note](../../archived/simplification/2026-07-04-drop-unconsumed-web-observation-surface.md) 记录了这一判断:基于调用的派生选择与基于启用的注册使得没有消费方需要变更信号或独立于执行和错误路由的可用性探测;未来的提供方状态面板会重新引入它实际消费的最小信号或查询。 @@ -66,13 +66,13 @@ flowchart LR toolWeb -->|ctx.tools.register| webFetch["tool: web_fetch"] ``` -`@deepseek-ai/dsh-web` 仅依赖 Cordis 和底层 harness 支持。它声明 `ctx.web`、提供方接口、请求/结果类型、提供方可用性契约和错误码。它不导入工具、agent、会话、LLM 或提供方包。 +`@deepseek-ai/dsh-web` 仅依赖 Cordis 和底层 harness 支持。它声明 `ctx.web`、提供方接口、请求/结果类型、提供方可用性约定和错误码。它不导入工具、agent、会话、LLM 或提供方包。 提供方包仅依赖 `dsh-web` 和 Cordis。它们拥有凭证、端点、协议格式映射、解析和 `WebError` 转换,使用平台 `fetch`。每个提供方注入共享服务并注册后端;只有 `dsh-web` 拥有 `ctx.web` 键。提供方私有的协议形状不会产生对 `ctx.llm` 或 Cordis HTTP 服务的依赖。 `@deepseek-ai/dsh-tool-web` 依赖 `@deepseek-ai/dsh-web`、`@deepseek-ai/dsh-tools`、`@deepseek-ai/dsh-system-prompt` 和 Cordis。它从不导入具体的提供方包。 -## `ctx.web` 契约 +## `ctx.web` 约定 `ctx.web` 是一个提供方注册表加上一个带提供方选择的执行面。注册表部分与 `LlmService` 保持接近:每种能力类别一个 `Map`,`registerSearchProvider`/`registerFetchProvider` 方法返回 disposer,重复 id 抛出 `WebError`,执行时解析在选定提供方缺失或不可用时抛出异常。权威签名见 `packages/web/web/src/types.ts`;seam 的形状: @@ -280,7 +280,7 @@ SSRF/私有网络防护(阻断私有、回环、链路本地、多播及其他 ## 测试 -每一层在自己的 seam 处固定:`dsh-web` 中的注册/选择/截断/abort 契约与 `WebError` 码;每个提供方基于录制的 fixture(测试前置数据)的请求/响应映射(Perplexity fixture 包含纯 URL 引用,以保持可选 source 字段的诚实性),加上每个真实提供方的自跳过带密钥冒烟测试;`web-fetch-local` 中的真实本地 HTTP 行为;`dsh-tool-web` 中通过真实工具注册表的启用驱动注册、结构化执行错误和结果格式化。一个真实 Loader 冒烟测试守护两种导出形状([事后分析 0001](../../../../docs/postmortem/0001-acp-default-export-drops-inject.md)):`dsh-web` 是默认导出的服务,而提供方和 `tool-web` 是命名空间插件,误加 `export default` 会丢失 `inject`。 +每一层在自己的 seam 处固定:`dsh-web` 中的注册/选择/截断/abort 约定与 `WebError` 码;每个提供方基于录制的 fixture(测试前置数据)的请求/响应映射(Perplexity fixture 包含纯 URL 引用,以保持可选 source 字段的诚实性),加上每个真实提供方的自跳过带密钥冒烟测试;`web-fetch-local` 中的真实本地 HTTP 行为;`dsh-tool-web` 中通过真实工具注册表的启用驱动注册、结构化执行错误和结果格式化。一个真实 Loader 冒烟测试守护两种导出形状([事故复盘(postmortem) 0001](../../../../docs/postmortem/0001-acp-default-export-drops-inject.md)):`dsh-web` 是默认导出的服务,而提供方和 `tool-web` 是命名空间插件,误加 `export default` 会丢失 `inject`。 ## 曾考虑的替代方案 @@ -322,6 +322,8 @@ SSRF/私有网络防护(阻断私有、回环、链路本地、多播及其他 **大量 web 内容可能损害上下文质量。** 提供方强制执行字节/字符上限并报告 `truncated`;`tool-web` 格式化有界的模型输出,附带清晰的继续或后续引导。 + + ## 推迟工作 - `web_fetch` 的 SSRF/私有网络防护:阻断私有、回环、链路本地、多播及其他非公开目的地,使 `web_fetch` 不再是 SSRF 原语。正确实现不仅仅是 URL 字符串检查——需要先 DNS 解析再连接到已验证的 IP(防御 DNS rebinding/TOCTOU)、跨重定向的每跳重新验证,以及 IPv6 边缘处理(私有范围、IPv4 映射地址)。所调研的参考实现均未做 IP 级阻断(OpenCode 做前缀检查后直接 fetch;Claude Code 依赖集中式主机名黑名单加「私有 URL 会失败」的提示词),因此没有可复制的实现,且这是 harness 唯一的 SSRF 防线——值得一次专门的设计/spike。在其落地之前,`web_fetch` 只能在无法触达敏感内部目标的部署中启用。 diff --git a/.agents/notes/implemented/architecture/2026-06-26-file-context-as-event-gate.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-26-file-context-as-event-gate.i18n.yaml index 614868ada0..726ab7374d 100644 --- a/.agents/notes/implemented/architecture/2026-06-26-file-context-as-event-gate.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-06-26-file-context-as-event-gate.i18n.yaml @@ -1,6 +1,6 @@ # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: -# pnpm run verify-translation-pairing --write +# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-06-26-file-context-as-event-gate.md 2026-06-26-file-context-as-event-gate.md: 4700222aa2e0f91d9f355495c228e2eb92825f55 -2026-06-26-file-context-as-event-gate.zh.md: 21c8706bcc14790a5092fa59e03bce329049760a +2026-06-26-file-context-as-event-gate.zh.md: dff5c3e9ea99e73d3d1a86c4012da1e4232021bb diff --git a/.agents/notes/implemented/architecture/2026-06-26-file-context-as-event-gate.zh.md b/.agents/notes/implemented/architecture/2026-06-26-file-context-as-event-gate.zh.md index 21c8706bcc..dff5c3e9ea 100644 --- a/.agents/notes/implemented/architecture/2026-06-26-file-context-as-event-gate.zh.md +++ b/.agents/notes/implemented/architecture/2026-06-26-file-context-as-event-gate.zh.md @@ -6,7 +6,7 @@ Status: implemented ## 问题 -[拆分文件系统 seam Agent Note(agent 决策记录)](../simplification/2026-06-26-fsspec-style-fs-seam.md) 在面向模型的工具与 `ctx.fs` 提供方之间放置了 `ctx.fileContext`:`dsh-tool-fs` 注入 `fileContext`,并将每次 `read`/`write`/`edit` 路由到它的方法。这使得 `fileContext` **位于关键路径上且不可省略**。工具不经过它就无法访问 `ctx.fs`,策略层掌控着 fs I/O 和读取窗口,而一个不需要观测状态策略的部署也无法简单地移除该包——`dsh-tool-fs` 会因无法解析 `ctx.fileContext` 而失败。 +[拆分文件系统 seam Agent Note](../simplification/2026-06-26-fsspec-style-fs-seam.md) 在面向模型的工具与 `ctx.fs` 提供方之间放置了 `ctx.fileContext`:`dsh-tool-fs` 注入 `fileContext`,并将每次 `read`/`write`/`edit` 路由到它的方法。这使得 `fileContext` **位于关键路径上且不可省略**。工具不经过它就无法访问 `ctx.fs`,策略层掌控着 fs I/O 和读取窗口,而一个不需要观测状态策略的部署也无法简单地移除该包——`dsh-tool-fs` 会因无法解析 `ctx.fileContext` 而失败。 这把三件本应可分离的事情耦合在了一起: @@ -44,7 +44,7 @@ provider dsh-fs-local local implementation of ctx.fs 这是有意为之的。如果 `dsh-fs-policy` 在其 waterfall(瀑布式事件)处理器中 stat 并比较版本,该检查与工具实际写入之间会存在 TOCTOU 间隙——文件可能在此期间变化,因此该检查只是一个虚假保证,提供方的锁无论如何都要兜底。将版本检查放在提供方的临界区中既无竞态又无额外 `stat`。所以 `dsh-fs-policy` **不做**任何文件系统 I/O;「必须基于最近一次读取」的保证由 CAS *实现*,`dsh-fs-policy` 只负责选择基准(`vObserved`)并对先前观测进行门控。 -## 提供方契约变更:版本守卫变为可选 +## 提供方约定变更:版本守卫变为可选 为使裸提供方不受约束,其两个 mutation 上的版本守卫变为**可选**——传入则守卫,省略则无条件执行: @@ -66,7 +66,7 @@ editText(target: FsTarget, edit: FsEditRequest, expected?: { version: FsVersion ## 事件词汇(由 `dsh-fs` 拥有) -事件定义在 `@deepseek-ai/dsh-fs` 中,而非 `dsh-fs-policy` 中。这是解耦契约所迫:`dsh-tool-fs` 是发射方,因此它必须引用事件类型,且即使 `dsh-fs-policy` 不再提供方法服务,它也必须能编译通过。`dsh-fs` 是 `dsh-tool-fs` 和 `dsh-fs-policy` 都已依赖的包,因此它是唯一能让发射方和策略监听方共享词汇而不让发射方依赖策略插件的归属地。 +事件定义在 `@deepseek-ai/dsh-fs` 中,而非 `dsh-fs-policy` 中。这是解耦约定所迫:`dsh-tool-fs` 是发射方,因此它必须引用事件类型,且即使 `dsh-fs-policy` 不再提供方法服务,它也必须能编译通过。`dsh-fs` 是 `dsh-tool-fs` 和 `dsh-fs-policy` 都已依赖的包,因此它是唯一能让发射方和策略监听方共享词汇而不让发射方依赖策略插件的归属地。 这些事件携带既有的 `dsh-fs` 词汇(`FsTarget`、`FsVersion`、`FsWriteIntent`)加一个不透明的 actor——不携带面向模型的概念(行窗口、行号或渲染后的页脚不会泄漏到此层)。 @@ -108,7 +108,7 @@ interface Events { `fs/*` 决策事件是**由工具分发的无绑定 waterfall**(类似 `agent/request`,由循环分发且无 `this`),而非服务绑定的 waterfall(如 `llm/stream`)。分发者是 `dsh-tool-fs` 插件,它不是一个服务。 -## 工具契约(`dsh-tool-fs`) +## 工具约定(`dsh-tool-fs`) 工具保留其面向模型的 schema(`read`/`write`/`edit`,逐字节不变)和提示词段落。提示词引导仍以策略优先,因为加载 fs 工具的部署预期也会加载 `dsh-fs-policy`:模型仍被告知在覆写或编辑前先读取,任何声称「后端」要求如此的措辞应修正为 fs-policy 插件要求如此。裸提供方回退不改变提示词立场。 @@ -124,9 +124,9 @@ interface Events { 工具在每次分发时将 `exec`(工具执行上下文)作为 `actor` 参数传入,以便 `dsh-fs-policy` 推导其观测状态的 owner。工具不知道策略插件是否存在:它始终在 `next` thunk 中提供裸默认行为,而 `dsh-fs-policy` 在默认部署中会在 thunk 运行前短路它。 -**`fs/observed` 在操作成功后触发。** 其监听器必须是同步、不抛异常的记录器;工具不对 plain emit 做保护,因此抛异常的监听器会在 mutation 已成功后报告失败。异步或可失败的观测需要另一份事件契约。 +**`fs/observed` 在操作成功后触发。** 其监听器必须是同步、不抛异常的记录器;工具不对 plain emit 做保护,因此抛异常的监听器会在 mutation 已成功后报告失败。异步或可失败的观测需要另一份事件约定。 -## 策略插件契约(`dsh-fs-policy`) +## 策略插件约定(`dsh-fs-policy`) `dsh-fs-policy` 是插件,不是服务。它不注册 `ctx.fileContext`,没有公开方法面,不暴露 `read`/`write`/`edit`/`resolve` 方法。它通过 `ctx.on()` 注册三个监听器(每个返回一个 disposer 用于 HMR)。它维护观测状态 `WeakMap>`,以及结构化的 owner 推导(将事件中不透明的 `object` actor 收窄为自己的 `{ agent?: { session? } }` 形状),但不注入 `fs`——每个处理器只操作自己的 `WeakMap`,从不操作 `ctx.fs`。 @@ -150,7 +150,7 @@ interface Events { ## 取代关系 -本 Agent Note 修正——而非推翻——[拆分文件系统 seam Agent Note](../simplification/2026-06-26-fsspec-style-fs-seam.md)。四层拆分、提供方契约和新鲜度*策略*均保留。变更的是**工具与策略层之间的耦合方式**:强制性方法服务变为插件拥有的事件门控,fs I/O + 读取窗口从 `fileContext` 上移至 `dsh-tool-fs`。拆分文件系统 seam Agent Note 中关于 `dsh-tool-fs` 注入 `fileContext` 以及 `fileContext` 拥有 `read`/`write`/`edit` 的描述已在同一变更中更新。 +本 Agent Note 修正——而非推翻——[拆分文件系统 seam Agent Note](../simplification/2026-06-26-fsspec-style-fs-seam.md)。四层拆分、提供方约定和新鲜度*策略*均保留。变更的是**工具与策略层之间的耦合方式**:强制性方法服务变为插件拥有的事件门控,fs I/O + 读取窗口从 `fileContext` 上移至 `dsh-tool-fs`。拆分文件系统 seam Agent Note 中关于 `dsh-tool-fs` 注入 `fileContext` 以及 `fileContext` 拥有 `read`/`write`/`edit` 的描述已在同一变更中更新。 ## 验证 diff --git a/.agents/notes/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.i18n.yaml index 690aa1f9b4..459ffa188c 100644 --- a/.agents/notes/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.i18n.yaml @@ -1,6 +1,6 @@ # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: -# pnpm run verify-translation-pairing --write -2026-06-30-bash-stdin-env-trusted-plugin-surface.md: 556d5dd86dfcc92c4628e68c19390f0033560d25 -2026-06-30-bash-stdin-env-trusted-plugin-surface.zh.md: 9d67797f86903e70e7bdcd6f80f19d17c41ac18e +# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md +2026-06-30-bash-stdin-env-trusted-plugin-surface.md: aa0c785be84bcb8a49f8a2670afa0f6bed6277db +2026-06-30-bash-stdin-env-trusted-plugin-surface.zh.md: 48108fdd5b8217263590fba336480f1b487e882f diff --git a/.agents/notes/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md b/.agents/notes/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md index 556d5dd86d..aa0c785be8 100644 --- a/.agents/notes/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md +++ b/.agents/notes/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md @@ -30,4 +30,4 @@ Three deliberate choices: ## Consequences -Hook bridges pass JSON payloads and hook-specific variables through the existing bash seam, retaining its process-group, truncation, and spill behavior. The model surface remains unchanged, and the bash tool remains the sole owner of model-call request construction. The vocabulary lives in [the bash data-structure reference](../../../../docs/core-data-structures/bash.md). +Hook bridges pass JSON payloads and hook-specific variables through the existing bash seam, retaining its process-group, truncation, and spill behavior. The model surface remains unchanged, and the bash tool remains the sole owner of model-call request construction. The vocabulary lives in [the bash data-structure reference](../../../../docs/subsystems/bash.md). diff --git a/.agents/notes/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.zh.md b/.agents/notes/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.zh.md index 9d67797f86..48108fdd5b 100644 --- a/.agents/notes/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.zh.md +++ b/.agents/notes/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.zh.md @@ -18,7 +18,7 @@ Status: implemented 1. **模型侧工具不暴露 `stdin` 和 `env`。** Shell 语法已覆盖这些需求,重复参数只会增加接口面而不带来权限隔离。工具仅从声明的模型参数、signal 和 owner 构建请求;受信的进程内调用方可以直接设置 seam 字段。harness 自有变量使用[托管环境决策](../feature/2026-07-10-agent-session-identity-and-log-location.md)规定的独立 `dshEnv` 通道,因此普通 `env` 无法替换它们。 -2. **`env` 在凭证擦除之后合并,因此调用方显式设置的条目即使具有凭证形态的名称也会胜出。** 后续的托管命名空间决策托管 `DSH_*`:环境条目会被移除,受信的 `dshEnv` 最后合并,因此普通 `env` 条目永远无法顶掉托管值。完整顺序为 `scrub(process.env, including DSH_*)` → `ENV_OVERRIDES` → 普通 `env` → `dshEnv`。 +2. **`env` 在凭证擦除之后合并,因此调用方显式设置的条目即使具有凭证形态的名称也会胜出。** 后续的托管命名空间决策负责管理 `DSH_*`:这类环境条目会被移除,受信的 `dshEnv` 最后合并,因此普通 `env` 条目永远无法顶掉托管值。完整顺序为 `scrub(process.env, including DSH_*)` → `ENV_OVERRIDES` → 普通 `env` → `dshEnv`。 3. **`stdin`/`env` 在已解析 spec 上是 required-absent-OK(普通 optional),而非像 `owner` 那样 required-but-nullable。** `owner` 之所以是 required-but-nullable,是因为*静默*缺失的 owner 会产生一个无主、跨会话可读的任务——一个安全隐患,显式的 `undefined` 可以防范。`stdin`/`env` 没有这种风险:缺失意味着「无 stdin / 无额外 env」,这是安全的常规情况(所有模型驱动的调用都如此)。因此它们保持普通 optional,与 `signal` 一致。 @@ -30,4 +30,4 @@ Status: implemented ## 后果 -钩子桥接层通过既有的 bash seam 传递 JSON 载荷和钩子特定变量,保留其进程组终止、截断和溢出行为。模型接口面不变,bash 工具仍是模型调用请求构建的唯一所有者。相关词汇定义见 [bash 数据结构参考](../../../../docs/core-data-structures/bash.md)。 +钩子桥接层通过既有的 bash seam 传递 JSON 载荷和钩子特定变量,保留其进程组终止、截断和溢出行为。模型接口面不变,bash 工具仍是模型调用请求构建的唯一所有者。相关词汇定义见 [bash 数据结构参考](../../../../docs/subsystems/bash.md)。 diff --git a/.agents/notes/implemented/architecture/2026-06-30-event-domain-semantics.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-30-event-domain-semantics.i18n.yaml index c6d8176b90..2e69991c33 100644 --- a/.agents/notes/implemented/architecture/2026-06-30-event-domain-semantics.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-06-30-event-domain-semantics.i18n.yaml @@ -1,6 +1,6 @@ # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: -# pnpm run verify-translation-pairing --write -2026-06-30-event-domain-semantics.md: 75c1cac11d1bfc9aa7fba9c523eab8c0475027e8 -2026-06-30-event-domain-semantics.zh.md: a412b8735b72274252473f3218e0d57d4f814bde +# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-06-30-event-domain-semantics.md +2026-06-30-event-domain-semantics.md: 14102b105e7bcaa6a00ac9c406933f772fc45a6f +2026-06-30-event-domain-semantics.zh.md: 2607e59490d8ba139bb1289d0f2941894281f6c6 diff --git a/.agents/notes/implemented/architecture/2026-06-30-event-domain-semantics.md b/.agents/notes/implemented/architecture/2026-06-30-event-domain-semantics.md index 75c1cac11d..14102b105e 100644 --- a/.agents/notes/implemented/architecture/2026-06-30-event-domain-semantics.md +++ b/.agents/notes/implemented/architecture/2026-06-30-event-domain-semantics.md @@ -21,7 +21,7 @@ This vocabulary is the foundation for interception decisions, the durable `hook/ **Three domains, one job each, with a single boundary rule.** - **`session/*` — the durable, replayable FACT log.** Owns `SessionEventMap`; every entry is JSON-only (no live objects). One `session/event` emit per append, plus the `session/flush` parallel durability checkpoint. It is also the live transcript feed: a consumer that wants to render or react to what happened subscribes here, so live rendering and replay projections share one path. -- **`agent/*` — the LIVE runtime surface.** Always carries the live `Agent`. Two shapes: INTERCEPTION waterfalls (`agent/request`, `agent/step-result`, `agent/turn-continuation`) that mutate or veto, and TRANSIENT emits (`agent/status`, `agent/error`, `agent/created`/`agent/disposed`, `agent/queued`) that notify with the `Agent` in hand. Turn and step BOUNDARIES are NOT here — they are durable session events read off `session/event`, and so are the token stream (`assistant/chunk`) and mid-turn steering (`steering/message`). +- **`agent/*` — the LIVE runtime surface.** Always carries the live `Agent`. Interception waterfalls (`agent/pre-step`, `agent/request`, `agent/request-error`) transform, reject, or recover; awaited `agent/turn-stopping` observes the stop boundary; transient emits report lifecycle, status, inbox insertion/claim/discard, and errors. Turn and step BOUNDARIES are NOT here — they are durable session events read off `session/event`, as are the token stream (`assistant/chunk`) and mid-turn steering (a `user/message`). - **`tools/*` — the tool registry + execution seam.** **The boundary rule:** a durable, replayable fact is a `SessionEvent`; a live interception or a transient/live-object signal is an `agent`/`tools` Cordis event. A turn or step boundary is a durable fact, so it lives in the session log and is read off the `session/event` feed — it is NOT mirrored as an `agent/*` emit. @@ -33,7 +33,7 @@ This vocabulary is the foundation for interception decisions, the durable `hook/ - The loop no longer emits any boundary mirror; `closeStep` appends `step/end` only and `closeTurn` appends `turn/end` only. `Session.append` owns post-commit observer containment, so a throwing boundary observer cannot change the turn outcome or starve later consumers; an acceptance or internal validation failure still escapes before the boundary enters the log. - Tests that observed boundaries via the removed emits now observe the durable `turn/start`/`turn/end`/`step/start`/`step/end` session events — the behavior they pin (boundary ordering, step counting) is unchanged; only the feed they read moved to the canonical one. The tests that exercised a *throwing turn-boundary emit listener* were deleted, because that code path no longer exists (there is no emit to throw from). Per [AGENTS.md "tests document behavior, not golden truth"](../../../../AGENTS.md), the behavior and its test moved (or died) together. - The loop marks the step open (`stepOpen = true`) only after `append('step/start')` returns. Internal dispatch validation runs before the log push and may reject without opening a step; post-commit `session/event` observer failures are contained inside `Session.append`. The marker therefore represents exactly the committed boundary that owes a later `step/end`. -- The full realization of this is [the simplification Agent Note "Stop mirroring durable boundaries as agent events"](../simplification/2026-06-20-remove-agent-boundary-mirror-events.md): all four boundary mirrors are removed and every consumer reads boundaries off `session/event`. `agent/steering` (not a boundary mirror) stayed outside that Agent Note's scope and was removed by its own follow-up, [Remove the `agent/steering` mirror emit](../../archived/simplification/2026-07-04-remove-agent-steering-mirror.md) — it mirrored the durable `steering/message`. +- The full realization of this is [the simplification Agent Note "Stop mirroring durable boundaries as agent events"](../simplification/2026-06-20-remove-agent-boundary-mirror-events.md): all four boundary mirrors are removed and every consumer reads boundaries off `session/event`. `agent/steering` (not a boundary mirror) stayed outside that Agent Note's scope and was removed by its own follow-up, [Remove the `agent/steering` mirror emit](../../archived/simplification/2026-07-04-remove-agent-steering-mirror.md) — it mirrored the durable mid-turn steering `user/message`. - The cordis events catalog (`docs/cordis-catalog/events.md`) is regenerated to drop the mirror events. diff --git a/.agents/notes/implemented/architecture/2026-06-30-event-domain-semantics.zh.md b/.agents/notes/implemented/architecture/2026-06-30-event-domain-semantics.zh.md index a412b8735b..2607e59490 100644 --- a/.agents/notes/implemented/architecture/2026-06-30-event-domain-semantics.zh.md +++ b/.agents/notes/implemented/architecture/2026-06-30-event-domain-semantics.zh.md @@ -21,19 +21,19 @@ harness 通过 Cordis 事件分类体系扩展 agent loop(智能体循环) **三个域,各司其职,以一条边界规则统一。** - **`session/*`——持久的、可回放的事实日志。** 拥有 `SessionEventMap`;每条记录仅含 JSON(无活对象)。每次追加触发一次 `session/event` emit,加上 `session/flush` 并行持久性检查点。它同时也是实时 transcript(文本记录)源:想渲染或响应已发生事件的消费方在此订阅,因此实时渲染与回放投影共享同一路径。 -- **`agent/*`——运行时实时表面。** 始终携带活的 `Agent`。两种形态:拦截 waterfall(瀑布式事件)(`agent/request`、`agent/step-result`、`agent/turn-continuation`)可变更或否决;瞬态 emit(`agent/status`、`agent/error`、`agent/created`/`agent/disposed`、`agent/queued`)在持有 `Agent` 的情况下通知。轮次和步骤边界不在此处——它们是持久的会话事件,从 `session/event` 读取;token 流(`assistant/chunk`)和中途 steering(中途引导)(`steering/message`)同理。 +- **`agent/*`——运行时实时表面。** 始终携带活的 `Agent`。拦截 waterfall(瀑布式事件)(`agent/pre-step`、`agent/request`、`agent/request-error`)负责变换、拒绝或恢复;awaited `agent/turn-stopping` 观察停止边界;瞬态 emit 报告生命周期、状态、inbox 插入/领取/丢弃与错误。轮次和步骤边界不在此处——它们是持久的会话事件,从 `session/event` 读取;token 流(`assistant/chunk`)和作为一条 `user/message` 的轮次中途 steering(中途引导)同理。 - **`tools/*`——工具注册表与执行 seam。** **边界规则:** 持久的、可回放的事实是 `SessionEvent`;实时拦截或瞬态/活对象信号是 `agent`/`tools` Cordis 事件。轮次或步骤边界是持久事实,因此存在于会话日志中并从 `session/event` 源读取——不会被镜像为 `agent/*` emit。 -**将规则应用于边界镜像:** 全部四个边界镜像——`agent/turn-start`、`agent/turn-end`、`agent/step-start`、`agent/step-end`——被**移除**。没有生产消费方需要在边界处获取活的 `Agent`:ACP 桥接将其进行中的提示词与精确对应的 `session/event` `turn/start`/`turn/end` 事件对关联,其他 transcript 消费方同样从持久流派生边界。见[移除边界镜像事件 Agent Note](../simplification/2026-06-20-remove-agent-boundary-mirror-events.md),该决策由它负责。移除 emit 也简化了循环的 `closeStep`/`closeTurn`(各只需一次 append,无需配对 emit)。 +**将规则应用于边界镜像:** 全部四个边界镜像——`agent/turn-start`、`agent/turn-end`、`agent/step-start`、`agent/step-end`——被**移除**。没有生产消费方需要在边界处获取活的 `Agent`:ACP(Agent Client Protocol)桥接将其进行中的提示词与精确对应的 `session/event` `turn/start`/`turn/end` 事件对关联,其他 transcript 消费方同样从持久流派生边界。见[移除边界镜像事件 Agent Note](../simplification/2026-06-20-remove-agent-boundary-mirror-events.md),该决策由它负责。移除 emit 也简化了循环的 `closeStep`/`closeTurn`(各只需一次 append,无需配对 emit)。 ## 后果 -- 循环不再 emit 任何边界镜像;`closeStep` 仅追加 `step/end`,`closeTurn` 仅追加 `turn/end`。`Session.append` 负责 post-commit observer 隔离,因此抛出异常的边界 observer 无法改变轮次结果或饿死后续消费方;接受或内部校验失败仍会在边界进入日志之前逃逸。 -- 之前通过已移除 emit 观察边界的测试,现在观察持久的 `turn/start`/`turn/end`/`step/start`/`step/end` 会话事件——它们固定的行为(边界顺序、步骤计数)不变;只是读取的源移到了规范源。那些测试*抛出异常的轮次边界 emit 监听器*的用例被删除,因为该代码路径不再存在(没有 emit 可供抛出)。按照 [AGENTS.md「测试记录行为,而非黄金真相」](../../../../AGENTS.md),行为与其测试一同迁移(或一同消亡)。 +- 循环不再 emit 任何边界镜像;`closeStep` 仅追加 `step/end`,`closeTurn` 仅追加 `turn/end`。`Session.append` 负责 post-commit observer 隔离,因此抛出异常的边界 observer 无法改变轮次结果或饿死后续消费方;事件接纳失败或内部校验失败仍会在边界进入日志之前向外抛出。 +- 之前通过已移除 emit 观察边界的测试,现在观察持久的 `turn/start`/`turn/end`/`step/start`/`step/end` 会话事件——它们所锁定的行为(边界顺序、步骤计数)不变;只是读取的源移到了规范源。那些测试*抛出异常的轮次边界 emit 监听器*的用例被删除,因为该代码路径不再存在(没有 emit 可供抛出)。按照 [AGENTS.md「测试记录行为,而非黄金真相」](../../../../AGENTS.md),行为与其测试一同迁移(或一同消亡)。 - 循环仅在 `append('step/start')` 返回后才标记步骤已打开(`stepOpen = true`)。内部分发校验在日志推入之前运行,可能在不打开步骤的情况下拒绝;post-commit `session/event` observer 的失败被隔离在 `Session.append` 内部。因此该标记精确表示已提交的、欠一个后续 `step/end` 的边界。 -- 完整实现见[简化 Agent Note「停止将持久边界镜像为 agent 事件」](../simplification/2026-06-20-remove-agent-boundary-mirror-events.md):全部四个边界镜像被移除,所有消费方从 `session/event` 读取边界。`agent/steering`(不是边界镜像)不在该 Agent Note 范围内,由其后续 Agent Note [移除 `agent/steering` 镜像 emit](../../archived/simplification/2026-07-04-remove-agent-steering-mirror.md) 单独移除——它镜像的是持久的 `steering/message`。 +- 完整实现见[简化 Agent Note「停止将持久边界镜像为 agent 事件」](../simplification/2026-06-20-remove-agent-boundary-mirror-events.md):全部四个边界镜像被移除,所有消费方从 `session/event` 读取边界。`agent/steering`(不是边界镜像)不在该 Agent Note 范围内,由其后续 Agent Note [移除 `agent/steering` 镜像 emit](../../archived/simplification/2026-07-04-remove-agent-steering-mirror.md) 单独移除——它镜像的是持久的中途 steering `user/message`。 - Cordis 事件目录(`docs/cordis-catalog/events.md`)重新生成以移除镜像事件。 diff --git a/.agents/notes/implemented/architecture/2026-07-02-fs-per-session-cwd.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-02-fs-per-session-cwd.i18n.yaml index e48cfbacb6..da7848d581 100644 --- a/.agents/notes/implemented/architecture/2026-07-02-fs-per-session-cwd.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-02-fs-per-session-cwd.i18n.yaml @@ -1,6 +1,6 @@ # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: -# pnpm run verify-translation-pairing --write +# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-02-fs-per-session-cwd.md 2026-07-02-fs-per-session-cwd.md: d3f54e89e735016a373fa14c60123c681b3e7adf -2026-07-02-fs-per-session-cwd.zh.md: ae732a3e4dacc3d4b800044aad60df3f3ce17cc0 +2026-07-02-fs-per-session-cwd.zh.md: 86058437a14f64cc7faf6e6ad413c52efba5fd39 diff --git a/.agents/notes/implemented/architecture/2026-07-02-fs-per-session-cwd.zh.md b/.agents/notes/implemented/architecture/2026-07-02-fs-per-session-cwd.zh.md index ae732a3e4d..86058437a1 100644 --- a/.agents/notes/implemented/architecture/2026-07-02-fs-per-session-cwd.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-02-fs-per-session-cwd.zh.md @@ -26,7 +26,7 @@ ACP(Agent Client Protocol)桥接层为每个会话提供独立的工作区 ### 为何由调用方(而非提供方)提供 cwd -提供方 seam 不得依赖 `dsh-agent`/`dsh-session`——它是一个文本存储后端,沙箱或远程实现同样满足该接口,而这些实现没有「agent 会话」的概念。工具已经接收了 `ToolExecution`(`exec`),其中携带 agent,因此工具是将 `exec → cwd` 投影并向提供方传递一个纯字符串的正确位置。这遵循「包(package)边界处显式优于隐式」的约定:基准目录作为显式参数传入,提供方据此行动,而非让提供方越界去读取它不应知晓的会话。这也与 `dsh-tool-bash` 一一对应,使两个面向模型的文件操作接口以相同方式解析路径。 +提供方 seam 不得依赖 `dsh-agent`/`dsh-session`——它是一个文本存储后端,沙箱或远程实现同样满足该接口,而这些实现没有「agent 会话」的概念。工具已经接收了 `ToolExecution`(`exec`),其中携带 agent,因此工具是将 `exec → cwd` 投影并向提供方传递一个纯字符串的正确位置。这遵循「包边界处显式优于隐式」的约定:基准目录作为显式参数传入,提供方据此行动,而非让提供方越界去读取它不应知晓的会话。这也与 `dsh-tool-bash` 一一对应,使两个面向模型的文件操作接口以相同方式解析路径。 默认值只存在于一个地方——提供方的 `config.cwd`。`sessionCwd` 在没有会话时返回 `undefined` 而非 `process.cwd()`,因此工具永远不会自行制造一个提供方本应自行选择的基准目录。 diff --git a/.agents/notes/implemented/architecture/2026-07-02-tool-render-intent-union.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-02-tool-render-intent-union.i18n.yaml index 6d8498e21c..d467684e40 100644 --- a/.agents/notes/implemented/architecture/2026-07-02-tool-render-intent-union.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-02-tool-render-intent-union.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-02-tool-render-intent-union.md -2026-07-02-tool-render-intent-union.md: d82141f519bff66df000f1316093aacd38b8e42b -2026-07-02-tool-render-intent-union.zh.md: 71fe81ba8f87cb707512cf7880126c006321c799 +2026-07-02-tool-render-intent-union.md: 67607b2848305439513503d7e03ad5e2a2e4020a +2026-07-02-tool-render-intent-union.zh.md: f69442cc1cf226a5dd949fc3890029a69a639953 diff --git a/.agents/notes/implemented/architecture/2026-07-02-tool-render-intent-union.md b/.agents/notes/implemented/architecture/2026-07-02-tool-render-intent-union.md index d82141f519..67607b2848 100644 --- a/.agents/notes/implemented/architecture/2026-07-02-tool-render-intent-union.md +++ b/.agents/notes/implemented/architecture/2026-07-02-tool-render-intent-union.md @@ -14,7 +14,7 @@ A tool declares how its calls render in a UI (an editor's tool-call card) throug - Which combinations are *valid* is unwritten: a `terminal` call that also sets `content` means "description above the card"; a generic call that sets `terminal` is meaningless but representable. The type permits nonsense. - There is no way to express the one file-tool affordance an editor most wants — a **diff card** (`{path, oldText, newText}`, which Zed renders as an inline diff / new-file preview). `ToolCallPresentation.content` is the *LLM* `ContentBlock[]` vocabulary (text/image), so a tool literally cannot ask for a diff. -The existing `FIXME(tool-presentation)` in `packages/core/tools/src/index.ts` named the fix: "redesign the type so a tool declares its render INTENT once (e.g. a tagged union over card kinds) rather than a bag of optional fields the bridge stitches together." An earlier rejected collapse-tool-owned-presentation proposal deferred it explicitly: rich rendering "should return later as a tagged render-intent union after there are at least two real tools and two real consumers to validate the vocabulary." That bar is met by multiple producer families plus the TUI and host/client-runtime (Web) consumers. +An earlier rejected collapse-tool-owned-presentation proposal deferred rich rendering until it could "return later as a tagged render-intent union after there are at least two real tools and two real consumers to validate the vocabulary." That bar is met by multiple producer families plus the TUI and host/client-runtime (Web) consumers. ## Decision diff --git a/.agents/notes/implemented/architecture/2026-07-02-tool-render-intent-union.zh.md b/.agents/notes/implemented/architecture/2026-07-02-tool-render-intent-union.zh.md index 71fe81ba8f..f69442cc1c 100644 --- a/.agents/notes/implemented/architecture/2026-07-02-tool-render-intent-union.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-02-tool-render-intent-union.zh.md @@ -4,7 +4,7 @@ Status: implemented [English](2026-07-02-tool-render-intent-union.md) | 中文 -> render-intent 联合类型对 UI 传输层仍然有效;其 ACP 映射已被 [ACP 作为仅面向自动化的协议](../simplification/2026-07-23-acp-automation-only-protocol.md)取代。 +> render-intent 联合类型对 UI 传输层仍然有效;其 ACP(Agent Client Protocol)映射已被 [ACP 作为仅面向自动化的协议](../simplification/2026-07-23-acp-automation-only-protocol.md)取代。 ## 问题 @@ -14,7 +14,7 @@ Status: implemented - 哪些组合是*合法的*没有文档说明:一个设置了 `content` 的 `terminal` 调用意味着「卡片上方的描述」;一个设置了 `terminal` 的 generic 调用毫无意义但类型上可表达。类型允许无意义的状态存在。 - 无法表达编辑器最需要的文件工具能力:**diff 卡片**(`{path, oldText, newText}`,Zed 将其渲染为内联 diff / 新文件预览)。`ToolCallPresentation.content` 使用的是 *LLM(大语言模型)* 的 `ContentBlock[]` 词汇(text/image),工具根本无法请求 diff 展示。 -`packages/core/tools/src/index.ts` 中已有的 `FIXME(tool-presentation)` 指出了修复方向:「重新设计类型,让工具一次性声明其渲染意图(例如按卡片种类的带标签联合类型),而非一堆由 bridge 拼接的可选字段。」一个早先被否决的折叠工具自有呈现提案明确推迟了此事:富渲染「应当在至少有两个真实工具和两个真实消费方验证词汇之后,以带标签 render-intent 联合类型的形式回归。」该条件已由多个生产者族,加上 TUI 与宿主/客户端运行时(Web)这些消费方满足。 +一个早先被否决的折叠工具自有呈现提案把富渲染推迟到它能够「在至少有两个真实工具和两个真实消费方验证词汇之后,以带标签 render-intent 联合类型的形式回归」之时。该条件已由多个生产者族,加上 TUI 与宿主/客户端运行时(Web)这些消费方满足。 ## 决策 @@ -36,7 +36,7 @@ interface GenericResultView { card: 'generic'; title?: string; content?: Content interface TerminalResultView { card: 'terminal'; title?: string; output?: string; exitCode?: number; signal?: string } ``` -`card` 在每个变体上都是**必填**的——真正的判别式,而非可选默认值。bridge 执行 `switch (view.card) { case 'generic': … case 'terminal': … case 'diff': … default: assertNever(view) }`。该联合类型是**封闭的**(遵循 [switch 穷举约定](../../../../AGENTS.md)):第四种渲染意图(表格、图表)无论如何需要新的 bridge 代码来渲染,因此一个由插件添加但被 bridge 静默丢弃的变体,比编译错误更糟糕。新增变体会在 bridge 的 switch 处中断编译——这正是我们想要的信号。 +`card` 在每个变体上都是**必填**的——真正的判别字段,而非可选默认值。bridge 执行 `switch (view.card) { case 'generic': … case 'terminal': … case 'diff': … default: assertNever(view) }`。该联合类型是**封闭的**(遵循 [switch 穷举约定](../../../../AGENTS.md)):第四种渲染意图(表格、图表)无论如何需要新的 bridge 代码来渲染,因此一个由插件添加但被 bridge 静默丢弃的变体,比编译错误更糟糕。新增变体会在 bridge 的 switch 处中断编译——这正是我们想要的信号。 ### 为什么带标签联合类型优于字段集合 @@ -47,7 +47,7 @@ interface TerminalResultView { card: 'terminal'; title?: string; output?: string ### 生产者映射 - `dsh-tool-fs` read → `generic`(`kind:'read'`,附带一个 follow-along `location`);write → `diff`(`oldText:null`);edit → `diff`(`oldText:old_string || null`,`newText:new_string ?? ''`)。这与 `claude-agent-acp` 的 `toolInfoFromToolUse` 中 Read/Write/Edit 各分支逐字段对应。 -- `dsh-tool-bash` foreground → `terminal` 调用 + `terminal` 结果;`run_in_background` → `generic`。通用 `task_*` 控制工具拥有各自的 generic 卡片。 +- `dsh-tool-bash` 前台运行 → `terminal` 调用 + `terminal` 结果;`run_in_background` → `generic`。通用 `task_*` 控制工具拥有各自的 generic 卡片。 - `dsh-tool-todo` → `generic`。 ### 终端回退的归属 @@ -63,7 +63,7 @@ terminal 意图只用于展示。harness 仍通过自身的 bash 服务执行命 ## 曾考虑的替代方案 - **完全删除工具自有的展示**:即本 Agent Note 所取代的那个被否决的 collapse 提案;其自身的结论正是推迟到两个真实工具和两个真实消费方存在后再做此联合类型,该条件现已满足。 -- **让 UI 执行 terminal 意图**:否决。这样会绕过 harness 的 bash 策略与归属契约,并把命令执行分裂到不同后端。terminal 卡片描述的是 harness 拥有的执行,绝不授权客户端侧执行。 +- **让 UI 执行 terminal 意图**:否决。这样会绕过 harness 的 bash 策略与归属约定,并把命令执行分裂到不同后端。terminal 卡片描述的是 harness 拥有的执行,绝不授权客户端侧执行。 - **可合并扩展的联合类型**(`ContentBlockMap` 模式):否决。新的渲染意图无论如何需要新的 bridge 代码来渲染,因此一个被 bridge 静默丢弃的插件添加变体,比封闭联合类型在 bridge 的 `assertNever` switch 处引发的编译错误更糟糕。 - **保留可选字段集合**:即「问题」一节所剖析的现状:无效状态可表达、字段交互无文档、且完全无法请求 diff 卡片。 @@ -78,5 +78,5 @@ terminal 意图只用于展示。harness 仍通过自身的 bash 服务执行命 ## 相关 - 取代早先被否决的折叠工具自有呈现提案(已否决——「等两个真实工具和两个真实消费方,然后做带标签 render-intent 联合类型」)中的推迟决定。该条件现已满足;本 Agent Note 即为那个联合类型。 -- 被[结果时已应用 hunk 差异](../../archived/architecture/2026-07-02-result-time-applied-hunk-diffs.md)(已归档)扩展:后者添加了一个持久化的 `meta` 通道,使 write/edit 在结果时输出 `DiffResultView`(应用后的变更:带上下文行的 contextual hunk / 每个 `replace_all` 位点一个,或创建时的整文件 diff)——值/呈现拆分与持久化的 `presentationMeta` 通道现由[规范工具输出契约](2026-07-20-canonical-tool-output-contract.md)拥有。 +- 被[结果时已应用 hunk 差异](../../archived/architecture/2026-07-02-result-time-applied-hunk-diffs.md)(已归档)扩展:后者添加了一个持久化的 `meta` 通道,使 write/edit 在结果时输出 `DiffResultView`(应用后的变更:带上下文行的 contextual hunk / 每个 `replace_all` 位点一个,或创建时的整文件 diff)——值/呈现拆分与持久化的 `presentationMeta` 通道现由[规范工具输出约定](2026-07-20-canonical-tool-output-contract.md)拥有。 - 将 `ToolTerminal` 折入当前 UI 传输层使用的带标签 `terminal` 视图。 diff --git a/.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.i18n.yaml index 1f232965a5..f80e5c3c77 100644 --- a/.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.i18n.yaml @@ -1,6 +1,6 @@ # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: -# pnpm run verify-translation-pairing --write -2026-07-05-prompt-variables-and-tool-guidance-ownership.md: 94f5fa409e7b539b48750d12576c7a342a30c9ba -2026-07-05-prompt-variables-and-tool-guidance-ownership.zh.md: f1379e143a94a3ae3a07b3120c6f0b9fc8561fe9 +# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md +2026-07-05-prompt-variables-and-tool-guidance-ownership.md: a3b5021daf323971308760bde4f97651db8edbda +2026-07-05-prompt-variables-and-tool-guidance-ownership.zh.md: 0b84f188e6637d8b1b42ed2e6df3cd7e4061d75d diff --git a/.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md b/.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md index 94f5fa409e..a3b5021daf 100644 --- a/.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md +++ b/.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md @@ -10,7 +10,7 @@ The assembled system prompt had four defects, all of one family: facts the harne **The model could not know its own name.** `AgentOptions.model` drives every request, but no prompt text carried it — and nothing COULD carry it: sections in `dsh-system-prompt` were context-global while the model name is per-agent, and `assemble()` took no per-agent input at all. -**Tool guidance was hand-written prose in leaf YAML.** The bash/subagent/todo_write usage guidance lived in the coding-agent and ACP persona strings — two drifting copies (the ACP one was already abridged) — while `dsh-tool-fs` and `dsh-tool-web` owned their guidance as `ctx.systemPrompt.section()` contributions. Loading or dropping a tool plugin meant editing every deployment's persona by hand; both YAMLs carried a `FIXME(config-comments)` apologizing for a symptom of the split, and the old terminal welcome banner hand-enumerated the tool set too. +**Tool guidance was hand-written prose in leaf YAML.** The bash/subagent/todo_write usage guidance lived in the coding-agent and ACP persona strings — two drifting copies (the ACP one was already abridged) — while `dsh-tool-fs` and `dsh-tool-web` owned their guidance as `ctx.systemPrompt.section()` contributions. Loading or dropping a tool plugin meant editing every deployment's persona by hand, and the old terminal welcome banner hand-enumerated the tool set too. **The persona rendered after tool guidance.** The loop string-joined `agent.options.systemPrompt` AFTER the assembled sections, so the model read "Use the read tool…" before "You are a coding agent" — backwards relative to the identity-first convention (Claude Code, Codex) and a second composition path besides the section pipeline. diff --git a/.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.zh.md b/.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.zh.md index f1379e143a..0b84f188e6 100644 --- a/.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.zh.md @@ -10,7 +10,7 @@ Status: implemented **模型无法知道自己的名字。** `AgentOptions.model` 驱动每个请求,但没有任何提示词文本携带它——也不可能携带:`dsh-system-prompt` 中的 section 是上下文全局的,而模型名称是 per-agent 的,`assemble()` 根本不接受任何 per-agent 输入。 -**工具指导是 leaf YAML 中的手写行文。** bash/subagent/todo_write 的使用指导存放在 coding-agent 和 ACP persona 字符串里——两份漂移的副本(ACP 那份已经被删减)——而 `dsh-tool-fs` 和 `dsh-tool-web` 则通过 `ctx.systemPrompt.section()` 贡献各自的指导。加载或卸载一个工具插件意味着手动编辑每个部署的 persona;两份 YAML 都带着一条 `FIXME(config-comments)` 为这种分裂的症状道歉,旧终端欢迎横幅也手动枚举了工具集。 +**工具指导是 leaf YAML 中的手写行文。** bash/subagent/todo_write 的使用指导存放在 coding-agent 和 ACP persona 字符串里——两份漂移的副本(ACP 那份已经被删减)——而 `dsh-tool-fs` 和 `dsh-tool-web` 则通过 `ctx.systemPrompt.section()` 贡献各自的指导。加载或卸载一个工具插件意味着手动编辑每个部署的 persona,旧终端欢迎横幅也手动枚举了工具集。 **Persona 渲染在工具指导之后。** agent loop(智能体循环)将 `agent.options.systemPrompt` 字符串拼接在已组装的 section 之后,于是模型先读到「Use the read tool…」再读到「You are a coding agent」——与 identity-first 约定(Claude Code、Codex)相反,且是 section 流水线之外的第二条组合路径。 @@ -18,7 +18,7 @@ Status: implemented ## 决策 -**一条原则:提示词中的每个事实恰好有一个归属方。** 模型名称和工作区是配置/会话事实 → harness 将它们暴露为变量,persona 引用它们。每个工具的语义和何时使用 → 工具的 `description`。description 无法承载的跨调用习惯 → 工具包(package)的提示词 section。harness 来源标识 → 静态的 `harness:identity` section。部署角色与行为 → 部署的 persona。 +**一条原则:提示词中的每个事实恰好有一个归属方。** 模型名称和工作区是配置/会话事实 → harness 将它们暴露为变量,persona 引用它们。每个工具的语义和何时使用 → 工具的 `description`。description 无法承载的跨调用习惯 → 包的提示词 section。harness 来源标识 → 静态的 `harness:identity` section。部署角色与行为 → 部署的 persona。 ### 组装上下文 @@ -26,21 +26,21 @@ Status: implemented ### 提示词变量 -插件通过 `ctx.systemPrompt.variable(name, provider)` 注册 `{{name}}` 值。组装过程将它们解析到 waterfall 可见的变量映射中。渲染阶段拒绝以下情况:引用了未知的 own-property、已注册的提供方返回 `undefined`、格式错误的完整引用、以及仍包含闭合 `}}` 的不平衡引用;孤立的未匹配 `{{` 保留为行文,替换后的值不会被重新扫描。注册阶段拒绝无效或重复的变量名,section 名称也必须唯一。 +插件通过 `ctx.systemPrompt.variable(name, provider)` 注册 `{{name}}` 值。组装过程将它们解析到 waterfall 可见的变量映射中。渲染阶段拒绝以下情况:引用未知的自有属性、已注册的提供方返回 `undefined`、格式错误的完整引用、以及仍包含闭合 `}}` 的不平衡引用;孤立的未匹配 `{{` 保留为行文,替换后的值不会被重新扫描。注册阶段拒绝无效或重复的变量名,section 名称也必须唯一。 `dsh-agent-loop` 注册两个内置变量,均为上下文 agent 的纯投影:`model`(= `options.model`)和 `cwd`(= `session.header.cwd`)。示例 persona 写 `powered by the {{model}} model`——模型名称只在 `model:` 配置键中声明一次。`{{cwd}}` 仅在 ACP 示例中演示:每个 ACP 会话携带客户端的 cwd,而配置预创建的 stdio agent 没有 cwd(在那里声称 `{{cwd}}` 的 persona 会导致该轮次失败——这是有意为之)。变量留在 loop 插件上(不同于下面的 section):它们是本循环驱动的 agent 的运行时事实,替换循环自行提供自己的变量。 ### Persona 作为 order-0 section -`dsh-system-prompt` 拥有 order 为 `-100` 的 `harness:identity` 和 order 为 0 的配置 `deployment:persona`,因此两者在循环被替换时仍然存活。提示词渲染只有一条路径 `renderPrompt(assembly)`,已路由请求 header 因此会记录准确的提示词,稍后由 `ctx.tokenMeter` 为压缩压力回放。agent 作用域的 `deployment:persona` 遮蔽全局默认值,允许 subagent 提供方在发布前安装 persona。约定的 order 区间为:identity `-100`、persona `0`、工具指导 `100–199`。 +`dsh-system-prompt` 拥有 order 为 `-100` 的 `harness:identity` 和 order 为 0 的配置 `deployment:persona`,因此两者在循环被替换时仍然存活。提示词渲染只有一条路径 `renderPrompt(assembly)`,已路由请求 header 因此会记录准确的提示词,稍后由 `ctx.tokenMeter` 为压缩(compaction)压力回放。agent 作用域的 `deployment:persona` 遮蔽全局默认值,允许 subagent 提供方在发布前安装 persona。约定的 order 区间为:identity `-100`、persona `0`、工具指导 `100–199`。 ### 工具指导归属 -每个工具的语义和选择指导放在工具 description 中。提示词 section 只承载跨调用习惯,例如检查 bash 退出标记或优先使用文件系统工具而非 shell 命令。`todo_write` 和 subagent 工具不需要 section,因为它们的 description 包含完整契约。部署 persona 只包含角色和行为。 +每个工具的语义和选择指导放在工具 description 中。提示词 section 只承载跨调用习惯,例如检查 bash 退出标记或优先使用文件系统工具而非 shell 命令。`todo_write` 和 subagent 工具不需要 section,因为它们的 description 包含完整约定。部署 persona 只包含角色和行为。 ### Subagent 对话历史描述符 -`SubagentProvider.inheritsParentContext` 描述的是对话种子,而非作用域、服务、工具或权限。spawn 和 ACP 将其设为 `false`;fork 设为 `true`。`dsh-tool-subagent` 根据该标志派生工具和提示词参数的描述,包括 fork 继承已完成轮次但不继承进行中轮次这一点。提供方生命周期事件使该措辞与响应式提供方注册保持同步;其设计动机见[提供方生命周期事件 Agent Note](2026-07-05-subagent-provider-lifecycle-events.md)。 +`SubagentProvider.inheritsParentContext` 描述的是对话历史初始化,而非作用域、服务、工具或权限。spawn 和 ACP 将其设为 `false`;fork 设为 `true`。`dsh-tool-subagent` 根据该标志派生工具描述和提示词参数描述,包括 fork 继承已完成轮次但不继承进行中轮次这一点。提供方生命周期事件使该措辞与响应式提供方注册保持同步;其设计动机见[提供方生命周期事件 Agent Note](2026-07-05-subagent-provider-lifecycle-events.md)。 ## 曾考虑的替代方案 @@ -49,7 +49,7 @@ Status: implemented - **在每个 persona 中手写模型名称**:与上方一行的 `model:` 键重复,配置修改后静默失实;正是本 Agent Note 要治愈的病症。 - **宽松插值(未知引用保留原样或替换为空)**:一个拼写错误 `{{modle}}`(或一个空洞)会被发送给模型,直到 transcript(文本记录)审查时才会被发现。 - **在配置中为每个 subagent 实例编写措辞**:面向模型的行文回到每个部署 × 实例中,重蹈 P2 病症。**根据提供方名称选择措辞**:`providerName` 本身是配置,重命名提供方后会静默获得错误的措辞。 -- **在 `apply` 时解析提供方(加载顺序要求)** 与 **仅用 section 承载 subagent 措辞(在 assemble 时惰性解析)**:提供方生命周期事件的替代方案;两者均在[提供方生命周期事件 Agent Note](2026-07-05-subagent-provider-lifecycle-events.md)中被否决。 +- **在 `apply` 时解析提供方(加载顺序要求)**与**仅用 section 承载 subagent 措辞(在 assemble 时惰性解析)**:提供方生命周期事件的替代方案;两者均在[提供方生命周期事件 Agent Note](2026-07-05-subagent-provider-lifecycle-events.md)中被否决。 ## 不在范围内 @@ -68,5 +68,5 @@ Status: implemented - 组装后的提示词中每个事实现在恰好有一个归属方,leaf YAML 中手工维护的工具行文已消除:加载或卸载一个工具插件不再需要编辑任何部署的 persona。 - `{{model}}` 在组装时反映 `AgentOptions.model`。如果一个插件在 `agent/request` waterfall 中切换模型,提示词对该步骤的声明就会过时;如果一个插件在那里提供模型(options.model 未设置——循环文档中记载的回退路径),变量在渲染时无值,包含 `{{model}}` 的 persona 会在 waterfall 运行前失败。两者的补救方式相同,就是归属规则本身:拥有延迟绑定模型事实的插件在 `system-prompt/assemble` waterfall 上提前声明它(`assembly.variables['model'] = …`)——一个归属方,两处声明;一个循环测试端到端固定了 supply 路径。已接受。 - 当一个已绑定的提供方不存在时(尚未激活、已卸载、HMR(热模块替换)重载中),subagent 工具不存在,该窗口内的模型请求中不会包含它。这是诚实的状态——替代方案是注册一个 description 或执行都不可信的工具。 -- 严格性意味着 persona 可能在渲染时导致轮次失败(例如在无 cwd 的会话上使用 `{{cwd}}`)。失败是受控的——该轮次以 `error` 结束,循环存活——且这是一个我们希望大声暴露的撰写错误。 +- 严格性意味着 persona 可能在渲染时导致轮次失败(例如在无 cwd 的会话上使用 `{{cwd}}`)。失败是受控的——该轮次以 `error` 结束,循环存活——且这是一个我们希望明确暴露的撰写错误。 - 目前没有在提示词行文中转义字面 `{{name}}` 的语法;如果真实提示词确实需要,再行添加。 diff --git a/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.i18n.yaml index f9c309c39f..1b5962f672 100644 --- a/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.i18n.yaml @@ -1,6 +1,6 @@ # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: -# pnpm run verify-translation-pairing --write -2026-07-05-reconstructable-requests.md: 153d37a2faf2265134d5ff9e88f0bbfa275328e0 -2026-07-05-reconstructable-requests.zh.md: caf51c3065e416fd11aebc1c1d4dc2ee248e2e5c +# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.md +2026-07-05-reconstructable-requests.md: ebca9b99cad791159302da9c2bbce9f4df147aab +2026-07-05-reconstructable-requests.zh.md: e7ed83bbc553e86d53d88e442b0fd8992973c9e7 diff --git a/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.md b/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.md index 153d37a2fa..ebca9b99ca 100644 --- a/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.md +++ b/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.md @@ -22,11 +22,11 @@ Prefix-cache stability is corollary #1, not the headline: an append-only log pro **Messages.** `Session.deriveMessages()` is cached: each surface entry is projected exactly once, when first seen, through the public per-event function `deriveEventMessage(event)`; a surface rewrite (a compaction `replace` — `SurfaceManager.replaceGeneration`) rebuilds. Callers get a fresh array per call over shared, deep-frozen messages: mutating logged history through a projection is unrepresentable (it throws), replacing the old clone-per-call isolation. External reconstructors fold the same public function over a log prefix, so no two paths can disagree. -`EpochHeader` records the request's non-history state: call config, rendered system prompt, tool schemas, and session prefix, with empty values canonicalized to absence. `request/header` always writes a full snapshot: the first loop instance uses reason `initial`, later instances use `resume`, and an in-instance change uses `change`. `foldRequestHeader` selects the latest snapshot. Legacy `request/header-delta` events and the removed `fallback` reason are rejected when appended or loaded. +`EpochHeader` records the request's non-history state: call config, rendered system prompt, and tool schemas, with empty values canonicalized to absence. `request/header` always writes a full snapshot: the first loop instance uses reason `initial`, later instances use `resume`, and an in-instance change uses `change`. `foldRequestHeader` selects the latest snapshot. Legacy `request/header-delta` events and the removed `fallback` reason are rejected when appended or loaded. -Each step rebuilds prompt assembly. On the instance's first step, `agent/session-prefix` extends a frozen empty seed with request-only opener messages; the result is frozen and cached for that loop instance before the generic `agent/pre-step` checkpoint and boundary snapshot. The first call config starts from explicit `AgentOptions`, preserving fork overrides and resume reconfiguration; later calls start from the folded header. `agent/request` may replace only that frozen config seed, while model-visible content enters through logged channels. The loop records the owed header event—the prefix's only durable home—builds `GenerateOptions` from prefix, snapshot, and header, and deep-freezes it while leaving `AbortSignal` live. Per-instance state is only the cached prefix and whether its anchoring snapshot has been written. +Each proposed step first claims its inbox batch and runs `agent/pre-step`. Rejection opens no step; enter opens `step/start` and records the final message batch as `user/message` events. The step then assembles the system prompt and tools, while `agent/request` may replace only the frozen call-config seed. The loop records the owed full header snapshot, builds `GenerateOptions` from derived messages and that header, and deep-freezes it while leaving `AbortSignal` live. The first call config starts from explicit `AgentOptions`, preserving fork overrides and resume reconfiguration; later calls start from the folded header. -**`step/start` is the reconstruction boundary.** A step derives messages from events before that sequence. Injection after the snapshot joins the next request, and reentrant appends are rejected during event publication. `agent/pre-step(agent, turn, step, signal)` remains the generic seam for content needed by the current request. Header reconstruction selects the step's `request/header`, or carries the prior snapshot when no new header is written. +**The open step is the reconstruction boundary.** Its entered `user/message` batch and any newly written `request/header` precede request dispatch. Injection after the atomic claim joins a later request, while a listener that must affect this request returns messages through `agent/pre-step`. Header reconstruction selects the step's `request/header`, or carries the prior snapshot when no new header is written. **Enforcement.** The `dsh-agent-loop/invariant` companion registers with `ctx.invariants` and, when selected, independently rebuilds each loop request through a fresh `Session`, so the live cache cannot vouch for itself, then compares messages and folded header fields at `llm/stream`. The loop records the exact frozen request through `markAgentLoopRequest()` in `dsh-llm`; the process-local identity lets the companion and other request observers recognize conversation work, while direct one-shots remain excluded regardless of their frozen shape or session id. Correctness depends on sequence-bounded reconstruction rather than listener order. A with-key e2e requires positive cache-read tokens after the first request; per-step usage is the production signal, and a header change or compaction appears as a cache-read drop on the next step. @@ -47,10 +47,9 @@ Like MiniCode, the conversation advances append-only and resets only when model- ## Consequences - A request that is not explained by the log cannot be constructed by accident — not by the loop, not by a listener; mutating a built request throws; every header change is a durable, diffable log event. -- Choosing between the advisory channels is a change-frequency decision, and the design makes the stable one structural: an `agent/session-prefix` contribution is composed once per loop instance and reused verbatim, so it extends the cacheable prefix at zero marginal cost and CANNOT bust the provider cache mid-session; content that changes mid-session flows through the append-only history channels — `agent.inject()` and tool/prompt-submit `additionalContexts` — each a durable `context/message` paid once and prefix-cached thereafter, at the price of accumulating in history and the log. Route session-frozen openers to the prefix and change notices to the history channels; a per-step request-only tail slot was deliberately dropped (no consumer, and a durable append covers every current update pattern). +- Model-visible context uses logged message channels. `agent.inject()` and tool `additionalContexts` enter the inbox for a later claim, while `agent/pre-step` returns context that must settle with the current claimed batch. Each entered value is a durable sourced `user/message`, paid once and prefix-cached thereafter at the price of accumulating in history until compaction. - What still costs full price at the provider is inherent and logged: compaction (its `compact/*` events and replacement entry), a real prompt, tool, or config change (`request/header` with reason `change`), or a process boundary with drift (a differing `resume` snapshot). The provider's own reasoning-content exclusion is managed server-side. -- The `step/start`-listener behavior change (above) is the one observable semantics change for plugins; `agent/pre-step` is the current-request seam. +- `agent/pre-step` is the current-request message seam; direct inbox mutation is the eventual later-request seam. - Tool-result trimming (planned) needs no new mechanism: a logged single-entry surface replace (`start === end`) carrying a trimmed `tool/result` under the same `callId` — compaction-family, replay-correct, cache-bust batched by the same pressure logic. - Session logs grow one `request/header` snapshot per loop instance plus snapshots on real changes. This is larger than a delta codec but small beside chunk-heavy logs and retains one replay representation. `SESSION_FORMAT_VERSION` stays `0`; legacy delta events are rejected rather than migrated. - Snapshot expected outputs changed once (every transcript gains its header events); the fs-writing fixtures are stored in the normalized authored form with cwd-relative tool arguments, because replay only round-trips cwd-independent argument paths. -- FIXME(call-config-shape): revisit `LlmCallConfig`'s exact field set — which fields are genuinely epoch-level for cache purposes (`model` certainly; the sampling scalars sit there out of caution), and where provider-specific extras (reasoning options, extra body params) belong when an adapter needs them. diff --git a/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.zh.md b/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.zh.md index caf51c3065..e7ed83bbc5 100644 --- a/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.zh.md @@ -1,4 +1,4 @@ -# Agent Note: 每个 LLM(大语言模型)请求都可从会话日志重建 +# Agent Note: 每个 LLM 请求都可从会话日志重建 Status: implemented @@ -22,11 +22,11 @@ Status: implemented **消息。** `Session.deriveMessages()` 带缓存:每个 surface 条目在首次出现时通过公开的逐事件函数 `deriveEventMessage(event)` 精确投影一次;surface 重写(压缩的 `replace`,即 `SurfaceManager.replaceGeneration`)触发重建。调用方每次获得一个新数组,底层是共享的深度冻结消息:通过投影变异已记录的历史是不可表达的(会抛异常),取代了旧的逐次调用克隆隔离。外部重建器对日志前缀折叠同一个公开函数,因此不可能有两条路径产生分歧。 -`EpochHeader` 记录请求的非历史状态:调用配置、渲染后的系统提示词、工具 schema 和会话前缀,空值规范化为缺失。`request/header` 始终写入完整快照:首个循环实例使用 reason `initial`,后续实例使用 `resume`,实例内变更使用 `change`。`foldRequestHeader` 选择最新快照。旧的 `request/header-delta` 事件和已移除的 `fallback` reason 在追加或加载时都会被拒绝。 +`EpochHeader` 记录请求的非历史状态:调用配置、渲染后的系统提示词和工具 schema,空值规范化为缺失。`request/header` 始终写入完整快照:首个循环实例使用 reason `initial`,后续实例使用 `resume`,实例内变更使用 `change`。`foldRequestHeader` 选择最新快照。旧的 `request/header-delta` 事件和已移除的 `fallback` reason 在追加或加载时都会被拒绝。 -每个步骤重建提示词组装。在实例的首个步骤中,`agent/session-prefix` 以一个冻结的空种子为基础,用仅限请求的开场消息进行扩展;结果在通用 `agent/pre-step` 检查点与边界快照之前被冻结并缓存于该循环实例。首次调用配置从显式的 `AgentOptions` 出发,保留 fork 覆盖和恢复重配置;后续调用从折叠后的 header 出发。`agent/request` 只能替换那个冻结的配置种子,模型可见内容通过已记录的通道进入。循环记录欠下的 header 事件(前缀唯一的持久归宿),从前缀、快照和 header 构建 `GenerateOptions`,对其深度冻结但保持 `AbortSignal` 活跃。每实例状态仅有缓存的前缀和锚定快照是否已写入。 +每个拟议步骤先领取其 inbox 批次,再运行 `agent/pre-step`。reject 不打开步骤;enter 打开 `step/start`,并把最终消息批次记录为 `user/message` 事件。随后步骤组装系统提示词与工具,`agent/request` 只能替换冻结的调用配置种子。循环记录所需的完整 header 快照,从派生消息与该 header 构建 `GenerateOptions`,对其深度冻结但保持 `AbortSignal` 活跃。首次调用配置从显式的 `AgentOptions` 出发,保留 fork 覆盖和恢复重配置;后续调用从折叠后的 header 出发。 -**`step/start` 是重建边界。** 一个步骤从该序列之前的事件推导消息。快照之后的注入加入下一次请求,事件发布期间的重入追加被拒绝。`agent/pre-step(agent, turn, step, signal)` 仍是当前请求所需内容的通用 seam。header 重建选择该步骤的 `request/header`,或在无新 header 写入时沿用前一个快照。 +**已打开步骤是重建边界。** 进入步骤的 `user/message` 批次与任何新写入的 `request/header` 都位于请求分派之前。原子领取后发生的注入加入后续请求;必须影响本次请求的监听器则通过 `agent/pre-step` 返回消息。header 重建选择该步骤的 `request/header`,或在无新 header 写入时沿用前一个快照。 **强制执行。** `dsh-agent-loop/invariant` 配套插件向 `ctx.invariants` 注册,并在被选用时通过一个全新的 `Session` 独立重建每个循环请求,使活跃缓存无法为自身背书,然后在 `llm/stream` 处比较消息和折叠后的 header 字段。循环通过 `dsh-llm` 的 `markAgentLoopRequest()` 记录精确的冻结请求;这一进程内标识让配套插件和其他请求观察者识别对话工作,而直接的一次性调用无论其冻结形状或会话 id 如何都保持排除。正确性依赖于序列有界的重建,而非监听器顺序。带密钥的 e2e 要求首次请求之后有正值的 cache-read token;逐步骤用量是生产信号,header 变更或压缩表现为下一步骤的 cache-read 下降。 @@ -47,10 +47,9 @@ Status: implemented ## 后果 - 一个日志无法解释的请求不可能被意外构造——无论是循环还是监听器;变异已构建的请求会抛异常;每个 header 变更都是持久的、可 diff 的日志事件。 -- 在建议性通道之间做选择是变更频率的决策,而本设计使稳定的那个在结构上成为默认:`agent/session-prefix` 的贡献在每个循环实例中只组合一次并逐字复用,因此以零边际成本扩展可缓存前缀,且不可能在会话中途击穿提供方缓存;会话中途变化的内容通过仅追加的历史通道流入——`agent.inject()` 以及工具/prompt-submit 的 `additionalContexts`——每条都是持久的 `context/message`,付出一次代价后即被前缀缓存,代价是在历史和日志中累积。将会话冻结的开场内容路由到前缀,将变更通知路由到历史通道;逐步骤的仅限请求尾部槽位被有意放弃(无消费方,且持久追加覆盖了当前所有更新模式)。 -- 在提供方处仍需全价计算的内容是固有的且已记录的:压缩(其 `compact/*` 事件和替换条目)、真正的提示词、工具或配置变更(reason 为 `change` 的 `request/header`),或带漂移的进程边界(不同的 `resume` 快照)。提供方自身的 reasoning-content 排除由服务端管理。 -- `step/start` 监听器行为变更(见上文)是对插件唯一可观察的语义变更;`agent/pre-step` 是当前请求的 seam。 -- 工具结果裁剪(计划中)无需新机制:一个已记录的单条目 surface replace(`start === end`),携带同一 `callId` 下裁剪后的 `tool/result`——属压缩家族,回放正确,缓存击穿由相同的压力逻辑批量处理。 +- 模型可见上下文使用已记录消息通道。`agent.inject()` 与工具 `additionalContexts` 进入 inbox,等待后续领取;必须与当前已领取批次一起结算的上下文由 `agent/pre-step` 返回。每个进入步骤的值都是带来源的持久 `user/message`,只付出一次代价,此后即被前缀缓存,代价是会在历史中累积直至压缩。 +- 在提供方处仍需全价计算的内容是固有的且已记录的:压缩(其 `compact/*` 事件和替换条目)、真正的提示词、工具或配置变更(reason 为 `change` 的 `request/header`),或带漂移的进程边界(不同的 `resume` 快照)。提供方自身对思考内容的排除由服务端管理。 +- `agent/pre-step` 是当前请求的消息 seam;直接修改 inbox 则是最终进入后续请求的 seam。 +- 工具结果裁剪(计划中)无需新机制:一个已记录的单条目 surface replace(`start === end`),携带同一 `callId` 下裁剪后的 `tool/result`——属压缩家族,回放正确,缓存失效由相同的压力逻辑批量处理。 - 会话日志每个循环实例增长一个 `request/header` 快照,并在真正变更时增加快照。它比 delta 编解码器更大,但相对分片密集型日志仍然很小,并只保留一种回放表示。`SESSION_FORMAT_VERSION` 保持 `0`;旧的 delta 事件被拒绝而非迁移。 - 快照预期输出变更一次(每个 transcript(文本记录)增加其 header 事件);写入文件系统的 fixture(测试前置数据)以规范化的撰写形式存储,工具参数使用 cwd 相对路径,因为回放只对 cwd 无关的参数路径做往返。 -- FIXME(call-config-shape):重新审视 `LlmCallConfig` 的确切字段集——哪些字段对缓存而言真正属于 epoch 级别(`model` 毫无疑问;采样标量出于谨慎放在那里),以及当适配器需要时,提供方特定的额外项(reasoning 选项、额外 body 参数)应归属何处。 diff --git a/.agents/notes/implemented/architecture/2026-07-05-subagent-provider-lifecycle-events.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-05-subagent-provider-lifecycle-events.i18n.yaml index 516dd4edcb..336d9669ed 100644 --- a/.agents/notes/implemented/architecture/2026-07-05-subagent-provider-lifecycle-events.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-05-subagent-provider-lifecycle-events.i18n.yaml @@ -1,6 +1,6 @@ # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: -# pnpm run verify-translation-pairing --write -2026-07-05-subagent-provider-lifecycle-events.md: afd45027e8b56cbf1d17e6dec749d8602c81124d -2026-07-05-subagent-provider-lifecycle-events.zh.md: 58d439936a3f2cc51d8190cbebe8e68cdb14c855 +# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-05-subagent-provider-lifecycle-events.md +2026-07-05-subagent-provider-lifecycle-events.md: 503c0d638785e3a4944c8903b8d7d469c68b1881 +2026-07-05-subagent-provider-lifecycle-events.zh.md: e7d1d8c398a6d77efb2dbccc365e0040f38f2d33 diff --git a/.agents/notes/implemented/architecture/2026-07-05-subagent-provider-lifecycle-events.md b/.agents/notes/implemented/architecture/2026-07-05-subagent-provider-lifecycle-events.md index afd45027e8..503c0d6387 100644 --- a/.agents/notes/implemented/architecture/2026-07-05-subagent-provider-lifecycle-events.md +++ b/.agents/notes/implemented/architecture/2026-07-05-subagent-provider-lifecycle-events.md @@ -31,6 +31,6 @@ The events also complete the seam's vocabulary: `ctx.subagents` is a named regis ## Consequences - Consumers deriving state from a named provider react to `subagent/provider-added`/`-removed` instead of reading the registry at `apply` time; `dsh-tool-subagent` is the reference implementation. -- **Addition fails loud; removal is contained per listener.** An addition listener may unwind registration. Removal runs during disposal, so one throwing listener is logged without starving later mirrors or disrupting teardown. `start()` still resolves the provider by name for every run, preventing stale tools from calling a removed backend. See the [events catalog](../../../../docs/cordis-catalog/events.md) and [producer/consumer map](../../../../docs/event-producer-consumer.md). +- **Addition fails loud; removal is contained per listener.** An addition listener may unwind registration. Removal runs during disposal, so one throwing listener is logged without starving later mirrors or disrupting teardown. `start()` still resolves the provider by name for every run, preventing stale tools from calling a removed backend. See the [events catalog](../../../../docs/subsystems/subagent.md#cordis-surface) and [producer/consumer map](../../../../docs/event-producer-consumer.md). - **A window where the tool is absent.** Between backend disposal and re-registration (an HMR reload), the model sees no subagent tool. This is the honest state — the alternative is a tool that dispatches into nothing — and the tool registry's `tools/change` emit keeps prompt assembly current. - **Two waiting fibers sharing a `toolName` is an invalid config caught late.** If two loads of `dsh-tool-subagent` name different providers but the same `toolName`, both wait, and whichever provider arrives first registers; the second registration throws only when ITS provider arrives. `TODO(subagent-dup-toolname)` in the plugin records this blast radius; the tool registry's duplicate-name rejection remains the backstop. diff --git a/.agents/notes/implemented/architecture/2026-07-05-subagent-provider-lifecycle-events.zh.md b/.agents/notes/implemented/architecture/2026-07-05-subagent-provider-lifecycle-events.zh.md index 58d439936a..e7d1d8c398 100644 --- a/.agents/notes/implemented/architecture/2026-07-05-subagent-provider-lifecycle-events.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-05-subagent-provider-lifecycle-events.zh.md @@ -6,7 +6,7 @@ Status: implemented ## 问题 -[提示词变量 Agent Note](2026-07-05-prompt-variables-and-tool-guidance-ownership.md) 让 `dsh-tool-subagent` 从其提供方派生面向模型的措辞:`SubagentProvider.inheritsParentContext`(spawn/ACP 为 `false`,fork 为 `true`)同时驱动工具描述和 `prompt` 参数描述,使 fork 工具不再在上下文继承问题上对模型撒谎。这一修复引入了跨 fiber 的数据依赖:工具描述在工具注册时固定(这是有意为之——描述是 tool-choice 引导所在之处),但提供方在自己的插件 fiber 上到达,时机不确定。 +[提示词变量 Agent Note](2026-07-05-prompt-variables-and-tool-guidance-ownership.md) 让 `dsh-tool-subagent` 从其提供方派生面向模型的措辞:`SubagentProvider.inheritsParentContext`(spawn 和 ACP(Agent Client Protocol)为 `false`,fork 为 `true`)同时驱动工具描述和 `prompt` 参数描述,使 fork 工具不再在上下文继承问题上对模型撒谎。这一修复引入了跨 fiber 的数据依赖:工具描述在工具注册时固定(这是有意为之——描述是 tool-choice 引导所在之处),但提供方在自己的插件 fiber 上到达,时机不确定。 如果在工具插件的 `apply` 时刻解析提供方,就会产生一个隐式的加载顺序要求(「在 cordis.yml 中把后端列在工具前面」)。这个要求不成立,因为 Cordis Loader 并发启动同级条目,且 `Entry.init()` 不会等待激活完成:延迟到达的后端即使列在前面,也可能让工具 fiber 失败。Loader 不提供同级顺序保证——「异步状态不是同步状态」(见[防御性模式](../../../../docs/defensive-patterns.md))。 @@ -31,6 +31,6 @@ Status: implemented ## 后果 - 从命名提供方派生状态的消费方响应 `subagent/provider-added`/`-removed` 事件,而非在 `apply` 时读取注册表;`dsh-tool-subagent` 是参考实现。 -- **添加时大声失败;移除时按监听器隔离。** 添加监听器可以回滚注册。移除在 disposal 期间运行,因此单个监听器抛异常只会被记录日志,不会饿死后续镜像或干扰拆解流程。`start()` 仍在每次运行时按名称解析提供方,防止陈旧工具调用已移除的后端。见[事件目录](../../../../docs/cordis-catalog/events.md)与[生产者/消费方映射](../../../../docs/event-producer-consumer.md)。 -- **工具不存在的窗口期。** 在后端 disposal 与重新注册之间(HMR 重载期间),模型看不到 subagent 工具。这是诚实的状态——替代方案是一个向空处分发的工具——工具注册表的 `tools/change` 事件发出会保持提示词组装的时效性。 -- **两个等待中的 fiber 共享同一 `toolName` 是无效配置,被延迟捕获。** 如果两个 `dsh-tool-subagent` 加载实例命名了不同的提供方但相同的 `toolName`,两者都会等待,先到达的提供方先注册;第二次注册仅在其提供方到达时才抛异常。插件中的 `TODO(subagent-dup-toolname)` 记录了这一影响范围;工具注册表的重名拒绝机制仍是最终防线。 +- **添加时大声失败;移除时按监听器隔离。** 添加监听器可以回滚注册。移除在 disposal 期间运行,因此单个监听器抛异常只会被记录日志,不会饿死后续镜像或干扰拆解流程。`start()` 仍在每次运行时按名称解析提供方,防止陈旧工具调用已移除的后端。见[事件目录](../../../../docs/subsystems/subagent.md#cordis-surface)与[生产者/消费方映射](../../../../docs/event-producer-consumer.md)。 +- **工具不存在的窗口期。** 在后端 disposal 与重新注册之间(HMR 重载期间),模型看不到 subagent 工具。这是诚实的状态——替代方案是一个向空处分发的工具——工具注册表发出的 `tools/change` 事件会使提示词组装保持最新状态。 +- **两个等待中的 fiber 共享同一 `toolName` 是无效配置,被延迟捕获。** 如果两个 `dsh-tool-subagent` 加载实例分别指定了不同的提供方但相同的 `toolName`,两者都会等待,先到达的提供方先注册;第二次注册仅在其提供方到达时才抛异常。插件中的 `TODO(subagent-dup-toolname)` 记录了这一影响范围;工具注册表的重名拒绝机制仍是最终防线。 diff --git a/.agents/notes/implemented/architecture/2026-07-05-windows-jsonl-durable-publish.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-05-windows-jsonl-durable-publish.i18n.yaml index 4322906bb9..951017ba47 100644 --- a/.agents/notes/implemented/architecture/2026-07-05-windows-jsonl-durable-publish.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-05-windows-jsonl-durable-publish.i18n.yaml @@ -1,6 +1,6 @@ # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: -# pnpm run verify-translation-pairing --write +# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-05-windows-jsonl-durable-publish.md 2026-07-05-windows-jsonl-durable-publish.md: 38c4adc7a4f85d45e53e70fcac84073ab4e50775 -2026-07-05-windows-jsonl-durable-publish.zh.md: 8dc77a0ab1b9273cf3f6ecb26916c7861ee81ec4 +2026-07-05-windows-jsonl-durable-publish.zh.md: 205460bcd374bd351cfdf541eb4041c09461229d diff --git a/.agents/notes/implemented/architecture/2026-07-05-windows-jsonl-durable-publish.zh.md b/.agents/notes/implemented/architecture/2026-07-05-windows-jsonl-durable-publish.zh.md index 8dc77a0ab1..205460bcd3 100644 --- a/.agents/notes/implemented/architecture/2026-07-05-windows-jsonl-durable-publish.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-05-windows-jsonl-durable-publish.zh.md @@ -6,9 +6,9 @@ Status: implemented ## 问题 -`dsh-session-persistence-jsonl` 在首次追加时延迟发布会话日志。POSIX 协议会写入临时文件,对其执行 fsync,将其链接至最终名称,对父目录执行 fsync,然后移除临时链接。对父目录执行 fsync 是持久性契约的一部分:命名空间变更后发生崩溃时,已经提交的最终名称不能丢失,否则调用方会误以为会话日志已经物化。 +`dsh-session-persistence-jsonl` 在首次追加时延迟发布会话日志。POSIX 协议会写入临时文件,对其执行 fsync,将其链接至最终名称,对父目录执行 fsync,然后移除临时链接。对父目录执行 fsync 是持久性约定的一部分:命名空间变更后发生崩溃时,已经提交的最终名称不能丢失,否则调用方会误以为会话日志已经物化。 -Windows 具备原子命名空间操作,但 Node 没有暴露与 POSIX 等价的父目录 fsync 契约。如果把 Windows 目录同步失败视为成功,就会在无提示的情况下削弱持久化后端。因此,Windows 路径需要采用不同的发布原语,而不是在 POSIX 的 `syncDir` 辅助函数中添加条件分支。 +Windows 具备原子命名空间操作,但 Node 没有暴露与 POSIX 等价的父目录 fsync 约定。如果把 Windows 目录同步失败视为成功,就会在无提示的情况下削弱持久化后端。因此,Windows 路径需要采用不同的发布原语,而不是在 POSIX 的 `syncDir` 辅助函数中添加条件分支。 ## 决策 @@ -16,7 +16,7 @@ JSONL 后端会在 `materialize()` 内部、任何命名空间变更之前分流 POSIX 保留现有协议:创建根目录、项目目录与会话目录,并对其父目录执行 fsync;写入临时文件并对其执行 fsync;使用 `link()` 发布,确保绝不覆盖已有的最终日志;对会话目录执行 fsync;最后移除多余的临时硬链接。 -Windows 通过持久的暂存发布来创建缺失目录:在固定的 `.dsh-mkdir-` 前缀下创建一个随机同级目录,其名称与目标基本名无关;随后使用 `MoveFileExW(..., MOVEFILE_WRITE_THROUGH)` 将其发布为最终目录名称,且不使用 `MOVEFILE_REPLACE_EXISTING` 或 `MOVEFILE_COPY_ALLOWED`。文件物化先写入临时日志并对其执行 fsync,再以同一个启用写穿透的 `MoveFileExW` 调用将临时文件发布到最终路径,并且同样不允许替换。`koffi` 是覆盖这组 API 所需的最小 Win32 桥接层;`pnpm-workspace.yaml` 允许执行它的安装脚本,因为该包(package)会分发原生 loader 和预构建的平台模块。 +Windows 通过持久的暂存发布来创建缺失目录:创建一个以固定的 `.dsh-mkdir-` 为前缀的随机同级目录,其名称与目标基本名无关;随后使用 `MoveFileExW(..., MOVEFILE_WRITE_THROUGH)` 将其发布为最终目录名称,且不使用 `MOVEFILE_REPLACE_EXISTING` 或 `MOVEFILE_COPY_ALLOWED`。文件物化先写入临时日志并对其执行 fsync,再以同一个启用写穿透的 `MoveFileExW` 调用将临时文件发布到最终路径,并且同样不允许替换。`koffi` 是覆盖这组 API 所需的最小 Win32 桥接层;`pnpm-workspace.yaml` 允许执行它的安装脚本,因为该包会分发原生 loader 和预构建的平台模块。 ## 考虑过的替代方案 @@ -28,8 +28,8 @@ Windows 通过持久的暂存发布来创建缺失目录:在固定的 `.dsh-mk ## 影响 -该后端在各平台上维持同一项外部契约:首次追加要么把完整日志发布到最终名称,要么失败且不覆盖已有日志。平台分流只是实现细节;`SessionPersistence` API 和 JSONL 逻辑记录格式均不改变。后续的 [Zstandard 编码决策](2026-07-19-zstandard-jsonl-session-logs.md)会先作用于不透明字节,然后才由任一平台执行发布。 +该后端在各平台上维持同一项外部约定:首次追加要么把完整日志发布到最终名称,要么失败且不覆盖已有日志。平台分流只是实现细节;`SessionPersistence` API 和 JSONL 逻辑记录格式均不改变。后续的 [Zstandard 编码决策](2026-07-19-zstandard-jsonl-session-logs.md)会先作用于不透明字节,然后才由任一平台执行发布。 -Windows 测试会在原生 Windows 上执行真实的 Win32 发布路径。断电行为属于 API 契约属性,单元测试无法证明;可测试的不变量包括:Windows 物化不会调用目录 fsync、最终路径冲突会失败、达到最大长度的目标路径组件仍可物化、临时日志在发布前已经执行 fsync,并且生成的日志可以正常加载。 +Windows 测试会在原生 Windows 上执行真实的 Win32 发布路径。断电行为属于 API 约定属性,单元测试无法证明;可测试的不变量包括:Windows 物化不会调用目录 fsync、最终路径冲突会失败、达到最大长度的目标路径组件仍可物化、临时日志在发布前已经执行 fsync,并且生成的日志可以正常加载。 两个平台的追加和修复仍使用普通文件句柄 fsync。追加失败后,系统会关闭仅追加句柄,以读写模式重新打开日志,将文件截断到追加前的大小,并对回滚结果执行 fsync,因为 Windows 不允许在仅追加句柄上调用 `ftruncate`。 diff --git a/.agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.i18n.yaml index 471cf9f92d..24a047b540 100644 --- a/.agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.i18n.yaml @@ -1,6 +1,6 @@ # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: -# pnpm run verify-translation-pairing --write +# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.md 2026-07-06-timeout-deadline-library.md: 63463a76a65743436d4e78479800c19e257a42de -2026-07-06-timeout-deadline-library.zh.md: c3d3cdf1c63813fc24c10727e42d326142f3f4de +2026-07-06-timeout-deadline-library.zh.md: c47e6d4e6ed0bec368fca8857e5bd4d7229b6b0e diff --git a/.agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.zh.md b/.agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.zh.md index c3d3cdf1c6..c47e6d4e6e 100644 --- a/.agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.zh.md @@ -77,7 +77,7 @@ export function timeoutOf(x: AbortSignal | { reason?: unknown }, code?: string): | 关注点 | 负责方 | |---|---| -| 校验请求提示并钳位默认值/最大值 | `dsh-timeout`(`clampTimeout`):纯算术加共享的正有限请求契约 | +| 校验请求提示并钳位默认值/最大值 | `dsh-timeout`(`clampTimeout`):纯算术加共享的正有限请求约定 | | 启动一次性定时器、到期中止、携带 reason、与上游取消融合 | `dsh-timeout`(`deadline`) | | 仅围绕未结算的迭代器 demand 启动和重启 | `dsh-timeout`(`idleWatchdog`) | | 清除定时器 | `dsh-timeout`(任一原语的 `[Symbol.dispose]`) | @@ -90,9 +90,9 @@ export function timeoutOf(x: AbortSignal | { reason?: unknown }, code?: string): ### 各能力如何消费该库 -- **web_fetch**:工具层保持校验并转发;提供方手写的 controller + `setTimeout` + 手动监听器 + `finally` + `signal.reason` 恢复被替换为提供方自有的 `deadline`/`timeoutOf`。已预先中止的上游信号仍然立即抛出 `WEB_ABORTED`;否则 `fetch` 使用融合后的 `d.signal` 运行,`translateAbortOrNetwork` 根据信号分类抛出的错误(`timeoutOf` → `WEB_FETCH_TIMEOUT`,否则已中止 → `WEB_ABORTED`,否则网络错误 → `WEB_PROVIDER_ERROR`)。公开的错误码契约不变,`TimeoutReason` 永远不会作为公开错误跨越 web seam。 +- **web_fetch**:工具层保持校验并转发;提供方手写的 controller + `setTimeout` + 手动监听器 + `finally` + `signal.reason` 恢复被替换为提供方自有的 `deadline`/`timeoutOf`。已预先中止的上游信号仍然立即抛出 `WEB_ABORTED`;否则 `fetch` 使用融合后的 `d.signal` 运行,`translateAbortOrNetwork` 根据信号分类抛出的错误(`timeoutOf` → `WEB_FETCH_TIMEOUT`,否则已中止 → `WEB_ABORTED`,否则网络错误 → `WEB_PROVIDER_ERROR`)。公开的错误码约定不变,`TimeoutReason` 永远不会作为公开错误跨越 web seam。 - **bash**:`resolve()` 将请求钳位为显式规格。前台 `run()` 创建 deadline 并将其信号传给进程执行,后者既有的 abort 监听器执行进程组 kill。执行器将首个 abort 分类为超时或取消。后台启动保持无超时,仅转发上游取消。 -- **LLM 适配器**:`dsh-llm-deepseek` 和 `dsh-llm-pi-ai` 用 `idleWatchdog` 包装实际的传输迭代。配置的五分钟间隔只覆盖尚未结算的提供方 demand,不包括下游消费方在分片之间花费的时间。稳定信号在整个调用期间传给 `fetch` 或 SDK,因此超时会关闭底层请求并映射为 `TIMEOUT`,而更早的调用方中止映射为 `ABORTED`。 +- **LLM(大语言模型)适配器**:`dsh-llm-deepseek` 和 `dsh-llm-pi-ai` 用 `idleWatchdog` 包装实际的传输迭代。配置的五分钟间隔只覆盖尚未结算的提供方 demand,不包括下游消费方在分片之间花费的时间。稳定信号在整个调用期间传给 `fetch` 或 SDK,因此超时会关闭底层请求并映射为 `TIMEOUT`,而更早的调用方中止映射为 `ABORTED`。 ## 后果 @@ -100,16 +100,16 @@ export function timeoutOf(x: AbortSignal | { reason?: unknown }, code?: string): - `SpawnSpec.timeoutMs` 和 `SpawnOutcome.timedOut`/`aborted` 被移除,而非作为始终为零/始终为 false 的残余保留:由于 `runBash` 不再拥有定时器且执行器负责分类,这些字段无处被读取。这是与字面提案形状(向 `runBash` 传入 `timeoutMs: 0`)的唯一偏差;一个始终为 0 且无处读取的字段在逐文件覆盖率门禁下属于死代码。 - web_fetch 去除了其定制的 controller/timer/listener/reason-recovery;分类器现在基于 deadline 信号(`timeoutOf` + `aborted`)而非抛出错误的形状来判断,这在请求阶段的 reject-with-reason 和读取阶段的裸 `AbortError` 两种情况下都是健壮的。 - `AbortSignal.any` 和 `using`/`Symbol.dispose` 在此首次进入本仓库(Node ≥ 24 基线,已满足)。 -- 模型流现在共享一个可重启的定时器契约,不会把滑动的空闲间隔变成总调用截止时间,也不会计入消费方思考时间。该原语仍然只做通知;适配器测试证明其传输观察到稳定信号并终止。 +- 模型流现在共享一个可重启的定时器约定,不会把滑动的空闲间隔变成总调用截止时间,也不会计入消费方思考时间。该原语仍然只做通知;适配器测试证明其传输观察到稳定信号并终止。 -以下内容不在本次范围内,列出以标明边界:`web_search` 可以在其工具 schema/快照覆盖率规划就绪后获得可选的面向模型的 `timeout_ms`;未来基于 ripgrep 的文件系统发现工具可以在存在后消费同样的提供方自有 deadline 形状;`tools/execute` waterfall(瀑布式事件)中间件可以通过驱动 `exec.signal` 为每次工具调用设置默认 deadline——那将是一个*消费*本库的插件,仍然只做通知,硬终止仍是各能力自己的事。 +以下内容不在本次范围内,列出以标明边界:`web_search` 可以在其工具 schema 和快照覆盖规划完成后获得可选的面向模型的 `timeout_ms`;未来基于 ripgrep 的文件系统发现工具可以在实现后消费同样的提供方自有 deadline 形状;`tools/execute` waterfall(瀑布式事件)中间件可以通过驱动 `exec.signal` 为每次工具调用设置默认 deadline——那将是一个*消费*本库的插件,仍然只做通知,硬终止仍是各能力自己的事。 ## 曾考虑的替代方案 **统一的超时*插件* / `ctx.timeout` 服务。** 基于微内核原则否决。一个能停止任何工具工作的服务必须理解每个能力的终止机制(进程组 SIGKILL、socket 拆除、系统调用边界检查),这正是架构所禁止的「内核知道太多」。Codex 的 `ExecExpiration` 被限定于 exec 族,正是因为它驱动的 kill(`killpg`)是进程族特有的;MCP 和模型流各自保有自己的。不存在一个连贯的中间层能为所有东西拥有终止权,因此共享部分只能是纯计时/分类那一半——一个库,而非服务。 -**每个工具各自实现超时,不共享代码(先前的现状,也是 Claude Code 的选择)。** 否决,因为它已经在产生分化和重复的正确性负担:web_fetch 手写了与未来网络/进程类工具各自需要重新推导的完全相同的 controller/reason 逻辑,而融合 + `signal.reason` 恢复正是容易出错的部分。Claude Code 容忍完全重复;本仓库有一个统一的共享 abort 通道(每次 `execute` 上的 `exec.signal`),使得一个小型共享原语严格更优,因此成本/收益不同。 +**每个工具各自实现超时,不共享代码(先前的现状,也是 Claude Code 的选择)。** 否决,因为它已经在产生分化和重复的正确性负担:web_fetch 手写了与未来网络/进程类工具各自需要重新推导的完全相同的 controller/reason 逻辑,而融合 + `signal.reason` 恢复正是容易出错的部分。Claude Code 容忍完全重复;本仓库有一个统一的共享 abort 通道(每次 `execute` 上的 `exec.signal`),使得采用一个小型共享原语明显更简洁,因此成本/收益不同。 **用 `withTimeout(promise, ms)` 包装器代替信号工厂。** 否决,因为让 promise 与定时器竞争只是在截止时间到达时 resolve *工具调用*的 promise,而不会停止底层工作——子进程或 fetch socket 会泄漏。分发信号并要求能力监听,才能强制一条真实的终止路径存在。这与「dispose 必须达到完全停稳,而非仅仅请求它」的防御性规则一致。 -**保留 bash 独立的超时和取消触发器。** 否决,因为一个 deadline 信号移除了定制定时器并标准化了分类。竞争的原因报告先到达的那个 abort,而既有的 SIGTERM→SIGKILL 终止路径保持不变。 +**保留 bash 独立的超时和取消触发器。** 否决,因为一个 deadline 信号移除了定制定时器并标准化了分类。发生竞争时,报告先到达的那个 abort 作为原因,而既有的 SIGTERM→SIGKILL 终止路径保持不变。 diff --git a/.agents/notes/implemented/architecture/2026-07-06-tool-result-retention-library.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-06-tool-result-retention-library.i18n.yaml index 6663606c3c..29c7c13813 100644 --- a/.agents/notes/implemented/architecture/2026-07-06-tool-result-retention-library.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-06-tool-result-retention-library.i18n.yaml @@ -1,6 +1,6 @@ # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: -# pnpm run verify-translation-pairing --write +# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-06-tool-result-retention-library.md 2026-07-06-tool-result-retention-library.md: 5e42660360e5a23b419c75b9c8006bec459bc322 -2026-07-06-tool-result-retention-library.zh.md: 6e824667f17b361efb57b173c44f489da2cab3b3 +2026-07-06-tool-result-retention-library.zh.md: 2a523e2eff36daf9100ac10bf5ae569eca30f830 diff --git a/.agents/notes/implemented/architecture/2026-07-06-tool-result-retention-library.zh.md b/.agents/notes/implemented/architecture/2026-07-06-tool-result-retention-library.zh.md index 6e824667f1..2a523e2eff 100644 --- a/.agents/notes/implemented/architecture/2026-07-06-tool-result-retention-library.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-06-tool-result-retention-library.zh.md @@ -12,7 +12,7 @@ Status: implemented ## 决策 -`@deepseek-ai/dsh-retention` 位于 `packages/util/` 下,与 `dsh-brand` 和 `dsh-timeout` 同级,负责有界的模型可见输出。它是一组纯类与函数构成的库,**不是** Cordis 服务或插件:不接收 `ctx`、不注册任何内容、不持有跨调用状态,也不发出事件。各工具包(package)需要限制输出时直接导入它。 +`@deepseek-ai/dsh-retention` 位于 `packages/util/` 下,与 `dsh-brand` 和 `dsh-timeout` 同级,负责有界的模型可见输出。它是一组纯类与函数构成的库,**不是** Cordis 服务或插件:不接收 `ctx`、不注册任何内容、不持有跨调用状态,也不发出事件。各工具包需要限制输出时直接导入它。 该库包含两个相互独立的 retainer: @@ -95,7 +95,7 @@ type TextRetentionStrategy = ### 工具映射 -`read` 被有意排除在 v1 保留库之外。它的 `read-render` 辅助函数拥有文件专用的分页契约:`offset`/`limit`、行号、`totalLines`、offset 越界错误、逐行预览截断,以及能够在窗口中途停止扫描的所选输出字节上限。这是行窗口渲染器,不是通用保留原语。它未来可以共享中性的提示辅助函数,但不应把已经选定的窗口再传入 `ItemRetainer`。 +`read` 被有意排除在 v1 保留库之外。它的 `read-render` 辅助函数拥有文件专用的分页约定:`offset`/`limit`、行号、`totalLines`、offset 越界错误、逐行预览截断,以及能够在窗口中途停止扫描的所选输出字节上限。这是行窗口渲染器,不是通用保留原语。它未来可以共享中性的提示辅助函数,但不应把已经选定的窗口再传入 `ItemRetainer`。 下文的 `FsGlobEntry` 与 `FlatGrepMatch` 是预期由发现工具使用的条目形态,不是现有保留库的导出。`FsGlobEntry` 是一个由后端派生的路径;`FlatGrepMatch` 是后端将保留匹配项按文件分组之前的一条未分组 grep 匹配。 @@ -138,7 +138,7 @@ const formatGrepNotice = (notice: RetentionNotice): string => **已交付内容。** `@deepseek-ai/dsh-retention` 导出 `ItemRetainer`、`TextRetainer`、结果类型(`RetainedItems`、`RetainedText`)、策略类型(`ItemRetentionStrategy`、`TextRetentionStrategy`)、`Omitted`、`PushDecision`、`RetentionNotice`,以及中性的提示辅助函数 `describeOmitted`/`formatRetentionNotice`,且不依赖 Cordis 或任何工具包。单元测试覆盖具有精确省略计数的条目头部保留、文本头部保留、文本尾部保留、首尾字节保留、零预算、UTF-8 边界处理(2、3、4 字节码位,以及每个裁切位置上的无效起始字节)和未知省略量的措辞。 -**已记录但尚未迁移的内容。** `glob`、`grep`、`bash`、`web_fetch` 与 `web_search` 的映射已记录在[包 README](../../../../packages/util/retention/README.md) 中,但本次改动并未把每个工具都迁移到该库;迁移工作刻意留作独立的后续任务。`read` 被明确记录为不在范围内:其 `read-render` 行窗口契约(`offset`/`limit`、`totalLines`、offset 范围错误、逐行预览截断,以及针对所选窗口的字节上限)不属于通用保留,而一个 `Omitted` 计数也无法同时表达行窗口两侧。 +**已记录但尚未迁移的内容。** `glob`、`grep`、`bash`、`web_fetch` 与 `web_search` 的映射已记录在[包 README](../../../../packages/util/retention/README.md) 中,但本次改动并未把每个工具都迁移到该库;迁移工作刻意留作独立的后续任务。`read` 被明确记录为不在范围内:其 `read-render` 行窗口约定(`offset`/`limit`、`totalLines`、offset 范围错误、逐行预览截断,以及针对所选窗口的字节上限)不属于通用保留,而一个 `Omitted` 计数也无法同时表达行窗口两侧。 **该库维持的边界。** `truncated` 表示 retainer 因预算省略了原本可用的内容,绝不表示上游不完整。工具专用状态,包括 `incomplete`、权限失败、提供方局部失败、跳过二进制文件、bash 落盘路径恢复和无效 UTF-8,均留在工具领域字段中、位于 retainer 之外。未来改动迁移某项工具时,该包的 README 与测试必须证明,除了有意改变的提示措辞外,模型可见的结果文本没有变化。 @@ -152,6 +152,6 @@ const formatGrepNotice = (notice: RetentionNotice): string => **把 `read` 窗口交给 `ItemRetainer`。** v1 不予采纳:`read` 是当前唯一的窗口消费方,其语义属于文件分页,而不是通用保留。一个 `Omitted` 计数无法表示行窗口两侧,而且 `read` 还携带 `totalLines`、offset 范围错误、逐行预览截断和针对所选输出的字节上限。让 `read-render` 由工具所有,可以避免共享库围绕一项特例膨胀。 -**让截断成为 `ToolExecutionResult` 的一部分。** 不予采纳:工具注册表将不得不理解工具专用的恢复指引、分组、行号、退出状态和提供方语义。保留是由工具的 Native renderer 使用的库;模型可见投影继续由工具所有,而[规范值](2026-07-20-canonical-tool-output-contract.md)可以保留完整的已采集结果。 +**让截断成为 `ToolExecutionResult` 的一部分。** 不予采纳:工具注册表将不得不理解工具专用的恢复指引、分组、行号、退出状态和提供方语义。保留是由工具的 Native renderer(原生渲染器)使用的库;模型可见投影继续由工具所有,而[规范值](2026-07-20-canonical-tool-output-contract.md)可以保留完整的已采集结果。 **在每个面向模型的工具 schema 中公开上限。** 不作为默认方案:Claude Code 的 grep 公开 `head_limit`/`offset`,但本 harness 会把常规预算保留为部署配置,除非模型确实需要控制分页。未来可以为具体工具增加类似 read 的续传字段;它不属于共享保留原语。 diff --git a/.agents/notes/implemented/architecture/2026-07-07-tool-call-timeout-policy.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-07-tool-call-timeout-policy.i18n.yaml index bd2426f377..6e7aa8291a 100644 --- a/.agents/notes/implemented/architecture/2026-07-07-tool-call-timeout-policy.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-07-tool-call-timeout-policy.i18n.yaml @@ -1,6 +1,6 @@ # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: -# pnpm run verify-translation-pairing --write -2026-07-07-tool-call-timeout-policy.md: 69fd1ee721de69621d3b57c10d960da0651b94dd -2026-07-07-tool-call-timeout-policy.zh.md: c0dc56127cb983bd515db424d0ca37da9d0e978a +# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-07-tool-call-timeout-policy.md +2026-07-07-tool-call-timeout-policy.md: b85a4d2d60ef60d9f75bd47d4d405aa55c132af6 +2026-07-07-tool-call-timeout-policy.zh.md: f6a85c13a66689c48b10f160890ce3825125aec1 diff --git a/.agents/notes/implemented/architecture/2026-07-07-tool-call-timeout-policy.md b/.agents/notes/implemented/architecture/2026-07-07-tool-call-timeout-policy.md index 69fd1ee721..b85a4d2d60 100644 --- a/.agents/notes/implemented/architecture/2026-07-07-tool-call-timeout-policy.md +++ b/.agents/notes/implemented/architecture/2026-07-07-tool-call-timeout-policy.md @@ -40,7 +40,7 @@ That the catch is the base `next` — not something outside the waterfall — is ### The `timeout-policy` plugin -The plugin is `@deepseek-ai/dsh-timeout-policy`, a zero-config function/namespace plugin (`name` / `inject` / `apply`) in the `packages/timeout/` group. The per-tool budget is DECLARED on the tool, not on this plugin: a `ToolDefinition` carries an optional `timeoutMs`, which the owning tool plugin sets from its own config. `dsh-tool-web`, for example, resolves `fetchTimeoutMs` / `searchTimeoutMs` (default 30000) onto the `web_fetch` / `web_search` definitions: +The plugin is `@deepseek-ai/dsh-timeout-policy`, a zero-config function/namespace plugin (`name` / `inject` / `apply`) in the `packages/guard/` group (originally its own `timeout/` group). The per-tool budget is DECLARED on the tool, not on this plugin: a `ToolDefinition` carries an optional `timeoutMs`, which the owning tool plugin sets from its own config. `dsh-tool-web`, for example, resolves `fetchTimeoutMs` / `searchTimeoutMs` (default 30000) onto the `web_fetch` / `web_search` definitions: ```yaml - id: timeout-policy @@ -89,7 +89,7 @@ A future model-facing grep/glob tool can be implemented on top of `ctx.bash` wit ## Alternatives considered -**Name the plugin `tool-timeout`.** The literal Agent Note name matched the `gen-tool-catalog` completeness guard's `packages/*/tool-*` glob, which requires every match to register a model-facing tool. This plugin registers none — it is a `tools/execute` wrapper — so a `tool-*` name would either fail `verify-tool-catalog` or force a misleading boot entry. The package is `@deepseek-ai/dsh-timeout-policy` in a new `packages/timeout/` group; the cordis.yml `id` can still be `timeout-policy`. +**Name the plugin `tool-timeout`.** The literal Agent Note name matched the `gen-tool-catalog` completeness guard's `packages/*/tool-*` glob, which requires every match to register a model-facing tool. This plugin registers none — it is a `tools/execute` wrapper — so a `tool-*` name would either fail `verify-tool-catalog` or force a misleading boot entry. The package is `@deepseek-ai/dsh-timeout-policy` in what was then a new `timeout/` group, since folded into `packages/guard/`; the cordis.yml `id` can still be `timeout-policy`. **Keep per-tool timeout handling only.** This was the shape for `bash` and `web_fetch`, and it matches Claude Code and Codex for shell commands. It loses for web-style tools because every new timeout-capable tool must choose validation, cap semantics, docs, snapshots, and classification. The plugin centralizes policy and classification while leaving each tool's schema focused on business input. diff --git a/.agents/notes/implemented/architecture/2026-07-07-tool-call-timeout-policy.zh.md b/.agents/notes/implemented/architecture/2026-07-07-tool-call-timeout-policy.zh.md index c0dc56127c..f6a85c13a6 100644 --- a/.agents/notes/implemented/architecture/2026-07-07-tool-call-timeout-policy.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-07-tool-call-timeout-policy.zh.md @@ -40,7 +40,7 @@ catch 是基础 `next`(而非 waterfall 之外的东西)这一点至关重 ### `timeout-policy` 插件 -该插件是 `@deepseek-ai/dsh-timeout-policy`,一个零配置的函数/命名空间插件(`name` / `inject` / `apply`),位于 `packages/timeout/` 组。每个工具的预算声明在工具自身,而非本插件:`ToolDefinition` 携带一个可选的 `timeoutMs`,由拥有该工具的插件从自身配置中设置。例如 `dsh-tool-web` 将 `fetchTimeoutMs` / `searchTimeoutMs`(默认 30000)解析到 `web_fetch` / `web_search` 的定义上: +该插件是 `@deepseek-ai/dsh-timeout-policy`,一个零配置的函数/命名空间插件(`name` / `inject` / `apply`),位于 `packages/guard/` 组。每个工具的预算声明在工具自身,而非本插件:`ToolDefinition` 携带一个可选的 `timeoutMs`,由拥有该工具的插件从自身配置中设置。例如 `dsh-tool-web` 将 `fetchTimeoutMs` / `searchTimeoutMs`(默认 30000)解析到 `web_fetch` / `web_search` 的定义上: ```yaml - id: timeout-policy @@ -52,7 +52,7 @@ catch 是基础 `next`(而非 waterfall 之外的东西)这一点至关重 searchTimeoutMs: 30000 ``` -超时放在工具定义上而非自由文本名称映射中,消除了拼错名称导致策略不生效的问题。`defineTool` 校验预算为正有限数。分发期间,执行器派生截止信号并将其赋给 `exec.signal`;注册表依据[工具取消契约](2026-07-19-cooperative-tool-cancellation.md),在执行工具体之前将该截止信号与调用方的原始信号融合。执行器随后恢复调用方信号,并将自身的超时转换为 `TOOL_TIMEOUT`;没有预算的工具原样通过。 +超时放在工具定义上而非自由文本名称映射中,消除了拼错名称导致策略不生效的问题。`defineTool` 校验预算为正有限数。分发期间,执行器派生截止信号并将其赋给 `exec.signal`;注册表依据[工具取消约定](2026-07-19-cooperative-tool-cancellation.md),在执行工具体之前将该截止信号与调用方的原始信号融合。执行器随后恢复调用方信号,并将自身的超时转换为 `TOOL_TIMEOUT`;没有预算的工具原样通过。 信号替换采用**就地修改 `exec.signal`** 的方式,而非向 `next()` 传递新对象。Cordis 的 waterfall `next()` 忽略传入的任何参数,并以共享的 payload 数组重新调用下游监听器(`vendor/cordis/src/events.ts`),因此修改共享对象是包装器向注册表提供截止信号的方式。注册表会在进入工具体前再次融合已捕获的调用方信号;插件则在 `finally` 中将 `exec.signal` 恢复为调用方的原始值,使 `tools/post-execute` 永远不会看到本插件的截止信号。 @@ -71,7 +71,7 @@ function toolTimeoutResult(timeoutMs: number): ToolExecutionResult { } ``` -这是一个协作式截止。它不会通过竞争工具 promise 来杀死任意工作;工具或其调用的能力必须遵循 `exec.signal` 并达到完全停稳。因此声明 `timeoutMs` 意味着「此工具与 `exec.signal` 协作」,插件 README 将此作为其契约。 +这是一个协作式截止。它不会通过竞争工具 promise 来杀死任意工作;工具或其调用的能力必须遵循 `exec.signal` 并达到完全停稳。因此声明 `timeoutMs` 意味着「此工具与 `exec.signal` 协作」,插件 README 将此作为其约定。 无需新的会话事件来保证可重建性:`TOOL_TIMEOUT` 是该调用的最终面向模型的 `tool/result`,因此现有会话日志已经记录了下一次模型请求所见的内容和结构化 `{ name, code }` 错误。 @@ -79,7 +79,7 @@ function toolTimeoutResult(timeoutMs: number): ToolExecutionResult { `web_fetch` 和 `web_search` 已迁移。`dsh-tool-web` 保留对其面向模型 schema 的所有权,这些 schema 不暴露超时旋钮:`web_fetch` 移除了 `timeout_ms` 参数以匹配参考 agent 的形状,`web_search` 保持仅查询。工具体不导入 `@deepseek-ai/dsh-timeout`;它们将 `exec.signal` 转发给 `ctx.web`。 -`dsh-web-fetch-local` 保留一个配置级别的 `timeoutMs` 作为大型资源兜底,服务于直接调用 `ctx.web.fetch()` 的调用方和配置错误的部署;它不拥有面向模型的超时。当 `TOOL_TIMEOUT` 信号先到达 fetch 提供方时,提供方作用域的分类将其视为上游 `WEB_ABORTED`,而外层 `tools/execute` 包装器将最终工具结果替换为 `TOOL_TIMEOUT`。一个已发布的 web 工具部署将提供方兜底配置为高于 `timeout-policy` 预算,使工具调用策略在模型调用中通常胜出。 +`dsh-web-fetch-local` 保留一个在提供方层面配置的 `timeoutMs`,作为较大的资源兜底值,服务于直接调用 `ctx.web.fetch()` 的调用方和配置错误的部署;它不拥有面向模型的超时。当 `TOOL_TIMEOUT` 信号先到达 fetch 提供方时,提供方作用域的分类将其视为上游 `WEB_ABORTED`,而外层 `tools/execute` 包装器将最终工具结果替换为 `TOOL_TIMEOUT`。一个已发布的 web 工具部署将提供方兜底配置为高于 `timeout-policy` 预算,使工具调用策略在模型调用中通常胜出。 `bash` 保持当前的后端超时路径。`dsh-tool-bash` 继续暴露 `timeoutMs` 和 `run_in_background`;`dsh-bash-local` 继续使用 `@deepseek-ai/dsh-timeout` 处理 `BASH_TIMEOUT`;钩子桥接继续调用 `runHook()` 并通过 `ctx.bash` 传递 `timeoutMs`。这保持了前台/后台/钩子行为的稳定。 @@ -89,7 +89,7 @@ function toolTimeoutResult(timeoutMs: number): ToolExecutionResult { ## 曾考虑的替代方案 -**将插件命名为 `tool-timeout`。** 字面的 Agent Note 名称匹配了 `gen-tool-catalog` 完整性守卫的 `packages/*/tool-*` glob,该 glob 要求每个匹配项注册一个面向模型的工具。本插件不注册任何工具——它是一个 `tools/execute` 包装器——因此 `tool-*` 名称要么导致 `verify-tool-catalog` 失败,要么强制产生一个误导性的启动条目。包(package)为 `@deepseek-ai/dsh-timeout-policy`,位于新的 `packages/timeout/` 组;cordis.yml 的 `id` 仍可为 `timeout-policy`。 +**将插件命名为 `tool-timeout`。** 字面的 Agent Note 名称匹配了 `gen-tool-catalog` 完整性守卫的 `packages/*/tool-*` glob,该 glob 要求每个匹配项注册一个面向模型的工具。本插件不注册任何工具——它是一个 `tools/execute` 包装器——因此 `tool-*` 名称要么导致 `verify-tool-catalog` 失败,要么强制产生一个误导性的启动条目。包为 `@deepseek-ai/dsh-timeout-policy`,位于新的 `packages/guard/` 组;cordis.yml 的 `id` 仍可为 `timeout-policy`。 **仅保留逐工具的超时处理。** 这是 `bash` 和 `web_fetch` 的既有形态,也与 Claude Code 和 Codex 对 shell 命令的做法一致。它对 web 类工具不利,因为每个新的支持超时的工具都必须自行选择校验方式、上限语义、文档、快照和分类。插件集中了策略和分类,让每个工具的 schema 专注于业务输入。 @@ -101,14 +101,14 @@ function toolTimeoutResult(timeoutMs: number): ToolExecutionResult { **让 `timeout-policy` 自行匹配工具参数。** 诸如「当 `bash.run_in_background` 为 true 时禁用超时」之类的规则引擎会让策略插件了解工具特定的参数语义。通过不将 bash 迁移到工具调用超时来规避此问题。 -**使用 `tools/pre-execute` 加 `tools/post-execute` 代替新的环绕 seam。** pre 监听器可以启动截止时间并修改 `exec.signal`;post 监听器可以分类并替换。这样做的问题是截止时间的生命周期会跨越两个独立的 waterfall:需要 call-id 映射、在每条 pre-deny/tool-throw/post-throw/dispose 路径上清理,以及与其他监听器的排序规则。`tools/pre-execute` 也是允许/拒绝门禁,而非执行包装器。`tools/execute` 给超时一个词法作用域:启动、委托、分类、释放。 +**使用 `tools/pre-execute` 加 `tools/post-execute` 代替新的环绕 seam。** pre 监听器可以启动截止时间并修改 `exec.signal`;post 监听器可以分类并替换。这样做的问题是截止时间的生命周期会跨越两个独立的 waterfall:需要 call-id 映射、在每条 pre-deny/tool-throw/post-throw/dispose(资源释放)路径上清理,以及与其他监听器的排序规则。`tools/pre-execute` 也是允许/拒绝门禁,而非执行包装器。`tools/execute` 给超时一个词法作用域:启动、委托、分类、释放。 **使用 `Promise.race` 对非协作工具强制超时。** 与超时库 Agent Note 相同的理由否决:它在底层进程、fetch 或提供方操作可能仍在运行时就将控制权返回给调用方。插件只发送信号;终止仍是实现方的责任。 ## 后果 -- `@deepseek-ai/dsh-tools` 在有意拆分 pre/post 工具钩子的拦截 seam 之后,获得了一个环绕分发的表面。其契约是狭窄的——包装注册表分发,而非替代 pre 门禁或 post 结果策略——且基础 `next()` 是带规范化的分发,因此包装器永远不会看到原始的工具抛出。 +- `@deepseek-ai/dsh-tools` 在有意拆分 pre/post 工具钩子的拦截 seam 之后,获得了一个环绕分发接口。其约定是狭窄的——包装注册表分发,而非替代 pre 门禁或 post 结果策略——且基础 `next()` 是带规范化的分发,因此包装器永远不会看到未经处理的工具异常。 - 多个 `tools/execute` 监听器按普通 Cordis waterfall 顺序组合:调用 `next()` 的监听器包装下游监听器加分发;不调用 `next()` 直接返回的监听器短路它们。一个同时组合超时与未来重试/沙箱/指标包装器的部署通过注册顺序选择语义(「超时覆盖整个重试」vs「超时覆盖每次尝试」)。 -- 按声明加入是一个有意的误配置风险:工具可以声明 `timeoutMs` 但不遵循 `exec.signal`,这样的工具在超时时不会停止。注册表会等待这一未达完全停稳的工具体,而不是竞速它;同时插件契约声明:声明预算意味着协作;web 工具在已转发信号的工具上验证了这一模式。 +- 按声明加入是一个有意的误配置风险:工具可以声明 `timeoutMs` 但不遵循 `exec.signal`,这样的工具在超时时不会停止。注册表会等待这个尚未完全停稳的工具体结束,而不是与它竞速;同时插件约定声明:声明预算意味着协作;web 工具在已转发信号的工具上验证了这一模式。 - 过渡期间 `bash` 和已迁移的 web 工具有意使用不同的超时路径:`TOOL_TIMEOUT` 是面向模型的工具调用预算,而 `BASH_TIMEOUT` 仍是 bash 和钩子使用的 bash 后端超时。 - 与字面提案的偏差,按 implemented-Agent Note 规则记录:插件包为 `@deepseek-ai/dsh-timeout-policy`(而非 `tool-timeout`);信号替换是在 `next()` 之前就地修改 `exec.signal`(而非 `next({ ...exec, signal })`,Cordis 会忽略后者);逐工具预算声明在 `ToolDefinition` 上(`timeoutMs`,由拥有该工具的插件从其配置中设置),而非在本插件配置中按工具名映射——因此执行器是零配置的,拼错工具名不可能发生。以上三点均在上文 `## Decision` 中描述。 diff --git a/.agents/notes/implemented/architecture/2026-07-08-agent-scope-contexts.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-08-agent-scope-contexts.i18n.yaml index cdee6ab259..8f9fb5e270 100644 --- a/.agents/notes/implemented/architecture/2026-07-08-agent-scope-contexts.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-08-agent-scope-contexts.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-08-agent-scope-contexts.md -2026-07-08-agent-scope-contexts.md: 5e09bdbcae1e57e6b65eb7d1720a6e7a7f758a9f -2026-07-08-agent-scope-contexts.zh.md: 4714045f28e0386a3a53b53437d063462e75a9f1 +2026-07-08-agent-scope-contexts.md: eb3f6f247bac1a1d81aa2644132c7b9cc04d602c +2026-07-08-agent-scope-contexts.zh.md: a6dcd421cb2e8a64cdbe6393253355ad8554303e diff --git a/.agents/notes/implemented/architecture/2026-07-08-agent-scope-contexts.md b/.agents/notes/implemented/architecture/2026-07-08-agent-scope-contexts.md index 5e09bdbcae..eb3f6f247b 100644 --- a/.agents/notes/implemented/architecture/2026-07-08-agent-scope-contexts.md +++ b/.agents/notes/implemented/architecture/2026-07-08-agent-scope-contexts.md @@ -104,7 +104,7 @@ An event about Agent A normally reaches unscoped listeners and A-scoped listener At the Cordis level, `Scoped` is an opaque routing receiver. It carries the filter used to choose listeners but is not the domain object. Event signatures therefore keep the real `Agent`, tool execution, approval request, or other subject as an explicit argument that listeners can inspect. -A listener registered with `{ global: true }` deliberately bypasses contextual audience filtering while its cleanup still follows the registering context. Registry-membership notifications remain unfiltered because they describe shared registry state rather than one agent's operation. The generated [event catalog](../../../../docs/cordis-catalog/events.md) is the exhaustive event reference. +A listener registered with `{ global: true }` deliberately bypasses contextual audience filtering while its cleanup still follows the registering context. Registry-membership notifications remain unfiltered because they describe shared registry state rather than one agent's operation. The exhaustive event reference is the set of generated `cordis-surface` regions across the [subsystem pages](../../../../docs/subsystems/core.md) — each event scope on its owning page (`agent/*` and `agent-loop/*` on core.md itself). ### Creation publishes last and disposal revokes last diff --git a/.agents/notes/implemented/architecture/2026-07-08-agent-scope-contexts.zh.md b/.agents/notes/implemented/architecture/2026-07-08-agent-scope-contexts.zh.md index 4714045f28..a6dcd421cb 100644 --- a/.agents/notes/implemented/architecture/2026-07-08-agent-scope-contexts.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-08-agent-scope-contexts.zh.md @@ -18,7 +18,7 @@ Status: implemented Cordis 是 SDK 底层的插件框架。Cordis **上下文**是插件用来访问服务和注册效果的对象,效果的清理跟随该上下文。[Cordis 入门](../../../../docs/cordis-primer.md)对该框架有更详细的说明。 -对大多数贡献者而言,完整契约是四条规则: +对大多数贡献者而言,完整约定是四条规则: | 问题 | 规则 | |---|---| @@ -56,7 +56,7 @@ flowchart LR | 普通插件上下文 | 每个符合条件的 agent 视图 | 注册插件 | | `agent.ctx` | 仅该 agent 的视图 | agent 作用域 | -工具、提示词段落与变量、工具限制、守卫以及作用域事件监听器都遵循此契约。命名的本地值通常对该 agent 遮蔽同名全局值;各所属服务文档会说明例外与合并行为。 +工具、提示词段落与变量、工具限制、守卫以及作用域事件监听器都遵循此约定。命名的本地值通常对该 agent 遮蔽同名全局值;各所属服务文档会说明例外与合并行为。 普通贡献者的模式是在 agent setup 期间注册完整的本地世界: @@ -88,7 +88,7 @@ await handle.dispose() ctx.tools.get('review_summary', handle.agent) // undefined: scope is gone ``` -setup 接收一个完整的受信 Cordis 上下文,因此可以组合普通插件和服务。其契约仅限组合:不支持通过 cast 或内部注册表调用来驱动或发布正在构建中的 agent。 +setup 接收一个完整的受信 Cordis 上下文,因此可以组合普通插件和服务。其约定仅限组合:不支持通过 cast 或内部注册表调用来驱动或发布正在构建中的 agent。 ### 操作选择视图 @@ -96,7 +96,7 @@ setup 接收一个完整的受信 Cordis 上下文,因此可以组合普通插 工具查找与执行接收其所服务的 agent。提示词组装接收正在构建请求的 agent 的组装上下文。事件分发接收其领域主体。这使共享服务实例可在多个 agent 间复用,同时让每个操作的视图保持显式。 -只有采纳了作用域契约的服务才会解析 agent 层。`agent.ctx` 不会自动改变任意 Cordis 服务调用的行为。 +只有采纳了作用域约定的服务才会解析 agent 层。`agent.ctx` 不会自动改变任意 Cordis 服务调用的行为。 ### 作用域事件将路由与事件数据分离 @@ -104,7 +104,7 @@ setup 接收一个完整的受信 Cordis 上下文,因此可以组合普通插 在 Cordis 层面,`Scoped` 是一个不透明的路由接收器。它携带用于选择监听器的过滤器,但本身不是领域对象。因此事件签名将真实的 `Agent`、工具执行、审批请求或其他主体作为显式参数保留,供监听器检查。 -以 `{ global: true }` 注册的监听器有意绕过上下文受众过滤,但其清理仍跟随注册上下文。注册表成员变更通知保持不过滤,因为它们描述的是共享注册表状态而非某个 agent 的操作。生成的[事件目录](../../../../docs/cordis-catalog/events.md)是详尽的事件参考。 +以 `{ global: true }` 注册的监听器有意绕过上下文受众过滤,但其清理仍跟随注册上下文。注册表成员变更通知保持不过滤,因为它们描述的是共享注册表状态而非某个 agent 的操作。详尽的事件参考是各[子系统页面](../../../../docs/subsystems/core.md)上生成的 `cordis-surface` 区块的集合——每个事件作用域在其所属页面上(`agent/*` 与 `agent-loop/*` 在 core.md 本页)。 ### 创建最后发布,dispose 最后撤销 diff --git a/.agents/notes/implemented/architecture/2026-07-08-tool-output-spill-files.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-08-tool-output-spill-files.i18n.yaml index c241ef4ece..dbac0c0688 100644 --- a/.agents/notes/implemented/architecture/2026-07-08-tool-output-spill-files.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-08-tool-output-spill-files.i18n.yaml @@ -1,6 +1,6 @@ # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: -# pnpm run verify-translation-pairing --write +# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-08-tool-output-spill-files.md 2026-07-08-tool-output-spill-files.md: 7c0ca90452645d251559be25108d12883210d00e -2026-07-08-tool-output-spill-files.zh.md: 917d710eb8650e2797287578edd1b0d62813bbd3 +2026-07-08-tool-output-spill-files.zh.md: 628023a9d12fec17d32749f9d17a3b701ca3a475 diff --git a/.agents/notes/implemented/architecture/2026-07-08-tool-output-spill-files.zh.md b/.agents/notes/implemented/architecture/2026-07-08-tool-output-spill-files.zh.md index 917d710eb8..628023a9d1 100644 --- a/.agents/notes/implemented/architecture/2026-07-08-tool-output-spill-files.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-08-tool-output-spill-files.zh.md @@ -8,15 +8,15 @@ Status: implemented 工具输出需要有界的模型可见预览,但部分超大结果仍可能在之后有用。抓取的页面正文或冗长的工具响应不应完整占用下一次模型请求,但模型应能使用现有文件读取工具,在之后查看经过格式化的完整结果。 -这项改动之前的行为并不一致。`dsh-bash-local` 已经会在内存尾部溢出时,把完整 stdout/stderr 流写入私有的临时落盘文件;普通文本工具结果则仍以内联形式返回,除非工具自行临时实现上限。[工具结果保留库](2026-07-06-tool-result-retention-library.md)负责预览机制,但不负责存储,也不负责把这些机制应用于最终工具结果的执行流水线策略。 +这项改动之前的行为并不一致。`dsh-bash-local` 已经会在内存尾部溢出时,把完整 stdout/stderr 流写入私有的临时落盘文件;普通文本工具结果则仍以内联形式返回,除非工具自行实现上限。[工具结果保留库](2026-07-06-tool-result-retention-library.md)负责预览机制,但不负责存储,也不负责把这些机制应用于最终工具结果的执行流水线策略。 -其形态与超时策略设计一致:工具作者声明规范值与 Native renderer,由策略插件在渲染后的内容上执行部署默认的上下文预算。工具仍可在提供方采集上限处提前落盘;由工具负责的展示落盘可以保留已完整采集的规范值,而只替换展示内容。[规范工具输出契约](2026-07-20-canonical-tool-output-contract.md)规定了这项区分。 +其形态与超时策略设计一致:工具作者声明规范值与 Native renderer(原生渲染器),由策略插件在渲染后的内容上执行部署默认的上下文预算。工具仍可在提供方采集上限处提前落盘;由工具负责的展示落盘可以保留已完整采集的规范值,而只替换展示内容。[规范工具输出约定](2026-07-20-canonical-tool-output-contract.md)规定了这项区分。 ## 决策 在新的 `packages/spill/` 分组下增加一层轻量落盘存储 seam 和一个默认落盘策略插件: -| 包(package) | 角色 | +| 包 | 角色 | |---|---| | `@deepseek-ai/dsh-spill` | 接口:`ctx.spillStore`、词汇类型,不包含存储实现。 | | `@deepseek-ai/dsh-spill-local` | 本地后端:在宿主文件系统中提供私有、会话作用域的文件存储。 | @@ -140,7 +140,7 @@ ctx.tools.register(defineTool({ 最终结果策略不能取代由工具负责的提前落盘。部分有用内容并不存在于最终 `ToolExecutionResult.content` 中: - `bash` 的最终输出已经是尾部内容加临时落盘路径;完整的 stdout/stderr 流位于执行器文件中。 -- `subagent` 的最终输出是子 agent(智能体)的最终回答,而不是子 agent 的执行轨迹。 +- `subagent` 的最终输出是 subagent 的最终回答,而不是 subagent 的执行轨迹。 - 未来的工具可能生成从未出现在最终 `ToolExecutionResult.content` 中的运行时产物。 这些场景可以在后续工作中直接使用 `ctx.spillStore`,不属于首个示例的范围。 @@ -164,7 +164,7 @@ ctx.tools.register(defineTool({ ## 测试 -- `dsh-spill` 单元测试锁定 seam 契约:注册为 `ctx.spillStore`、每个上下文只允许一种实现,并在 dispose(资源释放)时释放。 +- `dsh-spill` 单元测试锁定 seam 约定:注册为 `ctx.spillStore`、每个上下文只允许一种实现,并在 dispose(资源释放)时释放。 - `dsh-spill-local` 单元测试覆盖 `saveText`、`encodeSegment` 清理(分隔符/波浪号/完整路径段的点/空值)、会话哈希目录、仅所有者权限、每次保存生成不同路径、配置根目录/私有根目录,以及存储失败时的拒绝。 - `dsh-spill-policy` 单元测试通过 `ctx.tools.execute` 驱动真实工具:禁用模式下无操作、替换超大文本、小结果/非文本结果保持不变、跳过 `read`、尽力回退(保存失败/无后端/无所有者),以及下游组合(限制已替换结果、保留 `additionalContexts`)。 - `dsh-tool-web` 集成测试驱动 `web_fetch`,其实际执行路径经过 `ctx.tools.execute`,并使用真实的 `spill-local` 后端与策略;测试证明只有刻意加入的落盘提示会改变模型可见文本,而落盘文件保存完整的格式化结果。 @@ -174,7 +174,7 @@ ctx.tools.register(defineTool({ 默认策略只能看见最终格式化文本。它无法保留已经由提供方限制的内部内容,也无法保留从未成为结果一部分的运行时产物。第一版聚焦最终结果落盘而不是提前落盘,因此可以接受这一限制;由工具负责的提前落盘仍属于后续工作。 -本地后端返回真实路径,使 v1 保持简单并符合已经验证的 agent 工具行为;seam 本身只承诺一个不透明定位符加检索提示,所以远程后端可以返回非文件定位符。 +本地后端返回真实路径,使 v1 保持简单并符合已经验证的 agent(智能体)工具行为;seam 本身只承诺一个不透明定位符加检索提示,所以远程后端可以返回非文件定位符。 本地后端的价值取决于现有 `read`/`grep` 工具能否检查返回的本地路径,即使落盘目录位于会话 cwd 之外。目前这一条件成立,因为文件系统策略会记录观察结果并设置写保护,但不会把读取限制在工作区内。未来的工作区限制策略必须显式允许本地落盘路径,或改用检索提示指向受支持读取器的非文件落盘后端。 diff --git a/.agents/notes/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.i18n.yaml index 1904a25158..03acf306b4 100644 --- a/.agents/notes/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md -2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md: 51d488db28c57426c75c9ed1cfc90892261c0224 -2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md: ae33cf5c2e944e584cd3d3c6ff76d93619adf7dc +2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md: 6fbd5e2c9d57da3f25c72c652ca50eb45b84323c +2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md: 8a480999038cf892842290e3ea3902683d87e431 diff --git a/.agents/notes/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md b/.agents/notes/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md index 51d488db28..6fbd5e2c9d 100644 --- a/.agents/notes/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md +++ b/.agents/notes/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md @@ -12,17 +12,17 @@ Successful calls are not the only pressure signal. A provider can reject a reque ## Decision -### Successful pressure moves to a durable post-step checkpoint +### Successful pressure runs at the next pre-step boundary -`agent/pre-step` is narrowed to `(agent, turn, step, signal)`. It remains a generic serial checkpoint before `step/start`, but it carries no compaction-only prompt or prefix fields. +`agent/pre-step` receives the exclusive claimed message batch plus `{ turn, step, signal }` and returns the final reject/enter decision. It carries no compaction-only prompt or prefix fields. -The loop fires awaited serial `agent/post-step(agent, turn, step, signal)` after assistant output, every dispatched or synthetic tool result, post-tool context, and steering are durable, but before `step/end`. This placement gives pressure policy the complete successful-call state without splitting an assistant tool call from its result. A propagated listener failure is an ordinary turn failure; it never enters model-request recovery. Compact-basic contains its expected operational failures as described below. +Compact-basic wraps `agent/pre-step` before each proposed request. At a continuation boundary the preceding assistant output, every dispatched or synthetic tool result, post-tool context, and steering are already durable, so pressure policy sees the complete successful-call state without splitting an assistant tool call from its result. At the initial boundary a headerless session has no completed routed request and produces no pressure work. Compact-basic contains operational failures, warns, and delegates without rejecting the proposed step. `dsh-compact-basic` reads the exact latest routed model from the durable request header only to establish that a completed route exists, then asks the singleton `ctx.tokenMeter` to measure the canonical logged envelope and current surface. It does not fall back to `AgentOptions.model` for automatic pressure. A headerless session has no completed routed request to assess and produces no work; any durable non-empty model name uses the same estimator. Operational measurement or summarization failures warn and continue from the latest durable surface: full history before any replacement, or the pruned surface if pruning already landed. ### Request recovery is limited to the final model boundary -`RequestError` and the `agent/request-error` waterfall represent failures after the final adapter has been selected. Each returned stream handle owns a private failure set that preserves the original thrown error identity across dispatch, iterator construction, and iteration without leaking nested-call provenance into an outer call. Terminal in-band `error` or `aborted` finishes enter the same path. Prompt assembly, request middleware, request logging, result processing, tools, step listeners, and cleanup remain ordinary failures. +`agent/request-error` represents terminal failures from the final adapter boundary. Adapter selection, dispatch, iterator construction, and iteration throws become terminal `error` or `aborted` finishes before the agent loop consumes them; adapter-emitted terminal finishes enter the same path. Prompt assembly, request middleware, request logging, result processing, tools, step listeners, and cleanup remain ordinary failures. [Terminal LLM stream failures](2026-07-29-terminal-llm-stream-failures.md) owns this normalization boundary. The failed step closes before recovery runs. A handling listener repairs durable state, returns `{ kind: 'retry' }`, and stops waterfall delegation. The loop then closes the failed turn and opens one retry turn from the durable log without an intervening idle notification. Retry policy and attempt counts remain plugin-owned; compact-basic clears its per-agent overflow count when the chain reaches terminal `agent/settled`. Both DeepSeek adapters normalize recognized provider context-limit failures to `CONTEXT_WINDOW_EXCEEDED`. The [retry-action decision](../simplification/2026-07-27-request-error-retry-action.md) owns the return boundary. @@ -42,11 +42,11 @@ The default summarizer resolves explicit configuration, then the latest logged r ## Testing -Unit tests cover final-adapter failure provenance and identity, closed-turn retry numbering and reset, cancellation and disposal, step-boundary ordering, routed-envelope pressure, pressure-gated pruning, pruning-only relief, pruned-input summarization, balanced overflow reduction, durable prune progress before later failure, generation proof, caps, delegation, and auxiliary-call routing. Real-loop tests cover thrown and in-band overflow through pruning or summary compaction to a reconstructed retry request. +Unit tests cover the final-adapter normalization boundary, closed-turn retry numbering and reset, cancellation and disposal, step-boundary ordering, routed-envelope pressure, pressure-gated pruning, pruning-only relief, pruned-input summarization, balanced overflow reduction, durable prune progress before later failure, generation proof, caps, delegation, and auxiliary-call routing. Real-loop tests cover thrown and in-band overflow through pruning or summary compaction to a reconstructed retry request. ## Alternatives considered -- **Keep provisional pre-step pressure and add more arguments** — rejected because later routing and request mutation remain outside any earlier snapshot, while generic lifecycle becomes coupled to one plugin. +- **Add compaction-only fields to pre-step** — rejected because the canonical durable session and token meter already own the measurement input; the generic lifecycle need not carry a second envelope. - **Retry the same numbered step** — rejected because recovery appends durable events after the failed boundary. A new step preserves balanced nesting and reconstructability. - **Retry whenever `compactIfNeeded` returns a result** — rejected because a custom backend can report success without changing model-visible state. `replaceGeneration` is the authoritative proof. - **Let compact-basic parse provider wording** — rejected because classification belongs at adapters and must cover both thrown and in-band delivery. @@ -54,8 +54,8 @@ Unit tests cover final-adapter failure provenance and identity, closed-turn retr ## Consequences -Post-step pressure describes the completed routed request, including durable tool results and request-only prefix fields. Optional model-free pruning removes predictable tool-output bulk before summary selection and can independently create retry-worthy progress. Canonical overflow supplies the backstop when no successful usage anchor exists. Recovery is bounded, cancellation-owned, and monotonic: it retries only after a visible surface generation change. +The next pre-step pressure check describes the preceding completed routed request, including durable tool results and newly claimed input. Optional model-free pruning removes predictable tool-output bulk before summary selection and can independently create retry-worthy progress. Canonical overflow supplies the backstop when no successful usage anchor exists. Recovery is bounded, cancellation-owned, and monotonic: it retries only after a visible surface generation change. -The cost is one additional serial checkpoint on successful steps and adapter-maintained overflow classification. Provider wording and heuristic character density remain maintenance risks. Surface compaction still cannot repair an envelope that alone exceeds the window, split an indivisible non-tool node, or repair a tool unit whose non-prunable remainder remains oversized. The optional pruner can repair an otherwise indivisible tool pair when removable text-bearing tool-result content is the bulk. +The cost is pressure work in the shared pre-step waterfall and adapter-maintained overflow classification. Provider wording and heuristic character density remain maintenance risks. Surface compaction still cannot repair an envelope that alone exceeds the window, split an indivisible non-tool node, or repair a tool unit whose non-prunable remainder remains oversized. The optional pruner can repair an otherwise indivisible tool pair when removable text-bearing tool-result content is the bulk. -This Agent Note supersedes only the pre-step automatic-trigger portion of the [compaction capability-seam Agent Note](../feature/2026-06-18-compaction-capability-seam.md). The service split, standalone token meter, balanced range contract, log-recorded lock, summary replacement, and sole `summarize()` subclass hook remain unchanged. +The [claimed pre-step lifecycle](2026-07-31-claimed-pre-step-inbox-lifecycle.md) supersedes this note's former post-step trigger. The service split, standalone token meter, balanced range contract, log-recorded lock, summary replacement, and sole `summarize()` subclass hook remain unchanged. diff --git a/.agents/notes/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md b/.agents/notes/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md index ae33cf5c2e..8a48099903 100644 --- a/.agents/notes/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md @@ -1,4 +1,4 @@ -# Agent Note:调用后压缩压力与上下文溢出恢复 +# Agent Note: 调用后压缩压力与上下文溢出恢复 Status: implemented @@ -6,25 +6,25 @@ Status: implemented ## 问题 -`agent/pre-step` 运行在最终请求路由之前,也早于 assistant 输出、工具结果、缓冲上下文与 steering 的产生。即使它接收已装配提示词与会话前缀,压力视图仍是临时的,因为 `agent/request` 还可以改变路由或调用配置,工具 schema 也没有与这些输入一同冻结。增加字段无法让调用前状态描述已完成调用,还会把通用 seam 与压缩耦合。 +`agent/pre-step` 运行在最终请求路由之前,也早于 assistant 输出、工具结果、缓冲上下文与 steering(中途引导)的产生。即使它接收已装配提示词与会话前缀,压力视图仍是临时的,因为 `agent/request` 还可以改变路由或调用配置,工具 schema 也没有与这些输入一同冻结。增加字段无法让调用前状态描述已完成调用,还会把通用 seam 与压缩耦合。 成功调用也不是唯一的压力信号。提供方可能在返回 usage 之前就因上下文窗口超限拒绝请求,一些成功调用也不提供 usage。因此,系统需要可回放的调用后压力,以及一条狭窄的失败恢复路径;当压缩无法证明取得有效进展时,必须保留原始提供方错误。 ## 决策 -### 成功压力移动到持久 post-step 检查点 +### 成功压力在下一个 pre-step 边界运行 -`agent/pre-step` 收窄为 `(agent, turn, step, signal)`。它仍是 `step/start` 之前的通用串行检查点,但不再携带压缩专用的提示词或前缀字段。 +`agent/pre-step` 接收独占的已领取消息批次与 `{ turn, step, signal }`,并返回最终 reject/enter 决策。它不携带压缩专用的提示词或前缀字段。 -循环在 assistant 输出、所有已分发或合成的工具结果、工具后上下文与 steering 都持久化之后、`step/end` 之前,触发等待式串行 `agent/post-step(agent, turn, step, signal)`。该位置让压力策略看到完整的成功调用状态,同时不会拆开 assistant 工具调用与其结果。向外传播的监听器失败属于普通 turn 失败,绝不会进入模型请求恢复;compact-basic 会按下文所述在内部处理其预期的操作性失败。 +Compact-basic 会在每个拟议请求之前包装 `agent/pre-step`。在续步边界,前一条 assistant 输出、所有已分发或合成的工具结果、工具后上下文与 steering 都已经持久化,因此压力策略能看到完整的成功调用状态,同时不会拆开 assistant 工具调用与其结果。初始边界上的无 header 会话尚无已完成路由请求,因此不执行压力工作。Compact-basic 会在内部处理操作性失败、发出警告并继续委托,不会 reject 拟议步骤。 -`dsh-compact-basic` 从持久请求头读取精确的最新实际路由模型,只用它确认已经存在完整路由,随后让单例 `ctx.tokenMeter` 计量规范日志信封与当前表层。自动压力不会回退到 `AgentOptions.model`。没有请求头的会话尚无已完成路由请求可供判断,因此不执行工作;任意持久记录的非空模型名都使用同一个估算器。操作性的计量或摘要失败会发出警告,并从最新持久表层继续:任何替换发生前使用完整历史;若剪枝已经落盘,则使用已剪枝表层。 +`dsh-compact-basic` 从持久请求头读取精确的最新实际路由模型,只用它确认已经存在已完成的路由,随后让单例 `ctx.tokenMeter` 计量规范日志信封与当前表层。自动压力不会回退到 `AgentOptions.model`。没有请求头的会话尚无已完成路由请求可供判断,因此不执行工作;任意持久记录的非空模型名都使用同一个估算器。操作性的计量或摘要失败会发出警告,并从最新持久表层继续:任何替换发生前使用完整历史;若剪枝已经落盘,则使用已剪枝表层。 ### 请求恢复只覆盖最终模型边界 -`RequestError` 与 `agent/request-error` waterfall 表示最终适配器已经选定之后的失败。每个返回的流句柄都绑定一个私有失败集合;该集合在分发、异步迭代器构造与迭代过程中保留原始抛出错误的身份,同时防止把嵌套调用的错误来源误归到外层调用。终止性的带内 `error` 或 `aborted` finish 进入同一路径。提示词装配、请求中间件、请求日志、结果处理、工具、step 监听器与清理仍属于普通失败。 +`agent/request-error` 表示来自最终适配器边界的终止失败。适配器选择、分发、iterator 构造与迭代抛出会在 agent loop(智能体循环)消费前成为终止 `error` 或 `aborted` finish;适配器直接发出的终止 finish 进入同一路径。提示词装配、请求 middleware、请求日志、结果处理、工具、step 监听器与清理仍属于普通失败。[LLM(大语言模型)流的终止失败](2026-07-29-terminal-llm-stream-failures.md)规定这一规范化边界。 -恢复运行前,失败 step 已经关闭。负责处理的监听器修复持久状态、返回 `{ kind: 'retry' }`,并停止 waterfall 委托。循环随后关闭失败 turn,并从持久日志开启一个重试 turn,中间不发布空闲通知。重试策略与尝试计数由插件自己拥有;compact-basic 在链路到达终态 `agent/settled` 时清除对应 agent 的溢出计数。两个 DeepSeek 适配器都把识别出的提供方上下文限制错误规范化为 `CONTEXT_WINDOW_EXCEEDED`。[重试动作决策](../simplification/2026-07-27-request-error-retry-action.md)规定这一返回边界。 +恢复运行前,失败 step 已经关闭。负责处理的监听器修复持久状态、返回 `{ kind: 'retry' }`,并停止 waterfall(瀑布式事件)委托。循环随后关闭失败 turn,并从持久日志开启一个重试 turn,中间不发布空闲通知。重试策略与尝试计数由插件自己拥有;compact-basic 在链路到达终态 `agent/settled` 时清除对应 agent 的溢出计数。两个 DeepSeek 适配器都把识别出的提供方上下文限制错误规范化为 `CONTEXT_WINDOW_EXCEEDED`。[重试动作决策](../simplification/2026-07-27-request-error-retry-action.md)规定这一返回边界。 如果取消发生在 assistant 工具调用已经持久化之后、所有调用完成分发之前,循环会为每个尚未分发的调用记录一对合成的 `tool/call` 与 aborted `tool/result`,随后进入正常中止路径。因此,表层不会仅因取消赢得竞态而留下孤立的持久工具调用。 @@ -32,7 +32,7 @@ Status: implemented `CompactService.compactIfNeeded(agent, trigger, signal)` 接收 `trigger: 'pressure' | 'context-overflow'`。接口不增加估算方法或 token 类型;`ctx.tokenMeter` 继续作为可复用的核算所有者。 -对于 `pressure`,compact-basic 先解析持久提供方/模型目标的适配器所属容量与精确目标策略,再把得到的阈值与保留尾部预算应用到一次统一的 `ctx.tokenMeter.measure()` 结果。低于压力时直接返回,不执行剪枝。压力达到条件后,可选的 `ctx.toolResultPrune` 会改写当前表层中过大的工具结果,compact-basic 再通过同一个 meter 重新计量;若压力恢复安全则跳过模型调用,否则从已剪枝表层选择范围并生成摘要。范围定价、来源、被遮蔽 token 数与非缩小摘要拒绝也由同一个单例 meter 完成。通用默认值保持为阈值比例 `0.8`、保留历史比例 `0.16`、摘要提供方/模型 `''`、`maxTokens: 8192`、`compactionRetries: 1` 与 `auto: true`;可选 `modelPolicies` 项可以按精确提供方/模型组合覆盖这些值。 +对于 `pressure`,compact-basic 先解析持久提供方/模型目标对应适配器所维护的容量与精确目标策略,再把得到的阈值与保留尾部预算应用到一次统一的 `ctx.tokenMeter.measure()` 结果。未达到压力阈值时直接返回,不执行剪枝。压力达到条件后,可选的 `ctx.toolResultPrune` 会改写当前表层中过大的工具结果,compact-basic 再通过同一个 meter 重新计量;若压力已降至安全水平则跳过模型调用,否则从已剪枝表层选择范围并生成摘要。范围定价、来源、被遮蔽 token 数与非缩小摘要拒绝也由同一个单例 meter 完成。通用默认值保持为阈值比例 `0.8`、保留历史比例 `0.16`、摘要提供方/模型 `''`、`maxTokens: 8192`、`compactionRetries: 1` 与 `auto: true`;可选 `modelPolicies` 项可以按精确提供方/模型组合覆盖这些值。 对于规范化溢出,compact-basic 不要求容量元数据,并绕过标量压力与普通保留 token 预算。它先执行剪枝,再在保留最新不可分割单元的同时选择最大的工具配对平衡头部范围;存在范围时,才在同一 signal 下尝试一次缩小摘要压缩。自动监听器先记录 `session.surface.replaceGeneration`,剪枝或摘要让 generation 增加时就返回 `{ kind: 'retry' }`。即使剪枝先落盘而后续摘要工作抛错,这条规则仍然成立;取消依然优先。后端若只返回结果但没有替换表层,不能授权重试;只有剪枝取得进展时,即使没有 `CompactionResult` 也可以授权重试。 @@ -42,11 +42,11 @@ Status: implemented ## 测试 -单元测试覆盖最终适配器失败的来源与身份、已关闭 turn 的重试编号与重置、取消与销毁、step 边界顺序、已路由信封压力、压力门控剪枝、剪枝独立解除压力、从已剪枝输入生成摘要、平衡溢出缩减、后续失败前已落盘的剪枝进展、generation 证明、上限、委托与辅助调用路由。真实循环测试覆盖抛出式和带内溢出,并验证剪枝或摘要压缩后的重试请求从替换表层重建。 +单元测试覆盖最终适配器规范化边界、已关闭 turn 的重试编号与重置、取消与销毁、step 边界顺序、已路由信封压力、压力门控剪枝、剪枝独立解除压力、从已剪枝输入生成摘要、平衡溢出缩减、后续失败前已落盘的剪枝进展、generation 证明、上限、委托与辅助调用路由。真实循环测试覆盖抛出式和带内溢出在经剪枝或摘要压缩后重建重试请求的过程。 ## 考虑过的替代方案 -- **保留临时 pre-step 压力并增加更多参数**——不予采纳,因为后续路由与请求变换仍在更早快照之外,同时通用生命周期会耦合到单个插件。 +- **向 pre-step 增加压缩专用字段**——不予采纳,因为规范持久会话与 token meter 已拥有计量输入;通用生命周期不需要携带第二份信封。 - **重试相同编号的 step**——不予采纳,因为恢复会在失败边界之后追加持久事件。新 step 保持边界配对与可重建性。 - **只要 `compactIfNeeded` 返回结果就重试**——不予采纳,因为自定义后端可能报告成功却没有改变模型可见状态。`replaceGeneration` 才是权威证明。 - **让 compact-basic 解析提供方措辞**——不予采纳,因为分类属于适配器,而且必须同时覆盖抛出式与带内交付。 @@ -54,8 +54,8 @@ Status: implemented ## 后果 -Post-step 压力描述已完成的路由请求,包括持久工具结果与仅请求前缀字段。可选的无模型剪枝会在选择摘要前移除可预测的工具输出体积,也能独立产生足以重试的进展。当成功 usage 锚点不存在时,规范化溢出提供兜底路径。恢复有明确上限、以取消为准,并保持单调:只有模型可见的表层 generation 变化后才重试。 +下一个 pre-step 的压力检查描述前一个已完成的路由请求,包括持久工具结果与新领取输入。可选的无模型剪枝会在选择摘要前移除可预测的工具输出体积,也能独立产生足以重试的进展。当成功 usage 锚点不存在时,规范化溢出提供兜底路径。恢复有明确上限、以取消为准,并保持单调:只有模型可见的表层 generation 变化后才重试。 -代价是成功 step 增加一个串行检查点,并需要适配器持续维护溢出分类。提供方措辞与启发式字符密度仍是维护风险。表层压缩依然无法修复仅信封本身就超出窗口的情况,也不能拆分不可分割的非工具节点,或修复非可剪枝剩余部分仍然过大的工具单元。若可移除的文本工具结果是主要体积,可选剪枝器仍可修复原本不可分割的工具配对。 +代价是在共享 pre-step waterfall 中执行压力工作,并需要适配器持续维护溢出分类。提供方措辞与启发式字符密度仍是维护风险。表层压缩依然无法修复仅信封本身就超出窗口的情况,也不能拆分不可分割的非工具节点,或修复非可剪枝剩余部分仍然过大的工具单元。若可移除的文本工具结果是主要体积,可选剪枝器仍可修复原本不可分割的工具配对。 -本 Agent Note 只取代[压缩能力接缝 Agent Note](../feature/2026-06-18-compaction-capability-seam.md) 中的 pre-step 自动触发部分。服务拆分、独立 token meter、平衡范围契约、日志记录锁、摘要替换与唯一 `summarize()` 子类 hook 均保持不变。 +[已领取 pre-step 生命周期](2026-07-31-claimed-pre-step-inbox-lifecycle.md)取代了本记录原先的 post-step 触发方式。服务拆分、独立 token meter、平衡范围约定、日志记录锁、摘要替换与唯一 `summarize()` 子类 hook 均保持不变。 diff --git a/.agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.i18n.yaml index 27e43ef4b2..aa1d2c9d6f 100644 --- a/.agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md -2026-07-10-single-file-executable-sdk-runtime-distribution.md: f749d6a72b4c32a189a9f848595076457819d9b9 -2026-07-10-single-file-executable-sdk-runtime-distribution.zh.md: 2b511573bc68e5378279cec8d22ce960af0966e9 +2026-07-10-single-file-executable-sdk-runtime-distribution.md: fe09e1b83f4f0a9f867f78351f643b1bd26d7c9d +2026-07-10-single-file-executable-sdk-runtime-distribution.zh.md: 0279e0cf032928e96bad9da02340cae753a0927f diff --git a/.agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md b/.agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md index f749d6a72b..fe09e1b83f 100644 --- a/.agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md +++ b/.agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md @@ -27,8 +27,8 @@ Terminology reminder: pkg's `/snapshot` VFS has nothing to do with this repo's t The deterministic protocol implementation (`server.ts` / `transport.ts`) lands as two packages on the existing `acp/acp` + `examples/acp-demo` pattern — the serving surface is itself a plugin: -- [`packages/ui/jsonrpc`](../../../../packages/ui/jsonrpc/README.md) (`@deepseek-ai/dsh-jsonrpc`): the pure protocol plugin; on apply it mounts `HarnessSdkServer` plus a line-delimited JSON-RPC transport on the process stdio, with disposal through `ctx.effect()`. Whether to serve is decided by `cordis.yml`; a yml that does not mount it is a legitimate process that does not serve. Protocol-level exit belongs to the plugin (after answering the `shutdown` request it disposes its own fiber, then `exit(0)`; an HMR-style unload only stops the service without exiting the process). -- [`packages/examples/jsonrpc-demo`](../../../../packages/examples/jsonrpc-demo/README.md) (`@deepseek-ai/dsh-jsonrpc-demo`): a thin app bin — `installFailLoud` + `loadEnv` + config discovery + `boot()` from [`dsh-app-boot`](../../../../packages/ui/app-boot/src/index.ts), done once boot completes; the server is brought up by the `dsh-jsonrpc` entry in the yml. Its only dependency is app-boot. Process-level exit belongs to the bin (stdin EOF/SIGTERM → dispose then 0, SIGINT → 130). +- [`packages/scaffold/server`](../../../../packages/scaffold/server/README.md) (`@deepseek-ai/dsh-jsonrpc`): the pure protocol plugin; on apply it mounts `HarnessSdkServer` plus a line-delimited JSON-RPC transport on the process stdio, with disposal through `ctx.effect()`. Whether to serve is decided by `cordis.yml`; a yml that does not mount it is a legitimate process that does not serve. Protocol-level exit belongs to the plugin (after answering and flushing the `shutdown` response it disposes the root runtime so persistence drains, then `exit(0)`; an HMR-style unload only stops the service without exiting the process). +- [`packages/examples/jsonrpc-demo`](../../../../packages/examples/jsonrpc-demo/README.md) (`@deepseek-ai/dsh-jsonrpc-demo`): a thin app bin — `installFailLoud` + `loadEnv` + config discovery + `boot()` from [`dsh-app-boot`](../../../../packages/boot/app-boot/src/index.ts), done once boot completes; the server is brought up by the `dsh-jsonrpc` entry in the yml. Its only dependency is app-boot. Process-level exit belongs to the bin (stdin EOF/SIGTERM → dispose then 0, SIGINT → 130). Config discovery has two channels and fails loudly when both are missing: the `DSH_CORDIS_CONFIG` environment variable first (the SDK client convention), then an argv positional argument; no default path and no built-in fallback whatsoever — "the plugins actually booted are decided by an external cordis.yml" is a hard semantic. diff --git a/.agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.zh.md b/.agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.zh.md index 2b511573bc..0279e0cf03 100644 --- a/.agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.zh.md @@ -21,28 +21,28 @@ exe 使用 [@yao-pkg/pkg](https://github.com/yao-pkg/pkg)(vercel/pkg 归档后 `--sea` 要求构建目标 ≥ node22,exe 统一以 node24 为构建目标;每次 pkg 调用只打包一个构建目标,多平台各调用一次。 -术语提醒:pkg 的 `/snapshot` VFS 与本仓库测试体系的“快照”(ACP 回放预期输出、`$DSH_SNAPSHOT`)无关,本文用“VFS”指前者。 +术语提醒:pkg 的 `/snapshot` VFS 与本仓库测试体系的「快照」(ACP 回放预期输出、`$DSH_SNAPSHOT`)无关,本文用「VFS」指前者。 -### 对外服务接口也是插件:ui/jsonrpc + examples/jsonrpc-demo 两包 +### 对外服务接口也是插件:ui/jsonrpc + examples/jsonrpc-demo 两个包 确定性协议实现(`server.ts` / `transport.ts`)按 `acp/acp` + `examples/acp-demo` 的既有模式落为两包——对外服务接口本身也是插件: -- [`packages/ui/jsonrpc`](../../../../packages/ui/jsonrpc/README.md)(`@deepseek-ai/dsh-jsonrpc`):纯协议插件;执行 `apply` 时,在进程 stdio 上挂载 `HarnessSdkServer` 与按行传输的 JSON-RPC 层,资源释放走 `ctx.effect()`。是否提供服务由 `cordis.yml` 决定;未挂载该插件的配置会启动一个不提供此服务的合法进程。协议级退出归插件所有(应答 `shutdown` 请求后 dispose 自身 fiber,再调用 `exit(0)`;HMR 式卸载只停止服务,不退出进程)。 -- [`packages/examples/jsonrpc-demo`](../../../../packages/examples/jsonrpc-demo/README.md)(`@deepseek-ai/dsh-jsonrpc-demo`):轻量应用入口——`installFailLoud` + `loadEnv` + 配置发现 + [`dsh-app-boot`](../../../../packages/ui/app-boot/src/index.ts) 的 `boot()`;`boot()` 完成后入口即完成,服务器由 `cordis.yml` 中的 `dsh-jsonrpc` 条目启动。它只依赖 `app-boot`。进程级退出归 `bin` 所有(stdin EOF/SIGTERM → dispose 后返回 0,SIGINT → 130)。 +- [`packages/scaffold/server`](../../../../packages/scaffold/server/README.md)(`@deepseek-ai/dsh-jsonrpc`):纯协议插件;执行 `apply` 时,在进程 stdio 上挂载 `HarnessSdkServer` 与按行传输的 JSON-RPC 层,资源释放走 `ctx.effect()`。是否提供服务由 `cordis.yml` 决定;未挂载该插件的配置会启动一个不提供此服务的合法进程。协议级退出归插件所有(应答并确保 `shutdown` 响应发送完毕后,对根运行时执行 dispose(资源释放),让待处理的持久化操作完成,再调用 `exit(0)`;HMR 式卸载只停止服务,不退出进程)。 +- [`packages/examples/jsonrpc-demo`](../../../../packages/examples/jsonrpc-demo/README.md)(`@deepseek-ai/dsh-jsonrpc-demo`):轻量应用入口——`installFailLoud` + `loadEnv` + 配置发现 + [`dsh-app-boot`](../../../../packages/boot/app-boot/src/index.ts) 的 `boot()`;`boot()` 完成后入口即完成,服务器由 `cordis.yml` 中的 `dsh-jsonrpc` 条目启动。它只依赖 `app-boot`。进程级退出归 `bin` 所有(stdin EOF/SIGTERM → dispose 后返回 0,SIGINT → 130)。 -配置发现有两个通道,均缺失时立即报错:优先使用 `DSH_CORDIS_CONFIG` 环境变量(SDK 客户端约定),其次使用 argv 位置参数;没有默认路径或内置回退——“实际启动的插件由外部 `cordis.yml` 决定”是硬语义。 +配置发现有两个通道,均缺失时立即报错:优先使用 `DSH_CORDIS_CONFIG` 环境变量(SDK 客户端约定),其次使用 argv 位置参数;没有默认路径或内置回退——「实际启动的插件由外部 `cordis.yml` 决定」是硬语义。 -### 插件解析:VFS 装载真实包树,闭包清单就是部署根目录 +### 插件解析:VFS 装载真实包树,闭包 manifest(元数据清单)就是部署根目录 exe 的 VFS 内是**构建产物形态的真实包树**(各包的 `lib/` + 真实 `node_modules`)。loader 通过标准动态 `import()` 解析插件名:裸包名从 VFS 内 loader 所在位置沿 `node_modules` 向上解析,自然落在 VFS 内。封闭集不需要白名单代码——VFS 中安装了什么,集合中就有什么;`import()` 集合外的名称会失败。 -部署根目录是 [`python/sdk-runtime/package.json`](../../../../python/sdk-runtime/package.json)(`dsh-jsonrpc-agent-pkg`,pnpm 工作区成员、零代码纯依赖清单),也是“exe 安装哪些插件”与“Python 运行时分发什么”的统一事实源。向 exe 添加插件,就是在清单中增加一行依赖后重新打包。[`scripts/verify-runtime-closure.ts`](../../../../scripts/verify-runtime-closure.ts) 遍历该清单覆盖的全部工作区包,要求每个非可选的工作区对等依赖(peer dependency)都显式列在运行时根目录,并报告“引用包 → 缺失对等依赖”的完整链路;`pnpm run hygiene`、CI 静态检查与 single-exe 构建都会在打包前运行该门禁。部署还会依据各包的 `files` 字段打包,因此 tsdown 拆出的共享分片必须被 `files` 覆盖。 +部署根目录是 [`python/sdk-runtime/package.json`](../../../../python/sdk-runtime/package.json)(`dsh-jsonrpc-agent-pkg`,pnpm 工作区成员、零代码纯依赖 manifest),也是「exe 安装哪些插件」与「Python 运行时分发什么」的统一真源。向 exe 添加插件,就是在 manifest 中增加一行依赖后重新打包。[`scripts/verify-runtime-closure.ts`](../../../../scripts/verify-runtime-closure.ts) 遍历该 manifest 覆盖的全部工作区包,要求每个非可选的工作区对等依赖(peer dependency)都显式列在运行时根目录,并报告“引用包 → 缺失对等依赖”的完整链路;`pnpm run hygiene`、CI 静态检查与 single-exe 构建都会在打包前运行该门禁。部署还会依据各包的 `files` 字段打包,因此 tsdown 拆出的共享分片必须被 `files` 覆盖。 ### 构建管线与产物 [`scripts/build-exe-for-python-sdk.ts`](../../../../scripts/build-exe-for-python-sdk.ts):运行时闭包校验 → `pnpm run build` →(清空后)`pnpm --filter dsh-jsonrpc-agent-pkg deploy --legacy --prod --config.node-linker=hoisted --config.auto-install-peers=false --config.link-workspace-packages=true` **直接写入** `python/sdk-runtime/src/deepseek_harness_runtime/runtime/node/` → 注入 pkg 配置(`bin` 指向闭包内的 `node_modules/@deepseek-ai/dsh-jsonrpc-demo/lib/bin.js`;`assets` 使用全量 glob,因为动态 `import()` 对 pkg 静态分析不可见,必须显式打入全部内容)→ 暂存目标平台的 `node-pty` addon → 每个构建目标调用一次 `pkg --sea` → 可执行文件 `dsh-jsonrpc-agent-pkg--` 写入 `dist-exe/`,并拷回运行时目录。Linux 安装会从源码构建 `pty.node`,而 `--legacy` 部署会省略该副作用目录,因此构建器会把它从根安装目录复制到暂存闭包;macOS 使用对应目标的预构建产物,并在可执行文件旁生成所需的 `-spawn-helper`。CI 将这些产物作为测试中间输入,只保留对应平台的 wheel 包。四个部署标志都有实测依据:未启用 `inject-workspace-packages` 时必须使用 `--legacy`;`hoisted` 产出无符号链接的文件树(对 pkg VFS 最稳定,并从物理上保证只有一个 Cordis 实例);关闭对等依赖自动安装可避免未发布包名触发注册表解析;`link-workspace-packages` 让闭包指向工作区/vendor 源码。 -CI 使用 [`.github/workflows/build-exe-for-python-sdk.yml`](../../../../.github/workflows/build-exe-for-python-sdk.yml),且只允许显式触发:手动派发 `workflow_dispatch`,或给 PR 添加 `build-exe` 标签。linux-x64、linux-arm64(`ubuntu-24.04-arm`)和 macos-arm64 三个平台分别进行原生构建,并缓存 `~/.pkg-cache`;macOS 的 ad-hoc 签名由 pkg 处理。每个平台都使用模拟 SSE 模型,分别通过默认配置和自定义 `cordis.yml` 驱动 SDK,再通过 NDJSON JSON-RPC 直接驱动 exe,校验 JSONL 与最终响应;最后把发布形态的 wheel 包安装到干净的 venv 中,并在不传 `runtime_bin` 的情况下运行。Linux 还会检查 GLIBC 依赖,并在 manylinux 2.28 容器中运行。完整构建三个目标时保留 4 个产物,每个产物只含一个发布文件:平台无关的 SDK wheel 包与 3 个原生运行时 wheel 包;手动选择部分目标时保留 SDK wheel 与所选运行时 wheel。裸 exe 与源码包只作为测试中间输入。[`.gitlab-ci.yml`](../../../../.gitlab-ci.yml) 只接受版本与根目录 `package.json` 匹配的 `python-vX.Y.Z` 标签流水线,构建一个 SDK wheel 包和 3 个原生运行时 wheel 包,再由单个串行任务校验并将这 4 个文件发布到项目的 PyPI 注册表。Windows 不在目标范围内。 +CI 使用 [`.github/workflows/build-exe-for-python-sdk.yml`](../../../../.github/workflows/build-exe-for-python-sdk.yml),且只允许显式触发:手动派发 `workflow_dispatch`,或给 PR(Pull Request)添加 `build-exe` 标签。linux-x64、linux-arm64(`ubuntu-24.04-arm`)和 macos-arm64 三个平台分别进行原生构建,并缓存 `~/.pkg-cache`;macOS 的 ad-hoc 签名由 pkg 处理。每个平台都使用 mock SSE(Server-Sent Events)模型,分别通过默认配置和自定义 `cordis.yml` 驱动 SDK,再通过 NDJSON JSON-RPC 直接驱动 exe,校验 JSONL 与最终响应;最后把发布形态的 wheel 包安装到干净的 venv 中,并在不传 `runtime_bin` 的情况下运行。Linux 还会检查 GLIBC 依赖,并在 manylinux 2.28 容器中运行。完整构建三个目标时保留 4 个产物,每个产物只含一个发布文件:平台无关的 SDK wheel 包与 3 个原生运行时 wheel 包;手动选择部分目标时保留 SDK wheel 与所选运行时 wheel。裸 exe 与源码包只作为测试中间输入。[`.gitlab-ci.yml`](../../../../.gitlab-ci.yml) 只接受版本与根目录 `package.json` 匹配的 `python-vX.Y.Z` 标签流水线,构建一个 SDK wheel 包和 3 个原生运行时 wheel 包,再由单个串行任务校验并将这 4 个文件发布到项目的 PyPI 注册表。Windows 不在目标范围内。 ### Python SDK 分发:双载体,exe 用于生产,`node` 用于开发 @@ -50,11 +50,11 @@ Python SDK 位于 [`python/`](../../../../python/README.md):`python/sdk` 是 [`scripts/build-python-release.py`](../../../../scripts/build-python-release.py) 从仓库根目录的 `package.json` 读取权威的稳定版本 `X.Y.Z`,以该版本暂存两个包,并让 SDK 精确依赖 `deepseek-harness-runtime-bin==X.Y.Z`。可选的 `python-vX.Y.Z` 发布标签只是一项一致性断言,与仓库版本不同时会被拒绝;源码 `pyproject.toml` 中的开发占位版本从不决定发布版本。SDK 是 `py3-none-any` wheel 包;每个只提供 wheel 包的运行时包都包含一个 exe,macOS wheel 包还包含与其架构匹配的 helper。运行时 wheel 包使用 `py3-none-manylinux_2_28_x86_64`、`py3-none-manylinux_2_28_aarch64` 或 `py3-none-macosx_11_0_arm64` 三种标签之一;Hatch 钩子拒绝 sdist、通用标签、混合平台载荷、helper 缺失或多余,以及不支持的平台。 -exe“必须显式配置”的硬语义不变;零配置体验由包装层恢复:调用方没有提供 `cordis`、没有显式指定运行时,且环境中没有 `DSH_CORDIS_CONFIG` 时,客户端将检入的默认 `cordis.yml`(`agent-core` + 预载的 `llm-deepseek` + JSONL 持久化 + `bash-local` + `dsh-jsonrpc` 对外服务条目,并通过 `!!js` 使用环境变量兜底)显式注入 `DSH_CORDIS_CONFIG`。 +exe「必须显式配置」的硬语义不变;零配置体验由包装层恢复:调用方没有提供 `cordis`、没有显式指定运行时,且环境中没有 `DSH_CORDIS_CONFIG` 时,客户端将检入的默认 `cordis.yml`(`agent-core` + 预载的 `llm-deepseek` + JSONL 持久化 + `bash-local` + `dsh-jsonrpc` 对外服务条目,并通过 `!!js` 使用环境变量兜底)显式注入 `DSH_CORDIS_CONFIG`。 ### 命名血统 -`@deepseek-ai/dsh-jsonrpc-demo`(包)→ `dsh-jsonrpc-agent`(`bin`)→ `dsh-jsonrpc-agent-pkg`(闭包清单;没有作用域前缀,刻意避开 `constraints` 对 `@deepseek-ai/dsh-*` 的包形状规则)→ `dsh-jsonrpc-agent-pkg--`(exe 产物)。协议字段 `serverInfo.name` 保持为 `deepseek-harness-sdk-runtime`(协议稳定值);Python 分发名为 `deepseek-harness` / `deepseek-harness-runtime-bin`。 +`@deepseek-ai/dsh-jsonrpc-demo`(包)→ `dsh-jsonrpc-agent`(`bin`)→ `dsh-jsonrpc-agent-pkg`(闭包 manifest;没有作用域前缀,刻意避开 `constraints` 对 `@deepseek-ai/dsh-*` 的包形状规则)→ `dsh-jsonrpc-agent-pkg--`(exe 产物)。协议字段 `serverInfo.name` 保持为 `deepseek-harness-sdk-runtime`(协议稳定值);Python 分发名为 `deepseek-harness` / `deepseek-harness-runtime-bin`。 ## 工作线程插件 @@ -62,24 +62,24 @@ exe 内支持 `dsh-workflow-workerthread` 与 `dsh-code-runtime-worker`。两个 ## 测试 -验证面分三层。机制层:`--sea` 链路的实测结论内嵌在“决策”各节(VFS 内 ESM 动态 `import()`、单一 Cordis 实例、明确报错的配置链路、`node:sqlite`、macOS ad-hoc 签名可运行)。SDK 层:完整的无密钥 pytest 套件以假运行时对端覆盖客户端协议、子进程清理、绝对 `cwd` 传递、双载体启动与载体解析;根 CI 在 Python 3.10 上运行全部用例。端到端层:每个平台构建都通过默认 SDK 路径、自定义配置和直接二进制协议,对模拟端点完成一个轮次,并校验最终文本与 JSONL。自定义配置还会通过打包进 VFS 的真实工作线程文件执行 `run_code` 和不启动 agent 的 `workflow`。同一构建任务还会经 Python SDK 运行一组检入的 exe 专用快照:无密钥脚本化模型挂载一个会注册工具的 Cordis 插件,从 `run_code` 调用该工具,运行一个由 spawn 提供方直接启动的 subagent(子 agent)和一个会通过 spawn 启动第二个子 agent 的工作流,随后卸载该插件。该 fixture(测试前置数据)会显式禁用组合包中未使用的 Bash 和本地 skill(技能)发现,使其工具集不依赖仓库外部状态;比较时会规范化以下各处的不透明消息 ID:SDK 结果与通知流,以及父会话和两个子会话的 JSONL 日志。该 harness 与 ACP 的 `pnpm run test:snapshot` 保持独立,因为二者的协议和构建产物不同。随后把平台 wheel 包安装进干净的 venv,并在不传 `runtime_bin` 的情况下运行。 +验证面分三层。机制层:`--sea` 链路的实测结论内嵌在「决策」各节(VFS 内 ESM 动态 `import()`、单一 Cordis 实例、明确报错的配置链路、`node:sqlite`、macOS ad-hoc 签名可运行)。SDK 层:完整的无密钥 pytest 套件以 mock 运行时对端覆盖客户端协议、子进程清理、绝对 `cwd` 传递、双载体启动与载体解析;根 CI 在 Python 3.10 上运行全部用例。端到端层:每个平台构建都通过默认 SDK 路径、自定义配置和直接二进制协议,对 mock 端点完成一个轮次,并校验最终文本与 JSONL。自定义配置还会通过打包进 VFS 的真实工作线程文件执行 `run_code` 和不启动 agent 的 `workflow`。同一构建任务还会经 Python SDK 运行一组检入的 exe 专用快照:无密钥脚本化模型挂载一个会注册工具的 Cordis 插件,从 `run_code` 调用该工具,运行一个直接 spawn 的 subagent 和一个会通过 spawn 启动第二个 subagent 的工作流,随后卸载该插件。该 fixture(测试前置数据)会显式禁用组合包中未使用的 Bash 和本地 skill(技能)发现,使其工具集不依赖仓库外部状态;比较时会规范化以下各处的不透明消息 ID:SDK 结果与通知流,以及父会话和两个子会话的 JSONL 日志。该 harness 与 ACP 的 `pnpm run test:snapshot` 保持独立,因为二者的协议和构建产物不同。随后把平台 wheel 包安装进干净的 venv,并在不传 `runtime_bin` 的情况下运行。 -手工驱动注意:`bin` 将 stdin EOF 视为“客户端已离开”并立即 dispose,短命管道会中止进行中的轮次——管道驱动必须保持 stdin 打开,直到轮次结束。 +手工驱动注意:`bin` 将 stdin EOF 视为「客户端已离开」并立即 dispose,短命管道会中止进行中的轮次——管道驱动必须保持 stdin 打开,直到轮次结束。 ## 曾考虑的替代方案 -**裸用 Node 原生 SEA。** 注入的主脚本必须是 CJS 单文件,blob 内没有文件系统与模块解析,因此动态 `import()` 无法解析裸包名;只能把插件静态编译进主脚本并手工注册。这会绕过标准模块解析并硬编码插件集合,与“配置决定一切”相悖。最终路线实际是“官方 SEA 基础 + pkg 的 VFS/模块钩子层”;否决的是裸用方式,而不是 SEA 本身。 +**裸用 Node 原生 SEA。** 注入的主脚本必须是 CJS 单文件,blob 内没有文件系统与模块解析,因此动态 `import()` 无法解析裸包名;只能把插件静态编译进主脚本并手工注册。这会绕过标准模块解析并硬编码插件集合,与「配置决定一切」相悖。最终路线实际是「官方 SEA 基础 + pkg 的 VFS/模块钩子层」;否决的是裸用方式,而不是 SEA 本身。 **pkg 标准模式。** PoC 证明该模式不可行,而非权衡后放弃:它通过 esbuild 将 ESM 转为 CJS + V8 字节码,但运行时 VM 编译没有接入动态 `import()` 回调,任何 `import()` 都会抛出 `ERR_VM_DYNAMIC_IMPORT_CALLBACK_MISSING`,`--options experimental-require-module` 也无效;此外,它依赖社区补丁版 Node 二进制(macos-arm64 没有预编译版本,现场从源码编译约需 10 分钟)。该模式不适用于本仓库架构。 **每包 ESM→CJS 预打包进 VFS。** 保持真实解析语义、只降级模块格式的折中;`--sea` 直接通过实测,这层构建复杂度无需引入。 -**让 jsonrpc-agent 承担完整闭包依赖。** 应用入口将声明 53 个以上自身并不 `import()` 的依赖,使“打包清单”伪装成真实依赖关系,还会迫使 `constraints` 为其增加 `cordis-in-dependencies` 与 `files` 通配符两个例外。将闭包清单放在 Python 侧的清单包后,`constraints` 不需要任何例外,`bin` 也能保持与 acp-agent 同构的正常包形状。 +**让 jsonrpc-agent 承担完整闭包依赖。** 应用入口将声明 53 个以上自身并不 `import()` 的依赖,使「打包 manifest」伪装成真实依赖关系,还会迫使 `constraints` 为其增加 `cordis-in-dependencies` 与 `files` 通配符两个例外。将闭包清单放在 Python 侧的 manifest 包后,`constraints` 不需要任何例外,`bin` 也能保持与 acp-agent 同构的正常包形状。 **开放插件集(从磁盘加载用户插件)。** 本期采用封闭集;PoC 同时证实,可以通过 `ctx.baseUrl` 相对路径通道从 VFS 外的磁盘 `import()` ESM。该能力列为后续演进,届时还需解决外部插件与 exe 内 Cordis 实例的共享问题。 ## 后果 -**买到的**:目标平台零依赖的单文件分发;插件语义与源码运行严格一致(同一棵真实包树,无转译、无注册表);对外服务接口、插件集与配置全部收敛到 `cordis.yml` 和一份依赖清单这两个事实源;exe 与 `node` 双载体使用同一棵树和相同语义,开发验证无需等待打包;官方 Node 二进制消除了补丁版二进制的供应链顾虑。 +**买到的**:目标平台零依赖的单文件分发;插件语义与源码运行严格一致(同一棵真实包树,无转译、无注册表);对外服务接口、插件集与配置全部收敛到 `cordis.yml` 和一份依赖 manifest 这两个真源;exe 与 `node` 双载体使用同一棵树和相同语义,开发验证无需等待打包;官方 Node 二进制消除了补丁版二进制的供应链顾虑。 **付出的**:产物约 174MB,且源码原样进入 blob(没有字节码混淆;闭源分发诉求需要另行评估);pkg 的 VFS/模块钩子层仍由社区维护(构建脚本钉死 `@yao-pkg/pkg@6.21.0`,升级需要显式改动);`--sea` 每个构建目标调用一次(与 CI 每个平台一个任务相匹配,本地多平台构建串行执行)。 diff --git a/.agents/notes/implemented/architecture/2026-07-12-agent-scope-runtime-design.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-12-agent-scope-runtime-design.i18n.yaml index d05f034c0f..f5fdd4e906 100644 --- a/.agents/notes/implemented/architecture/2026-07-12-agent-scope-runtime-design.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-12-agent-scope-runtime-design.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-12-agent-scope-runtime-design.md -2026-07-12-agent-scope-runtime-design.md: d6b865977a76061784c88dbad089fa5963be8c7e -2026-07-12-agent-scope-runtime-design.zh.md: 5b6b9b1ca582d83a267a30f8f76e38ea87d52e9b +2026-07-12-agent-scope-runtime-design.md: b8f265551c4ebbb94d32b3599959fe6cc4da974d +2026-07-12-agent-scope-runtime-design.zh.md: 22cd35a601bc011c27a748098be11990f5ee4653 diff --git a/.agents/notes/implemented/architecture/2026-07-12-agent-scope-runtime-design.md b/.agents/notes/implemented/architecture/2026-07-12-agent-scope-runtime-design.md index d6b865977a..b8f265551c 100644 --- a/.agents/notes/implemented/architecture/2026-07-12-agent-scope-runtime-design.md +++ b/.agents/notes/implemented/architecture/2026-07-12-agent-scope-runtime-design.md @@ -34,7 +34,7 @@ The [July 8 Agent Note](2026-07-08-agent-scope-contexts.md) remains the contribu ## Cordis model: context, fiber, effect, receiver, and waterfall -Five Cordis ideas are required to understand the implementation. A context selects services and registration ownership; a fiber is one live plugin or child lifecycle; an effect attaches cleanup to a fiber; an event receiver selects listeners; and a waterfall lets listeners transform or veto an operation in sequence. +Five Cordis ideas are required to understand the implementation. A context selects services and registration ownership; a fiber is one live plugin or child lifecycle; an effect attaches cleanup to a fiber; an event receiver selects listeners; and a waterfall lets listeners transform or short-circuit an operation in sequence. ### A context is an ownership path through one service graph @@ -56,7 +56,7 @@ Cordis filters listeners using the dispatch receiver (`this`), while harness lis Product helpers therefore construct the carrier and pass the domain subject separately. This prevents listener routing from becoming an alternate object model and keeps event signatures understandable without knowledge of carrier internals. -A Cordis waterfall is middleware-style dispatch. Each listener receives `next()`: calling it delegates to the remaining listeners and base operation, while returning without it vetoes or replaces the downstream result. Waterfalls power prompt assembly and tool policy; ordinary emit events notify synchronously, and parallel events await all listeners without a veto result. +A Cordis waterfall is middleware-style dispatch. Each listener receives `next()`: calling it delegates to the remaining listeners and base operation, while returning without it short-circuits or replaces the downstream result. Waterfalls power prompt assembly and tool policy; ordinary emit events notify synchronously, and parallel events await all listeners without a veto result. ## Scope routing: one opaque key selects one layer @@ -150,7 +150,7 @@ sequenceDiagram Every teardown request joins one memoized path. The order is: 1. Deactivate creation or driving and let synchronous publication finish. -2. Stop and drain the driver, including idle injection flushes. +2. Stop and drain the driver, discarding any injection that remains pending. 3. Detach the agent. 4. Detach the session. 5. Dispose the agent scope. @@ -238,7 +238,7 @@ For a native call, the observer deletes the stage and commits its value only whe For a Code Mode SDK call, the inner successful result records `{ parentToken, value }` rather than committing. The observer waits for the `run_code` execution whose token matches `parentToken` and commits only if that outer final result also succeeds. Program failure, runtime abort, or outer post-policy denial discards the pending value. -Once a value is pending or committed, a scoped monotonic guard denies later tool calls. After commit, the ordinary serial `agent/turn-stop` listener returns a stop decision after continuation and steering have already folded. A schema-validation failure remains an ordinary `INVALID_ARGS` tool error and leaves the child able to retry within the same turn. +Once a value is pending or committed, a scoped monotonic guard denies later tool calls. The successful structured-output execution calls `exec.concludeTurn()`, so its own immutable result carries `concludesTurn: true` and the loop ends the tool loop at that step. A schema-validation failure remains an ordinary `INVALID_ARGS` tool error and leaves the child able to retry within the same turn. Pure Code Mode's registry contribution omits `structured_output` from native wire schemas and exposes it through the generated SDK. The assembly waterfall may deliberately change that presentation; execution still validates against the child-scoped definition, and the listener owns the consistency of any alternate model-visible route it creates. @@ -250,9 +250,9 @@ Prompt assembly is intentionally cooperative, but three execution facts need one |---|---|---| | Tool pre-policy | Deny monotonically | A later listener must not re-allow an already denied call | | Tool result | Observe the immutable committed outcome | Structured output must commit only the result that actually escaped the pipeline | -| Turn continuation | Stop after ordinary continuation folding | A committed terminal output must end the turn | +| Turn continuation | Conclude through the committed tool result | A committed terminal output must end the turn | -`ToolGuard` is the monotonic policy registry. Committed tool observation is the contained `tools/result` point described above. Terminal structured output listens on the ordinary serial `agent/turn-stop` fold after normal continuation and steering decisions; no public `strictSerial()` dispatcher is needed for the typed listener contract. +`ToolGuard` is the monotonic policy registry. Committed tool observation is the contained `tools/result` point described above. Terminal structured output marks its own execution with `concludesTurn`, so terminality is data on the authoritative result rather than a separate hook decision. ### Skill and approval services trust typed callers diff --git a/.agents/notes/implemented/architecture/2026-07-12-agent-scope-runtime-design.zh.md b/.agents/notes/implemented/architecture/2026-07-12-agent-scope-runtime-design.zh.md index 5b6b9b1ca5..22cd35a601 100644 --- a/.agents/notes/implemented/architecture/2026-07-12-agent-scope-runtime-design.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-12-agent-scope-runtime-design.zh.md @@ -6,7 +6,7 @@ Status: implemented ## 问题 -[agent 作用域契约](2026-07-08-agent-scope-contexts.md)对贡献者而言很简单:通过 `agent.ctx` 注册,解析出一个全局加单 agent 的视图,仅在 setup 完成后发布,并保持作用域直到工作停止。运行时必须在协作式插件框架、异步创建、可重入监听器、持久化会话提交以及 worker 或进程故障等场景下维护这份契约。 +[agent 作用域约定](2026-07-08-agent-scope-contexts.md)对贡献者而言很简单:通过 `agent.ctx` 注册,解析出一个全局加单 agent 的视图,仅在 setup 完成后发布,并保持作用域直到工作停止。运行时必须在协作式插件框架、异步创建、可重入监听器、持久化会话提交以及 worker 或进程故障等场景下维护这份约定。 主要的设计风险是为每个竞态条件引入第二套机制。独立的预留、就绪哨兵、取消中继、快照层和保护注册表可能镜像同一个事实,直到没有读者能分辨哪个才是权威的。这些机制还会诱使运行时把可信的类型化调用当作敌对的序列化边界来处理。 @@ -24,17 +24,17 @@ Status: implemented | 拥有一个活跃的 agent 或会话 | 由其 disposer 捕获的单条注册表条目 | | 协调创建/恢复 | 单个 `AgentCreationTransaction` | | 保护持久化、队列、模型或协议格式数据 | 在该边界处一次性物化 | -| 在同一进程内传递类型化值 | Readonly 借用契约 | +| 在同一进程内传递类型化值 | Readonly 借用约定 | | 组合模型可见的提示词与工具表面 | 单个共享工具视图加权威的 assembly-waterfall 结果 | | 协调 subagent、worker 和进程关闭 | 单个取消信号加该边界独立的终止态/完全停稳态事实 | 本 Agent Note 余下部分按依赖顺序展开这些选择:Cordis 机制、作用域路由、创建与会话提交、工具与提示词、subagent 与工作流,最后是可执行检查。 -[7 月 8 日 Agent Note](2026-07-08-agent-scope-contexts.md)仍然是贡献者契约。独立的 [subagent 组合控制 Agent Note](../feature/2026-07-12-subagent-persona-tool-filter-and-depth.md)拥有 `persona`、`toolFilter` 和 `maxDepth`;本文仅讨论它们的 setup 如何融入生命周期。 +[7 月 8 日 Agent Note](2026-07-08-agent-scope-contexts.md)仍然是贡献者约定。独立的 [subagent 组合控制 Agent Note](../feature/2026-07-12-subagent-persona-tool-filter-and-depth.md)拥有 `persona`、`toolFilter` 和 `maxDepth`;本文仅讨论它们的 setup 如何融入生命周期。 ## Cordis 模型:上下文、fiber、effect、receiver 与 waterfall -理解实现需要五个 Cordis 概念。上下文选择服务和注册所有权;fiber 是一个活跃的插件或子生命周期;effect 将清理逻辑附加到 fiber;事件接收器选择监听器;waterfall(瀑布式事件)让监听器按顺序变换或否决一个操作。 +理解实现需要五个 Cordis 概念。上下文选择服务和注册所有权;fiber 是一个活跃的插件或子生命周期;effect 将清理逻辑附加到 fiber;事件接收器选择监听器;waterfall(瀑布式事件)让监听器按顺序变换或短路一个操作。 ### 上下文是贯穿单个服务图的所有权路径 @@ -56,7 +56,7 @@ Cordis 使用 dispatch receiver(`this`)过滤监听器,而 harness 的监 因此,产品辅助函数构造载体并单独传递领域主体。这防止监听器路由变成另一套对象模型,并使事件签名在不了解载体内部的情况下也可理解。 -Cordis waterfall 是中间件风格的 dispatch。每个监听器接收 `next()`:调用它则委托给剩余监听器和基础操作,不调用则否决或替换下游结果。Waterfall 驱动提示词组装和工具策略;普通 emit 事件同步通知,parallel 事件等待所有监听器但没有否决结果。 +Cordis waterfall 是中间件风格的 dispatch。每个监听器接收 `next()`:调用它则委托给剩余监听器和基础操作,不调用则短路或替换下游结果。Waterfall 驱动提示词组装和工具策略;普通 emit 事件同步通知,parallel 事件等待所有监听器但没有否决结果。 ## 作用域路由:一个不透明键选择一层 @@ -104,7 +104,7 @@ detach 闭包捕获其确切注册表条目。它仅在映射仍指向该注册 ### Setup 是私有世界内的可信组合 -Setup 接收完整的子上下文,可以等待插件激活。它可以注册工具、提示词段、限制、监听器和其他 effect,但公开契约不支持通过强制转换或内部注册表调用来驱动或发布正在创建中的 agent。 +Setup 接收完整的子上下文,可以等待插件激活。它可以注册工具、提示词段、限制、监听器和其他 effect,但公开约定不支持通过强制转换或内部注册表调用来驱动或发布正在创建中的 agent。 事务将异步加载和 setup 与停用进行竞争,而非无限等待外部代码拥有的 promise。如果取消或所有者卸载获胜,即使外部 promise 永不结算,公开创建也会在事务拥有的清理之后拒绝。 @@ -150,7 +150,7 @@ sequenceDiagram 每个拆除请求加入一条记忆化路径。顺序为: 1. 停用创建或驱动,让同步发布完成。 -2. 停止并排空 driver,包括空闲注入刷新。 +2. 停止并排空 driver,丢弃仍处于待处理状态的注入。 3. 分离 agent。 4. 分离会话。 5. Dispose agent 作用域。 @@ -185,7 +185,7 @@ Session 头部、种子和追加的事件是无损 JSON 数据。Session 构造 ## 信任边界:仅在所有权真正变更时复制 -运行时区分类型化的进程内契约与序列化及持久化边界。这是值和回调的主要简化规则。 +运行时区分类型化的进程内约定与序列化及持久化边界。这是值和回调的主要简化规则。 | 边界 | 所有权规则 | |---|---| @@ -196,9 +196,9 @@ Session 头部、种子和追加的事件是无损 JSON 数据。Session 构造 | 持久化会话或持久化数据 | 在提交前物化并验证 | | Worker、进程或协议格式消息 | 序列化、验证并拥有解码后的值 | -测试中构造恶意 getter、在交接后替换类型化回调、或强制转换伪造服务对象的做法本身不定义生产契约。运行时在数据跨越解析器、队列、模型、持久化、文件、worker、进程或协议格式(wire format)边界时保留检查,并在可信进程内依赖 readonly 类型加插件纪律。 +测试中构造恶意 getter、在交接后替换类型化回调、或强制转换伪造服务对象的做法本身不定义生产约定。运行时在数据跨越解析器、队列、模型、持久化、文件、worker、进程或协议格式(wire format)边界时保留检查,并在可信进程内依赖 readonly 类型加插件纪律。 -回调隔离与数据所有权是分开的。监听器是任意扩展代码,即使其参数是可信的也可能抛出异常;发布和提交后路径仍按其事件契约隔离失败。 +回调隔离与数据所有权是分开的。监听器是任意扩展代码,即使其参数是可信的也可能抛出异常;发布和提交后路径仍按其事件约定隔离失败。 ## 工具与提示词:单一视图、权威组装、已提交的结果 @@ -216,7 +216,7 @@ Session 头部、种子和追加的事件是无损 JSON 数据。Session 构造 注册表为每次执行分配一个新的带品牌的 `Symbol` token。嵌套的 Code Mode 调用将外层 token 作为 `parent` 携带,因此结构化输出可以通过标识将内层捕获与其外层 `run_code` 结果关联。 -注册表分配的新 Symbol 提供无碰撞的执行标识,无需 WeakSet 成员注册表。调用方无法通过 `ToolExecutionInput` 提供执行自身的 token;它们仅在注册表创建后接收流水线拥有的 `ToolExecution`。这是一个可信的类型化契约,而非针对任意强制转换或 JavaScript 调用方的运行时防御。 +注册表分配的新 Symbol 提供无碰撞的执行标识,无需 WeakSet 成员注册表。调用方无法通过 `ToolExecutionInput` 提供执行自身的 token;它们仅在注册表创建后接收流水线拥有的 `ToolExecution`。这是一个可信的类型化约定,而非针对任意强制转换或 JavaScript 调用方的运行时防御。 参数在模型/工具 JSON 进入流水线时一次性物化。Pre-、around- 和 post-execute 监听器操作类型化的 execution 和决策。Call ID 关联、审批、单调守卫和 Code Mode 嵌套仍然是显式的关系检查。 @@ -238,7 +238,7 @@ Scope 直接解决了真正的隔离问题。结构化输出贡献注册在子 对于 Code Mode SDK 调用,内层成功结果记录 `{ parentToken, value }` 而非提交。观察者等待 token 匹配 `parentToken` 的 `run_code` 执行,仅在该外层最终结果也成功时才提交。程序失败、运行时中止或外层 post-policy 拒绝会丢弃待定值。 -一旦值处于待定或已提交状态,作用域单调守卫拒绝后续工具调用。提交后,普通串行的 `agent/turn-stop` 监听器在 continuation 和 steering(中途引导)已折叠之后返回停止决策。Schema 验证失败仍然是普通的 `INVALID_ARGS` 工具错误,子级可以在同一轮次内重试。 +一旦值处于待定或已提交状态,作用域单调守卫拒绝后续工具调用。成功的结构化输出执行会调用 `exec.concludeTurn()`,因此其自身不可变结果携带 `concludesTurn: true`,循环在该步骤结束工具循环。Schema 验证失败仍然是普通的 `INVALID_ARGS` 工具错误,子级可以在同一轮次内重试。 纯 Code Mode 的注册表贡献从原生 wire schema 中省略 `structured_output`,并通过生成的 SDK 暴露它。Assembly waterfall 可以有意改变该展示;执行仍然针对子作用域定义进行验证,监听器拥有其创建的任何替代模型可见路由的一致性。 @@ -250,13 +250,13 @@ Scope 直接解决了真正的隔离问题。结构化输出贡献注册在子 |---|---|---| | 工具 pre-policy | 单调拒绝 | 后续监听器不得重新允许已被拒绝的调用 | | 工具结果 | 观察不可变的已提交结果 | 结构化输出必须仅提交实际逃出流水线的结果 | -| 轮次 continuation | 在普通 continuation 折叠之后停止 | 已提交的终端输出必须结束轮次 | +| 轮次 continuation | 通过已提交工具结果终止 | 已提交的终端输出必须结束轮次 | -`ToolGuard` 是单调策略注册表。已提交的工具观察是上述被隔离的 `tools/result` 点。终端结构化输出监听普通串行的 `agent/turn-stop` 折叠,在正常 continuation 和 steering 决策之后;类型化的监听器契约不需要公开的 `strictSerial()` dispatcher。 +`ToolGuard` 是单调策略注册表。已提交的工具观察是上述被隔离的 `tools/result` 点。终端结构化输出在自身执行上标记 `concludesTurn`,因此终止性成为权威结果上的数据,而不是独立 hook 决策。 ### Skill 和 approval 服务信任类型化调用方 -Skill 注册表定义和 approval 策略是 readonly 的同进程契约。它们的服务不克隆回调对象,也不防御交接后的回调替换。 +Skill 注册表定义和 approval 策略是 readonly 的同进程约定。它们的服务不克隆回调对象,也不防御交接后的回调替换。 Skill 仍然验证外部 skill 文件和解析的提供方输出,通过调用 agent 的工具视图路由目录,并精确 dispose 注册。Approval 仍然解析策略、观察取消、按 `request.agent` 路由 `approval/request`、记录持久化审计对,并隔离应答者和提交后观察者的失败。 @@ -264,9 +264,9 @@ Skill 仍然验证外部 skill 文件和解析的提供方输出,通过调用 Subagent 启动有一次所有权转移。提供方拥有未发布资源,直到其 start promise 以一个已发布 run 兑现;调用方拥有返回的 run 并必须 dispose 它。 -### 服务契约有一个取消通道 +### 服务约定有一个取消通道 -`SubagentProvider.start()` 和 `SubagentService.start()` 返回 `Promise`。Promise 会在后端跨过发布边界后兑现,因此调用方和 `subagent/start` 观察者从不需要第二个 `run.started` promise。提供方工作如果在发布前失败,`start()` 就会被拒绝;发布后的提示词、轮次、取消与基础设施结果会通过 `SubagentRun.result` 结算,且不会隐藏 child id,这也是[持久化目录决策](../feature/2026-07-22-durable-subagent-catalog-and-list-agents.md)所要求的契约。 +`SubagentProvider.start()` 和 `SubagentService.start()` 返回 `Promise`。Promise 会在后端跨过发布边界后兑现,因此调用方和 `subagent/start` 观察者从不需要第二个 `run.started` promise。提供方工作如果在发布前失败,`start()` 就会被拒绝;发布后的提示词、轮次、取消与基础设施结果会通过 `SubagentRun.result` 结算,且不会隐藏 child id,这也是[持久化目录决策](../feature/2026-07-22-durable-subagent-catalog-and-list-agents.md)所要求的约定。 `SubagentStartRequest.signal` 是必需的。中止它会在启动期间,以及已发布 run 的剩余就绪或轮次工作中请求取消。`SubagentRun.dispose()` 也请求取消并等待完全停稳。没有单独的公开 `run.cancel()` 通道。 @@ -314,11 +314,11 @@ Worker 边界仍然序列化请求和结果。宿主保留首个终端结果仲 ## 正确性强制 -该设计通过类型、运行时逃逸点、生成的契约和行为测试来强制执行。没有哪一层被要求证明它无法观察到的东西。 +该设计通过类型、运行时逃逸点、生成的约定和行为测试来强制执行。没有哪一层被要求证明它无法观察到的东西。 ### 类型使常规路径难以误用 -Readonly 契约描述借用的同进程值。`Scoped` 标记事件接收器,`agentEvents()` 融合载体和主体,工具输入省略注册表拥有的 token,subagent 异步返回类型直接暴露发布与结算。 +Readonly 约定描述借用的同进程值。`Scoped` 标记事件接收器,`agentEvents()` 融合载体和主体,工具输入省略注册表拥有的 token,subagent 异步返回类型直接暴露发布与结算。 TypeScript 无法管控 JavaScript 强制转换、直接 Cordis dispatch、进程消息或持久化文件,因此运行时强制保留在这些逃逸点。 @@ -326,9 +326,9 @@ TypeScript 无法管控 JavaScript 强制转换、直接 Cordis dispatch、进 `dsh-scope/invariant` 配套插件在被选用时验证每个声明的作用域事件使用带标记的载体,以及暴露主体的事件族使用匹配的键。独立的 `dsh-session/invariant` 贡献在追加提交前暂存 trace 验证,并在同一事件提交后推进;二者都通过 `ctx.invariants` 注册。 -该插件不通过扫描注册表来管控可信 setup,也不拒绝通过强制转换构造的提示词 assembly 对象。这些检查会将组合契约变成推测性的运行时机制,却不保护真实的外部边界。 +该插件不通过扫描注册表来管控可信 setup,也不拒绝通过强制转换构造的提示词 assembly 对象。这些检查会将组合约定变成推测性的运行时机制,却不保护真实的外部边界。 -### 生成的产物使公开契约保持对齐 +### 生成的产物使公开约定保持对齐 事件目录、服务目录、生产者/消费方矩阵、配置目录、模块图、工具目录、type-equiv 块和作用域事件解析器映射都是从源码生成或受新鲜度门禁约束的。[TypeScript 语义门禁 Agent Note](../process/2026-07-14-typescript-program-backed-semantic-gates.md)拥有 Program 构造、语义事件发现和解析器生成规则。 @@ -336,7 +336,7 @@ TypeScript 无法管控 JavaScript 强制转换、直接 Cordis dispatch、进 ## 曾考虑的替代方案 -[7 月 8 日 Agent Note](2026-07-08-agent-scope-contexts.md#alternatives-considered)拥有公开扁平作用域契约的替代方案。此处的替代方案关注实现形态。 +[7 月 8 日 Agent Note](2026-07-08-agent-scope-contexts.md#alternatives-considered)拥有公开扁平作用域约定的替代方案。此处的替代方案关注实现形态。 ### 使用透明代理作为作用域载体 @@ -348,7 +348,7 @@ TypeScript 无法管控 JavaScript 强制转换、直接 Cordis dispatch、进 ### 对每个类型化的同进程参数做快照 -通用复制防御有状态 getter 和违反 readonly 契约的调用方,但增加分配、重复验证器和可能遗忘复制的路径。物化属于解析器、队列、模型、持久化、worker、进程和协议格式边界——即所有权真正变更的地方。 +通用复制防御有状态 getter 和违反 readonly 约定的调用方,但增加分配、重复验证器和可能遗忘复制的路径。物化属于解析器、队列、模型、持久化、worker、进程和协议格式边界——即所有权真正变更的地方。 ### 为就绪、取消和 dispose 提供独立控制器 @@ -375,10 +375,10 @@ Worker 消息、进程死亡和持久化输入确实跨越所有权和序列化 - 作用域贡献仅在其精确的 agent 视图中可见,并随该作用域一起 dispose。 - 创建和恢复不暴露部分配置的句柄;最终写入注册表时的失败者和发布失败清理每个已准备的资源。 - Dispose 在 driver 排空和最终会话工作期间保留作用域监听器和持久化,然后撤销作用域。 -- 持久化、队列、模型、worker、进程和协议格式的值在其真实边界处被拥有;类型化的同进程值遵循 readonly 契约。 +- 持久化、队列、模型、worker、进程和协议格式的值在其真实边界处被拥有;类型化的同进程值遵循 readonly 约定。 - ToolRegistry 的展示、查找和执行在专家 assembly 变换之前解析相同的活跃视图,已提交的结果有一个不可变的观察点。 - 注册表贡献是确定性输入,而可信的 assembly waterfall 拥有最终的模型可见组合。 -- Subagent start 仅返回已发布的 run,必需的 signal 取消待定或活跃的工作,dispose 到达后端的完全停稳契约。 +- Subagent start 仅返回已发布的 run,必需的 signal 取消待定或活跃的工作,dispose 到达后端的完全停稳约定。 - Worker/进程结果优先级和清理在死亡、迟到消息和有界拆除下保持正确。 ### 代价与局限 @@ -387,6 +387,6 @@ Worker 消息、进程死亡和持久化输入确实跨越所有权和序列化 可信的 `system-prompt/assemble` 监听器可以移除或替换 Code Mode 和结构化输出协议片段。这是有意为之:监听器拥有最终组合,必须保持部署期望仍可用的任何协议。 -该设计信任同进程中的类型化插件。它不防御任意强制转换、有状态 getter、违反 readonly 契约的修改,或插件有意在支持的组合 API 之外使用环境服务访问。 +该设计信任同进程中的类型化插件。它不防御任意强制转换、有状态 getter、违反 readonly 约定的修改,或插件有意在支持的组合 API 之外使用环境服务访问。 [安全与权限非目标](2026-07-08-agent-scope-contexts.md#security-and-authority-are-non-goals)仍然是根本性的。这些机制证明注册组合、发布和生命期所有权;它们不证明隔离或父到子的非升权。 diff --git a/.agents/notes/implemented/architecture/2026-07-12-scoped-layers-store.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-12-scoped-layers-store.i18n.yaml index 46f0a1cd41..d4886965ad 100644 --- a/.agents/notes/implemented/architecture/2026-07-12-scoped-layers-store.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-12-scoped-layers-store.i18n.yaml @@ -1,6 +1,6 @@ # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: -# pnpm run verify-translation-pairing --write +# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-12-scoped-layers-store.md 2026-07-12-scoped-layers-store.md: c5186d1652bca617eed62ec02937f2d055ea727c -2026-07-12-scoped-layers-store.zh.md: 3183811be553428ebcd8f59f15989c44d458b477 +2026-07-12-scoped-layers-store.zh.md: f5084426beef836d71e55c0898ec1edbdc7725f3 diff --git a/.agents/notes/implemented/architecture/2026-07-12-scoped-layers-store.zh.md b/.agents/notes/implemented/architecture/2026-07-12-scoped-layers-store.zh.md index 3183811be5..f5084426be 100644 --- a/.agents/notes/implemented/architecture/2026-07-12-scoped-layers-store.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-12-scoped-layers-store.zh.md @@ -16,11 +16,11 @@ agent(智能体)作用域机制([决策](2026-07-08-agent-scope-contexts.m - change 回调运行前必须收集 undo,抛错的回调才能回滚变更。 - 公开 disposer 必须就是 `ctx.effect()` 返回的那个函数;包装它会破坏 Cordis 基于身份的有序拆除。 -共享的是生命周期与保持插入顺序的存储,而不是注册表策略。工具限制、保留传输处理、提示词求值时机、命令规范化、精确诊断和回调异常隔离,仍分别属于不同的领域契约。 +共享的是生命周期与保持插入顺序的存储,而不是注册表策略。工具限制、保留传输处理、提示词求值时机、命令规范化、精确诊断和回调异常隔离,仍分别属于不同的领域约定。 ## 决策 -`@deepseek-ai/dsh-scope` 提供与键类型无关的 `store.ts` 实现模块。该包(package)继续将 Cordis 和 `@deepseek-ai/dsh-invariants` 列为对等依赖(peer dependency),其不变量配套模块保持不变。包根导出四个存储符号:`ScopeLayer`、`ScopedLayers`、`NamedEntries` 和 `AnonymousEntries`。`EntryValues` 仍是内部接口,`store.ts` 不是包子路径。 +`@deepseek-ai/dsh-scope` 提供与键类型无关的 `store.ts` 实现模块。该包继续将 Cordis 和 `@deepseek-ai/dsh-invariants` 列为对等依赖(peer dependency),其不变量配套模块保持不变。包根导出四个存储符号:`ScopeLayer`、`ScopedLayers`、`NamedEntries` 和 `AnonymousEntries`。`EntryValues` 仍是内部接口,`store.ts` 不是包子路径。 `ScopeLayer` 保留显式的聚合概念,同时只要求判断整个层是否为空。服务定义一个具体层,使其表结构与领域 helper 适合该服务;`ScopedLayers` 负责构造、选择、生命周期挂接、通知和聚合回收。 @@ -70,14 +70,14 @@ export class AnonymousEntries { } ``` -## 存储契约 +## 存储约定 - 构造器只创建一次 `global`,调用的是 `createLayer(undefined)`。只有 `effect()` 会创建专属层;`peek()` 和 `merge()` 从不创建专属层,而 `peek(undefined)` 返回 `undefined`,因为全局层已经显式存在。 - `merge()` 是唯一会物化结果的通用读取接口。它按插入顺序复制全局命名条目,再按专属条目的插入顺序应用这些条目;同名条目完成遮蔽,但不会移动无关名称。 - `NamedEntries.insert()` 以原子方式检查并插入,返回幂等且只撤销该精确条目的 undo,并通过调用方提供的工厂取得所属注册表的精确重名诊断。查询与迭代器保留 `Map` 的原生顺序,并在同一个非空表 generation 内保持活遍历;清空表会开启新的 generation,因此尚未结束的迭代器无法观察到自我替换。 - `AnonymousEntries.append()` 为每次登记分配唯一内部键,因此值相等的回调或其他值仍彼此独立。其迭代器保留插入顺序,并采用同样的 generation 活遍历边界。 - `effect()` 通过 `scopeOf(ctx)` 导出键,并把 action 挂到同一个 `ctx.effect()` 上。它只接受一个同步 action,且该 action 只返回一个同步 undo;action 要么返回其 undo,要么必须在保留任何贡献之前抛错。helper 不会规范化更宽泛的 Cordis `Effect` union。 -- `effect()` 在调用 `onChange` 前收集 action 的 undo,并原样返回 `ctx.effect()` 的 disposer。销毁时先运行 action undo 再通知;Cordis 保证其幂等性;只有整个层的 `ScopeLayer.isEmpty()` 变为 true 后,helper 才删除专属层。 +- `effect()` 在调用 `onChange` 前收集 action 的 undo,并原样返回 `ctx.effect()` 的 disposer。销毁时先运行 action undo 再通知;Cordis 保证其幂等性;只有在整个层的 `ScopeLayer.isEmpty()` 返回 true 后,helper 才会删除专属层。 - `options.notify` 默认为 `true`。回调自身的策略仍具最终效力:工具与提示词的 change 回调可以抛错并触发登记回滚;`CommandService.notifyChange()` 会隔离观察者失败;工具 guard 传入 `notify: false`。 ## 注册表迁移 @@ -100,7 +100,7 @@ export class AnonymousEntries { **注册方法上的显式 scope 参数。** 分开的可见性与属主输入让不匹配的生命周期成为可表达状态,而遗漏 scope 则会静默变成全局登记。 -**接受完整的 Cordis `Effect` union。** 七个登记口都没有异步 setup、多份 undo 或独立 settlement 边界。通用规范化会在没有现有消费者需要它时重复 Cordis 的生命周期 machinery。 +**接受完整的 Cordis `Effect` union。** 七个登记口都不涉及异步 setup、多份 undo 或独立结算边界。若没有现有消费方需要,通用规范化只会重复实现 Cordis 的生命周期机制。 **暴露 `ScopedLayers.values()`、`ScopedLayers.keys()` 或全局放行谓词。** 这些操作会编码消费方特有的活遍历或物化策略,以及过滤策略。直接遍历条目表可保留显式的活语义,`merge()` 覆盖共享的命名遮蔽操作,而 `ToolRegistry` 继续保有功能更丰富的私有解析器。 @@ -111,16 +111,16 @@ export class AnonymousEntries { ## 后果 - 支持作用域的注册表各自通过一个聚合层表达状态,并复用相同的构造、属主、回滚、通知和回收编排。各注册表仍各自保有领域特有的校验、诊断、过滤、求值和观察者策略。 -- 公开读取接口保持狭窄:直接遍历条目表可保留显式的活语义,`merge()` 是唯一共享的物化遮蔽操作。异构的 `ScopeLayer` 不具备整层 `values()` 契约。 -- helper 刻意保持同步。未来的登记若需要异步 setup 或多份分别拥有属主的 undo,必须先明确属主与 settlement 边界,再拓宽这项契约。 -- action 必须在保留贡献前抛错,或者为自己保留的一切返回 undo;helper 无法修复超出这项契约的变更。提供的条目操作是原子的,迁移后的注册表会在插入前执行可能失败的校验。 +- 公开读取接口保持狭窄:直接遍历条目表可保留显式的活语义,`merge()` 是唯一共享的物化遮蔽操作。异构的 `ScopeLayer` 不具备整层 `values()` 约定。 +- helper 刻意保持同步。未来的登记若需要异步 setup 或多份分别拥有属主的 undo,必须先明确属主与 settlement 边界,再拓宽这项约定。 +- action 必须在保留贡献前抛错,或者为自己保留的一切返回 undo;helper 无法修复超出这项约定的变更。提供的条目操作是原子的,迁移后的注册表会在插入前执行可能失败的校验。 - 专属层会一直保持已分配状态,直到其聚合内的所有表都为空。因此,销毁一个门面不会丢弃同一 scope 拥有的其他贡献。 -- 四个公开符号构成一项可复用的包契约。将 `EntryValues` 保持为内部接口,并把消费方策略留在 helper 之外,可以限制兼容性范围。 +- 四个公开符号构成一项可复用的包约定。将 `EntryValues` 保持为内部接口,并把消费方策略留在 helper 之外,可以限制兼容性范围。 - 迁移不改变任何公开注册表行为,也不改变模型、人类、协议、持久化、配置或依赖图层面的任何输出。 ## 验证 - `dsh-scope` 单元测试覆盖全局构造、专属层延迟构造、非创建式读取、命名合并顺序与遮蔽、聚合回收、工厂与 action 失败清理、通知顺序与回滚、`notify: false`、effect 标签、原始 disposer 身份、幂等拆除、调用方提供的重名错误、相同匿名值的独立登记、活迭代器,以及表清空后的 generation 脱离。 -- 工具、系统提示词和命令专项测试套件覆盖 restriction、保留传输处理、已知名称与可限制名称的一致性、guard 重入与自我替换、校验顺序、精确诊断、section 先遮蔽再求值、提供方快照成员关系、variable 重入与自我替换、隔离失败的命令观察者、冻结且有序的视图、直接执行和生命周期销毁。 +- 工具、系统提示词和命令专项测试套件覆盖 restriction、保留传输处理、已知名称与可限制名称的一致性、guard 重入与自我替换、校验顺序、精确诊断、section 先遮蔽再求值、提供方快照成员关系、variable 重入与自我替换、隔离失败的命令观察者、冻结且经过排序的视图、直接执行和生命周期销毁。 - 作用域核心数据的类型等价性检查将 `ScopeLayer` 文档与其源声明绑定。仓库级的文档、模块图、构建、hygiene、覆盖率与构建产物门禁会覆盖包根导出与包边界。 - 现有 ACP(Agent Client Protocol)、headless 和 TUI 无密钥快照继续作为工具 schema 与提示词组装的回归边界;人类命令由 TUI 覆盖。实现不会更新任何预期 transcript(文本记录)。 diff --git a/.agents/notes/implemented/architecture/2026-07-14-provider-routed-llm-adapters.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-14-provider-routed-llm-adapters.i18n.yaml index c34acd2db1..2d39db2332 100644 --- a/.agents/notes/implemented/architecture/2026-07-14-provider-routed-llm-adapters.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-14-provider-routed-llm-adapters.i18n.yaml @@ -1,6 +1,6 @@ # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: -# pnpm run verify-translation-pairing --write -2026-07-14-provider-routed-llm-adapters.md: 1bd9197667f6e49c5025c98b4a77500f78595c2b -2026-07-14-provider-routed-llm-adapters.zh.md: 4d57f2cb33ac296500a4a19771ea493621ff93f6 +# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-14-provider-routed-llm-adapters.md +2026-07-14-provider-routed-llm-adapters.md: 9039334370ba5d71eb71879970c2e572a5b023df +2026-07-14-provider-routed-llm-adapters.zh.md: eff33496e1a61472534009533270f8f943ccc1f8 diff --git a/.agents/notes/implemented/architecture/2026-07-14-provider-routed-llm-adapters.md b/.agents/notes/implemented/architecture/2026-07-14-provider-routed-llm-adapters.md index 1bd9197667..9039334370 100644 --- a/.agents/notes/implemented/architecture/2026-07-14-provider-routed-llm-adapters.md +++ b/.agents/notes/implemented/architecture/2026-07-14-provider-routed-llm-adapters.md @@ -40,7 +40,7 @@ pi-ai's common stream options do not expose stop sequences. `dsh-llm-pi-ai` reje Assistant messages carry provider-neutral provenance containing the request's `provider` and `model`, plus an optional JSON-serializable adapter replay state. A successful `assistant/message` session event records this provenance and `deriveMessages()` returns it with the assistant message. User, system, context, and tool-result messages carry no assistant provenance. The provider/model fields are authoritative loop data; an adapter owns only its opaque replay-state payload. -A terminal successful `finish` chunk may carry replay state, and `BlockAssembler` retains it alongside usage and finish reason. The loop attaches it to the assistant provenance only when the post-`agent/step-result` content is structurally equal to the assembled provider output. A listener that rewrites content keeps the provider/model provenance but loses the now-stale replay state. Error and aborted responses do not produce a normal assistant message and therefore do not enter future model history. +A terminal successful `finish` chunk may carry replay state, and `BlockAssembler` retains it alongside usage and finish reason. The loop attaches that state to the assembled assistant provenance without exposing a response-rewrite hook. Error and aborted responses do not produce a normal assistant message and therefore do not enter future model history. The pi-ai replay state is a versioned, minimal projection of its successful `AssistantMessage`: source API/provider/model, response id/model, stop reason, and index-aligned text, thinking, and tool-call signatures. It does not duplicate text or tool arguments already carried by Harness content blocks, and it omits diagnostics, timestamps, usage, and errors. On a later request, `LlmService` gives replay state to the target adapter only when the historical provider and target provider are currently owned by the same adapter instance. That adapter combines the logged Harness content with replay state when it can restore the historical response, and owns any required cross-model or cross-provider conversion. An adapter receiving replay state with an unknown version or mismatched block shape fails explicitly; a different adapter receives only provider-neutral content and provenance. @@ -84,7 +84,7 @@ The on-disk session format remains the pre-release pinned version `0`, with no c - Unit coverage exercises registry conflicts, request reconstruction, session validation, profile resolution, single-attempt option forwarding, native API selection including OpenAI Responses, conversion, replay validation, error mapping, caller cancellation, idle-timeout transport termination, content rewrites, and same-instance versus different-instance replay dispatch. - Keyless loop/session tests and ACP snapshots exercise durable provider/model metadata, resume and fork propagation, workflow/subagent overrides, and unchanged user-visible transcripts; the key-gated DeepSeek e2e retains real provider streaming and tool follow-up coverage. -- Public JSDoc, package READMEs, architecture and core-data-structure docs, generated catalogs, examples, session fixtures, and Python SDK pairs use provider/model targets consistently and are checked by the repository documentation and type-equivalence gates. +- Public JSDoc, package READMEs, architecture and subsystem docs, generated catalogs, examples, session fixtures, and Python SDK pairs use provider/model targets consistently and are checked by the repository documentation and type-equivalence gates. ## Risks diff --git a/.agents/notes/implemented/architecture/2026-07-14-provider-routed-llm-adapters.zh.md b/.agents/notes/implemented/architecture/2026-07-14-provider-routed-llm-adapters.zh.md index 4d57f2cb33..eff33496e1 100644 --- a/.agents/notes/implemented/architecture/2026-07-14-provider-routed-llm-adapters.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-14-provider-routed-llm-adapters.zh.md @@ -84,7 +84,7 @@ JSON-RPC 运行时显式接收 provider 与 model。仅当 `deepseek` 提供方 - 单元测试覆盖注册表冲突、请求重建、会话验证、配置解析、单次请求的选项转发、包括 OpenAI Responses 在内的原生 API 选择、转换、回放验证、错误映射、调用方取消、空闲超时导致的传输终止、内容重写,以及同一实例与不同实例间的回放分发。 - 无密钥的 agent loop/会话测试和 ACP 快照覆盖持久化 provider/model 元数据、恢复与 fork 传播、工作流/subagent 覆盖,以及不变的用户可见 transcript(文本记录);密钥门控的 DeepSeek e2e 测试保留真实提供方的流式输出与工具后续调用覆盖率。 -- 公共 JSDoc、package README、架构与核心数据结构文档、生成目录、示例、会话 fixture(测试前置数据)和 Python SDK 配对文档统一使用 provider/model 目标,并由仓库文档与类型等价门禁校验。 +- 公共 JSDoc、package README、架构与子系统文档、生成目录、示例、会话 fixture(测试前置数据)和 Python SDK 配对文档统一使用 provider/model 目标,并由仓库文档与类型等价门禁校验。 ## 风险 diff --git a/.agents/notes/implemented/architecture/2026-07-15-agent-initiator-scope.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-15-agent-initiator-scope.i18n.yaml index d5e16246fe..7f295cd363 100644 --- a/.agents/notes/implemented/architecture/2026-07-15-agent-initiator-scope.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-15-agent-initiator-scope.i18n.yaml @@ -1,6 +1,6 @@ # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: -# pnpm run verify-translation-pairing --write -2026-07-15-agent-initiator-scope.md: 69648100e76cfc212469854188d664357fec22f1 -2026-07-15-agent-initiator-scope.zh.md: 835d7a5b2ab6d2d6fce7971de4fd9d6c69e50d77 +# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-15-agent-initiator-scope.md +2026-07-15-agent-initiator-scope.md: 2f388ae1de3dd6583686e129a03f0cd76701e18d +2026-07-15-agent-initiator-scope.zh.md: a0e3638081d875adc2412191829ab84c8dcd697c diff --git a/.agents/notes/implemented/architecture/2026-07-15-agent-initiator-scope.md b/.agents/notes/implemented/architecture/2026-07-15-agent-initiator-scope.md index 69648100e7..2f388ae1de 100644 --- a/.agents/notes/implemented/architecture/2026-07-15-agent-initiator-scope.md +++ b/.agents/notes/implemented/architecture/2026-07-15-agent-initiator-scope.md @@ -12,7 +12,7 @@ Deep process-local infrastructure sometimes needs a trusted initiating Agent bel ## Decision -The mandatory `ctx.agents` service uses Node `AsyncLocalStorage` to carry the initiating Agent. It stores the exact `Agent` directly rather than introducing a one-field frame; a separate private run token records nested boundary lineage only for teardown bookkeeping and carries no identity. The [core-data catalog](../../../../docs/core-data-structures/core.md#initiating-agent) identifies the carried type. +The mandatory `ctx.agents` service uses Node `AsyncLocalStorage` to carry the initiating Agent. It stores the exact `Agent` directly rather than introducing a one-field frame; a separate private run token records nested boundary lineage only for teardown bookkeeping and carries no identity. The [core-data catalog](../../../../docs/subsystems/core.md#initiating-agent) identifies the carried type. `currentInitiator()` reads optionally, `requireInitiator()` throws `no initiating agent is active`, and `withInitiator(agent, operation)` preserves the operation's exact synchronous value or Promise. `withoutInitiator(operation)` establishes a clearing boundary for work that must not inherit an Agent. Session remains derived as `agent.session`; turn, step, tool call, `signal`, model, `cwd`, sandbox, and authorization stay with their existing owners. diff --git a/.agents/notes/implemented/architecture/2026-07-15-agent-initiator-scope.zh.md b/.agents/notes/implemented/architecture/2026-07-15-agent-initiator-scope.zh.md index 835d7a5b2a..a0e3638081 100644 --- a/.agents/notes/implemented/architecture/2026-07-15-agent-initiator-scope.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-15-agent-initiator-scope.zh.md @@ -6,13 +6,13 @@ Status: implemented ## 问题 -Harness 中存在两种有用但不同的上下文概念。Cordis `Context` 负责选择服务、注册归属和生命周期;`agent.ctx` 是一个存活 Agent 所拥有的扁平注册作用域。Agent 与会话身份描述的则是异步操作主体。若把根 `ctx.agent` 改成「当前正在运行的 Agent」,就会混淆这两种含义,并在单进程并发驱动多个 Agent 时失效。 +harness 中存在两种有用但不同的上下文概念。Cordis `Context` 负责选择服务、注册归属和生命周期;`agent.ctx` 是一个存活 Agent 所拥有的扁平注册作用域。Agent 与会话身份描述的则是异步操作主体。若把根 `ctx.agent` 改成「当前正在运行的 Agent」,就会混淆这两种含义,并在单进程并发驱动多个 Agent 时失效。 进程内深层基础设施有时需要在显式传递的循环、工具及请求参数之下获取可信的发起 Agent,例如宿主感知传输层、追踪辅助函数、日志器或网关客户端。要求每个私有辅助函数都转发 `agent` 会造成重复,而进程级可变槽会在跨 `await` 时发生并发错误。模型可见参数也不适用,因为模型不得选择可信的会话或路由请求头。该载体归 Agent 服务所有,而非模型可见的可选上下文。 ## 决策 -必需的 `ctx.agents` 服务使用 Node `AsyncLocalStorage` 携带发起 Agent。它直接存储同一个 `Agent`,不引入只有一个字段的帧;另一个私有运行标记只记录嵌套边界的谱系,供 teardown 记账使用,不携带身份。[核心数据目录](../../../../docs/core-data-structures/core.md#initiating-agent)标明了所携带的类型。 +必需的 `ctx.agents` 服务使用 Node `AsyncLocalStorage` 携带发起 Agent。它直接存储同一个 `Agent`,不引入只有一个字段的帧;另一个私有运行标记只记录嵌套边界的谱系,供 teardown 记账使用,不携带身份。[核心数据目录](../../../../docs/subsystems/core.md#initiating-agent)标明了所携带的类型。 `currentInitiator()` 用于可选读取,`requireInitiator()` 抛出 `no initiating agent is active`,`withInitiator(agent, operation)` 保留操作返回的同步值或 Promise 本身。`withoutInitiator(operation)` 会建立清空边界,供不得继承 Agent 的工作使用。会话仍通过 `agent.session` 推导;轮次、步骤、工具调用、`signal`、模型、`cwd`、沙箱和授权继续由现有归属方管理。 @@ -20,21 +20,21 @@ Harness 中存在两种有用但不同的上下文概念。Cordis `Context` 负 因此,并发驱动使用彼此独立的存储。子驱动的异步延续携带子 Agent;`withInitiator()` 返回后,调用方立即恢复之前的存储,而活动运行计数仍持续跟踪返回的 Promise,直到其结束。创建、持久化加载和尚未发布的 `setup(agentCtx)` 位于子驱动边界之外:由父 Agent 发起的创建使用父身份,而 `agentCtx.agent` 显式标识子 Agent。 -隐式身份不会取代显式契约。`ToolExecution.agent`、`AssembleContext.agent`、`GenerateOptions.sessionId`、任务归属、父子请求、`ctx.agent`、`agentCtx.agent`、审批与 hook 主体、`cwd` 选择、取消、worker 和进程消息、持久化记录及协议身份都保持显式传递。远程边界会把所需身份写入类型化请求,因为 ALS 只在进程内有效。 +隐式身份不会取代显式约定。`ToolExecution.agent`、`AssembleContext.agent`、`GenerateOptions.sessionId`、任务归属、父子请求、`ctx.agent`、`agentCtx.agent`、审批与 hook 主体、`cwd` 选择、取消、worker 和进程消息、持久化记录及协议身份都保持显式传递。远程边界会把所需身份写入类型化请求,因为 ALS 只在进程内有效。 -`AgentRegistry` 管理一个有序的发起方生命周期。teardown 会先拒绝新边界;移除 `ctx.agents` 后,AgentLoop 等注入方开始排空,注册表随后等待活动的返回 Promise 边界,最后调用 `AsyncLocalStorage.disable()`。如果某个边界继承的异步调用链启动所属 Cordis fiber 的卸载,私有运行标记谱系会从排空范围中释放该嵌套边界链,从而避免 teardown 等待自身完成,同时继续排空无关边界。在普通排空期间,进行中代码可通过保留的服务引用继续调用 `currentInitiator()` 和 `requireInitiator()`;dispose 后,发起方方法会抛出 `agent initiator scope is disposed`。根 Context dispose 可能并发启动同级 fiber 的 teardown,因此除 Cordis 依赖顺序外仍必须统计活动边界。 +`AgentRegistry` 管理一个有序的发起方生命周期。teardown 会先拒绝新边界;移除 `ctx.agents` 后,AgentLoop 等注入方开始排空,注册表随后等待活动的返回 Promise 边界,最后调用 `AsyncLocalStorage.disable()`。如果某个边界继承的异步调用链启动所属 Cordis fiber 的卸载,私有运行标记谱系会从排空范围中释放该嵌套边界链,从而避免 teardown 等待自身完成,同时继续排空无关边界。在普通排空期间,进行中代码可通过保留的服务引用继续调用 `currentInitiator()` 和 `requireInitiator()`;dispose(资源释放)后,发起方方法会抛出 `agent initiator scope is disposed`。根 Context dispose 可能并发启动同级 fiber 的 teardown,因此除 Cordis 依赖顺序外仍必须统计活动边界。 -发起方作用域不负责管理脱离返回链的工作:注册表排空只跟踪 `withInitiator()` 或 `withoutInitiator()` 返回的 Promise。边界内创建的异步资源会继承其存储,直到自身结束或 ALS 被禁用;所属 seam 必须显式停止未纳入返回 Promise 的工作。Agent 所有前台工作会把完整生命周期纳入返回值,并保留显式取消契约。无关的定时器、队列和部署基础设施在 `withoutInitiator(operation)` 下启动;队列、worker、进程和协议边界必须序列化身份,不能期待 ALS 传播。 +发起方作用域不负责管理脱离返回链的工作:注册表排空只跟踪 `withInitiator()` 或 `withoutInitiator()` 返回的 Promise。边界内创建的异步资源会继承其存储,直到自身结束或 ALS 被禁用;所属 seam 必须显式停止未纳入返回 Promise 的工作。Agent 所属的前台工作会把完整生命周期纳入返回值,并保留显式取消约定。无关的定时器、队列和部署基础设施在 `withoutInitiator(operation)` 下启动;队列、worker、进程和协议边界必须序列化身份,不能期待 ALS 传播。 宿主感知的传输层可以从 `ctx.agents.requireInitiator().session.id` 推导由部署方拥有的 `X-Harness-Session-Id` 等请求头;模型可见 schema 和参数中不包含该请求头。本决策不让现有生产 MCP 或 Web 传输层采用此请求头。测试替身传输层用于证明可信边界,而不会把宿主路由策略分配给现有的提供方无关 seam。 -本决策扩展 [Agent 注册作用域契约](2026-07-08-agent-scope-contexts.md)及其[运行时设计](2026-07-12-agent-scope-runtime-design.md),不会改变其中 `agent.ctx` 的静态含义。 +本决策扩展 [Agent 注册作用域约定](2026-07-08-agent-scope-contexts.md)及其[运行时设计](2026-07-12-agent-scope-runtime-design.md),不会改变其中 `agent.ctx` 的静态含义。 ## 验证 -Agent 服务测试锁定可选与必需读取、同步值和跨 realm Promise 的引用身份、内建 Promise 结束状态观察、并发、嵌套及清空边界、同步抛错或 Promise 拒绝后的恢复、普通与重入排空顺序及保留引用的错误。AgentLoop 集成测试锁定并发与嵌套驱动、无 Agent 调用、AgentRegistry 重启、根 Context 销毁,以及包内私有的循环和工具调度通过隐式查找完成。组合、模块图、构建及运行时闭包检查确保默认组合包、SDK 主干、Python 运行时闭包及直接 AgentLoop harness 通过 `ctx.agents` 完成接线,无需其他提供方。 +Agent 服务测试锁定可选与必需读取、同步值及跨 realm Promise 的精确身份、内建 Promise 结束状态观察、并发、嵌套及清空边界、同步抛错或 Promise 拒绝后的恢复、普通与重入排空顺序及保留引用的错误。AgentLoop 集成测试锁定并发与嵌套驱动、无 Agent 调用、AgentRegistry 重启、根 Context 销毁,以及包内私有的循环和工具调度通过隐式查找完成。组合、模块图、构建及运行时闭包检查确保默认组合包、SDK 主干、Python 运行时闭包及直接 AgentLoop harness 通过 `ctx.agents` 完成接线,无需其他提供方。 -测试替身形式的宿主感知传输层在内部推导 `X-Harness-Session-Id`,并验证工具 schema 与记录参数都不包含身份字段。服务有意不排空边界操作所返回 Promise 之外的异步工作;这类工作仍由所属方的显式停止契约管理。 +测试替身形式的宿主感知传输层在内部推导 `X-Harness-Session-Id`,并验证工具 schema 与日志中记录的参数都不包含身份字段。服务有意不排空边界操作所返回 Promise 之外的异步工作;这类工作仍由所属方的显式停止约定管理。 ## 考虑过的替代方案 @@ -46,9 +46,9 @@ Agent 服务测试锁定可选与必需读取、同步值和跨 realm Promise **保存命名帧或完整运行时帧。** 只有一个字段的 `{ agent }` 帧只是包装该值,而 Agent、会话、inbox、取消、轮次、步骤、工具执行和持久化已经有各自的真源。增加更多字段会产生陈旧快照和另一套生命周期;直接携带 `Agent`,由方法名标识边界,无需重复保存状态。 -**包含步骤级 `AbortSignal`、`cwd`、沙箱或授权。** 它们的生命周期及权限范围与驱动边界不一致,而且现有 seam 已经显式传递这些值。新增控制能力需要独立决策和嵌套生命周期契约。 +**包含步骤级 `AbortSignal`、`cwd`、沙箱或授权。** 它们的生命周期及权限范围与驱动边界不一致,而且现有 seam 已经显式传递这些值。新增控制能力需要独立决策和嵌套生命周期约定。 -**使用进程级 `currentAgent`。** 并发 Agent 和 subagent 会在异步延续执行之间相互覆盖,因此可变全局值只在 Harness 不具备的串行保证下才正确。 +**使用进程级 `currentAgent`。** 并发 Agent 和 subagent 会在异步延续执行之间相互覆盖,因此可变全局值只在 harness 不具备的串行保证下才正确。 **从模型可见参数推导身份。** 不能信任模型或用户输入来选择会话、租户或沙箱路由。 @@ -56,7 +56,7 @@ Agent 服务测试锁定可选与必需读取、同步值和跨 realm Promise ## 后果 -深层基础设施可以获得一个可信的进程内发起 Agent,而无需加宽现有工具和能力请求。并发及嵌套驱动会自动隔离,AgentLoop 不增加新的必需服务,HMR 或根 Context dispose 会在禁用 ALS 前完成排空。 +深层基础设施可以获得一个可信的进程内发起 Agent,而无需加宽现有工具和能力请求。并发及嵌套驱动会自动隔离,AgentLoop 不增加新的必需服务,HMR(热模块替换)或根 Context dispose 会在禁用 ALS 前达到完全停稳。 该依赖不会出现在函数签名中,并且携带一个具有控制能力的 Agent 对象。消费方必须将其限制在横切基础设施中,把隐式存在视为既不证明存活、也不授予权限,并保留显式取消和归属检查。ALS 还有常驻传播成本,也无法跨越 worker、进程、HTTP 或持久化队列边界。 diff --git a/.agents/notes/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.i18n.yaml index 89204b0a67..f38ba32c11 100644 --- a/.agents/notes/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.i18n.yaml @@ -1,6 +1,6 @@ # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: -# pnpm run verify-translation-pairing --write -2026-07-15-llm-model-catalog-and-acp-selection.md: 9edc723b0dfafeaf395eb9325373835138ddbc41 -2026-07-15-llm-model-catalog-and-acp-selection.zh.md: 677d9e2a200d488fa9fc27fc2a922dc8f1f871d1 +# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.md +2026-07-15-llm-model-catalog-and-acp-selection.md: 41174209d2c44bedb5dd0615c5f877ecebd43639 +2026-07-15-llm-model-catalog-and-acp-selection.zh.md: 43442487649f7a552d66bd66b64e0e5072f5e00b diff --git a/.agents/notes/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.md b/.agents/notes/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.md index 9edc723b0d..41174209d2 100644 --- a/.agents/notes/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.md +++ b/.agents/notes/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.md @@ -34,9 +34,9 @@ The ACP automation transport is not a catalog consumer. Its deployment config su ### Prompt/request consistency and durability -`installAgentLlmTarget` (in `dsh-agent`) installs scoped `system-prompt/assemble` and `agent/request` listeners for a front-door-owned target. Prompt assembly snapshots the selected pair once per step, overwrites the assembled `provider` and `model` variables after downstream prompt listeners, and the request listener applies that same snapshot after downstream request listeners. A selection during asynchronous assembly therefore starts on the next step rather than splitting prompt text from routing. Other call-config fields remain untouched. +`installModelSelection` (in `dsh-agent`) installs scoped `system-prompt/assemble` and `agent/request` listeners for a front-door-owned selection. Prompt assembly snapshots the selected pair once per step, overwrites the assembled `provider` and `model` variables after downstream prompt listeners, and the request listener applies that same snapshot after downstream request listeners. A selection during asynchronous assembly therefore starts on the next step rather than splitting prompt text from routing. Other call-config fields remain untouched. -The request header remains the durable source of truth. When a selected target is actually used, the existing full `request/header` snapshot records it, and a front door initializes its selection from the folded last request header before falling back to creation options. A selection that is never used by a request is intentionally in-memory only because it never became model-visible state. +The request header remains the durable source of truth. When a selection is actually used, the existing full `request/header` snapshot records it, and a front door initializes its selection from the folded last request header before falling back to creation options. A selection that is never used by a request is intentionally in-memory only because it never became model-visible state. ## Alternatives considered diff --git a/.agents/notes/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.zh.md b/.agents/notes/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.zh.md index 677d9e2a20..4344248764 100644 --- a/.agents/notes/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.zh.md @@ -8,11 +8,11 @@ Status: implemented ## 问题 -基于提供方路由的适配器允许每次请求选择 `provider + model`,但 `LlmService` 只暴露路由和流式调用。UI 无法发现已注册的提供方,也无法知道适配器愿意推荐哪些模型。因此,ACP 客户端收不到 `model` 会话配置项;即使请求接缝已经支持运行时切换,Zed、JetBrains 和 VS Code 集成仍没有模型列表。 +基于提供方路由的适配器允许每次请求选择 `provider + model`,但 `LlmService` 只暴露路由和流式调用。UI 无法发现已注册的提供方,也无法知道适配器愿意推荐哪些模型。因此,ACP 客户端收不到 `model` 会话配置项;即使请求 seam 已经支持运行时切换,Zed、JetBrains 和 VS Code 集成仍没有模型列表。 模型发现不能变成请求校验。手写 DeepSeek 适配器会把任意模型 ID 原样转发给公开或私有端点,而 pi-ai 的有限安装目录则是其自身请求解析的权威依据。将共享目录视为白名单,会破坏提供方路由需要保留的私有端点能力。 -ACP 选择还必须保留提供方维度。同一个模型 ID 可能存在于多个路由下;切换全局适配器或 agent 模板会让一个编辑器会话的选择泄漏到其他会话。Prompt 变量与请求路由必须同时变化;如果选择发生在异步 prompt 组装期间,不能让 `{{model}}` 表示一个模型、实际请求却到达另一个模型。 +ACP 选择还必须保留提供方维度。同一个模型 ID 可能存在于多个路由下;切换全局适配器或 agent(智能体)模板会让一个编辑器会话的选择泄漏到其他会话。提示词变量与请求路由必须同时变化;如果选择发生在异步提示词组装期间,不能让 `{{model}}` 表示一个模型、实际请求却到达另一个模型。 ## 决策 @@ -20,7 +20,7 @@ ACP 选择还必须保留提供方维度。同一个模型 ID 可能存在于多 `LlmAdapter` 增加 `providerInfo(provider)` 与异步 `listModels(provider)` 方法。其提供方无关结果分别为 `LlmProviderInfo { id, name }` 和 `LlmModelInfo { provider, id, name, description? }`。默认实现以路由名称作为提供方名称,并且不展示模型,从而保持现有适配器行为。 -`LlmService.listProviders()` 按注册顺序返回分离后的元数据。`LlmService.listModels(provider)` 委托给路由所有者,校验非空 ID 和名称,并在提供方不匹配或模型 ID 重复时以 `INVALID_CATALOG` 失败,最后返回分离后的值。未知提供方仍以 `NO_ADAPTER` 失败。提供方元数据在 `registerAdapter()` 期间进行原子校验,错误展示记录不会留下部分注册。 +`LlmService.listProviders()` 按注册顺序返回元数据副本。`LlmService.listModels(provider)` 委托给路由所有者,校验非空 ID 和名称,并在提供方不匹配或模型 ID 重复时以 `INVALID_CATALOG` 失败,最后返回值的副本。未知提供方仍以 `NO_ADAPTER` 失败。提供方元数据在 `registerAdapter()` 期间进行原子校验,错误展示记录不会留下部分注册。 目录成员关系仅提供建议。它驱动选择器与诊断,但不会改变 `stream()` 路由,也不会拒绝原本有效的请求。提供方所有权仍然具有排他性并绑定生命周期;模型 ID 仍是请求时传给适配器的输入。 @@ -32,11 +32,11 @@ ACP 选择还必须保留提供方维度。同一个模型 ID 可能存在于多 ACP 自动化传输层不是目录消费方。它通过部署配置为新创建的 agent 提供一个可选的提供方/模型目标,不展示模型选择器或配置选项接口。 -### Prompt/请求一致性与持久化 +### 提示词/请求一致性与持久化 -`installAgentLlmTarget`(位于 `dsh-agent`)为前门拥有的目标安装 agent 作用域的 `system-prompt/assemble` 与 `agent/request` 监听器。Prompt 组装在每个 step 对所选组合做一次快照,在下游 prompt 监听器之后覆写组装出的 `provider` 与 `model` 变量;请求监听器在下游请求监听器之后应用同一快照。因此,发生在异步组装期间的选择会从下一个 step 生效,而不会让 prompt 文本与路由分裂。其他调用配置字段保持不变。 +`installModelSelection`(位于 `dsh-agent`)为前门拥有的选择安装 agent 作用域的 `system-prompt/assemble` 与 `agent/request` 监听器。提示词组装在每个步骤对所选组合做一次快照,在下游提示词监听器之后覆写组装出的 `provider` 与 `model` 变量;请求监听器在下游请求监听器之后应用同一快照。因此,发生在异步组装期间的选择会从下一个步骤生效,而不会让提示词文本与路由分裂。其他调用配置字段保持不变。 -请求头仍是持久化的事实来源。当所选目标真正被使用时,现有的完整 `request/header` 快照会记录它;前门先从折叠后的最后一个请求头初始化其选择,然后才回退到创建选项。从未被请求使用的选择有意只保留在内存中,因为它从未成为模型可见状态。 +请求头仍是持久化的真源。当某个选择真正被使用时,现有的完整 `request/header` 快照会记录它;前门先从折叠后的最后一个请求头初始化其选择,然后才回退到创建选项。从未被请求使用的选择有意只保留在内存中,因为它从未成为模型可见状态。 ## 考虑过的替代方案 @@ -46,17 +46,17 @@ ACP 自动化传输层不是目录消费方。它通过部署配置为新创建 **把选择存进 `AgentOptions` 或 `LlmService`。** 它们是创建级或部署级对象。改动它们会把并发会话耦合在一起,并绕过有日志记录的 `agent/request` 替换路径。 -**立即持久化一个新的模型选择会话事件。** 未被使用的 UI 选择尚未影响任何模型请求。在目标被消费时记录现有请求头,既保持“模型可见当且仅当有日志”的规则,又不会引入第二个事实来源。 +**立即持久化一个新的模型选择会话事件。** 未被使用的 UI 选择尚未影响任何模型请求。在目标被消费时记录现有请求头,既保持「模型可见当且仅当有日志」的规则,又不会引入第二个真源。 ## 结果 -- 任意适配器都能暴露动态模型列表,无需把提供方库类型泄漏到核心接缝。 -- 目录消费者必须把缺失理解为“未展示”,而不是“请求无效”。 +- 任意适配器都能暴露动态模型列表,无需把提供方库类型泄漏到核心 seam。 +- 目录消费方必须把缺失理解为「未展示」,而不是「请求无效」。 - pi-ai 适配器会暴露其已安装的提供方目录;手写 DeepSeek 部署显式列出已知选项,同时保留对任意模型的支持。 - 面向人类的目录消费方拥有各自的选择交互。ACP 使用固定部署目标,不会为模型发现扩大协议范围。 - 请求头与基于提供方路由的会话形态保持兼容;不需要新的 JSONL 事件或格式版本。 -- 目录读取可以是异步的,且每个调用方都会收到分离后的值。 +- 目录读取可以是异步的,且每个调用方都会收到值的独立副本。 ## 测试 -单元测试覆盖目录分离与错误元数据、pi-ai 和 DeepSeek 目录投影、提供方/模型请求路由,以及 prompt 变量对齐;按 agent 的隔离来自监听器安装在 agent 作用域上下文这一事实。ACP 传输测试独立验证固定提供方/模型的转发行为;TUI 套件覆盖选择器交互与基于请求头的恢复。 +单元测试覆盖目录值副本与格式错误的元数据、pi-ai 和 DeepSeek 目录投影、提供方/模型请求路由,以及提示词变量对齐;监听器安装在 agent 作用域的上下文中,因此能够实现 agent 间隔离。ACP 传输测试独立验证固定提供方/模型的转发行为;TUI 套件覆盖选择器交互与基于请求头的恢复。 diff --git a/.agents/notes/implemented/architecture/2026-07-15-lsp-capability-seam.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-15-lsp-capability-seam.i18n.yaml index 005f23b151..ebf474f78b 100644 --- a/.agents/notes/implemented/architecture/2026-07-15-lsp-capability-seam.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-15-lsp-capability-seam.i18n.yaml @@ -1,6 +1,6 @@ # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: -# pnpm run verify-translation-pairing --write -2026-07-15-lsp-capability-seam.md: d96b3a9c5139c1455a51f4fff793293d7b5a11c0 -2026-07-15-lsp-capability-seam.zh.md: 54dd32e46dded5722dda910e9138879d3f99de07 +# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-15-lsp-capability-seam.md +2026-07-15-lsp-capability-seam.md: 63cec0a4e349ffc5be27a84e955b15e9168f898b +2026-07-15-lsp-capability-seam.zh.md: fa82e29e0252b612ae38357c363478f1cbad9ead diff --git a/.agents/notes/implemented/architecture/2026-07-15-lsp-capability-seam.md b/.agents/notes/implemented/architecture/2026-07-15-lsp-capability-seam.md index d96b3a9c51..63cec0a4e3 100644 --- a/.agents/notes/implemented/architecture/2026-07-15-lsp-capability-seam.md +++ b/.agents/notes/implemented/architecture/2026-07-15-lsp-capability-seam.md @@ -62,7 +62,7 @@ interface LspProviderQuery extends LspQueryRequest { } type LspQueryResult = - | { readonly kind: 'locations'; readonly locations: readonly { readonly uri: string; readonly range: LspRange }[]; readonly resolvedWorkspaceRoot: string } + | { readonly kind: 'locations'; readonly locations: readonly { readonly uri: string; readonly range: LspRange }[]; readonly resolvedWorkspaceUri: string } | { readonly kind: 'hover'; readonly hover: { readonly contents: string; readonly range?: LspRange } | null } interface LspProvider { @@ -77,9 +77,9 @@ interface LspService { } ``` -Mapping keys normalize to lowercase, leading-dot extensions selected from `filePath`'s final extension; language ids only synchronize documents. Seam positions and ranges are zero-based UTF-16. `findReferences` always includes declarations: providers enforce this internally, the local mapping sets `context.includeDeclaration: true`, and callers get no flag. Closed result unions normalize navigation to locations and hover to content or `null`; navigation results carry the provider's resolved workspace root so consumers relativize file URIs in the same canonical namespace. The seam exposes no protocol types, process or document controls, or generic request escape hatch. +Mapping keys normalize to lowercase, leading-dot extensions selected from `filePath`'s final extension; language ids only synchronize documents. Seam positions and ranges are zero-based UTF-16. `findReferences` always includes declarations: providers enforce this internally, the local mapping sets `context.includeDeclaration: true`, and callers get no flag. Closed result unions normalize navigation to locations and hover to content or `null`; navigation results carry the provider's canonical workspace URI so consumers relativize file URIs in the execution world's namespace. The seam exposes no protocol types, process or document controls, or generic request escape hatch. -`dsh-lsp-local` owns host files, server configuration, JSON-RPC, process and transient-document state, and protocol translation; it depends on `dsh-lsp` and Node APIs, not `dsh-fs`. The server-table key is its provider id. The plugin resolves every server-local setting before registration, rolls back earlier registrations if a later mapping is invalid or conflicts, and retains an independent process pool per provider. `dsh-tool-lsp` runtime-injects only `tools`, `lsp`, and `systemPrompt`, obtains the workspace from `exec.agent?.session.header.cwd` through a package-local `sessionCwd(exec)` helper matching the filesystem tools' lookup, and imports no provider. +`dsh-lsp-local` owns server configuration, JSON-RPC, process and transient-document state, and protocol translation. It reads through `ctx.fs` and launches through `ctx.subprocess`, depending on their interface packages rather than concrete providers; the [portable execution-world decision](2026-07-28-portable-execution-world-consumers.md) owns that pairing. The server-table key is its provider id. The plugin resolves every server-local setting before registration, rolls back earlier registrations if a later mapping is invalid or conflicts, and retains an independent process pool per provider. `dsh-tool-lsp` runtime-injects only `tools`, `lsp`, and `systemPrompt`, obtains the workspace from `exec.agent?.session.header.cwd` through a package-local `sessionCwd(exec)` helper matching the filesystem tools' lookup, and imports no provider. ## Model-facing contract @@ -98,7 +98,7 @@ interface LspToolInput { The tool requires `workspaceRoot` from session `header.cwd`, with no fallback; absence fails as `LSP_WORKSPACE_REQUIRED` before querying or startup. The local provider resolves relative paths against that root and accepts absolute paths directly; both forms are canonicalized and rejected before startup when the target is outside the canonical workspace. -Locations render as stable, file-grouped `path:line:character` entries. A `file:` URI accepted by Node `fileURLToPath()` becomes a relative path inside the workspace or an absolute path outside it; other URIs remain verbatim. `maxLocations` defaults to `100` and reports omitted items; `maxResultChars` defaults to `16_000` and bounds every complete rendered result, including its truncation metadata. Empty locations and `null` hover are successful no-result responses; missing or malformed server payloads fail with structured `LSP_MALFORMED_RESPONSE` errors. +Locations render as stable, file-grouped `path:line:character` entries without applying harness-host path rules. A valid `file:` URI becomes a relative path inside the provider's canonical workspace URI or a URI-derived absolute path outside it; malformed and non-`file:` URIs remain verbatim. `maxLocations` defaults to `100` and reports omitted items; `maxResultChars` defaults to `16_000` and bounds every complete rendered result, including its truncation metadata. Empty locations and `null` hover are successful no-result responses; missing or malformed server payloads fail with structured `LSP_MALFORMED_RESPONSE` errors. The transport-neutral presenter uses `{ card: 'generic', kind: 'search', title, locations: [{ path: file_path, line }] }` with an args-derived operation/cursor `title`. Because `FileLocation` has no character, follow-along focuses the input line while the title preserves the cursor; presentation remains pure. @@ -112,26 +112,26 @@ Provider disposal occurs outside tool execution, so `dsh-lsp-local` keeps `shutd ## Workspace, filesystem, and document synchronization -`dsh-lsp-local` canonicalizes and reads through Node APIs in the subprocess's host namespace. It rejects missing, non-regular, non-UTF-8, oversized, or canonical out-of-workspace sources and keeps one `O_NOFOLLOW | O_NONBLOCK` handle through validation and reading, so a FIFO with no writer cannot block before the regular-file check. It observes caller cancellation around each filesystem operation. It does not consume `ctx.fs` or emit `fs/observed`: only the LSP result is model-visible, so the query does not satisfy read-before-write policy. +`dsh-lsp-local` canonicalizes and reads through `ctx.fs` in the language server's execution world. It requires the workspace target to be a directory, rejects out-of-workspace sources through provider-owned containment, consumes `streamText`, and enforces `maxDocumentBytes` as chunks arrive; the provider retains regular-file validation and UTF-8 decoding while the protocol consumer owns its document limit. It fuses caller cancellation with provider disposal across each filesystem operation, tracks workspace lookups before they enter a queue, and awaits those lookups during disposal. It does not emit `fs/observed`: only the LSP result is model-visible, so the query does not satisfy read-before-write policy. The `read` tool is unsuitable source because its output is windowed, numbered, transcript-visible, and observed. Reading in `tool-lsp` would also assign provider-specific synchronization to the consumer and preclude non-local providers. The local provider uses a compatibility-first transient-open sequence for every query. It accepts legacy `textDocumentSync` `Full` or `Incremental`, or options with `openClose: true`; omitted, `None`, or explicitly incompatible synchronization fails as unsupported before `didOpen`. -1. Canonicalize and validate the host path, then read the current source with Node filesystem APIs. +1. Resolve and contain the source through `ctx.fs`, then stream its current text through the same provider while enforcing the document byte limit. 2. Send `textDocument/didOpen` with version `1`, full text, and the configured language id. Its write remains abortable; failure or cancellation invalidates the instance and awaits bounded process termination before the pool can reuse it. 3. Send the requested `textDocument/definition`, `textDocument/references`, `textDocument/implementation`, or `textDocument/hover` request. 4. If `didOpen` succeeded, attempt `textDocument/didClose` in `finally` after the request settles or aborts. A close-write failure does not replace the settled result or error, but invalidates the instance and awaits bounded process termination. Documents close after each call, so the first version needs no `didChange`, `didSave`, content cache, mutation listener, or document LRU. One abortable per-workspace provider queue serializes source-read/open/query/close lifecycles, so a waiting query reads current bytes only when its turn starts; the instance also keeps protocol lifecycles serialized. Distinct workspaces may run in parallel. The server's workspace index remains responsible for closed files reached from the source. -The canonical workspace `realpath` must be a directory and supplies process cwd, `rootUri`, the sole `workspaceFolders` entry, and pool identity; symlink aliases therefore share an instance. Result locations may be external, but an external path cannot become a query source. Remote, virtual, or independently sandboxed filesystems require another provider. +The canonical workspace target must be a directory. Its target key supplies pool identity, its process path supplies cwd, and its provider-owned `file:` URI supplies `rootUri` and the sole `workspaceFolders` entry; aliases share an instance when the filesystem provider resolves them to one key. Result locations may be external, but an external path cannot become a query source. A filesystem that cannot share paths with the mounted subprocess provider is a composition error, not a reason for another LSP package. ## Local server lifecycle and protocol behavior -`dsh-lsp-local` lazily single-flights one server per `(provider id, canonical workspace realpath)`. At load it resolves the executable after credential scrubbing and environment overrides, failing before registration if unavailable; server process launch stays lazy (first query spawns it) and uses no shell. `maxMessageBytes` defaults to `16_000_000`, `maxStderrBytes` to `1_000_000`, and `maxDocumentBytes` to `4_000_000`. A crash fails the active query without replay; a later query may replace the process. Each query starts at most one process, so the MVP has no cross-request restart counter. +`dsh-lsp-local` lazily single-flights one server per `(provider id, canonical workspace target)`. At load it calls `ctx.subprocess.resolveExecutable()` with the configured environment, failing before registration if unavailable; first query launches through raw protocol pipes with no shell and a bounded collected stderr tail. `maxMessageBytes` defaults to `16_000_000`, `maxStderrBytes` to `1_000_000`, and `maxDocumentBytes` to `4_000_000`. A crash fails the active query without replay; a later query may replace the process. Each query starts at most one process, so the MVP has no cross-request restart counter. -Initialization advertises `general.positionEncodings: ['utf-16']`, `workspace: { workspaceFolders: true, configuration: true }`, `textDocument.hover.contentFormat: ['markdown', 'plaintext']`, and `linkSupport: true` for definition and implementation, with no dynamic registration. Returned operation and synchronization capabilities are authoritative. An omitted server `positionEncoding` defaults to `utf-16`; any other value is a protocol error. Configuration may supply initialization options and `workspace/configuration` responses, but the client rejects `workspace/applyEdit` and never executes commands or edits. +Initialization uses `processId: null` because the client and server may inhabit different process namespaces. It advertises `general.positionEncodings: ['utf-16']`, `workspace: { workspaceFolders: true, configuration: true }`, `textDocument.hover.contentFormat: ['markdown', 'plaintext']`, and `linkSupport: true` for definition and implementation, with no dynamic registration. Returned operation and synchronization capabilities are authoritative. An omitted server `positionEncoding` defaults to `utf-16`; any other value is a protocol error. Configuration may supply initialization options and `workspace/configuration` responses, but the client rejects `workspace/applyEdit` and never executes commands or edits. Navigation maps `Location` directly and `LocationLink` from `targetUri` plus `targetSelectionRange`. Positions must be nonnegative integers. Hover normalization accepts only valid `MarkupContent` and `MarkedString` shapes, preserves string values, renders language-tagged values as fenced code, and joins arrays with one blank line. The model-facing tool applies `maxResultChars` after rendering. @@ -143,7 +143,7 @@ Symbols are deferred because they need different schemas and overlap read/search Diagnostics need separate freshness, accumulation, and transcript rules. Mutations such as rename, code actions, and formatting require separate tools with preview, permission, and write-policy integration. -The local provider trusts its configured server and claims no sandbox confinement. Supporting untrusted binaries requires a later process/filesystem contract for workspace reads plus private cache and temporary writes; restricted, remote, or virtual workspaces require another provider. +The provider trusts its configured server. Its filesystem visibility and process confinement are exactly those of the mounted execution world; LSP adds no independent sandbox policy. ## Alternatives considered @@ -157,7 +157,7 @@ The local provider trusts its configured server and claims no sandbox confinemen **Wrap the signal in a per-seam execution-context object.** Web passes a bare `AbortSignal`; wrapping this single field would add unexplained asymmetry. `query()` gains a context object only when another field requires it. -**Read through `ctx.fs` or the `read` tool.** This could mix the document with a server index from another filesystem namespace; tool output is also windowed, numbered, and observed. The host-local provider reads unobserved full text beside its subprocess. +**Read through the model-facing `read` tool.** Rejected because tool output is windowed, numbered, transcript-visible, and observed. The provider consumes streamed full text directly through the same `ctx.fs` execution world used by its subprocess. **Keep documents open.** Mirroring edits requires version ownership, all-path `didChange`, HMR recovery, eviction, and stale-state rules. Transient opens avoid that MVP state machine. @@ -180,7 +180,7 @@ The local provider trusts its configured server and claims no sandbox confinemen - Synchronization tests pin UTF-16 negotiation and conversion, supported and rejected `textDocumentSync` forms, blocked and failed open writes, balanced transient open/close, close-write failure, and malformed-response rejection. - Timeout tests pin one `TOOL_TIMEOUT` budget, unclassified upstream cancellation, no hidden seam deadline, and bounded awaited teardown. - Lifecycle tests pin startup single-flight, complete-lifecycle serialization with fresh queued source reads, cross-workspace parallelism, abortable queues, crash replacement without replay, failed-stdin teardown, and quiescent disposal. -- Host-filesystem tests pin session-cwd requirements, relative and absolute source containment through symlinks, document validation, file/non-file URI rendering, unformatted source, and no `fs/observed` event. +- Filesystem-host tests pin session-cwd requirements, provider-owned containment and URI rendering, bounded document reads, unformatted source, and no `fs/observed` event. - A keyless pinned TypeScript real-server e2e exercises all four operations; runnable configuration uses the same explicit provider mapping. - Snapshots cover model-visible schema, prompt, results, and omissions; a built-artifact smoke test covers framing and cleanup. - Package and architecture docs cover configuration, security boundaries, and search/read guidance; the new `packages/lsp/` group is added to the AGENTS.md repository-layout block, the packages/README.md group table, and architecture.md in the same change. @@ -195,4 +195,4 @@ Extension ownership is exclusive within one runtime. Two providers cannot both c UTF-16 cursor columns are exact for the protocol but difficult for a model to count around non-BMP characters. Invalid or off-symbol positions may produce empty results, so error text and prompt examples must explain the coordinate convention without encouraging broad LSP use. -Direct Node access aligns the query snapshot with the server index but bypasses `ctx.fs` and its policy. Canonical containment rejects source files outside the workspace; a trusted server may still read the workspace and use caches. The first implementation therefore requires trusted host-local deployment and provides no sandbox guarantee. +The paired filesystem/subprocess providers align the query snapshot with the server index but do not make a trusted language server safe. Canonical containment rejects query sources outside the workspace at resolution time, but stream opening does not add stable-handle identity across a concurrent path replacement; the server itself receives the execution world's configured authority and may read other paths or use caches. diff --git a/.agents/notes/implemented/architecture/2026-07-15-lsp-capability-seam.zh.md b/.agents/notes/implemented/architecture/2026-07-15-lsp-capability-seam.zh.md index 54dd32e46d..fa82e29e02 100644 --- a/.agents/notes/implemented/architecture/2026-07-15-lsp-capability-seam.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-15-lsp-capability-seam.zh.md @@ -8,7 +8,7 @@ Status: implemented harness 已具备文本搜索与文件读取能力,但二者都无法识别程序符号。文本匹配无法可靠地区分同名函数、跟踪导入别名、关联接口与具体实现,也无法报告推断类型。因此,agent(智能体)在修改代码前缺少人类通过编辑器语言服务器获得的语义导航能力。 -语言服务器协议(Language Server Protocol,LSP)支持分属三个职责方:模型需要稳定的查询 schema,harness 需要提供方选择与规范化结果,本地实现则负责进程、JSON-RPC、工作区、同步与文件系统行为。将三者合并会使模型契约绑定本地子进程,并阻碍远程或沙箱原生提供方。 +语言服务器协议(Language Server Protocol,LSP)支持分属三个职责方:模型需要稳定的查询 schema,harness 需要提供方选择与规范化结果,本地实现则负责进程、JSON-RPC、工作区、同步与文件系统行为。将三者合并会使模型约定绑定本地子进程,并阻碍远程或沙箱原生提供方。 许多语言服务器在查询文档已按当前文本打开时表现最佳。兼容的 agent 客户端必须限制这项状态、定义内部读取是否算作模型观察,并确保文档快照与服务器工作区索引位于同一文件系统命名空间。 @@ -32,7 +32,7 @@ harness 已具备文本搜索与文件读取能力,但二者都无法识别程 服务边界只公开 `query(request, signal?)`,因为没有字段需要实现层填充默认值:`workspaceRoot` 是必填项,`languageId` 来自注册映射,超时与结果限制由消费方负责。`query()` 执行选择与推导时不使用隐藏的 `??` 后备逻辑,因此没有需要 resolve 的可执行 spec。`dsh-tool-lsp` 校验模型参数,并只把 `exec.signal` 作为裸 `AbortSignal` 传递,与 web 一致,并使 `dsh-lsp` 不依赖 `dsh-tools`。提供方在选择前被移除时按不可用失败;之后的释放遵循已选提供方的取消生命周期,不改路由。 -预期契约如下: +预期约定如下: ```ts import type { Branded } from '@deepseek-ai/dsh-brand' @@ -62,7 +62,7 @@ interface LspProviderQuery extends LspQueryRequest { } type LspQueryResult = - | { readonly kind: 'locations'; readonly locations: readonly { readonly uri: string; readonly range: LspRange }[]; readonly resolvedWorkspaceRoot: string } + | { readonly kind: 'locations'; readonly locations: readonly { readonly uri: string; readonly range: LspRange }[]; readonly resolvedWorkspaceUri: string } | { readonly kind: 'hover'; readonly hover: { readonly contents: string; readonly range?: LspRange } | null } interface LspProvider { @@ -77,11 +77,11 @@ interface LspService { } ``` -映射键规范化为带前导点的小写扩展名,并按 `filePath` 的最后一个扩展名选择;语言 id 仅用于文档同步。服务边界中的位置和范围从零开始按 UTF-16 计数。`findReferences` 始终包含声明:提供方在内部执行该约束,本地映射设置 `context.includeDeclaration: true`,调用方不能配置。封闭结果联合将导航统一为位置,将 `hover` 统一为内容或 `null`;导航结果携带提供方解析后的工作区根目录,使消费方依据同一规范化根目录相对化文件 URI。服务边界不公开协议类型、进程或文档控制,也不提供通用请求逃生口。 +映射键规范化为带前导点的小写扩展名,并按 `filePath` 的最后一个扩展名选择;语言 id 仅用于文档同步。服务边界中的位置和范围从零开始按 UTF-16 计数。`findReferences` 始终包含声明:提供方在内部执行该约束,本地映射设置 `context.includeDeclaration: true`,调用方不能配置。封闭结果联合将导航统一为位置,将 `hover` 统一为内容或 `null`;导航结果携带提供方的规范工作区 URI,使消费方在执行世界的命名空间内相对化文件 URI。服务边界不公开协议类型、进程或文档控制,也不提供通用请求逃生口。 -`dsh-lsp-local` 负责主机文件、服务器配置、JSON-RPC、进程与临时文档状态和协议转换;它依赖 `dsh-lsp` 与 Node API,不依赖 `dsh-fs`。服务器表的键是提供方 id。插件在注册前解析每个服务器的本地设置;如果后续映射无效或发生冲突,插件会撤销此前的注册,并为每个提供方保留独立进程池。`dsh-tool-lsp` 在运行时只注入 `tools`、`lsp` 和 `systemPrompt`,通过包内的 `sessionCwd(exec)` 辅助函数从 `exec.agent?.session.header.cwd` 取得工作区,其取值方式与文件系统工具一致,也不导入提供方。 +`dsh-lsp-local` 负责服务器配置、JSON-RPC、进程与临时文档状态和协议转换。它通过 `ctx.fs` 读取,通过 `ctx.subprocess` 启动,只依赖二者的接口包而非具体提供方;[可移植执行环境决策](2026-07-28-portable-execution-world-consumers.md)负责定义这种配对。服务器表的键是提供方 id。插件在注册前解析每个服务器的本地设置;如果后续映射无效或发生冲突,插件会撤销此前的注册,并为每个提供方保留独立进程池。`dsh-tool-lsp` 在运行时只注入 `tools`、`lsp` 和 `systemPrompt`,通过包内的 `sessionCwd(exec)` 辅助函数从 `exec.agent?.session.header.cwd` 取得工作区,其取值方式与文件系统工具一致,也不导入提供方。 -## 面向模型的契约 +## 面向模型的约定 单一 `lsp` 工具接受以下参数: @@ -98,7 +98,7 @@ interface LspToolInput { 工具必须从会话 `header.cwd` 取得 `workspaceRoot`,没有后备值;缺失时在查询或启动前以 `LSP_WORKSPACE_REQUIRED` 失败。本地提供方基于根目录解析相对路径并直接接受绝对路径;两种路径都会进行规范化,如果目标位于规范工作区外,则在启动前拒绝。 -位置按文件稳定分组并渲染为 `path:line:character`。Node `fileURLToPath()` 可接受的 `file:` URI 在工作区内转换为相对路径,在工作区外转换为绝对路径;其他 URI 保持原样。`maxLocations` 默认值为 `100`,并报告省略的条目;`maxResultChars` 默认值为 `16_000`,并限制每个完整渲染结果,其中包括截断元数据。空位置与 `null` hover 是成功的无结果响应;服务器载荷缺失或格式错误时,以结构化 `LSP_MALFORMED_RESPONSE` 错误失败。 +位置在不应用 harness 宿主路径规则的情况下按文件稳定分组并渲染为 `path:line:character`。有效的 `file:` URI 落在提供方的规范工作区 URI 内时转换为相对路径,位于其外时转换为从 URI 派生的绝对路径;格式错误的 URI 与非 `file:` URI 保持原样。`maxLocations` 默认值为 `100`,并报告省略的条目;`maxResultChars` 默认值为 `16_000`,并限制每个完整渲染结果,其中包括截断元数据。空位置与 `null` hover 是成功的无结果响应;服务器载荷缺失或格式错误时,以结构化 `LSP_MALFORMED_RESPONSE` 错误失败。 与传输方式无关的展示器使用 `{ card: 'generic', kind: 'search', title, locations: [{ path: file_path, line }] }`,`title` 由参数推导并标明操作与光标。由于 `FileLocation` 没有 character,跟随位置聚焦输入行,标题保留完整光标;展示保持纯函数。 @@ -112,26 +112,26 @@ interface LspToolInput { ## 工作区、文件系统与文档同步 -`dsh-lsp-local` 通过 Node API 在子进程所在的主机命名空间中规范化并读取文件。它拒绝缺失、非普通、非 UTF-8、超大或规范路径越出工作区的源文件,并在校验与读取期间保持同一个 `O_NOFOLLOW | O_NONBLOCK` 句柄,因此没有写入方的 FIFO 不会在普通文件校验前造成阻塞。它在每项文件系统操作前后检查调用方是否取消。它不使用 `ctx.fs` 或发送 `fs/observed`:只有 LSP 结果对模型可见,因此查询不满足写前读取策略。 +`dsh-lsp-local` 在语言服务器的执行环境中通过 `ctx.fs` 规范化并读取文件。它要求工作区目标是目录,使用提供方自有的 containment 拒绝工作区外的源文件,消费 `streamText`,并在分片到达时执行 `maxDocumentBytes` 上限;普通文件校验和 UTF-8 解码仍由提供方负责,文档上限则由协议消费方负责。它会针对每项文件系统操作合并调用方取消与提供方资源释放,跟踪尚未进入队列的工作区查找,并在资源释放期间等待这些查找结算。它不发送 `fs/observed`:只有 LSP 结果对模型可见,因此查询不满足写前读取策略。 `read` 工具的输出带窗口与行号,进入 transcript(文本记录)且已被观察,不适合作为源文件。在 `tool-lsp` 内读取还会把提供方专用同步职责交给消费方,并排除非本地提供方。 本地提供方对每次查询都采用兼容优先的临时打开流程。它接受旧式 `textDocumentSync` 的 `Full` 或 `Incremental`,也接受设置了 `openClose: true` 的选项;同步能力缺失、为 `None` 或明确不兼容时,在 `didOpen` 前以不支持错误失败。 -1. 规范化并校验主机路径,再使用 Node 文件系统 API 读取当前源文件。 +1. 通过 `ctx.fs` 解析源文件并检查其位于工作区内,再通过同一提供方流式读取当前文本,同时执行文档字节上限。 2. 发送 `textDocument/didOpen`,其中包含版本 `1`、完整文本和配置的语言 id。该写入仍可取消;写入失败或遭取消会使实例失效,并等待有界进程终止完成,池才能复用它。 3. 发送所请求的 `textDocument/definition`、`textDocument/references`、`textDocument/implementation` 或 `textDocument/hover` 请求。 4. 如果 `didOpen` 成功,则在请求完成或取消后于 `finally` 中尝试发送 `textDocument/didClose`。关闭写入失败不会覆盖已经确定的结果或错误,但会使实例失效,并等待有界进程终止完成。 每次调用后都关闭文档,因此第一版不需要 `didChange`、`didSave`、内容缓存、变更监听器或文档 LRU。每个工作区的提供方队列可取消,并串行执行源文件读取、打开、查询和关闭的完整生命周期,因此等待中的查询只在轮到它时才读取当前字节;实例也会串行执行协议生命周期。不同工作区可以并行。服务器工作区索引仍负责从源文件跳转到的已关闭文件。 -规范工作区 `realpath` 必须是目录,并用于进程 cwd、`rootUri`、唯一的 `workspaceFolders` 条目和进程池 identity;符号链接别名因此共享实例。结果位置可以在工作区外,但外部路径不能成为查询源。远程、虚拟或独立沙箱化文件系统需要另一种提供方。 +规范工作区目标必须是目录。其目标键提供进程池 identity,进程路径提供 cwd,归提供方所有的 `file:` URI 则提供 `rootUri` 和唯一的 `workspaceFolders` 条目;文件系统提供方将别名解析为同一键时,它们共享实例。结果位置可以在工作区外,但外部路径不能成为查询源。无法与挂载的子进程提供方共享路径的文件系统属于组合错误,不是另建 LSP 包的理由。 ## 本地服务器生命周期与协议行为 -`dsh-lsp-local` 按 `(provider id, canonical workspace realpath)` 懒启动一个服务器,并通过 single-flight 合并启动。插件加载时,它在清除凭据并应用环境变量覆盖后解析可执行文件;命令不可用时在注册前失败。服务器进程的启动保持懒执行(首次查询时才拉起),且不经过 shell。`maxMessageBytes` 默认值为 `16_000_000`,`maxStderrBytes` 默认值为 `1_000_000`,`maxDocumentBytes` 默认值为 `4_000_000`。崩溃使当前查询失败且不重放;后续查询可以替换进程。每次查询最多启动一个进程,因此 MVP 不设置跨请求重启计数器。 +`dsh-lsp-local` 按 `(provider id, canonical workspace target)` 懒启动一个服务器,并通过 single-flight 合并启动。插件加载时,它使用已配置的环境调用 `ctx.subprocess.resolveExecutable()`;命令不可用时在注册前失败。首次查询通过原始协议管道启动服务器,不经过 shell,并收集有界的 stderr 尾部。`maxMessageBytes` 默认值为 `16_000_000`,`maxStderrBytes` 默认值为 `1_000_000`,`maxDocumentBytes` 默认值为 `4_000_000`。崩溃使当前查询失败且不重放;后续查询可以替换进程。每次查询最多启动一个进程,因此 MVP 不设置跨请求重启计数器。 -初始化声明 `general.positionEncodings: ['utf-16']`、`workspace: { workspaceFolders: true, configuration: true }`、`textDocument.hover.contentFormat: ['markdown', 'plaintext']`,以及 definition 与 implementation 的 `linkSupport: true`,但不支持动态注册。服务器返回的操作与同步能力均为真源。服务器省略 `positionEncoding` 时默认为 `utf-16`;其他值均属于协议错误。配置可以提供初始化选项和 `workspace/configuration` 响应,但客户端拒绝 `workspace/applyEdit`,绝不执行命令或编辑。 +初始化使用 `processId: null`,因为客户端与服务器可能位于不同的进程命名空间。它声明 `general.positionEncodings: ['utf-16']`、`workspace: { workspaceFolders: true, configuration: true }`、`textDocument.hover.contentFormat: ['markdown', 'plaintext']`,以及 definition 与 implementation 的 `linkSupport: true`,但不支持动态注册。服务器返回的操作与同步能力均为真源。服务器省略 `positionEncoding` 时默认为 `utf-16`;其他值均属于协议错误。配置可以提供初始化选项和 `workspace/configuration` 响应,但客户端拒绝 `workspace/applyEdit`,绝不执行命令或编辑。 导航结果直接映射 `Location`,并将 `LocationLink` 的 `targetUri` 与 `targetSelectionRange` 映射为统一位置。位置必须是非负整数。`hover` 归一化只接受有效的 `MarkupContent` 和 `MarkedString` 结构,保留字符串值,把带语言标签的值渲染为围栏代码块,并以一个空行连接数组。面向模型的工具在渲染后应用 `maxResultChars`。 @@ -143,13 +143,13 @@ interface LspToolInput { 诊断需要独立的新鲜度、累积与 transcript 规则。重命名、代码操作和格式化等变更能力需要单独工具,并集成预览、权限和写入策略。 -本地提供方信任配置的服务器,不声称具备沙箱隔离。支持不受信任的二进制文件需要后续补充允许读取工作区并写入私有缓存与临时目录的进程/文件系统契约;受限、远程或虚拟工作区需要另一种提供方。 +提供方信任配置的服务器。其文件系统可见性与进程隔离完全取决于挂载的执行环境;LSP 不增加独立的沙箱策略。 ## 备选方案 **照搬 Claude Code 的统一 schema。** 它的光标操作验证了核心场景,但符号与调用层级需要不同参数。照搬九种操作会固化尚未验证的接口,因此本提案只对齐四种语义查询。 -**允许提供方注册工具。** 已加载服务器会控制模型 schema 和提示词,无法在本地与远程提供方之间维持统一契约。 +**允许提供方注册工具。** 已加载服务器会控制模型 schema 和提示词,无法在本地与远程提供方之间维持统一约定。 **公开任意 LSP 方法。** JSON-RPC 逃生口会泄露协议载荷,并允许未经评审的变更或命令执行;操作联合保持封闭。 @@ -157,7 +157,7 @@ interface LspToolInput { **将信号包装为每服务边界的执行上下文对象。** Web 传递裸 `AbortSignal`;仅包装这一个字段会造成无谓的不对称。只有另一个字段确有需要时,`query()` 才引入上下文对象。 -**通过 `ctx.fs` 或 `read` 工具读取。** 这可能把文档与另一文件系统命名空间中的服务器索引混合;工具输出还带窗口、行号且已被观察。host-local 提供方在子进程旁读取未观察的完整文本。 +**通过面向模型的 `read` 工具读取。**拒绝,因为工具输出带窗口与行号,会进入 transcript 且已被观察。提供方直接通过子进程所用的同一 `ctx.fs` 执行环境消费流式传输的完整文本。 **保持文档打开。** 镜像编辑需要版本归属、覆盖所有路径的 `didChange`、HMR 恢复、淘汰和陈旧状态规则。临时打开避免在 MVP 引入这套状态机。 @@ -180,7 +180,7 @@ interface LspToolInput { - 同步测试固定 UTF-16 协商与转换、受支持和被拒绝的 `textDocumentSync` 形式、打开写入阻塞与失败、配对的临时打开/关闭、关闭写入失败和错误响应拒绝。 - 超时测试固定一个 `TOOL_TIMEOUT` 预算、不对上游取消错误分类、服务边界无隐藏截止时间,以及受限且等待完成的清理。 - 生命周期测试固定启动 single-flight、完整生命周期串行化及排队查询读取最新源文件、跨工作区并行、可取消队列、崩溃后不重放的替换、stdin 失败后的进程拆除,以及释放后完全停稳。 -- 主机文件系统测试固定 session cwd 要求、符号链接下相对与绝对源路径的规范 containment、文档校验、file/non-file URI 渲染、无格式源文本和不发送 `fs/observed`。 +- 文件系统宿主测试固定 session cwd 要求、提供方自有的 containment 与 URI 渲染、有界文档读取、无格式源文本和不发送 `fs/observed`。 - 无密钥且固定版本的 TypeScript 真实服务器 e2e 覆盖四种操作;可运行配置使用同一项显式提供方映射。 - 快照覆盖模型可见 schema、提示词、结果和省略提示;构建产物冒烟测试覆盖分帧与清理。 - 包与架构文档覆盖配置、安全边界和搜索/读取指导;同一改动中,新的 `packages/lsp/` 包组要加入 AGENTS.md 的仓库布局块、packages/README.md 的分组表和 architecture.md。 @@ -195,4 +195,4 @@ interface LspToolInput { UTF-16 光标列与协议完全一致,但模型难以在包含非 BMP 字符的文本中准确计数。无效位置或不在符号上的位置可能返回空结果,因此错误文本和提示词示例必须说明坐标约定,同时避免鼓励模型广泛使用 LSP。 -直接访问 Node 文件系统会对齐查询快照与服务器索引,但绕过 `ctx.fs` 及其策略。规范路径 containment 会拒绝工作区外的源文件;受信任的服务器仍可读取工作区并使用缓存。因此,第一版要求受信任的 host-local 部署,不提供沙箱保证。 +配对的文件系统/子进程提供方会对齐查询快照与服务器索引,但不会因此使受信任的语言服务器变得安全。规范 containment 会在解析时拒绝工作区外的查询源,但打开流不会在路径并发替换期间额外保证稳定句柄身份;服务器本身获得执行环境所配置的权限,仍可读取其他路径或使用缓存。 diff --git a/.agents/notes/implemented/architecture/2026-07-15-replay-token-meter-service.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-15-replay-token-meter-service.i18n.yaml index dd16a5f327..80fe86f2bc 100644 --- a/.agents/notes/implemented/architecture/2026-07-15-replay-token-meter-service.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-15-replay-token-meter-service.i18n.yaml @@ -1,6 +1,6 @@ # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: -# pnpm run verify-translation-pairing --write -2026-07-15-replay-token-meter-service.md: 3496364663c1f73b8161461d1a229b19d9730c6d -2026-07-15-replay-token-meter-service.zh.md: 0bc4d9decac36bd5674cd0fb04f82fdcd277554e +# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-15-replay-token-meter-service.md +2026-07-15-replay-token-meter-service.md: c0f4b467ad0013dd4ac0a0301281b011ea8c261c +2026-07-15-replay-token-meter-service.zh.md: c1d81dc0e76ee687ced5c23d26197627551e1ced diff --git a/.agents/notes/implemented/architecture/2026-07-15-replay-token-meter-service.md b/.agents/notes/implemented/architecture/2026-07-15-replay-token-meter-service.md index 3496364663..c0f4b467ad 100644 --- a/.agents/notes/implemented/architecture/2026-07-15-replay-token-meter-service.md +++ b/.agents/notes/implemented/architecture/2026-07-15-replay-token-meter-service.md @@ -36,7 +36,7 @@ Automatic compaction uses one unified measurement for each threshold-and-retenti Compact policy has service-wide defaults: threshold ratio `0.8`, retained-tail ratio `0.16`, `summarizationProvider: ''`, `summarizationModel: ''`, `maxTokens: 8192`, `compactionRetries: 1`, `maxOverflowRetries: 1`, and `auto: true`. Top-level fields apply to every routed target; exact provider/model entries in `modelPolicies` partially override them. Pressure scales ratios against capacity resolved from the owning adapter, and `retainTokens` may replace `retainRatio`; retention must remain below the resulting threshold. The summarization provider and model must both be set or both be empty; an empty pair resolves the latest logged request target, then the `AgentOptions` pair. -Automatic pressure runs at `agent/post-step` and measures the canonical durable envelope produced under the provider/model actually selected by `agent/request`. A headerless session has no completed routed request to assess and produces no work; any routed target can use the singleton estimator. Canonical overflow recovery uses the same measurement for forced range selection and retries only after a proven surface replacement. +Automatic pressure runs at `agent/pre-step` before request derivation and measures the canonical durable envelope produced under the provider/model actually selected by the preceding `agent/request`. A headerless session has no completed routed request to assess and produces no work; any routed target can use the singleton estimator. Canonical overflow recovery uses the same measurement for forced range selection and retries only after a proven surface replacement. ## Testing diff --git a/.agents/notes/implemented/architecture/2026-07-15-replay-token-meter-service.zh.md b/.agents/notes/implemented/architecture/2026-07-15-replay-token-meter-service.zh.md index 0bc4d9deca..c1d81dc0e7 100644 --- a/.agents/notes/implemented/architecture/2026-07-15-replay-token-meter-service.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-15-replay-token-meter-service.zh.md @@ -6,17 +6,17 @@ Status: implemented ## 问题 -上下文压力并不只对压缩有用。压缩后端、溢出保护或未来的请求策略插件都可能需要回答同一个问题:持久请求消耗了多少 token?如果把该折叠逻辑留在 `dsh-compact-basic` 内部,就会重复实现回放逻辑,使未加载压缩的调用方无法使用计量,并诱使调用方复用陈旧的核算结果。 +上下文压力并不只对压缩(compaction)有用。压缩后端、溢出保护或未来的请求策略插件都可能需要回答同一个问题:持久请求消耗了多少 token?如果把该折叠逻辑留在 `dsh-compact-basic` 内部,就会重复实现回放逻辑,使未加载压缩的调用方无法使用计量,并诱使调用方复用陈旧的核算结果。 提供方 usage 也不是完整答案。它只描述某个精确请求信封下的一次成功调用,而当前表层之后还可能增长、缩小或被替换。会话也可能切换提供方与模型,旧日志可能缺少分片来源,usage 字段还会分别报告输入、缓存读取、缓存写入、输出与推理计数。因此,可用的服务必须把最新精确锚点与保守的启发式重新定价结合起来,并公开每个结果已经消费的日志修订号。 ## 决策 -### 一个具体的 LLM 家族服务 +### 一个具体的 LLM(大语言模型)家族服务 `@deepseek-ai/dsh-token-meter` 是 `packages/llm/` 下的单个具体包,并注册 `ctx.tokenMeter`。在第二种实现出现之前,它不会被拆成接口与后端。`TokenMeterService` 本身公开 `measure(session, requestHeader?)` 与 `estimateMessage(message)`;消费方直接调用这个单例服务。 -服务没有配置。估算采用固定的每 token 四个字符启发式规则,并加上结构开销。服务不提供模型 profile、容量设置、密度设置、分词器后端或语言专用策略。精确提供方/模型容量由独立的适配器查询拥有,具体见[路由模型上下文与压缩策略 Agent Note](2026-07-20-routed-model-context-and-compaction-policy.md)。 +服务没有配置。估算采用固定的每 token 四个字符启发式规则,并加上结构开销。服务不提供模型 profile、容量设置、密度设置、分词器后端或语言专用策略。对精确提供方/模型容量的查询由适配器单独负责,具体见[路由模型上下文与压缩策略 Agent Note](2026-07-20-routed-model-context-and-compaction-policy.md)。 ### 逐会话回放折叠 @@ -30,22 +30,22 @@ Usage 会对互不重叠的输入、缓存读取、缓存写入与输出 bucket ### compact-basic 消费计量,但不拥有计量 -`dsh-compact-basic` 要求 `ctx.tokenMeter`;`CompactService` 不增加 token 方法或类型。配置、区域事务与摘要器分别保留在独立模块中,服务自身注册自动监听器,而 `summarize()` 仍是唯一的子类 hook。单例计量器一致用于压力、保留、被遮蔽内容、来源以及非缩小摘要拒绝的定价。 +`dsh-compact-basic` 要求 `ctx.tokenMeter`;`CompactService` 不增加 token 方法或类型。配置、区域事务与摘要分别保留在独立模块中,服务自身注册自动监听器,而 `summarize()` 仍是唯一的子类钩子。单例计量器一致用于压力、保留、被遮蔽内容、来源以及非缩小摘要拒绝的定价。 自动压缩的每次阈值与保留联合决策只使用一次统一计量。区域事务会在追加持久 `compact/start` 锁后执行计量,在异步摘要完成后再次计量,随后比较分离的表层节点向量。期间发生的表层变更会阻止替换;`logRevision` 可以因无关的纯日志事实而推进,而不会使未变的选定范围失效。 压缩策略采用服务级默认值:阈值比例 `0.8`、保留尾部比例 `0.16`、`summarizationProvider: ''`、`summarizationModel: ''`、`maxTokens: 8192`、`compactionRetries: 1`、`maxOverflowRetries: 1` 与 `auto: true`。顶层字段适用于每个路由目标;`modelPolicies` 中的精确提供方/模型项可以部分覆盖这些字段。压力检查根据所属适配器解析的容量缩放比例,`retainTokens` 可以替代 `retainRatio`;保留值必须小于最终阈值。摘要提供方与模型必须同时设置或同时为空;空组合先解析最近记录的请求目标,再使用 `AgentOptions` 中的组合。 -自动压力检查运行在 `agent/post-step`,并计量 `agent/request` 实际所选提供方/模型产生的规范持久信封。没有请求头的会话尚无已完成的路由请求可供判断,因此不执行工作;任意路由目标都可使用这个单例估算器。规范化溢出恢复使用同一计量结果强制选择范围,并且只有在表层替换得到证明后才重试。 +自动压力检查在请求派生前运行于 `agent/pre-step`,并计量前一个 `agent/request` 实际所选提供方/模型产生的规范持久信封。没有请求头的会话尚无已完成的路由请求可供判断,因此不执行工作;任意路由目标都可使用这个单例估算器。规范化溢出恢复使用同一计量结果强制选择范围,并且只有在表层替换得到证明后才重试。 ## 测试 -单元测试覆盖固定估算、信封失效与锚点替换、回放边界、不可变快照、已路由压力、收敛、溢出 generation 证明与回滚。真实 Loader/Include fixture 验证零配置 token-meter 与 compact-basic 按依赖顺序加载的路径。 +单元测试覆盖固定估算、信封失效与锚点替换、回放边界、不可变快照、已路由压力、收敛、溢出 generation 证明与回滚。真实 Loader/Include fixture(测试前置数据)验证零配置 token-meter 与 compact-basic 按依赖顺序加载的路径。 ## 考虑过的替代方案 - **把估算保留在 `CompactService` 内**——不予采纳,因为计量拥有独立于压缩的消费方与回放语义;它还会强迫每个压缩器暴露同一套无关 API。 -- **立即把 token meter 拆成接口与启发式后端**——不予采纳,因为目前只有一种实现。单个具体服务保留未来接缝,同时避免推测性的包与配置。 +- **立即把 token meter 拆成接口与启发式后端**——不予采纳,因为目前只有一种实现。单个具体服务保留未来的 seam,同时避免推测性的包与配置。 - **把模型键控窗口与密度 profile 放进 meter**——不予采纳,因为回放估算不拥有模型路由或容量事实。路由所属适配器公开容量,compact-basic 则拥有消费方专用的阈值与保留策略。 - **保留独立的标量与表层计量**——不予采纳,因为消费方必须为一次决策执行两次读取并匹配修订号。仅读取标量可以避免在低于阈值时复制节点,但拆分 API 会在消费方引入竞态窗口;统一快照接受 O(surface) 复制成本,以换取结果一致性。 - **在不同信封之间移用提供方 usage**——不予采纳,因为模型、工具、前缀与调用配置都是请求事实。不匹配时会重新定价完整当前请求。 diff --git a/.agents/notes/implemented/architecture/2026-07-16-explicit-turn-cancellation.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-16-explicit-turn-cancellation.i18n.yaml index 11c3d9b5a2..f683189f93 100644 --- a/.agents/notes/implemented/architecture/2026-07-16-explicit-turn-cancellation.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-16-explicit-turn-cancellation.i18n.yaml @@ -1,6 +1,6 @@ # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: -# pnpm run verify-translation-pairing --write -2026-07-16-explicit-turn-cancellation.md: 15085a1da2cf183bace9957a4bedb3ea466aa472 -2026-07-16-explicit-turn-cancellation.zh.md: e945b0fea51bdbfee38048573c643b0fb8ecb685 +# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-16-explicit-turn-cancellation.md +2026-07-16-explicit-turn-cancellation.md: 2b7cb8cc77184edf1331764d28aefe748c1614a1 +2026-07-16-explicit-turn-cancellation.zh.md: 0b9a06c0ae340a41eab9d6bff6126996bfc63bcf diff --git a/.agents/notes/implemented/architecture/2026-07-16-explicit-turn-cancellation.md b/.agents/notes/implemented/architecture/2026-07-16-explicit-turn-cancellation.md index 15085a1da2..2b7cb8cc77 100644 --- a/.agents/notes/implemented/architecture/2026-07-16-explicit-turn-cancellation.md +++ b/.agents/notes/implemented/architecture/2026-07-16-explicit-turn-cancellation.md @@ -16,11 +16,11 @@ Agent owns the runtime-only `AgentCancelCause` union `{ kind: 'user' } | { kind: An interrupted live turn ends with the coarse durable `{ kind: 'aborted' }` outcome. The terminal event records what happened to the turn, while the runtime signal identifies who requested cancellation; it does not duplicate `user` or `parent` into replay. Session seed/load rejects legacy aborted records with a reason or any other extra field, so replay cannot reintroduce caller-owned cancellation detail. The process-local `agent/cancel-requested` notification is not durable; a future audit requirement uses a separate durable control-request event so a request and its eventual outcome remain distinct. Durable events contain no stack, signal, error object, free-form cancellation text, or backend-private detail. -AgentLoop privately owns one `TurnCancellation` per prospective turn. It installs the holder before notifying `agent/status = running`, retains its single `AbortController` through prompt processing, prompt assembly, every step, model and tool execution, continuation, and `agent/turn-stop`, then clears the exact holder immediately before publishing `turn/end`. Terminal event observers and the following durability flush therefore cannot cancel already-completed turn work even though driver status may remain `running` until the flush settles. Every participating method, event, and request value receives that same explicit signal; the next turn receives a fresh signal. +AgentLoop privately owns one `TurnCancellation` per prospective turn. It installs the holder before notifying `agent/status = running`, retains its single `AbortController` through inbox claim, `agent/pre-step`, prompt assembly, every step, model and tool execution, and `agent/turn-stopping`, then clears the exact holder immediately before publishing `turn/end`. Terminal event observers and the following durability flush therefore cannot cancel already-completed turn work even though driver status may remain `running` until the flush settles. Every participating method, event, and request value receives that same explicit signal; the next turn receives a fresh signal. -The driver keeps only a cause-less pre-run marker for queued work cancelled before a turn is claimed. An effective `cancel()` emits the observe-only `agent/cancel-requested` notification with its resolved typed cause before clearing queued and steering work or aborting the holder; notification failures cannot veto the stop, and an idle call emits nothing. Work synchronously queued by a notification observer is included in that clear, while work queued by a later signal abort observer belongs to the next turn. If a `running` listener synchronously cancels old work and sends a replacement, the driver discards the aborted holder and creates a fresh one for the replacement. Repeated cancellation is first-wins for the active holder, while later calls may still clear newly queued pending work. +The driver keeps only a cause-less pre-run marker for queued work cancelled before a turn is claimed. An effective `cancel()` emits the observe-only `agent/cancel-requested` notification with its resolved typed cause before clearing queued and steering work or aborting the holder; notification failures cannot veto the stop, and an idle call emits nothing. Work synchronously queued by a notification observer is included in that clear, while work queued by a later signal abort observer is latched and runs when the aborted activity converges to idle — a `disposed` cancel leaves it parked ([cancel-convergence wake latch](../bug-fix/2026-08-07-cancel-convergence-wake-latch.md)). If a `running` listener synchronously cancels old work and sends a replacement, the driver discards the aborted holder and creates a fresh one for the replacement. Repeated cancellation is first-wins for the active holder, while later calls may still clear newly queued pending work. -The explicit event signatures keep their positional form and place `signal` immediately before a waterfall's final `next`. Prompt submission, request configuration, step-result processing, continuation, and terminal stop join the pre-existing explicit signal seams for pre-step, session prefix, model generation, tool execution, approval, and subagent or workflow requests. Hook bridges must also supply `RunHookOptions.signal`, so a turn cancellation reaches the bash executor's process-group kill and join boundary. `SystemPrompt.assemble()` carries `signal?: AbortSignal` in `AssembleContext` because that object is an explicit request value that can also represent signal-less assembly outside a turn. Listeners may cooperate with the signal but must not retain it to control another turn. +The explicit event signatures pass a single payload object: agent-scoped events carry `agent` and `signal` in the payload with `next` last, and the remaining seams keep `signal` immediately before a waterfall's final `next`. `PreStepContext` and `RequestFailureContext` are retired, with their fields folded into the `agent/pre-step` and `agent/request-error` payloads ([payload-object events](2026-08-06-agent-event-payload-objects.md)). Pre-step entry, request configuration, request-error recovery, model generation, tool execution, approval, turn stopping, and subagent or workflow requests all receive the current signal. Hook bridges must also supply `RunHookOptions.signal`, so a turn cancellation reaches the bash executor's process-group kill and join boundary. `SystemPrompt.assemble()` carries `signal?: AbortSignal` in `AssembleContext` because that object is an explicit request value that can also represent signal-less assembly outside a turn. Listeners may cooperate with the signal but must not retain it to control another turn. `ctx.agents` continues to carry only the initiating Agent. Ambient Agent presence does not imply liveness, a current turn, or cancellation authority. The cause reader is private to the loop and states the machine-private slot invariant (only `cancel()` aborts a turn controller, always with a canonical frozen cause) instead of re-validating the reason structurally; no public helper reads a cause off an arbitrary signal. Concurrent Agents isolate both their initiator identities and their turn signals; a child driver shadows the parent initiator while its parent request signal still travels through the subagent seam. @@ -30,7 +30,7 @@ Cancellation remains cooperative. The loop checks interruption before and after ## Verification -Contract tests verify the typed caller union, frozen detachment, default and first-wins behavior, the coarse Session JSON round trip and legacy-record rejection, ACP `user`, in-process subagent `parent`, and disposal precedence. Loop tests make cooperative listeners wait on the signal at prompt submission, system-prompt assembly, session prefix, pre-step, request, model stream, step result, tool execution, continuation, and terminal stop; they assert one signal within a turn, a fresh signal across turns, and no cancellation authority during terminal publication or a blocked durability flush. A real hook bridge test cancels and reaps a blocked prompt hook before idle. +Contract tests verify the typed caller union, frozen detachment, default and first-wins behavior, the coarse Session JSON round trip and legacy-record rejection, ACP `user`, in-process subagent `parent`, and disposal precedence. Loop tests make cooperative listeners wait on the signal at pre-step, system-prompt assembly, request, model stream, request-error recovery, tool execution, and turn stopping; they assert one signal within a turn, a fresh signal across turns, and no cancellation authority during terminal publication or a blocked durability flush. A real hook bridge test cancels and reaps a blocked prompt hook before idle. Initiator-scope tests assert that every hook still observes the exact Agent and no ambient turn signal, concurrent Agents retain independent identities and signals, and a nested child driver shadows only identity. Race tests cover idle cancellation, pre-run cancellation, replacement submission from a `running` listener, repeated cancellation, and cancel-versus-dispose quiescence. @@ -44,7 +44,7 @@ Initiator-scope tests assert that every hook still observes the exact Agent and **Define speculative `superseded`, `timeout`, and `shutdown` variants now.** No current Agent cancellation producer implements those semantics. `shutdown` is already lifecycle disposal, and timeout or supersession should enter the union only with an owning policy and unique terminal meaning. -**Expose public turn or step context wrappers.** Existing positional seams already identify Agent, turn, and step. A wrapper would widen every API, duplicate ownership, and tempt callers to treat a captured object as durable authority. +**Expose public turn or step context wrappers.** Existing seams already identify Agent, turn, and step. A wrapper would widen every API, duplicate ownership, and tempt callers to treat a captured object as durable authority. **Abandon uncooperative work after a grace period.** Returning idle while same-process work still runs breaks teardown and resource-ownership guarantees. Hard termination requires a worker or process isolation boundary and is outside this control seam. diff --git a/.agents/notes/implemented/architecture/2026-07-16-explicit-turn-cancellation.zh.md b/.agents/notes/implemented/architecture/2026-07-16-explicit-turn-cancellation.zh.md index e945b0fea5..0b9a06c0ae 100644 --- a/.agents/notes/implemented/architecture/2026-07-16-explicit-turn-cancellation.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-16-explicit-turn-cancellation.zh.md @@ -1,4 +1,4 @@ -# Agent Note:显式轮次取消能力 +# Agent Note: 显式轮次取消能力 Status: implemented @@ -12,27 +12,27 @@ Status: implemented ## 决策 -Agent 拥有仅用于运行时的 `AgentCancelCause` 联合类型 `{ kind: 'user' } | { kind: 'parent' }`;`agent.cancel()` 默认使用 `user`。TypeScript 在这份类型化同进程契约中强制执行该词汇,不提供运行时校验器、后备行为,也不为无类型调用方提供特殊兼容性契约。活跃的 `TurnCancellation` 会把类型化判别字段复制为一个全新且已冻结的 signal 原因;空闲状态下没有可修改的持有者,也不会让后续工作预先进入取消状态。 +Agent 拥有仅用于运行时的 `AgentCancelCause` 联合类型 `{ kind: 'user' } | { kind: 'parent' }`;`agent.cancel()` 默认使用 `user`。TypeScript 在这个类型化的同进程 seam 中强制执行该词汇,不提供运行时校验器、后备行为,也不为无类型调用方提供特殊兼容性约定。活跃的 `TurnCancellation` 会把类型化判别字段复制为一个全新且已冻结的 signal 原因;空闲状态下没有可修改的持有者,也不会让后续工作预先进入取消状态。 -正在运行的轮次被中断后,以粗粒度的持久化结果 `{ kind: 'aborted' }` 结束。终态事件记录轮次发生了什么,运行时 signal 标识谁请求了取消;回放不会重复保存 `user` 或 `parent`。Session seed/load 会拒绝携带取消原因或任何其他额外字段的旧式中止记录,因此回放无法重新引入由调用方持有的取消细节。仅限进程内的 `agent/cancel-requested` 通知不会持久化;未来若有审计需求,应使用独立的持久化控制请求事件,让请求与最终结果保持为两项事实。持久化事件不包含调用栈、signal、错误对象、自由文本取消原因或后端私有细节。 +正在运行的轮次被中断后,以粗粒度的持久化结果 `{ kind: 'aborted' }` 结束。终态事件记录轮次发生了什么,运行时 signal 标识谁请求了取消;回放不会重复保存 `user` 或 `parent`。会话 seed/load 会拒绝携带取消原因或任何其他额外字段的旧式中止记录,因此回放无法重新引入由调用方持有的取消细节。仅限进程内的 `agent/cancel-requested` 通知不会持久化;未来若有审计需求,应使用独立的持久化控制请求事件,让请求与最终结果保持为两项事实。持久化事件不包含调用栈、signal、错误对象、自由文本取消原因或后端私有细节。 -AgentLoop 为每个待启动轮次私有地持有一个 `TurnCancellation`。它在通知 `agent/status = running` 前安装该持有者,使其中唯一的 `AbortController` 持续覆盖提示词处理、提示词组装、每个步骤、模型与工具执行、继续决策和 `agent/turn-stop`;随后在发布 `turn/end` 前立即清除所安装的那个持有者。因此,即使驱动器状态可能在持久化刷新结算前保持 `running`,终态事件观察者及其后的持久化刷新也无法取消已完成的轮次工作。所有参与的方法、事件和请求值都会收到同一个显式 signal;下一个轮次会收到全新的 signal。 +AgentLoop 为每个待启动轮次私有地持有一个 `TurnCancellation`。它在通知 `agent/status = running` 前安装该持有者,使其中唯一的 `AbortController` 持续覆盖 inbox 领取、`agent/pre-step`、提示词组装、每个步骤、模型与工具执行以及 `agent/turn-stopping`;随后在发布 `turn/end` 前立即清除所安装的那个持有者。因此,即使驱动器状态可能在持久化刷新结算前保持 `running`,终态事件观察者及其后的持久化刷新也无法取消已完成的轮次工作。所有参与的方法、事件和请求值都会收到同一个显式 signal;下一个轮次会收到全新的 signal。 -对于轮次被认领前已取消的排队工作,驱动器只保留一个不携带取消原因的运行前标记。实际生效的 `cancel()` 会先发出仅供观察的 `agent/cancel-requested` 通知并携带最终确定的类型化取消原因,然后才清除排队工作和 steering(中途引导)工作或中止持有者;通知失败不能阻止此次停止,空闲状态下调用则不发出任何通知。通知观察者同步加入队列的工作也会被这次清除,而稍后由 signal 中止观察者加入队列的工作属于下一个轮次。若 `running` 监听器同步取消旧工作并发送替代提示词,驱动器会丢弃已中止的持有者,并为替代提示词创建全新的持有者。同一活跃持有者上的重复取消遵循首次请求优先,后续调用仍可清除新入队的待处理工作。 +对于轮次被认领前已取消的排队工作,驱动器只保留一个不携带取消原因的运行前标记。实际生效的 `cancel()` 会先发出仅供观察的 `agent/cancel-requested` 通知并携带最终确定的类型化取消原因,然后才清除排队工作和 steering(中途引导)工作或中止持有者;通知失败不能阻止此次停止,空闲状态下调用则不发出任何通知。通知观察者同步加入队列的工作也会被这次清除,而稍后由 signal 中止观察者加入队列的工作会被锁存,并在被中止的活动收敛到空闲时执行——`disposed` 取消则将其停放([取消收敛窗口唤醒锁存](../bug-fix/2026-08-07-cancel-convergence-wake-latch.md))。若 `running` 监听器同步取消旧工作并发送替代提示词,驱动器会丢弃已中止的持有者,并为替代提示词创建全新的持有者。同一活跃持有者上的重复取消遵循首次请求优先,后续调用仍可清除新入队的待处理工作。 -显式事件签名保留位置参数形式,并把 `signal` 放在 waterfall(瀑布式事件)的最后一个参数 `next` 之前。提示词提交、请求配置、步骤结果处理、继续决策和终止停止加入已有的步骤前处理、会话前缀、模型生成、工具执行、审批以及 subagent 或工作流请求的显式 signal seam。钩子桥接器也必须提供 `RunHookOptions.signal`,使轮次取消能够到达 Bash 执行器终止进程组并等待其退出的边界。`SystemPrompt.assemble()` 在 `AssembleContext` 中携带 `signal?: AbortSignal`,因为该对象是显式请求值,也可表示轮次之外不携带 signal 的组装。监听器可以配合该 signal 取消,但不得保留它来控制其他轮次。 +显式事件签名传递单个 payload 对象:agent 作用域事件在 payload 中携带 `agent` 和 `signal`,`next` 位于最后;其余 seam 保持 `signal` 紧邻 waterfall(瀑布式事件)的最终 `next` 之前。`PreStepContext` 与 `RequestFailureContext` 已退役,其字段并入 `agent/pre-step` 与 `agent/request-error` 的 payload([payload-object 事件](2026-08-06-agent-event-payload-objects.md))。步骤前处理入口、请求配置、请求错误恢复、模型生成、工具执行、审批、轮次停止以及 subagent 或工作流请求都会收到当前 signal。钩子桥接器也必须提供 `RunHookOptions.signal`,使轮次取消能够到达 Bash 执行器终止进程组并等待其退出的边界。`SystemPrompt.assemble()` 在 `AssembleContext` 中携带 `signal?: AbortSignal`,因为该对象是显式请求值,也可表示轮次之外不携带 signal 的组装。监听器可以配合该 signal 取消,但不得保留它来控制其他轮次。 `ctx.agents` 仍只携带发起 Agent。环境中的 Agent 并不代表存活、当前轮次或取消权限。cause 读取器是 loop 私有的,它直接陈述机器私有的 slot 不变量(只有 `cancel()` 会中止轮次控制器,且总是携带规范的冻结 cause),而不是对 reason 做结构化再校验;不存在从任意 signal 读取 cause 的公开辅助函数。并发 Agent 会同时隔离各自的发起方身份和轮次 signal;子驱动会遮蔽父发起方,而父请求 signal 仍通过 subagent seam 传递。 Agent dispose(资源释放)会在活跃持有者上请求仅用于运行时的 `{ kind: 'disposed' }` 中断。若取消已经先占用控制器的中断原因,该原因便无法改写,因此终态分类会先检查生命周期状态:资源释放结果优先,之后受支持的 `user` 或 `parent` 取消原因形成粗粒度的中止结果,其他异常保留现有错误路径。ACP(Agent Client Protocol)取消映射为 `user`;进程内 spawn 和 fork 的传播映射为 `parent`。远程 ACP subagent 保持现有协议。 -取消仍然是协作式的。AgentLoop 会在异步等待边界前后检查中断,但不会用 `Promise.race` 放弃进程内监听器、适配器或工具 Promise。忽略 signal 的工作必须真正结算,`whenIdle()`、句柄 dispose 和作用域清理才会报告静止状态。 +取消仍然是协作式的。AgentLoop 会在异步等待边界前后检查中断,但不会用 `Promise.race` 放弃进程内监听器、适配器或工具 Promise。忽略 signal 的工作必须真正结算,`whenIdle()`、句柄 dispose 和作用域清理才会报告完全停稳。 ## 验证 -契约测试验证类型化调用方联合类型、冻结且与调用方分离、默认行为与首次请求优先行为、粗粒度的会话 JSON 往返与旧式记录拒绝、ACP `user`、进程内 subagent `parent` 以及 dispose 优先级。AgentLoop 测试让协作式监听器在提示词提交、系统提示词组装、会话前缀、步骤前处理、请求、模型流、步骤结果、工具执行、继续决策和终止停止处等待 signal;并断言同一轮次使用一个 signal,不同轮次使用全新的 signal,终态发布期间和持久化刷新受阻期间不存在取消权限。真实钩子桥接器测试会在报告空闲状态前取消并回收受阻的提示词钩子。 +约定测试验证类型化调用方联合类型、冻结且与调用方分离、默认行为与首次请求优先行为、粗粒度的会话 JSON 往返与旧式记录拒绝、ACP `user`、进程内 subagent `parent` 以及 dispose 优先级。AgentLoop 测试让协作式监听器在步骤前处理、系统提示词组装、请求、模型流、请求错误恢复、工具执行和轮次停止处等待 signal;并断言同一轮次使用一个 signal,不同轮次使用全新的 signal,终态发布期间和持久化刷新受阻期间不存在取消权限。真实钩子桥接器测试会在报告空闲状态前取消并回收受阻的提示词钩子。 -发起方作用域测试断言所有钩子仍观察到同一个 Agent 且没有环境中的轮次 signal,并发 Agent 保持独立的身份与 signal,嵌套子驱动只遮蔽身份。竞态测试覆盖空闲状态取消、运行前取消、从 `running` 监听器提交替代提示词、重复取消以及取消与 dispose 竞争下的静止状态。 +发起方作用域测试断言所有钩子仍观察到同一个 Agent 且没有环境中的轮次 signal,并发 Agent 保持独立的身份与 signal,嵌套子驱动只遮蔽身份。竞态测试覆盖空闲状态取消、运行前取消、从 `running` 监听器提交替代提示词、重复取消以及取消与 dispose 竞争下的完全停稳。 ## 考虑过的替代方案 @@ -44,7 +44,7 @@ Agent dispose(资源释放)会在活跃持有者上请求仅用于运行时 **现在就定义推测性的 `superseded`、`timeout` 和 `shutdown` 变体。** 当前没有 Agent 取消生产方实现这些语义。`shutdown` 已经属于生命周期 dispose;超时或替代只有在拥有明确归属策略和唯一终态含义时才应进入联合类型。 -**公开轮次或步骤上下文包装类型。** 现有位置参数 seam 已经标识 Agent、轮次和步骤。包装类型会加宽所有 API、重复归属,并诱导调用方把捕获的对象当成持久权限。 +**公开轮次或步骤上下文包装类型。** 现有 seam 已经标识 Agent、轮次和步骤。包装类型会加宽所有 API、重复归属,并诱导调用方把捕获的对象当成持久权限。 **在宽限期后放弃不协作的工作。** 同进程工作仍在运行时就报告空闲状态,会破坏资源清理与资源归属保证。硬终止需要 worker 或进程隔离边界,不属于该控制 seam。 @@ -52,4 +52,4 @@ Agent dispose(资源释放)会在活跃持有者上请求仅用于运行时 取消拥有一个运行时归属方、每个活跃轮次一个 signal,以及一套类型化的运行时调用方词汇。会话保留其消费方实际使用的粗粒度 `aborted` 结果,拒绝携带原因的旧式形式,并与运行时对象保持隔离。协作式取消覆盖每个异步轮次 seam,包括第一个步骤之前和最后一个步骤之后的工作,而终态发布和持久化仍在其权限范围之外。 -显式 signal 会给多个公开事件增加参数,并要求插件有意识地转发取消。这是有意设计:权限在调用边界可见,生命周期与轮次匹配,陈旧的环境异步后代无法获得控制能力。不协作的进程内工作可能延迟取消,但所报告的静止状态仍然真实。 +显式 signal 会给多个公开事件增加参数,并要求插件有意识地转发取消。这是有意设计:权限在调用边界可见,生命周期与轮次匹配,陈旧的环境异步后代无法获得控制能力。不协作的进程内工作可能延迟取消,但所报告的完全停稳仍然真实。 diff --git a/.agents/notes/implemented/architecture/2026-07-19-cooperative-tool-cancellation.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-19-cooperative-tool-cancellation.i18n.yaml index 77e3b8c14a..a0956af598 100644 --- a/.agents/notes/implemented/architecture/2026-07-19-cooperative-tool-cancellation.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-19-cooperative-tool-cancellation.i18n.yaml @@ -1,6 +1,6 @@ # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: -# pnpm run verify-translation-pairing --write -2026-07-19-cooperative-tool-cancellation.md: be237f6ca9475699bb4af76896772a1a7409033d -2026-07-19-cooperative-tool-cancellation.zh.md: 9ad212c2073063ccb0c838c08ab8f89c9285b26b +# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-19-cooperative-tool-cancellation.md +2026-07-19-cooperative-tool-cancellation.md: 4e82452cd6883593d4693766bea803c97fa4c977 +2026-07-19-cooperative-tool-cancellation.zh.md: aa94fd9f3d32167dc7d6b906ff14a6afd36ccb32 diff --git a/.agents/notes/implemented/architecture/2026-07-19-cooperative-tool-cancellation.md b/.agents/notes/implemented/architecture/2026-07-19-cooperative-tool-cancellation.md index be237f6ca9..4e82452cd6 100644 --- a/.agents/notes/implemented/architecture/2026-07-19-cooperative-tool-cancellation.md +++ b/.agents/notes/implemented/architecture/2026-07-19-cooperative-tool-cancellation.md @@ -46,7 +46,7 @@ This decision requires cancellation at the tool invocation seam only. Making sig ## Verification -[`execution-signal-types.spec.ts`](../../../../packages/core/tools/tests/execution-signal-types.spec.ts) proves the required exact signal types, readonly observer and tool views, mutable-but-required around-dispatch view, and `defineTool()` inference. [`tools.spec.ts`](../../../../packages/core/tools/tests/tools.spec.ts) covers pre-aborted materialization, phase skipping, policy and wrapper races, body invocation classification, caller-signal fusion, error precedence, context retention, and quiescent drainage. [`tool-calls.spec.ts`](../../../../packages/core/agent-loop/tests/tool-calls.spec.ts) and [`contract-regressions.spec.ts`](../../../../packages/core/agent-loop/tests/contract-regressions.spec.ts) cover balanced durable results for undispatched siblings. [`code-mode.spec.ts`](../../../../packages/core/tools/tests/code-mode.spec.ts) and first-party integration suites cover explicit forwarding, while [`timeout-policy.spec.ts`](../../../../packages/timeout/timeout-policy/tests/timeout-policy.spec.ts) preserves timeout ownership. +[`execution-signal-types.spec.ts`](../../../../packages/core/tools/tests/execution-signal-types.spec.ts) proves the required exact signal types, readonly observer and tool views, mutable-but-required around-dispatch view, and `defineTool()` inference. [`tools.spec.ts`](../../../../packages/core/tools/tests/tools.spec.ts) covers pre-aborted materialization, phase skipping, policy and wrapper races, body invocation classification, caller-signal fusion, error precedence, context retention, and quiescent drainage. [`tool-calls.spec.ts`](../../../../packages/core/agent-loop/tests/tool-calls.spec.ts) and [`contract-regressions.spec.ts`](../../../../packages/core/agent-loop/tests/contract-regressions.spec.ts) cover balanced durable results for undispatched siblings. [`code-mode.spec.ts`](../../../../packages/core/tools/tests/code-mode.spec.ts) and first-party integration suites cover explicit forwarding, while [`timeout-policy.spec.ts`](../../../../packages/guard/timeout-policy/tests/timeout-policy.spec.ts) preserves timeout ownership. No registry test can prove that arbitrary third-party same-process code observes the signal or stops in bounded time. Capability tests continue to prove cancellation and quiescence at the boundary that owns each side effect. diff --git a/.agents/notes/implemented/architecture/2026-07-19-cooperative-tool-cancellation.zh.md b/.agents/notes/implemented/architecture/2026-07-19-cooperative-tool-cancellation.zh.md index 9ad212c207..aa94fd9f3d 100644 --- a/.agents/notes/implemented/architecture/2026-07-19-cooperative-tool-cancellation.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-19-cooperative-tool-cancellation.zh.md @@ -10,7 +10,7 @@ Status: implemented 流水线各阶段对可变性的需求也不同。工具实现、前置策略、后置策略和结果观察者只借用取消状态,而环绕调度包装层必须临时替换信号,以加入截止时间或其他词法取消作用域。单一的可变公开类型要么把修改权限授予过多阶段,要么阻止这种组合。 -取消可能发生在策略之前、审批期间、环绕调度等待期间、工具主体启动之后,或后置策略等待期间。单一的 `ABORTED` 结果无法让持久化结果的使用方判断工具主体是否可能产生过副作用。让工具 promise 与取消竞速也不是安全的后备方案,因为注册表报告完成后,被丢弃的同进程工作仍会继续运行。 +取消可能发生在策略之前、审批期间、环绕调度等待期间、工具主体启动之后,或后置策略等待期间。单一的 `ABORTED` 结果无法让持久化结果的消费方判断工具主体是否可能产生过副作用。让工具 promise 与取消竞速也不是安全的后备方案,因为注册表报告完成后,被丢弃的同进程工作仍会继续运行。 ## 决策 @@ -18,7 +18,7 @@ Status: implemented `ToolDefinition.execute(args, exec)` 保持现有签名。`defineTool()` 会把 `exec.signal` 上下文推断为必填的 `AbortSignal`,因此每个已注册的 TypeScript 工具都能在无需类型断言的情况下观察或转发取消。所有第一方直接调用方和 Code Mode 嵌套调度都会显式传入当前操作的信号。 -注册表信任这份类型化同进程契约。它不在运行时校验 `AbortSignal`,也不为缺失或畸形信号添加敌意输入测试。校验仍位于解析器与配置、队列、模型与工具 JSON、持久化与文件、worker、进程和线协议边界;违反 TypeScript 接口的无类型 JavaScript 不享有兼容性契约。 +注册表信任这份类型化同进程约定。它不在运行时校验 `AbortSignal`,也不为缺失或畸形信号添加敌意输入测试。校验仍位于解析器与配置、模型与工具 JSON、持久化与文件、worker、进程和协议边界;违反 TypeScript 接口的无类型 JavaScript 不享有兼容性约定。 ### 可变性由流水线阶段决定 @@ -28,9 +28,9 @@ Status: implemented ### 取消代码记录是否发生过调度 -`dsh-tools` 导出 `TOOL_ABORTED = 'ABORTED'` 和 `TOOL_ABORTED_BEFORE_DISPATCH = 'ABORTED_BEFORE_DISPATCH'`。注册表在调用 `ToolDefinition.execute()` 的前一刻记录工具主体已经开始。 +`dsh-tools` 导出 `TOOL_ABORTED = 'ABORTED'` 和 `TOOL_ABORTED_BEFORE_DISPATCH = 'ABORTED_BEFORE_DISPATCH'`。注册表在调用 `ToolDefinition.execute()` 的前一刻记录工具主体已调用。 -`ABORTED_BEFORE_DISPATCH` 携带 `{ name: 'AbortError' }` 和模型可见文本 `Error: tool call aborted before dispatch`。凡取消阻止工具主体调用时都使用该结果,包括进入时已中止、前置策略或审批期间取消、包装层信号已中止、包装层在委托前返回的成功结果被调用方取消抢先,以及轮次取消后 agent loop 跳过的同批调用。 +`ABORTED_BEFORE_DISPATCH` 携带 `{ name: 'AbortError' }` 和模型可见文本 `Error: tool call aborted before dispatch`。凡取消阻止工具主体调用时都使用该结果,包括进入时已中止、前置策略或审批期间取消、包装层信号已中止、包装层在委托前返回的成功结果被调用方取消抢先,以及轮次取消后 agent loop(智能体循环)跳过的同批调用。 `ABORTED` 携带模型可见文本 `Error: tool call aborted`,并且只在工具主体已经调用后使用,包括工具主体完成后环绕包装层或后置策略监听器等待期间发生的取消。拒绝、包装层失败、工具失败或后置策略失败比通用取消更具体。timeout-policy 自身拥有的超时仍为 `TOOL_TIMEOUT`,成功结果被取消替换前延后附加的上下文仍会保留。 @@ -42,11 +42,11 @@ Status: implemented 工具主体一旦启动,注册表就会等待它完成。取消通过融合信号到达工具主体,但注册表不会与其 promise 竞速或丢弃该 promise。协作式实现会停止自身工作或继续转发取消,并在所持有的工作完全停稳后完成;不协作的同进程实现可能让注册表无限期保持等待。进程、worker、网络和提供方层仍负责各自的终止机制。 -这项决策只要求工具调用接缝携带取消信号。让工具主体可达的异步能力也必须接收信号,属于另一项迁移,见提议中的[工具可达能力接缝中的必填取消](../../proposed/architecture/2026-07-19-required-cancellation-through-tool-capability-seams.md)。 +这项决策只要求工具调用 seam 携带取消信号。让工具主体可达的异步能力也必须接收信号,属于另一项迁移,见提议中的[工具可达能力 seam 中的必填取消](../../proposed/architecture/2026-07-19-required-cancellation-through-tool-capability-seams.md)。 ## 验证 -[`execution-signal-types.spec.ts`](../../../../packages/core/tools/tests/execution-signal-types.spec.ts) 证明必填的精确信号类型、观察者与工具的只读视图、环绕调度可替换但不可删除的视图,以及 `defineTool()` 推断。[`tools.spec.ts`](../../../../packages/core/tools/tests/tools.spec.ts) 覆盖进入时已中止的物化与阶段跳过、策略和包装层竞态、工具主体调用分类、调用方信号融合、错误优先级、上下文保留和完全停稳。[`tool-calls.spec.ts`](../../../../packages/core/agent-loop/tests/tool-calls.spec.ts) 与 [`contract-regressions.spec.ts`](../../../../packages/core/agent-loop/tests/contract-regressions.spec.ts) 覆盖未调度同批调用的持久化配对结果。[`code-mode.spec.ts`](../../../../packages/core/tools/tests/code-mode.spec.ts) 和第一方集成测试覆盖显式转发,[`timeout-policy.spec.ts`](../../../../packages/timeout/timeout-policy/tests/timeout-policy.spec.ts) 保持超时归属。 +[`execution-signal-types.spec.ts`](../../../../packages/core/tools/tests/execution-signal-types.spec.ts) 证明必填的精确信号类型、观察者与工具的只读视图、环绕调度可替换但不可删除的视图,以及 `defineTool()` 推断。[`tools.spec.ts`](../../../../packages/core/tools/tests/tools.spec.ts) 覆盖进入时已中止的物化与阶段跳过、策略和包装层竞态、工具主体调用分类、调用方信号融合、错误优先级、上下文保留和完全停稳。[`tool-calls.spec.ts`](../../../../packages/core/agent-loop/tests/tool-calls.spec.ts) 与 [`contract-regressions.spec.ts`](../../../../packages/core/agent-loop/tests/contract-regressions.spec.ts) 覆盖为未调度的同批调用补齐持久化结果。[`code-mode.spec.ts`](../../../../packages/core/tools/tests/code-mode.spec.ts) 和第一方集成测试覆盖显式转发,[`timeout-policy.spec.ts`](../../../../packages/guard/timeout-policy/tests/timeout-policy.spec.ts) 保持超时归属。 任何注册表测试都无法证明任意第三方同进程代码会观察信号或在有界时间内停止。各能力的测试仍需在拥有相应副作用的边界证明取消与完全停稳。 @@ -54,20 +54,20 @@ Status: implemented **保留可选信号并生成后备值。** 不予采纳,因为注册表持有的后备信号不代表任何调用方生命周期,也会保留类型系统本应阻止的缺失情况。 -**在运行时校验 `AbortSignal`。** 不予采纳,因为这是类型化同进程接缝,不是序列化边界。运行时检查只会重复静态契约,仍无法强制实现协作式使用信号。 +**在运行时校验 `AbortSignal`。** 不予采纳,因为这是类型化同进程 seam,不是序列化边界。运行时检查只会重复静态约定,仍无法强制实现协作式使用信号。 -**添加 `supportsCancellation` 元数据、回调参数数量检查或信号使用 lint。** 不予采纳,因为这些方法都无法证明异步工作会观察或正确转发取消。信号可用性属于类型契约;具体行为仍由工具和能力负责。 +**添加 `supportsCancellation` 元数据、回调参数数量检查或信号使用 lint。** 不予采纳,因为这些方法都无法证明异步工作会观察或正确转发取消。信号可用性属于类型约定;具体行为仍由工具和能力负责。 **向所有阶段公开同一个可变执行类型。** 不予采纳,因为观察者和工具实现只需要借用信号。按阶段划分类型可以把替换权限限制在流水线拥有该操作的位置。 -**禁止环绕包装层替换信号。** 不予采纳,因为截止时间和嵌套运行时作用域需要词法派生信号。捕获并融合调用方信号既保留组合能力,也不允许切断调用方取消。 +**禁止环绕包装层替换信号。** 不予采纳,因为截止时间和嵌套操作作用域需要词法派生信号。捕获并融合调用方信号既保留组合能力,也不允许切断调用方取消。 **让工具 promise 与取消竞速。** 不予采纳,因为这种方式会在副作用仍可能存活时报告完成,违反[资源释放必须完全停稳的规则](../../../../docs/defensive-patterns.md#dispose-must-reach-quiescence-not-just-request-it)。 ## 后果 - TypeScript 会拒绝所有缺少 `signal` 的 `ToolExecutionInput`、工具或观察者对只读信号的修改,以及环绕调度删除信号的尝试。 -- 持久化结果的使用方可以区分工具主体可能产生过副作用的调用(`ABORTED`)和从未进入工具主体的调用(`ABORTED_BEFORE_DISPATCH`)。 +- 持久化结果的消费方可以区分工具主体可能产生过副作用的调用(`ABORTED`)和从未进入工具主体的调用(`ABORTED_BEFORE_DISPATCH`)。 - 根据仓库的预发布原则,这项变更刻意保持破坏性;不保留兼容重载或运行时后备行为。 - 协作式工具会及时停止并完全停稳;忽略信号的实现会表现为仍在等待的调用。 - 下游能力接口保持不变,直到关联的提议 Agent Note 被接受并实现。 diff --git a/.agents/notes/implemented/architecture/2026-07-19-gui-layering-and-rpc-protocol.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-19-gui-layering-and-rpc-protocol.i18n.yaml index ca90cebb0e..13da6f9711 100644 --- a/.agents/notes/implemented/architecture/2026-07-19-gui-layering-and-rpc-protocol.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-19-gui-layering-and-rpc-protocol.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-19-gui-layering-and-rpc-protocol.md -2026-07-19-gui-layering-and-rpc-protocol.md: 7ad2a2403eb9962b369b016070e8ca378ed55c60 -2026-07-19-gui-layering-and-rpc-protocol.zh.md: 90850c469f1444e7f6cd105551e6cc21920e91d9 +2026-07-19-gui-layering-and-rpc-protocol.md: ceb8e5db593aef14d6db259f6293381fe83defe2 +2026-07-19-gui-layering-and-rpc-protocol.zh.md: ecd577f7ec5af5d588d0dbf03f94010e00782732 diff --git a/.agents/notes/implemented/architecture/2026-07-19-gui-layering-and-rpc-protocol.md b/.agents/notes/implemented/architecture/2026-07-19-gui-layering-and-rpc-protocol.md index 7ad2a2403e..ceb8e5db59 100644 --- a/.agents/notes/implemented/architecture/2026-07-19-gui-layering-and-rpc-protocol.md +++ b/.agents/notes/implemented/architecture/2026-07-19-gui-layering-and-rpc-protocol.md @@ -4,18 +4,18 @@ Status: implemented English | [中文](2026-07-19-gui-layering-and-rpc-protocol.zh.md) -> Division of labor: this document = the layering model + the channel-independent RPC protocol; the protocol's Web implementation (HTTP+SSE) is in the [web client architecture RFC](2026-07-19-gui-web-client-architecture.md). +> Division of labor: this document = the layering model + the channel-independent RPC protocol; the protocol's Web implementation combines HTTP uplink with the [WebSocket downlink carrier](2026-08-04-websocket-downlink-carrier.md), while the browser object layer is in the [web client architecture RFC](2026-07-19-gui-web-client-architecture.md). ## Problem We need a UI integration layer. Beyond the existing ACP/stdio baseline, more product UI shapes are coming — Web (server), Electron, and others. We call these shapes Clients, uniformly, and want the following capabilities: -- One `dsh` process supporting both `dsh web` (serve) and `dsh -p` (headless) — one process, two modes (a design reservation) +- One `dsh` process supporting both `dsh web` (serve) and `dsh run` (headless) — one process, two modes (a design reservation) - Launching inside Electron with the same Web technology shape as `dsh web` That demands a stable layered responsibility model in the engineering codebase, so future client shapes plug in cleanly. -At the same time the physical channels differ per consumer (HTTP/SSE, in-process direct calls, IPC later), so we also need a channel-independent message model and a single contract source of truth — "adding a method" and "swapping a carrier" must not entangle each other, and every message on the wire must be type-validatable, observable, and reconcilable. +At the same time the physical channels differ per consumer (browser HTTP/WebSocket, in-process fetch/SSE, IPC later), so we also need a channel-independent message model and a single contract source of truth — "adding a method" and "swapping a carrier" must not entangle each other, and every message on the wire must be type-validatable, observable, and reconcilable. ## Decision @@ -31,7 +31,7 @@ Directories layer as follows: - **Fetch-arrival plugin packages** (`ui-layout`, `ui-sidebar`, `ui-conversation`, `ui-trajectory`): dual-entry — the root index is the node half (an empty `apply`, existing so the host Loader governs lifecycle and the web plugin registry discovers the package.json `dshClient` declaration); the implementation lives under `src/client/`, shipped as the `./client` subpath (a tsdown closure-factory bundle). Cross-plugin consumption of `/client` is type-only; value cooperation goes through cordis services. - `apps/` holds the externally exported application shapes, assembled from Client / Host mixtures. - `apps/web` (`dsh-frontend`) is the vite application: a thin `main.ts` over the shell surface exported by `dsh-client-web`. - - `apps/cli` (`@deepseek-ai/dsh`) dispatches shapes: `dsh web` = startHost + webserver + the built `dsh-frontend` dist; `dsh -p` = headless in-process calls, zero HTTP. + - `apps/cli` (`@deepseek-ai/dsh`) dispatches shapes: `dsh web` = Host + webserver + the built `dsh-frontend` dist; `dsh run` = [a direct core Agent/Session front door](2026-08-09-headless-direct-core-front-door.md), with zero Host, HTTP, or browser layer. - A future Electron shape reuses the same web client packages over an IPC fetch carrier. ``` @@ -64,7 +64,7 @@ On the protocol side: TS interfaces (`packages/host/apiproxy/src/api/`, zero Nod |---|---|---|---| | Front layer | `dsh-host-apiproxy` | TS/zod definitions (api/) + the fetch abstraction (fetch/: handler + client base class) | Keep it simple — every consumer needs it; importable from Node and browser alike; protocol content in the "Message protocol" sections below; clients must not bypass api through ctx | | Assembly layer | `dsh-host-runtime` | Plugin composition + ApiProxy integration + the web UI plugin mount (in-memory Loader tree over the eight dshClient packages); home of host-level configuration (defaults/persistenceRoot, future user profile) | Which plugins mount and with what defaults is decided only here; shells must not alter the assembly | -| Carrier layer | `dsh-host-webserver` | Web-shape HTTP: static serving + `/api/*`→handler forwarding + SSE write-out + close semantics; plugin bundle endpoint + `__DSH_BOOT__` manifest injection (fed by the web plugin registry) | Web (browser access) only; zero workspace dependencies (the registry arrives by structural injection); Electron does not reuse it | +| Carrier layer | `dsh-host-webserver` | Web-shape HTTP and upgrade: static serving + `/api/*`→handler forwarding + WebSocket upgrade route + close semantics; plugin bundle endpoint + `__DSH_BOOT__` manifest injection (fed by the web plugin registry) | Web (browser access) only; zero workspace dependencies (the registry arrives by structural injection); Electron does not reuse it | | Client libraries | `dsh-client-ui-slots` / `dsh-client-web-react` / `dsh-client-ui-primitives` | Slot registry core / ctx↔React glue / pure React atoms | Zero cordis runtime dependency in components; seeded into the loader module table by the shell | | Client plugins | `dsh-client-connection` / `dsh-client-runtime` / `dsh-client-ui-theme` / `dsh-client-i18n` / `dsh-client-ui-layout` / `dsh-client-ui-sidebar` / `dsh-client-ui-conversation` / `dsh-client-ui-trajectory` | Browser-side cordis plugin tree (wire consumer, core services, theme, i18n, layout, sidebar, conversation, trajectory) — see the web client architecture RFC | Dual entry (node half = empty apply; implementation in `src/client/`); the consumption face goes exclusively through ApiProxy | | Application shape | `@deepseek-ai/dsh` (apps/cli) + `dsh-frontend` (apps/web, the vite application) | Coarse bin dispatch + one assembly module per shape (web.ts / headless.ts); the vite app is a thin main over the `dsh-client-web` shell surface | Shapes dynamic-import so they never load each other; workspace knowledge like dist location stays in the app | @@ -79,7 +79,7 @@ Packages under `packages/host/*` and `packages/client/*` **must carry the direct 2. **Write an assembly module under `apps/`**: `startHost()` + a client subclass + the shape's private signal/print/exit semantics; a mixture never becomes a package — assembly is written in the app. 3. **Import `dsh-host-webserver` only if you need HTTP carriage**, otherwise zero ports. -The two existing shapes are the template: `apps/cli/src/web.ts` (startHost + dist location + startWebServer + signal shutdown) and `headless.ts` (startHost + InProcessApiClient isomorphic direct calls, zero HTTP zero ports). ACP-class protocol bridges do not follow this checklist: they expose core to the external ecosystem, mount via `ctx.plugin(front-door plugin)` directly, and wear no fetch. +The two existing shapes preserve the boundary: the Web shape mounts Host, carrier, and browser composition, while `dsh run` mounts a direct core runner with zero Host, HTTP, or ports. ACP-class protocol bridges do not follow the client-carrier checklist: they expose core to the external ecosystem, mount via `ctx.plugin(front-door plugin)` directly, and wear no fetch. ## Message protocol @@ -88,7 +88,7 @@ The sections from here down are the protocol body carried by the front layer (`d ``` client 发起 server 发起 request ① ClientRequest ③ ServerRequest - (POST /api/ body) (SSE 帧:session 事件、审批/问答 requested) + (POST /api/ body) (WebSocket message:session 事件、审批/问答 requested) response ② ServerResponse ④ ClientResponse (该 POST 的 HTTP 应答体) (POST /api/respond body,回填 ③ 的 rpcId) ``` @@ -99,7 +99,7 @@ The sections from here down are the protocol body carried by the front layer (`d |---|---|---|---|---| | `ClientRequest` | `'client-request'` | `rpcId` `method` `payload` | client mints | `POST /api/` body | | `ServerResponse` | `'server-response'` | `rpcId` `result` | echoes ① | that POST's response body (always HTTP 200) | -| `ServerRequest` | `'server-request'` | `rpcId` `method` `payload` | server mints | SSE `data:` line | +| `ServerRequest` | `'server-request'` | `rpcId` `method` `payload` | server mints | WebSocket text message | | `ClientResponse` | `'client-response'` | `rpcId` `result` | echoes ③ | `POST /api/respond` body | `RpcMessage = ClientRequest | ServerResponse | ServerRequest | ClientResponse`, narrowed via `switch (message.type)`. @@ -169,7 +169,7 @@ The remaining methods (`session.create`/`session.history`/`session.rename`/`sess ### Frames (server→client, named unions) -Two SSE streams: the mux stream (`GET /api/events.mux`, all-session aggregate) and the host stream (`GET /api/events.host`, host-level events). One example frame row: +Two logical streams: the mux stream (`/api/events.mux`, all-session aggregate) and the host stream (`/api/events.host`, host-level events). The browser consumes one downlink WebSocket per stream, while the in-process fetch carrier retains SSE to preserve the same shape; see the [WebSocket downlink carrier](2026-08-04-websocket-downlink-carrier.md) for the physical boundary. One example frame row: | frame type | payload | when | |---|---|---| @@ -215,8 +215,8 @@ All four quadrant full forms pass through `onEnvelope`; the base implementation | Subclass | Package | doFetch | Purpose | |---|---|---|---| -| `InProcessApiClient` | apiproxy itself | the injected `{ fetch }` handler | **The isomorphic point**: `new InProcessApiClient(toFetchHandler(api))` never touches the network yet runs the real wire serialization/zod/SSE framing — `dsh -p` headless is the protocol's second real consumer | -| `WebApiClient` | dsh-client-connection | `globalThis.fetch` (same-origin `/api/*`) | the browser shape; HTTP+SSE carriage details in the web client architecture RFC | +| `InProcessApiClient` | apiproxy itself | the injected `{ fetch }` handler | **The isomorphic point**: `new InProcessApiClient(toFetchHandler(api))` never touches the network yet runs the real wire serialization/zod/SSE framing; carrier tests and callers can exercise the protocol without opening a port, while product `dsh run` drives core directly | +| `WebApiClient` | dsh-client-connection | `globalThis.fetch` uplink + one same-origin WebSocket downlink per logical stream | the browser shape; physical boundary in the [WebSocket downlink carrier](2026-08-04-websocket-downlink-carrier.md) | | `FixtureApiClient` | dsh-client-connection | unused (protocol-layer override) | serverless UI development (`?fixture`): overrides the `callUnary`/`openMux`/`openHost`/`respond` virtuals and is itself the fake server (frame rpcIds minted by it, semantics self-consistent) | | (future) IPC bridge subclass | apps/electron | IPC serialization round trip | swaps only doFetch; contract and base class unchanged | @@ -242,7 +242,7 @@ Every client shape consumes one contract: adding a unary method is a five-step m |---|---| | Packaging by "product shape" (a web family, an electron family) | What shapes share is host/client capability, not the shape itself; capability-provider layering means a new shape needs zero new packages | | A package per mixture (e.g. a standalone headless package) | A mixture has exactly one consumer (its own app); packaging it is ownerless abstraction, while assembly in the app is readable and disposable | -| Consuming clients connecting to ctx directly (skipping the apiproxy layer) | A second command plane bypasses the contract, losing wire validation/observability/multi-client consistency; ctx keeps exactly two formal uses — front doors and headless event subscription | +| Consuming clients connecting to ctx directly (skipping the apiproxy layer) | Client shapes require wire validation, observability, and multi-client consistency. Direct headless is a local front door with no client boundary and uses the public Agent/Session seams rather than a client command plane | | webserver depending on runtime (saving the handler injection) | Structural-typing injection keeps webserver reusable by sidecars/tests with zero workspace deps; a package dependency would drag assembly knowledge into the carrier layer | | Package names without the group prefix (continuing dsh-) | `dsh-runtime`/`dsh-web-ui` lose their belonging in the flat npm namespace; the cost is one explicit paths entry per package | | Reusing the in-repo JSON-RPC 2.0 (dsh-jsonrpc) | Numeric error codes degrade to a single fallback code, contracts get aligned by hand in two copies, and naming drifts without a convention | diff --git a/.agents/notes/implemented/architecture/2026-07-19-gui-layering-and-rpc-protocol.zh.md b/.agents/notes/implemented/architecture/2026-07-19-gui-layering-and-rpc-protocol.zh.md index 90850c469f..ecd577f7ec 100644 --- a/.agents/notes/implemented/architecture/2026-07-19-gui-layering-and-rpc-protocol.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-19-gui-layering-and-rpc-protocol.zh.md @@ -4,17 +4,17 @@ Status: implemented [English](2026-07-19-gui-layering-and-rpc-protocol.md) | 中文 -> 分工线:本篇 = 分层模型 + 通道无关的 RPC 协议;协议的 Web 实现(HTTP+SSE)见 [Web 客户端架构 RFC](2026-07-19-gui-web-client-architecture.md)。 +> 分工线:本篇 = 分层模型 + 通道无关的 RPC 协议;协议的 Web 实现由 HTTP 上行加 [WebSocket 下行载体](2026-08-04-websocket-downlink-carrier.md)组成,浏览器对象层见 [Web 客户端架构 RFC](2026-07-19-gui-web-client-architecture.md)。 ## Problem 需要提供 UI 对接层,除已有 ACP/stdio基础版本外,还需要 Web(server) 、 Electron 、等其他产品 UI 形态。我们把这些形态统一称为 Client。希望有如下能力支持: -- 以 `dsh` 进程,同时支持 `dsh web`(启动) 和 `dsh -p`(headless) ,一个进程两种模式(设计预留) +- 以 `dsh` 进程,同时支持 `dsh web`(启动) 和 `dsh run`(headless) ,一个进程两种模式(设计预留) - 以与 `dsh web` 同构的 Web 技术形态,在 Electron 中启动 那么当前的工程代码需要稳定的分层职责模型,便于以后接入各类 client 形态。 -同时各消费端的物理通道不同(HTTP/SSE、进程内直调、将来 IPC),还需要一个通道无关的消息模型和单一契约事实源,让「加一个方法」「换一种载体」互不牵连,且 wire 上的每条消息可类型校验、可观测、可对账。 +同时各消费端的物理通道不同(浏览器 HTTP/WebSocket、进程内 fetch/SSE、将来 IPC),还需要一个通道无关的消息模型和单一约定事实源,让「加一个方法」「换一种载体」互不牵连,且 wire 上的每条消息可类型校验、可观测、可对账。 ## Decision @@ -29,7 +29,7 @@ Status: implemented - **fetch 到达插件包**(`ui-layout`、`ui-sidebar`、`ui-conversation`、`ui-trajectory`):双入口——根入口是 node 半边(空 `apply`,其存在是为了让 host Loader 管辖生命周期、让 web 插件注册表发现 package.json 的 `dshClient` 声明);实现住在 `src/client/` 下,经 `./client` 子路径发布(tsdown 闭包工厂 bundle)。跨插件消费 `/client` 只限类型;值层面的协作走 cordis 服务。 - `apps/` 作为对外导出的应用形态入口,可以由 Client / Host 混合组装。 - `apps/web`(`dsh-frontend`)是 vite 应用:`dsh-client-web` 导出的壳表面之上的一层薄 `main.ts`。 - - `apps/cli`(`@deepseek-ai/dsh`)做形态分发:`dsh web` = startHost + webserver + 构建出的 `dsh-frontend` dist;`dsh -p` = headless 进程内直调,零 HTTP。 + - `apps/cli`(`@deepseek-ai/dsh`)做形态分发:`dsh web` = Host + webserver + 构建出的 `dsh-frontend` dist;`dsh run` = [直接使用核心 Agent/Session 的前门](2026-08-09-headless-direct-core-front-door.md),不含 Host、HTTP 或浏览器层。 - 将来的 Electron 形态经由 IPC fetch 载体复用同一套 web client 包。 ``` @@ -62,7 +62,7 @@ TypeScript 以 solution 根引用的**两个聚合 program** 检查(`tsconfig. |---|---|---|---| | 前置层 | `dsh-host-apiproxy` | TS/zod 定义 (api/)+ fetch 抽象 (fetch/:handler + 客户端基类) | 做简单、所有接入方都要;Node/浏览器皆可 import;协议内容见下文「消息协议」起各节;client 不得经 ctx 绕开 api | | 装配层 | `dsh-host-runtime` | 插件组合 + ApiProxy 集成 + web UI 插件挂载(覆盖八个 dshClient 包的内存 Loader 树);host 级配置归属地(defaults/persistenceRoot,将来用户 profile) | 装什么插件、给什么默认值只在这里定;壳不得改装配 | -| 承载层 | `dsh-host-webserver` | Web 形态 HTTP:静态服务 + `/api/*`→handler 转发 + SSE 写出 + close 语义;插件 bundle 端点 + `__DSH_BOOT__` manifest(元数据清单)注入(由 web 插件注册表供给) | Web(浏览器访问)专用;零 workspace 依赖(注册表经结构注入到达);Electron 不复用它 | +| 承载层 | `dsh-host-webserver` | Web 形态 HTTP 与 upgrade:静态服务 + `/api/*`→handler 转发 + WebSocket upgrade route + close 语义;插件 bundle 端点 + `__DSH_BOOT__` manifest(元数据清单)注入(由 web 插件注册表供给) | Web(浏览器访问)专用;零 workspace 依赖(注册表经结构注入到达);Electron 不复用它 | | client 库 | `dsh-client-ui-slots` / `dsh-client-web-react` / `dsh-client-ui-primitives` | slot 注册表核心 / ctx↔React 胶合 / 纯 React 原子组件 | 组件零 cordis 运行时依赖;由壳播种进 loader 模块表 | | client 插件 | `dsh-client-connection` / `dsh-client-runtime` / `dsh-client-ui-theme` / `dsh-client-i18n` / `dsh-client-ui-layout` / `dsh-client-ui-sidebar` / `dsh-client-ui-conversation` / `dsh-client-ui-trajectory` | 浏览器侧 cordis 插件树(wire 消费者、核心服务、主题、i18n、布局、侧栏、对话、轨迹)——见 Web 客户端架构 RFC | 双入口(node 半边=空 apply;实现在 `src/client/`);消费面唯一经 ApiProxy | | 应用态 | `@deepseek-ai/dsh`(apps/cli)+ `dsh-frontend`(apps/web,vite 应用) | bin 粗分发 + 每形态一个拼装模块(web.ts / headless.ts);vite 应用是 `dsh-client-web` 壳表面之上的薄 main | 形态间动态 import 互不加载;dist 定位等 workspace 知识留在 app | @@ -77,7 +77,7 @@ TypeScript 以 solution 根引用的**两个聚合 program** 检查(`tsconfig. 2. **在 `apps/` 下写拼装模块**:`startHost()` + 客户端子类 + 该形态私有的信号/打印/退出语义;混合体不建包,拼装写在 app 里。 3. **需要 HTTP 承载才 import `dsh-host-webserver`**,否则零端口。 -现有两形态即模板:`apps/cli/src/web.ts`(startHost + dist 定位 + startWebServer + 信号停机)与 `headless.ts`(startHost + InProcessApiClient 同构直调,零 HTTP 零端口)。ACP 类协议桥不走本清单:它把 core 暴露给外部生态,直接 `ctx.plugin(前门插件)` 挂载、不套 fetch。 +现有两种形态保持这一边界:Web 形态挂载 Host、载体与浏览器组合,而 `dsh run` 挂载直接使用核心服务的 runner,不包含 Host、HTTP 或端口。ACP 类协议桥不遵循 client 载体清单:它把 core 暴露给外部生态,直接通过 `ctx.plugin(前门插件)` 挂载,不套 fetch。 ## 消息协议 @@ -86,7 +86,7 @@ TypeScript 以 solution 根引用的**两个聚合 program** 检查(`tsconfig. ``` client 发起 server 发起 request ① ClientRequest ③ ServerRequest - (POST /api/ body) (SSE 帧:session 事件、审批/问答 requested) + (POST /api/ body) (WebSocket message:session 事件、审批/问答 requested) response ② ServerResponse ④ ClientResponse (该 POST 的 HTTP 应答体) (POST /api/respond body,回填 ③ 的 rpcId) ``` @@ -97,7 +97,7 @@ TypeScript 以 solution 根引用的**两个聚合 program** 检查(`tsconfig. |---|---|---|---|---| | `ClientRequest` | `'client-request'` | `rpcId` `method` `payload` | client mint | `POST /api/` body | | `ServerResponse` | `'server-response'` | `rpcId` `result` | 回填 ① | 该 POST 的应答体(恒 HTTP 200) | -| `ServerRequest` | `'server-request'` | `rpcId` `method` `payload` | server mint | SSE `data:` 行 | +| `ServerRequest` | `'server-request'` | `rpcId` `method` `payload` | server mint | WebSocket text message | | `ClientResponse` | `'client-response'` | `rpcId` `result` | 回填 ③ | `POST /api/respond` body | `RpcMessage = ClientRequest | ServerResponse | ServerRequest | ClientResponse`,`switch (message.type)` 窄化。 @@ -151,7 +151,7 @@ export type ResponseValue = - **锚定**:schema 统一 `satisfies z.ZodType>`(`api/rpc.schema.ts`)。`Wire` 是深度「| undefined」宽化——仓库开 `exactOptionalPropertyTypes` 而 zod `.optional()` 输出 `T | undefined`,直接锚原类型全线不可用;JSON wire 上缺席与 undefined 同形,宽化不损失校验语义。透传宽分支(`SessionEvent`/`ContentBlock`/帧 union/`RpcError`)与 brand id schema 用显式 cast + 注释。 - brand cast 单点:每个 schema 文件的 id cast 收口一处(`rpcIdSchema` 是 rpc.schema.ts 唯一 cast 点)。 -## 契约面(ApiProxy) +## 约定面(ApiProxy) 根接口 `ApiProxy = { sessions, host, events, respond }`(`api/index.ts`)。新 client-request 域 = 新的一对文件(`<域>.ts` + `<域>.schema.ts`)+ 根接口一个字段 + map 加行。 @@ -167,7 +167,7 @@ export type ResponseValue = ### 帧(server→client,具名 union) -两条 SSE 流:mux 流(`GET /api/events.mux`,全 session 聚合)与 host 流(`GET /api/events.host`,host 级事件)。帧示例一行: +两条逻辑流:mux 流(`/api/events.mux`,全 session 聚合)与 host 流(`/api/events.host`,host 级事件)。浏览器通过每流一条下行 WebSocket 消费,进程内 fetch 载体以 SSE 保持同构;物理边界见 [WebSocket 下行载体](2026-08-04-websocket-downlink-carrier.md)。帧示例一行: | 帧 type | 载荷 | 何时发 | |---|---|---| @@ -183,7 +183,7 @@ export type ResponseValue = - **prompt 关联**:prompt 的 rpcId 经 MessageSource(`'user-rpc'`)透传进 `user/message` 事件,client 以此把乐观回显转正。 - **重连 = 重建**:不做续传 cursor(`mux` 的 `since` 签名留座、传了忽略);断线重开流 + 重拉 history;`subscribed.lastSeq` 与 history 尾 seq 比对,有缝再补拉一次。 - **冷会话处理遵循所有权**:`session.history` 与 `session.fork` 的源端读取会在不获取 Agent 的情况下检查持久化存储,而绑定到 Agent 的普通会话方法(如 `prompt`)则通过在途表去重后恢复会话。由会话支撑的 subagent 会拒绝这条通用恢复路径,且附加状态不对客户端暴露(`running` 已经覆盖)。 -- **审批/问答**:requested 帧受理时 mint 稳定 rpcId;先到先赢,host 内存 pending 表(keyed by rpcId)是唯一裁判;mux 重开后在 subscribed 帧后重放仍 pending 的 requested 帧(rpcId 原样复用,刷新恢复)。审计事件 `approval/asked`/`decided` 照旧走 durable 日志——帧=live 控制面,事件=durable 审计。**现状**:契约与帧类型已 shipped,host 侧 pending 表/wire answerer 未实现(`api-proxy.ts` 的 `respond` 是 stub,恒回 `not-pending`);PendingCard v1 只展示。 +- **审批/问答**:requested 帧受理时 mint 稳定 rpcId;先到先赢,host 内存 pending 表(keyed by rpcId)是唯一裁判;mux 重开后在 subscribed 帧后重放仍 pending 的 requested 帧(rpcId 原样复用,刷新恢复)。审计事件 `approval/asked`/`decided` 照旧走 durable 日志——帧=live 控制面,事件=durable 审计。**现状**:约定与帧类型已 shipped,host 侧 pending 表/wire answerer 未实现(`api-proxy.ts` 的 `respond` 是 stub,恒回 `not-pending`);PendingCard v1 只展示。 - **不设协议版本**:client 与 host 绑定发布,`host.describe` 无 protocolVersion 字段;出现独立发布的 client 时再引入。 - **预留接缝纪律**:map 只含已实现方法,未知 method 在信封 parse 即 fail loud(`bad-request`),不设 not-implemented 兜底码。预留清单(实现时把签名抄进域接口+map 加行+schema 加对即升格):`session.fork`、`prompt.mode` 加 `'inject'`、`task.list`、`host.listModels`、describe 加 `hostInstanceId`。(`session.rename` 已从本清单毕业:追加 user 来源的 `session/title` 事件。) @@ -193,7 +193,7 @@ export type ResponseValue = ### IApiClient:caller 视图 -与 `ApiProxy` 同域树,但 unary 方法**收业务 payload 直传**——载体 mint rpcId 并包信封,业务代码永不 mint;需要本次调用 rpcId 的从返回的 `RpcResponse` 回显里读。`ApiProxy` 是 impl 侧实现的窄形签名契约,`IApiClient` 是 client 侧消费的 payload 直传视图,`AbstractApiClient` 桥接两者。方法逐 key 从 `RpcMethodMap` 派生——map 加行即机械更新。 +与 `ApiProxy` 同域树,但 unary 方法**收业务 payload 直传**——载体 mint rpcId 并包信封,业务代码永不 mint;需要本次调用 rpcId 的从返回的 `RpcResponse` 回显里读。`ApiProxy` 是 impl 侧实现的窄形签名约定,`IApiClient` 是 client 侧消费的 payload 直传视图,`AbstractApiClient` 桥接两者。方法逐 key 从 `RpcMethodMap` 派生——map 加行即机械更新。 ### 基类持有的协议路径 @@ -213,10 +213,10 @@ export type ResponseValue = | 子类 | 所在包 | doFetch | 用途 | |---|---|---|---| -| `InProcessApiClient` | apiproxy 本包 | 注入的 `{ fetch }` handler | **同构点**:`new InProcessApiClient(toFetchHandler(api))` 全程不过网络但真跑 wire 序列化/zod/SSE 帧——`dsh -p` headless 即协议第二真实消费者 | -| `WebApiClient` | dsh-client-connection | `globalThis.fetch`(同源 `/api/*`) | 浏览器形态;HTTP+SSE 承载落地见 Web 客户端架构 RFC | +| `InProcessApiClient` | apiproxy 本包 | 注入的 `{ fetch }` handler | **同构点**:`new InProcessApiClient(toFetchHandler(api))` 全程不过网络但真跑 wire 序列化/zod/SSE 帧;载体测试与调用方可以在不打开端口的情况下运行这套协议,而产品 `dsh run` 直接驱动 core | +| `WebApiClient` | dsh-client-connection | `globalThis.fetch` 上行 + 每逻辑流一条同源 WebSocket 下行 | 浏览器形态;物理边界见 [WebSocket 下行载体](2026-08-04-websocket-downlink-carrier.md) | | `FixtureApiClient` | dsh-client-connection | 不用(协议层覆写) | 无 server 的 UI 开发(`?fixture`):覆写 `callUnary`/`openMux`/`openHost`/`respond` 虚方法,自己就是假 server(帧 rpcId 由它 mint,语义自洽) | -| (将来)IPC 桥子类 | apps/electron | IPC 序列化往返 | 仅换 doFetch,契约/基类零改 | +| (将来)IPC 桥子类 | apps/electron | IPC 序列化往返 | 仅换 doFetch,约定/基类零改 | ## 怎么扩展(操作清单) @@ -226,13 +226,13 @@ export type ResponseValue = **加一个错误码(2 步)**:①`RpcErrorDetailsMap` 加一行(details 必填);②`rpcErrorSchema` discriminatedUnion 加一支。 -**接一种新载体**:继承 `AbstractApiClient` 只实现 `doFetch`;需要拦截协议层(如 fixture)再覆写 `callUnary`/`openMux`/`openHost` 虚方法。契约与基类零改。 +**接一种新载体**:继承 `AbstractApiClient` 只实现 `doFetch`;需要拦截协议层(如 fixture)再覆写 `callUnary`/`openMux`/`openHost` 虚方法。约定与基类零改。 **升格一个预留接缝**:把预留签名抄进域接口 → map 加行 → schema 加对 → UNARY_ROUTES 加行 → impl 实现。 ## Consequences -所有 client 形态消费同一契约:加一个 unary 方法是从单一签名辐射的五步机械改动,换载体只动一个 `doFetch` 子类,wire 上每条消息可 zod 校验、可经 envelope tap 观测、可按 rpcId 对账。普通 unary 调用仍受时限约束,而 `host.pickDirectory` 与 `command.execute` 可保持挂起,直到操作完成或调用方/连接取消到来;若由用户掌控节奏的操作不自行结束,请求可能一直挂起,这是为避免把合理的操作时长视为传输失败而接受的代价。其余接受的代价:两组包需要显式 tsconfig paths 条目;预留接缝(fork/inject/task.list/listModels/hostInstanceId)在真实消费者出现前保持休眠。 +所有 client 形态消费同一约定:加一个 unary 方法是从单一签名辐射的五步机械改动,换载体只动一个 `doFetch` 子类,wire 上每条消息可 zod 校验、可经 envelope tap 观测、可按 rpcId 对账。普通 unary 调用仍受时限约束,而 `host.pickDirectory` 与 `command.execute` 可保持挂起,直到操作完成或调用方/连接取消到来;若由用户掌控节奏的操作不自行结束,请求可能一直挂起,这是为避免把合理的操作时长视为传输失败而接受的代价。其余接受的代价:两组包需要显式 tsconfig paths 条目;预留接缝(fork/inject/task.list/listModels/hostInstanceId)在真实消费者出现前保持休眠。 ## Alternatives considered @@ -240,10 +240,10 @@ export type ResponseValue = |---|---| | 按「产品形态」分包(web 一族、electron 一族) | 形态间共享的是 host/client 两侧能力而非形态本身;能力支持方分层让新形态零新包 | | 混合体建包(如 headless 独立包) | 混合体只有一个消费者(它自己的 app),建包是无主抽象;拼装写在 app 里可读可弃 | -| 消费型 client 直连 ctx(省 apiproxy 一层) | 第二命令面绕开契约,wire 校验/观测/多端一致性全失;ctx 只留给前门与 headless 事件订阅两个正式用途 | +| 消费型 client 直连 ctx(省 apiproxy 一层) | client 形态需要 wire 校验、观测与多 client 一致性。直接 headless 是没有 client 边界的本地前门,使用公开的 Agent/Session seam,而不是 client 命令面 | | webserver 依赖 runtime(省 handler 注入) | 结构 typing 注入让 webserver 可被 sidecar/测试复用且零 workspace 依赖;包依赖会把装配知识拖进承载层 | | 包名不带组前缀(沿用 dsh-<尾段>) | `dsh-runtime`/`dsh-web-ui` 在扁平 npm 命名空间里失去归属信息;代价只是每包一条显式 paths | -| 复用仓内 JSON-RPC 2.0(dsh-jsonrpc) | 数字错误码退化成单码兜底、契约双份人肉对齐、命名无 convention 自然漂移 | +| 复用仓内 JSON-RPC 2.0(dsh-jsonrpc) | 数字错误码退化成单码兜底、约定双份人肉对齐、命名无 convention 自然漂移 | | 三信封模型(Request/Response/Frame 各一信封,签名不感知方向) | rpcId 是逻辑层关联,帧与应答的方向语义靠通道推断在换载体时即失效 | | 具名 Request/Response 类型对为事实源(map 登记类型对) | 平铺具名类型是同一事实的第二个名字;签名 infer 反推让加方法只改一处 | | REST 风格路径 | 消费者是自家 client,无第三方 REST 体验诉求;RPC 直映方法表更机械 | diff --git a/.agents/notes/implemented/architecture/2026-07-19-gui-web-client-architecture.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-19-gui-web-client-architecture.i18n.yaml index 61e6a93e23..5523e6d3b2 100644 --- a/.agents/notes/implemented/architecture/2026-07-19-gui-web-client-architecture.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-19-gui-web-client-architecture.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-19-gui-web-client-architecture.md -2026-07-19-gui-web-client-architecture.md: b1f777172774f1cf8fef4d9494f15b38064d0c73 -2026-07-19-gui-web-client-architecture.zh.md: e43151b7d5ff096d574c786e3aae107523d22c96 +2026-07-19-gui-web-client-architecture.md: e25d002b92df2016faf4073108aa905b65a1b115 +2026-07-19-gui-web-client-architecture.zh.md: 10779107a9dc6dc7335b2c5932c8c4877b531b50 diff --git a/.agents/notes/implemented/architecture/2026-07-19-gui-web-client-architecture.md b/.agents/notes/implemented/architecture/2026-07-19-gui-web-client-architecture.md index b1f7771727..e25d002b92 100644 --- a/.agents/notes/implemented/architecture/2026-07-19-gui-web-client-architecture.md +++ b/.agents/notes/implemented/architecture/2026-07-19-gui-web-client-architecture.md @@ -44,7 +44,7 @@ Implementation homes: registry core and the props-share types in `packages/clien A service is a plugin's only API surface toward other plugins (UI components and injection faces are not APIs; a plugin nobody calls mounts no service — ui-trajectory is the minimal-plugin exemplar: no ctx service, only view-slot registrations). The roster: `ctx.connection` (api client + stream handles), `ctx.slots` (registry wrapper emitting `slots/changed`, render entry, renderer install seam), `ctx.sessions` (list store, current-session state, scope tree), `ctx.loader`, `ctx.theme`, `ctx.i18n`, `ctx.layout` (cross-plugin view navigation), `ctx.conversation` (send/cancel/startSession). Viewing state that used to live in service stores (panel widths, selection, drafts) now lives in entry-declared stores per the [slot system standard](2026-07-22-slot-type-chain-implementation.md). -There is no registration model besides slots — the former view and tool rings both dissolved into it. Conversation views are entries of the `'conversation.view'` list slot ui-conversation declares, tab metadata rides the registration options (`id`/`order`/`label`), and per-view chrome lives inside the view components themselves. A tool row is a keyed child slot each view declares for itself — today `'conversation.chat.toolview'` (keyed/session), declared by the chat entry's `children` table; the key space is runtime-open (SlotMap declares slots, never keys), which is what the tool ring's open tool-name set required. The render site dispatches per row via `entryKey: toolName` with `GenericToolCard` as the call-site `fallback`; the owner payload is the uniform `ToolRowOwnerProps` (`callId`/`toolName`/`block`/`openDetails`), and `ToolRowProps` composes it with the session standard kit for registrant components. Registrants are plain plugins with zero dedicated machinery: `ctx.slots.register({ name: 'conversation.chat.toolview', key: '', inject? }, Row)`, with `inject: ['slots', 'conversation']` as the load-order seam (the conversation service being present guarantees the slot is declared). Interaction drafts and other row state ride the ordinary store seat. Trajectory/waterfall get same-shaped slots (names fixed by the slot-naming discipline `..`, one shared owner type) that land with their own row render sites — RendersCheck rejects a declaration nobody renders, so the two slots cannot be declared early. +There is no registration model besides slots — the former view and tool rings both dissolved into it. Conversation views are entries of the `'conversation.view'` list slot ui-conversation declares, tab metadata rides the registration options (`id`/`order`/`label`), and per-view chrome lives inside the view components themselves. Tool presentation crosses one explicit package boundary: Runtime projects Code Dispatch topology into each root's recursive `subCalls`; ui-conversation places that ordered root into the single `'conversation.chat.tool'` seat without interpreting Tool names or topology; ui-tool renders the supplied tree and declares the keyed/session `'tool.call.toolview'` child slot. The key space stays runtime-open (SlotMap declares slots, never keys), and roots and descendants dispatch by `entryKey: toolName` with `GenericToolCard` as the fallback. Business packages register atomic views through `ctx.slots.inject('tool.call.toolview', () => ctx.slots.register({ name: 'tool.call.toolview', key: '', inject? }, Row))`; the declaration is the load and reload dependency ([decision](2026-08-05-slot-declaration-injection.md)). ui-conversation separately delegates the selected call's details body through `'conversation.details.tool'`, so ui-tool's card models remain the single presentation owner without making conversation import Tool components. **Scope addressing** mirrors the host's agent-scope idiom: services are root singletons whose methods take no sessionId — they read the caller's scope mark (`scopeOf(ctx)`). Inside a session scope, `ctx.conversation.send('hi', 'queue')` targets that session; cross-session calls re-target by switching ctx (`ctx.sessions.scope(id)!.conversation.send(...)`); calling a scoped method from root ctx throws. Client session scopes are minted like host agent scopes (a no-op plugin fiber + a scope-key extend), built lazily on first viewing and torn down only when the session is removed and unwatched — host-session death alone does not tear a scope (it freezes into a read-only viewport). @@ -73,7 +73,7 @@ Notifier 微任务合批 ──► ConversationSnapshot 缓存 ──uSES── - **SessionManager** (manager.ts): instance cluster + frame entry + the session list. sessionId-bearing frames go only to existing instances (a mux broadcast must not instantiate every session); approval/question `requested` frames are the exception — they never land in history, so they buffer in `pendingBuffers` and replay on instantiation. - **Notifier** (notifier.ts): two channels chosen by change source. `markDirty()` (default; frame-driven changes always) batches per microtask — N changes, one notification, one re-render; the flush rebuilds the snapshot cache before notifying. `notifyNow()` (only direct echoes of user gestures) rebuilds and notifies in the same tick — controlled inputs roll the DOM back and jump the caret if their echo defers to a microtask. Frame-driven code using notifyNow collapses batching back to per-frame renders; banned. - **TranscriptAdapter / PartialAccumulator**: the transcript is the append-origin surface projected in log order (`isAppendSurfaceEvent` from `@deepseek-ai/dsh-session/surface`) plus one marker per landed compaction checkpoint — never the model surface, which shadows replaced ranges and would erase conversation the reader already saw. Node order is seq-monotonic by construction, so there is no core `seq === index` assertion to satisfy and no degradation branch. Chunks contribute no node (O(1) skip): the accumulator folds StreamChunks into `AssistantBlock[]`, a delta swapping only that block's reference, and the finalizing message discards the accumulator in the same batch (no flicker on promotion). Cost model: one chunk = one string concatenation + a dirty mark; an unsubscribed Session under a frame storm costs only the mark. -- **ConnectionController** (in `packages/client/connection`): opens the mux/host streams, pumps with for-await, reconnects with exponential backoff (500ms doubling to 10s, jitter, unlimited) behind a generation fence; sinks are injected one-way (the Controller does not know Session). Reconnect = rebuild: `onConnected` → list refresh + per-open-session resync. The object layer faces only `IApiClient`; the Web carriage (HTTP POST for the two client→server quadrants, SSE for the two server→client) and the client class family are the layering RFC's territory. +- **ConnectionController** (in `packages/client/connection`): opens the mux/host streams, pumps with for-await, reconnects with exponential backoff (500ms doubling to 10s, jitter, unlimited) behind a generation fence; sinks are injected one-way (the Controller does not know Session). Reconnect = rebuild: `onConnected` → list refresh + per-open-session resync. The object layer faces only `IApiClient`; Web carriage uses HTTP POST for the two client→server quadrants and [one WebSocket per logical stream](2026-08-04-websocket-downlink-carrier.md) for the two server→client quadrants, while the client class family remains the layering RFC's territory. ## The React face (`packages/client/web-react`) @@ -86,22 +86,24 @@ The glue package is the whole ctx↔React boundary; components stay framework-fr ## Directory shape -Twelve `packages/client/*` packages (ui-slots, ui-primitives, web-react, connection, runtime, ui-layout, ui-sidebar, ui-conversation, ui-trajectory, ui-theme, i18n, web) plus `apps/web` — the vite application, a thin `main` over the shell's boot export. Plugin packages keep their browser half under `src/client/`; **every build artifact lands in `lib/`** — the node half as `lib/index.js`/`lib/invariant.js`, the browser bundle as `lib/client.js` (the shared tsdown client preset emits both; there is no `dist/` directory, and `exports["./client"]` points at `./lib/client.js`). Dependency direction: `ui-slots ← web-react ← runtime ← ui-* (peers) ← web`, with ui-primitives/ui-theme/i18n as zero-dependency side paths. +Client packages live under `packages/client/*`, with `apps/web` as the thin Vite application over the shell's boot export. Plugin packages keep their browser half under `src/client/`; **every build artifact lands in `lib/`** — the node half as `lib/index.js`/`lib/invariant.js`, the browser bundle as `lib/client.js` (the shared tsdown client preset emits both; there is no `dist/` directory, and `exports["./client"]` points at `./lib/client.js`). `ui-slots`, web-react, and runtime form the infrastructure direction; feature plugins cooperate through services and slots rather than importing presentation implementations. A multi-domain plugin package additionally splits its client half by future package boundaries — ui-conversation is the exemplar: ``` src/client/ - contract/ the only shared face between domains (types + composed props shares) - service.ts cross-domain orchestration (imports contract only) - skeleton/ domain: shell components (ConversationRoot/InputBar/EmptyState/DetailsPanel) - chat/ domain: the chat view - toolviews/ domain: sample tool-row registrants (third-party posture) - apply.ts the ONLY file allowed to import across domains (assembly point) - index.ts thin re-export shell (contract + apply + components) + contract/ shared slot and cross-domain types + service.ts cross-domain orchestration + skeleton/ conversation shell and details host + chat/ ordered conversation view + input/ composer state machine + queue/ queued-message presentation + settings/ conversation settings rows + apply.ts cross-domain assembly point + index.ts public contract surface ``` -Domain implementation files never import a sibling domain — shared surfaces route through `contract/` (e.g. the toolviews samples take `ToolRowProps` from the contract, never chat internals). `scripts/verify-client-domain-graph.ts` enforces the layering (contract=0, domains=1, apply/index=2; imports may only point at levels ≤ own; sibling-domain edges fail). A future package split promotes each domain directory to a package and mechanically rewrites import paths. +Domain implementation files never import a sibling domain; shared surfaces route through `contract/`. `scripts/verify-client-domain-graph.ts` enforces the layering (contract=0, domains=1, apply/index=2; imports may only point at levels ≤ own; sibling-domain edges fail). Tool presentation is already a separate `ui-tool` package and reaches chat and details only through the slots ui-conversation declares. ## How to develop @@ -122,5 +124,5 @@ Token streams no longer shake the render tree: a frame storm costs unsubscribed | One statically-linked SPA bundle | Plugins must be host-composable at runtime (config-driven); a monolith re-couples every UI feature to one build | | window globals / import maps for shared deps | The DI require table keeps sharing explicit, fail-loud, and swappable; globals leak identity and version silently | | Business data in zustand slices | The event window/accumulator is a behavioral state machine, not a flat slice; the object layer keeps snapshot granularity and batching controllable | -| String-keyed global component registry for tool rows | Per-view keyed child slots plus in-component session branching carry the same need with the one registration model; a parallel registry does not come back ([toolview dissolution](2026-07-23-toolview-dissolution.md)) | +| Parallel string-keyed component registry for Tool rows | ui-tool's keyed child slot carries the runtime-open Tool-name set through the one slot registration model ([toolview dissolution](2026-07-23-toolview-dissolution.md)) | | Progressive/Suspense boot in P-I | One-flip boot is strictly simpler; the loader's per-plugin status face is kept so progressive lighting can land later without re-architecture | diff --git a/.agents/notes/implemented/architecture/2026-07-19-gui-web-client-architecture.zh.md b/.agents/notes/implemented/architecture/2026-07-19-gui-web-client-architecture.zh.md index e43151b7d5..10779107a9 100644 --- a/.agents/notes/implemented/architecture/2026-07-19-gui-web-client-architecture.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-19-gui-web-client-architecture.zh.md @@ -4,7 +4,7 @@ Status: implemented [English](2026-07-19-gui-web-client-architecture.md) | 中文 -> 分工线:通道无关的分层模型与 RPC 协议(消息模型/类型体系/契约面/客户端基类)见 [分层与 RPC 协议 RFC](2026-07-19-gui-layering-and-rpc-protocol.md);本篇 = 浏览器侧:client cordis 树如何装载、UI 插件如何经 slot 与服务组合、React-free 对象层如何以不可变快照供给 React。 +> 分工线:通道无关的分层模型与 RPC 协议(消息模型/类型体系/约定面/客户端基类)见 [分层与 RPC 协议 RFC](2026-07-19-gui-layering-and-rpc-protocol.md);本篇 = 浏览器侧:client cordis 树如何装载、UI 插件如何经 slot 与服务组合、React-free 对象层如何以不可变快照供给 React。 ## Problem @@ -44,7 +44,7 @@ slot 体系有自己的 RFC——[slot 体系标准](2026-07-22-slot-type-chain- 服务是插件对其他插件的唯一 API 面(UI 组件与注入面都不是 API;无人调用的插件不挂服务——ui-trajectory 即最小插件样板:无 ctx 服务,只做视图坑注册)。名册:`ctx.connection`(api client + 流句柄)、`ctx.slots`(注册表包装层,发 `slots/changed`,渲染入口,渲染器安装缝)、`ctx.sessions`(列表 store、当前会话状态、scope 树)、`ctx.loader`、`ctx.theme`、`ctx.i18n`、`ctx.layout`(跨插件视图导航)、`ctx.conversation`(send/cancel/startSession)。过去住在服务 store 里的观看态(面板宽、选中、草稿)现按 [slot 体系标准](2026-07-22-slot-type-chain-implementation.md) 住 entry 声明的 store。 -slot 之外不存在第二种注册模型——原视图环与工具环都已溶解进来。会话视图即 ui-conversation 声明的 `'conversation.view'` list 坑的 entry,tab 元数据随注册 options(`id`/`order`/`label`)走,per-view chrome 住视图组件自身。工具行是各视图自己声明的 keyed 子槽——今天是 `'conversation.chat.toolview'`(keyed/session),由 chat 条目的 `children` 表声明;key 空间运行时开放(SlotMap 声明槽、从不声明 key),这正是工具环「tool 名开放集」的原需求。渲染点逐行以 `entryKey: toolName` 分发、以 `GenericToolCard` 作调用点 `fallback`;owner 载荷是统一的 `ToolRowOwnerProps`(`callId`/`toolName`/`block`/`openDetails`),`ToolRowProps` 把它与 session 标配 kit 预组合供注册方组件取用。注册方就是普通插件、零专用设施:`ctx.slots.register({ name: 'conversation.chat.toolview', key: '', inject? }, Row)`,以 `inject: ['slots', 'conversation']` 作加载序缝(conversation 服务在场即保证槽已声明)。交互草稿等行内状态走普通 store 席位。trajectory/waterfall 得同形槽(槽名按槽名纪律 `<域>.<条目>.<孔位>` 已定死,共用一张 owner 类型),随各自的行渲染点落地——RendersCheck 拒绝无人渲染的声明,两槽无法提前声明。 +slot 之外不存在第二种注册模型——原视图环与工具环都已溶解进来。会话视图即 ui-conversation 声明的 `'conversation.view'` list 坑的 entry,tab 元数据随注册 options(`id`/`order`/`label`)走,per-view chrome 住视图组件自身。Tool 展示跨越一条显式包边界:运行时把 Code Dispatch 拓扑投影进每个 root 递归的 `subCalls`;ui-conversation 把这个已排序 root 放进 single `'conversation.chat.tool'` seat,不解释 Tool 名称或拓扑;ui-tool 渲染传入的树,并声明 keyed/session 的 `'tool.call.toolview'` 子 slot。key 空间仍在运行时开放(SlotMap 声明 slot、从不声明 key),root 与任意深度的后代都按 `entryKey: toolName` 分发,以 `GenericToolCard` 兜底。业务包通过 `ctx.slots.inject('tool.call.toolview', () => ctx.slots.register({ name: 'tool.call.toolview', key: '', inject? }, Row))` 注册原子视图;声明本身就是加载与重载依赖([决策](2026-08-05-slot-declaration-injection.md))。ui-conversation 还通过 `'conversation.details.tool'` 委托选中调用的详情正文,使 ui-tool 的 card model 保持为唯一展示所有者,同时避免 conversation 导入 Tool 组件。 **scope 寻址**与 host 侧 agent scope 惯例同构:服务是 root 单例,方法不收 sessionId——它们读调用方 ctx 上的 scope 标(`scopeOf(ctx)`)。在会话 scope 内,`ctx.conversation.send('hi', 'queue')` 自动打到该会话;跨会话调用换 ctx 定向(`ctx.sessions.scope(id)!.conversation.send(...)`);从 root ctx 直接调 scoped 方法即 throw。client 会话 scope 的铸造方式与 host agent scope 相同(no-op 插件 fiber + scope 键 extend),首次观看时惰性建,只有会话被移除且无人观看才拆——仅 host 会话死亡不拆 scope(冻结为只读视窗)。 @@ -69,44 +69,46 @@ Notifier 微任务合批 ──► ConversationSnapshot 缓存 ──uSES── ``` - **Session**(session.ts):懒建、常驻——建成后在后台持续吃帧,切走切回秒显。操作面:`prompt`/`cancel`(RPC 透传;失败落进快照的 `promptError`)、`open`(拉尾页 history,幂等)、`loadOlder`(向上翻页,防重入)、`resync`(重连 = 清窗口重跑 open)。订阅面:`subscribe`/`getSnapshot`(恒返缓存引用)——`implements ObservableSnapshot`,构造时挂 `useSelector = bindSnapshotSelector(this)`,Session 本身就是 uSES 源。帧分发是一个 switch:`session/event` 帧按 seq 去重(唯一去重键),open 在途时缓冲,否则追加 + 增量投影;open/缝合按 seq 合并 live 缓冲并去重,`subscribed.lastSeq` 超出窗口尾则回补一次。 -- **ConversationSnapshot**(conversation.ts):不可变快照契约——`nodes`(人类对话记录,日志序)、`partial`、`runningCalls`、`pending`、`running`、`removed`、`openState`、`hasMore`、`promptError` 等。**引用纪律**(memo 与 uSES 的前提):顶层对象每变必新;未变化的 nodes 投影保持同一数组引用,消息流变化时返回新数组并复用未变化的元素引用;未变的子结构复用上一快照的引用。 +- **ConversationSnapshot**(conversation.ts):不可变快照约定——`nodes`(人类对话记录,日志序)、`partial`、`runningCalls`、`pending`、`running`、`removed`、`openState`、`hasMore`、`promptError` 等。**引用纪律**(memo 与 uSES 的前提):顶层对象每变必新;未变化的 nodes 投影保持同一数组引用,消息流变化时返回新数组并复用未变化的元素引用;未变的子结构复用上一快照的引用。 - **SessionManager**(manager.ts):实例簇 + 帧总入口 + 会话列表。带 sessionId 的帧只投已存在实例(mux 广播不得把每个会话都实例化);例外是审批/问答 `requested` 帧——它们不落 history、open 无法回补,故缓冲进 `pendingBuffers`,实例化时回放。 - **Notifier**(notifier.ts):两条通知通道,按变更来源取用。`markDirty()`(默认;帧驱动一律用它)按微任务合批——N 次变更、一次通知、一次重渲染;flush 先重建快照缓存再通知。`notifyNow()`(仅用户手势的直接回响)同 tick 重建并通知——受控输入的回响若延到微任务,DOM 会回滚、光标跳尾。帧驱动代码用 notifyNow 会让合批塌回逐帧渲染;禁。 - **TranscriptAdapter / PartialAccumulator**:对话记录是按日志顺序投影的 append 来源 surface(`@deepseek-ai/dsh-session/surface` 的 `isAppendSurfaceEvent`),外加每次落地的压缩检查点一个标记——绝不用模型 surface,后者遮蔽被替换的范围,会抹掉读者已经看过的对话。节点顺序天然按 seq 单调,因此既无核心 `seq === index` 断言需要满足,也没有降级分支。分片不贡献任何节点(O(1) 跳过):累积器把 StreamChunk 折叠成 `AssistantBlock[]`,一次增量只换该块引用;定稿消息到达即在同一批内弃掉累积器(提升无闪烁)。成本模型:一个分片 = 一次字符串拼接 + 一个脏标记;帧风暴下未订阅的 Session 只花那个标记。 -- **ConnectionController**(在 `packages/client/connection`):开 mux/host 双流、for-await 泵入,代际围栏之内指数退避重连(500ms 翻倍至 10s 封顶、抖动、无限重试);sinks 单向注入(Controller 不认识 Session)。重连 = 重建:`onConnected` → 列表刷新 + 各已打开会话 resync。对象层只面向 `IApiClient`;Web 承载(HTTP POST 载两个 client→server 象限、SSE 载两个 server→client 象限)与客户端类族归分层 RFC 属地。 +- **ConnectionController**(在 `packages/client/connection`):开 mux/host 双流、for-await 泵入,代际围栏之内指数退避重连(500ms 翻倍至 10s 封顶、抖动、无限重试);sinks 单向注入(Controller 不认识 Session)。重连 = 重建:`onConnected` → 列表刷新 + 各已打开会话 resync。对象层只面向 `IApiClient`;Web 承载以 HTTP POST 载两个 client→server 象限、以[每逻辑流一条 WebSocket](2026-08-04-websocket-downlink-carrier.md)载两个 server→client 象限,客户端类族归分层 RFC 属地。 ## React 面(`packages/client/web-react`) 胶水包就是整条 ctx↔React 边界;组件保持零框架依赖。 -- 快照 store 引擎**住 runtime 包**(zustand vanilla + 草稿式更新,缺省 `flush: 'sync'`,帧驱动 store 可选 `'raf'` 合批,可选整值 localStorage 持久化,dev 深冻结——全部从 `runtime` 的 `./client` 主出口导出,无子路径):store 产物是裸的可观察源,不带任何 hook 成员。插件只经 [slot 体系标准](2026-07-22-slot-type-chain-implementation.md) 的 `defineStore` 声明触及引擎。web-react 在绑定处(`bindSnapshotSelector`,按源缓存)从 React 消费的唯一数据契约合成每个 hook:`ObservableSnapshot`(`getSnapshot`/`subscribe`)——Session 对象与快照 store 同构满足它。业务插件包只依赖 runtime 与 ui-slots;web-react 是仅壳可用的胶水。 -- `bindSnapshotSelector(source)`:把一个源绑定为经 uSES-with-selector 的带类型 selector hook。uSES 契约四条按构造成立:getSnapshot 恒返缓存引用;subscribe 是绑定期闭包(引用永稳);纯 CSR 不传 server snapshot;相等性缺省 `Object.is`,按调用可选 `shallowEqual`。 +- 快照 store 引擎**住 runtime 包**(zustand vanilla + 草稿式更新,缺省 `flush: 'sync'`,帧驱动 store 可选 `'raf'` 合批,可选整值 localStorage 持久化,dev 深冻结——全部从 `runtime` 的 `./client` 主出口导出,无子路径):store 产物是裸的可观察源,不带任何 hook 成员。插件只经 [slot 体系标准](2026-07-22-slot-type-chain-implementation.md) 的 `defineStore` 声明触及引擎。web-react 在绑定处(`bindSnapshotSelector`,按源缓存)从 React 消费的唯一数据约定合成每个 hook:`ObservableSnapshot`(`getSnapshot`/`subscribe`)——Session 对象与快照 store 同构满足它。业务插件包只依赖 runtime 与 ui-slots;web-react 是仅壳可用的胶水。 +- `bindSnapshotSelector(source)`:把一个源绑定为经 uSES-with-selector 的带类型 selector hook。uSES 约定四条按构造成立:getSnapshot 恒返缓存引用;subscribe 是绑定期闭包(引用永稳);纯 CSR 不传 server snapshot;相等性缺省 `Object.is`,按调用可选 `shallowEqual`。 - `useInvoke(fn)`:把异步动作包成引用恒定的触发器加 pending 标志;pending 走 per-hook 外部 store 经 uSES 读出(渲染路径零 setState),并发调用计数,invoke 引用永不变。 - 相等性协议,全链一致:生产端结构共享;消费端以 `Object.is` 或 `shallowEqual` 短路;`React.memo` 浅比较。深比较全链禁止。 ## 目录形态 -十二个 `packages/client/*` 包(ui-slots、ui-primitives、web-react、connection、runtime、ui-layout、ui-sidebar、ui-conversation、ui-trajectory、ui-theme、i18n、web)加 `apps/web`——vite 应用,壳 boot 导出之上的薄 `main`。插件包的浏览器半边在 `src/client/` 下;**一切构建产物落 `lib/`**——node 半边为 `lib/index.js`/`lib/invariant.js`,浏览器 bundle 为 `lib/client.js`(共享 tsdown client 预设两者皆出;无 `dist/` 目录,`exports["./client"]` 指向 `./lib/client.js`)。依赖方向:`ui-slots ← web-react ← runtime ← ui-*(并列)← web`,ui-primitives/ui-theme/i18n 为零依赖旁路。 +Client 包位于 `packages/client/*`,`apps/web` 是壳 boot 导出之上的薄 Vite 应用。插件包的浏览器半边在 `src/client/` 下;**一切构建产物落 `lib/`**——node 半边为 `lib/index.js`/`lib/invariant.js`,浏览器 bundle 为 `lib/client.js`(共享 tsdown client 预设两者皆出;无 `dist/` 目录,`exports["./client"]` 指向 `./lib/client.js`)。`ui-slots`、web-react 与 runtime 构成基础设施方向;功能插件通过 service 与 slot 协作,不导入展示实现。 多域插件包的 client 半边还按未来包边界再拆——ui-conversation 即样板: ``` src/client/ - contract/ the only shared face between domains (types + composed props shares) - service.ts cross-domain orchestration (imports contract only) - skeleton/ domain: shell components (ConversationRoot/InputBar/EmptyState/DetailsPanel) - chat/ domain: the chat view - toolviews/ domain: sample tool-row registrants (third-party posture) - apply.ts the ONLY file allowed to import across domains (assembly point) - index.ts thin re-export shell (contract + apply + components) + contract/ shared slot and cross-domain types + service.ts cross-domain orchestration + skeleton/ conversation shell and details host + chat/ ordered conversation view + input/ composer state machine + queue/ queued-message presentation + settings/ conversation settings rows + apply.ts cross-domain assembly point + index.ts public contract surface ``` -域实现文件永不 import 兄弟域——共享面一律走 `contract/`(如 toolviews 样例从契约取 `ToolRowProps`,永不碰 chat 内部)。`scripts/verify-client-domain-graph.ts` 把守分层(contract=0、域=1、apply/index=2;import 只准指向 ≤ 自己的层级;兄弟域边即失败)。将来拆包=每个域目录升格为包+机械改写 import 路径。 +各领域实现文件不 import 兄弟领域;共享面统一经过 `contract/`。`scripts/verify-client-domain-graph.ts` 把守分层(contract=0、domain=1、apply/index=2;import 只准指向不高于自身的层级;兄弟领域依赖会失败)。Tool 展示已经拆为独立 `ui-tool` 包,只通过 ui-conversation 声明的 slot 到达 chat 与 details。 ## 怎么开发 - **新 UI 功能** = 新插件包:package.json 声明 `dshClient`(+ `inject` 拓扑),浏览器半边写在 `src/client/`(apply 挂服务/建 store、注册 slot),无 host 逻辑时 node 半边保持空 apply,用共享预设构建。把插件加进 host 配置;manifest 与装载随之自动跟上。 -- **新 slot**:见 [slot 体系标准 RFC](2026-07-22-slot-type-chain-implementation.md)——契约合并进 `SlotMap`,在父 entry 的 `children` 里声明,经自动注入的 `renderSlot` prop 渲染。永不全局导出组件。 +- **新 slot**:见 [slot 体系标准 RFC](2026-07-22-slot-type-chain-implementation.md)——约定合并进 `SlotMap`,在父 entry 的 `children` 里声明,经自动注入的 `renderSlot` prop 渲染。永不全局导出组件。 - **消费新帧类型**:带 sessionId → Session 分发 switch 加一个分支;host 级 → Manager 路由表;UI 需要时给 `ConversationSnapshot` 加字段并守住引用纪律。 - **状态住哪**:业务数据(事件、流式、待答)→ 永远对象层;父知道的 → renderSlot 现场的 owner props;单组件私有(滚动、搜索词、展开集)→ 组件状态;跨 entry 共享或跨重挂载存活(选中、草稿、面板宽)→ entry 声明的 store([slot 体系标准](2026-07-22-slot-type-chain-implementation.md))。 - **通知通道**:帧驱动/异步 = `markDirty` 合批;受控输入需要同 tick 的用户手势直接回响 = `notifyNow`。 @@ -122,5 +124,5 @@ token 流不再震荡渲染树:帧风暴对未订阅会话只花一个脏位 | 静态链接的单 SPA bundle | 插件必须由 host 在运行时按配置组合;单体把每个 UI 功能重新耦回一次构建 | | window 全局变量 / import map 供共享依赖 | DI require 表让共享显式、大声失败、可替换;全局变量静默泄漏身份与版本 | | 业务数据进 zustand 切片 | 事件窗口/累积器是行为状态机,不是扁平切片;对象层保住快照粒度与合批的可控性 | -| 工具行走字符串键的全局组件注册表 | per-view keyed 子槽 + 组件内会话分支以唯一注册模型承载同一需求;平行 registry 不复活([toolview 溶解](2026-07-23-toolview-dissolution.md)) | +| Tool 行使用平行的字符串键组件注册表 | ui-tool 的 keyed 子 slot 通过唯一的 slot 注册模型承载运行时开放的 Tool 名称集合([toolview 溶解](2026-07-23-toolview-dissolution.md)) | | P-I 就做渐进/Suspense 启动 | 一次成型严格更简单;loader 的按插件状态面已保留,渐进点亮日后可落地而无需重构 | diff --git a/.agents/notes/implemented/architecture/2026-07-19-package-invariant-runtime-contracts.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-19-package-invariant-runtime-contracts.i18n.yaml index 0379a79e52..6af30fd423 100644 --- a/.agents/notes/implemented/architecture/2026-07-19-package-invariant-runtime-contracts.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-19-package-invariant-runtime-contracts.i18n.yaml @@ -1,6 +1,6 @@ # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: -# pnpm run verify-translation-pairing --write -2026-07-19-package-invariant-runtime-contracts.md: 40d152b2320ac65f9ea7d8732b1a667236d2780a -2026-07-19-package-invariant-runtime-contracts.zh.md: bd2f440d5dce15b352e7bcea0d1243400d290f11 +# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-19-package-invariant-runtime-contracts.md +2026-07-19-package-invariant-runtime-contracts.md: 86d86f69b606c348e85d1ae654b6b35c4326985a +2026-07-19-package-invariant-runtime-contracts.zh.md: 94d332a34c1d6e681c10832ea4deb559d88b21a6 diff --git a/.agents/notes/implemented/architecture/2026-07-19-package-invariant-runtime-contracts.md b/.agents/notes/implemented/architecture/2026-07-19-package-invariant-runtime-contracts.md index 40d152b232..86d86f69b6 100644 --- a/.agents/notes/implemented/architecture/2026-07-19-package-invariant-runtime-contracts.md +++ b/.agents/notes/implemented/architecture/2026-07-19-package-invariant-runtime-contracts.md @@ -50,7 +50,7 @@ The current 103-package workspace has 21 executable companions and 82 justified | `dsh-user-approval` | Approval asked/decided records pair by call and use valid outcomes and policies. | | `dsh-workflow` | Workflow and child-agent start/end events preserve run metadata, identity, outcome, count, and error relations. | | `dsh-tasks` | Current and terminal task snapshots preserve id/kind, owner, status, and timestamp relationships. | -| `dsh-tool-todo` | Durable whole-list snapshots use unique trimmed items, closed statuses, and at most one active item. | +| `dsh-tool-todo` | Durable whole-list snapshots use unique trimmed items and closed statuses. | | `dsh-time-context` | Plugin-attributed clock readings agree with the session's open turn, next pre-step position, and elapsed baseline; rendered time parses and does not postdate its event. | Session-backed companions validate existing durable events when they load, using the prefix preceding each candidate where the relationship depends on event order. Other checks observe the authoritative live event boundary or mutable service result. Validation runs before publication where accepting an invalid event would otherwise commit bad state. diff --git a/.agents/notes/implemented/architecture/2026-07-19-package-invariant-runtime-contracts.zh.md b/.agents/notes/implemented/architecture/2026-07-19-package-invariant-runtime-contracts.zh.md index bd2f440d5d..94d332a34c 100644 --- a/.agents/notes/implemented/architecture/2026-07-19-package-invariant-runtime-contracts.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-19-package-invariant-runtime-contracts.zh.md @@ -1,4 +1,4 @@ -# Agent Note: 有意义的包不变量契约 +# Agent Note: 有意义的包不变量约定 Status: implemented @@ -6,11 +6,11 @@ Status: implemented ## 问题 -包自有不变量接缝让发布和注册实现了全覆盖,但最初的生成基线允许空安装器。后续方案又用针对插件名称、注入、effect、服务方法和固定纯函数示例的通用断言替代这些空实现。这些断言虽然让每个 companion 都能执行,却没有提高系统安全性:TypeScript、Cordis 启动、包测试和模块加载测试已经约束这些形状,而不变量服务应当发现不可能出现的运行时状态。 +包自有不变量 seam 让发布和注册实现了全覆盖,但最初的生成基线允许空安装器。后续方案又用针对插件名称、注入、effect、服务方法和纯工具库中的固定示例的通用断言替代这些空实现。这些断言虽然让每个 companion 都能执行,却没有提高系统安全性:TypeScript、Cordis 启动、包测试和模块加载测试已经约束这些形状,而不变量服务应当发现不可能出现的运行时状态。 -有用的运行时不变量会关联时间上的多个观测,或关联可变数据结构中的多个部分。例如:终止事件没有对应的开始事件、LLM delta 指向未打开的 block,或持久化结果的身份与请求不同。仅确认声明的方法存在、插件名称符合预期,或常量示例仍返回已知值,都不属于这种关系。 +有用的运行时不变量会关联时间上的多个观测,或关联可变数据结构中的多个部分。例如:终止事件没有对应的开始事件、LLM(大语言模型)delta 指向未打开的块,或持久化结果的身份与请求不同。仅确认声明的方法存在、插件名称符合预期,或常量示例仍返回已知值,都不属于这种关系。 -有些包确实没有可持续观测的关系。纯工具、仅负责组合的包、薄适配器、可执行入口和测试支持包可能仍有重要契约,但类型检查、加载检查、聚焦单元测试或集成测试更适合执行这些契约。强迫这些包添加合成运行时断言,只会让实现围绕通过门禁优化,而不是检测损坏。 +有些包确实没有可持续观测的关系。纯工具、仅负责组合的包、薄适配器、可执行入口和测试支持包可能仍有重要约定,但类型检查、加载检查、聚焦单元测试或集成测试更适合执行这些约定。强迫这些包添加合成运行时断言,只会让实现围绕通过门禁优化,而不是检测损坏。 ## 决策 @@ -23,7 +23,7 @@ Status: implemented 空形式是明确的架构结论,不是生成占位符。如果后续包变更引入可变状态或事件协议,就必须用相应检查替换该说明。 -中央 `dsh-invariants` 服务只负责配置、注册唯一性、子 fiber 生命周期、回滚、释放和归属到包的失败。它不暴露通用插件形状、服务形状或启动断言 helper,也不导入产品包。 +中央 `dsh-invariants` 服务只负责配置、注册唯一性、子 fiber 生命周期、回滚、dispose(资源释放)和归属到包的失败。它不暴露通用插件形状、服务形状或启动断言 helper,也不导入产品包。 ### 已实施的检查 @@ -31,29 +31,29 @@ Status: implemented | 所有者 | 运行时关系 | |---|---| -| `dsh-session` | 序号严格递增、turn/step 包围关系,以及同一 step 内的工具调用/结果配对。 | +| `dsh-session` | 序号严格递增、轮次/步骤包围关系,以及同一步骤内的工具调用/工具结果配对。 | | `dsh-agent` | agent 状态不得重复,并且不能离开终态 disposed。 | -| `dsh-scope` | scoped event 必须携带 carrier,且路由 subject 保持一致。 | -| `dsh-agent-loop` | 从 session 事件日志重建带显式标记的冻结 loop 请求。 | -| `dsh-llm` | stream block 文法、delta 类型/索引匹配、单次 usage、block 闭合和终止 finish。 | -| `dsh-llm-retry` | 持久化重试记录指向当前打开 turn 中最近关闭的 step;每个 step 的记录保持唯一,重试次数单调递增,并且重试次数和非负的定时器延迟均保持在边界内。 | +| `dsh-scope` | 作用域事件必须携带 carrier,且路由 subject 保持一致。 | +| `dsh-agent-loop` | 从会话事件日志重建带显式标记的冻结 loop 请求。 | +| `dsh-llm` | 流中块的文法、delta 类型/索引匹配、单次 usage、块闭合和终止 finish。 | +| `dsh-llm-retry` | 持久化重试记录指向当前打开轮次中最近关闭的步骤;每个步骤的记录保持唯一,重试次数单调递增,并且重试次数和非负的定时器延迟均保持在边界内。 | | `dsh-tools` | pre/execute/post 阶段单调推进,以及最终 execution/result 快照不可变。 | -| `dsh-system-prompt` | 权威 assembly 中 section、tool 和 variable 的数据约束。 | -| `dsh-compact` | compaction start/summary/end 配对、范围端点、token 数量和成功时必须存在 summary。 | -| `dsh-hook-protocol` | hook invocation/result 的关联、dialect、身份和 duration 约束。 | +| `dsh-system-prompt` | 权威 assembly 中 section、工具和 variable 的数据约束。 | +| `dsh-compact` | 压缩(compaction)start/summary/end 配对、范围端点、token 数量和成功时必须存在 summary。 | +| `dsh-hook-protocol` | 钩子 invocation/result 的关联、dialect、身份和 duration 约束。 | | `dsh-sandbox-policy` | 持久化 `sandbox/mode` 事件必须使用封闭的 sandbox-mode 词表。 | | `dsh-fs` | 文件系统决策/观测事件必须携带可用的 target 和 version 身份。 | -| `dsh-goal` | 持久化目标快照保持来源归属、渲染内容、修订号、生命周期和时间戳关系,并保证已准入的目标回合连续编号。 | +| `dsh-goal` | 持久化目标快照保持来源归属、渲染内容、修订号、生命周期和时间戳关系,并保证已准入的 Round 连续编号。 | | `dsh-goal-session` | 目标来源的继续执行消息必须匹配根据此前持久化目标状态重建的提示词。 | -| `dsh-subagent` | provider add/remove 和 child start/end 事件必须保持身份与配对。 | +| `dsh-subagent` | 提供方 add/remove 和 child start/end 事件必须保持身份与配对。 | | `dsh-permission` | 持久化 permission 决策必须引用当前 permission 表中的 preset。 | | `dsh-user-approval` | approval asked/decided 记录按 call 配对,并使用有效 outcome 和 policy。 | -| `dsh-workflow` | workflow 和 child-agent start/end 事件保持 run metadata、身份、outcome、数量和 error 关系。 | -| `dsh-tasks` | 当前与终态 task snapshot 保持 id/kind、owner、status 和 timestamp 关系。 | -| `dsh-tool-todo` | 持久化全量 snapshot 使用唯一且已 trim 的条目、封闭 status,并且最多有一个活动条目。 | -| `dsh-time-context` | 标注插件来源的时钟 reading 必须匹配 session 当前打开的 turn、下一个 step 开始前的位置和 elapsed baseline;渲染时间必须可解析,且不得晚于对应事件。 | +| `dsh-workflow` | 工作流和 child-agent start/end 事件保持 run metadata、身份、outcome、数量和 error 关系。 | +| `dsh-tasks` | 当前与终态 task 快照保持 id/kind、owner、status 和 timestamp 关系。 | +| `dsh-tool-todo` | 持久化全量快照使用唯一且已 trim 的条目和封闭 status。 | +| `dsh-time-context` | 标注插件来源的时钟 reading 必须匹配会话当前打开的轮次、下一个步骤开始前的位置和 elapsed baseline;渲染时间必须可解析,且不得晚于对应事件。 | -基于 session 的 companion 在加载时验证已有持久化事件;关系依赖事件顺序时,会使用每个候选事件之前的事件前缀。其他检查观测权威 live event 边界或可变服务结果。如果接受无效事件会提交错误状态,验证就在发布前执行。 +基于会话的 companion 在加载时验证已有持久化事件;关系依赖事件顺序时,会使用每个候选事件之前的事件前缀。其他检查观测权威实时事件边界或可变服务结果。如果接受无效事件会提交错误状态,验证就在发布前执行。 ### 仓库门禁与测试 @@ -64,7 +64,7 @@ Vitest 为每个包测试拓扑使用 `{ enabled: true }` 挂载 `InvariantServi ## 考虑过的替代方案 - **保留生成的空 companion。** 拒绝,因为包获得有意义的运行时关系后,没有解释的占位符仍可能继续存在。 -- **要求每个包都执行断言。** 拒绝,因为方法存在性、插件形状和固定示例断言会重复更强的类型、加载和单元测试契约,却没有检查运行时一致性。 +- **要求每个包都执行断言。** 拒绝,因为方法存在性、插件形状和固定示例断言会重复更强的类型、加载和单元测试约定,却没有检查运行时一致性。 - **在服务中保留通用形状 helper。** 拒绝,因为这会混淆编译期 API 验证和运行时不变量,并鼓励在中央定义产品假设。 - **把产品检查移入服务。** 拒绝,因为产品词汇、依赖、测试和变更所有权应归属于产生这些数据的包。 - **从根入口隐式注册 companion。** 拒绝,因为组合顺序和可选服务存在性会产生隐藏 effect。 @@ -75,4 +75,4 @@ Vitest 为每个包测试拓扑使用 `{ enabled: true }` 挂载 `InvariantServi - 空 companion 是带包专属说明、可评审的决策;删除说明后门禁会失败。 - 类型声明、Cordis 可加载性、插件 metadata、服务方法形状和纯代数继续由所属的编译、加载、单元或集成门禁覆盖。 - 运行时失败会标明所属 npm 包,并指出不一致的观测,而不是复述必要的 API 形状。 -- 原有 selection、blocklist 优先级、重复所有权、回滚、释放和 HMR 服务契约保持不变。 +- 原有 selection、blocklist 优先级、重复所有权、回滚、dispose 和 HMR(热模块替换)服务约定保持不变。 diff --git a/.agents/notes/implemented/architecture/2026-07-19-package-owned-invariant-service.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-19-package-owned-invariant-service.i18n.yaml index 3c005a6deb..291a3f3ce1 100644 --- a/.agents/notes/implemented/architecture/2026-07-19-package-owned-invariant-service.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-19-package-owned-invariant-service.i18n.yaml @@ -3,4 +3,4 @@ # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-19-package-owned-invariant-service.md 2026-07-19-package-owned-invariant-service.md: e32efe9f6b3ce6b782c61db56d928e87c160dc9a -2026-07-19-package-owned-invariant-service.zh.md: 60edaa3f6009acc516017683232ca0c07f64ec0d +2026-07-19-package-owned-invariant-service.zh.md: abb77cfc2dc4c15510baf0b205cefdbf3c890041 diff --git a/.agents/notes/implemented/architecture/2026-07-19-package-owned-invariant-service.zh.md b/.agents/notes/implemented/architecture/2026-07-19-package-owned-invariant-service.zh.md index 60edaa3f60..abb77cfc2d 100644 --- a/.agents/notes/implemented/architecture/2026-07-19-package-owned-invariant-service.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-19-package-owned-invariant-service.zh.md @@ -1,4 +1,4 @@ -# Agent Note: 包拥有的不变式服务接缝 +# Agent Note: 包拥有的不变式服务 seam Status: implemented @@ -18,7 +18,7 @@ Status: implemented `@deepseek-ai/dsh-invariants` 是与产品无关的 Cordis 服务插件,注册 `ctx.invariants`。它只负责配置、注册唯一性、子 fiber 生命周期和带包归属的失败;不导入 session、agent、scope 或 agent-loop 包,也不包含这些包的检查。 -工作区内的每个包都发布 `./invariant` 伴随插件,注册自己完整且准确的 npm 包名。如果所有者具备有意义的事件或可变数据关系,companion 就检查该关系;否则空 installer 必须携带该所有者专属的说明。后续的[运行时契约 Agent Note](2026-07-19-package-invariant-runtime-contracts.md) 禁止生成的所有权占位符和合成 API 形状断言。包的根入口不会隐式导入或注册诊断,因此加载根包不会改变运行时检查,也不要求不变式服务存在。 +工作区内的每个包都发布 `./invariant` 伴随插件,注册自己完整且准确的 npm 包名。如果所有者具备有意义的事件或可变数据关系,companion 就检查该关系;否则空 installer 必须携带该所有者专属的说明。后续的[运行时约定 Agent Note](2026-07-19-package-invariant-runtime-contracts.md) 禁止生成的所有权占位符和合成 API 形状断言。包的根入口不会隐式导入或注册诊断,因此加载根包不会改变运行时检查,也不要求不变式服务存在。 ### 配置与选择 @@ -64,13 +64,13 @@ blocklist 匹配优先于 allowlist 匹配。每个条目都是区分大小写 | `@deepseek-ai/dsh-scope/invariant` | `@deepseek-ai/dsh-scope` | scoped event carrier 存在性与主体一致性 | | `@deepseek-ai/dsh-agent-loop/invariant` | `@deepseek-ai/dsh-agent-loop` | 模型请求重建 | -这四个所有者提供了首批有状态检查。后续运行时契约决策为另外十七个确有事件或可变数据关系的所有者增加检查,并为其余包记录有理由的空 companion。每个伴随入口都是单独打包的 `./invariant` export,具有独立声明和对 Loader 安全的命名空间插件形态;服务包自身的伴随插件导入本地服务类型,避免形成自依赖。 +这四个所有者提供了首批有状态检查。后续运行时约定决策为另外十七个确有事件或可变数据关系的所有者增加检查,并为其余包记录有理由的空 companion。每个伴随入口都是单独打包的 `./invariant` export,具有独立声明和对 Loader 安全的命名空间插件形态;服务包自身的伴随插件导入本地服务类型,避免形成自依赖。 `verify-package-invariants` 会发现每个工作区包,并拒绝缺失的伴随插件源码、生成标记、没有解释的空 installer、缺少或不使用失败报告器的非空 installer、外部或无法解析的注册名、缺失的 `./invariant` export 或发布文件、缺失的不变式对等依赖(peer dependency)、开发依赖及项目引用,以及遗漏伴随入口的自定义构建配置。 ### Scoped event 语义映射 -生成的 scoped event 主体解析表位于 `dsh-scope`,与消费它的契约和不变式相邻。`gen-scoped-events` 使用根 TypeScript Program 枚举 `this: Scoped` 声明,从真实 `scopeTarget(base, key)` 调用推断路由键类型,并要求唯一、无歧义的 payload 主体或显式 unsupported 标记。提交的运行时映射不导入事件所有者包,因此语义完整性不会扩大服务包或 scope 包的运行时依赖闭包。 +生成的 scoped event 主体解析表位于 `dsh-scope`,与消费它的约定和不变式相邻。`gen-scoped-events` 使用根 TypeScript Program 枚举 `this: Scoped` 声明,从真实 `scopeTarget(base, key)` 调用推断路由键类型,并要求唯一、无歧义的 payload 主体或显式 unsupported 标记。提交的运行时映射不导入事件所有者包,因此语义完整性不会扩大服务包或 scope 包的运行时依赖闭包。 ### 示例组合与 SDK 输出 @@ -88,9 +88,9 @@ Workspace 约束识别独立的不变式 bundle;包 exports、项目引用、 ## 考虑过的替代方案 -- **把所有检查保留在 `dsh-invariants`。** 不予采纳,因为注册包仍要导入所有被检查的产品领域,所有者变更仍需中央编辑,测试也继续远离被保护的契约。 +- **把所有检查保留在 `dsh-invariants`。** 不予采纳,因为注册包仍要导入所有被检查的产品领域,所有者变更仍需中央编辑,测试也继续远离被保护的约定。 - **当 `ctx.invariants` 恰好存在时,让根包入口隐式注册检查。** 不予采纳,因为根入口行为会依赖组合顺序与可选服务是否存在,诊断无法独立选择,而且包加载会隐藏一个不在显式伴随插件中的注册 effect。 -- **在运行时自动发现所有 `invariant.ts` 文件。** 不予采纳,因为文件系统或包发现不是运行时所有权契约,会让 bundle 发布含义不清,也无法表达显式 Cordis 加载顺序或依赖安装。构建期生成与校验以及测试 host 可以枚举源码树,因为它们验证的是仓库完整性,而不是组合已发布的部署。 +- **在运行时自动发现所有 `invariant.ts` 文件。** 不予采纳,因为文件系统或包发现不是运行时所有权约定,会让 bundle 发布含义不清,也无法表达显式 Cordis 加载顺序或依赖安装。构建期生成与校验以及测试 host 可以枚举源码树,因为它们验证的是仓库完整性,而不是组合已发布的部署。 - **根据当前已加载包集合验证 allow/block 条目。** 不予采纳,因为零匹配模式可能有意指向稍后加载或 HMR 加载的贡献;当前加载顺序不能决定配置有效性。 ## 后果 diff --git a/.agents/notes/implemented/architecture/2026-07-19-zstandard-jsonl-session-logs.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-19-zstandard-jsonl-session-logs.i18n.yaml index d63e6d4b88..be9d15968f 100644 --- a/.agents/notes/implemented/architecture/2026-07-19-zstandard-jsonl-session-logs.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-19-zstandard-jsonl-session-logs.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-19-zstandard-jsonl-session-logs.md -2026-07-19-zstandard-jsonl-session-logs.md: 287ec94a91101850e9343d36ffd27870daf1333b -2026-07-19-zstandard-jsonl-session-logs.zh.md: 4e578432640651de1eb1977229b7cdd462766c24 +2026-07-19-zstandard-jsonl-session-logs.md: 93fc20f931c75552352834b9340e7d38680d4254 +2026-07-19-zstandard-jsonl-session-logs.zh.md: e5495f2f5ae356d49bd2321e442c19ca834c2ab7 diff --git a/.agents/notes/implemented/architecture/2026-07-19-zstandard-jsonl-session-logs.md b/.agents/notes/implemented/architecture/2026-07-19-zstandard-jsonl-session-logs.md index 287ec94a91..93fc20f931 100644 --- a/.agents/notes/implemented/architecture/2026-07-19-zstandard-jsonl-session-logs.md +++ b/.agents/notes/implemented/architecture/2026-07-19-zstandard-jsonl-session-logs.md @@ -28,7 +28,7 @@ First materialization compresses the two initial frames before opening the tempo ### Read, listing, and crash recovery -A frame-boundary scanner reads the standard magic, variable header fields, block headers and payload sizes, and optional checksum trailer. It does not interpret compressed blocks. Complete frames are decompressed independently and sequentially with Node's default `ZSTD_e_end`, which requires frame completion and validates their checksums, and their plaintext is passed to the existing JSONL scanner. A checksum/decompression failure in any complete frame, a malformed complete-frame JSONL tail, or invalid frame structure is corruption and rejects. +A frame-boundary scanner reads the standard magic, variable header fields, block headers and payload sizes, and optional checksum trailer. It does not interpret compressed blocks. Complete frames are independently checksum-validated and passed through the [large-session restore pipeline](2026-08-05-large-session-jsonl-restore-pipeline.md), which owns decoder reuse, cooperative yielding, and incremental JSONL scanning. A checksum/decompression failure in any complete frame, a malformed complete-frame JSONL tail, or invalid frame structure is corruption and rejects. Listing reads in bounded chunks only until the first complete frame is available, validates and decompresses that header frame, and never reads an event frame. The dedicated header frame therefore preserves metadata-only listing even for very large session logs. @@ -53,5 +53,5 @@ The shared persistence and coordinator contracts run against both encodings. Bac - Ordinary session roots store `.jsonl.zstd` and retain append-only, fsync, rollback, and interrupted-turn recovery semantics. - Raw JSONL remains a deliberate configuration, but changing encoding requires a fresh/separate root or selecting the mode that matches existing artifacts. - One frame per durable batch adds bounded framing/checksum overhead and allows header-only listing plus repair from an exact append boundary. -- External tools must understand concatenated Zstandard frames or consume raw-mode artifacts; generic one-shot Node decompression reads only the first independent frame, so backend reads walk frames explicitly. +- External tools must understand concatenated Zstandard frames or consume raw-mode artifacts; generic one-shot Node decompression reads only the first independent frame, so backend reads walk frames through the [restore pipeline](2026-08-05-large-session-jsonl-restore-pipeline.md). - The implementation depends on Node's experimental built-in Zstandard API without an npm dependency; the supported-version compatibility gate makes drift visible. diff --git a/.agents/notes/implemented/architecture/2026-07-19-zstandard-jsonl-session-logs.zh.md b/.agents/notes/implemented/architecture/2026-07-19-zstandard-jsonl-session-logs.zh.md index 4e57843264..e5495f2f5a 100644 --- a/.agents/notes/implemented/architecture/2026-07-19-zstandard-jsonl-session-logs.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-19-zstandard-jsonl-session-logs.zh.md @@ -28,7 +28,7 @@ JSONL 持久化后端会逐字保留每个 `SessionEvent`,其中包括数量 ### 读取、列举与崩溃恢复 -帧边界扫描器会读取标准魔数、可变头字段、块头与负载长度,以及可选校验和尾部,但不会解释压缩块。后端使用 Node 默认的 `ZSTD_e_end` 独立且按顺序解压完整帧;该模式要求帧完整并验证各帧校验和,再把明文交给既有 JSONL 扫描器。任何完整帧的校验和或解压失败、完整帧中畸形的 JSONL 尾部,或者无效帧结构都属于损坏并拒绝加载。 +帧边界扫描器会读取标准魔数、可变头字段、块头与负载长度,以及可选校验和尾部,但不会解释压缩块。完整帧会独立验证校验和,再进入[大型会话恢复流水线](2026-08-05-large-session-jsonl-restore-pipeline.md);该流水线负责复用解码器、协作式让出事件循环和增量扫描 JSONL。任何完整帧的校验和或解压失败、完整帧中畸形的 JSONL 尾部,或者无效帧结构都属于损坏并拒绝加载。 列举只按有界分片读取到第一个完整帧可用为止,验证并解压该头部帧,绝不读取事件帧。因此,即使会话日志很大,专用头部帧仍能维持仅元数据列举。 @@ -38,7 +38,7 @@ JSONL 持久化后端会逐字保留每个 `SessionEvent`,其中包括数量 CLI、ACP 与 stdio 应用包公开对称的 `persistenceCompression` 透传配置。web 宿主装配与普通应用组合省略该选项并使用压缩默认值。快照录制与回放组合显式选择 `'none'`,因为提交的 fixture 是回放与规范化过程使用的原始 JSONL 输入。 -共享持久化契约与协调器契约会针对两种编码运行。后端测试覆盖标准帧与校验和互操作性、仅头部列举、追加回滚、编码不匹配拒绝、完整帧损坏,以及横跨头部、块和校验和尾部的最终帧撕裂。默认运行时、构建后二进制、headless、ACP 与 Python 冒烟测试会断言压缩后缀与 Zstandard 魔数,或解码头部;读取原始内容的测试则显式退出压缩。 +共享持久化约定与协调器约定会针对两种编码运行。后端测试覆盖标准帧与校验和互操作性、仅头部列举、追加回滚、编码不匹配拒绝、完整帧损坏,以及横跨头部、块和校验和尾部的最终帧撕裂。默认运行时、构建后二进制、headless、ACP 与 Python 冒烟测试会断言压缩后缀与 Zstandard 魔数,或解码头部;读取原始内容的测试则显式退出压缩。 ## 考虑过的替代方案 @@ -53,5 +53,5 @@ CLI、ACP 与 stdio 应用包公开对称的 `persistenceCompression` 透传配 - 普通会话根目录存储 `.jsonl.zstd`,并保留仅追加、fsync、回滚与中断轮次恢复语义。 - 原始 JSONL 仍是显式配置,但切换编码需要使用全新或单独根目录,或者选择与既有产物匹配的模式。 - 每个持久批次一个帧会增加有界的帧与校验和开销,同时支持仅头部列举和从精确追加边界开始修复。 -- 外部工具必须理解串联的 Zstandard 帧,或者消费原始模式产物;Node 通用的一次性解压只读取第一个独立帧,因此后端读取会显式遍历各帧。 +- 外部工具必须理解串联的 Zstandard 帧,或者消费原始模式产物;Node 通用的一次性解压只读取第一个独立帧,因此后端读取会通过[恢复流水线](2026-08-05-large-session-jsonl-restore-pipeline.md)遍历各帧。 - 实现依赖 Node 的实验性内置 Zstandard API,但不增加 NPM 依赖;受支持版本兼容性门禁会暴露 API 漂移。 diff --git a/.agents/notes/implemented/architecture/2026-07-20-canonical-tool-output-contract.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-20-canonical-tool-output-contract.i18n.yaml index 17d864cb57..75c2b53cef 100644 --- a/.agents/notes/implemented/architecture/2026-07-20-canonical-tool-output-contract.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-20-canonical-tool-output-contract.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-20-canonical-tool-output-contract.md -2026-07-20-canonical-tool-output-contract.md: b2de9480d2659153dfb8a76ee07438d12e5b07c3 -2026-07-20-canonical-tool-output-contract.zh.md: 1ae2654fb1e1d6913bc91c4aeb380dc533a6b258 +2026-07-20-canonical-tool-output-contract.md: 2429e1c141ad8c8ee932c6d654a6ba74bc4f7618 +2026-07-20-canonical-tool-output-contract.zh.md: 534aa2ed7ad65719b280f64f73a412bf5b17a1de diff --git a/.agents/notes/implemented/architecture/2026-07-20-canonical-tool-output-contract.md b/.agents/notes/implemented/architecture/2026-07-20-canonical-tool-output-contract.md index b2de9480d2..2429e1c141 100644 --- a/.agents/notes/implemented/architecture/2026-07-20-canonical-tool-output-contract.md +++ b/.agents/notes/implemented/architecture/2026-07-20-canonical-tool-output-contract.md @@ -46,7 +46,7 @@ The first-party tools preserve their existing Native text while returning domain | `glob` | `{ paths: string[] }` | | `grep` | `{ matches: [{ path, lineNumber, line }] }` | | `web_search` / `web_fetch` | The normalized `WebSearchResult` / `WebFetchResult` | -| `lsp` | `{ kind: "locations", locations, resolvedWorkspaceRoot }` or `{ kind: "hover", hover }` | +| `lsp` | `{ kind: "locations", locations, resolvedWorkspaceUri }` or `{ kind: "hover", hover }` | | `bash` | `{ kind: "background", taskId }` or `{ kind: "foreground" } & BashRunResult` | | `terminal_open` / `terminal_list` / `terminal_send` / `terminal_read` / `terminal_signal` / `terminal_close` | Public session snapshots, bounded read/send DTOs, signal/close outcomes, or a background task handle | | `task_output` / `task_list` / `task_kill` | Public task snapshots without owner or notification bookkeeping | diff --git a/.agents/notes/implemented/architecture/2026-07-20-canonical-tool-output-contract.zh.md b/.agents/notes/implemented/architecture/2026-07-20-canonical-tool-output-contract.zh.md index 1ae2654fb1..534aa2ed7a 100644 --- a/.agents/notes/implemented/architecture/2026-07-20-canonical-tool-output-contract.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-20-canonical-tool-output-contract.zh.md @@ -1,4 +1,4 @@ -# Agent Note:规范工具输出契约 +# Agent Note: 规范工具输出约定 Status: implemented @@ -8,7 +8,7 @@ Status: implemented 工具主体过去直接编写面向模型的 `ContentBlock[]`,并可选择将其与不透明的 `meta` 包装在一起。因此,Native 模式的 Function Calling(函数调用)虽然拥有可供人阅读的投影,但程序化调用方没有稳定的领域值:Code Mode 会将内容块重新展平为字符串,动态工具会重复定义内容形态,策略也可以替换展示内容,却无法区分这项变更究竟是替换展示,还是替换操作结果。多个能力 seam 已经返回了信息更丰富的提供方值,却又在面向模型的工具边界丢弃这些值。 -持久会话契约将这份展示内容视为回放时的权威来源,但如果持久化每一个信息丰富的中间值,就会扩大日志、使实现数据进入压缩和迁移流程,还会错误地把执行期本地 API 变成会话格式的一部分。因此,系统底层需要在执行期间保留一个类型化值,并显式将其投影为现有的持久化内容和模型可见内容。 +持久会话约定将这份展示内容视为回放时的权威来源,但如果持久化每一个信息丰富的中间值,就会扩大日志、使实现数据进入压缩(compaction)和迁移流程,还会错误地把执行期本地 API 变成会话格式的一部分。因此,系统底层需要在执行期间保留一个类型化值,并显式将其投影为现有的持久化内容和模型可见内容。 ## 决策 @@ -22,9 +22,9 @@ output: { } ``` -`defineTool` 从统一的 `ValueSchemaSpec` 推导工具主体返回值和两个投影器的类型。原始定义和动态定义则提供编译后的 `JsonSchemaNode` 形式。注册时会拒绝缺失输出声明或采用不受支持原始 schema 的定义,不提供兼容旧式内容返回值的路径。 +`defineTool` 从统一的 `ValueSchemaSpec` 推导工具主体返回值和两个投影器的类型。原始定义和动态定义则提供编译后的 `JsonSchemaNode` 形式。注册时会拒绝缺失输出声明或采用不受支持的原始 schema 的定义,不提供兼容旧式内容返回值的路径。 -每次成功分发时,注册表会将返回值快照为无损 `JsonValue`,依据 `output.schema` 校验并深度冻结,然后调用纯渲染器;对于直接的外层调用,还会调用可选的元数据投影器。渲染器、投影器、schema 或无损 JSON 处理失败都会被收敛为普通 `ToolOutputError` 结果。around `tools/execute` 包装层接收并返回规范的成功/失败联合;包装层自行产生的成功结果会再次通过已解析工具的输出声明完成归一化,而不会信任其独立编写的内容。每个规范结果只归属于一个不可变的分发 token;因此,如果包装层返回来自其他调用或工具的缓存结果,系统会依据当前生效的输出声明重新执行归一化,而不会绕过这一步。 +每次成功分发时,注册表会将返回值快照为无损 `JsonValue`,依据 `output.schema` 校验并深度冻结,然后调用纯渲染器;对于直接的外层调用,还会调用可选的元数据投影器。渲染器、投影器、schema 或无损 JSON 处理失败都会被收敛为普通 `ToolOutputError` 结果。围绕 `tools/execute` 的包装层接收并返回规范的成功/失败联合;包装层自行产生的成功结果会再次通过已解析工具的输出声明完成归一化,而不会信任其独立编写的内容。每个规范结果的来源归属仅限于一个不可变的分发 token;因此,如果包装层返回来自其他调用或工具的缓存结果,系统会依据当前生效的输出声明重新执行归一化,而不会绕过这一步。 ```ts ignore-check type ToolExecutionResult = @@ -46,21 +46,21 @@ type ToolExecutionResult = | `glob` | `{ paths: string[] }` | | `grep` | `{ matches: [{ path, lineNumber, line }] }` | | `web_search` / `web_fetch` | 归一化后的 `WebSearchResult` / `WebFetchResult` | -| `lsp` | `{ kind: "locations", locations, resolvedWorkspaceRoot }` 或 `{ kind: "hover", hover }` | +| `lsp` | `{ kind: "locations", locations, resolvedWorkspaceUri }` 或 `{ kind: "hover", hover }` | | `bash` | `{ kind: "background", taskId }` 或 `{ kind: "foreground" } & BashRunResult` | | `terminal_open` / `terminal_list` / `terminal_send` / `terminal_read` / `terminal_signal` / `terminal_close` | 公开会话快照、有界的读取/发送 DTO、信号/关闭操作结果,或后台任务句柄 | -| `task_output` / `task_list` / `task_kill` | 不含所有者或通知账务字段的公开任务快照 | +| `task_output` / `task_list` / `task_kill` | 不含所有者或通知管理信息的公开任务快照 | | `subagent` | 后台任务句柄或 `{ kind: "foreground", runId, output: JsonValue[] }` | | `workflow` / `ralph` | `{ runId, agentsStarted, result: JsonValue }` | | `skill` | `{ name, provider, resourceBase?, content }` | | `todo_write` | `{ todos, counts }` | | `ask_user_question` | `{ answers: [{ id, selected, custom? }] }` | | `exit_plan_mode` | `{ approved: true }` | -| `cordis_inspect` / `cordis_mount` / `cordis_unmount` | 检查文本或类型化的临时 Plugin 句柄 | +| `cordis_inspect` / `cordis_mount` / `cordis_unmount` | 检查文本或类型化的临时插件句柄 | | `structured_output` | `{ recorded: true }` | | `run_code` | `{ logs: string[], result?: JsonValue }` | -提供方和执行器的采集上限仍会实际限制规范值。仅用于格式化的限制归 `render` 所有;例如,`glob` 和 `grep` 会在 `value` 中保留所有已采集项,而其 Native 投影仍只保留配置指定的第一页,并尽力将完整展示内容写入落盘文件。通用落盘机制会前置注册其 post-execute 监听器,并让该监听器先向后委托,因此无论插件加载顺序如何,普通工具自有的异步投影都会在通用字节数上限处理之前完成。文件系统变更工具根据 `args` 和规范的变更前/后值推导可回放的 diff 元数据,不再由工具主体返回 UI 状态。 +提供方和执行器的采集上限仍会实际限制规范值。仅用于格式化的限制归 `render` 所有;例如,`glob` 和 `grep` 会在 `value` 中保留所有已采集项,而其 Native 投影会保留配置指定的第一页,并尽力将其写入落盘文件。通用落盘机制会前置注册其 post-execute 监听器,并让该监听器先向后委托,因此无论插件加载顺序如何,普通工具自有的异步投影都会在通用字节数上限处理之前完成。文件系统变更工具根据 `args` 和规范的变更前/后值推导可回放的 diff 元数据,不再由工具主体返回 UI 状态。 MCP 桥接层通过 `McpResult<{...}> = { content: JsonValue[]; structuredContent? }` 保留协议内容块。当公布的 `outputSchema` 属于受支持的原始子集时,系统会强制校验;不受支持的 schema 则回退为 `JsonValue`,而不会假装已完成校验。Native 渲染仍使用现有的 MCP 到 `ContentBlock` 投影,MCP `isError` 则会变为失败的工具结果。 @@ -74,6 +74,6 @@ MCP 桥接层通过 `McpResult<{...}> = { content: JsonValue[]; structuredConten ## 影响 -Native 和回放行为仍以内容为先,并保持逐字节兼容;执行期调用方则无需解析内容,即可使用经过校验的领域值。失败结果必须包含消息,并可选择附加内部类名/代码信息;成功与失败结果由判别字段区分,失败结果绝不会承诺存在值。工具作者必须一并设计值及其 Native 投影;增加这项声明是有意为之,因为它避免从自然语言内容意外推导出程序化契约。 +Native 和回放行为仍以内容为先,并保持逐字节兼容;执行期调用方则无需解析内容,即可使用经过校验的领域值。失败结果必须包含消息,并可选择附加内部类名/代码信息;成功与失败结果由判别字段区分,失败结果绝不会承诺存在值。工具作者必须一并设计值及其 Native 投影;增加这项声明是有意为之,因为它避免从自然语言内容意外推导出程序化约定。 -中间值只受产生它们的能力和进程内存限制。日志不包含这些值,因此回放无法恢复;仅处理内容的 post 策略也无法隐藏这些值。这些都是执行期本地契约的明确属性,并非意外缺口。 +中间值只受产生它们的能力和进程内存限制。日志不包含这些值,因此回放无法恢复;仅处理内容的 post 策略也无法隐藏这些值。这些都是执行期本地约定的明确属性,并非意外缺口。 diff --git a/.agents/notes/implemented/architecture/2026-07-20-routed-model-context-and-compaction-policy.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-20-routed-model-context-and-compaction-policy.i18n.yaml index d6ca73e9e0..20abdeec64 100644 --- a/.agents/notes/implemented/architecture/2026-07-20-routed-model-context-and-compaction-policy.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-20-routed-model-context-and-compaction-policy.i18n.yaml @@ -3,4 +3,4 @@ # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-20-routed-model-context-and-compaction-policy.md 2026-07-20-routed-model-context-and-compaction-policy.md: 6a2626d4eea3e30533199320b6b0ed5b05e7fd28 -2026-07-20-routed-model-context-and-compaction-policy.zh.md: 2881b2d4205359b715303622268ee9218dd75831 +2026-07-20-routed-model-context-and-compaction-policy.zh.md: 128563718554e2f8ed49f933aceb77cb18623dee diff --git a/.agents/notes/implemented/architecture/2026-07-20-routed-model-context-and-compaction-policy.zh.md b/.agents/notes/implemented/architecture/2026-07-20-routed-model-context-and-compaction-policy.zh.md index 2881b2d420..1285637185 100644 --- a/.agents/notes/implemented/architecture/2026-07-20-routed-model-context-and-compaction-policy.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-20-routed-model-context-and-compaction-policy.zh.md @@ -8,19 +8,19 @@ Status: implemented 当一个进程把请求路由到不同容量的模型时,压缩不能安全地应用同一个全局上下文窗口。相同模型 id 也可能存在于多个提供方下,适配器还可能接受不在建议目录中的动态 id。错误容量要么让压缩触发过晚并造成原本可避免的溢出,要么让压缩触发过早并丢弃有用上下文。 -两个直观的配置归属方都无法独立解决问题。Compact-basic 是可选插件,不知道适配器接受哪些模型。LLM 适配器拥有模型路由,但不能依赖可选压缩插件,也不应吸收消费方专用的阈值、保留、摘要器与重试策略。该设计既需要权威容量事实和可选的逐目标压缩策略,又不能建立第二套模型注册表。 +两个直观的配置归属方都无法独立解决问题。Compact-basic 是可选插件,不知道适配器接受哪些模型。LLM(大语言模型)适配器拥有模型路由,但不能依赖可选压缩插件,也不应吸收消费方专用的阈值、保留、摘要器与重试策略。该设计既需要权威容量事实和可选的逐目标压缩策略,又不能建立第二套模型注册表。 ## 决策 ### 适配器拥有精确路由容量 -`LlmAdapter.resolveModel(provider, model, signal?)` 返回一条精确路由的聚合元数据,其中可选的 `LlmModelContext` 位于 `context` 字段下。`LlmService.resolveModelInfo()` 选择已注册的路由所属方,验证 `contextWindow` 为正整数,并返回分离的元数据。该查询独立于 `listModels()`:不在目录中的动态模型也可以拥有容量元数据,而缺少 `context` 只表示适配器无法描述容量。 +`LlmAdapter.resolveModel(provider, model, signal?)` 返回一条精确路由的聚合元数据,其中可选的 `LlmModelContext` 位于 `context` 字段下。`LlmService.resolveModelInfo()` 选择已注册的路由所属方,验证 `contextWindow` 为正整数,并返回与适配器内部状态分离的元数据。该查询独立于 `listModels()`:不在目录中的动态模型也可以拥有容量元数据,而缺少 `context` 只表示适配器无法描述容量。 手写 DeepSeek 适配器允许每个已配置模型提供可选 `contextWindow`,并支持适配器级 `defaultContextWindow`。精确模型容量优先;未提供容量的模型项与未列出的透传 id 会继承适配器默认值,若默认值也不存在则省略 `context`。两个内置模型项都公开精确的 256,000 token 容量。pi-ai 适配器从同一个目录描述符解析容量,该描述符也用于权威解析请求模型。 ### Token 计量保持模型无关 -`dsh-token-meter` 没有配置,也没有模型 profile。它拥有一个固定回放折叠,并返回绝对估算 token 压力与逐位置表层价格。移除全局容量后,未加载 compact-basic 时仍可复用计量,同时避免让回放核算变成另一套模型注册表。 +`dsh-token-meter` 没有配置,也没有模型 profile。它拥有一个固定回放折叠,并返回绝对估算 token 压力,以及按位置排列的表层节点 token 估值。移除全局容量后,未加载 compact-basic 时仍可复用计量,同时避免让回放核算变成另一套模型注册表。 ### Compact-basic 解析目标规格 @@ -32,11 +32,11 @@ Compact-basic 拥有消费方策略。顶层字段定义默认值;`modelPolici ### 目标专用压力错误仍保留可选组合 -缺少容量元数据的适配器仍是有效 LLM 路由。手动主动压力检查会返回目标专用配置错误;自动监听器按精确路由只警告一次,并继续保留完整历史。当已解析容量暴露出无效的绝对保留预算时,系统也按路由抑制重复警告;其他运行故障仍会各自对外可见。提供方已经确认的规范化溢出不需要容量元数据:它绕过主动阈值与普通保留预算,尝试一次最大的平衡缩减,并在替换无法证明进展时保留原始提供方错误。 +缺少容量元数据的适配器仍是有效 LLM 路由。手动主动压力检查会返回目标专用配置错误;自动监听器按精确路由只警告一次,并继续保留完整历史。当已解析容量暴露出无效的绝对保留预算时,系统也按路由抑制重复警告;其他运行故障仍会各自对外可见。提供方已经确认的规范化溢出不需要容量元数据:它绕过主动阈值与普通保留预算,尝试一次最大且平衡的缩减,并在替换无法证明进展时保留原始提供方错误。 ## 测试 -服务测试覆盖分离上下文元数据、无效适配器输出、目录独立性与默认缺失行为。适配器测试覆盖 DeepSeek 的精确容量、默认容量、未列出模型解析及无效容量,以及 pi-ai 的精确描述符解析。压缩测试覆盖比例缩放、精确提供方/模型覆盖、加载期拒绝无效合并比例、运行时校验绝对预算、相同模型 id 的提供方切换、目标专用警告抑制与不依赖容量的溢出恢复。Loader fixture 会拒绝已经移除的 token-meter 容量设置,示例则在适配器上配置容量。 +服务测试覆盖与适配器内部状态分离的上下文元数据、无效适配器输出、目录独立性与默认缺失行为。适配器测试覆盖 DeepSeek 的精确容量、默认容量、未列出模型解析及无效容量,以及 pi-ai 的精确描述符解析。压缩测试覆盖比例缩放、精确提供方/模型覆盖、加载期拒绝无效合并比例、运行时校验绝对预算、相同模型 id 的提供方切换、目标专用警告抑制与不依赖容量的溢出恢复。Loader fixture(测试前置数据)会拒绝已经移除的 token-meter 容量设置,示例则在适配器上配置容量。 ## 考虑过的替代方案 diff --git a/.agents/notes/implemented/architecture/2026-07-20-unified-json-value-schema-dsl.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-20-unified-json-value-schema-dsl.i18n.yaml index 19a6b628c3..152bae16ac 100644 --- a/.agents/notes/implemented/architecture/2026-07-20-unified-json-value-schema-dsl.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-20-unified-json-value-schema-dsl.i18n.yaml @@ -1,6 +1,6 @@ # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: -# pnpm run verify-translation-pairing --write +# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-20-unified-json-value-schema-dsl.md 2026-07-20-unified-json-value-schema-dsl.md: 5de3523eab15a91ea32dc09e2e239146fadea6f1 -2026-07-20-unified-json-value-schema-dsl.zh.md: 321136c31a6aa6c0268150fcde2d97dcdbb0ac58 +2026-07-20-unified-json-value-schema-dsl.zh.md: 0dc38dc289a32269c0f9e545ae53a8098ba02189 diff --git a/.agents/notes/implemented/architecture/2026-07-20-unified-json-value-schema-dsl.zh.md b/.agents/notes/implemented/architecture/2026-07-20-unified-json-value-schema-dsl.zh.md index 321136c31a..0dc38dc289 100644 --- a/.agents/notes/implemented/architecture/2026-07-20-unified-json-value-schema-dsl.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-20-unified-json-value-schema-dsl.zh.md @@ -1,4 +1,4 @@ -# Agent Note:统一 JSON 值 schema DSL +# Agent Note: 统一 JSON 值 schema DSL Status: implemented @@ -6,17 +6,17 @@ Status: implemented ## 问题 -工具参数使用一套精简的作者侧 schema DSL,subagent/工作流的结构化输出则使用另一套原始 JSON Schema 子集和校验器。两套词汇在根类型、标量约束和校验方式上并不一致;如果继续沿用这种划分,类型化的规范工具输出契约要么还需重复实现两条路径,要么只能接受部分投影无法强制执行的 schema。 +工具参数使用一套精简的作者侧 schema DSL,subagent/工作流的结构化输出则使用另一套原始 JSON Schema 子集和校验器。两套词汇在根类型、标量约束和校验方式上并不一致;如果继续沿用这种划分,类型化的规范工具输出约定要么还需重复实现两条路径,要么只能接受部分投影无法强制执行的 schema。 ## 决策 -`dsh-tools` 以两种表示形式统一管理一套 JSON 值 schema 词汇。`ValueSchemaSpec` 是可描述任意 JSON 根类型的作者侧形式;`ParameterSchemaSpec` 是其隐式对象属性映射形式,每个属性可标记 `required: true`。`JsonSchemaNode` 是原始协议表示。两种形式都支持字符串、有限数值、整数、布尔值、null、数组、对象、类型正确的标量 `enum`/`const`,以及要求恰好匹配一个分支的 `oneOf`;`{ type: 'json' }` 仅是作者侧语法糖,会编译为仅含注解、不施加约束的原始节点。 +`dsh-tools` 以两种表示形式统一管理一套 JSON 值 schema 词汇。`ValueSchemaSpec` 是可描述任意 JSON 根类型的作者侧形式;`ParameterSchemaSpec` 是其隐式对象属性映射形式,每个属性可标记 `required: true`。`JsonSchemaNode` 是原始协议形式。两种形式都支持字符串、有限数值、整数、布尔值、null、数组、对象、类型正确的标量 `enum`/`const`,以及要求恰好匹配一个分支的 `oneOf`;`{ type: 'json' }` 仅是作者侧语法糖,会编译为仅含注解、不施加约束的原始节点。 显式的作者侧对象必须声明 `additionalProperties: true | false`。隐式参数根对象和原始 JSON Schema 保留标准的默认开放语义。schema 记录只能包含自有且可枚举的字符串键,schema 数组必须是稠密的内建数组,系统只从自有属性读取受支持的关键字;因此,自定义原型、继承的约束、symbol 和 JSON 不可见的附加内容都无法让编译、投影和校验观察到不同的声明。内建的普通 Object 和 Array 容器跨 JavaScript 运行域后仍视为普通容器,而子类和伪造构造函数的原型仍视为非普通对象。 -`InferValue` 和 `InferArgs

    ` 根据同一份声明推导 TypeScript 值,`valueSchemaSpecToJsonSchema()` 和 `parameterSchemaSpecToJsonSchema()` 也将这些声明编译为 JSON Schema。精确类型推导以 16 层容器为界,超过后使用 `JsonValue`,从而避免 TypeScript 的类型实例化栈限制作者能声明的嵌套深度。`assertSupportedJsonSchema()` 会拒绝不受支持或位置错误的关键字;`validateJsonSchemaValue()` 则以无损 `JsonValue` 边界校验受支持的子集,不允许 `undefined`、负零、非有限数、稀疏数组、循环引用、非普通对象、函数、symbol 及其他需要强制转换的值。作者侧 schema 编译、原始 schema 断言、值校验、schema 到 TypeScript 的渲染、注册表数据分离,以及动态 Cordis 的跨运行域规范化与克隆均使用显式工作栈,因此运行时嵌套只受可用内存限制,不受 JavaScript 调用栈限制。 +`InferValue` 和 `InferArgs

    ` 根据同一份声明推导 TypeScript 值,`valueSchemaSpecToJsonSchema()` 和 `parameterSchemaSpecToJsonSchema()` 也将这些声明编译为 JSON Schema。精确类型推导以 16 层容器为界,超过后使用 `JsonValue`,从而避免 TypeScript 的类型实例化栈限制作者能声明的嵌套深度。`assertSupportedJsonSchema()` 会拒绝不受支持或位置错误的关键字;`validateJsonSchemaValue()` 则以无损 `JsonValue` 边界校验受支持的子集,不允许 `undefined`、负零、非有限数、稀疏数组、循环引用、非普通对象、函数、symbol 及其他需要强制转换的值。作者侧 schema 编译、原始 schema 断言、值校验、schema 到 TypeScript 的渲染、注册表脱离引用,以及动态 Cordis 的跨运行域规范化与克隆均使用显式工作栈,因此运行时嵌套只受可用内存限制,不受 JavaScript 调用栈限制。 -对象根限制属于消费方规则,不属于 schema 词汇本身。subagent 和工作流中由调用方定义的结构化输出通过 `assertObjectJsonSchema()` 和 `ObjectJsonSchema` 保持对象根限制;工具输出可以使用任意根类型。动态 Cordis 注册会把跨 JavaScript 运行域传入的 schema 重建为当前运行时持有的 JSON,保留原始包装层的默认开放语义,并要求直接使用 DSL 声明的对象明确选择开放方式,然后再调用同一编译器。动态边界会在规范化之前拒绝 JSON 不可见的记录键和非普通 schema 数组,因此不会静默丢弃约束,也不会触发自定义迭代逻辑。 +对象根限制属于消费方规则,不属于 schema 词汇本身。subagent 和工作流中由调用方定义的结构化输出通过 `assertObjectJsonSchema()` 和 `ObjectJsonSchema` 保持对象根限制;工具输出可以使用任意根类型。动态 Cordis 注册会把跨 JavaScript 运行域传入的 schema 重建为宿主拥有的 JSON 值,保留原始包装层的默认开放语义,并要求直接使用 DSL 声明的对象明确选择开放方式,然后再调用同一编译器。动态边界会在规范化之前拒绝 JSON 不可见的记录键和非普通 schema 数组,因此不会静默丢弃约束,也不会触发自定义迭代逻辑。 ## 备选方案 @@ -33,5 +33,5 @@ Status: implemented - 显式的对象开放方式和类型正确的字面量约束会让格式错误的声明在编写或注册阶段快速失败,而不是拖到后续模型调用时才失败。 - 有界类型推导会为常规声明保留有用的精确类型,并将异常深的尾部结构退化为 `JsonValue`;运行时 schema 强制执行在任意深度仍保持精确。 - 原始工具仍可直接注册范围更广的 JSON Schema,但统一代码生成会把不受支持的 schema 视为未知类型,不会假装自己能够强制执行。 -- 每个属性的 `required: true` 仍是工具作者契约;原有推导路径暴露可选性缺陷后,类型级回归覆盖会锁定必填键不得为可选。 -- 运行时和编译期测试覆盖所有根类型、恰好匹配一个分支时的重叠/无匹配行为、原始 schema 的默认开放语义、显式开放方式、有损 JSON 值、类型推导、核心投影和动态投影中的深层嵌套、动态注册中 JSON 不可见的键,以及非普通 schema 数组。 +- 每个属性的 `required: true` 仍是工具作者约定;原有推导路径暴露可选性缺陷后,类型级回归覆盖会锁定必填键不得为可选。 +- 运行时测试和编译期测试覆盖所有根类型、恰好匹配一个分支时的重叠/无匹配行为、原始 schema 的默认开放语义、显式开放方式、有损 JSON 值、类型推导、核心投影和动态投影中的深层嵌套、动态注册中 JSON 不可见的键,以及非普通 schema 数组。 diff --git a/.agents/notes/implemented/architecture/2026-07-22-slot-type-chain-implementation.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-22-slot-type-chain-implementation.i18n.yaml index 1604914ac0..7c13de5842 100644 --- a/.agents/notes/implemented/architecture/2026-07-22-slot-type-chain-implementation.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-22-slot-type-chain-implementation.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-22-slot-type-chain-implementation.md -2026-07-22-slot-type-chain-implementation.md: e88361701fc05c1ab30174dde147ae9558265ce6 -2026-07-22-slot-type-chain-implementation.zh.md: 90473861c199f326f4b3635580c885517f0d612b +2026-07-22-slot-type-chain-implementation.md: 2f0ec32766100e492c68c474f8798be3df0a3d15 +2026-07-22-slot-type-chain-implementation.zh.md: 6ef7eaa7614b88b33f0fa2aa6089e97eb3a45c25 diff --git a/.agents/notes/implemented/architecture/2026-07-22-slot-type-chain-implementation.md b/.agents/notes/implemented/architecture/2026-07-22-slot-type-chain-implementation.md index e88361701f..2f0ec32766 100644 --- a/.agents/notes/implemented/architecture/2026-07-22-slot-type-chain-implementation.md +++ b/.agents/notes/implemented/architecture/2026-07-22-slot-type-chain-implementation.md @@ -36,6 +36,8 @@ There is no separate slot-definition API. The `children` object both **declares Parity rule: **the declaring entry holds the exclusive right to render its child slots**, settled entirely at register time (misconfiguration fails loud at load; the render hot path carries no checks). Loud-at-load cases: a second entry declaring an already-declared slot; registering into an undeclared slot; one store handle mounted under two scopes; a chain registration missing its `select`. +A contributor whose activation order is independent from the declaring entry uses `ctx.slots.inject(key, callback)` and keeps direct `register()` fail-loud. The declaration, contributor, replacement, and failure lifetimes are specified by the [slot declaration injection decision](2026-08-05-slot-declaration-injection.md). + `SlotMap` declaration merging remains the type authority, and an entry declares only its own axes plus the **owner share** — the registrant's injected props never enter the global table ("whoever injects it, owns its type"). ### Component props: four shares, each from its own source of truth diff --git a/.agents/notes/implemented/architecture/2026-07-22-slot-type-chain-implementation.zh.md b/.agents/notes/implemented/architecture/2026-07-22-slot-type-chain-implementation.zh.md index 90473861c1..6ef7eaa761 100644 --- a/.agents/notes/implemented/architecture/2026-07-22-slot-type-chain-implementation.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-22-slot-type-chain-implementation.zh.md @@ -6,17 +6,17 @@ Status: implemented > 范围:Web 客户端 slot 体系的终版设计——UI 插件如何拼合页面、渲染权威落在哪里、组件 props 如何定型、业务活数据住在哪里。周边语境(装载链、对象层、服务)归 [Web 客户端架构 RFC](2026-07-19-gui-web-client-architecture.md) 所有,其 slot 各节移交本文。 -## Problem +## 问题 -页面在运行时由各自独立装载的插件拼合而成,UI 因此需要一套能以静态强制力回答四个问题的组合机制。谁可以渲染进某块区域——这份权威是可强制执行的,还是仅靠约定?组件如何在保持纯函数(零 ctx、零框架 import)的同时拿到它需要的一切,而不必把每个值都经装配代码手工穿线?业务活数据住在哪里,才能让流式更新恰好只重渲染订阅者——而不必每个插件自建一套订阅机械?以及这一切有多少能交给编译器检查,让漂移的组件、越权的渲染调用、错配的 store schema 成为单一可见调用点上的编译错误,而非运行时的意外? +页面在运行时由各自独立装载的插件拼合而成,UI 因此需要一套能以静态强制力回答四个问题的组合机制。谁可以渲染进某块区域——这份权威是可强制执行的,还是仅靠约定?组件如何在保持纯函数(零 ctx、零框架 import)的同时拿到它需要的一切,而不必把每个值都经装配代码手工穿线?实时业务数据应存放在哪里,才能让流式更新恰好只重渲染订阅者,而不必让每个插件自建一套订阅机制?以及这一切有多少能交给编译器检查,让漂移的组件、越权的渲染调用、错配的 store schema 成为单一可见调用点上的编译错误,而非运行时的意外? -## Decision +## 决策 -一句话:**壳只渲染 `'root'`;插件用单独一次 `register` 调用组合 UI——这一次调用同时占坑、声明并授权子坑、声明 store、注入业务面;组件是纯函数,props 分四份额到达,每一份额都从各自唯一的真源自动推导。** +一句话:**壳只渲染 `'root'`;插件用单独一次 `register` 调用组合 UI——这一次调用同时占用 slot、声明并授权子 slot、声明 store、注入业务面;组件是纯函数,props 分四份额到达,每一份额都从各自唯一的真源自动推导。** -### 'root' 是唯一的先验坑 +### 'root' 是唯一的先验 slot -`SlotsService`(client 运行时)在构造时声明 `'root'`——single/root、`owner: {}`——其 `SlotMap` 合并声明住 runtime 包(package)。壳的全部装配就是 `ctx.slots.renderSlot('root', {})`:唯一的 ctx 级渲染入口;传任何其他键、渲染器未安装、root 无人注册,一律大声失败(无 fallback)。 +`SlotsService`(client 运行时)在构造时声明 `'root'`——single/root、`owner: {}`——其 `SlotMap` 合并声明住 runtime 包。壳的全部装配就是 `ctx.slots.renderSlot('root', {})`:唯一的 ctx 级渲染入口;传任何其他键、渲染器未安装、root 无人注册,一律大声失败(无 fallback)。 ### register 是唯一 API;children = 声明+授权+运行时 spec @@ -32,9 +32,11 @@ ctx.slots.register({ }, AppFrame) ``` -不存在独立的坑位定义 API。`children` 对象同时做两件事:**把子坑声明出来**,并**授权本组件渲染它们**——坑是渲染树上的一个洞,因为有人要渲染它才存在,所以坑的生命周期就是声明它的 entry 的生命周期(entry 一经 dispose(资源释放),坑随之消亡、坑内既有贡献清空)。children 的值是运行时 spec(`kind`/`scope` 驱动 outlet 的迭代形态与 binding 选择;`SlotMap` 是纯类型、运行时即被擦除,这正是键数组形行不通的原因),并与对应 `SlotMap` entry 静态对齐校验——类型与值在同一点声明、交叉验证。 +不存在独立的 slot 定义 API。`children` 对象同时做两件事:**声明子 slot**,并**授权本组件渲染它们**——slot 是渲染树上的一个洞,因为有人要渲染它才存在,所以 slot 的生命周期就是声明它的 entry 的生命周期(entry 一经 dispose(资源释放),slot 随之消亡、slot 内既有贡献清空)。children 的值是运行时 spec(`kind`/`scope` 驱动 outlet 的迭代形态与 binding 选择;`SlotMap` 是纯类型、运行时即被擦除,这正是键数组行不通的原因),并与对应 `SlotMap` entry 静态对齐校验——类型与值在同一点声明、交叉验证。 -对等原则:**声明子坑的 entry 独占渲染这些子坑的权力**,全部在 register 时结清(配置错误在装载时大声失败;渲染热径零校验)。装载即炸的情形:第二个 entry 声明已被声明的坑;向未声明的坑 register;同一个 store 句柄挂到两个 scope 之下;chain 注册缺 `select`。 +对等原则:**声明子 slot 的 entry 独占渲染这些子 slot 的权力**,全部在 register 时确定(配置错误会在装载时明确失败;渲染热路径不再校验)。装载即炸的情形:第二个 entry 声明已被声明的 slot;向未声明的 slot register;同一个 store 句柄挂到两个 scope 之下;chain 注册缺 `select`。 + +激活顺序独立于声明条目的贡献方使用 `ctx.slots.inject(key, callback)`,并让直接调用 `register()` 继续大声失败。声明、贡献方、替换与失败各自的生命周期由 [slot 声明注入决策](2026-08-05-slot-declaration-injection.md) 规定。 `SlotMap` 声明合并仍是类型权威,且 entry 只声明自己的轴加 **owner 份额**——注册方注入的 props 永不进入全局表(「谁注入的,类型归谁」)。 @@ -43,23 +45,23 @@ ctx.slots.register({ | 份额 | 类型 | 真源 | 内容 | |---|---|---|---| | 运行时 | `PropsRuntime` | K 对应的 SlotMap entry | `OwnerOf`(渲染现场传参)+ session scope 标配 `useSession`/`sessionId` + 全局 `useSessions`/`useWorkspaces` | -| 子坑渲染 | `PropsRenderSlots` | register 的 `children` 键集 | `renderSlot(key, owner)`,键参静态收窄到 S;chain 键另有 `renderSlotChain` | +| 子 slot 渲染 | `PropsRenderSlots` | register 的 `children` 键集 | `renderSlot(key, owner)`,键参静态收窄到 S;chain 键另有 `renderSlotChain` | | store | `PropsStore` | store 工厂的返回类型 | `useStore` selector hook + `actions.*`(剥去 draft 形参) | -| 业务 | `I` | inject 的返回类型 | 普通数据+回调;保留键 `hooks` 格的裸 observable 经绑定以 `use` 选择器 hook 到达(`InjectFace`) | +| 业务 | `I` | inject 的返回类型 | 普通数据+回调;保留的 `hooks` 区域内,裸 observable 经绑定后以 `use` 选择器 hook 的形式到达(`InjectFace`) | -凡声明 `scope: 'session'` 之处,`sessionId` 一律由框架供给——owner 传参不携带它。register 调用点是双向锁的收口:组件的 renderSlot 键集超出 `children` 声明、漏接某个已声明的面、store/inject 形状漂移,任何一条都在那一行上报编译错误。转授就是普通的 props 传递(把 `renderSlot` 函数递下去,可按需包一层更窄的签名)——不存在白名单面对象,也不存在铸面 API。 +凡声明 `scope: 'session'` 之处,`sessionId` 一律由框架供给——owner 传参不携带它。register 调用点是双重类型约束的收口:组件的 renderSlot 键集超出 `children` 声明、漏接某个已声明的面、store/inject 形状漂移,任何一条都在那一行上报编译错误。转授就是普通的 props 传递(把 `renderSlot` 函数递下去,可按需包一层更窄的签名)——不存在白名单面对象,也不存在铸面 API。 -### chain kind:entry 自荐,首中即渲 +### chain kind:entry 自荐,首个匹配项负责渲染 -第四种 `SlotKind`——`'chain'`——把路由权相对 `keyed` 反转:keyed 的分派现场以 `entryKey` 点选占坑者,chain 则由 entry 自荐——owner 只分派一份通用货币形态的 owner props,永远不知道谁来接管,新的接管包注册进来 owner 零改动。chain 注册携带一个 `select` 纯选择器(`ChainSelect`:`(owner) => matched | null`)与可选的 `priority`(升序;同值保持注册序 = 装配序——部署可控的 inject 拓扑——复用 list `order` 的同一稳定排序);注册缺 `select` 即上文装载即炸情形之一。渲染时 outlet 按链序依次执行各 select:首个非 null 返回值当选,该值以 `matched` 并入组件 props(组件绝不自行重新推导匹配);返回 `null` 则轮到下一个 entry;全 null 则渲染 owner 的 fallback 体(`ChainRenderOpts`)。 +第四种 `SlotKind`——`'chain'`——把路由权相对 `keyed` 反转:keyed 的分派现场以 `entryKey` 点选占用 slot 的 entry,chain 则由 entry 自荐——owner 只分派一套格式统一的 owner props,永远不知道谁来接管,新的接管包注册进来 owner 零改动。chain 注册携带一个 `select` 纯选择器(`ChainSelect`:`(owner) => matched | null`)与可选的 `priority`(升序;同值保持注册序 = 装配序——部署可控的 inject 拓扑——复用 list `order` 的同一稳定排序);注册缺 `select` 即上文装载即炸情形之一。渲染时 outlet 按链序依次执行各 select:首个非 null 返回值当选,该值以 `matched` 并入组件 props(组件绝不自行重新推导匹配);返回 `null` 则轮到下一个 entry;全 null 则渲染 owner 的 fallback 体(`ChainRenderOpts`)。 -「不接」的判定住在 `select` 里,绝不在挂载后的组件里自探 props:组件为了渲染 null 也得先挂载,其 hook 与 effect 全部白跑,随之而来的挂载/卸载抖动还会破坏 memo 化与 React key 语义;而选择器是纯函数——可单测、零挂载副作用——与「presentation methods are pure functions of `args`」是同一条纪律。纯,就是选择器的契约:不读外部可变状态、不产副作用,路由判定因此完全是 owner props 的函数,每次分派都可安全执行。选择器只做路由、绝不铸对象——按分派逐次构造对象会让引用每次渲染都换新;把匹配值包成更丰富的面这件事,发生在当选组件内部(以 `matched` 为依赖的 `useMemo`)。 +「不接」的判定住在 `select` 里,绝不在挂载后的组件里自探 props:组件为了渲染 null 也得先挂载,其 hook 与 effect 全部白跑,随之而来的挂载/卸载抖动还会破坏 memo 化与 React key 语义;而选择器是纯函数——可单测、零挂载副作用——与「presentation methods are pure functions of `args`」是同一条纪律。纯,就是选择器的约定:不读外部可变状态、不产副作用,路由判定因此完全是 owner props 的函数,每次分派都可安全执行。选择器只做路由,绝不创建新对象——按分派逐次构造对象会让引用每次渲染都换新;把匹配值包成更丰富的面这件事,发生在当选组件内部(以 `matched` 为依赖的 `useMemo`)。 类型链上,chain entry 的 SlotMap 形状是 `{ kind: 'chain'; scope; owner }`,`owner` 即链的货币;`M`——`matched` prop 的类型——从 select 返回值推导(选择器收窄 union 成员时,`matched` 类型自动随之收窄),且组件位不参与 `M` 的推断,与钉住 inject 份额的 NoInfer 裁定同源(见下文裁定)。owner 侧,`renderSlotChain(key, owner, { fallback })` 与 `renderSlot` 同住 `PropsRenderSlots` 份额,其键域静态收窄到本 entry children 声明中 chain kind 的键(`ChainKeysOf`);分派现场只有一行,不含任何自有的派生或路由逻辑。 ### store 席位:引擎归框架,schema 归注册方 -框架拥有恰好一台订阅机械:快照 store 引擎(zustand vanilla + immer + 可选 localStorage 持久化)住 **runtime 包**(`./client` 主出口——无子路径),产出裸的可观察源;web-react 在 outlet 处把它们绑定成 hook(按源缓存的 uSES 绑定)。store 里*装什么*是注册方的声明,且必须写成工厂函数,使模块级句柄根本无从存在(模块级句柄会成为跨插件重载存活的事实单例): +框架只拥有一套订阅机制:快照 store 引擎(zustand vanilla + immer + 可选 localStorage 持久化)住 **runtime 包**(`./client` 主出口——无子路径),产出裸的可观察源;web-react 在 outlet 处把它们绑定成 hook(按源缓存的 uSES 绑定)。store 里*装什么*是注册方的声明,且必须写成工厂函数,使模块级句柄根本无从存在(模块级句柄会成为跨插件重载存活的事实单例): ```ts ignore-check export function createChatStore() { @@ -76,11 +78,11 @@ export function createChatStore() { 一个工厂,三个消费点:① `register`——独占 store 直接传工厂;要共享实例,则在 `apply` 里调用一次工厂、把同一句柄传给多次 register(跨插件共享构造性不可能:句柄从不出包);② `PropsStore>` 推导出组件的 store 份额,零手写成员;③ 测试自己调用工厂并 `.create()` 出真引擎实例,把 `useSelector`/`actions` 直接当 props 喂进去——生产 outlet 走的正是同一条 `create` 路径,不存在第二套机械。 -store 的 scope **从挂载 entry 的 scope 推导**(session 坑→每个会话一个实例,随会话生灭;root 坑→每个 entry 一个)。读 = `props.useStore`;写 = 仅 `props.actions.*`——裸实例(带 `update`/`set`)永远到不了组件,声明的 actions 就是完整且可审计的变更面。生产代码在 `apply` 之外从不调用工厂或 `create`。 +store 的 scope **从挂载 entry 的 scope 推导**(session slot →每个会话一个实例,随会话生灭;root slot →每个 entry 一个)。读 = `props.useStore`;写 = 仅 `props.actions.*`——裸实例(带 `update`/`set`)永远到不了组件,声明的 actions 就是完整且可审计的变更面。生产代码在 `apply` 之外从不调用工厂或 `create`。 -### inject:注册方的业务面,立足自己的 ctx +### inject:注册方通过自己的 ctx 提供业务接口 -inject 工厂只收其声明挣来的形参——session 坑得 `sessionId`,声明了 store 的得绑定好的 `actions`,否则无参——取服务一律经 **apply 闭包自己的 ctx**,其能力边界因此就是本插件声明的 `inject` 拓扑(cordis property proxy 原生生效;不存在携带更宽 ctx 的装配句柄)。返回值是普通数据与回调,至多外加保留键 `hooks` 格:一张裸 observable source(getSnapshot+subscribe)表,渲染器在业务面抵达组件前把每个 source 绑成 `use` 选择器 hook——即 provide 通道 hooks 格的注册方私有孪生,供太小众、不该进全局标准件的响应式事实(composer 的 notices/lexicon、settings 导航行)取用。组件永远收不到裸 source,业务代码因此仍零订阅机械。其余保持普通:本插件自有服务的收窄读写面、跨服务编排(如 `send` = `actions.clearDraft()` + `ctx.conversation.send(...)`)、以及 per-(entry×session) 的装配副作用。禁手造 hook、禁 ReactNode 生产者、禁递整个服务对象——收窄本身就是价值:组件能做什么,恰由工厂返回值的形状圈定。 +inject 工厂只接收其声明所授权的形参——session slot 获得 `sessionId`,声明了 store 的获得绑定好的 `actions`,否则无参——取服务一律经 **apply 闭包自己的 ctx**,其能力边界因此就是本插件声明的 `inject` 拓扑(cordis property proxy 原生生效;不存在携带更宽 ctx 的装配句柄)。返回值是普通数据与回调,至多外加保留键 `hooks` 格:一张裸 observable source(getSnapshot+subscribe)表,渲染器在业务面抵达组件前把每个 source 绑成 `use` 选择器 hook——即 provide 通道 hooks 格的注册方私有孪生,供太小众、不该进全局标准件的响应式事实(composer 的 notices/lexicon、settings 导航行)取用。组件永远收不到裸 source,业务代码因此仍不包含订阅机制。其余保持普通:本插件自有服务的收窄读写面、跨服务编排(如 `send` = `actions.clearDraft()` + `ctx.conversation.send(...)`)、以及 per-(entry×session) 的装配副作用。不得手写 hook,不得生成 ReactNode,也不得传递整个服务对象——收窄本身就是价值:组件能做什么,恰由工厂返回值的形状圈定。 ### 数据界线纪律 @@ -88,9 +90,9 @@ hook 只许框架造:`useSession`、`useSessions`、`useWorkspaces`、`useStor ### 树上语境与渲染器安装缝 -`SessionProvider` 是框架组件,**以标配席形式送达**:`children` 里声明了 session scope 坑的 entry 经 prop 收到它(类型住 ui-slots,值由渲染器注入)——组件永不对它做值 import。它框架自接线(内部自读 runtime 的当前会话状态,装配方零传参),render-prop 形——`children(sessionId)` 外加 `empty` 分支,以 `key={sessionId}` 重挂。`BindingContext` 属机械内部;业务组件可见的 React Context 为零。inject 工厂有意在 outlet 内部执行(per-entry 错误边界接得住它们;崩溃的注册方只黑掉自己那一格,装配错误则重抛);outlet 把树上语境当作仅机械可用的暗参读取——即「身份出自 register 闭包、现场出自树位置」的分工。 +`SessionProvider` 是框架组件,**以标配 slot 形式送达**:`children` 里声明了 session scope slot 的 entry 经 prop 收到它(类型住 ui-slots,值由渲染器注入)——组件永不对它做值 import。它框架自接线(内部自读 runtime 的当前会话状态,装配方零传参),render-prop 形——`children(sessionId)` 外加 `empty` 分支,以 `key={sessionId}` 重挂。`BindingContext` 属机械内部;业务组件可见的 React Context 为零。inject 工厂有意在 outlet 内部执行(per-entry 错误边界接得住它们;崩溃的注册方只黑掉自己那一格,装配错误则重抛);outlet 将树上下文作为仅供框架机制使用的隐式参数读取——即「身份出自 register 闭包、现场出自树位置」的分工。 -渲染住在一条安装缝之后,runtime 因此保持 React-free:`SlotRenderer`(接口住 ui-slots,实现 `createSlotRenderer()` 住 web-react)在壳 boot 时经 `ctx.slots.install(...)` 安装一次;双重安装与安装前渲染均 throw。归属记账是服务里的单一 `Map`——账本、坑、贡献、渲染绑定、store 实例全部沿同一条 entry 轴生灭,跨插件重载的陈旧权威窗口由此在构造上关闭(已 dispose 的 entry 所捕获的 `renderSlot`,一进入口即抛陈旧授权(stale-authorization)错误)。 +渲染位于一个 install seam 之后,因此 runtime 不依赖 React:`SlotRenderer`(接口住 ui-slots,实现 `createSlotRenderer()` 住 web-react)在壳 boot 时经 `ctx.slots.install(...)` 安装一次;双重安装与安装前渲染均 throw。归属记账是服务里的单一 `Map`——账本、slot、贡献、渲染绑定、store 实例全部沿同一条 entry 轴生灭,跨插件重载的陈旧权威窗口由此在构造上关闭(已 dispose 的 entry 所捕获的 `renderSlot`,一进入口即抛陈旧授权(stale-authorization)错误)。 ### 类型链实现裁定 @@ -99,11 +101,11 @@ register 签名里的两条硬化裁定之所以存在,是因为显然的替 1. **注册位用 `SlotComponent

    `(裸调用签名)而非 `FC

    `。** React 的 `FC` 携带静态字段(`propTypes`、`defaultProps`),其类型在协变位引用 `P`;两个 `FC` 实例化之间的可赋性检查连这些静态位一起查,会拒绝设计本想接受的组件。裸调用签名只走干净的形参逆变检查;组件仍是普通函数。 2. **`NoInfer` 把业务份额的推断钉在 inject 工厂上。** 没有它,TS 还会从组件形参位收集推断候选,漂移的组件(消费一个工厂并不供给的键)会静默把 `I` 加宽到让调用通过——恰好吸收掉类型链本要抓的漂移。负样本 spec 钉住这一点:若这个 `NoInfer` 日后被「顺手简化」掉,expect-error 位会第一个变红。 -## Consequences +## 后果 -渲染权威从此可强制执行,而非仅靠约定:谁渲染什么是装载期事实,审计 UI 结构 = 通读 register 调用;对 chain 坑,「谁来渲染」额外多出一层渲染期事实,但做决定的选择器全是 register 现场的声明,审计面仍是 register 调用。每个 props 面都从单一真源静态推导(SlotMap entry、children 键集、store 工厂、inject 返回值),schema 变更由编译器传播,而不靠 grep。插件不再自带任何订阅机械——store 生命周期(每会话实例、dispose、持久化)是钉在 entry 轴上的框架语义。代价:注册选项稠密(children spec 对象);框架背上实打实的推断机械(`defineStore` 的 init/actions 同轮推断可能需要柯里化兜底);编译期双向锁意味着原型阶段的漂移直接是硬错误,而非警告。 +渲染权威从此可强制执行,而非仅靠约定:谁渲染什么是装载期事实,审计 UI 结构 = 通读 register 调用;对 chain slot,「谁来渲染」额外多出一层渲染期事实,但做决定的选择器全是 register 现场的声明,审计面仍是 register 调用。每个 props 面都从单一真源静态推导(SlotMap entry、children 键集、store 工厂、inject 返回值),schema 变更由编译器传播,而不靠 grep。插件不再自带任何订阅机制——store 生命周期(每会话实例、dispose、持久化)是钉在 entry 轴上的框架语义。代价:注册选项稠密(children spec 对象);框架背上实打实的推断机械(`defineStore` 的 init/actions 同轮推断可能需要柯里化兜底);编译期双向锁意味着原型阶段的漂移直接是硬错误,而非警告。 -## Alternatives considered +## 考虑过的替代方案 | Rejected | One-line reason | |---|---| @@ -115,5 +117,5 @@ register 签名里的两条硬化裁定之所以存在,是因为显然的替 | 模块级 store 句柄 | 模块级句柄是跨插件重载与跨测试用例的单例;工厂形把身份圈定在单次 apply/测试调用内 | | 组件直收 store 实例 | 渲染代码里能用 `update`/`set`,变更面就无从审计;声明的 actions 让「什么能变」保持为 register 现场的事实 | | 注册位用 `FC` / 从组件推断 `I` | FC 静态位产生协变噪音、拒绝合法组件;组件侧推断静默吸收 props 漂移(见上文裁定) | -| 接管坑用 keyed 分派 + owner 侧路由 | owner 会不断攒下逐 entry 契约与硬编码路由表(每种接管一份 `find` + `entryKey`);chain 货币让新增接管注册保持 owner 零改动 | +| 接管 slot 用 keyed 分派 + owner 侧路由 | owner 会不断攒下逐 entry 约定与硬编码路由表(每种接管一份 `find` + `entryKey`);chain 货币让新增接管注册保持 owner 零改动 | | 组件靠渲染 null 表示不接 | 不接也得先挂载——hook 与 effect 白跑,挂载/卸载抖动破坏 memo 化与 key 语义;纯选择器无需组件实例即可裁决 | diff --git a/.agents/notes/implemented/architecture/2026-07-22-tui-interactive-extension-service.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-22-tui-interactive-extension-service.i18n.yaml deleted file mode 100644 index 0b599bc639..0000000000 --- a/.agents/notes/implemented/architecture/2026-07-22-tui-interactive-extension-service.i18n.yaml +++ /dev/null @@ -1,6 +0,0 @@ -# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each -# side as of the last confirmed-consistent state. Both languages carry equal authority; -# after editing either side, bring the other along and re-record with: -# pnpm run verify-translation-pairing --write -2026-07-22-tui-interactive-extension-service.md: 86cb39748358882d26766467d08f4f43510c1cc2 -2026-07-22-tui-interactive-extension-service.zh.md: d53f526a07b20fcff7086a1f501558d23e7eea8a diff --git a/.agents/notes/implemented/architecture/2026-07-22-unified-send-and-coalesced-user-messages.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-22-unified-send-and-coalesced-user-messages.i18n.yaml index dfae9677c4..0575e85c1c 100644 --- a/.agents/notes/implemented/architecture/2026-07-22-unified-send-and-coalesced-user-messages.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-22-unified-send-and-coalesced-user-messages.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-22-unified-send-and-coalesced-user-messages.md -2026-07-22-unified-send-and-coalesced-user-messages.md: 4d0cbeff0c8a07362caa1ec18493267a9f0d2823 -2026-07-22-unified-send-and-coalesced-user-messages.zh.md: 935a1a78a6bed451c1db646dec2ec5f4f5e87949 +2026-07-22-unified-send-and-coalesced-user-messages.md: f32d6ca65d5236e1fabdd177cdf54e36929c853f +2026-07-22-unified-send-and-coalesced-user-messages.zh.md: 6148cf4e0dda9032fca0ced5b466787877b89fa0 diff --git a/.agents/notes/implemented/architecture/2026-07-22-unified-send-and-coalesced-user-messages.md b/.agents/notes/implemented/architecture/2026-07-22-unified-send-and-coalesced-user-messages.md index 4d0cbeff0c..f32d6ca65d 100644 --- a/.agents/notes/implemented/architecture/2026-07-22-unified-send-and-coalesced-user-messages.md +++ b/.agents/notes/implemented/architecture/2026-07-22-unified-send-and-coalesced-user-messages.md @@ -12,23 +12,23 @@ Separately, `context/message` and `user/message` had converged: the surface proj ## Decision -**One primitive, three preset aliases.** The `Agent` interface's `send(message, { target, wakeup })` covers the (`target` × `wakeup`) matrix. Its complete `UserMessage` owns identity, role, model-facing `content`, and producer `source`; the complete `SendOptions` owns only routing policy. `followup` (`next-turn`/wakeup), `steer` (`next-step`/wakeup), and `inject` (`next-step`/no-wakeup) each accept that one message and fix the policy. `wakeup` means "make the model run": wake a parked driver for a `next-turn` item, or force a continuation for a running `next-step` item. `next-turn`/no-wakeup (queue without waking) is representable with no alias and no current caller. +**One primitive, three preset aliases.** The `Agent` interface's `send(message, target, wakeup)` covers the (`target` × `wakeup`) matrix. Its complete `UserMessage` owns identity, role, model-facing `content`, and producer `source`; the remaining arguments own only routing policy. `followup` (`next-turn`/wakeup), `steer` (`next-step`/wakeup), and `inject` (`next-step`/no-wakeup) each accept that one message and fix the policy. `wakeup` reserves a driver when the agent is idle; an already active driver receives no second reservation and can claim the input only if it reaches a later pre-step boundary. `next-turn`/no-wakeup (queue without waking) is representable with no alias and no current caller. -**inject keeps its mechanism.** The `next-step`/no-wakeup path is exactly the old `inject`: durable model-facing context appended at the current log position, deferred while prompt admission or a turn owns the next safe boundary, and appended directly outside that window. It bypasses the FIFOs entirely, while its required `UserMessage.source` preserves the caller's explicit provenance. +**inject is a non-waking next-step delivery.** It always appends the complete message to the next-step inbox and records that insertion in a durable `agent/inbox/spliced` event. The driver claims it at a later pre-step and records it as model-visible `user/message` only when the final decision returns it in the entering batch; idle injection remains pending until another delivery wakes the driver. Its required `UserMessage.source` preserves the caller's explicit provenance. -**context/message is gone.** Injected context is now a `user/message`; context producers supply the appropriate non-user `source` explicitly, and typed source variants carry any domain-specific durable provenance. The surface, derivation, and `SurfaceEventType` drop `context/message`; consumers that need "is this a human prompt?" read `source.kind === 'user'` instead of the event type. +**context/message is gone.** Injected context uses one `UserMessage` value in the inbox and becomes a `user/message` event if admitted; context producers supply the appropriate non-user `source` explicitly, and typed source variants carry any domain-specific durable provenance. The surface, derivation, and `SurfaceEventType` drop `context/message`; consumers that need "is this a human prompt?" read `source.kind === 'user'` instead of the event type. -**Goal replay disambiguates by round, not type.** A goal state change is a round-zero goal-sourced `user/message` whose source carries the complete change; a positive round is an admitted continuation prompt. `decodeGoalEvent` takes a `user/message` and fails loud when goal-state content and its typed source disagree. +**Goal continuation attribution uses positive rounds.** Goal lifecycle state commits through the domain-owned `goal/change` event defined by the later [goal-owned durable event decision](2026-07-31-goal-owned-durable-events.md). A positive round advances only from an admitted continuation `user/message`; goal persistence does not use injection or inbox state. **`send` does not return identity.** Callers already own the complete message and its opaque `MessageId`; creation and freezing are owned by the [identified immutable message decision](2026-07-28-identified-immutable-message-values.md), not by routing. -**Inbox lifecycle events carry occurrence identities.** `agent/inbox/enqueue` (an item entered a FIFO), `agent/inbox/update` (a pending queued item was edited), `agent/inbox/dequeue` (the driver claimed one), and `agent/inbox/discard` (pending items were dropped) carry an `InboxItem`: an occurrence-local `InboxItemId`, the accepted `UserMessage`, and the resolved `queued | steering` placement captured at acceptance. The occurrence identity lets observers and reconnect mirrors distinguish repeated sends of the same `MessageId` without reconstructing routing from later status or session history. Injection never touches a FIFO and emits none of these. Every FIFO entry publishes one enqueue and exactly one terminal dequeue or discard; updates are non-terminal. The `dsh-agent` invariant companion asserts this FIFO conservation. +**Inbox mutations have one durable projection and three minimal live notifications.** Every append, prepend, edit, remove, cancellation, and claim records normalized `agent/inbox/spliced` coordinates. Insertions emit `agent/inbox/inserted { message }`; ordinary removals carry durable `outcome: 'canceled'` and emit `agent/inbox/discarded { message }`; the loop's atomic `claim()` records pure deletion splices and then emits `agent/inbox/claimed { message, turn }`. `MessageId` is the sole occurrence identity and remains unique across both pending lists. The live payloads deliberately omit placement, outcome, and batch envelopes because the durable splice owns those facts. -**Admission accepts next-step input without becoming a turn.** The loop opens a private next-step acceptance window before `agent/prompt-submit`, keeps it open through the turn, and closes it before `turn/end`. Steering and injection received during admission therefore remain together in the outbox and join an allowed turn. If admission blocks or fails, a context-only caller batch takes idle injection's immediate append, while steering and context staged beside it remain available to retry; neither path writes the rejected prompt. When a later prompt is admitted, retained outbox input enters its turn before that prompt, while input accepted during the current admission remains after the prompt. Closing the window before `turn/end` preserves the rule that reentrant late steering becomes an independent queued turn. `Agent.acceptsNextStep` exposes whether a `next-step` send would currently join this window; `status` remains the broader activity signal rather than a routing predicate. +**Pre-step claims next-step input without making it a separate turn.** Steering and injection always enter the same next-step inbox; steering wakes the driver, while injection does not. At a turn boundary the driver atomically claims pending next-step input before one queued prompt, and between steps it claims only next-step input. Claiming records pure deletion splices and emits `agent/inbox/claimed { message, turn }` once per message. `agent/pre-step` then rejects the proposed step or returns its complete entering batch. Rejection and listener failure leave the claimed batch removed; input arriving after the claim waits for a later boundary. -**One accepted message keeps one representation.** Durable user-role input and additional model-facing context both use the identified, frozen `UserMessage` directly. The loop stores that value beside private routing state rather than copying its identity, content, or source into another public shape. A queued message that becomes steering keeps the same message value in the outbox, while injected and tool-produced context each carry their own identified message. The [identified immutable message decision](2026-07-28-identified-immutable-message-values.md) supersedes this note's former `UserMessageData`/`AgentMessage` hierarchy and extends the representation to assistant and tool-result messages. +**One accepted message keeps one representation.** Durable user-role input and additional model-facing context both use the identified, frozen `UserMessage` directly. The loop stores that value beside private routing state rather than copying its identity, content, or source into another public shape. Steering, injection, and tool-produced context each keep their identified messages in the next-step inbox. The [identified immutable message decision](2026-07-28-identified-immutable-message-values.md) supersedes this note's former `UserMessageData`/`AgentMessage` hierarchy and extends the representation to assistant and tool-result messages. -**Idle wakeup follows acceptance.** Before publishing enqueue, a waking queued send installs quiescence ownership and schedules driver admission for a microtask that runs after the id returns. Every send in one synchronous caller stack therefore resolves placement against the same pre-admission state, while reentrant cancellation or teardown cannot retire before the scheduled admission settles. Two idle `steer()` calls remain two FIFO turns instead of the first opening an admission window that captures the second. +**Idle wakeup follows insertion.** A waking send inserts its input, then enters the running driver before returning. The first pre-step may claim that input immediately; later synchronous sends therefore join the running loop and wait for a later boundary. Cancellation belongs to the running turn signal from wakeup onward; no distinct pre-run phase intervenes. **cancel gains keepInbox.** `cancel(cause, { keepInbox? })`; callers choose the cause explicitly, and `keepInbox: true` aborts the active turn while preserving queued and steering items (no discard event, and un-started work is not dropped). @@ -36,14 +36,14 @@ Separately, `context/message` and `user/message` had converged: the surface proj - **A dedicated `MessageSource` kind `context`** for injected content. Rejected because `plugin` already means "not a human," so a fourth kind would add a parallel axis the authority checks would have to learn. Plugin-produced injected context supplies its plugin source explicitly. - **A typed discriminant field on `UserMessage`** (e.g. `origin: 'prompt' | 'context'`) to replace the event-type split. Rejected in favor of `source`, which every consumer already carries and which the goal system already keyed on; a second discriminant would duplicate that fact. -- **Keeping `agent/queued` alongside the inbox events.** Rejected as a mirror: `agent/inbox/enqueue` is the same enqueue-time signal with the resolved placement, and the dequeue/discard events complete the FIFO lifecycle the single event could not describe. -- **Derive inbox placement from agent status or the session log.** Rejected because `running` includes admission and settlement, while reconnect baselines need the original acceptance result even when the earlier turn boundary is absent. The producer already owns the exact routing decision. +- **Keeping `agent/queued` alongside the inbox events.** Rejected as a mirror: `agent/inbox/inserted` is the live insertion signal, while claimed/discarded notifications describe exits and the durable splice retains placement. +- **Derive inbox placement from agent status.** Rejected because `running` includes pre-step processing and settlement. The producer already supplies the exact target to the durable splice. ## Consequences -The delivery surface is now one primitive plus three self-documenting presets, and the (`target` × `wakeup`) matrix makes previously-unreachable combinations explicit. One durable message type serves prompts, injected context, and goal rounds, so the surface projection and every "human prompt?" check simplify to a `source` test. The `Agent` contract remains an interface, so alternate implementations and object-literal test fakes implement the same minimal structural surface. The goal fold's channel split moved from event type to `source.round`, and every consumer that filtered `context/message` now filters `user/message` by source. An idle injection appends `user/message` between turns without opening a turn or running the model. +The delivery surface is now one primitive plus three self-documenting presets, and the (`target` × `wakeup`) matrix makes previously-unreachable combinations explicit. One identified message value serves prompts, injected context, and goal rounds, so every "human prompt?" check simplifies to a `source` test. The `Agent` contract remains an interface, so alternate implementations and object-literal test fakes implement the same minimal structural surface. Positive goal rounds fold from admitted `user/message` events, while goal lifecycle state remains outside the delivery surface. An idle injection remains pending without opening a turn or running the model, then becomes `user/message` when a later waking delivery's pre-step returns it in the entering batch. -`wakeup` is the "should the model run" signal, so the inbox distinguishes waking queued work from anything available to dequeue: a lone `next-turn`/no-wakeup item stays parked at idle and rides along the next waking send, and `whenIdle`/`cancel` settle quiescence off the waking signal. Every FIFO exit publishes exactly one lifecycle event, while domain-specific durable facts travel in typed message sources rather than a parallel metadata channel. The direct pending-item representation keeps public lifecycle events correlated without maintaining a second steering wrapper or allowing its durable data to diverge. The later [addressable queue operations](../feature/2026-07-29-addressable-queue-operations.md) decision adds live mutations over that occurrence identity without changing the one-message-per-turn or durable-message contracts. +`wakeup` is the "should the model run" signal, so the inbox distinguishes waking queued work from anything available to claim: a lone `next-turn`/no-wakeup item stays parked at idle and rides along the next waking send, and `whenIdle`/`cancel` settle quiescence off the waking signal. Every insertion and exit publishes its matching live notification, while domain-specific durable facts travel in typed message sources rather than a parallel metadata channel. The direct pending-message representation keeps durable splices and live events correlated without maintaining a second steering wrapper or allowing its data to diverge. The later [claimed pre-step inbox lifecycle](2026-07-31-claimed-pre-step-inbox-lifecycle.md) decision keeps live queue mutations addressed by `MessageId` and separates single-message lifecycle notifications from the durable whole-queue splice projection. ## Related diff --git a/.agents/notes/implemented/architecture/2026-07-22-unified-send-and-coalesced-user-messages.zh.md b/.agents/notes/implemented/architecture/2026-07-22-unified-send-and-coalesced-user-messages.zh.md index 935a1a78a6..6148cf4e0d 100644 --- a/.agents/notes/implemented/architecture/2026-07-22-unified-send-and-coalesced-user-messages.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-22-unified-send-and-coalesced-user-messages.zh.md @@ -8,27 +8,27 @@ Status: implemented agent 的对外驱动接口逐渐长出三个近乎平行的动词——`send`、`steer`、`inject`——各自带有独立的选项类型、独立的实时事件叙事,以及独立的持久事件。`send` 和 `steer` 都会把一条冻结的 inbox 记录入队并发出 `agent/queued`;`inject` 则绕过 inbox,写入一条独立的 `context/message` 持久事件。这三个动词实际上只沿两条独立的轴变化:一个队列项加入哪个队列(一个全新的轮次,还是当前活跃的轮次),以及这个队列项是否让模型运行。把这个 2×2 编码成三个手写方法,掩盖了其中的对称性,让“排入一个轮次但不唤醒驱动器”无法表达,也让 `cancel()` 无从在保留排队工作的前提下中止一个轮次。 -另外,`context/message` 与 `user/message` 已经趋同:对外接口把二者都投影为逐字的 user 角色内容,唯一真正的区别是注入的上下文携带非 user `source` 且“不是提示词”。一个投影对应两种事件类型,意味着每个消费方都要根据事件类型分支来回答“这是不是一条人类提示词?”,而 goal 系统把这种类型区分当作侧信道使用(第 0 轮的状态变更是 `context/message`,已准入的轮次是 `user/message`)。 +另外,`context/message` 与 `user/message` 已经趋同:对外接口把二者都原样投影为 user 角色内容,唯一真正的区别是注入的上下文携带非 user `source` 且“不是提示词”。一个投影对应两种事件类型,意味着每个消费方都要根据事件类型分支来回答“这是不是一条人类提示词?”,而 goal 系统把这种类型区分当作侧信道使用(第 0 轮的状态变更是 `context/message`,已准入的轮次是 `user/message`)。 ## 决策 -**一个原语,三个预设别名。** `Agent` 接口的 `send(message, { target, wakeup })` 覆盖 (`target` × `wakeup`) 矩阵。完整的 `UserMessage` 持有标识、角色、模型可见 `content` 与生产方 `source`;完整的 `SendOptions` 只持有路由策略。`followup`(`next-turn`/wakeup)、`steer`(`next-step`/wakeup)和 `inject`(`next-step`/no-wakeup)都接收这一条消息并固定策略。`wakeup` 意为“让模型运行”:为一个 `next-turn` 队列项唤醒处于停泊状态的驱动器,或为一个运行中的 `next-step` 队列项强制继续执行。`next-turn`/no-wakeup(入队但不唤醒)可以表达,只是没有别名,也没有当前调用方。 +**一个原语,三个预设别名。** `Agent` 接口的 `send(message, target, wakeup)` 覆盖 (`target` × `wakeup`) 矩阵。完整的 `UserMessage` 持有标识、角色、模型可见 `content` 与生产方 `source`;其余参数只持有路由策略。`followup`(`next-turn`/wakeup)、`steer`(`next-step`/wakeup)和 `inject`(`next-step`/no-wakeup)都接收这一条消息并固定策略。`wakeup` 会在 agent 空闲时保留一个驱动器;已经活跃的驱动器不会获得第二次保留,只有在抵达后续 pre-step 边界时才能领取该输入。`next-turn`/no-wakeup(入队但不唤醒)可以表达,只是没有别名,也没有当前调用方。 -**inject 保留其机制。** `next-step`/no-wakeup 路径正是旧的 `inject`:持久的面向模型上下文会追加到当前日志位置;提示词准入或一个轮次占有下一个安全边界时,它会延迟处理,而在该窗口之外则直接追加。它完全绕过 FIFO 队列,而必填的 `UserMessage.source` 会保留调用方显式提供的来源信息。 +**inject 是不会唤醒的 next-step 投递。** 它始终把完整消息追加到 next-step inbox,并在持久 `agent/inbox/spliced` 事件中记录该插入。驱动器会在后续 pre-step 领取它,并且只有最终决策把它放入进入步骤的批次时,才会将其记录为模型可见的 `user/message`;空闲注入会保持待处理,直到其他投递唤醒驱动器。必填的 `UserMessage.source` 会保留调用方显式提供的来源信息。 -**context/message 已移除。** 注入的上下文现在是一条 `user/message`;上下文生产方显式提供合适的非 `user` 类别 `source`,类型化 source 变体携带所有特定于领域的持久来源信息。对外接口、派生逻辑和 `SurfaceEventType` 都不再包含 `context/message`;需要判断“这是不是一条人类提示词?”的消费方改为读取 `source.kind === 'user'`,而不是事件类型。 +**context/message 已移除。** 注入的上下文在 inbox 中使用同一个 `UserMessage` 值,并在获准时成为 `user/message` 事件;上下文生产方显式提供合适的非 `user` 类别 `source`,类型化 source 变体携带所有特定于领域的持久来源信息。对外接口、派生逻辑和 `SurfaceEventType` 都不再包含 `context/message`;需要判断“这是不是一条人类提示词?”的消费方改为读取 `source.kind === 'user'`,而不是事件类型。 -**goal 回放靠轮次而非类型来区分。** 一次 goal 状态变更是一条第 0 轮、来源为 goal 的 `user/message`,其 source 携带完整变更;正数轮次则是一条已准入的继续执行提示词。`decodeGoalEvent` 接收一条 `user/message`,并在 goal 状态内容与其类型化 source 不一致时立即报错。 +**Goal 继续执行归属使用正数 Round。** Goal 生命周期状态通过后续的[Goal 自有持久事件决策](2026-07-31-goal-owned-durable-events.md)所定义的领域自有 `goal/change` 事件提交。正数 Round 只从已准入的继续执行 `user/message` 推进;goal 持久化不使用注入或 inbox 状态。 **`send` 不返回标识。** 调用方已经持有完整消息及其不透明的 `MessageId`;消息的创建与冻结由[带标识的不可变消息值决策](2026-07-28-identified-immutable-message-values.md)负责,而不是由路由负责。 -**Inbox 生命周期事件携带单次入队标识。** `agent/inbox/enqueue`(一个队列项进入某个 FIFO)、`agent/inbox/update`(待处理的 queued 项被编辑)、`agent/inbox/dequeue`(驱动器认领一个项)和 `agent/inbox/discard`(待处理项被丢弃)都会携带一个 `InboxItem`:仅属于本次入队的 `InboxItemId`、已接受的 `UserMessage`,以及生产方在接受消息时捕获的已解析 `queued | steering` 放置方式。单次入队标识让观察方和重连镜像能够区分同一 `MessageId` 的多次发送,无需根据后续状态或会话历史重建路由。注入从不触及 FIFO,也不发出这些事件中的任何一个。每次 FIFO 入队都会发布一个 enqueue,并且恰好发布一个终态 dequeue 或 discard;update 不是终态。`dsh-agent` 的不变量配套断言这种 FIFO 守恒。 +**Inbox 变更只有一份持久投影和三种最小实时通知。** 每次 append、prepend、编辑、删除、取消与领取都会记录规范化的 `agent/inbox/spliced` 坐标。插入会发出 `agent/inbox/inserted { message }`;普通删除携带持久 `outcome: 'canceled'`,并发出 `agent/inbox/discarded { message }`;循环的原子 `claim()` 会记录纯删除 splice,随后发出 `agent/inbox/claimed { message, turn }`。`MessageId` 是唯一的单次出现标识,并在两个待处理列表间保持唯一。实时载荷刻意不携带 placement、outcome 或批次封套,因为这些事实由持久 splice 持有。 -**准入接受 next-step 输入,但不会因此成为一个轮次。** 循环会在 `agent/prompt-submit` 前打开一个私有的 next-step 接受窗口,使其贯穿整个轮次,并在 `turn/end` 前关闭。因此,在准入期间收到的 steering 和注入会一起留在 outbox 中并加入获准轮次。如果准入被阻止或失败,仅含调用方上下文的批次会采用空闲注入的立即追加行为,而 steering 及与其一同暂存的上下文仍可重试;两种路径都不会写入被拒绝的提示词。后续提示词获准时,保留在 outbox 中的输入会先于该提示词进入其轮次,而当前准入期间接受的输入则留在提示词之后。在 `turn/end` 前关闭窗口,可以保留这样的规则:可重入的晚到 steering 会成为一个独立的排队轮次。`Agent.acceptsNextStep` 会公开一次 `next-step` 发送当前是否会加入该窗口;`status` 仍是更宽泛的活动信号,而非路由判据。 +**pre-step 会领取 next-step 输入,但不会为它单独创建轮次。** steering 和注入始终进入同一个 next-step inbox;steering 会唤醒驱动器,注入则不会。在轮次边界,驱动器会原子领取待处理的 next-step 输入,再领取一条排队提示词;在步骤之间则只领取 next-step 输入。领取会记录纯删除 splice,并针对每条消息发出一次 `agent/inbox/claimed { message, turn }`。随后 `agent/pre-step` 会拒绝拟议步骤,或返回进入步骤的完整批次。拒绝与监听器失败都会让已领取批次保持已删除;领取后才到达的输入会等待后续边界。 -**一条已接受消息只保留一种表示。** 持久的用户角色输入和附加的模型可见上下文都直接使用带标识且冻结的 `UserMessage`。循环把该值与私有路由状态存放在一起,不会将其标识、内容或来源复制到另一种公开形状中。一条成为 steering 的排队消息会在 outbox 中保留同一个消息值,而注入和工具产生的上下文则各自携带带标识的消息。[带标识的不可变消息值决策](2026-07-28-identified-immutable-message-values.md)取代了本记录此前的 `UserMessageData`/`AgentMessage` 层级,并将这一表示扩展到 assistant 消息和工具结果消息。 +**一条已接受消息只保留一种表示。** 持久的用户角色输入和附加的模型可见上下文都直接使用带标识且冻结的 `UserMessage`。循环把该值与私有路由状态存放在一起,不会将其标识、内容或来源复制到另一种公开形状中。steering、注入和工具产生的上下文都会在 next-step inbox 中保留各自带标识的消息。[带标识的不可变消息值决策](2026-07-28-identified-immutable-message-values.md)取代了本记录此前的 `UserMessageData`/`AgentMessage` 层级,并将这一表示扩展到 assistant 消息和工具结果消息。 -**空闲唤醒在接受之后发生。** 在发布 enqueue 前,一次会唤醒驱动器的排队发送会先取得完全停稳所有权,并把驱动器准入调度到一个会在该次发送返回 id 后运行的微任务中。因此,同一同步调用栈中的每次发送都会基于同一份准入前状态解析放置方式,而可重入的取消或拆除在已调度的准入结算前无法完成退役。空闲时的两次 `steer()` 调用会保留为两个 FIFO 轮次,而不会因第一次调用打开准入窗口而把第二次吸纳进去。 +**空闲唤醒在插入之后发生。** 会唤醒的发送会先插入输入,再于返回前进入 running 驱动器。首次 pre-step 可能立即领取该输入;因此,后续同步发送会加入正在运行的循环,并等待更晚的边界。自唤醒开始,取消就归属于 running 轮次信号,中间不会插入独立的预运行 phase。 **cancel 新增 keepInbox。** `cancel(cause, { keepInbox? })`;调用方显式选择 cause,且 `keepInbox: true` 会中止活跃轮次,同时保留排队项和 steering 项(不发出 discard 事件,尚未启动的工作也不会被丢弃)。 @@ -36,18 +36,18 @@ agent 的对外驱动接口逐渐长出三个近乎平行的动词——`send` - **为注入内容设立专门的 `MessageSource` 类别 `context`。** 不予采纳,因为 `plugin` 已经表示“不是人类”,因此第四种类别会增加一条平行的轴,让授权检查不得不去学习它。由插件产生的注入上下文会显式提供其 plugin 来源。 - **在 `UserMessage` 上设一个类型化的判别字段**(例如 `origin: 'prompt' | 'context'`)来取代事件类型的区分。不予采纳,转而采用 `source`——每个消费方都已经携带它,goal 系统也已经以它为键;第二个判别字段会重复这一事实。 -- **在 inbox 事件之外保留 `agent/queued`。** 作为镜像而被否决:`agent/inbox/enqueue` 是同一个入队时刻的信号,只是带有已解析的放置方式,而 dequeue/discard 事件补全了单个事件无法描述的 FIFO 生命周期。 -- **根据 agent 状态或会话日志推导 inbox 放置方式。** 不予采纳,因为 `running` 同时涵盖准入与结算,而重连基线即使缺少此前的轮次边界,也需要最初的接受结果。生产方已经拥有精确的路由决策。 +- **在 inbox 事件之外保留 `agent/queued`。** 作为镜像而被否决:`agent/inbox/inserted` 已经是实时插入信号,claimed/discarded 通知描述退出,而持久 splice 保留 placement。 +- **根据 agent 状态推导 inbox 放置方式。** 不予采纳,因为 `running` 同时涵盖 pre-step 处理与结算。生产方已经把精确目标写入持久 splice。 ## 后果 -投递接口现在是一个原语加三个自解释的预设,(`target` × `wakeup`) 矩阵把此前无法表达的组合显式化。一种持久消息类型同时服务提示词、注入的上下文和 goal 轮次,因此对外接口的投影和每一处“是否人类提示词?”检查都简化为一次 `source` 判断。`Agent` 契约仍是接口,因此其他实现和对象字面量形式的测试替身只需实现同一个最小结构接口。goal 折叠的通道区分从事件类型改到了 `source.round`;此前过滤 `context/message` 的每个消费方现在改为按来源过滤 `user/message`。空闲状态下的注入会在两个轮次之间追加 `user/message`,既不打开轮次,也不运行模型。 +投递接口现在是一个原语加三个自解释的预设,(`target` × `wakeup`) 矩阵把此前无法表达的组合显式化。同一个带标识消息值同时服务提示词、注入的上下文和 Goal Round,因此每一处“是否人类提示词?”检查都简化为一次 `source` 判断。`Agent` 约定仍是接口,因此其他实现和对象字面量形式的测试替身只需实现同一个最小结构接口。正数 Goal Round 从已准入的 `user/message` 事件折叠,而 goal 生命周期状态位于投递接口之外。空闲注入会保持待处理,不打开轮次也不运行模型;后续会唤醒的投递在 pre-step 将其放入进入步骤的批次时,它才成为 `user/message`。 -`wakeup` 是“模型是否应当运行”的信号,因此 inbox 会区分能唤醒的排队工作与任何可 dequeue 的项:一个孤立的 `next-turn`/no-wakeup 队列项会停泊在空闲状态,并随下一次唤醒 send 一同带出,而 `whenIdle`/`cancel` 依据唤醒信号来结算完全停稳。每一次 FIFO 退出都恰好发布一个生命周期事件,特定于领域的持久事实则通过类型化消息 source 传递,而非通过平行的元数据通道。直接使用待处理项的表示方式,使公开生命周期事件保持可关联,既无需维护第二个 steering 包装层,也避免其持久数据发生分歧。后续的[可寻址队列操作](../feature/2026-07-29-addressable-queue-operations.md)决策在该单次入队标识上增加了实时变更,但不改变单消息单轮次或持久消息契约。 +`wakeup` 是“模型是否应当运行”的信号,因此 inbox 会区分能唤醒的排队工作与任何可领取的项:一个孤立的 `next-turn`/no-wakeup 队列项会停泊在空闲状态,并随下一次唤醒 send 一同带出,而 `whenIdle`/`cancel` 依据唤醒信号来结算完全停稳。每次插入与退出都会发布对应的实时通知,特定于领域的持久事实则通过类型化消息 source 传递,而非通过平行的元数据通道。直接使用待处理消息的表示方式,使持久 splice 与实时事件保持可关联,既无需维护第二个 steering 包装层,也避免数据发生分歧。后续的[已领取 pre-step inbox 生命周期](2026-07-31-claimed-pre-step-inbox-lifecycle.md)决策保留通过 `MessageId` 寻址的实时队列变更,并把单消息生命周期通知与持久的整体队列 splice 投影分离。 ## 相关 - [one-send-one-turn](../simplification/2026-07-17-one-send-one-turn.md)——本决策所依托的“每轮次只认领一条消息”规则。 - [remove-agent-steering-mirror](../../archived/simplification/2026-07-04-remove-agent-steering-mirror.md)——折叠镜像实时事件的先例。 - [explicit-turn-cancellation](2026-07-16-explicit-turn-cancellation.md)——`keepInbox` 所扩展的取消原因信号。 -- [带标识的不可变消息值](2026-07-28-identified-immutable-message-values.md)——本路由决策现在所依托的消息标识与表示契约。 +- [带标识的不可变消息值](2026-07-28-identified-immutable-message-values.md)——本路由决策现在所依托的消息标识与表示约定。 diff --git a/.agents/notes/implemented/architecture/2026-07-23-client-plugin-loading-model.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-23-client-plugin-loading-model.i18n.yaml index 451dcd1fca..021857e30b 100644 --- a/.agents/notes/implemented/architecture/2026-07-23-client-plugin-loading-model.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-23-client-plugin-loading-model.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-23-client-plugin-loading-model.md -2026-07-23-client-plugin-loading-model.md: 02347f2964942b89ec1f0a6ec483f4c2b2f9e68c -2026-07-23-client-plugin-loading-model.zh.md: ea927d35860fbbba567c47cea0ee3a45133ce0f4 +2026-07-23-client-plugin-loading-model.md: 2dc0c68e5f20bd790c2362f92c16dece171babf5 +2026-07-23-client-plugin-loading-model.zh.md: 8cb8fb5523475fd0cc03fa20fc04422c6b7397e3 diff --git a/.agents/notes/implemented/architecture/2026-07-23-client-plugin-loading-model.md b/.agents/notes/implemented/architecture/2026-07-23-client-plugin-loading-model.md index 02347f2964..2dc0c68e5f 100644 --- a/.agents/notes/implemented/architecture/2026-07-23-client-plugin-loading-model.md +++ b/.agents/notes/implemented/architecture/2026-07-23-client-plugin-loading-model.md @@ -14,7 +14,9 @@ The browser client runs the same cordis plugin mechanism, so it needs the same s Conventional frontend engineering digests all dependencies at build time: one bundle, externals resolved by the bundler, nothing left to manage at runtime. Runtime module management on top of that is the unusual requirement here. The client therefore splits into two layers: the upper layer is cordis plugin loading through the same vendored Loader, and the lower layer is module-granular dependency management — `dsh-client-modules`. -The lower layer supplies four capabilities: externals (the platform list), remote arrival (bundle fetch plus lazy factory registration), versioning (content-hash revs), and hot update (invalidate/prefetch). +The lower layer supplies four capabilities: externals (the platform list), remote arrival (same-origin external classic scripts plus lazy factory registration), versioning (content-hash revs), and hot update (invalidate/prefetch). + +Plugin bundles are built independently outside Vite's module graph. Feeding response text into an inline script leaves the browser with a dynamic source execution: no standard source-map chain connects the network resource, generated bundle, and TypeScript/TSX source, so performance profiles and stacks stop at generated `client.js`; the module system must also buffer the complete source and split one arrival responsibility across fetch and execute transport seams. On top of that, client and host plugins register and load consistently: a package declares `dshClient` once, the host scans the declaration into the boot graph, and the same Loader semantics govern entries on both sides. @@ -46,10 +48,18 @@ Four edge rules govern imports across the two kinds. None of them depends on any The browser mirrors the host's division of labor. `dsh-client-modules` (`ClientModuleSystem`) takes the module-system seat that Node's internal ESM loader holds host-side; the same vendored `@cordisjs/plugin-loader` keeps the governance seat on both sides. The line between them in one sentence: **the module system owns module identity and bytes — how code arrives, registers, and becomes an export surface; the Loader owns plugin lifecycle — when a plugin mounts, what it waits for, and how it is torn down.** -`ClientModuleSystem` is a lazy CJS table. Executing a bundle only **registers** its factory — the bundle calls `window.__ModuleLoader__.load({ id, factory })` and nothing else happens. Every module body side effect, CSS injection included, lives inside the factory closure and runs at materialization: the first `require`/import of that id, memoized after that. A factory that requires a registered-but-unmaterialized sibling materializes it recursively, so no sort order exists anywhere. When asked to import an id, the table resolves through a fixed branch order: seed word → memoized record → static registration (shell-own modules, e.g. app-shell) → registered factory → graph-row fetch + execute → loud throw. That final throw is the runtime mirror of the build-time purity gate. The system also keeps per-module bookkeeping — owned `