diff --git a/.agents/notes/implemented/feature/2026-06-14-acp-agent-client-protocol.i18n.yaml b/.agents/notes/implemented/feature/2026-06-14-acp-agent-client-protocol.i18n.yaml index a3a3e3b72f..91d675acea 100644 --- a/.agents/notes/implemented/feature/2026-06-14-acp-agent-client-protocol.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-06-14-acp-agent-client-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 -2026-06-14-acp-agent-client-protocol.md: c6976ed28a254684fca62e2d309cdde7ea90340d -2026-06-14-acp-agent-client-protocol.zh.md: 6bd234f2aa3f43f4fc6cbd921161253c46aab73e +2026-06-14-acp-agent-client-protocol.md: 61e2fd609b9f2762b50ef0fa76173259506c1470 +2026-06-14-acp-agent-client-protocol.zh.md: 608f445432913e3a332f5e8320a4154768217af4 diff --git a/.agents/notes/implemented/feature/2026-06-14-acp-agent-client-protocol.zh.md b/.agents/notes/implemented/feature/2026-06-14-acp-agent-client-protocol.zh.md index 6bd234f2aa..608f445432 100644 --- a/.agents/notes/implemented/feature/2026-06-14-acp-agent-client-protocol.zh.md +++ b/.agents/notes/implemented/feature/2026-06-14-acp-agent-client-protocol.zh.md @@ -52,7 +52,7 @@ harness 最初仅通过 readline 循环暴露 agent。该接口能传输文本 桥接层有意不实现会话列表/删除/恢复/关闭能力、MCP 透传、附加目录、图片/音频/嵌入资源提示词、plan、斜杠命令、用量更新、编辑器文件系统委托或 ACP 终端执行子协议。后续已通过标准会话配置选项加入运行时模型选择,见 [LLM 目录与 ACP 选择 Agent Note](../architecture/2026-07-15-llm-model-catalog-and-acp-selection.md)。 -空闲时的配置选择在实时响应中是真实的,但在下一次 `agent/prompt-submit` 将其锚定到开放轮次之前不具持久性。在该边界之前崩溃会丢失待定选择;这是保持会话事件封闭于轮次内且回放安全的代价。 +空闲时的配置选择在实时响应中是真实的,但在下一次 `agent/step` 将其锚定到开放轮次之前不具持久性。在该边界之前崩溃会丢失待定选择;这是保持会话事件封闭于轮次内且回放安全的代价。 ## 验证 diff --git a/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.i18n.yaml b/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.i18n.yaml index 7998dc3257..a31d1ee801 100644 --- a/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.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 -2026-06-18-compaction-capability-seam.md: a263b5e7d0245bd1279024a50e05b2f33edad521 -2026-06-18-compaction-capability-seam.zh.md: df0cf9d9131978e608d47124ba0f0db0343ee12a +2026-06-18-compaction-capability-seam.md: 73fd78af9d4ef86ae7bafc3a3608ff1afbbd87bd +2026-06-18-compaction-capability-seam.zh.md: 8fc92ccd5ae6ad61a174e01b3ee3afa1df0a4529 diff --git a/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.zh.md b/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.zh.md index df0cf9d913..8fc92ccd5a 100644 --- a/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.zh.md +++ b/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.zh.md @@ -39,7 +39,7 @@ Status: implemented 成功调用的压力检查不能在步骤前运行,因为最终的 `agent/request` 路由、提供方输出、工具结果、缓冲上下文与 steering 当时尚不存在。串行的 `agent/post-step(agent, turn, step, signal)` 会在这些事实持久化后、`step/end` 之前触发。`dsh-compact-basic` 通过 `ctx.tokenMeter` 测量规范的已记录请求,因此下一个请求无需推测性覆盖信封即可看到任何替换。压力达到条件后,可选的 `ctx.toolResultPrune` 重写在摘要范围选择前运行;compact-basic 重新测量持久 surface,如果修剪恢复到安全压力便跳过摘要生成。 -规范的提供方上下文溢出走另一条路径。失败步骤先关闭,`agent/request-error` 接收原始请求错误与连续重试次数,compact-basic 在强制执行一次有效且平衡的缩减前先修剪。仅当 `session.surface.replaceGeneration` 增加时,它才返回 retry;这包括没有摘要范围时仅修剪取得的进展。随后循环开启新的编号步骤,并从持久日志重建请求。没有替换、任何替换前的恢复失败、取消、耗尽的上限或无关错误都会保留原始提供方失败。如果修剪已经推进 generation,而后续摘要工作失败,恢复会从该持久的已修剪 surface 重试,除非取消或资源释放胜出。完整生命周期决策见[调用后恢复 Agent Note](../architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md)。 +规范的提供方上下文溢出走另一条路径。失败步骤先关闭,`agent/request-error` 接收原始请求错误。compact-basic 自行持有按 agent 计的溢出次数,在强制执行一次有效且平衡的缩减前先修剪,且仅当 `session.surface.replaceGeneration` 增加时才调用 `agent.retry()`;这包括没有摘要范围时仅修剪取得的进展。随后循环关闭失败轮次,开启新的编号重试轮次,并从持久日志重建请求。没有替换、任何替换前的恢复失败、取消、耗尽的上限或无关错误都会保留原始提供方失败。如果修剪已经推进 generation,而后续摘要工作失败,恢复会从该持久的已修剪 surface 重试,除非取消或资源释放胜出。完整生命周期决策见[调用后恢复 Agent Note](../architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md)。 ``` assistant/message → tool/result/context/steering diff --git a/.agents/notes/implemented/feature/2026-06-30-hook-bridges.i18n.yaml b/.agents/notes/implemented/feature/2026-06-30-hook-bridges.i18n.yaml index cfcf477426..08e3acdef5 100644 --- a/.agents/notes/implemented/feature/2026-06-30-hook-bridges.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-06-30-hook-bridges.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 -2026-06-30-hook-bridges.md: b6b0894e5551563187b1631e8c641e326fa166b0 -2026-06-30-hook-bridges.zh.md: 5f3adef958738d9d23c159c388be35b89f321828 +2026-06-30-hook-bridges.md: c944a7699eda1878c1ec2db20f45c788da89c607 +2026-06-30-hook-bridges.zh.md: cd4886e146d3d4c8b016aea166819750aa497823 diff --git a/.agents/notes/implemented/feature/2026-06-30-hook-bridges.zh.md b/.agents/notes/implemented/feature/2026-06-30-hook-bridges.zh.md index 5f3adef958..cd4886e146 100644 --- a/.agents/notes/implemented/feature/2026-06-30-hook-bridges.zh.md +++ b/.agents/notes/implemented/feature/2026-06-30-hook-bridges.zh.md @@ -6,7 +6,7 @@ Status: implemented ## 问题 -harness 的扩展面是其类型化的拦截 seam(见[拦截 seam Agent Note](2026-06-30-interception-seams.md)):所谓「原生钩子」不过是一个普通的 Cordis 插件,订阅 `agent/session-start`、`agent/prompt-submit`、`tools/pre-execute`、`tools/post-execute`、`agent/turn-continuation`、`subagent/start`、`subagent/end`。但用户带着**既有的** Claude Code(CC)和 Codex 钩子配置到来,一个 `hooks.json`(或 settings 文件中的 `hooks` 键)里满是 shell 命令钩子,并希望它们原样运行。本 Agent Note 引入两个**桥接插件**,将外部 shell 钩子协议翻译到类型化 seam 上,构建于共享的协议格式(wire format)库之上(见 [hook-protocol-lib Agent Note](2026-06-30-hook-protocol-lib.md))。 +harness 的扩展面是其类型化的拦截 seam(见[拦截 seam Agent Note](2026-06-30-interception-seams.md)):所谓「原生钩子」不过是一个普通的 Cordis 插件,订阅 `agent/session-start`、`agent/prompt-submit`、`tools/pre-execute`、`tools/post-execute`、`agent/stopping`、`subagent/start` 或 `subagent/end`。但用户带着**既有的** Claude Code(CC)和 Codex 钩子配置到来,一个 `hooks.json`(或 settings 文件中的 `hooks` 键)里满是 shell 命令钩子,并希望它们原样运行。本 Agent Note 引入两个**桥接插件**,将外部 shell 钩子协议翻译到类型化 seam 上,构建于共享的协议格式(wire format)库之上(见 [hook-protocol-lib Agent Note](2026-06-30-hook-protocol-lib.md))。 贯穿整个设计的定位:**桥接是兼容性适配器,不是高级工具。** 桥接能做的事(阻止工具、注入上下文、强制继续、观察 subagent),原生 Cordis 插件都能做得更强——类型化返回值、完整 `ctx`、无序列化边界。桥接存在的理由是运行外部 CC/Codex 命令钩子中被明确支持的子集。这使每个桥接保持精简:解析配置、选择匹配模式、构建每事件的 payload、调用共享库的 `runHook` + `mergeHookOutputs`,再将中性结果映射为 seam Decision。各包的 README 维护着当前不支持的事件和部分字段的完整清单,以官方协议为参照。 @@ -27,7 +27,7 @@ harness 的扩展面是其类型化的拦截 seam(见[拦截 seam Agent Note]( | `agent/prompt-submit` | `deny`→`block`;仅上下文→delegate+fold | `block`→`block`;仅上下文→delegate+fold | | `tools/pre-execute` | `deny`→`deny`;`ask`→`ask` | `block`→`deny`(无 allow/ask) | | `tools/post-execute` | `deny`→`block`+feedback;仅上下文→delegate+fold | 同上 | -| `agent/turn-continuation` | 阻塞的 Stop → `continue`(reason = 下一步 steering(中途引导)) | 同上 | +| `agent/stopping` | 阻塞的 Stop → 下一步 steering(中途引导) | 同上 | | `subagent/start`(emit) | additionalContext → 注入到存活的进程内 subagent;远程 subagent 无本地注入目标 | 本桥接不支持 | | `subagent/end`(emit) | 仅观察 | 本桥接不支持 | @@ -35,7 +35,9 @@ CC 桥接的 `ask` 结果是一条真正的权限路径,而非终态桥接决 ### 上下文来源始终是插件(误标签防护) -`agent.inject()` 在缺少 `MessageSource` 时默认为 `{ kind: 'user' }`,因此每个桥接的 `inject()` 和 `HookContext` 都传入 `{ kind: 'plugin', plugin: 'hooks-claude' | 'hooks-codex' }`。单元测试覆盖率固定验证结果中的 `context/message.source` 为插件而非用户。 +每个桥接的 `inject()` 和 additional-context 输入都显式传入 `{ kind: 'plugin', plugin: 'hooks-claude' | 'hooks-codex' }`。单元测试覆盖率固定验证结果中的 `user/message.source` 为插件而非用户。 + +`UserPromptSubmit` 在准入阶段运行,早于任何轮次开启。因此它不写入任何轮次范围的 `hook/invoked` / `hook/result` 对:阻止不会留下 transcript(文本记录),而被允许的额外上下文由其带来源的 `user/message` 持久呈现。Codex payload 仍会收到候选的下一个 `turn_id`;拒绝不会消耗该编号。 ### 添加上下文不是否决——先 delegate,再 prepend @@ -57,13 +59,13 @@ Claude Code 始终导出 `CLAUDE_PROJECT_DIR`,常见的未修改钩子引用 ` - **工具输入重写。** CC/Codex 的 `updatedInput` 被记录日志并发出警告,但不予执行——输入重写是一个推迟的一致性设计问题(见 [pre-tool-input-rewrite Agent Note](../../proposed/feature/2026-06-30-pre-tool-input-rewrite.md)),因为 pre-execution 参数被 `tool/call` 审计、`assistant/message` 历史和 ACP/tool-bash 展示共同读取,诚实的重写是一个设计单元,而非一个字段。 - **Stop 循环防护**(`TODO(stop-loop-guard)`)。Claude Code 提供 `stop_hook_active` 并在连续八次阻塞后覆盖钩子;Codex 提供 `stop_hook_active` 但未记录等效上限。两个桥接始终报告 `false`,因此一个无条件阻塞的 Stop 钩子会在每一步强制继续——在状态追踪落地之前,钩子作者必须自行限制。 -- **钩子 `continue:false`(硬停止)。** 钩子可以请求终止整个运行(CC/Codex `continue:false`);共享合并将其折叠为 `MergedHookOutcome.stop`/`stopReason`,但没有桥接对其采取行动(`TODO(hook-continue-false)`)——拦截 seam 尚无「硬停止 agent」原语(Decision 阻塞/引导的是单个点,而非整个运行)。与循环防护工作一同推迟;停止请求记录在 `hook/result` 日志中,钩子在此期间保留其逐点效果(决策/上下文)。 +- **钩子 `continue:false`(硬停止)。** 钩子可以请求终止整个运行(CC/Codex `continue:false`);共享合并将其折叠为 `MergedHookOutcome.stop`/`stopReason`,但没有桥接对其采取行动(`TODO(hook-continue-false)`)——拦截 seam 尚无「硬停止 agent」原语(Decision 阻塞/引导的是单个点,而非整个运行)。与循环防护工作一同推迟;轮中请求会将停止请求记录在 `hook/result` 中,钩子在此期间保留其逐点效果(决策/上下文)。 - **配置发现。** 路径在 `cordis.yml` 中显式指定且为进程级(见上文);完整的多层 CC/Codex 优先级遍历、按会话的项目本地发现以及信任/hash 模型未被重新实现(`TODO(per-session-hook-config)`)。 - **Session-start / subagent-start 上下文为尽力而为(`TODO(session-start-gating)`)。** 两个钩子以 detached 方式运行于启动过程之外,因此其上下文在就绪时注入,但可能错过首个请求或短命的 subagent。要保证首请求送达,需要一个 awaited 的启动 seam。 ## 曾考虑的替代方案 -**每点钩子并发执行。** 参考引擎对一个点匹配到的钩子并发运行并折叠结果。本桥接**串行**运行(匹配循环内每个钩子 `await`),并以相同的最严格合并策略折叠。串行是刻意的:它使每个钩子的 `hook/invoked`/`hook/result` 对在会话日志中相邻且顺序确定,而折叠对决策是顺序无关的(`deny > ask > allow`),因此结果一致。代价是延迟(钩子 *N* 等待钩子 *N−1*)以及每钩子超时不重叠——对真实配置中的钩子数量可以接受;如果某配置的扇出大到影响总耗时,再重新评估。 +**每点钩子并发执行。** 参考引擎对一个点匹配到的钩子并发运行并折叠结果。本桥接**串行**运行(匹配循环内每个钩子 `await`),并以相同的最严格合并策略折叠。串行是刻意的:对轮次范围的拦截点,它使每个钩子的 `hook/invoked`/`hook/result` 对相邻且顺序确定,而折叠对决策是顺序无关的(`deny > ask > allow`),因此结果一致。代价是延迟(钩子 *N* 等待钩子 *N−1*)以及每钩子超时不重叠——对真实配置中的钩子数量可以接受;如果某配置的扇出大到影响总耗时,再重新评估。 ## 后果 diff --git a/.agents/notes/implemented/feature/2026-06-30-interception-seams.i18n.yaml b/.agents/notes/implemented/feature/2026-06-30-interception-seams.i18n.yaml index 639a586e7c..8fc176cd9a 100644 --- a/.agents/notes/implemented/feature/2026-06-30-interception-seams.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-06-30-interception-seams.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 -2026-06-30-interception-seams.md: 8af489d3f575dd457e1981e433330f08cefa2043 -2026-06-30-interception-seams.zh.md: 3886ed21504abfe14a2ccb344d7aa0d3f8d25064 +2026-06-30-interception-seams.md: fb0532741239058e7bcdf9e42a5030431b418f96 +2026-06-30-interception-seams.zh.md: 7a87f4cb7130e677ab3b376e5d08a1a8ab567c6f diff --git a/.agents/notes/implemented/feature/2026-06-30-interception-seams.zh.md b/.agents/notes/implemented/feature/2026-06-30-interception-seams.zh.md index 3886ed2150..7a87f4cb71 100644 --- a/.agents/notes/implemented/feature/2026-06-30-interception-seams.zh.md +++ b/.agents/notes/implemented/feature/2026-06-30-interception-seams.zh.md @@ -16,9 +16,9 @@ harness 需要一套钩子子系统:用户像 Claude Code(CC)和 Codex 那 **Agent 事件**(`dsh-agent`): - `agent/session-start(agent, source)` ——emit,在第 1 轮次之前触发一次,携带 `SessionStartSource`(`startup` 表示全新/fork 创建,`resume` 表示重新加载的持久化会话;`clear`/`compact` 保留)。纯通知,不能阻塞启动(这是有意的空白:桥接可以记录/注入,但不管控启动)。监听器通过 `agent.inject()` 注入上下文。 -- `agent/prompt-submit(agent, content, source, signal, next) → PromptDecision` ——waterfall,在轮次唯一取得所有权的排队消息追加为 `user/message` 之前触发。显式轮次 signal 位于最后的 `next` 之前;`allow` 可以重写提示词 `content` 或附加来源各自独立的 `additionalContexts[]`,而 `block` 会追加一条持久的 `prompt/blocked`,并拒绝这个零步骤轮次。 +- `agent/prompt-submit(agent, content, source, signal, next) → PromptDecision` ——waterfall,针对一条取得所有权的排队消息触发,早于循环开启轮次或追加 `user/message`。显式准入 signal 位于最后的 `next` 之前;`allow` 可以重写提示词 `content` 或附加来源各自独立的 `additionalContexts[]`,而 `block` 会丢弃该候选消息,不产生会话历史。 -**`agent/turn-continuation`** 接收并返回一个 `ContinuationDecision`。`{action:'continue', reason?}` 可携带面向模型的内容和来源,记录为同一轮次内的下一步 steering(中途引导)——与 `/goal` step-end-steer 模式互为类型化孪生。它不是 `context/message`,因此其类型不提供持久上下文元数据。 +**`agent/stopping`** 是自然停止边界上的一次 awaited 通知。需要再执行一步的监听器调用 `agent.steer()`,传入来源显式的面向模型的内容(steering,中途引导);循环随后重新读取 outbox,继续执行或关闭轮次。 ### 工具流水线为每个阶段赋予一种权限 @@ -33,15 +33,13 @@ harness 需要一套钩子子系统:用户像 Claude Code(CC)和 Codex 那 核心调度与工具体位于规范化边界内部,因此工具、监听器、无效规范值、渲染器/投影器、非 JSON 呈现和身份形状错误均解析为 JSON 安全的 `isError` 结果,而非逃逸出轮次。post-execute 监听器因此可以检查一个抛出异常的工具;由定义拥有的最终内容不变式也会覆盖外层流水线与候选结果实体化失败;最终观测者会同时看到执行期间的规范值,以及会话日志能够持久化的确切呈现字段。[规范工具输出契约](../architecture/2026-07-20-canonical-tool-output-contract.md)定义值/投影与持久性规则。 -**`TurnEndReason.rejected`**(`dsh-session`):取得所有权的提示词被 `prompt-submit` 阻止的零步骤轮次。 - ### 三个承重的循环决策 -1. **在提示词策略之前开启轮次。** 被阻止的提示词成为零步骤的 `rejected` 轮次,保持封闭性并为 ACP(Agent Client Protocol)提供持久的终结事件。否决记录 `prompt/blocked`(含原始提示词和原因),而每个允许的 `additionalContexts` 条目都注入到已开启的轮次中。依照[一次 send 对应一个轮次的简化](../simplification/2026-07-17-one-send-one-turn.md),每个取得所有权的 ordinary-send 条目都是其轮次中的唯一消息;启动前丢弃不会创建轮次。 +1. **在开启轮次之前运行提示词策略。** 被阻止的提示词不会创建轮次,也不产生持久事件。允许时,循环先暂存重写后的提示词,再暂存每个返回的 `additionalContexts` 条目,然后开启轮次并在第一个步骤之前排空该 outbox。依照[一次 send 对应一个轮次的简化](../simplification/2026-07-17-one-send-one-turn.md),每个取得所有权的 ordinary-send 条目都是其轮次中唯一的直接提示词。 -2. **工具执行后的 `additionalContexts` 与异步注入进入活跃批次 FIFO,并在该批次结算时追加。** `content`/`feedback` 塑造 `execute()` 返回的结果,但每项上下文都是独立的 `context/message`,而单个步骤或组合工具可以产生许多上下文。立即追加上下文会产生 `result(c1) → context → result(c2)` 的交错,或把嵌套上下文放在外层结果之前,破坏工具调用/结果邻接性。因此 `ToolRunContext.deferContext()` 会在失败路径上也收集嵌套调度上下文,`execute()` 在 `ToolExecutionResult` 上暴露有序数组,循环再把它接纳到与执行期间 `agent.inject()` 调用相同的 FIFO 中。FIFO 在批次结算时,于每个已记录结果之后追加,其中也包括被中断轮次关闭之前。被接受的外层调用将 deferred contexts 保留在 decision contexts 之前;被外层阻止时则丢弃 deferred contexts,只暴露阻止 decision 显式提供的上下文。 +2. **工具执行后的 `additionalContexts` 与异步注入进入活跃批次 FIFO,并在该批次结算时追加。** `content`/`feedback` 塑造 `execute()` 返回的结果,但每项上下文都是一条独立的带来源 `user/message`,而单个步骤或组合工具可以产生许多上下文。立即追加上下文会产生 `result(c1) → context → result(c2)` 的交错,或把嵌套上下文放在外层结果之前,破坏工具调用/结果邻接性。因此 `ToolRunContext.deferContext()` 会在失败路径上也收集嵌套调度上下文,`execute()` 在 `ToolExecutionResult` 上暴露有序数组,循环再把它接纳到与执行期间 `agent.inject()` 调用相同的 FIFO 中。FIFO 在批次结算时,于每个已记录结果之后追加,其中也包括被中断轮次关闭之前。被接受的外层调用将 deferred contexts 保留在 decision contexts 之前;被外层阻止时则丢弃 deferred contexts,只暴露阻止 decision 显式提供的上下文。 -3. **强制 `continue` 的 `reason` 通过 steering 通道入队**,使得下一步骤在循环顶部排空时将其记录为当前轮次的 steering——同一轮次内的下一*步骤* steering,而非下一*轮次*的提示词(与现有的 `hasSteering` 强制继续覆盖一致)。 +3. **stopping 监听器通过 steering 通道请求继续执行**,使得下一步骤在循环顶部排空时将其记录为当前轮次的 steering——同一轮次内的下一*步骤* steering,而非下一*轮次*的提示词。 ### 工具执行前输入重写是一个独立的一致性决策 @@ -49,7 +47,7 @@ harness 需要一套钩子子系统:用户像 Claude Code(CC)和 Codex 那 ### 边界 -seam 包**不**声明 `hook/*` 会话事件(持久的钩子调用日志);那些属于 `dsh-hook-protocol`,因为原生插件使用类型化 decision 而无需外部钩子日志。原生插件集成测试(`packages/core/agent-loop/tests/interception.spec.ts`)通过真实循环组合这些 seam,不涉及 `hook/*` 协议。压缩(compaction)(`PreCompact`/`PostCompact`)、Notification 和 Codex `PermissionRequest` 不在本决策范围内。[审批 seam](2026-07-06-approval-seam.md) 通过 `ctx.approval` 解析 `ask` decision,而终结性的单调停止由 `agent/turn-stop` 独立负责。 +seam 包**不**声明 `hook/*` 会话事件(持久的钩子调用日志);那些属于 `dsh-hook-protocol`,因为原生插件使用类型化 decision 而无需外部钩子日志。原生插件集成测试(`packages/core/agent-loop/tests/interception.spec.ts`)通过真实循环组合这些 seam,不涉及 `hook/*` 协议。压缩(compaction)(`PreCompact`/`PostCompact`)、Notification 和 Codex `PermissionRequest` 不在本决策范围内。[审批 seam](2026-07-06-approval-seam.md) 通过 `ctx.approval` 解析 `ask` decision;终结性的单调停止由工具结果数据表达,而 `agent/stopping` 是引导再执行一步的最后机会。 ## 曾考虑的替代方案 @@ -58,4 +56,4 @@ seam 包**不**声明 `hook/*` 会话事件(持久的钩子调用日志); ## 后果 -规范拦截表面具有统一的类型化,同时不给每个扩展相同的权力:钩子返回 decision,执行包装层做包装,终结 guard 只能拒绝,最终观测者只能观测。循环负责 session-start、prompt-submit、工具执行后上下文缓冲和 continuation;`dsh-tools` 负责身份封存与五阶段执行流水线。它们的契约记录在 [architecture.md](../../../../docs/architecture.md)、各包 README、[核心拦截 decision](../../../../docs/core-data-structures/core.md#interception-decisions) 与[工具结构](../../../../docs/core-data-structures/tools.md)中。ACP 桥接将 `rejected` 轮次映射为其 `cancelled` 编解码值,而钩子驱动的快照端到端验证可观测的桥接行为。 +规范拦截表面具有统一的类型化,同时不给每个扩展相同的权力:钩子返回 decision,执行包装层做包装,终结 guard 只能拒绝,最终观测者只能观测。循环负责 session-start、轮次前的提示词准入、工具执行后上下文缓冲和 stopping;`dsh-tools` 负责身份封存与五阶段执行流水线。它们的契约记录在 [architecture.md](../../../../docs/architecture.md)、各包 README、[核心拦截 decision](../../../../docs/core-data-structures/core.md#interception-decisions) 与[工具结构](../../../../docs/core-data-structures/tools.md)中。ACP 桥接在 agent 空闲且不再拥有轮次后,将准入拒绝结算为 `cancelled`,而钩子驱动的快照端到端验证可观测的桥接行为。 diff --git a/.agents/notes/implemented/feature/2026-07-06-sandbox.i18n.yaml b/.agents/notes/implemented/feature/2026-07-06-sandbox.i18n.yaml index 287deaff20..7cb853744e 100644 --- a/.agents/notes/implemented/feature/2026-07-06-sandbox.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-07-06-sandbox.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 -2026-07-06-sandbox.md: c1307a7201ed1bc331a86d4ffee002d69fd1d5e5 -2026-07-06-sandbox.zh.md: 4e3d4951f71a602bc78551c90dda04317d0f8284 +2026-07-06-sandbox.md: a63779d1848b5a77bfceeaea51f5103084b9fce3 +2026-07-06-sandbox.zh.md: 2511278b1424f01c8a54f8a9a9b1874888bb43b3 diff --git a/.agents/notes/implemented/feature/2026-07-06-sandbox.zh.md b/.agents/notes/implemented/feature/2026-07-06-sandbox.zh.md index 4e3d4951f7..2511278b14 100644 --- a/.agents/notes/implemented/feature/2026-07-06-sandbox.zh.md +++ b/.agents/notes/implemented/feature/2026-07-06-sandbox.zh.md @@ -165,7 +165,7 @@ fs/web/todo 在进程内执行,因此它们的沙箱语义是各自 seam 层 - 恢复的会话的覆盖生效并报告给编辑器,无需特殊处理;进程停止期间变更的默认值在会话的首个新请求前被叙述,归因于运维人员。 - 两个并发会话永远看不到彼此的状态、通知或配置选项。 - 同一个 Cordis 上下文中的两个并发项目会话解析各自独立的工作区根目录;bash 和 fs 写入在调用方会话的 cwd 内成功,对其相邻会话的 cwd 则失败。 -- `agent-loop` 未被触及——一切搭载 `systemPrompt.section`、`SessionEventMap` 合并、`agent.inject()`、`agent/pre-step`、`agent/prompt-submit` 和 ACP handler 表面。 +- `agent-loop` 未被触及——一切搭载 `systemPrompt.section`、`SessionEventMap` 合并、`agent.inject()`、`agent/step`、`agent/prompt-submit` 和 ACP handler 表面。 代价与已接受的限制: @@ -192,7 +192,7 @@ fs/web/todo 在进程内执行,因此它们的沙箱语义是各自 seam 层 - **沙箱限制网络或进程可见性吗?** 不——`SandboxMode` 仅声称文件操作;bwrap profile 刻意不 unshare pid,没有后端声称网络。网络限制是否成为自己的旋钮留在 § seam 中开放。 - **哪些工具实际在约束下运行?** 通过 `ctx.bash` 的 OS 子进程——bash 工具及传递性的钩子命令——再加上通过沙箱化 `ctx.fs` 提供方运行的文件系统工具(`read`/`write`/`edit`,见[跨工具族 fs 沙箱 Agent Note](2026-07-14-cross-family-fs-sandbox.md)):bash 通过 OS runner 约束,fs 通过进程内路径围栏约束,二者都以同一个 `ctx.sandboxPolicy` 模式为键。web/todo 仍在进程内且不受限制(web 的唯一效果是网络,不在文件效果模式词汇内)。 - **授权的升级会持久化吗?** 不会。授权由发起请求的确切前台或后台调用消费;每个相邻调用保留自己的有效模式。后续的后台拒绝通过 `task_output` 呈现,并且可以作为一次新的精确命令重试的依据。 -- **编辑器的模式切换何时生效?** 轮中:立即追加,由下一次调用的盖章兑现。空闲:保持在 bridge 的会话记录上,在下一次 `agent/prompt-submit` 时锚定到其开放轮次中,N 次切换合并为最多一个事件(净零则无);锚定前崩溃回退它,`session/load` 报告真实状态。模型不被告知——其下一个命令直接在新模式下运行。 +- **编辑器的模式切换何时生效?** 轮中:立即追加,由下一次调用的盖章兑现。空闲:保持在 bridge 的会话记录上,在下一次 `agent/step` 时锚定到其开放轮次中,N 次切换合并为最多一个事件(净零则无);锚定前崩溃回退它,`session/load` 报告真实状态。模型不被告知——其下一个命令直接在新模式下运行。 - **重启后什么存活——如果运维人员在进程停止期间改了配置默认值呢?** 覆盖从会话日志回放(`effective = fold ?? config`),因此恢复的会话以零追赶机制保持其模式;离线漂移的默认值以与切换相同的方式改变行为(批准策略因被声明,还额外以运维人员/配置归因叙述)。 - **结果上的 `enforcement: 'partial'` 是什么意思?** 所选后端强制其内核 ABI 管控的子集——例如 ABI v3 之前的 Landlock 不管控路径 truncate——并以结构化方式如此声明而非拒绝主机;探测的报告行区分各种情况。bwrap 和 Seatbelt profile 构造上管控所有承诺的文件操作,因此始终报告 `full`。 diff --git a/.agents/notes/implemented/feature/2026-07-07-session-prefix.i18n.yaml b/.agents/notes/implemented/feature/2026-07-07-session-prefix.i18n.yaml index 63ac02b35e..7c81df63b3 100644 --- a/.agents/notes/implemented/feature/2026-07-07-session-prefix.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-07-07-session-prefix.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 -2026-07-07-session-prefix.md: 322413f541706244a8a9a9113c0b79693fe54ccd -2026-07-07-session-prefix.zh.md: 710cfbd2656d132640d39b1d62374ef2d16be612 +2026-07-07-session-prefix.md: 6671a7e84c885ff066adbd55b0a2e0d5ddffe49a +2026-07-07-session-prefix.zh.md: 4efbf200dfa71222b276b9d933748c8f0eb01607 diff --git a/.agents/notes/implemented/feature/2026-07-07-session-prefix.zh.md b/.agents/notes/implemented/feature/2026-07-07-session-prefix.zh.md index 710cfbd265..4efbf200df 100644 --- a/.agents/notes/implemented/feature/2026-07-07-session-prefix.zh.md +++ b/.agents/notes/implemented/feature/2026-07-07-session-prefix.zh.md @@ -2,6 +2,8 @@ Status: implemented +下文所述的仅请求前缀 seam 后来已被[统一带来源消息的决策](../architecture/2026-07-22-unified-send-and-coalesced-user-messages.md)移除。当前的生产方在 `agent/step` 时注入持久的带来源 `user/message` 上下文;本记录保留了早先的设计及其权衡。 + [English](2026-07-07-session-prefix.md) | 中文 ## 问题 @@ -12,7 +14,7 @@ Status: implemented ## 决策 -`agent/session-prefix` 是 agent 事件映射上的一个 waterfall(瀑布式事件)([`packages/core/agent/src/types.ts`](../../../../packages/core/agent/src/types.ts)):监听器接收一个冻结的空种子并返回扩展(规范的贡献方式是前置插入 `[mine, ...await next()]`,在协议格式上产生注册顺序)。agent loop(智能体循环)([`packages/core/agent-loop/src/loop.ts`](../../../../packages/core/agent-loop/src/loop.ts))在每个循环实例中触发一次,惰性地在实例首次 `agent/pre-step` 之前执行;组合后的列表被深拷贝、深冻结、缓存在实例上,并在该实例发出的每个请求中置于整个派生历史之前——紧接在提供方的 system 槽位之后([协议格式顺序](../../../../docs/core-data-structures/core.md#the-request-envelope-llmcallconfig-and-the-logged-header))。 +`agent/session-prefix` 是 agent 事件映射上的一个 waterfall(瀑布式事件)([`packages/core/agent/src/types.ts`](../../../../packages/core/agent/src/types.ts)):监听器接收一个冻结的空种子并返回扩展(规范的贡献方式是前置插入 `[mine, ...await next()]`,在协议格式上产生注册顺序)。agent loop(智能体循环)([agent-loop 源码](../../../../packages/core/agent-loop/src/))在每个循环实例中触发一次,惰性地在实例首次 `agent/pre-step` 之前执行;组合后的列表被深拷贝、深冻结、缓存在实例上,并在该实例发出的每个请求中置于整个派生历史之前——紧接在提供方的 system 槽位之后([协议格式顺序](../../../../docs/core-data-structures/core.md#the-request-envelope-llmcallconfig-and-the-logged-header))。 三个属性承载了这一设计: diff --git a/.agents/notes/implemented/simplification/2026-06-20-drop-unconsumed-llm-assembled-surfaces.i18n.yaml b/.agents/notes/implemented/simplification/2026-06-20-drop-unconsumed-llm-assembled-surfaces.i18n.yaml index ad842ae732..cf51518edd 100644 --- a/.agents/notes/implemented/simplification/2026-06-20-drop-unconsumed-llm-assembled-surfaces.i18n.yaml +++ b/.agents/notes/implemented/simplification/2026-06-20-drop-unconsumed-llm-assembled-surfaces.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 -2026-06-20-drop-unconsumed-llm-assembled-surfaces.md: b6b596e822b4bd6fd1bd891c336c622ad675ad45 -2026-06-20-drop-unconsumed-llm-assembled-surfaces.zh.md: bafc5d3bc630d89c776bbcf53719b29223e1c90d +2026-06-20-drop-unconsumed-llm-assembled-surfaces.md: 40fa71a7bcf00d8933165ee8d4594112fdb8c0a8 +2026-06-20-drop-unconsumed-llm-assembled-surfaces.zh.md: 00b3b907eed9cbbb37eac028f32ca5cf3f796ac5 diff --git a/.agents/notes/implemented/simplification/2026-06-20-drop-unconsumed-llm-assembled-surfaces.zh.md b/.agents/notes/implemented/simplification/2026-06-20-drop-unconsumed-llm-assembled-surfaces.zh.md index bafc5d3bc6..00b3b907ee 100644 --- a/.agents/notes/implemented/simplification/2026-06-20-drop-unconsumed-llm-assembled-surfaces.zh.md +++ b/.agents/notes/implemented/simplification/2026-06-20-drop-unconsumed-llm-assembled-surfaces.zh.md @@ -12,7 +12,7 @@ Status: implemented - `streamBlocks()`:一个「便捷视图」,将分片送入 `BlockAssembler` 并按流顺序产出已组装的 `ContentBlock`([index.ts:137-144](../../../../packages/llm/llm/src/index.ts))。 - `generate()`:一个完整组装的 `GenerateResult`,通过第二条 `llm/generate` waterfall 分发([index.ts:151-157](../../../../packages/llm/llm/src/index.ts))。 -LLM(大语言模型)服务唯一的生产消费方是 agent loop(智能体循环),它只使用 `stream()`:将原始分片送入自己的 `BlockAssembler`,以便在并行组装的同时记录分片,保证回放保真度([packages/core/agent-loop/src/loop.ts](../../../../packages/core/agent-loop/src/loop.ts),`ctx.llm.stream(req)` 步骤)。在 `packages/*/src` 和 `examples/*/src` 中 grep `streamBlocks` 与 `ctx.llm.generate`,找不到任何生产调用方。仅有的引用来自服务方法定义、文档和测试;适配器测试用 `generate()` 作为便捷驱动,但它们完全可以通过同一个 assembler 辅助函数手动消费 `stream()`,无需为此保留一个公开的生产 API。 +LLM(大语言模型)服务唯一的生产消费方是 agent loop(智能体循环),它只使用 `stream()`:将原始分片送入自己的 `BlockAssembler`,以便在并行组装的同时记录分片,保证回放保真度([packages/core/agent-loop/src/agent.ts](../../../../packages/core/agent-loop/src/agent.ts),`ctx.llm.stream(req)` 步骤)。在 `packages/*/src` 和 `examples/*/src` 中 grep `streamBlocks` 与 `ctx.llm.generate`,找不到任何生产调用方。仅有的引用来自服务方法定义、文档和测试;适配器测试用 `generate()` 作为便捷驱动,但它们完全可以通过同一个 assembler 辅助函数手动消费 `stream()`,无需为此保留一个公开的生产 API。 这属于[删除可变会话 summary](2026-06-19-drop-mutable-session-summary.md) 的同类模式:带有受测契约的组装视图 API,由测试而非生产代码消费。它们是为不关心 token 级增量的消费方推测性构建的,但唯一的真实消费方恰恰关心增量,以便持久化高保真重放数据。 diff --git a/.agents/notes/implemented/simplification/2026-07-02-remove-stream-chunk-mirror.i18n.yaml b/.agents/notes/implemented/simplification/2026-07-02-remove-stream-chunk-mirror.i18n.yaml index b6b4adcc16..2926d785eb 100644 --- a/.agents/notes/implemented/simplification/2026-07-02-remove-stream-chunk-mirror.i18n.yaml +++ b/.agents/notes/implemented/simplification/2026-07-02-remove-stream-chunk-mirror.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 -2026-07-02-remove-stream-chunk-mirror.md: 5dd816940a4b2c2b63980e01f1bd4e0aac53a3e2 -2026-07-02-remove-stream-chunk-mirror.zh.md: ca65a3c2ad46d14835416c14d0087ef542de03bb +2026-07-02-remove-stream-chunk-mirror.md: 62421bfd6032d3be6e942c00abefe17ec947c986 +2026-07-02-remove-stream-chunk-mirror.zh.md: 6e006a2c1930e47a651813252d3fd2c4471e6e9e diff --git a/.agents/notes/implemented/simplification/2026-07-02-remove-stream-chunk-mirror.zh.md b/.agents/notes/implemented/simplification/2026-07-02-remove-stream-chunk-mirror.zh.md index ca65a3c2ad..6e006a2c19 100644 --- a/.agents/notes/implemented/simplification/2026-07-02-remove-stream-chunk-mirror.zh.md +++ b/.agents/notes/implemented/simplification/2026-07-02-remove-stream-chunk-mirror.zh.md @@ -6,7 +6,7 @@ Status: implemented ## 问题 -agent loop(智能体循环)将模型的每个 token delta 同时记录为持久的 `assistant/chunk` 会话事件,并发射一个携带相同数据的并行实时 `agent/stream-chunk` Cordis 事件。在 `packages/core/agent-loop/src/loop.ts` 中,二者仅相隔一行: +agent loop(智能体循环)将模型的每个 token delta 同时记录为持久的 `assistant/chunk` 会话事件,并发射一个携带相同数据的并行实时 `agent/stream-chunk` Cordis 事件。在 `packages/core/agent-loop/src/agent.ts` 中,二者仅相隔一行: ```ts ignore-check const chunkEvent = session.append('assistant/chunk', { turn, step, chunk }) diff --git a/.agents/notes/implemented/simplification/2026-07-04-prune-producerless-vocabulary-variants.i18n.yaml b/.agents/notes/implemented/simplification/2026-07-04-prune-producerless-vocabulary-variants.i18n.yaml index c343b6ff92..115c11bb23 100644 --- a/.agents/notes/implemented/simplification/2026-07-04-prune-producerless-vocabulary-variants.i18n.yaml +++ b/.agents/notes/implemented/simplification/2026-07-04-prune-producerless-vocabulary-variants.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 -2026-07-04-prune-producerless-vocabulary-variants.md: 34492e6906cd2d795f880310b1bcd120e3953fcf -2026-07-04-prune-producerless-vocabulary-variants.zh.md: a68a8b04fedefed8a2ab92f08baf5e8b3ea90222 +2026-07-04-prune-producerless-vocabulary-variants.md: aa8c0500e79b91443e8b224c586a07644068799b +2026-07-04-prune-producerless-vocabulary-variants.zh.md: 0ef2b68d7f6812c5f9ae380e6086a442d336c6cb diff --git a/.agents/notes/implemented/simplification/2026-07-04-prune-producerless-vocabulary-variants.zh.md b/.agents/notes/implemented/simplification/2026-07-04-prune-producerless-vocabulary-variants.zh.md index a68a8b04fe..0ef2b68d7f 100644 --- a/.agents/notes/implemented/simplification/2026-07-04-prune-producerless-vocabulary-variants.zh.md +++ b/.agents/notes/implemented/simplification/2026-07-04-prune-producerless-vocabulary-variants.zh.md @@ -30,4 +30,4 @@ Status: implemented ## 后果 -操作行为没有变化——原本就没有内容能够构造这些值。镜像事件移除([边界镜像 Agent Note](2026-06-20-remove-agent-boundary-mirror-events.md)、[流分片 Agent Note](2026-07-02-remove-stream-chunk-mirror.md))只触及瞬态 `agent/*` 事件,从不触及持久词汇,因此不存在冲突。其他位置已经遵守准入策略:`rejected`、`prompt/blocked` 和 `hook/invoked`/`hook/result` 都有实时生产者——本 Agent Note 将同一门槛扩展到缺少生产者的三个变体。图像块自身的 `cache?` 字段归属[删除图像 Agent Note](2026-07-04-drop-image-content-block.md),后者将其与该块一同移除;本 Agent Note 覆盖剩余块类型上的两个字段。 +操作行为没有变化——原本就没有内容能够构造这些值。镜像事件移除([边界镜像 Agent Note](2026-06-20-remove-agent-boundary-mirror-events.md)、[流分片 Agent Note](2026-07-02-remove-stream-chunk-mirror.md))只触及瞬态 `agent/*` 事件,从不触及持久词汇,因此不存在冲突。后来的轮次前准入清理将 `rejected` 和 `prompt/blocked` 连同其生产者一并移除;轮中的 `hook/invoked`/`hook/result` 仍然体现同一条以生产者为准的准入规则。图像块自身的 `cache?` 字段归属[删除图像 Agent Note](2026-07-04-drop-image-content-block.md),后者将其与该块一同移除;本 Agent Note 覆盖剩余块类型上的两个字段。 diff --git a/.agents/notes/implemented/simplification/2026-07-04-remove-agent-steering-mirror.i18n.yaml b/.agents/notes/implemented/simplification/2026-07-04-remove-agent-steering-mirror.i18n.yaml index 8b6bb07da2..21e7cf9217 100644 --- a/.agents/notes/implemented/simplification/2026-07-04-remove-agent-steering-mirror.i18n.yaml +++ b/.agents/notes/implemented/simplification/2026-07-04-remove-agent-steering-mirror.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 -2026-07-04-remove-agent-steering-mirror.md: 9f7cd5abe968ff216cbd7012163ea1c04dc00599 -2026-07-04-remove-agent-steering-mirror.zh.md: 63f575347d989f288b3129e0a53e5690b85bb4e8 +2026-07-04-remove-agent-steering-mirror.md: 6d78217a4939c4a87325cd120638042acbd68dc1 +2026-07-04-remove-agent-steering-mirror.zh.md: 6aabb71903eaeb7204df2d5880a52acabc6d612a diff --git a/.agents/notes/implemented/simplification/2026-07-04-remove-agent-steering-mirror.zh.md b/.agents/notes/implemented/simplification/2026-07-04-remove-agent-steering-mirror.zh.md index 63f575347d..6aabb71903 100644 --- a/.agents/notes/implemented/simplification/2026-07-04-remove-agent-steering-mirror.zh.md +++ b/.agents/notes/implemented/simplification/2026-07-04-remove-agent-steering-mirror.zh.md @@ -6,7 +6,7 @@ Status: implemented ## 问题 -`agent/steering` 是最后一个仍存在的、对持久会话事件的瞬态镜像。agent loop(智能体循环)的 steering(中途引导)drain 逻辑先追加持久事件 `steering/message { turn, content, source }`,紧接着下一行就 emit `agent/steering(agent, turn, content, source)`——同一个事实以 fire-and-forget 事件的形式重复发出(`packages/core/agent-loop/src/loop.ts`,`drainSteering`)。它在生产环境中没有任何监听者:唯一的订阅方是一个 agent loop 回归测试,断言 emit 携带了 `source`——而这同一个事实已经由上一行的持久事件记录。 +`agent/steering` 是最后一个仍存在的、对持久会话事件的瞬态镜像。agent loop(智能体循环)的 steering(中途引导)drain 逻辑先追加持久事件 `steering/message { turn, content, source }`,紧接着下一行就 emit `agent/steering(agent, turn, content, source)`——同一个事实以 fire-and-forget 事件的形式重复发出(`packages/core/agent-loop/src/agent.ts`,`drainOutbox`)。它在生产环境中没有任何监听者:唯一的订阅方是一个 agent loop 回归测试,断言 emit 携带了 `source`——而这同一个事实已经由上一行的持久事件记录。 `agent/steering` 以相同的 payload 重复了紧接其前的持久事件 `steering/message`。`agent/queued` 仍保留为纯瞬态信号,因为它在持久化之前触发,覆盖了可能在进入日志前被取消的工作。 @@ -14,7 +14,7 @@ Steering 承载真实生产流量——钩子 bridge 的轮次延续决策通过 ## 决策 -`agent/steering` 已从 agent 事件分类中移除:包括 `packages/core/agent/src/types.ts` 中的声明(以及其中实时事件 JSDoc 列表对它的提及)、`drainSteering` 中的 emit(当时已无用的 `ctx` 参数也随之移除)、`packages/core/agent/README.md` 中的表格行,以及循环伪代码块(`packages/core/agent-loop/src/loop.ts` 模块文档和 [architecture.md](../../../../docs/architecture.md))中的 emit 行;Cordis 目录重新生成后不再包含它。唯一的回归测试改为在持久 `steering/message` 事件上固定来源保留行为——所固定的事实存在于日志上。 +`agent/steering` 已从 agent 事件分类中移除:包括 `packages/core/agent/src/types.ts` 中的声明(以及其中实时事件 JSDoc 列表对它的提及)、`drainOutbox` 中的 emit、`packages/core/agent/README.md` 中的表格行,以及循环伪代码块(`packages/core/agent-loop/src/agent.ts` 模块文档和 [architecture.md](../../../../docs/architecture.md))中的 emit 行;Cordis 目录重新生成后不再包含它。唯一的回归测试改为在持久 `steering/message` 事件上固定来源保留行为——所固定的事实存在于日志上。 三份已实现 Agent Note(agent 决策记录)曾说明保留该事件;按照 [implemented/AGENTS.md](../AGENTS.md),每份记录都已修改并指向本文作为移除记录:包括[边界 Agent Note](2026-06-20-remove-agent-boundary-mirror-events.md) 的保留列表条目、[流分片 Agent Note](2026-07-02-remove-stream-chunk-mirror.md) 的范围条款,以及[事件域语义 Agent Note](../architecture/2026-06-30-event-domain-semantics.md) 的瞬态 emit 枚举。 diff --git a/docs/cookbook/extension-cookbook.i18n.yaml b/docs/cookbook/extension-cookbook.i18n.yaml index a6d2ca2e38..87959a5f79 100644 --- a/docs/cookbook/extension-cookbook.i18n.yaml +++ b/docs/cookbook/extension-cookbook.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 -extension-cookbook.md: c13b46e06a3b34512cd371e6a4868a6e932a575f -extension-cookbook.zh.md: ef099ff318488ba26a3ba4fe736c5f320bdce4f3 +extension-cookbook.md: 7c5daaa33f888d7a94e962eaf9c9477fa2dcc5b8 +extension-cookbook.zh.md: 2e887df77fc875964e33d90102a920bdba04c0bb diff --git a/docs/core-data-structures/compaction.i18n.yaml b/docs/core-data-structures/compaction.i18n.yaml index 3f192f0194..58d6d23e6c 100644 --- a/docs/core-data-structures/compaction.i18n.yaml +++ b/docs/core-data-structures/compaction.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 -compaction.md: 71bbe7d9c17c6a3d35684a6c87d3072ab4f88df1 -compaction.zh.md: 35e9c9ef0050f01c5249d1502bb2782511acc819 +compaction.md: 0f2b6a8678b992170a29666fe3ac6e10b1d6ae8e +compaction.zh.md: 8fb4b9d1bb25ac7b2ca7fa00f69422d45e8bda3b diff --git a/docs/core-data-structures/compaction.zh.md b/docs/core-data-structures/compaction.zh.md index 35e9c9ef00..8fb4b9d1bb 100644 --- a/docs/core-data-structures/compaction.zh.md +++ b/docs/core-data-structures/compaction.zh.md @@ -62,7 +62,7 @@ type CompactionTrigger = 'pressure' | 'context-overflow' `CompactService` 暴露 `compactIfNeeded(agent, trigger, signal)` 以执行自动 `pressure` 或 `context-overflow` 策略;没有可安全执行的工作时返回 `null`。它还针对显式、两端均包含的 surface 范围暴露 `compactRegion(...)`。每个后端都使用包导出的 `COMPACT_CHECKPOINT_SOURCE` 标记其替换用的 `user/message`;消费方调用 `isCompactCheckpointSource()`,而不是把检查点识别逻辑耦合到某一个后端。实现必须把传入的 signal 转发给摘要流程。该 seam 不拥有计价 API:单例 [`ctx.tokenMeter`](token-meter.md) 直接拥有估算与回放,而 `dsh-compact-basic` 拥有保留策略、事件排序、按路由执行的摘要调用及其配置。 -压力压缩在串行 `agent/post-step` 中运行:此时成功的 assistant 输出、工具结果、缓冲上下文和 steering(中途引导)已持久化,但 `step/end` 尚未发生。一旦压力或规范化溢出满足条件,compact-basic 会在选择范围前调用可选的 [`ctx.toolResultPrune`](../../packages/compact/compact-tool-result-prune/README.md),再通过 `ctx.tokenMeter` 重新测量,并且可以在不生成摘要的情况下推进 surface。失败请求的恢复在失败的步骤关闭后通过 `agent/request-error` 运行;仅当 surface replacement generation 前进时才批准一个带新编号的步骤重试,即便后续摘要工作在剪枝后抛异常亦如此;取消仍然优先。区域边界保持工具调用/结果配对,但不保持整个轮次,因此一个过大轮次中较早关闭的步骤可以被压缩。`dsh-compact-basic` 拥有阈值、保留尾部策略、溢出上限与失败处理。 +压力压缩在串行 `agent/step` 中运行,先于请求推导。一旦压力或规范化溢出满足条件,compact-basic 会在选择范围前调用可选的 [`ctx.toolResultPrune`](../../packages/compact/compact-tool-result-prune/README.md),再通过 `ctx.tokenMeter` 重新测量,并且可以在不生成摘要的情况下推进 surface。失败请求的恢复在失败的步骤关闭后通过 `agent/request-error` 运行;仅当 surface replacement generation 前进时才调用 `agent.retry()`,即便后续摘要工作在剪枝后抛异常亦如此;取消仍然优先。区域边界保持工具调用/结果配对,但不保持整个轮次,因此一个过大轮次中较早关闭的步骤可以被压缩。`dsh-compact-basic` 拥有阈值、保留尾部策略、溢出上限与失败处理。 该 seam 导出 `toolPairingBalancedBefore(session, seq)` 与 `toolPairingBalancedAfter(session, seq)`,用于这些边缘检查。两者都会验证当前 surface 成员关系,并拒绝缺失的 seq 与遗留结果;其缓存语义由[包契约](../../packages/compact/compact/README.md#tool-pairing-boundaries)规定。 diff --git a/docs/core-data-structures/core.i18n.yaml b/docs/core-data-structures/core.i18n.yaml index 47310dd09b..c2f5475259 100644 --- a/docs/core-data-structures/core.i18n.yaml +++ b/docs/core-data-structures/core.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 -core.md: 781267cccdb5bbda33e5be6a9e807fdbe47dbc83 -core.zh.md: d0f67983b98b0cf679a8e599a5f8ab3c64490dd0 +core.md: e6e289315be286f8651ca7e948f9efa08c2919aa +core.zh.md: 3f904e4b2d9f4bbe98dc8a7a48674b3e12e0f3b3 diff --git a/docs/core-data-structures/core.zh.md b/docs/core-data-structures/core.zh.md index d0f67983b9..3f904e4b2d 100644 --- a/docs/core-data-structures/core.zh.md +++ b/docs/core-data-structures/core.zh.md @@ -224,8 +224,7 @@ interface GenerateOptions { /** * Ordered conversation messages, exactly as the provider sees them (after * the `system` slot). A loop-built request assembles them as - * `EpochHeader.messagePrefix` + the derived history (dsh-agent-loop); a - * hand-built one-shot passes any list. + * the derived history (dsh-agent-loop); a hand-built one-shot passes any list. */ messages: Message[] /** System prompt text (adapters map to the provider's system slot). */ @@ -295,11 +294,11 @@ interface ToolSchema { ### 请求信封:`LlmCallConfig` 与记录的 header -循环从已记录状态构建每个请求。`EpochHeader` 通过完整的 `request/header` 快照记录调用配置、渲染后的提示词、权威返回工具顺序(由 `toolOrder` 配置;未配置时按字典序)以及会话前缀。结合派生历史,请求便可由会话日志重建。见 [session.md](session.md#the-request-header-event-requestheader) 与[可重建性 Agent Note(agent 决策记录)](../../.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.md)。 +循环从已记录状态构建每个请求。`EpochHeader` 通过完整的 `request/header` 快照记录调用配置、渲染后的提示词以及权威返回工具顺序(由 `toolOrder` 配置;未配置时按字典序)。结合派生历史,请求便可由会话日志重建。见 [session.md](session.md#the-request-header-event-requestheader) 与[可重建性 Agent Note(agent 决策记录)](../../.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.md)。 -`agent/request` 接收冻结的调用配置种子,并可返回替代值以切换提供方、模型或采样参数。`agent/session-prefix` 为每个循环实例组合一次仅用于请求的 prefix 消息,header 记录实际使用的确切结果。到达 `llm/stream` 的请求会被深度冻结,因此变更会抛异常;请求还携带进程本地循环标识,使观察者不会把单独记录的冻结辅助调用误认成对话请求。 +`agent/request` 接收冻结的调用配置种子,并可返回替代值以切换提供方、模型或采样参数。到达 `llm/stream` 的请求会被深度冻结,因此变更会抛异常;请求还携带进程本地循环标识,使观察者不会把单独记录的冻结辅助调用误认成对话请求。 -在协议格式上,循环构建的请求按此顺序读取:`system` 槽位(渲染后的提示词组装)→ `messagePrefix`(冻结的会话前缀)→ 派生历史——边界快照,其尾部在轮次首步是最新的 `user/message`,在后续步骤是上一步的工具结果。前缀从不进入派生历史;它的持久记录是 header 事件,开发不变式针对每个循环构建的请求精确重算此等式。 +在协议格式上,循环构建的请求先读取 `system` 槽位(渲染后的提示词组装),再读取派生历史——边界快照,其尾部在轮次首步是最新的 `user/message`,在后续步骤是上一步的工具结果。开发不变式针对每个循环构建的请求精确重算此等式。 FIXME(call-config-shape):重新审视此类型的精确定义——出于缓存目的,哪些字段确实属于 epoch 层级(`model` 肯定属于;采样标量目前出于谨慎放在这里),以及适配器需要时,提供方特有的额外项(推理选项、额外 body 参数)应归属何处。 @@ -361,7 +360,7 @@ type SessionEvent = { }[T] ``` -十三种事件变体(`turn/start`、`turn/end`、`step/start`、`step/end`、`user/message`、`prompt/blocked`、`assistant/chunk`、`assistant/message`、`tool/call`、`tool/result`、`steering/message`、`todo/write`、`request/header`)、`deriveMessages()` 投影规则、`TurnTrigger`/`TurnEndReason` 原因以及轮次封闭不变量都在 **[session.md](session.md)** 中。日志如何持久化——`SessionPersistence` seam、JSONL/SQLite 后端、`session/flush` 检查点、崩溃恢复与 `SessionHeader`——则在 **[persistence.md](persistence.md)** 中。 +十二种事件变体(`turn/start`、`turn/end`、`step/start`、`step/end`、`user/message`、`assistant/chunk`、`assistant/message`、`tool/call`、`tool/result`、`steering/message`、`todo/write`、`request/header`)、`deriveMessages()` 投影规则、`TurnTrigger`/`TurnEndReason` 原因以及轮次封闭不变量都在 **[session.md](session.md)** 中。日志如何持久化——`SessionPersistence` seam、JSONL/SQLite 后端、`session/flush` 检查点、崩溃恢复与 `SessionHeader`——则在 **[persistence.md](persistence.md)** 中。 @@ -373,59 +372,45 @@ type SessionEvent = { ```ts type-equiv /** - * Options for {@link Agent.followup}, {@link Agent.queue}, and {@link Agent.steer}. - * An omitted source attests direct human input as `{ kind: 'user' }` and may - * authorize policy consumers, so non-human producers must label their content. + * Which inbox queue a {@link Agent.send} item joins: + * - `next-turn` — the item becomes its own turn, claimed at a turn boundary. + * - `next-step` — the item joins the active turn between steps as steering, + * or, when no turn is active, is promoted per its `wakeup` flag. + */ +type SendTarget = 'next-turn' | 'next-step' +``` + +```ts type-equiv +/** + * Options for the unified {@link Agent.send} primitive over the + * (`target` × `wakeup`) matrix. Named presets: {@link Agent.followup} + * (`next-turn`/wakeup), {@link Agent.steer} (`next-step`/wakeup), and + * {@link Agent.inject} (`next-step`/no-wakeup). + * + * The object is complete so routing policy is explicit. */ interface SendOptions { - source?: MessageSource + /** Queue the item joins. */ + target: SendTarget /** - * Model-facing contexts captured with this inbox item. A queued prompt exposes - * them through the default `agent/prompt-submit` allow decision, while steering - * records them directly at its next checkpoint. + * Whether this item makes the model run: wake a parked driver (`next-turn`) + * or force a continuation step (`next-step` while running). A `false` + * `next-turn` item queues without waking; a `false` + * `next-step` item attaches durable context without forcing another step + * (the injection preset). */ - contexts?: HookContext[] - /** Opaque JSON state retained on the durable message but hidden from the model. */ - meta?: JsonValue + wakeup: boolean } ``` -```ts type-equiv -/** Options specific to durable synthetic context injection. */ -interface InjectOptions { - /** Defaults to `{ kind: 'plugin', plugin: '' }`; non-human producers should identify themselves. */ - source?: MessageSource - /** Opaque JSON state retained on the durable message but hidden from the model. */ - meta?: JsonValue -} -``` +固定预设的别名方法自带 `target` 与 `wakeup`;其 `UserMessageData` 输入同时携带内容与 provenance。 -高级接收形式会显式给出所有默认值,并禁止为注入附加上下文: +`send` 返回被接收消息的不透明 `AgentMessageId`,该 id 在这条消息的各个 `agent/inbox/*` 事件中保持稳定: ```ts type-equiv /** - * Fully specified input for {@link Agent.send}. Unlike the intent-named - * helpers, this form applies no defaults: callers provide content, source, - * contexts, metadata (including explicit `undefined`), target, and wakeup. - * The union excludes attached contexts from non-waking next-step injection. - */ -type ResolvedAgentInput = { - content: ContentBlock[] - source: MessageSource - meta: JsonValue | undefined -} & ( - | { target: 'next-turn'; wakeup: boolean; contexts: HookContext[] } - | { target: 'next-step'; wakeup: true; contexts: HookContext[] } - | { target: 'next-step'; wakeup: false; contexts: [] } -) -``` - -FIFO 投递方法返回不透明的 `AgentMessageId`,该 id 在同一条消息的各个 `agent/inbox/*` 事件中保持稳定。注入也返回 id,但会绕过这些事件: - -```ts type-equiv -/** - * Opaque id assigned to one accepted agent input. FIFO inputs carry the same id - * on their `agent/inbox/*` events; injection bypasses those events. + * Opaque id assigned to one accepted {@link Agent.send} message; returned by + * `send` and carried on its `agent/inbox/*` events for correlation. */ type AgentMessageId = Branded<'AgentMessageId'> ``` @@ -434,26 +419,14 @@ type AgentMessageId = Branded<'AgentMessageId'> ```ts type-equiv /** - * One accepted FIFO message, carried by the `agent/inbox/*` live events. `id` - * is the value returned by the accepting helper or {@link Agent.send}, - * stable across this message's enqueue, dequeue, and discard events. Source - * defaults, when applicable, are already applied, so these are the exact values - * the item was accepted with. - * `steering` is true for an item drained between steps; otherwise it is claimed - * at a turn boundary. `SendOptions.meta` is intentionally omitted: it is durable - * model-hidden state that lands on the eventual `user/message`/ - * `steering/message`, not live-event routing data. + * One accepted {@link Agent.send} message, carried by the `agent/inbox/*` live + * events. `id` is the value `send` returned to the caller, stable across this + * message's enqueue, dequeue, and discard events. Its content and source are + * the exact input values accepted by the agent. */ -interface AgentMessage { - /** The id returned by the accepting helper or {@link Agent.send}. */ +interface AgentMessage extends UserMessageData { + /** The id `send` returned for this message. */ id: AgentMessageId - content: ContentBlock[] - source: MessageSource - contexts: HookContext[] - /** Whether the item joined the steering FIFO rather than the queued FIFO. */ - steering: boolean - /** Whether the item wakes the driver or requests another step. */ - wakeup: boolean } ``` @@ -476,10 +449,10 @@ type AgentCancelCause = | { readonly kind: 'parent' } ``` -结构化 `Agent` 接口公开四个按意图命名的辅助方法,以及接受完全解析输入的方法。具体驱动器只需实现一次这套路由矩阵,每个辅助方法提供其固定路由与默认值。 +`Agent` 是覆盖公开活跃 agent 契约的接口。具体驱动器拥有 `followup`/`steer`/`inject` 别名方法,并将它们经由 `send` 的(`target` × `wakeup`)矩阵路由。 ```ts type-equiv -/** Public agent handle; its concrete implementation is internal to `@deepseek-ai/dsh-agent-loop`. */ +/** Public live-agent handle with aliases over the unified delivery primitive. */ interface Agent { /** The single identity shared with {@link session}. */ readonly id: SessionId @@ -493,84 +466,81 @@ interface Agent { readonly ctx: Context /** - * Queue an ordinary message as its own FIFO-ordered turn and wake the driver. - * Content, resolved source, and attached contexts are detached, validated, - * and frozen together; invalid input throws synchronously before notification - * or enqueue. - * @param content - the prompt content blocks. - * @param options - source, attached contexts, and durable model-hidden meta. + * The unified delivery primitive over the (`target` × `wakeup`) matrix. + * It routes the caller's typed content and source as follows: + * + * - `next-turn` queues an item that becomes the sole ordinary message of its + * own FIFO-ordered turn; `wakeup:true` wakes a + * parked driver, while `wakeup:false` queues without waking. + * - `next-step` with `wakeup:true` submits steering into the active turn + * (idle falls back to a woken `next-turn`). + * - `next-step` with `wakeup:false` injects durable model-facing context + * without running the model: an open turn stages it for the next safe log + * position, while an idle injection appends it immediately without opening + * a turn. + * @param input - model-facing content and its producer provenance. + * @param options - target queue and wakeup decision. * @returns the accepted message's {@link AgentMessageId}, stable across its `agent/inbox/*` events. */ - followup(content: ContentBlock[], options?: SendOptions): AgentMessageId - - /** - * Queue an ordinary message without waking an idle driver. The item retains - * FIFO order and is claimed only after another input wakes the driver. A lone - * queued item leaves `whenIdle()` resolved. - * @param content - the prompt content blocks. - * @param options - source, attached contexts, and durable model-hidden meta. - * @returns the accepted message's {@link AgentMessageId}, stable across its `agent/inbox/*` events. - */ - queue(content: ContentBlock[], options?: SendOptions): AgentMessageId - - /** - * Submit steering into the running turn and request another step. An open turn - * records it at the next steering checkpoint before a request or continuation - * decision; policy may stop before another step. After turn close and its - * checkpoint, any remainder is queued for a later turn; terminal - * `agent/turn-stop`, cancellation, or disposal may discard it. Idle steering - * becomes a waking ordinary turn. - * @param content - the steering content blocks. - * @param options - source, attached contexts, and durable model-hidden meta. - * @returns the accepted message's {@link AgentMessageId}, stable across its `agent/inbox/*` events. - */ - steer(content: ContentBlock[], options?: SendOptions): AgentMessageId - - /** - * Append detached model-facing context without running the model. An open-turn - * injection joins at the current log position unless the current tool batch is - * executing; then it waits FIFO until that batch settles and drains before - * turn close even when interrupted. Idle injection uses a one-shot turn and - * durability checkpoint. Disposal awaits idle checkpoints; flush failures - * report through `agent/error`. An omitted source defaults to - * `{ kind: 'plugin', plugin: '' }`. - * @param content - the injected context content blocks. - * @param options - source and durable model-hidden meta. - * @returns the accepted injection's {@link AgentMessageId}; injection emits no `agent/inbox/*` events. - */ - inject(content: ContentBlock[], options?: InjectOptions): AgentMessageId - - /** - * Accept one fully specified input through the same snapshot and routing path - * as the four intent-named helpers. `next-turn` targets the ordinary FIFO; - * `next-step`/wakeup targets steering (falling back to an ordinary waking turn - * while idle); and `next-step` without wakeup injects durable context without - * running the model. Every field is mandatory and no source or routing default - * is applied. Invalid input throws synchronously before notification, enqueue, - * or append. - * @param input - the resolved content, attribution, context, metadata, and routing facts. - * @returns the accepted input's {@link AgentMessageId}, carried by FIFO lifecycle events when applicable. - */ - send(input: ResolvedAgentInput): AgentMessageId + send(input: UserMessageData, options: SendOptions): AgentMessageId /** * Clear queued and steering work — unless `keepInbox` — and abort the active * turn. An effective call first emits `agent/cancel-requested` with the * resolved typed cause. The first cause wins for the active turn, and - * `whenIdle()` resolves after cancellation reaches quiescence. Omitted cause - * means `{ kind: 'user' }`. Idle cancellation is a no-op and does not arm - * later work. The active turn snapshots and freezes the cause. + * `whenIdle()` resolves after cancellation reaches quiescence. Idle + * cancellation is a no-op and does not arm later work. * @param cause - the stable caller intent carried by the current turn signal. * @param options - cancellation options; `keepInbox` preserves pending work. */ - cancel(cause?: AgentCancelCause, options?: CancelOptions): void + cancel(cause: AgentCancelCause, options?: CancelOptions): void /** Resolve at idle quiescence; disposal waits for driver exit rather than only the status transition. */ whenIdle(): Promise + + /** + * Queue an ordinary follow-up turn and wake the driver — the + * `next-turn`/wakeup preset of {@link send}. The item becomes the sole + * ordinary message of its own turn. + * @param input - prompt content and its producer provenance. + * @returns the accepted message's {@link AgentMessageId}. + */ + followup(input: UserMessageData): AgentMessageId + + /** + * Submit steering into the running turn — the `next-step`/wakeup preset of + * {@link send}. An open turn records it at the next steering checkpoint before + * a request or stop decision. If the turn fails before that boundary, the + * remainder stays staged without waking the agent; retry or a later prompt + * takes it. Idle steering falls back to a woken follow-up turn, while + * cancellation or disposal may discard pending steering. + * @param input - steering content and its producer provenance. + * @returns the accepted message's {@link AgentMessageId}. + */ + steer(input: UserMessageData): AgentMessageId + + /** + * Append model-facing context without running the model — the + * `next-step`/no-wakeup preset of {@link send}. An open-turn injection stages + * at the next safe log position; an idle injection appends immediately + * without opening a turn. + * @param input - injected context and its producer provenance. + * @returns the accepted message's {@link AgentMessageId}. + */ + inject(input: UserMessageData): AgentMessageId + + /** + * Re-open a turn on the current session log without a new prompt — the + * explicit resummon verb. During `agent/request-error`, this schedules one + * retry turn after the failed turn closes; while idle, it starts one + * immediately. Repeated calls before the scheduled retry coalesce. + * @throws while other agent work is running. + */ + retry(): void } ``` -`AgentStatus` 为 `'idle' | 'running' | 'disposed'`,`SessionId` 是品牌类型。`running` 描述整个驱动器的排空区间,可能跨越轮次关闭、其持久化检查点以及连续的排队轮次;它不能证明某个轮次仍然打开。`AgentOptions` 可合并扩展:core 声明 `provider?` 与 `model?`(在 `agent/request` 后,分发要求两者都存在)。Persona 归 `dsh-system-prompt` 所有:agent 作用域的 `deployment:persona` 可以遮蔽全局默认值。 +`AgentStatus` 为 `'idle' | 'running'`,`SessionId` 是品牌类型。dispose(资源释放)会把 agent 从注册表移除并发出 `agent/disposed`;它不是一个终态 status 值。`running` 描述整个驱动器的排空区间,可能跨越连续的排队轮次;它不能证明某个轮次仍然打开。`AgentOptions` 可合并扩展:core 声明 `provider?` 与 `model?`(在 `agent/request` 后,分发要求两者都存在)。Persona 归 `dsh-system-prompt` 所有:agent 作用域的 `deployment:persona` 可以遮蔽全局默认值。 cause 是由 TypeScript 强制约束的同进程输入。活跃的 `TurnCancellation` 持有者会把其判别字段复制到仅运行时的 `AbortSignal.reason`,并在发布 `turn/end` 前退役;冻结后的 `AbortSignal.reason` 仍可读取。`agentInterruptReasonOf(signal)` 无需查询环境中的 initiator 状态,即可识别 `user`、`parent` 与仅用于生命周期的 `disposed`。持久 `turn/end` 保留粗粒度 `{ kind: 'aborted' }` 结果;若需记录请求 provenance,应使用单独的持久事件,而不是让终态结果承担额外含义。 @@ -582,78 +552,32 @@ cause 是由 TypeScript 强制约束的同进程输入。活跃的 `TurnCancella ## 拦截决策 -每个 `agent/*` 拦截 waterfall 都返回一个小型、特定于 seam 的类型化联合——统一的 Decision 惯用形状([tools.md](tools.md) 中工具 seam 的 `PreToolDecision`/`PostToolDecision` 也采用相同形状)。CC/Codex 钩子桥接层把其 `permissionDecision`/`decision`/`continue`/`additionalContext` 字段映射到这些联合上;原生插件则直接返回它们。提示词决策与工具后决策共享一种面向模型的上下文形状 `HookContext`,它必须携带 `source`(缺少 source 会默认成 `{kind:'user'}`,从而把插件上下文错标为用户提示词)。其中的 `content` 作为 user-role 输入逐字到达模型,而 JSON `meta` 持久保存插件状态但不向模型暴露。未指定放置方式或指定为 `separate` 时,上下文会成为一条注入的 `user/message`(来源类别为插件或 goal);`prompt-prefix` 放置方式可用于提示词和 steering 收件箱附件,会在同一条消息中把上下文置于最终生效的请求之前。两种决策都携带 `additionalContexts[]`,使每一项保留各自的 provenance、元数据与放置方式。Continuation reason 则是 steering 消息,并有意使用更窄的 content/source 形状。 +提示词决策与工具后决策使用与持久 user-role 输入相同的 `UserMessageData` content/source 形状。每个 `additionalContexts` 条目都会成为一条独立的 `user/message`,保留各自的 provenance。钩子桥接层把其原生决策字段映射到这些类型化结果上。 源码:[`packages/core/agent/src/types.ts`](../../packages/core/agent/src/types.ts) -```ts type-equiv -/** Model-facing context injected by a listener or atomically attached to one inbox message. */ -interface HookContext { - content: ContentBlock[] - source: MessageSource - /** - * Model placement. Absent or `separate` records an independent injected - * `user/message`; `prompt-prefix` prepends this context and a stable - * request delimiter to the same user-role message as its attached prompt. - */ - placement?: 'separate' | 'prompt-prefix' - /** Opaque JSON state retained in the session event but hidden from the model. */ - meta?: JsonValue -} -``` - -`agent/prompt-submit` 返回 `PromptDecision`(允许该轮次已领取的排队消息——可选地改写其 `content` 或附加 `additionalContexts`——或者记录 `prompt/blocked` 并以 `rejected` 结束这个零步骤轮次): +`agent/prompt-submit` 在轮次打开前返回 `PromptDecision`。allow 可以改写已领取的提示词或附加 `additionalContexts`;block 拒绝准入且不产生任何轮次事件: ```ts type-equiv /** - * Prompt interception result. `allow.content` replaces the prompt. Each - * `additionalContexts` entry follows its declared placement: separate context - * message by default, or a prefix inside the prompt's user-role message. - * `block` records a durable `prompt/blocked` and ends the claimed prompt's - * zero-step turn as rejected. An `allow` returned by a listener is - * authoritative: a listener wrapping `next()` preserves downstream `content` - * and `additionalContexts` unless it intentionally replaces them. + * Prompt interception result. `allow.content` replaces the prompt, while + * `additionalContexts` appends model-facing context before the turn starts. + * An `allow` returned by a listener is authoritative: a listener wrapping + * `next()` preserves both fields unless it intentionally replaces them. */ type PromptDecision = - | { kind: 'allow'; content?: ContentBlock[]; additionalContexts?: HookContext[] } + | { kind: 'allow'; content?: ContentBlock[]; additionalContexts?: UserMessageData[] } | { kind: 'block'; reason: string } ``` -`agent/turn-continuation` 返回 `ContinuationDecision`(步骤有工具调用或注入了 steering 时,循环默认为 `continue`,否则为 `stop`;`continue` 的 `reason` 会记录为同一轮次中下一个步骤的 steering,因此不携带上下文元数据——即类型化 `/goal` 模式): - -```ts type-equiv -/** Turn continuation override; a continue reason is recorded as next-step steering in the same turn. */ -type ContinuationDecision = - | { action: 'stop' } - | { action: 'continue'; reason?: { content: ContentBlock[]; source: MessageSource } } -``` - -`agent/request-error` 接收确切的原始 `RequestError`、其不可变 `LlmFailure`、在连续序列中已批准另一次请求的不可变失败列表、轮次信号以及 `next()`。恢复插件按 `failure.code` 路由,而不是按活跃错误的消息路由;每项策略只统计自身的 code,一次成功请求会清空历史: +`agent/request-error` 在失败的模型步骤关闭之后、其轮次关闭之前运行。listener 可以在失败轮次的 signal 仍然存活时修复持久状态或 await 策略工作。处理该错误的 listener 调用 `agent.retry()` 并直接返回而不调用 `next()`;重复调用会合并成一个重试轮次。 ```ts type-equiv /** Model-request failure with an optional machine-routable provider code. */ type RequestError = Error & { code?: string } ``` -它返回 `RequestErrorDecision`;`retry` 在恢复 listener 的持久变更之后打开一个带新编号的步骤,而 `fail` 在 `turn/end` 上保留结构化失败: - -```ts type-equiv -/** Failed-request recovery decision; `retry` opens another numbered step while listeners delegate by calling `next()`. */ -type RequestErrorDecision = { action: 'fail' } | { action: 'retry' } -``` - -`agent/post-step` 会在 assistant 输出、真实或合成的工具结果、缓冲上下文与 steering 持久化之后、`step/end` 之前被 await。被取消的工具批次在排空后携带 aborted signal 到达这里;其签名为 `(agent, turn, step, signal)`,可回放事实保留在会话日志中,而不是瞬态 payload 中。 - -`agent/turn-stop` 返回仅停止的 `ContinuationStop` 子集或 `undefined`。循环在折叠普通决策、其 reason 和待处理 steering 之后调用此串行检查点;stop 是终态,会丢弃待处理的 steering。 - -```ts type-equiv -/** - * The terminal subset of {@link ContinuationDecision}. A listener on - * `agent/turn-stop` returns this to make the already-composed continuation - * outcome terminal; `undefined` abstains. - */ -type ContinuationStop = Extract -``` +`agent/step` 是请求推导前唯一的串行边界。`agent/stopping` 在轮次没有工具或 steering(中途引导)后续时运行,先于最后一次 steering 排空。 `agent/session-start` 携带 `SessionStartSource`(会话生命周期为何开始;桥接层据此匹配其 SessionStart): @@ -662,8 +586,6 @@ type ContinuationStop = Extract type SessionStartSource = 'startup' | 'resume' | 'clear' | 'compact' ``` -`agent/session-prefix` 在每个循环实例中组合一次 `Message[]`。深度冻结的结果被记录在请求 header 中,并前置于每次派生历史,使其成为会话稳定开场白的归属。恢复的实例会重新组合;会话中途的变更使用仅追加的上下文通道。该 waterfall 直接返回内容,因为它是贡献而非决策。 - ## `ToolDefinition` 唯一属于核心的流水线编写类型:每个已注册工具*是什么*——一个面向模型的 `ToolSchema` 加上一个 `execute` 函数,以及可选的最终内容回调与 UI 回调。工具作者很少手动构造它(`defineTool` DSL 会用类型化参数构建),但它是注册表持有、循环分发所经过的契约。 diff --git a/docs/core-data-structures/llm-streaming.i18n.yaml b/docs/core-data-structures/llm-streaming.i18n.yaml index 28191bd56c..8ac6fe6f82 100644 --- a/docs/core-data-structures/llm-streaming.i18n.yaml +++ b/docs/core-data-structures/llm-streaming.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 -llm-streaming.md: cb99c935aea2dc9cc769e3056fdb98a2e5c9eacb -llm-streaming.zh.md: 740fa1f796088e63d0195cfbecf975adb236381c +llm-streaming.md: a3bc31240b621f40a3ab85d030b82cc6723535c7 +llm-streaming.zh.md: e51aababa701a32d8cba4cfe9ec816dccb9fdb3f diff --git a/docs/core-data-structures/llm-streaming.zh.md b/docs/core-data-structures/llm-streaming.zh.md index 740fa1f796..e51aababa7 100644 --- a/docs/core-data-structures/llm-streaming.zh.md +++ b/docs/core-data-structures/llm-streaming.zh.md @@ -59,12 +59,12 @@ interface LlmFailure { - **`usage` 在 `finish` 之前,`finish` 之后不再有任何分片。** 将两者都推迟到提供方的流结束标记,这样尾部的 usage-only 分片就不会违反顺序。 - **工具调用的 `arguments` 全程保持原始 JSON 字符串。** 部分片段通过 `argumentsDelta` 流式传输;如果提供方返回的是已解析的对象,适配器在 `block-end` 时重新序列化为字符串。 -- **两条受支持的错误路径,一种事实形状。** 失败可以从 `stream()` 抛出(传输/协议错误),**或者**以 `finish {kind:'error'|'aborted', failure}` 结束流(无法在流中途抛异常的适配器用它表示提供方带内错误)。`LlmError.failure` 携带同一个 `LlmFailure`。最终适配器边界保留被抛出的确切 `Error` 对象,并将不可变事实关联到该调用;agent loop(智能体循环)关闭失败的步骤,再把错误、事实与不可变的先前已重试事实提供给 `agent/request-error`。若未恢复,结构化失败会成为轮次错误,并且该次尝试不会提交正常 assistant 消息或工具副作用。 +- **两条受支持的错误路径,一种事实形状。** 失败可以从 `stream()` 抛出(传输/协议错误),**或者**以 `finish {kind:'error'|'aborted', failure}` 结束流(无法在流中途抛异常的适配器用它表示提供方带内错误)。`LlmError.failure` 携带同一个 `LlmFailure`。最终适配器边界保留被抛出的确切 `Error` 对象,并将不可变事实关联到该调用;agent loop(智能体循环)关闭失败的步骤,再把错误与事实提供给 `agent/request-error`。处理该错误的 listener 在其 await 的修复完成后调用 `agent.retry()`;若未恢复,结构化失败会成为轮次错误,并且该次尝试不会提交正常 assistant 消息或工具副作用。 - **一次适配器调用就是一次提供方尝试。** 适配器禁用库重试。agent 层恢复会打开另一个持久、带编号的步骤;直接调用 `ctx.llm.stream()` 的调用方仍然只尝试一次。 - **提供方停顿在传输层受到时限约束。** 两个已交付的远程适配器都暴露正数且有限的 `streamIdleTimeoutMs`,默认五分钟。watchdog 只在 iterator `next()` 尚未完成时启动,整个请求使用同一个稳定 signal,把自身到期映射为 `TIMEOUT`,并把更早发生的调用方中止保留为 `ABORTED`。 - **上下文溢出只有一个规范 code。** 两个 DeepSeek 适配器都通过 `isContextWindowExceededError()` 对提供方的显式细节分类并暴露 `CONTEXT_WINDOW_EXCEEDED`,无论失败以抛出的 HTTP `LlmError` 还是带内 finish error 到达。消费方按 code 路由,绝不依赖提供方文本。 - **每个提供方 HTTP 请求都携带应用归属头。** 适配器发送 `attributionHeaders()`(见下文)作为 `User-Agent` 基线,并通过协议级测试加以证明(mock 服务器断言收到的 header,或对基于库的适配器使用库的 header 钩子)。 -- **回放状态归适配器所有。** 成功的 `finish` 可以携带重建提供方原生响应所需的无损 JSON 状态。除非 `agent/step-result` listener 改写了内容,否则循环会将其与组装后的 assistant 消息一起存储。后续请求中,仅当历史提供方与目标提供方当前注册到完全相同的适配器实例时,`LlmService` 才会传递该状态。该适配器负责校验状态并拥有所有跨模型或跨提供方转换;其他适配器只会收到提供方无关的内容与 provenance,不会收到私有状态。 +- **回放状态归适配器所有。** 成功的 `finish` 可以携带重建提供方原生响应所需的无损 JSON 状态。循环会将其与组装后的 assistant 消息一起存储。后续请求中,仅当历史提供方与目标提供方当前注册到完全相同的适配器实例时,`LlmService` 才会传递该状态。该适配器负责校验状态并拥有所有跨模型或跨提供方转换;其他适配器只会收到提供方无关的内容与 provenance,不会收到私有状态。 该契约由两个有意保持独立的实现锁定:`dsh-llm-deepseek`(手写 fetch/SSE(Server-Sent Events))和 `dsh-llm-pi-ai`(通过 `@earendil-works/pi-ai` 实现的通用多提供方适配器)。基于库的适配器覆盖 finish 分片错误路径,而传输边界测试证明每个空闲 watchdog 都会停止其实际请求。 diff --git a/docs/core-data-structures/session.i18n.yaml b/docs/core-data-structures/session.i18n.yaml index f215956acf..56cc4f5140 100644 --- a/docs/core-data-structures/session.i18n.yaml +++ b/docs/core-data-structures/session.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 -session.md: 7a9ae919fecef7db19f3ca67feb128bcba1db4f0 -session.zh.md: 9e1e9a4f39ed6919416ff5cebf345b43bbc450ea +session.md: b46206a84103fa262b2b62b0e18654b9eb7e7cb0 +session.zh.md: d1d89dd160c1ddf0176adb833994c50c4ff10f6a diff --git a/docs/core-data-structures/session.zh.md b/docs/core-data-structures/session.zh.md index 9e1e9a4f39..d1d89dd160 100644 --- a/docs/core-data-structures/session.zh.md +++ b/docs/core-data-structures/session.zh.md @@ -12,28 +12,17 @@ ```ts type-equiv /** - * Shared payload for user, injected-context, and steering prompt messages. A + * Shared payload for user, injected-context, and steering messages. A * direct human prompt, a synthetic `agent.inject()` context, and mid-turn * steering all project into the model transcript as verbatim user-role content; * they are told apart by `source` (a non-`user` kind marks injected context), - * not by event type. `meta` carries durable model-hidden producer state. + * not by event type. */ -interface PromptMessageData { - /** Exact model-facing blocks, including any baked prompt-prefix contexts. */ +interface UserMessageData { + /** Exact model-facing blocks. */ content: ContentBlock[] - /** Producer provenance for the direct prompt. */ + /** Producer provenance. */ source: MessageSource - /** Present only when prompt-prefix contexts were baked into `content`. */ - envelope?: PromptMessageEnvelope - /** - * Opaque durable JSON state retained on the event but hidden from the model - * projection. It is the intended channel for a future framing directive (a - * producer declares the frame, a dedicated renderer applies it — see the - * deferred note in - * ../../../../.agents/notes/implemented/simplification/2026-07-20-unwrap-injected-content-envelopes.md), - * so the surface keeps projecting `content` verbatim rather than wrapping it. - */ - meta?: JsonValue } ``` @@ -46,10 +35,7 @@ interface PromptMessageData { */ interface SessionEventMap { /** - * Opens turn `turn`. `trigger` records what started it — one claimed queued - * message or an idle-time injection. The turn is the durability/replay - * boundary: every event sits between a `turn/start` and its matching - * `turn/end` (the turn-enclosure invariant). + * Opens turn `turn`. `trigger` records what started the model loop. */ 'turn/start': { turn: number; trigger: TurnTrigger } /** @@ -68,16 +54,10 @@ interface SessionEventMap { * (the queued message claimed for this turn), a synthetic `agent.inject()` * context (file-change notices, subdir AGENTS.md, skill content, cron * notifications, …), or an admitted goal continuation round. All three - * project their `content` verbatim; `source` (with a non-`user` kind marking - * injected context) is the only channel that tells them apart. An idle - * injection wraps this event in a one-shot turn so the log stays turn-enclosed. + * project their `content` verbatim; `source` tells them apart. An idle + * injection may append this event between turns without running the model. */ - 'user/message': PromptMessageData - /** - * Durable record of a prompt veto and its reason. It is log-only: the blocked - * prompt never enters the model-visible surface, and its turn runs zero steps. - */ - 'prompt/blocked': { content: ContentBlock[]; source: MessageSource; reason: string } + 'user/message': UserMessageData /** Raw stream chunk — token-level replay fidelity. */ 'assistant/chunk': { turn: number; step: number; chunk: StreamChunk } /** @@ -114,7 +94,7 @@ interface SessionEventMap { meta?: JsonValue } /** Steering content injected between steps of a running turn. */ - 'steering/message': PromptMessageData & { turn: number } + 'steering/message': UserMessageData & { turn: number } /** Whole-list snapshot; latest write wins on replay. Log-only UI state; never derived history. */ 'todo/write': { todos: TodoItem[] } /** @@ -125,7 +105,7 @@ interface SessionEventMap { } ``` -`PromptMessageData.content` 始终是确切的模型可见内容。当附加上下文声明 `prompt-prefix` 放置方式时,AgentLoop 会依次把它的块、一个 `## My request:` 分隔符以及最终生效的直接提示词拼接进该数组。可选且对模型隐藏的 `envelope` 会保留 `displayContent`,以及按顺序排列的前缀上下文来源/元数据描述信息,使 transcript(文本记录)、标题与重新引用消费方无需改变可重建历史,就能呈现人类提示词。`displayPromptContent()` 负责该选择,并为普通事件和较早的事件回退到 `content`。 +`UserMessageData` 是普通提示词、注入上下文与 steering(中途引导)共享的持久 `content` + `source` 基础形状。实时收件箱事件在同一形状上扩展一个 `AgentMessageId`;条目待处理期间,loop 只额外附加驱动器自有的路由状态。 ### `OutOfBandSessionEventMap`:受限的带外追加显式准入 @@ -169,13 +149,13 @@ interface TodoItem { ### 请求头事件:`request/header` -请求信封(即 `EpochHeader`:调用配置 + 渲染后的系统提示词 + 已组装的工具 schema + 会话前缀)会作为会话状态写入日志,因此每个对话请求都是日志的纯函数(见可重建性 Agent Note)。带有 reason `'initial'` 或 `'resume'` 的完整 `request/header` 快照记录每个 agent loop 实例的边界;之后请求发生变化时,系统会以 reason `'change'` 记录另一份完整快照。`foldRequestHeader(events)` 通过选择最新快照重建请求头。该事件不是 `SurfaceEventType`,不产生 LLM 消息。 +请求信封(即 `EpochHeader`:调用配置 + 渲染后的系统提示词 + 已组装的工具 schema)会作为会话状态写入日志,因此每个对话请求都是日志的纯函数(见可重建性 Agent Note)。带有 reason `'initial'` 或 `'resume'` 的完整 `request/header` 快照记录每个 agent loop 实例的边界;之后请求发生变化时,系统会以 reason `'change'` 记录另一份完整快照。`foldRequestHeader(events)` 通过选择最新快照重建请求头。该事件不是 `SurfaceEventType`,不产生 LLM 消息。 ```ts type-equiv /** - * Logged request state outside derived history: call config, system prompt, - * tools, and prefix. The latest full `request/header` snapshot reconstructs it; - * canonical empty optional fields are absent. + * Logged request state outside derived history: call config, system prompt, and + * tools. The latest full `request/header` snapshot reconstructs it; canonical + * empty optional fields are absent. */ interface EpochHeader { /** The conversation's call configuration (provider, model, and sampling scalars). */ @@ -184,18 +164,10 @@ interface EpochHeader { system?: string /** Assembled tool schemas; absent for a tool-less request. */ tools?: ToolSchema[] - /** - * The session prefix: request-only messages sent BEFORE the entire derived - * history (the `agent/session-prefix` waterfall's product, composed once - * per loop instance and reused for every request it sends). Not session - * history — `deriveMessages()` never returns it — so the header is its - * only durable record; absent when the instance composed none. - */ - messagePrefix?: Message[] } ``` -规范形式:空系统提示词、空工具列表和空会话前缀都表示为字段缺失,与请求构建方式一致。`messagePrefix` 是 `agent/session-prefix` waterfall(瀑布式事件)产物的持久记录(请求 = `messagePrefix + derived history`);每个 agent loop 实例只组合一次,并包含在该实例记录的每份完整快照中。包含已移除的 `request/header-delta` 事件或完整快照原因为 `fallback` 的旧版 v0 日志,会在 seed、append 和持久化加载边界被拒绝,而不会以不完整方式回放。 +规范形式:空系统提示词和空工具列表都表示为字段缺失,与请求构建方式一致。包含已移除的 `request/header-delta` 事件或完整快照原因为 `fallback` 的旧版 v0 日志,会在 seed、append 和持久化加载边界被拒绝,而不会以不完整方式回放。 ## `SessionEvent`:一条日志条目 @@ -475,7 +447,7 @@ declare class Session { - `user/message` → 一条携带确切 `content` 的 user 消息;可选 envelope 仅作为日志中的展示元数据保留。 - `assistant/message` → 一条 assistant 消息,包含事件的提供方/模型溯源信息和可选的适配器私有回放状态。原始 `assistant/chunk` 事件属于回放/UI 数据,在派生时会被**跳过**(组装后的消息才是权威)。**内容为空的** `assistant/message` 也会跳过:因 max-tokens 而截断且无内容的步骤仍会记录一条 `assistant/message` 以承载用量和溯源信息,但无内容的 assistant 轮次不得进入提供方 transcript。 - `tool/result` → 一条携带 `tool-result` 块的 user 消息。 -- `user/message`(注入上下文,即非 `user` 来源)→ 按时间顺序在相应位置生成一条 user-role 消息,并原样承载其 `content`。可选的 JSON `meta` 保留在事件日志中,绝不渲染。 +- `user/message`(注入上下文,即非 `user` 来源)→ 按时间顺序在相应位置生成一条 user-role 消息,并原样承载其 `content`;溯源信息与领域数据都在其类型化的 source 中。 - `steering/message` → 按时间顺序在相应位置生成一条携带确切 `content` 的 user-role 消息;可选 envelope 仅作为日志中的展示元数据保留。 其余所有事件(`turn/*`、`step/*`、插件所有的 `llm/retry`)均为结构信息,不会投影为消息。token 记账读取每个步骤的 `assistant/chunk { type: 'usage' }` 记录;如果没有用量分片,则将 `assistant/message.usage` 作为已提交步骤的后备。失败的模型请求尝试没有 assistant 消息,因此其用量分片是持久化的记账记录。操作错误的步骤号记录在 `turn/end.reason`(`kind: 'error'`)中;如果是最终模型请求失败,其中包含规范化的 `LlmFailure` 事实,其他实时错误则包含消息/代码。由于这一尚未发布的格式有意不提供兼容性承诺,seed/load 校验会拒绝缺少提供方和模型的请求头,以及缺少提供方/模型溯源信息的 assistant 消息,而不会猜测历史数据应走的提供方路由。 @@ -497,14 +469,12 @@ declare class Session { */ interface TurnTriggerMap { message: { kind: 'message'; source: MessageSource } + /** Recovery turn reopened over the repaired current session log. */ + retry: { kind: 'retry' } /** - * An out-of-band context injection (`agent.inject()`) made while the agent - * was idle. The loop wraps the injected `user/message` (a non-`user` source, - * plugin by default) in a one-shot turn (`turn/start` → `user/message` → - * `turn/end`) so every event in the log stays turn-enclosed — the - * durability/replay boundary is the turn, and a bare event between turns would - * otherwise be indistinguishable from a crash tail on reload. The trigger's - * `source` mirrors that message's producer. + * An out-of-band producer explicitly enclosed injected context in a one-shot + * turn. `Agent.inject()` appends idle context directly and does not use this + * trigger; the source mirrors the producer of the enclosed `user/message`. */ injection: { kind: 'injection'; source: MessageSource } } @@ -529,7 +499,8 @@ interface TurnEndReasonMap { * step number the failure occurred on (the operational error's location — the * single durable record of an in-turn failure; live diagnostics also fire via * `agent/error`). Final model-request failures retain their normalized facts - * as one `failure`; other turn failures retain their live Error message/code. + * as one `failure`; other thrown values retain their rendered message and a + * real `HarnessError` code when present. */ error: { kind: 'error'; step: number } & ( | { failure: LlmFailure; message?: never; code?: never } @@ -538,11 +509,6 @@ interface TurnEndReasonMap { disposed: { kind: 'disposed' } /** At least one step reached its output-token ceiling, even if a plugin continued the turn. */ 'max-tokens': { kind: 'max-tokens' } - /** - * Policy blocked the turn's claimed prompt before the first step. The - * zero-step turn still records a balanced durable boundary and veto reason. - */ - rejected: { kind: 'rejected'; reason: string } /** * A persistence backend closed a crash-orphaned turn on reload. The loop never * emits this marker, and the events recorded before the crash remain intact. @@ -551,7 +517,7 @@ interface TurnEndReasonMap { } ``` -`max-tokens` 与模型调用中同名的 `FinishReason` 对应:只要轮次内有任何步骤以 `max-tokens` 结束,整个轮次就以 `max-tokens` 而不是 `completed` 结束(即使之后继续执行,截断事实仍优先),让消费方能够区分正常停止和截断停止;但它只优先于 `completed`,`disposed`/`aborted`/`error` 结果的优先级更高。`rejected` 表示一个零步骤轮次,其已认领的提示词被 `agent/prompt-submit` 钩子阻止(ACP(Agent Client Protocol)桥接层将其映射为 `cancelled`)。`interrupted` 是唯一不会由任何 loop 发出的原因:它由崩溃恢复合成(见 [persistence.md](persistence.md))。两个 map 均可通过合并扩展。 +`max-tokens` 与模型调用中同名的 `FinishReason` 对应:只要轮次内有任何步骤以 `max-tokens` 结束,整个轮次就以 `max-tokens` 而不是 `completed` 结束(即使之后继续执行,截断事实仍优先),让消费方能够区分正常停止和截断停止;但它只优先于 `completed`,`disposed`/`aborted`/`error` 结果的优先级更高。`interrupted` 是唯一不会由任何 loop 发出的原因:它由崩溃恢复合成(见 [persistence.md](persistence.md))。两个 map 均可通过合并扩展。 ## 轮次封闭不变式 @@ -561,7 +527,7 @@ interface TurnEndReasonMap { 插件可以通过 declaration merging 添加额外的 `SessionEventMap` 类型。这些是**仅日志**事件:不是 `SurfaceEventType`(不携带 `surfaceOp`,不参与派生历史),但与所有事件一样,必须位于一个打开的轮次内。完整的逐事件枚举(核心与插件贡献的,含 payload 与溯源信息)见生成的[持久化日志事件目录](../persistence-catalog.md);压缩 seam 的 `compact/*` 语义在 [compaction.md](compaction.md) 中讨论。 -钩子桥接层的 `hook/invoked` / `hook/result` 溯源对(来自 `@deepseek-ai/dsh-hook-protocol`)通过 `handlerId` 关联。轮次中间的钩子点(`PreToolUse`/`PostToolUse`/`UserPromptSubmit`/`Stop`)在 loop 已打开的轮次内触发,因此其 `hook/*` 记录天然位于轮次之内。`SessionStart` 不生成 `hook/*` 记录:它注入的 `user/message` 已是持久证据,而且当时没有已打开的轮次可容纳该记录(见[钩子桥接 Agent Note](../../.agents/notes/implemented/feature/2026-06-30-hook-bridges.md))。 +钩子桥接层的 `hook/invoked` / `hook/result` 溯源对(来自 `@deepseek-ai/dsh-hook-protocol`)通过 `handlerId` 关联。轮次中间的钩子点(`PreToolUse`/`PostToolUse`/`Stop`)在 loop 已打开的轮次内触发,因此其 `hook/*` 记录天然位于轮次之内。`SessionStart` 与轮次开始前的 `UserPromptSubmit` 准入 seam 都不生成 `hook/*` 记录,因为两者都没有已打开的轮次可容纳该记录;被放行的上下文改由其带来源的 `user/message` 作为持久证据(见[钩子桥接 Agent Note](../../.agents/notes/implemented/feature/2026-06-30-hook-bridges.md))。 ## 持久性契约 diff --git a/docs/core-data-structures/skills.i18n.yaml b/docs/core-data-structures/skills.i18n.yaml index 2f67387224..81c105f515 100644 --- a/docs/core-data-structures/skills.i18n.yaml +++ b/docs/core-data-structures/skills.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 -skills.md: fc9599713dcfddec9719ed746b66ea0217b86cf5 -skills.zh.md: 0eb4c0aa69ed56117c7508358c0d47e3b3e95fcb +skills.md: 1b82da1c59f0159404e6ea792bf95ea4477e0a03 +skills.zh.md: 38450cce01aa81e7898aefffed7f4e27d09b0204 diff --git a/docs/core-data-structures/skills.zh.md b/docs/core-data-structures/skills.zh.md index 0eb4c0aa69..38450cce01 100644 --- a/docs/core-data-structures/skills.zh.md +++ b/docs/core-data-structures/skills.zh.md @@ -154,6 +154,6 @@ interface Config { ## 会话目录与工具契约 -`dsh-tool-skill` 通过 `agent/session-prefix` 贡献一条 user-role ``。目录只包含已排序的 skill `name` 和规范化、经 XML 转义的 `description`;不包含正文、路径、来源、提供方或路由提示。Prefix 发现通过 `SkillLookupOptions` 转发调用方的 abort signal。`catalogDescriptionMaxLength` 是消费方用于 description 上限的配置,默认值为 `500`,整数最小值为 `3`。其仅用于请求、记录在 header 中的生命周期由 [session-prefix Agent Note(agent 决策记录)](../../.agents/notes/implemented/feature/2026-07-07-session-prefix.md)定义。 +`dsh-tool-skill` 在存活会话的第一个 `agent/step` 注入一条持久的 user-role ``。目录只包含已排序的 skill `name` 和规范化、经 XML 转义的 `description`;不包含正文、路径、来源、提供方或路由提示。发现通过 `SkillLookupOptions` 转发该步骤的 abort signal。`catalogDescriptionMaxLength` 是消费方用于 description 上限的配置,默认值为 `500`,整数最小值为 `3`。 面向模型的 `skill({ name })` 工具校验 kebab-case 名称,为调用方 agent 的 cwd 加载完整定义,将未解析的 skill 报告为 unknown 或 no longer available,拒绝 `disableModelInvocation` 的 skill,并返回包含 ``、`` 和 `` 的工具结果。`resourceBase` 仅按需解析显式引用的脚本、参考资料和资产;加载结果不枚举 skill 目录。工具结果是模型获取完整指令的可见路径。 diff --git a/docs/core-data-structures/tools.i18n.yaml b/docs/core-data-structures/tools.i18n.yaml index d22f80c910..8a3a6107fd 100644 --- a/docs/core-data-structures/tools.i18n.yaml +++ b/docs/core-data-structures/tools.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 -tools.md: 43d91e72d83dce0bec99417ca90f9394f4c2169e -tools.zh.md: b92f6d3d99fda7dc28d10556adcceee3946a9571 +tools.md: 7c015b40bc6e5cb19b2e2d31bca85362ac871dc7 +tools.zh.md: 0083c23b16e03123c164073b6f8ab66af5fdfa3d diff --git a/docs/core-data-structures/tools.zh.md b/docs/core-data-structures/tools.zh.md index b92f6d3d99..0083c23b16 100644 --- a/docs/core-data-structures/tools.zh.md +++ b/docs/core-data-structures/tools.zh.md @@ -215,7 +215,9 @@ interface ToolRunContext extends ToolExecution { * the agent loop. Contexts retain their individual source and metadata and * are emitted in call order. */ - deferContext(context: HookContext): void + deferContext(context: UserMessageData): void + /** Mark a successful final result as terminal for the current agent turn. */ + concludeTurn(): void } ``` @@ -292,7 +294,9 @@ interface ToolExecutionSuccess { readonly content: ContentBlock[] readonly error?: never readonly meta?: JsonValue - readonly additionalContexts?: HookContext[] + readonly additionalContexts?: UserMessageData[] + /** The agent loop stops after committing this successful result batch. */ + readonly concludesTurn?: true } ``` @@ -304,7 +308,8 @@ interface ToolExecutionFailure { readonly value?: never readonly content: ContentBlock[] readonly meta?: JsonValue - readonly additionalContexts?: HookContext[] + readonly additionalContexts?: UserMessageData[] + readonly concludesTurn?: never } ``` @@ -340,9 +345,9 @@ type PreToolDecision = * next request, or block by turning corrective feedback into an error result. */ type PostToolDecision = - | { kind: 'accept'; content?: ContentBlock[]; value?: never; additionalContexts?: HookContext[] } - | { kind: 'accept'; value: JsonValue; content?: never; additionalContexts?: HookContext[] } - | { kind: 'block'; feedback: ContentBlock[]; additionalContexts?: HookContext[] } + | { kind: 'accept'; content?: ContentBlock[]; value?: never; additionalContexts?: UserMessageData[] } + | { kind: 'accept'; value: JsonValue; content?: never; additionalContexts?: UserMessageData[] } + | { kind: 'block'; feedback: ContentBlock[]; additionalContexts?: UserMessageData[] } ``` 调用 `next()` 获取默认决策,或直接返回一个决策以短路。前置策略可以 deny 或 ask;只有 `allowed-once` 才继续执行,而未授权、缺少审批通道或服务、或无 agent 的请求都会变为拒绝。Guard 仍可施加最终拒绝。参数不可被改写,因为历史记录、审计、UI 和执行必须保持一致。 diff --git a/packages/support/acp-snapshot/src/normalize.ts b/packages/support/acp-snapshot/src/normalize.ts index 6ffe84a6e8..6503bba375 100644 --- a/packages/support/acp-snapshot/src/normalize.ts +++ b/packages/support/acp-snapshot/src/normalize.ts @@ -33,12 +33,16 @@ const SNAPSHOT_SPILL_PATH_RE = new RegExp( /** * Extract every snapshot-mode spill path from a session log, keyed by spill * filename. Used by refresh write-back to keep spill paths stable across runs. + * @param content - the raw session log text to scan. + * @returns spill filename → the full matched spill path, last match wins per name. */ export function extractSnapshotSpillPaths(content: string): Map { const result = new Map() for (const match of content.matchAll(SNAPSHOT_SPILL_PATH_RE)) { const name = match[1] - if (name) result.set(name, match[0]) + /* v8 ignore next -- the filename capture is required and non-empty whenever the spill regex matches */ + if (name === undefined) continue + result.set(name, match[0]) } return result } diff --git a/scripts/type-equiv.manifest.json b/scripts/type-equiv.manifest.json index 40a5f51759..a47afcebb9 100644 --- a/scripts/type-equiv.manifest.json +++ b/scripts/type-equiv.manifest.json @@ -1395,146 +1395,6 @@ "symbol": "SessionSearchHit", "source": "packages/session-query/session-query/src/types.ts" }, - { - "doc": "docs/core-data-structures/core.zh.md", - "symbol": "Branded", - "source": "packages/util/brand/src/index.ts" - }, - { - "doc": "docs/core-data-structures/core.zh.md", - "symbol": "ContentBlockMap", - "source": "packages/llm/llm/src/types.ts" - }, - { - "doc": "docs/core-data-structures/core.zh.md", - "symbol": "AssistantProvenance", - "source": "packages/llm/llm/src/types.ts" - }, - { - "doc": "docs/core-data-structures/core.zh.md", - "symbol": "Message", - "source": "packages/llm/llm/src/types.ts" - }, - { - "doc": "docs/core-data-structures/core.zh.md", - "symbol": "MessageSourceMap", - "source": "packages/llm/llm/src/types.ts" - }, - { - "doc": "docs/core-data-structures/core.zh.md", - "symbol": "FinishReasonMap", - "source": "packages/llm/llm/src/types.ts" - }, - { - "doc": "docs/core-data-structures/core.zh.md", - "symbol": "LlmProviderInfo", - "source": "packages/llm/llm/src/types.ts" - }, - { - "doc": "docs/core-data-structures/core.zh.md", - "symbol": "LlmModelInfo", - "source": "packages/llm/llm/src/types.ts" - }, - { - "doc": "docs/core-data-structures/core.zh.md", - "symbol": "LlmModelContext", - "source": "packages/llm/llm/src/types.ts" - }, - { - "doc": "docs/core-data-structures/core.zh.md", - "symbol": "GenerateOptions", - "source": "packages/llm/llm/src/types.ts" - }, - { - "doc": "docs/core-data-structures/core.zh.md", - "symbol": "ToolSchema", - "source": "packages/llm/llm/src/types.ts" - }, - { - "doc": "docs/core-data-structures/core.zh.md", - "symbol": "LlmCallConfig", - "source": "packages/llm/llm/src/call-config.ts" - }, - { - "doc": "docs/core-data-structures/core.zh.md", - "symbol": "SessionEvent", - "source": "packages/core/session/src/types.ts" - }, - { - "doc": "docs/core-data-structures/core.zh.md", - "symbol": "SendOptions", - "source": "packages/core/agent/src/types.ts" - }, - { - "doc": "docs/core-data-structures/core.zh.md", - "symbol": "AgentCancelCause", - "source": "packages/core/agent/src/types.ts" - }, - { - "doc": "docs/core-data-structures/core.zh.md", - "symbol": "InjectOptions", - "source": "packages/core/agent/src/types.ts" - }, - { - "doc": "docs/core-data-structures/core.zh.md", - "symbol": "ResolvedAgentInput", - "source": "packages/core/agent/src/types.ts" - }, - { - "doc": "docs/core-data-structures/core.zh.md", - "symbol": "AgentMessageId", - "source": "packages/core/agent/src/types.ts" - }, - { - "doc": "docs/core-data-structures/core.zh.md", - "symbol": "AgentMessage", - "source": "packages/core/agent/src/types.ts" - }, - { - "doc": "docs/core-data-structures/core.zh.md", - "symbol": "CancelOptions", - "source": "packages/core/agent/src/types.ts" - }, - { - "doc": "docs/core-data-structures/core.zh.md", - "symbol": "Agent", - "source": "packages/core/agent/src/types.ts" - }, - { - "doc": "docs/core-data-structures/core.zh.md", - "symbol": "HookContext", - "source": "packages/core/agent/src/types.ts" - }, - { - "doc": "docs/core-data-structures/core.zh.md", - "symbol": "PromptDecision", - "source": "packages/core/agent/src/types.ts" - }, - { - "doc": "docs/core-data-structures/core.zh.md", - "symbol": "ContinuationDecision", - "source": "packages/core/agent/src/types.ts" - }, - { - "doc": "docs/core-data-structures/core.zh.md", - "symbol": "RequestError", - "source": "packages/core/agent/src/types.ts" - }, - { - "doc": "docs/core-data-structures/core.zh.md", - "symbol": "RequestErrorDecision", - "source": "packages/core/agent/src/types.ts" - }, - { - "doc": "docs/core-data-structures/core.zh.md", - "symbol": "ContinuationStop", - "source": "packages/core/agent/src/types.ts" - }, - { - "doc": "docs/core-data-structures/core.zh.md", - "symbol": "SessionStartSource", - "source": "packages/core/agent/src/types.ts" - }, { "doc": "docs/core-data-structures/scope.zh.md", "symbol": "ScopeKey", @@ -1607,82 +1467,6 @@ "source": "packages/llm/llm/src/index.ts", "projection": "public-api" }, - { - "doc": "docs/core-data-structures/session.zh.md", - "symbol": "PromptMessageData", - "source": "packages/core/session/src/types.ts" - }, - { - "doc": "docs/core-data-structures/session.zh.md", - "symbol": "SessionEventMap", - "source": "packages/core/session/src/types.ts" - }, - { - "doc": "docs/core-data-structures/session.zh.md", - "symbol": "OutOfBandSessionEventMap", - "source": "packages/core/session/src/types.ts" - }, - { - "doc": "docs/core-data-structures/session.zh.md", - "symbol": "EpochHeader", - "source": "packages/core/session/src/types.ts" - }, - { - "doc": "docs/core-data-structures/session.zh.md", - "symbol": "TodoItem", - "source": "packages/core/session/src/types.ts" - }, - { - "doc": "docs/core-data-structures/session.zh.md", - "symbol": "SessionEvent", - "source": "packages/core/session/src/types.ts" - }, - { - "doc": "docs/core-data-structures/session.zh.md", - "symbol": "TurnTriggerMap", - "source": "packages/core/session/src/types.ts" - }, - { - "doc": "docs/core-data-structures/session.zh.md", - "symbol": "TurnEndReasonMap", - "source": "packages/core/session/src/types.ts" - }, - { - "doc": "docs/core-data-structures/session.zh.md", - "symbol": "SurfaceEventType", - "source": "packages/core/session/src/types.ts" - }, - { - "doc": "docs/core-data-structures/session.zh.md", - "symbol": "SurfaceOp", - "source": "packages/core/session/src/types.ts" - }, - { - "doc": "docs/core-data-structures/session.zh.md", - "symbol": "SurfaceIntent", - "source": "packages/core/session/src/types.ts" - }, - { - "doc": "docs/core-data-structures/session.zh.md", - "symbol": "SessionSurface", - "source": "packages/core/session/src/surface.ts" - }, - { - "doc": "docs/core-data-structures/session.zh.md", - "symbol": "SurfaceFoldReplacement", - "source": "packages/core/session/src/surface.ts" - }, - { - "doc": "docs/core-data-structures/session.zh.md", - "symbol": "SurfaceFoldResult", - "source": "packages/core/session/src/surface.ts" - }, - { - "doc": "docs/core-data-structures/session.zh.md", - "symbol": "Session", - "source": "packages/core/session/src/index.ts", - "projection": "public-api" - }, { "doc": "docs/core-data-structures/persistence.zh.md", "symbol": "SessionHeader",