Merge remote-tracking branch 'origin/master' into worktree/drop-create-by-name
# Conflicts: # .agents/notes/implemented/feature/2026-07-25-session-list-browsing-and-manual-order.i18n.yaml # .agents/notes/implemented/feature/2026-07-25-workspace-ui-product-flow.i18n.yaml # .agents/notes/implemented/feature/2026-07-25-workspace-ui-product-flow.zh.md # .agents/notes/implemented/simplification/2026-07-31-one-route-to-add-a-workspace.i18n.yaml # .agents/notes/implemented/simplification/2026-07-31-one-route-to-add-a-workspace.md # .agents/notes/implemented/simplification/2026-07-31-one-route-to-add-a-workspace.zh.md # apps/cli/reference/README.i18n.yaml # docs/config-catalog.md # packages/host/apiproxy/README.i18n.yaml # packages/host/apiproxy/README.md # packages/host/apiproxy/README.zh.md # packages/host/apiproxy/src/api-proxy.ts # packages/host/apiproxy/src/index.ts # packages/host/apiproxy/tests/api-proxy-approval.spec.ts # packages/host/apiproxy/tests/api-proxy-blank.spec.ts # packages/host/apiproxy/tests/api-proxy-cold.spec.ts # packages/host/apiproxy/tests/api-proxy-commands.spec.ts # packages/host/apiproxy/tests/api-proxy-config.spec.ts # packages/host/apiproxy/tests/api-proxy-models.spec.ts # packages/host/apiproxy/tests/api-proxy-projections.spec.ts # packages/host/apiproxy/tests/api-proxy-question.spec.ts # packages/host/apiproxy/tests/api-proxy-rename.spec.ts # packages/host/apiproxy/tests/api-proxy-search.spec.ts # packages/host/apiproxy/tests/api-proxy-subagents.spec.ts # packages/host/apiproxy/tests/api-proxy-view.spec.ts # packages/host/apiproxy/tests/api-proxy-workspace.spec.ts # packages/todo/tool-todo/tests/projection.spec.ts # scripts/hero-composer-dom-continuity.mjs
This commit is contained in:
creatixchu
@@ -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/feature/2026-06-14-acp-multi-session.md
|
||||
2026-06-14-acp-multi-session.md: 088fe984fbc94fe0d8654702d5fce9eb0581cd3b
|
||||
2026-06-14-acp-multi-session.zh.md: 083b160aa51e669b74931654cd08acaa3d2aa221
|
||||
2026-06-14-acp-multi-session.zh.md: ffa849d4baf742734df3ac4694cc9413d317ed1b
|
||||
|
||||
@@ -4,7 +4,7 @@ Status: implemented
|
||||
|
||||
[English](2026-06-14-acp-multi-session.md) | 中文
|
||||
|
||||
> 本 Agent Note 写于 ACP 还是编辑器桥接层的时期，动机来自 Zed 的多会话客户端模型。[ACP 作为仅面向自动化的协议](../simplification/2026-07-23-acp-automation-only-protocol.md)移除了编辑器接口；多路复用决策本身不变，本 Agent Note 现依照自动化契约陈述它。
|
||||
> 本 Agent Note 写于 ACP 还是编辑器桥接层的时期，动机来自 Zed 的多会话客户端模型。[ACP 作为仅面向自动化的协议](../simplification/2026-07-23-acp-automation-only-protocol.md)移除了编辑器接口；多路复用决策本身不变，本 Agent Note 现依照自动化约定陈述它。
|
||||
|
||||
## 问题
|
||||
|
||||
@@ -26,7 +26,7 @@ ACP 桥接层将活跃会话存储在 `Map<SessionId, SessionRecord>` 中。agen
|
||||
|
||||
[ACP v1 明确允许一个连接上存在多个并发会话](https://github.com/agentclientprotocol/agent-client-protocol/blob/01beb5fb5eec60e9f516a80d85eb03594bac61e3/docs/get-started/architecture.mdx#L16-L24)，每个新会话都携带自己的主 `cwd`。本桥实现该会话级多路复用，其中包括[按会话 cwd 决策](../architecture/2026-07-02-fs-per-session-cwd.md)所记录的不同主工作区；它不会为每个会话创建一个 agent 子进程。
|
||||
|
||||
一个会话内部的多根项目是另一项可选能力：ACP 把[有效根目录定义为主 `cwd` 加 `additionalDirectories`](https://github.com/agentclientprotocol/agent-client-protocol/blob/01beb5fb5eec60e9f516a80d85eb03594bac61e3/docs/protocol/v1/session-setup.mdx#L313-L367)。自动化桥接层不公布任何多根能力，并拒绝非空的 `additionalDirectories`；如[包契约](../../../../packages/acp/acp/README.md#protocol-contract)所记录，每个全新会话恰好有一个工作区。
|
||||
一个会话内部的多根项目是另一项可选能力：ACP 把[有效根目录定义为主 `cwd` 加 `additionalDirectories`](https://github.com/agentclientprotocol/agent-client-protocol/blob/01beb5fb5eec60e9f516a80d85eb03594bac61e3/docs/protocol/v1/session-setup.mdx#L313-L367)。自动化桥接层不公布任何多根能力，并拒绝非空的 `additionalDirectories`；如[包约定](../../../../packages/acp/acp/README.md#protocol-contract)所记录，每个全新会话恰好有一个工作区。
|
||||
|
||||
[标准传输是每个 stdio 连接一个 agent 子进程](https://github.com/agentclientprotocol/agent-client-protocol/blob/01beb5fb5eec60e9f516a80d85eb03594bac61e3/docs/protocol/v1/transports.mdx#L17-L42)；多个连接因此需要多个子进程或自定义传输，而本决策保证的是一个连接内部存在多个会话。在该连接内，`ctx.sandboxPolicy` 把每个会话的 `cwd` 解析为其自己的 `workspace-write` 根目录，因此共享的 bash 和文件系统服务可以服务并发项目而不授予跨项目写入。这不会添加 ACP `additionalDirectories`；它只是从已经支持的「每会话一个主根目录」路径中移除了进程级根目录限制。
|
||||
|
||||
|
||||
@@ -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/2026-06-15-code-mode.md
|
||||
2026-06-15-code-mode.md: 99bbed3edab32512f88ece9694d6519a1f89c2dd
|
||||
2026-06-15-code-mode.zh.md: ca1bbe9ed3e412186763d1ed4fca9ed06669d4c3
|
||||
2026-06-15-code-mode.md: 5ad7be9506c2356f90050b86d85aa77f602946ce
|
||||
2026-06-15-code-mode.zh.md: 1902c6ba86b6b8d3fecd06c417347a9c082f67b4
|
||||
|
||||
@@ -19,7 +19,7 @@ Tool presentation belongs to the registry that owns tool visibility: implementin
|
||||
Three decisions, each elaborated in its own section below:
|
||||
|
||||
1. **Code Mode is a first-class presentation mode of `ToolRegistry`** (`dsh-tools`), selected by a validated `mode` config: `'native'` (the default, contributing the visible capability schemas), `'code'` (the registry contributes only its reserved `run_code` transport plus a generated SDK `.d.ts` in the system prompt), or `'both'` (native schemas and the transport + SDK). The registry shapes its canonical contribution at the source; the cooperative prompt-assembly result remains authoritative, and the logged request header records exactly that returned presentation.
|
||||
2. **Code execution is a capability seam** — `packages/code-runtime/` contains the interface package `@deepseek-ai/dsh-code-runtime`, which owns `ctx.codeRuntime` ([capability seams](../architecture/2026-06-13-capability-seams.md); consumer = `dsh-tools`, with core-consumes-a-seam precedent in `agent-loop` → `dsh-llm`). The runtime knows nothing about tools: it is handed a program and named async bindings, runs the program, and reports `{ value, logs, error? }`. Language and substrate are backend properties, so a future Python or container backend is another implementation package, not a redesign.
|
||||
2. **Code execution is a capability seam** — `packages/code-runtime/` contains the Service Definition package `@deepseek-ai/dsh-code-runtime`, which owns `ctx.codeRuntime` ([capability seams](../architecture/2026-06-13-capability-seams.md); Consumer = `dsh-tools`, with core-consumes-a-seam precedent in `agent-loop` → `dsh-llm`). The runtime knows nothing about tools: it is handed a program and named async bindings, runs the program, and reports `{ value, logs, error? }`. Language and substrate are backend properties, so a future Python or container backend is another Service provider package, not a redesign.
|
||||
3. **The shipped implementation is `@deepseek-ai/dsh-code-runtime-worker`**: one fresh Node worker thread per run, executing the model's TypeScript after type-strip, with bindings bridged over the message port, an empty environment, configurable heap/output/time caps, and hard termination. Its trust posture is bash-equivalent by design — no unsafe-acknowledgement flags — because the harness already ships `dsh-bash-local`, which executes arbitrary model-written shell commands with strictly *more* ambient authority.
|
||||
|
||||
This note owns Code Mode's presentation, composition, isolation, and settlement foundation. The later [typed tool-return Agent Note](2026-07-20-code-mode-typed-tool-returns.md) owns the generated output map, canonical binding values, `ToolCallError`, and the lossless outer-output boundary.
|
||||
@@ -30,7 +30,7 @@ This note owns Code Mode's presentation, composition, isolation, and settlement
|
||||
|
||||
**Wire tool list.** The registry contributes visible capabilities in `'native'`, only `run_code` in `'code'`, and both in `'both'`. The final `PromptAssembly.tools` list is logged in the request header. `run_code` is a reserved presentation transport outside registration and restriction layers; direct prompt providers and the assembly waterfall remain responsible for their own contributions.
|
||||
|
||||
**Interaction with `toolOrder`, stated up front:** a configured `systemPrompt.toolOrder` naming native capabilities rejects every assembly under `mode: 'code'`, because those names are outside that mode's wire-validation universe. This is correct behavior, not a bug: a deployment using Code Mode updates its order config or drops it.
|
||||
**Interaction with `toolOrder`:** a configured `systemPrompt.toolOrder` naming native capabilities rejects every assembly under `mode: 'code'`, because those names are outside that mode's wire-validation universe. This is correct behavior, not a bug: a deployment using Code Mode updates its order config or drops it.
|
||||
|
||||
**SDK prompt section.** In `'code'` and `'both'`, the lazy `tools:sdk` section in the tool-guidance order band renders the loaded runtime's language declarations plus fixed usage instructions for the scope's visible capabilities (TypeScript by default; the [language-dispatch note](2026-07-31-code-mode-language-dispatch.md) added Python and the `ctx.codeRuntime.language` renderer table). It shares lookup and execution visibility, excludes `run_code`, and sorts tools lexicographically for byte-stable output.
|
||||
|
||||
@@ -106,7 +106,7 @@ Deployments switching to `'code'` must update any native-only `toolOrder`. Assem
|
||||
|
||||
**Result elision / summarization over native tool-calling.** Addresses only the context-bloat half of the problem: trimming old `tool-result`s is cheap to add as a logged surface replacement under reconstructable requests, but still pays one model round-trip per call and cannot express loops, branches, or joins. Complementary, not competing; it can layer under Code Mode for residual native calls.
|
||||
|
||||
**Parallel native dispatch in the loop.** The other answer to round-trip cost at decision time; it was blocked on concurrency-safety metadata and offers no composition either way — it parallelizes calls the model already decided on in one step. Code Mode's queue decision kept the two compatible, and that is how it played out: the metadata landed as `isConcurrencySafe` (the [parallel tool-call note](2026-07-10-parallel-tool-call-execution.md)), and native rolling-pool dispatch and per-tool binding parallelism unlocked on the same classifier.
|
||||
**Parallel native dispatch in the loop.** The other answer to round-trip cost at decision time; it was blocked on concurrency-safety metadata and offers no composition either way — it parallelizes calls the model already decided on in one step. Code Mode's queue decision kept the two compatible, and both later shipped: the metadata as `isConcurrencySafe` (the [parallel tool-call note](2026-07-10-parallel-tool-call-execution.md)), and native rolling-pool dispatch plus per-tool binding parallelism on the same classifier.
|
||||
|
||||
**Always-exclusive (Cloudflare-faithful, no mode).** Rejected for this SDK's primary consumer: a coding agent's bread-and-butter single calls (`bash`, `read`, `edit`) are already ideal as native calls, and forcing every edit through a program taxes the common case. The mode config keeps the faithful form (`'code'`) one line away without imposing it.
|
||||
|
||||
@@ -118,7 +118,7 @@ Deployments switching to `'code'` must update any native-only `toolOrder`. Assem
|
||||
|
||||
## Risks
|
||||
|
||||
**The worker is not a hard security boundary.** Deliberate and documented (§Trust posture): posture equals the existing bash tool, containment exceeds it, gating uses the same seams. Deployments needing more need a future `isolation: 'container'` backend — tracked as the seam's designed extension, not a TODO on this design.
|
||||
**The worker is not a hard security boundary.** Deliberate and documented (§Trust posture): posture equals the existing bash tool, containment exceeds it, gating uses the same approval and sandbox policies. Deployments needing more need a future `isolation: 'container'` backend — tracked as the seam's designed extension, not a TODO on this design.
|
||||
|
||||
**`stripTypeScriptTypes` is marked experimental.** It is the same engine (amaro/swc) behind Node's own native `.ts` execution, exposed as an API across this repo's whole engines range. Mitigations: the runtime's unit suite pins the behaviors relied on (position preservation, erasable-only rejection message shape loosely), the call sits behind one private function, and `amaro`/`sucrase` are drop-in replacements if the API shifts. The erasable-only subset is a model-facing contract line, and the error path is a working feedback loop, not a dead end.
|
||||
|
||||
|
||||
@@ -19,7 +19,7 @@ Cloudflare 的 [Code Mode](https://blog.cloudflare.com/code-mode/) 提出了一
|
||||
三项决策，各自在下方独立小节中展开：
|
||||
|
||||
1. **Code Mode 是 `ToolRegistry`（`dsh-tools`）的一等呈现模式**，通过经校验的 `mode` 配置选择：`'native'`（默认，贡献可见能力 schema）、`'code'`（注册表仅贡献其保留的 `run_code` 传输通道加一份生成的 SDK `.d.ts` 到系统提示词中）或 `'both'`（原生 schema 加传输通道 + SDK）。注册表在源头塑造其权威贡献；协作式提示词组装的结果仍具权威性，记录在日志中的请求头精确反映该返回的呈现。
|
||||
2. **代码执行是一个能力 seam**——`packages/code-runtime/` 包含接口包`@deepseek-ai/dsh-code-runtime`，拥有 `ctx.codeRuntime`（[能力 seam](../architecture/2026-06-13-capability-seams.md)；消费方 = `dsh-tools`，core 消费 seam 的先例见 `agent-loop` → `dsh-llm`）。运行时对工具一无所知：它接收一段程序和命名的异步绑定，执行程序，报告 `{ value, logs, error? }`。语言和基底是后端属性，因此未来的 Python 或容器后端只是另一个实现包，而非重新设计。
|
||||
2. **代码执行是一个能力 seam**——`packages/code-runtime/` 包含 Service Definition 包 `@deepseek-ai/dsh-code-runtime`，拥有 `ctx.codeRuntime`（[能力 seam](../architecture/2026-06-13-capability-seams.md)；Consumer = `dsh-tools`，core 消费 seam 的先例见 `agent-loop` → `dsh-llm`）。运行时对工具一无所知：它接收一段程序和命名的异步绑定，执行程序，报告 `{ value, logs, error? }`。语言和基底是后端属性，因此未来的 Python 或容器后端只是另一个 Service provider 包，而非重新设计。
|
||||
3. **交付的实现是 `@deepseek-ai/dsh-code-runtime-worker`**：每次运行 spawn 一个全新的 Node worker 线程，对模型的 TypeScript 进行 type-strip 后执行，绑定通过消息端口桥接，环境为空，堆/输出/时间上限可配置，并支持硬终止。其信任姿态在设计上等同于 bash——无需 unsafe-acknowledgement flag——因为 harness 已经交付了 `dsh-bash-local`，后者以严格*更高*的环境权限执行模型编写的任意 shell 命令。
|
||||
|
||||
本说明负责定义 Code Mode 的呈现、组合、隔离与结算基础。后续的[类型化工具返回值 Agent Note](2026-07-20-code-mode-typed-tool-returns.md)负责定义生成的输出映射、规范绑定值、`ToolCallError` 和无损外层输出边界。
|
||||
@@ -30,7 +30,7 @@ Cloudflare 的 [Code Mode](https://blog.cloudflare.com/code-mode/) 提出了一
|
||||
|
||||
**协议工具列表。** 注册表在 `'native'` 下贡献可见能力，在 `'code'` 下仅贡献 `run_code`，在 `'both'` 下两者都贡献。最终的 `PromptAssembly.tools` 列表记录在请求头中。`run_code` 是一个保留的呈现传输通道，位于注册和限制层之外；直接提示词提供方和组装 waterfall 仍各自负责自己的贡献。
|
||||
|
||||
**与 `toolOrder` 的交互，预先说明：** 如果配置的 `systemPrompt.toolOrder` 引用了原生能力名称，在 `mode: 'code'` 下会拒绝所有组装，因为那些名称不在该模式的协议校验范围内。这是正确行为而非 bug：使用 Code Mode 的部署需要更新其 order 配置或移除它。
|
||||
**与 `toolOrder` 的交互：** 如果配置的 `systemPrompt.toolOrder` 引用了原生能力名称，在 `mode: 'code'` 下会拒绝所有组装，因为那些名称不在该模式的协议校验范围内。这是正确行为而非 bug：使用 Code Mode 的部署需要更新其 order 配置或移除它。
|
||||
|
||||
**SDK 提示词段。** 在 `'code'` 和 `'both'` 下，tool-guidance order band 中的惰性 `tools:sdk` 段为当前 scope 的可见能力渲染所加载运行时语言的声明加固定的使用说明（默认 TypeScript；[语言分发 note](2026-07-31-code-mode-language-dispatch.md) 加入了 Python 与按 `ctx.codeRuntime.language` 选择的渲染器表）。它共享查找和执行可见性，排除 `run_code`，并按字典序排列工具以获得字节稳定的输出。
|
||||
|
||||
@@ -42,13 +42,13 @@ Cloudflare 的 [Code Mode](https://blog.cloudflare.com/code-mode/) 提出了一
|
||||
|
||||
在 `'code'` 和 `'both'` 下，注册表拥有 `run_code` 作为保留的呈现传输通道，带两个必需参数 `{ code: string; description: string }`（description 为 UI 标注该调用，沿用 bash 的先例）。它由一个正常的 `ToolDefinition` 表示以供分发，但位于可过滤的能力层之外，因此限制规则不会意外移除 Code Mode 的唯一入口。调用遍历完整的工具流水线——`tools/pre-execute` → 单调性守卫 → `tools/execute` 包裹分发 → `tools/post-execute` → 由定义拥有的可选 `finalizeContent` → 不可变的 `tools/result` 通知——与原生调用完全一致；权限插件可以在程序运行前检查程序文本，最终结果观察者看到的是规范化的外层结果。其 `execute(args, exec)`：
|
||||
|
||||
1. **构建绑定。** 一个 run 级别的 signal 跟随外层取消，并在 run 结算时被 abort。每个可见工具绑定都会对无损 JSON 参数创建快照，进入原生契约的分发池（调度设计由[实时并行 Agent Note](2026-07-26-code-mode-live-parallel-dispatch.md) 负责），以确定性的 call id 和外层 token 作为 `parent` 执行，通过外层 execution 延后返回的上下文，并记录 `tool/code-dispatch-start`/`tool/code-dispatch` 事件对，其中结算侧携带完整渲染后的结果内容。成功时返回工具最终的规范 JSON 值；失败则变为程序可见的 `ToolCallError`。每个子调用保留自己不可变的执行标识，并遍历完整的工具流水线。
|
||||
1. **构建绑定。** 一个 run 级别的 signal 跟随外层取消，并在 run 结算时被 abort。每个可见工具绑定都会对无损 JSON 参数创建快照，进入原生约定的分发池（调度设计由[实时并行 Agent Note](2026-07-26-code-mode-live-parallel-dispatch.md) 负责），以确定性的 call id 和外层 token 作为 `parent` 执行，通过外层 execution 延后返回的上下文，并记录 `tool/code-dispatch-start`/`tool/code-dispatch` 事件对，其中结算侧携带完整渲染后的结果内容。成功时返回工具最终的规范 JSON 值；失败则变为程序可见的 `ToolCallError`。每个子调用保留自己不可变的执行标识，并遍历完整的工具流水线。
|
||||
2. **运行程序**：`ctx.codeRuntime.run({ program: args.code, bindings: [{ global: 'tools', functions }], signal: runController.signal })`。运行时接收的是 run 级别的 signal 而非仅调用方的外层 signal，因此外层 run 以任何方式结算都会同时 abort 运行时内部的工作。
|
||||
3. **完全停稳后结算。** 运行时结算后，桥 abort 未完成的工作并排空分发队列后再返回。成功时返回捕获的日志和完成值，将其作为规范输出；注册表再把该值渲染为持久化的 `tool/result.content`，供结果卡片直接读取。运行时失败变为 `CodeRunFailedError`；后端拒绝使用注册表的正常错误边界。两者都产生结构化的错误结果，且 `run_code` 结算后不允许子调用追加。
|
||||
|
||||
**子调用上下文通过父调用延后。** 在 `run_code` 内部注入会破坏父调用/结果的相邻性，因此 `ToolRunContext.deferContext()` 按分发顺序收集每个子结果的 `additionalContexts` 条目。即使程序后来抛出异常，注册表仍携带该数组；循环只在外层结果与步骤中所有兄弟结果之后追加每个条目。外层 post-execute 阻止会丢弃工具延后的条目，只暴露阻止 decision 显式附加的上下文。
|
||||
|
||||
**并发是有界的，而非被序列化。** 每次 run 拥有一个分发队列，严格按提交顺序启动调用，并通过 `registry.executionMode` 对每个调用分类——与原生循环所用的 fail-closed `isConcurrencySafe` 契约相同。连续的 parallel 类调用最多重叠 `maxParallelSubCalls` 个（默认 10；设为 `1` 恢复串行分发）；exclusive 类调用会排空池并单独运行。结算时放弃尚未开始的排队调用。本 note 交付的是被序列化的占位实现；取代它的调度器由[实时并行 Agent Note](2026-07-26-code-mode-live-parallel-dispatch.md) 负责。
|
||||
**并发是有界的，而非被序列化。** 每次 run 拥有一个分发队列，严格按提交顺序启动调用，并通过 `registry.executionMode` 对每个调用分类——与原生循环所用的 fail-closed `isConcurrencySafe` 约定相同。连续的 parallel 类调用最多重叠 `maxParallelSubCalls` 个（默认 10；设为 `1` 恢复串行分发）；exclusive 类调用会排空池并单独运行。结算时放弃尚未开始的排队调用。本 note 交付的是被序列化的占位实现；取代它的调度器由[实时并行 Agent Note](2026-07-26-code-mode-live-parallel-dispatch.md) 负责。
|
||||
|
||||
**呈现。** `run_code` 的 render intent 按[呈现意图 Agent Note](../architecture/2026-07-02-tool-render-intent-union.md)在此决定：`presentCall` 创建一个 `generic` 卡片，`kind: 'execute'`，以程序文本作为标题，并将同一程序文本作为 `rawInput`；`run_code` 有意不声明 `presentResult`，因此 TUI 和宿主/客户端运行时（Web）会通过通用原始内容回退机制，使用最终持久化的 `tool/result.content` 补全该卡片，其中包括捕获的日志，以及返回值、失败信息或 post-policy 输出落盘预览。这不是 `terminal` 卡片：该卡片的语义是「工作目录中的 shell 命令」，程序不是。参见[结果卡片完整性说明](../../archived/bug-fix/2026-07-20-code-mode-result-card-completeness.md)。
|
||||
|
||||
@@ -85,7 +85,7 @@ worker 运行时只能约束程序的运行，而不构成安全边界：模型
|
||||
|
||||
### 模型看到的内容
|
||||
|
||||
SDK 指示模型编写一个所加载运行时语言的异步函数体（默认可擦除 TypeScript；Python 运行时下为 Python `async` 函数体——见[语言分发 note](2026-07-31-code-mode-language-dispatch.md)），通过 `await tools.name(args)` 调用工具，在需要时捕获被拒绝的工具调用，并仅 return 或 log 应重新进入上下文的输出。两种 flavor 用各自的原语陈述同一契约：相互独立的只读调用可以在 `Promise.all`（TypeScript）或 `asyncio.gather`（Python）下重叠，有副作用的调用按提交顺序单独运行，有依赖的工作用 `await` 排序。声明前缀可能与原生 schema 一样大，尤其在 `'both'` 下，但对提供方缓存保持稳定。
|
||||
SDK 指示模型编写一个所加载运行时语言的异步函数体（默认可擦除 TypeScript；Python 运行时下为 Python `async` 函数体——见[语言分发 note](2026-07-31-code-mode-language-dispatch.md)），通过 `await tools.name(args)` 调用工具，在需要时捕获被拒绝的工具调用，并仅 return 或 log 应重新进入上下文的输出。两种 flavor 用各自的原语陈述同一约定：相互独立的只读调用可以在 `Promise.all`（TypeScript）或 `asyncio.gather`（Python）下重叠，有副作用的调用按提交顺序单独运行，有依赖的工作用 `await` 排序。声明前缀可能与原生 schema 一样大，尤其在 `'both'` 下，但对提供方缓存保持稳定。
|
||||
|
||||
## 后果
|
||||
|
||||
@@ -106,7 +106,7 @@ SDK 指示模型编写一个所加载运行时语言的异步函数体（默认
|
||||
|
||||
**在原生工具调用上做结果省略/摘要。** 仅解决问题中上下文膨胀这一半：裁剪旧 `tool-result` 作为可重建请求下的日志化表面替换成本低，但仍需每次调用一次模型往返，且无法表达循环、分支或汇合。互补而非竞争；它可以在 Code Mode 下为残余的原生调用分层。
|
||||
|
||||
**循环中的并行原生分发。** 决策当时对往返成本的另一个答案；它被并发安全元数据阻塞，且无论如何都不提供组合能力——它并行化的是模型在一步中已经决定的调用。Code Mode 的队列决策保持了两者兼容，后续也正是这样落地的：元数据以 `isConcurrencySafe` 的形式就绪（见[并行工具调用 note](2026-07-10-parallel-tool-call-execution.md)），原生 rolling-pool 分发与每工具绑定并行化基于同一个分类器一起解锁。
|
||||
**循环中的并行原生分发。** 决策当时对往返成本的另一个答案；它被并发安全元数据阻塞，且无论如何都不提供组合能力——它并行化的是模型在一步中已经决定的调用。Code Mode 的队列决策保持了两者兼容，两者后来都已交付：元数据即 `isConcurrencySafe`（见[并行工具调用 note](2026-07-10-parallel-tool-call-execution.md)），原生 rolling-pool 分发加每工具绑定并行化则基于同一个分类器。
|
||||
|
||||
**始终排他（忠于 Cloudflare，无模式）。** 否决，因为本 SDK 的主要消费方是编码 agent：其日常的单次调用（`bash`、`read`、`edit`）作为原生调用已经是最优的，强制每次编辑都通过程序会给常见场景增加负担。mode 配置让忠实形式（`'code'`）只需一行配置即可启用，而不强加于人。
|
||||
|
||||
@@ -118,9 +118,9 @@ SDK 指示模型编写一个所加载运行时语言的异步函数体（默认
|
||||
|
||||
## 风险
|
||||
|
||||
**Worker 不是硬安全边界。** 有意为之且已文档化（§信任姿态）：姿态等同于既有的 bash 工具，约束能力强于它，门禁使用相同的 seam。需要更强隔离的部署需要未来的 `isolation: 'container'` 后端——作为 seam 设计的扩展点跟踪，而非本设计的 TODO。
|
||||
**Worker 不是硬安全边界。** 有意为之且已文档化（§信任姿态）：姿态等同于既有的 bash 工具，约束能力强于它，门禁使用相同的审批与沙箱策略。需要更强隔离的部署需要未来的 `isolation: 'container'` 后端——作为 seam 设计的扩展点跟踪，而非本设计的 TODO。
|
||||
|
||||
**`stripTypeScriptTypes` 标记为 experimental。** 它与 Node 自身原生 `.ts` 执行背后的引擎（amaro/swc）相同，在本仓库的整个引擎范围内作为 API 暴露。缓解措施：运行时的单元测试套件固定了所依赖的行为（位置保持、可擦除限制的拒绝消息形状宽松匹配），调用位于一个私有函数之后，且 `amaro`/`sucrase` 是 API 变化时的直接替代品。仅可擦除子集是面向模型的契约线，错误路径是一个可工作的反馈循环，而非死胡同。
|
||||
**`stripTypeScriptTypes` 标记为 experimental。** 它与 Node 自身原生 `.ts` 执行背后的引擎（amaro/swc）相同，在本仓库的整个引擎范围内作为 API 暴露。缓解措施：运行时的单元测试套件固定了所依赖的行为（位置保持、可擦除限制的拒绝消息形状宽松匹配），调用位于一个私有函数之后，且 `amaro`/`sucrase` 是 API 变化时的直接替代品。仅可擦除子集是面向模型的约定线，错误路径是一个可工作的反馈循环，而非死胡同。
|
||||
|
||||
**SDK 的提示词成本，尤其在 `'both'` 下。** `.d.ts` 可能与它补充的原生 schema 体量相当；`'both'` 携带两种表示。前缀稳定性 + 提供方缓存摊销了每会话成本；mode 是每部署的；本 Agent Note 不做无条件节省的声明。何时优先使用哪种模式的量化指导明确属于上线后学习。
|
||||
|
||||
@@ -128,6 +128,6 @@ SDK 指示模型编写一个所加载运行时语言的异步函数体（默认
|
||||
|
||||
**大型无损 JSON 值可能耗尽内存。** 工具绑定会在分发前对无损 JSON 创建快照，并完整返回规范 JSON 返回值。运行时会校验 worker 端口两侧，但不对单次绑定设置字节数上限；结构化克隆成本以及进程或 worker 内存构成实际边界。只有包含日志、完成值和失败诊断的组合外层输出账本受字节数上限约束。
|
||||
|
||||
**子分发的重叠由工具自身的安全声明限定，而非由调用方决定。** 程序里的 `Promise.all` 或 `asyncio.gather` 只在工具自己分类为并发安全的调用之间换来挂钟并行性；一串 exclusive 调用仍要按顺序付出各自的往返开销，模型可能过度期望。两种 flavor 的 SDK 说明都陈述了真实契约。本 note 交付的是使该风险绝对化的序列化占位实现；调度器及其重叠上限由[实时并行 Agent Note](2026-07-26-code-mode-live-parallel-dispatch.md) 负责。
|
||||
**子分发的重叠由工具自身的安全声明限定，而非由调用方决定。** 程序里的 `Promise.all` 或 `asyncio.gather` 只在工具自己分类为并发安全的调用之间换来挂钟并行性；一串 exclusive 调用仍要按顺序付出各自的往返开销，模型可能过度期望。两种 flavor 的 SDK 说明都陈述了真实约定。本 note 交付的是使该风险绝对化的序列化占位实现；调度器及其重叠上限由[实时并行 Agent Note](2026-07-26-code-mode-live-parallel-dispatch.md) 负责。
|
||||
|
||||
**预算计量读取事件循环，而非 flag。** 忙碌时间轮询（`eventLoopUtilization()`）比精确 CPU 计量更粗糙——预算到期最多延迟一个轮询间隔——且其正确性声明（「pending 的分发不能暂停它」）是抵御恶意程序的关键。两种情况均有单元测试（带 pending 诱饵分发的热循环会在耗尽 `computeMs` 预算时终止；等待慢速绑定的空闲程序则会持续运行至 `maxWallMs`），轮询间隔是内部常量而非配置——部署无法将其误调为绕过手段。`maxWallMs` 是配置项，且会传入 `setTimeout`，后者会把超过 `MAX_TIMER_DELAY_MS`（2^31-1 ms）的延迟夹到 1 ms；因此仅有正数校验会放行一个 25 天的上限，它在第一个 tick 就到期，使每次运行都超时。worker 运行时正因如此在加载时对该字段做范围校验。`computeMs` 不需要上界，因为它对照的是实测占用率，而不是交给定时器。
|
||||
|
||||
@@ -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/2026-06-17-filesystem-tool-schemas.md
|
||||
2026-06-17-filesystem-tool-schemas.md: 9941b3916b361a916c8148eb099eb8cfd46371c8
|
||||
2026-06-17-filesystem-tool-schemas.zh.md: 4de0fe000a5524a3c5e76c6fa67f8a8b7e37ac6d
|
||||
2026-06-17-filesystem-tool-schemas.md: ede7daee5c0f49a094df16861b107c8f528664fa
|
||||
2026-06-17-filesystem-tool-schemas.zh.md: 5ab19b82d6523bc81dd57c319252d998cc203911
|
||||
|
||||
@@ -8,19 +8,19 @@ English | [中文](2026-06-17-filesystem-tool-schemas.zh.md)
|
||||
|
||||
[The filesystem capability-seam Agent Note](../architecture/2026-06-17-filesystem-capability-seam.md) defines the filesystem capability seam (`ctx.fs`), the package split (`dsh-fs`, `dsh-fs-local`, `dsh-tool-fs`, plus the `dsh-fs-policy` policy plugin), and the observed-file/stale-version policy for read-before-write/edit checks — which the [split-fs-seam](../simplification/2026-06-26-fsspec-style-fs-seam.md) and [event-gate](../architecture/2026-06-26-file-context-as-event-gate.md) Agent Notes moved off `ctx.fs` into the `dsh-fs-policy` plugin on the `fs/*` event gate. The remaining decision for the first filesystem tool delivery is the model-facing schema surface: what arguments the model sees for `read`, `write`, and `edit`.
|
||||
|
||||
The schema should be small enough to implement in the first `dsh-tool-fs` pass, but stable enough that future local/remote/sandboxed filesystem backends do not require model-facing churn. It should also avoid importing every option from reference systems. Claude Code and OpenCode expose similar core file tools but differ in naming style and extra flags; this Agent Note chooses the minimal shared surface for the prototype.
|
||||
The schema must be small, yet stable enough that local/remote/sandboxed filesystem backends do not require model-facing churn, and must avoid importing every option from reference systems. Claude Code and OpenCode expose similar core file tools but differ in naming style and extra flags; this decision picks the minimal shared surface.
|
||||
|
||||
## Decision
|
||||
|
||||
`@deepseek-ai/dsh-tool-fs` exposes these three model-facing tools in the first filesystem suite:
|
||||
|
||||
| Tool | Our schema | Claude Code | OpenCode | Notes | Part of prototype |
|
||||
|---|---|---|---|---|---|
|
||||
| `read` | `read(file_path, offset?, limit?)` | `Read(file_path, offset?, limit?, pages?)` | `read(filePath, offset?, limit?)` | Files only; 1-indexed `offset`; no image/PDF/multimodal support in the first pass. | YES |
|
||||
| `write` | `write(file_path, content)` | `Write(file_path, content)` | `write(content, filePath)` | Creates or overwrites UTF-8 text. Under the default fs-policy, updates to existing files require a prior observation; new-file creates do not. | YES |
|
||||
| `edit` | `edit(file_path, old_string, new_string, replace_all?)` | `Edit(file_path, old_string, new_string, replace_all?)` | `edit(filePath, oldString, newString, replaceAll?)` | Literal string replacement; unique match required by default; under the default fs-policy requires a prior observation (any windowed read counts). | YES |
|
||||
| Tool | Our schema | Claude Code | OpenCode | Notes |
|
||||
|---|---|---|---|---|
|
||||
| `read` | `read(file_path, offset?, limit?)` | `Read(file_path, offset?, limit?, pages?)` | `read(filePath, offset?, limit?)` | Files only; 1-indexed `offset`; no image/PDF/multimodal support in the first pass. |
|
||||
| `write` | `write(file_path, content)` | `Write(file_path, content)` | `write(content, filePath)` | Creates or overwrites UTF-8 text. Under the default fs-policy, updates to existing files require a prior observation; new-file creates do not. |
|
||||
| `edit` | `edit(file_path, old_string, new_string, replace_all?)` | `Edit(file_path, old_string, new_string, replace_all?)` | `edit(filePath, oldString, newString, replaceAll?)` | Literal string replacement; unique match required by default; under the default fs-policy requires a prior observation (any windowed read counts). |
|
||||
|
||||
The schema uses snake_case field names (`file_path`, `old_string`, `new_string`, `replace_all`) to align with Claude Code and with existing DeepSeek Harness tool-schema examples. The consumer package translates these model-facing names into `ctx.fs` calls and `fs/*` event dispatches.
|
||||
The schema uses snake_case field names (`file_path`, `old_string`, `new_string`, `replace_all`) to align with Claude Code and with existing DeepSeek Harness tool-schema examples. The Consumer package translates these model-facing names into `ctx.fs` calls and `fs/*` event dispatches.
|
||||
|
||||
## Tool schemas
|
||||
|
||||
|
||||
@@ -8,19 +8,19 @@ Status: implemented
|
||||
|
||||
[文件系统能力 seam Agent Note](../architecture/2026-06-17-filesystem-capability-seam.md) 定义了文件系统能力 seam（`ctx.fs`）、包拆分（`dsh-fs`、`dsh-fs-local`、`dsh-tool-fs`，加上 `dsh-fs-policy` 策略插件），以及针对 read-before-write/edit 检查的已观测文件／陈旧版本策略——[拆分文件系统 seam](../simplification/2026-06-26-fsspec-style-fs-seam.md)和[事件门控插件](../architecture/2026-06-26-file-context-as-event-gate.md) Agent Note 后来将其从 `ctx.fs` 移至 `dsh-fs-policy` 插件的 `fs/*` 事件门上。首次文件系统工具交付剩余的决策是面向模型的 schema 接口：模型在 `read`、`write` 和 `edit` 中看到哪些参数。
|
||||
|
||||
该 schema 应足够小，以便在 `dsh-tool-fs` 的首次实现中完成，但又足够稳定，使未来的本地/远程/沙箱文件系统后端不需要改动面向模型的接口。同时应避免从参考系统中照搬所有选项。Claude Code 和 OpenCode 暴露了类似的核心文件工具，但在命名风格和额外 flag 上有所不同；本 Agent Note 为原型选择最小的共有接口。
|
||||
该 schema 必须足够小，但又要足够稳定，使本地/远程/沙箱文件系统后端不需要改动面向模型的接口，并且必须避免从参考系统中照搬所有选项。Claude Code 和 OpenCode 暴露了类似的核心文件工具，但在命名风格和额外 flag 上有所不同；本决策选择最小的共有接口。
|
||||
|
||||
## 决策
|
||||
|
||||
`@deepseek-ai/dsh-tool-fs` 在首个文件系统工具套件中暴露以下三个面向模型的工具：
|
||||
|
||||
| 工具 | 我们的 schema | Claude Code | OpenCode | 说明 | 原型包含 |
|
||||
|---|---|---|---|---|---|
|
||||
| `read` | `read(file_path, offset?, limit?)` | `Read(file_path, offset?, limit?, pages?)` | `read(filePath, offset?, limit?)` | 仅文件；`offset` 从 1 开始；首版不支持图片、PDF 或多模态内容。 | 是 |
|
||||
| `write` | `write(file_path, content)` | `Write(file_path, content)` | `write(content, filePath)` | 创建或覆盖 UTF-8 文本。在默认 fs-policy 下，更新现有文件前必须先观测；创建新文件则不需要。 | 是 |
|
||||
| `edit` | `edit(file_path, old_string, new_string, replace_all?)` | `Edit(file_path, old_string, new_string, replace_all?)` | `edit(filePath, oldString, newString, replaceAll?)` | 字面字符串替换；默认要求唯一匹配；在默认 fs-policy 下必须先观测（任意窗口读取均算作观测）。 | 是 |
|
||||
| 工具 | 我们的 schema | Claude Code | OpenCode | 说明 |
|
||||
|---|---|---|---|---|
|
||||
| `read` | `read(file_path, offset?, limit?)` | `Read(file_path, offset?, limit?, pages?)` | `read(filePath, offset?, limit?)` | 仅文件；`offset` 从 1 开始；首版不支持图片、PDF 或多模态内容。 |
|
||||
| `write` | `write(file_path, content)` | `Write(file_path, content)` | `write(content, filePath)` | 创建或覆盖 UTF-8 文本。在默认 fs-policy 下，更新现有文件前必须先观测；创建新文件则不需要。 |
|
||||
| `edit` | `edit(file_path, old_string, new_string, replace_all?)` | `Edit(file_path, old_string, new_string, replace_all?)` | `edit(filePath, oldString, newString, replaceAll?)` | 字面字符串替换；默认要求唯一匹配；在默认 fs-policy 下必须先观测（任意窗口读取均算作观测）。 |
|
||||
|
||||
schema 使用 snake_case 字段名（`file_path`、`old_string`、`new_string`、`replace_all`），与 Claude Code 及现有 DeepSeek Harness 工具 schema 示例保持一致。消费方包将这些面向模型的名称转换为 `ctx.fs` 调用和 `fs/*` 事件分发。
|
||||
schema 使用 snake_case 字段名（`file_path`、`old_string`、`new_string`、`replace_all`），与 Claude Code 及现有 DeepSeek Harness 工具 schema 示例保持一致。Consumer 包将这些面向模型的名称转换为 `ctx.fs` 调用和 `fs/*` 事件分发。
|
||||
|
||||
## 工具 schema
|
||||
|
||||
@@ -66,11 +66,11 @@ schema 不将 `expected_hash`、`expected_version` 或 `create_only` 作为面
|
||||
|
||||
`edit` 要求同一执行上下文先前观测过该文件（任何窗口化的 read 都算——授权取决于观测到的版本是否仍为最新，而不要求查看全文），或该上下文先前对该文件执行过 write/edit。`dsh-fs-policy` 策略插件推导所有者，并将记录的版本作为陈旧版本防护提供；提供方的变更锁会强制执行该防护。
|
||||
|
||||
首次实现拒绝 Codex 风格的 patch 语法和多模式 edit API。它使用一种严格的字面替换模式，使面向模型的契约保持简单，并让后端掌控精确匹配、重复匹配、行尾和陈旧版本的语义。
|
||||
首次实现拒绝 Codex 风格的 patch 语法和多模式 edit API。它使用一种严格的字面替换模式，使面向模型的约定保持简单，并让后端掌控精确匹配、重复匹配、行尾和陈旧版本的语义。
|
||||
|
||||
## 结果形状
|
||||
|
||||
首次实现曾将 `ContentBlock[]` 格式化逻辑放在 `execute` 中。[规范工具输出契约](../architecture/2026-07-20-canonical-tool-output-contract.md)如今将 `ctx.fs` 的结果事实保留为工具经校验的值，并通过 `output.render` 派生相同的模型文本；文件状态的记录/刷新仍归 `ctx.fs` 所有。
|
||||
首次实现曾将 `ContentBlock[]` 格式化逻辑放在 `execute` 中。[规范工具输出约定](../architecture/2026-07-20-canonical-tool-output-contract.md)如今将 `ctx.fs` 的结果事实保留为工具经校验的值，并通过 `output.render` 派生相同的模型文本；文件状态的记录/刷新仍归 `ctx.fs` 所有。
|
||||
|
||||
默认原生投影：
|
||||
|
||||
@@ -99,7 +99,7 @@ schema 测试固定每个工具的必填/可选参数集、空 `old_string` 拒
|
||||
|
||||
## 曾考虑的替代方案
|
||||
|
||||
- **Codex 风格的 patch 语法或多模式 edit API**：否决。一种严格的字面替换模式使面向模型的契约保持简单，并让后端掌控精确匹配、重复匹配、行尾和陈旧版本的语义。
|
||||
- **Codex 风格的 patch 语法或多模式 edit API**：否决。一种严格的字面替换模式使面向模型的约定保持简单，并让后端掌控精确匹配、重复匹配、行尾和陈旧版本的语义。
|
||||
- **camelCase 参数名（OpenCode 风格）**：snake_case 与 Claude Code 及现有 harness 工具 schema 示例一致，且命名一旦发布即成为公开接口。
|
||||
- **面向模型的 `expected_hash` / `expected_version` / `create_only` 参数**：否决。陈旧检查由后端产生的版本和策略插件的观测状态驱动，从不依赖模型复制的脆弱令牌。
|
||||
|
||||
@@ -109,4 +109,4 @@ schema 测试固定每个工具的必填/可选参数集、空 `old_string` 拒
|
||||
|
||||
**v1 中没有显式的面向模型的陈旧版本防护。** schema 不要求模型提供 expected hash/version。这是有意为之：陈旧检查来自后端产生的版本和 `dsh-fs-policy` 插件的观测状态，而非模型复制的脆弱令牌。文件系统安全失败通过 `dsh-fs` 拥有的结构化 `FsError` 代码浮现，而非模型提供的版本字段。
|
||||
|
||||
**命名成为公开接口。** 一旦发布，将 `file_path` 改为 `filePath` 或 `old_string` 改为 `oldString` 会导致提示词、示例和下游客户端随之改动。本 Agent Note 预先选择 snake_case，并将其视为稳定的面向模型的契约。
|
||||
**命名成为公开接口。** 一旦发布，将 `file_path` 改为 `filePath` 或 `old_string` 改为 `oldString` 会导致提示词、示例和下游客户端随之改动。本 Agent Note 预先选择 snake_case，并将其视为稳定的面向模型的约定。
|
||||
|
||||
@@ -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/2026-06-18-compaction-capability-seam.md
|
||||
2026-06-18-compaction-capability-seam.md: 26e6e2468c7bea661d85c8fb994adf8b109105ee
|
||||
2026-06-18-compaction-capability-seam.zh.md: 8f9cd1f6bc31e648a5b923e816cad75ebc1a0bd8
|
||||
2026-06-18-compaction-capability-seam.md: 83f224aef50eb02712ac095da0cabf552399a9a6
|
||||
2026-06-18-compaction-capability-seam.zh.md: 12cf2498535d77dcf1a718b841a751bccadfdf1c
|
||||
|
||||
@@ -8,13 +8,13 @@ English | [中文](2026-06-18-compaction-capability-seam.zh.md)
|
||||
|
||||
A long-running agent conversation grows without bound. As the event log accumulates turns, the derived message history eventually approaches the model's context window — the model then truncates mid-response (`max-tokens`) or degrades. **Compaction** is the mitigation: replace a run of older history with a concise summary, keeping recent context intact.
|
||||
|
||||
The [session surface](../architecture/2026-06-18-session-surface.md) was built as the foundation for exactly this — an ordered projection over the event log with a `surfaceOp: { op: 'replace', start, end }` operation purpose-built to shadow a range of entries and insert a replacement, with `sourceEventSeqs` recording provenance so the decision replays deterministically. What remained was the plugin that *decides what to compact and produces the summary*.
|
||||
The [session surface](../architecture/2026-06-18-session-surface.md) was built as the foundation for exactly this — an ordered projection over the event log with a `surfaceOp: { op: 'replace', start, end }` operation purpose-built to shadow a range of entries and insert a replacement, with `sourceEventSeqs` listing every source event so replay can validate that the replacement cites every event it removes. What remained was the plugin that *decides what to compact and produces the summary*.
|
||||
|
||||
Two forces shape the design. First, compaction policy and reusable token measurement vary independently: measurement belongs to the LLM-family [`ctx.tokenMeter` service](../architecture/2026-07-15-replay-token-meter-service.md), while summarization can be a model call, a template, or a remote service. Second, `SurfaceEventType` is closed to the message-producing event types (`user/message`, `assistant/message`, `tool/result`); only those may carry `surfaceOp`. A bespoke `compaction/*` event therefore **cannot** itself appear on the surface — the compiler and Session's always-on append/seed boundary reject `surfaceOp` on it.
|
||||
|
||||
## Decision
|
||||
|
||||
### Compaction is a capability seam, split interface / implementation
|
||||
### Compaction is a capability seam with separate Service Definition and Service provider roles
|
||||
|
||||
Per the [capability-seams Agent Note](../architecture/2026-06-13-capability-seams.md), compaction ships as separate packages so the contract, the algorithm, and (later) the consumer surface evolve independently:
|
||||
|
||||
@@ -25,15 +25,15 @@ Per the [capability-seams Agent Note](../architecture/2026-06-13-capability-seam
|
||||
|
||||
### The contract depends on `dsh-session` and `dsh-llm` — a deliberate deviation
|
||||
|
||||
The capability-seams Agent Note states the interface package "depends only on cordis" (true of `dsh-bash`, whose vocabulary is self-contained). Compaction **cannot** honor that: its verbs act on an agent-owned `Session` (`compactRegion(start, end, agent)`) and its output uses the content vocabulary (`CompactionResult.summary: ContentBlock[]`). There is no way to express the contract without naming `Session`/`SessionEvent` (from `dsh-session`) and `ContentBlock` (from `dsh-llm`).
|
||||
The capability-seams Agent Note states the Service Definition package "depends only on cordis" (true of `dsh-bash`, whose vocabulary is self-contained). Compaction **cannot** honor that: its verbs act on an agent-owned `Session` (`compactRegion(start, end, agent)`) and its output uses the content vocabulary (`CompactionResult.summary: ContentBlock[]`). There is no way to express the contract without naming `Session`/`SessionEvent` (from `dsh-session`) and `ContentBlock` (from `dsh-llm`).
|
||||
|
||||
This is not a coupling smell — it is the contract's domain. The "only cordis" guidance was always shorthand for "the interface depends only on what the contract genuinely names, and never on an implementation." `dsh-session` and `dsh-llm` are themselves interface/vocabulary packages, not implementations; `dsh-compact` still imports no backend. The seam's real invariant — *consumers and implementations evolve independently behind an abstract service* — holds intact.
|
||||
|
||||
### Three abstract operations, algorithm in the backend
|
||||
|
||||
An earlier draft put the full algorithm (the retention walk, token-summing, text extraction) as concrete methods on the interface. That recouples the contract to one strategy: a backend that wants a different retention policy or event sequence would have to fight inherited concrete code. Making all three operations abstract puts every *how* decision in the backend and keeps the interface a statement of *what*. Token measurement is not a compaction hook at all; the singleton service lets multiple consumers share one per-session replay fold.
|
||||
Putting the full algorithm (the retention walk, token-summing, text extraction) as concrete methods on the interface recouples the contract to one strategy: a backend that wants a different retention policy or event sequence would have to fight inherited concrete code. Making all three operations abstract puts every *how* decision in the backend and keeps the interface a statement of *what*. Token measurement is not a compaction hook at all; the singleton service lets multiple consumers share one per-session replay fold.
|
||||
|
||||
`compactIfNeeded(agent, trigger, signal)` takes an explicit `'pressure' | 'context-overflow'` trigger and cancellation. It reads only the latest durable routed request; no header means no work, while any routed provider/model target uses the singleton estimator. `compactNow(agent, signal)` requires an idle agent and performs one useful balanced reduction even below pressure, returning `null` without writes when none exists. `compactRegion(start, end, agent, signal?)` uses `agent.session` as its single session identity and keeps an optional signal for explicit callers. The default summarizer resolves its target from explicit config, the latest logged routed target, then agent options, and records the provider/model pair after any `llm/stream` routing. It replays the routed request's prefix and appends the compaction directive as a trailing user message so the provider's warm KV cache is reused — see the [summary prefix-cache Agent Note](../bug-fix/2026-07-21-compaction-summary-prefix-cache-reuse.md). The call sets the provider-neutral `GenerateOptions.purpose` to `compaction`; adapters may map that purpose to model-hidden transport metadata, and the DeepSeek adapter sends `x-deepseek-harness-compact: 1`.
|
||||
`compactIfNeeded(agent, trigger, signal)` takes an explicit `'pressure' | 'context-overflow'` trigger and cancellation. It reads only the latest durable routed request; no header means no work, while any routed provider/model target uses the singleton estimator. `compactNow(agent, signal)` requires an idle agent and performs one useful balanced reduction even below pressure, returning `null` without writes when none exists. `compactRegion(start, end, agent, signal?)` uses `agent.session` as its single session identity and keeps an optional signal for explicit callers. The default summarizer resolves its target from explicit config, the latest logged routed target, then agent options, and records the provider/model pair after any `llm/stream` routing. It replays the routed request's prefix and appends the compaction directive as a trailing user message so the provider's warm KV cache is reused — see the [summary prefix-cache Agent Note](../bug-fix/2026-07-21-compaction-summary-prefix-cache-reuse.md). The result carries `llmStreamCall: true` because it consumed exactly one call through this context's LLM service; a subclass sets that marker only under the same condition, since retained `rawOutput` alone does not identify the call path. The call sets the provider-neutral `GenerateOptions.purpose` to `compaction`; adapters may map that purpose to model-hidden transport metadata, and the DeepSeek adapter sends `x-deepseek-harness-compact: 1`.
|
||||
|
||||
### Automatic pressure runs after successful durable step work
|
||||
|
||||
@@ -71,12 +71,12 @@ Auto-compaction always starts at the surface head, merging the prior checkpoint
|
||||
|
||||
### Surface replacement: `compact/*` events are log-only; one `user/message` carries the summary
|
||||
|
||||
Because `SurfaceEventType` is closed, the summary cannot ride on a `compact/*` event. The backend instead appends a **single `user/message`** with `source: COMPACT_CHECKPOINT_SOURCE` and `surfaceOp: { op: 'replace', start, end }` whose `content` is the (framed) summary and whose `sourceEventSeqs` covers the shadowed entries *and* the bookkeeping events. The interface exports that source and `isCompactCheckpointSource()` so consumers recognize a persisted or cloned checkpoint without depending on backend package identity. The `compact/*` events are pure log records (lock + provenance). The surface mutation sits **inside** the lock — `compact/end` is the last event appended:
|
||||
Because `SurfaceEventType` is closed, the summary cannot ride on a `compact/*` event. The backend instead appends a **single `user/message`** with `source: COMPACT_CHECKPOINT_SOURCE` and `surfaceOp: { op: 'replace', start, end }` whose `content` is the (framed) summary and whose `sourceEventSeqs` covers the shadowed entries *and* the bookkeeping events. The interface exports that source and `isCompactCheckpointSource()` so consumers recognize a persisted or cloned checkpoint without depending on backend package identity. The `compact/*` events record the lock, summary, selected range, shadowed seqs, token count, and model call without joining the surface. The surface mutation sits **inside** the lock — `compact/end` is the last event appended:
|
||||
|
||||
```
|
||||
compact/start → log-only. Acquires the lock.
|
||||
[summarize older range via the backend]
|
||||
compact/summary → log-only. Provenance: raw summary, range, shadowed seqs, token count.
|
||||
compact/summary → log-only. Records the raw summary, local-call marker, range, shadowed seqs, and token count.
|
||||
user/message → canonical checkpoint source + surfaceOp { op:'replace', start, end }.
|
||||
THE surface mutation (framed summary).
|
||||
deriveMessages() renders it as a user-role message.
|
||||
@@ -93,7 +93,7 @@ The basic backend wraps the summary as established checkpoint context and tags i
|
||||
|
||||
The `compact/start … compact/end` bracket is justified by two roles:
|
||||
|
||||
1. **Crash-detectable orphan + provenance** (primary). Summarization is a slow model call persisted *after* `compact/start`. A crash mid-summarization leaves a `compact/start` with no matching `compact/end` — a detectable orphan. Releasing the lock last (rather than first) converts the crash window from *silent corruption* into that detectable orphan.
|
||||
1. **Crash-detectable orphan plus recorded summary inputs** (primary). Summarization is a slow model call persisted *after* `compact/start`. A crash mid-summarization leaves a `compact/start` with no matching `compact/end` — a detectable orphan. Releasing the lock last (rather than first) converts the crash window from *silent corruption* into that detectable orphan.
|
||||
2. **Prevents concurrent compaction.** Every automatic, manual, and explicit-range entry point refuses a live unmatched `compact/start`. The bracket is the single lock; no process-local mutex duplicates it.
|
||||
|
||||
The lock excludes another compaction, not unrelated facts. Its markers are time points rather than an exclusive container, so durable inbox splices may appear between a standalone manual start and end. Automatic work requires whole-surface stability inside its turn. Manual work revalidates only the selected positional span, letting append-only context outside it remain visible after replacement.
|
||||
@@ -119,10 +119,10 @@ The lifecycle boundary makes crash state unambiguous:
|
||||
## Consequences
|
||||
|
||||
- **Packages**: `packages/compact/compact` supplies the interface, `compact-basic` supplies the backend, `compact-tool-result-prune` supplies optional deterministic rewriting, and `command-compact` supplies human `/compact`. `packages/llm/token-meter` owns replay-aware measurement independently.
|
||||
- **Automatic seams**: `agent/pre-step` (`@mode waterfall`) handles pressure before request derivation and `agent/request-error` (`@mode waterfall`) handles final request failures after the failed step closes. The pre-step payload carries the claimed batch, turn, step, and signal (see the [payload-object events decision](../architecture/2026-08-06-agent-event-payload-objects.md)), with no compaction-only prompt/prefix payload.
|
||||
- **Automatic extension points**: `agent/pre-step` (`@mode waterfall`) handles pressure before request derivation and `agent/request-error` (`@mode waterfall`) handles final request failures after the failed step closes. The pre-step payload carries the claimed batch, turn, step, and signal (see the [payload-object events decision](../architecture/2026-08-06-agent-event-payload-objects.md)), with no compaction-only prompt/prefix payload.
|
||||
- **`SessionEventMap`** gains `compact/start` / `compact/summary` / `compact/end` by declaration merging (merge-extensible); `SurfaceEventType` is **not** touched. These are session events, not cordis `Events`, so the event-taxonomy gate needs no entry.
|
||||
- **`dsh-compact`** owns `COMPACT_CHECKPOINT_SOURCE`, `isCompactCheckpointSource(source)`, `toolPairingBalancedBefore(session, seq)`, and `toolPairingBalancedAfter(session, seq)`. The marker identifies replacement summaries across backend implementations. The cached surface-edge checks prevent `compactRegion` and `compactIfNeeded` from splitting a tool-call/result pair, validate current membership by seq, answer both edges from one per-cut balance sequence, and reject stale or missing seqs and orphan results.
|
||||
- **`dsh-session`** validates positional replacement, complete provenance, and content-only single-node `tool/result` rewrites through its one surface manager. Its invariant companion treats fresh appended tool results as executions that require an open step and pending call, while the compaction companion owns numeric-turn versus standalone-null bracket relations.
|
||||
- **`dsh-session`** validates positional replacement, complete cited source-event coverage, and content-only single-node `tool/result` rewrites through its one surface manager. Its invariant companion treats fresh appended tool results as executions that require an open step and pending call, while the compaction companion owns numeric-turn versus standalone-null bracket relations.
|
||||
- **Wiring**: `examples/tui-agent/cordis.yml` loads zero-config `dsh-token-meter`, `dsh-compact-tool-result-prune`, `dsh-compact-basic`, then `dsh-command-compact`; service-wide defaults make the composition usable without repeated numeric policy.
|
||||
|
||||
## Testing
|
||||
@@ -131,4 +131,4 @@ The lifecycle boundary makes crash state unambiguous:
|
||||
- **Loop:** Tests pin pre-step after the preceding `step/end` and before the next `step/start`, actual `agent/request` routing, closed failed steps, fresh retry numbering, and complete thrown/in-band overflow → compaction → reconstructed retry composition.
|
||||
- **Manual:** Maintenance serialization, marker ordering, injection retention, live/stale orphan classification, cancellation, close/flush failures, command mapping, and the queued TUI journey are pinned without a model key.
|
||||
- **With-key e2e:** A real model and bash session with lowered limits triggers compaction, records a complete `compact/start…end` pair, shrinks the surface, and finishes the task.
|
||||
- **Snapshot gap:** Runaway-turn compaction cannot yet replay because the summarization call records no `assistant/chunk` events or `sessionId`; interleaved summarization-call replay remains follow-up work.
|
||||
- **Snapshot:** The assembled context-overflow scenario derives the auxiliary call from `compact/summary` only when `llmStreamCall: true` proves that the local LLM service consumed it; canonical reconstructed blocks pin the complete recovery without provider delta partitioning.
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
# Agent Note: 压缩作为能力 seam（抽象契约 + 基础后端）
|
||||
# Agent Note: 压缩作为能力 seam（抽象约定 + 基础后端）
|
||||
|
||||
Status: implemented
|
||||
|
||||
@@ -8,32 +8,32 @@ Status: implemented
|
||||
|
||||
长时间运行的 agent（智能体）对话会无限增长。随着事件日志不断累积轮次，派生出的消息历史最终逼近模型的上下文窗口，模型随即截断响应（`max-tokens`）或性能退化。**上下文压缩（context compaction）** 是对此的缓解手段：用一段简洁的摘要替换一批较早的历史，保持近期上下文完整。
|
||||
|
||||
[会话接口面](../architecture/2026-06-18-session-surface.md)正是为此而构建的基础设施：一份建立在事件日志之上的有序投影，带有专门设计的 `surfaceOp: { op: 'replace', start, end }` 操作，用于遮蔽一段条目并插入替换内容，`sourceEventSeqs` 记录溯源信息以便决策可确定性地回放。剩下的是那个*决定压缩什么、并产出摘要*的插件。
|
||||
[会话接口面](../architecture/2026-06-18-session-surface.md)正是为此而构建的基础设施：一份建立在事件日志之上的有序投影，带有专门设计的 `surfaceOp: { op: 'replace', start, end }` 操作，用于遮蔽一段条目并插入替换内容，`sourceEventSeqs` 列出每个来源事件，使回放可以验证替换是否引用了它移除的每个事件。剩下的是那个*决定压缩什么、并产出摘要*的插件。
|
||||
|
||||
两股力量塑造了设计。第一，压缩策略与可复用的 token 测量独立变化：测量归 LLM 系列的 [`ctx.tokenMeter` 服务](../architecture/2026-07-15-replay-token-meter-service.md)所有，摘要生成则可以使用模型调用、模板或远程服务。第二，`SurfaceEventType` 封闭为产生消息的事件类型（`user/message`、`assistant/message`、`tool/result`）；只有这些类型可以携带 `surfaceOp`。因此一个专用的 `compaction/*` 事件**不能**出现在 surface 上，编译器与 Session 始终启用的 append/seed 边界都会拒绝在其上附加 `surfaceOp`。
|
||||
|
||||
## 决策
|
||||
|
||||
### 压缩是一个能力 seam，接口与实现分离
|
||||
### 压缩是一个能力 seam，Service Definition 与 Service provider 角色分离
|
||||
|
||||
遵循[能力 seam Agent Note](../architecture/2026-06-13-capability-seams.md)，压缩以独立包发布，使契约、算法和（后续的）消费方 surface 各自独立演进：
|
||||
遵循[能力 seam Agent Note](../architecture/2026-06-13-capability-seams.md)，压缩以独立包发布，使约定、算法和（后续的）消费方 surface 各自独立演进：
|
||||
|
||||
1. **接口** — `@deepseek-ai/dsh-compact`：抽象 `CompactService`，拥有 `ctx.compact` 键、`CompactionResult` 词汇、`compact/*` 会话事件、手动失败分类体系以及规范的检查点消息来源。它将 `compactIfNeeded()`、`compactNow()` 和 `compactRegion()` 声明为**抽象方法**——契约说明压缩*做什么*，而非*怎么做*。
|
||||
1. **接口** — `@deepseek-ai/dsh-compact`：抽象 `CompactService`，拥有 `ctx.compact` 键、`CompactionResult` 词汇、`compact/*` 会话事件、手动失败分类体系以及规范的检查点消息来源。它将 `compactIfNeeded()`、`compactNow()` 和 `compactRegion()` 声明为**抽象方法**——约定说明压缩*做什么*，而非*怎么做*。
|
||||
2. **实现** — `@deepseek-ai/dsh-compact-basic`：具体的 `BasicCompactService`，消费 `ctx.tokenMeter`，并拥有尾→头保留遍历、通过 `ctx.llm.stream()` 生成摘要、surface 替换、锁、步骤前压力处理和规范的上下文溢出恢复。`summarize()` 是其唯一的子类钩子；计价与回放仍归 meter 所有。
|
||||
3. **无模型配套服务** — `@deepseek-ai/dsh-compact-tool-result-prune`：一个具体的可选服务，在后端选择摘要范围之前，重写当前过大的 `tool/result` 节点。它不是第二种压缩实现，也不实现 `CompactService`。
|
||||
4. **面向用户的消费方** — `@deepseek-ai/dsh-command-compact` 通过 `ctx.commands` 注册无参数 `/compact`，并调用后端无关的 `compactNow()` 操作。它是供用户直接控制的命令，不是面向模型的工具。
|
||||
|
||||
### 契约依赖 `dsh-session` 和 `dsh-llm`——有意为之的偏离
|
||||
### 约定依赖 `dsh-session` 和 `dsh-llm`——有意为之的偏离
|
||||
|
||||
能力 seam Agent Note 规定接口包「仅依赖 cordis」（对 `dsh-bash` 成立，因为其词汇是自包含的）。压缩**无法**遵守这一点：它的动词作用于 agent 所有的 `Session`（`compactRegion(start, end, agent)`），其输出使用内容词汇（`CompactionResult.summary: ContentBlock[]`）。不引用 `Session`/`SessionEvent`（来自 `dsh-session`）和 `ContentBlock`（来自 `dsh-llm`），契约就无法表达。
|
||||
能力 seam Agent Note 规定 Service Definition 包「仅依赖 cordis」（对 `dsh-bash` 成立，因为其词汇是自包含的）。压缩**无法**遵守这一点：它的动词作用于 agent 所有的 `Session`（`compactRegion(start, end, agent)`），其输出使用内容词汇（`CompactionResult.summary: ContentBlock[]`）。不引用 `Session`/`SessionEvent`（来自 `dsh-session`）和 `ContentBlock`（来自 `dsh-llm`），约定就无法表达。
|
||||
|
||||
这不是耦合异味，而是契约的领域所在。「仅 cordis」的指导原则一直是「接口仅依赖契约真正需要命名的东西，绝不依赖实现」的简写。`dsh-session` 和 `dsh-llm` 本身是接口/词汇包，不是实现；`dsh-compact` 仍然不导入任何后端。seam 的真正不变式——*消费方和实现在抽象服务背后独立演进*——完好无损。
|
||||
这不是耦合异味，而是约定的领域所在。「仅 cordis」的指导原则一直是「接口仅依赖约定真正需要命名的东西，绝不依赖实现」的简写。`dsh-session` 和 `dsh-llm` 本身是接口/词汇包，不是实现；`dsh-compact` 仍然不导入任何后端。seam 的真正不变式——*消费方和实现在抽象服务背后独立演进*——完好无损。
|
||||
|
||||
### 三个抽象操作，算法在后端
|
||||
|
||||
早期草案将完整算法（保留遍历、token 求和、文本提取）作为接口上的具体方法。这会将契约重新耦合到一种策略：想要不同保留策略或事件排序的后端必须与继承来的具体代码对抗。将三个操作都设为抽象，把所有*怎么做*的决策放在后端，并让接口保持为*做什么*的声明。token 测量根本不是压缩钩子；单例服务使多个消费方能够共享逐会话的回放折叠。
|
||||
将完整算法（保留遍历、token 求和、文本提取）作为接口上的具体方法，会将约定重新耦合到一种策略：想要不同保留策略或事件排序的后端必须与继承来的具体代码对抗。将三个操作都设为抽象，把所有*怎么做*的决策放在后端，并让接口保持为*做什么*的声明。token 测量根本不是压缩钩子；单例服务使多个消费方能够共享逐会话的回放折叠。
|
||||
|
||||
`compactIfNeeded(agent, trigger, signal)` 接受显式的 `'pressure' | 'context-overflow'` 触发原因与取消信号。它只读取最新的持久化已路由请求；没有 header 就不执行工作，任何已路由的提供方/模型目标都使用单例估算器。`compactNow(agent, signal)` 要求 agent 处于 idle，即使未达到压力也进行一次有效的平衡缩减；不存在这种范围时返回 `null`，且不写入任何内容。`compactRegion(start, end, agent, signal?)` 将 `agent.session` 作为唯一会话身份，并为显式调用方保留可选 signal。默认摘要器依次从显式配置、最新记录的已路由目标和 agent 选项解析目标，并在任何 `llm/stream` 路由后记录提供方/模型对。它回放已路由请求的前缀，并将压缩指令追加为尾部 user 消息，从而复用提供方的热 KV cache；见[摘要前缀缓存 Agent Note](../bug-fix/2026-07-21-compaction-summary-prefix-cache-reuse.md)。该调用将提供方无关的 `GenerateOptions.purpose` 设为 `compaction`；适配器可以将此用途映射为对模型隐藏的传输元数据，DeepSeek 适配器会发送 `x-deepseek-harness-compact: 1`。
|
||||
`compactIfNeeded(agent, trigger, signal)` 接受显式的 `'pressure' | 'context-overflow'` 触发原因与取消信号。它只读取最新的持久化已路由请求；没有 header 就不执行工作，任何已路由的提供方/模型目标都使用单例估算器。`compactNow(agent, signal)` 要求 agent 处于 idle，即使未达到压力也进行一次有效的平衡缩减；不存在这种范围时返回 `null`，且不写入任何内容。`compactRegion(start, end, agent, signal?)` 将 `agent.session` 作为唯一会话身份，并为显式调用方保留可选 signal。默认摘要器依次从显式配置、最新记录的已路由目标和 agent 选项解析目标，并在任何 `llm/stream` 路由后记录提供方/模型对。它回放已路由请求的前缀，并将压缩指令追加为尾部 user 消息，从而复用提供方的热 KV cache；见[摘要前缀缓存 Agent Note](../bug-fix/2026-07-21-compaction-summary-prefix-cache-reuse.md)。该结果携带 `llmStreamCall: true`，因为生成它时恰好通过此上下文的 LLM 服务发起了一次调用；只有满足相同条件时，子类才设置该标记，因为单有保留的 `rawOutput` 并不能判定调用路径。该调用将提供方无关的 `GenerateOptions.purpose` 设为 `compaction`；适配器可以将此用途映射为对模型隐藏的传输元数据，DeepSeek 适配器会发送 `x-deepseek-harness-compact: 1`。
|
||||
|
||||
### 成功的持久步骤工作完成后运行自动压力检查
|
||||
|
||||
@@ -71,12 +71,12 @@ retry → next numbered step/start ⟵ derives from the replacement surface
|
||||
|
||||
### Surface 替换：`compact/*` 事件仅存在于日志；一条 `user/message` 承载摘要
|
||||
|
||||
由于 `SurfaceEventType` 是封闭的，摘要不能搭载在 `compact/*` 事件上。后端改为追加一条**单独的 `user/message`**，带有 `source: COMPACT_CHECKPOINT_SOURCE` 和 `surfaceOp: { op: 'replace', start, end }`；其 `content` 是（带框架的）摘要，`sourceEventSeqs` 覆盖被遮蔽的条目*和*簿记事件。接口导出该来源和 `isCompactCheckpointSource()`，使消费方无需依赖后端包身份，即可识别持久化或克隆得到的检查点。`compact/*` 事件是纯日志记录（锁 + 溯源信息）。surface 变更位于锁**内部**，`compact/end` 是最后追加的事件：
|
||||
由于 `SurfaceEventType` 是封闭的，摘要不能搭载在 `compact/*` 事件上。后端改为追加一条**单独的 `user/message`**，带有 `source: COMPACT_CHECKPOINT_SOURCE` 和 `surfaceOp: { op: 'replace', start, end }`；其 `content` 是（带框架的）摘要，`sourceEventSeqs` 覆盖被遮蔽的条目*和*簿记事件。接口导出该来源和 `isCompactCheckpointSource()`，使消费方无需依赖后端包身份，即可识别持久化或克隆得到的检查点。`compact/*` 事件记录锁、摘要、选中区间、被遮蔽的 seq、token 数和模型调用，但不加入 surface。surface 变更位于锁**内部**，`compact/end` 是最后追加的事件：
|
||||
|
||||
```
|
||||
compact/start → log-only. Acquires the lock.
|
||||
[summarize older range via the backend]
|
||||
compact/summary → log-only. Provenance: raw summary, range, shadowed seqs, token count.
|
||||
compact/summary → log-only. Records the raw summary, local-call marker, range, shadowed seqs, and token count.
|
||||
user/message → canonical checkpoint source + surfaceOp { op:'replace', start, end }.
|
||||
THE surface mutation (framed summary).
|
||||
deriveMessages() renders it as a user-role message.
|
||||
@@ -93,7 +93,7 @@ compact/end → log-only. Releases the lock (carries `error` on a recoverab
|
||||
|
||||
`compact/start … compact/end` 标记对承担两项职责：
|
||||
|
||||
1. **可检测的崩溃孤儿 + 来源追溯**（首要）。摘要生成是一次慢速模型调用，持久化在 `compact/start` *之后*。摘要生成中途崩溃会留下一个没有匹配 `compact/end` 的 `compact/start`——一个可检测的孤儿。最后释放锁（而非最先）将崩溃窗口从*静默损坏*转变为可检测的孤儿。
|
||||
1. **可检测的崩溃孤儿 + 已记录的摘要输入**（首要）。摘要生成是一次慢速模型调用，持久化在 `compact/start` *之后*。摘要生成中途崩溃会留下一个没有匹配 `compact/end` 的 `compact/start`——一个可检测的孤儿。最后释放锁（而非最先）将崩溃窗口从*静默损坏*转变为可检测的孤儿。
|
||||
2. **防止并发压缩。** 每个自动、手动和显式范围入口点都会拒绝活动的未匹配 `compact/start`。该标记对就是唯一的锁；没有进程本地 mutex 重复承担同一职责。
|
||||
|
||||
该锁只排除另一项压缩，不排除无关事实。其标记是时间点，而不是排他的容器，因此持久 inbox splice 可以出现在独立手动 start 与 end 之间。自动工作要求其轮次内的整个 surface 保持稳定。手动工作只重新验证所选位置 span，使其外部的仅追加上下文在替换后保持可见。
|
||||
@@ -110,7 +110,7 @@ compact/end → log-only. Releases the lock (carries `error` on a recoverab
|
||||
|
||||
## 曾考虑的替代方案
|
||||
|
||||
- **完整算法作为接口的具体方法**——否决，因为它将契约重新耦合到一种保留策略。三个操作都是抽象的；可复用测量属于单独的 LLM 系列服务，`summarize()` 是 basic 唯一的钩子。
|
||||
- **完整算法作为接口的具体方法**——否决，因为它将约定重新耦合到一种保留策略。三个操作都是抽象的；可复用测量属于单独的 LLM 系列服务，`summarize()` 是 basic 唯一的钩子。
|
||||
- **在 `agent/request` 或压缩专属的 loop 回调上执行压缩**——否决，因为前者观察的是临时请求，后者会将通用生命周期耦合到压缩策略。对先前持久请求进行 pre-step 回放，再加上规范溢出恢复，即可覆盖成功和被拒绝的调用。
|
||||
- **`compact` 布尔值或无类型的请求元数据 map**——否决，因为多个辅助调用种类会变成互斥标志，而开放 map 会丢弃由编译器检查的词汇。一个类型化的 `purpose` 判别字段可以扩展其他调用种类，而无需再为 `GenerateOptions` 添加字段。
|
||||
- **单独的 `compact/error` 事件**——否决：`compact/end` 保留 `error?` 字段，与 `tool/result` 的自包含错误一致——一个事件即可区分成功与失败，无需关联兄弟事件。
|
||||
@@ -119,10 +119,10 @@ compact/end → log-only. Releases the lock (carries `error` on a recoverab
|
||||
## 后果
|
||||
|
||||
- **包**：`packages/compact/compact` 提供接口，`compact-basic` 提供后端，`compact-tool-result-prune` 提供可选的确定性重写，`command-compact` 提供面向用户的 `/compact`。`packages/llm/token-meter` 独立拥有回放感知的测量。
|
||||
- **自动 seam**：`agent/pre-step`（`@mode waterfall`）在请求派生前处理压力，`agent/request-error`（`@mode waterfall`）处理失败步骤关闭后的最终请求失败。pre-step 的 payload 携带已领取批次、轮次、步骤与 signal（参见 [payload-object 事件决策](../architecture/2026-08-06-agent-event-payload-objects.md)），不携带压缩专属的提示词/前缀 payload。
|
||||
- **自动扩展点**：`agent/pre-step`（`@mode waterfall`）在请求派生前处理压力，`agent/request-error`（`@mode waterfall`）处理失败步骤关闭后的最终请求失败。pre-step 的 payload 携带已领取批次、轮次、步骤与 signal（参见 [payload-object 事件决策](../architecture/2026-08-06-agent-event-payload-objects.md)），不携带压缩专属的提示词/前缀 payload。
|
||||
- **`SessionEventMap`** 通过可合并扩展的声明合并获得 `compact/start` / `compact/summary` / `compact/end`；`SurfaceEventType` **未被**触及。这些是会话事件，不是 cordis `Events`，因此事件分类门禁无需新增条目。
|
||||
- **`dsh-compact`** 拥有 `COMPACT_CHECKPOINT_SOURCE`、`isCompactCheckpointSource(source)`、`toolPairingBalancedBefore(session, seq)` 与 `toolPairingBalancedAfter(session, seq)`。该标记用于跨后端实现识别替换摘要。带缓存的 surface 边缘检查会防止 `compactRegion` 和 `compactIfNeeded` 拆分工具调用/结果对，按 seq 校验当前成员关系，从每个切割点的一条平衡序列回答两侧边缘，并拒绝陈旧或缺失的 seq 与孤立结果。
|
||||
- **`dsh-session`** 通过唯一的 surface 管理器校验位置替换、完整溯源信息和仅内容的单节点 `tool/result` 重写。其不变式配套插件将新追加的工具结果视为执行，要求存在已打开的步骤与待处理调用，而压缩配套组件拥有数字轮次归属与独立 `null` 归属标记对之间的关系。
|
||||
- **`dsh-session`** 通过唯一的 surface 管理器校验位置替换、引用的来源事件是否覆盖完整，以及仅内容的单节点 `tool/result` 重写。其不变式配套插件将新追加的工具结果视为执行，要求存在已打开的步骤与待处理调用，而压缩配套组件拥有数字轮次归属与独立 `null` 归属标记对之间的关系。
|
||||
- **接线**：`examples/tui-agent/cordis.yml` 依次加载零配置的 `dsh-token-meter`、`dsh-compact-tool-result-prune`、`dsh-compact-basic`，然后加载 `dsh-command-compact`；服务级默认值使组合无需重复数值策略即可使用。
|
||||
|
||||
## 测试
|
||||
@@ -131,4 +131,4 @@ compact/end → log-only. Releases the lock (carries `error` on a recoverab
|
||||
- **循环测试：** 测试固定 pre-step 发生在前一个 `step/end` 之后、下一个 `step/start` 之前，使用实际 `agent/request` 路由，关闭失败步骤，分配新的重试编号，并覆盖完整的抛出/带内溢出 → 压缩 → 重建重试组合。
|
||||
- **手动测试：** 无需模型密钥即可固定 maintenance 串行化、标记顺序、注入保留、活动／陈旧未匹配标记分类、取消、闭合／flush 失败、命令映射以及排队 TUI 流程。
|
||||
- **带密钥 e2e：** 真实模型和 bash 会话在降低的限制下触发压缩，记录完整的 `compact/start…end` 对，缩小 surface，并完成任务。
|
||||
- **快照缺口：** 失控轮次压缩尚无法回放，因为摘要调用未记录 `assistant/chunk` 事件或 `sessionId`；交错摘要调用的回放仍是后续工作。
|
||||
- **快照：** 组装后的上下文溢出场景仅在 `llmStreamCall: true` 证明本地 LLM 服务执行了辅助调用时，才从 `compact/summary` 派生该调用；规范重建的块在不固定提供方增量切分的情况下固定完整恢复过程。
|
||||
|
||||
@@ -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/2026-06-21-subagent-capability-seam.md
|
||||
2026-06-21-subagent-capability-seam.md: 752e639b09ea2ac0ba19841ddfe38b15b44d22e9
|
||||
2026-06-21-subagent-capability-seam.zh.md: 6009aeda6773357a4217f8956fb510c2116bbe3f
|
||||
2026-06-21-subagent-capability-seam.md: 28ecf985db1289ce4f80570583eac6a051cd2c0b
|
||||
2026-06-21-subagent-capability-seam.zh.md: 5f349ddcacebe66c346976b822c9dcc65bda8d18
|
||||
|
||||
@@ -8,24 +8,24 @@ English | [中文](2026-06-21-subagent-capability-seam.zh.md)
|
||||
|
||||
## Problem
|
||||
|
||||
The harness has a long-deferred seam for **subagents** — an agent delegating work to another agent. The intent was sketched in the `Agent`/`AgentLoop` interfaces ([packages/core/agent/src/types.ts](../../../../packages/core/agent/src/types.ts), [packages/core/agent-loop/src/index.ts](../../../../packages/core/agent-loop/src/index.ts)): a creation option referencing a parent agent (fork = seed the child session with the parent's event log; spawn = fresh session), with the child returned as an `Agent` handle so steering and event subscription work uniformly. This Agent Note realizes that seam; the banner above lists what shipped.
|
||||
The harness has a long-deferred seam for **subagents** — an agent delegating work to another agent. The intent was sketched in the `Agent`/`AgentLoop` interfaces ([packages/core/agent/src/types.ts](../../../../packages/core/agent/src/types.ts), [packages/core/agent-loop/src/index.ts](../../../../packages/core/agent-loop/src/index.ts)): a creation option referencing a parent agent (fork = seed the child session with the parent's event log; spawn = fresh session), with the child returned as an `Agent` handle so steering and event subscription work uniformly.
|
||||
|
||||
The distinctive requirement — the one that shapes the whole design — is that **multiple subagent implementations must coexist at runtime**. A parent may want a cheap in-process child for a scoped subtask AND an isolated out-of-process child (over ACP) in the same session. The transports we foresee:
|
||||
The distinctive requirement — the one that shapes the whole design — is that **multiple subagent implementations must coexist at runtime**. A parent may want a cheap in-process child for a scoped subtask AND an isolated out-of-process child (over ACP) in the same session. The transports:
|
||||
|
||||
- **in-process** — a child concrete `Agent` on the same `Context` (the cheapest, and nearly free given the existing agent factory);
|
||||
- **ACP** — act as an ACP *client* driving another agent process (which can be another instance of ourselves);
|
||||
- **Codex app-server and Claude Code Agent SDK** — current one-shot siblings that apply the same named-provider seam to official product processes ([product-provider Agent Note](2026-08-04-claude-code-and-codex-subagent-backends.md));
|
||||
- **Codex app-server and Claude Code Agent SDK** — current one-shot siblings that apply the same named-provider contract to official product processes ([product-provider Agent Note](2026-08-04-claude-code-and-codex-subagent-backends.md));
|
||||
- later: **A2A** using the same out-of-process "start a child, prompt it, settle, cancel" shape.
|
||||
|
||||
## Alternatives considered
|
||||
|
||||
### Why not the bash seam shape
|
||||
|
||||
The bash seam ([capability seams](../architecture/2026-06-13-capability-seams.md)) registers exactly one `BashExecutor` per context; loading a second throws. That is correct for bash (one machine, one way to run a command) but wrong here: coexistence is the requirement. So the subagent service is a **named-provider registry** — each implementation registers under a unique name and a caller picks one by name — mirroring the **LLM adapter registry** (`LlmService.registerAdapter`), not the single-service bash executor. The seam is still three-package (interface / implementation / consumer); only the "one vs. many implementations" axis differs.
|
||||
The bash seam ([capability seams](../architecture/2026-06-13-capability-seams.md)) registers exactly one `BashExecutor` per context; loading a second throws. That is correct for bash (one machine, one way to run a command) but wrong here: coexistence is the requirement. So the subagent service is a **named-provider registry** — each implementation registers under a unique name and a caller picks one by name — mirroring the **LLM adapter registry** (`LlmService.registerAdapter`), not the single-service bash executor. The seam is still three-package (Service Definition / Service provider / Consumer); only the "one vs. many implementations" axis differs.
|
||||
|
||||
## Decision
|
||||
|
||||
### The three-package seam
|
||||
### The three-package boundary
|
||||
|
||||
A new package group `packages/subagent/`:
|
||||
|
||||
@@ -62,7 +62,7 @@ Each in-process subagent runs in its **own `Session`** (own id, `parentSession`
|
||||
|
||||
### Provider selection is config, not model-facing
|
||||
|
||||
`dsh-tool-subagent` binds to exactly one provider name (`Config.provider`); the model sees only `{ description, prompt }`. To expose more than one transport, load the tool plugin more than once, each bound to a different provider and a distinct `toolName` (the tool registry rejects a duplicate name). The *service* holds the multi-provider registry; the *tool* picks one — no provider/type parameter in the schema this cut.
|
||||
`dsh-tool-subagent` binds to exactly one provider name (`Config.provider`); the model sees only `{ description, prompt }`. To expose more than one transport, load the tool plugin more than once, each bound to a different provider and a distinct `toolName` (the tool registry rejects a duplicate name). The *service* holds the multi-provider registry; the *tool* picks one — the schema carries no provider/type parameter.
|
||||
|
||||
## Testing
|
||||
|
||||
@@ -72,5 +72,5 @@ Registry and tool tests replace only the nondeterministic child boundary with a
|
||||
|
||||
- **Recursion.** Without a bound, an in-process child can see the delegation tool and recurse. The in-process backends implement the optional absolute depth limit and scoped live-global `toolFilter`; ACP advertises both capabilities off and rejects such a request. The [subagent composition-controls Agent Note](2026-07-12-subagent-persona-tool-filter-and-depth.md) owns their exact semantics and security limits.
|
||||
- **Blocking the parent turn.** Foreground collection holds the parent's step open for the child's full duration. Background delegation uses the shared `ctx.tasks` runtime and generic `task_*` tools, the same collection mechanism as background bash; the subagent seam itself remains task-agnostic.
|
||||
- **Live progress.** This cut surfaces only lifecycle + final result; a per-chunk child→parent update stream is deferred with the background redesign.
|
||||
- **ACP client surface.** Proxying `fs`/`terminal` from the ACP child back to the parent (a shared-workspace mode) is future work; the first cut advertises neither, so the child self-serves in its own process.
|
||||
- **Live progress.** Only lifecycle + the final result surface; a per-chunk child→parent update stream is deferred with the background redesign.
|
||||
- **ACP client surface.** Proxying `fs`/`terminal` from the ACP child back to the parent (a shared-workspace mode) is future work; the backend advertises neither capability, so the child self-serves in its own process.
|
||||
|
||||
@@ -1,37 +1,37 @@
|
||||
# Agent Note: Subagent 能力 seam
|
||||
# Agent Note: subagent 能力 seam
|
||||
|
||||
Status: implemented
|
||||
|
||||
[English](2026-06-21-subagent-capability-seam.md) | 中文
|
||||
|
||||
> 完整 seam 已交付：`dsh-subagent` 接口与 `dsh-tool-subagent` 消费方；两个进程内后端（`dsh-subagent-spawn`、`dsh-subagent-fork`）；嵌套 agent 快照基础设施（[逐会话快照回放](../testing/2026-06-22-subagent-snapshot-replay.md)）；以及进程外的 ACP、Codex 与 Claude Code 后端（[ACP Agent Note](2026-06-22-acp-subagent-backend.md)、[产品提供方 Agent Note](2026-08-04-claude-code-and-codex-subagent-backends.md)）。
|
||||
> 完整 seam 已交付：`dsh-subagent` 接口与 `dsh-tool-subagent` 消费方；两个进程内后端（`dsh-subagent-spawn`、`dsh-subagent-fork`）；嵌套 agent（智能体）快照基础设施（[逐会话快照回放](../testing/2026-06-22-subagent-snapshot-replay.md)）；以及进程外的 ACP（Agent Client Protocol）、Codex 与 Claude Code 后端（[ACP Agent Note](2026-06-22-acp-subagent-backend.md)、[产品提供方 Agent Note](2026-08-04-claude-code-and-codex-subagent-backends.md)）。
|
||||
|
||||
## 问题
|
||||
|
||||
harness 有一个长期搁置的 seam 用于 **subagent**：一个 agent（智能体）将工作委派给另一个 agent。这一意图在 `Agent`/`AgentLoop` 接口中已有草案（[packages/core/agent/src/types.ts](../../../../packages/core/agent/src/types.ts)、[packages/core/agent-loop/src/index.ts](../../../../packages/core/agent-loop/src/index.ts)）：一个创建选项引用父 agent（fork = 用父会话的事件日志初始化子会话；spawn = 全新会话），子 agent 以 `Agent` 句柄返回，使 steering（中途引导）和事件订阅可以统一工作。本 Agent Note 实现了这个 seam；上方横幅列出了已交付的内容。
|
||||
harness 有一个长期搁置的 seam 用于 **subagent**：一个 agent 将工作委派给另一个 agent。这一意图在 `Agent`/`AgentLoop` 接口中已有草案（[packages/core/agent/src/types.ts](../../../../packages/core/agent/src/types.ts)、[packages/core/agent-loop/src/index.ts](../../../../packages/core/agent-loop/src/index.ts)）：一个创建选项引用父 agent（fork = 用父会话的事件日志初始化子会话；spawn = 全新会话），子 agent 以 `Agent` 句柄返回，使 steering（中途引导）和事件订阅可以统一工作。
|
||||
|
||||
决定整体设计走向的核心需求是：**多种 subagent 实现必须在运行时共存**。一个父 agent 可能在同一个会话中既需要一个廉价的进程内子 agent 处理有限范围的子任务，又需要一个隔离的进程外子 agent（通过 ACP（Agent Client Protocol））。我们预见的传输方式：
|
||||
决定整体设计走向的核心需求是：**多种 subagent 实现必须在运行时共存**。一个父 agent 可能在同一个会话中既需要一个廉价的进程内子 agent 处理有限范围的子任务，又需要一个隔离的进程外子 agent（通过 ACP）。传输方式：
|
||||
|
||||
- **进程内**：在同一个 `Context` 上创建一个具体的子 `Agent`（最廉价，且鉴于现有 agent 工厂几乎零成本）；
|
||||
- **ACP**：作为 ACP *客户端*驱动另一个 agent 进程（可以是自身的另一个实例）；
|
||||
- **Codex app-server 与 Claude Code Agent SDK**：当前的一次性兄弟提供方，将同一个命名提供方 seam 应用于官方产品进程（[产品提供方 Agent Note](2026-08-04-claude-code-and-codex-subagent-backends.md)）；
|
||||
- **Codex app-server 与 Claude Code Agent SDK**：当前的一次性同类提供方，将同一个命名提供方约定应用于官方产品进程（[产品提供方 Agent Note](2026-08-04-claude-code-and-codex-subagent-backends.md)）；
|
||||
- 后续：**A2A**，采用同样的进程外形态：「启动子 agent、发送提示词、结算、取消」。
|
||||
|
||||
## 曾考虑的替代方案
|
||||
|
||||
### 为何不采用 bash seam 的形状
|
||||
|
||||
bash seam（[能力 seam](../architecture/2026-06-13-capability-seams.md)）在每个上下文中只注册恰好一个 `BashExecutor`；加载第二个会抛异常。这对 bash 是正确的（一台机器、一种执行命令的方式），但对这里是错误的：共存才是需求。因此 subagent 服务是一个**命名提供方注册表**——每个实现以唯一名称注册，调用方按名称选择——镜像 **LLM（大语言模型）适配器注册表**（`LlmService.registerAdapter`），而非单服务的 bash 执行器。seam 仍然是由三个包构成的结构（接口 / 实现 / 消费方）；只是「一个 vs. 多个实现」这个维度不同。
|
||||
bash seam（[能力 seam](../architecture/2026-06-13-capability-seams.md)）在每个上下文中只注册恰好一个 `BashExecutor`；加载第二个会抛异常。这对 bash 是正确的（一台机器、一种执行命令的方式），但对这里是错误的：共存才是需求。因此 subagent 服务是一个**命名提供方注册表**——每个实现以唯一名称注册，调用方按名称选择——镜像 **LLM（大语言模型）适配器注册表**（`LlmService.registerAdapter`），而非单服务的 bash 执行器。seam 仍然是由三个包构成的结构（Service Definition / Service provider / Consumer）；只是「一个 vs. 多个实现」这个维度不同。
|
||||
|
||||
## 决策
|
||||
|
||||
### 由三个包构成的 seam
|
||||
### 由三个包构成的边界
|
||||
|
||||
新建包（package）组 `packages/subagent/`：
|
||||
新建包组 `packages/subagent/`：
|
||||
|
||||
| 包 | 角色 |
|
||||
|---|---|
|
||||
| `@deepseek-ai/dsh-subagent` | 接口：`SubagentService`（`ctx.subagents`）、`SubagentProvider`、`SubagentRun`、请求/结果/能力词汇、`subagent/*` 事件 |
|
||||
| `@deepseek-ai/dsh-subagent` | 接口：`SubagentService`（`ctx.subagents`）、`SubagentProvider`、`SubagentRun`、请求、结果、能力词汇、`subagent/*` 事件 |
|
||||
| `@deepseek-ai/dsh-subagent-spawn` | 实现：通过 `ctx.agents.create` 创建全新的进程内子 agent |
|
||||
| `@deepseek-ai/dsh-subagent-fork` | 实现：用父 agent 日志快照初始化的进程内子 agent |
|
||||
| `@deepseek-ai/dsh-subagent-acp` | 实现：作为 ACP 客户端驱动已配置的子进程 |
|
||||
@@ -45,8 +45,8 @@ bash seam（[能力 seam](../architecture/2026-06-13-capability-seams.md)）在
|
||||
|
||||
### 两类可选能力，两种发现方式
|
||||
|
||||
- **启动时功能**（`outputSchema`、`depthLimit`、`toolFilter`、`persona`）挂在静态的 `provider.capabilities` 描述符上。服务在委派之前检查每个被请求的功能，如果提供方不支持则**大声拒绝**（`SubagentError('UNSUPPORTED_CAPABILITY')`），绝不接受后静默忽略。这些功能必须在 run 存在之前检查，因此不能是运行时方法。
|
||||
- **可继续创建**使用可选的 `SubagentProvider.prepareContinuable` 方法；方法是否存在本身即为能力，TypeScript 类型收窄即为发现机制，因此不需要可能与实现失同步的独立 flag。继续执行管理器直接通过 `AgentHandle` 负责后续投递与从持久化存储恢复，而一次性 `SubagentRun` 没有 steering 或 resume 操作，具体由[可继续 subagent](2026-07-28-continuable-subagent-conversations.md)细化。
|
||||
- **启动时功能**（`outputSchema`、`depthLimit`、`toolFilter`、`persona`）挂在静态的 `provider.capabilities` 描述符上。服务在委派之前检查每个被请求的功能，如果提供方不支持则**明确拒绝**（`SubagentError('UNSUPPORTED_CAPABILITY')`），绝不接受后静默忽略。这些功能必须在 run 存在之前检查，因此不能是运行时方法。
|
||||
- **可继续创建**使用可选的 `SubagentProvider.prepareContinuable` 方法；方法是否存在本身即为能力，TypeScript 类型收窄即为发现机制，因此不需要可能与实现失同步的独立 flag。继续执行管理器直接通过 `AgentHandle` 负责后续投递与冷恢复，而一次性 `SubagentRun` 没有 steering 或 resume 操作，具体由[可继续 subagent](2026-07-28-continuable-subagent-conversations.md) 细化。
|
||||
|
||||
### Fork 与 fresh 是独立后端，而非一个 flag
|
||||
|
||||
@@ -58,19 +58,19 @@ bash seam（[能力 seam](../architecture/2026-06-13-capability-seams.md)）在
|
||||
|
||||
### 同步收集（首版）
|
||||
|
||||
`dsh-tool-subagent` 将其执行信号传给 `start()`，等待子 agent 结果，并在报告前 dispose 该 run。非完成态的结果变为错误结果，而非成功的部分输出；相互独立的结果与 dispose rejection 会保留两项 diagnostic。
|
||||
`dsh-tool-subagent` 将其执行信号传给 `start()`，等待子 agent 结果，并在报告前 dispose 该 run。非完成态的结果变为错误结果，而非成功的部分输出；结果与 dispose 的拒绝相互独立，且两项诊断信息都会保留。
|
||||
|
||||
### 提供方选择是配置，不面向模型
|
||||
|
||||
`dsh-tool-subagent` 绑定到恰好一个提供方名称（`Config.provider`）；模型只看到 `{ description, prompt }`。若要暴露多种传输方式，请多次加载该工具插件，每次绑定不同的提供方和不同的 `toolName`（工具注册表拒绝重名）。*服务*持有多提供方注册表；*工具*选择其中一个——本版 schema 中没有提供方/type 参数。
|
||||
`dsh-tool-subagent` 绑定到恰好一个提供方名称（`Config.provider`）；模型只看到 `{ description, prompt }`。若要暴露多种传输方式，请多次加载该工具插件，每次绑定不同的提供方和不同的 `toolName`（工具注册表拒绝重名）。*服务*持有多提供方注册表；*工具*选择其中一个——schema 中没有提供方/type 参数。
|
||||
|
||||
## 测试
|
||||
|
||||
注册表与工具测试仅用包内脚本化提供方替换非确定性的子进程边界，同时运行真实的 `SubagentService`、生命周期、任务集成和面向模型的工具。提供方与消费方的 export 形状仍保留 Loader 回归覆盖，以防止[事后分析 0001](../../../../docs/postmortem/0001-acp-default-export-drops-inject.md) 中描述的失败。注册表测试覆盖重载安全性、重名和启动时能力拒绝；嵌套 agent 场景通过[逐会话快照回放](../testing/2026-06-22-subagent-snapshot-replay.md)进行无密钥回放；进程内后端还有真实循环的单元测试和带密钥的 e2e 测试。
|
||||
注册表与工具测试仅用包内脚本化提供方替换非确定性的子进程边界，同时运行真实的 `SubagentService`、生命周期、任务集成和面向模型的工具。提供方与消费方的 export 形状仍保留 Loader 回归覆盖，以防止[事故复盘（postmortem）0001](../../../../docs/postmortem/0001-acp-default-export-drops-inject.md) 中描述的失败。注册表测试覆盖重载安全性、重名和启动时能力拒绝；嵌套 agent 场景通过[逐会话快照回放](../testing/2026-06-22-subagent-snapshot-replay.md)进行无密钥回放；进程内后端还有真实循环的单元测试和带密钥的 e2e 测试。
|
||||
|
||||
## 后果
|
||||
|
||||
- **递归。** 如果不设限制，进程内子 agent 能看到委派工具并递归调用。进程内后端实现了可选的绝对深度限制和有作用域的实时全局 `toolFilter`；ACP 声明这两项能力为关闭状态，并拒绝此类请求。[subagent 组合控制 Agent Note](2026-07-12-subagent-persona-tool-filter-and-depth.md) 负责定义它们的确切语义和安全边界。
|
||||
- **阻塞父轮次。** 前台收集在子 agent 的整个持续时间内保持父 agent 的步骤打开。后台委派使用共享的 `ctx.tasks` 运行时与通用 `task_*` 工具，与后台 bash 共用同一套收集机制；subagent seam 本身仍不感知任务。
|
||||
- **实时进度。** 本版仅暴露生命周期事件与最终结果；逐分片的子→父更新流推迟到后台重新设计时一并处理。
|
||||
- **ACP 客户端接口。** 将 ACP 子 agent 的 `fs`/`terminal` 代理回父 agent（共享工作区模式）是后续工作；首版不声明这两项能力，子 agent 在自己的进程中自行服务。
|
||||
- **实时进度。** 仅暴露生命周期事件与最终结果；逐分片的子→父更新流推迟到后台重新设计时一并处理。
|
||||
- **ACP 客户端接口。** 将 ACP 子 agent 的 `fs`/`terminal` 代理回父 agent（共享工作区模式）是后续工作；该后端不声明这两项能力，子 agent 在自己的进程中自行服务。
|
||||
|
||||
@@ -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/2026-06-22-acp-subagent-backend.md
|
||||
2026-06-22-acp-subagent-backend.md: c994ebfa69649bb9e79d3aa389a0e13c178131c7
|
||||
2026-06-22-acp-subagent-backend.zh.md: 62d631e95b5d1f299bed1fd00353b5ac9349b9a0
|
||||
2026-06-22-acp-subagent-backend.md: 41a60bc8e73cbda1d382226acfbd9c0a4b146fa6
|
||||
2026-06-22-acp-subagent-backend.zh.md: 6aea991c2b4ab783b5f8c43ecb9529df07269d3f
|
||||
|
||||
@@ -18,7 +18,7 @@ Each `start` spawns a new child, runs exactly one ACP session (`initialize` →
|
||||
|
||||
### Minimal client stub
|
||||
|
||||
The client advertises NO optional capabilities (no `fs`, no `terminal`): the child self-serves file/terminal access in its own process. `session/update` notifications are consumed — the backend accumulates `agent_message_chunk` text as the result output and ignores the rest (thoughts, tool-call cards) in this cut, which surfaces only the child's final answer. `session/request_permission` is auto-answered by a configured policy (`reject` declines every prompt, `allow` approves via the first allow-shaped option) — the first cut surfaces no prompt to a human. Proxying `fs`/`terminal` back to the parent (a shared-workspace mode) remains future work, as the seam Agent Note noted.
|
||||
The client advertises NO optional capabilities (no `fs`, no `terminal`): the child self-serves file/terminal access in its own process. `session/update` notifications are consumed — the backend accumulates `agent_message_chunk` text as the result output and ignores the rest (thoughts, tool-call cards), so only the child's final answer surfaces. `session/request_permission` is auto-answered by a configured policy (`reject` declines every prompt, `allow` approves via the first allow-shaped option) — no prompt is surfaced to a human. Proxying `fs`/`terminal` back to the parent (a shared-workspace mode) remains future work, as the seam Agent Note noted.
|
||||
|
||||
### No start-time capabilities
|
||||
|
||||
@@ -59,4 +59,4 @@ Every run pays a fresh subprocess (spawn + `initialize` + `newSession`). The par
|
||||
|
||||
## Product-provider siblings
|
||||
|
||||
The [Codex app-server and Claude Code Agent SDK providers](2026-08-04-claude-code-and-codex-subagent-backends.md) apply the same out-of-process spawn/prompt/settle/cancel boundary as siblings registered by name. A2A remains a future sibling transport; the ACP backend proves that the common seam supports this boundary without owning product-private protocols.
|
||||
The [Codex app-server and Claude Code Agent SDK providers](2026-08-04-claude-code-and-codex-subagent-backends.md) apply the same out-of-process spawn/prompt/settle/cancel boundary as siblings registered by name. A2A remains a future sibling transport; the ACP backend proves that the subagent seam supports this boundary without owning product-private protocols.
|
||||
|
||||
@@ -18,7 +18,7 @@ subagent seam（[seam Agent Note](2026-06-21-subagent-capability-seam.md)）的
|
||||
|
||||
### 最小化客户端桩
|
||||
|
||||
客户端不声明任何可选能力（无 `fs`、无 `terminal`）：子 agent 在自己的进程中自行处理文件/终端访问。`session/update` 通知被消费：后端将 `agent_message_chunk` 文本累积为结果输出，在本阶段忽略其余内容（思考、工具调用卡片），仅暴露子 agent 的最终回答。`session/request_permission` 由配置的策略自动应答（`reject` 拒绝所有提示，`allow` 通过第一个表示允许的选项批准）——本阶段不向人类暴露任何权限提示。将 `fs`/`terminal` 代理回父进程（共享工作区模式）仍为后续工作，如 seam Agent Note 所述。
|
||||
客户端不声明任何可选能力（无 `fs`、无 `terminal`）：子 agent 在自己的进程中自行处理文件/终端访问。`session/update` 通知被消费：后端将 `agent_message_chunk` 文本累积为结果输出，忽略其余内容（思考、工具调用卡片），因此仅暴露子 agent 的最终回答。`session/request_permission` 由配置的策略自动应答（`reject` 拒绝所有提示，`allow` 通过第一个表示允许的选项批准）——不向人类暴露任何权限提示。将 `fs`/`terminal` 代理回父进程（共享工作区模式）仍为后续工作，如 seam Agent Note 所述。
|
||||
|
||||
### 无启动时能力
|
||||
|
||||
@@ -30,7 +30,7 @@ subagent seam（[seam Agent Note](2026-06-21-subagent-capability-seam.md)）的
|
||||
|
||||
### StopReason 映射
|
||||
|
||||
ACP `StopReason` → harness `SubagentStopReason`：`end_turn`→`completed`、`max_tokens`→`max-tokens`、`refusal`→`refusal`、`cancelled`→`aborted`、`max_turn_requests`→`error`（无对等语义，任务未完成）、未知→`error`。spawn/传输/RPC 失败时，结果为 `error`（如果已请求取消则为 `aborted`）；按 seam 契约，`result` 在子 agent 级别失败时从不 reject。
|
||||
ACP `StopReason` → harness `SubagentStopReason`：`end_turn`→`completed`、`max_tokens`→`max-tokens`、`refusal`→`refusal`、`cancelled`→`aborted`、`max_turn_requests`→`error`（无对等语义，任务未完成）、未知→`error`。spawn/传输/RPC 失败时，结果为 `error`（如果已请求取消则为 `aborted`）；按 seam 约定，`result` 在子 agent 级别失败时从不 reject。
|
||||
|
||||
### 安全：清洗子进程环境
|
||||
|
||||
@@ -59,4 +59,4 @@ ACP `StopReason` → harness `SubagentStopReason`：`end_turn`→`completed`、`
|
||||
|
||||
## 兄弟产品提供方
|
||||
|
||||
[Codex app-server 与 Claude Code Agent SDK 提供方](2026-08-04-claude-code-and-codex-subagent-backends.md)作为按名称注册的兄弟提供方，采用同样的进程外启动/提示词/结算/取消边界。A2A 仍是未来的兄弟传输方式；ACP 后端证明了通用 seam 能够支持这项边界，而无需负责产品私有协议。
|
||||
[Codex app-server 与 Claude Code Agent SDK 提供方](2026-08-04-claude-code-and-codex-subagent-backends.md)作为按名称注册的兄弟提供方，采用同样的进程外启动/提示词/结算/取消边界。A2A 仍是未来的兄弟传输方式；ACP 后端证明了 subagent seam 能够支持这项边界，而无需负责产品私有协议。
|
||||
|
||||
@@ -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/2026-06-24-workspace-context.md
|
||||
2026-06-24-workspace-context.md: 3c21b7599e6bb2dd759e4a040c1b999f1b0516cd
|
||||
2026-06-24-workspace-context.zh.md: e913ecb22b4692e1ee7b96d4f5effe2606775cf8
|
||||
2026-06-24-workspace-context.md: e7a3724847b9dc8cfad11e87b2c96a3ef442bcba
|
||||
2026-06-24-workspace-context.zh.md: 39c3f52da10b7299301d10bd8b78330cbae8e19c
|
||||
|
||||
@@ -14,7 +14,7 @@ The lifecycle has two distinct classes of content. The initial applicable chain
|
||||
|
||||
## Decision
|
||||
|
||||
The implementation lives in `packages/context/workspace-context` as `@deepseek-ai/dsh-workspace-context`. It is a request-context extension, not a core service or a filesystem backend. The shared demo spine and Host Runtime mount it from an explicit `{ maxBytes } | false` deployment choice; `dsh web` enables a 65,536-byte budget while the Host Runtime's headless consumer disables it. The plugin consumes `agent/pre-step`, `tools/post-execute`, and the optional `ctx.fs` capability.
|
||||
The implementation lives in `packages/context/workspace-context` as `@deepseek-ai/dsh-workspace-context`. It is a request-context extension, not a core service or a filesystem backend. The shared demo spine and Host Runtime mount it from an explicit `{ maxBytes } | false` deployment choice; `dsh web` enables a 65,536-byte budget while the Host Runtime's headless consumer disables it. The plugin consumes `agent/pre-step`, immutable `tools/result` outcomes, `session/event` boundaries, and the optional `ctx.fs` capability.
|
||||
|
||||
The plugin does not statically inject `fs`. Providerless product trees therefore boot normally and the plugin no-ops until a filesystem provider exists. All production reads go through that provider. Candidate probes resolve each path and stat the result, so a final-component symlink is followed to its target: a link to a regular file loads, while a missing path or a non-file target is a confirmed absence. Following repository-owned links across the trust boundary is a deliberate reversal of the original no-follow probe; the [instruction-symlink follow note](2026-07-21-follow-instruction-symlinks.md) owns that decision and its residual risk. The step signal and dynamic tool execution signal propagate through resolution, metadata probes, and streaming reads, so cancellation does not wait for an unrelated filesystem scan. A resolve or stat exception is classified as unavailable: it skips only that candidate and is never interpreted as the deletion of an already-loaded scope.
|
||||
|
||||
@@ -38,7 +38,7 @@ The baseline is a user-role `<system-reminder>` with `Instructions from: <path>`
|
||||
|
||||
### Dynamic Discovery And Refresh
|
||||
|
||||
After a successful first-party `read`, `write`, or `edit` call, the `tools/post-execute` listener reconciles the touched descendant chain and every scope already known to the session. A newly reached scope is returned through `additionalContexts` for the next request using an `Additional instructions from: <path>` system-reminder. Under Code Mode, `run_code` defers sub-dispatch contexts onto its outer result, so the same update is appended only after the parent result rather than being injected mid-call.
|
||||
After a successful first-party `read`, `write`, or `edit` call, the immutable `tools/result` observer reconciles the touched descendant chain and every scope already known to the session, then queues an `Additional instructions from: <path>` system-reminder in the agent inbox for the next request. Under Code Mode, successful sub-dispatch touches bubble through opaque parent execution tokens until the top-level result settles. A touch produced inside an agent-loop step does not begin its asynchronous projection until the durable `step/end`; a direct tool execution outside an open step projects immediately. The two boundaries keep result and step adjacency deterministic without making the tool pipeline await filesystem discovery.
|
||||
|
||||
A content edit appends `Updated instructions from: <path>`, states that the new content replaces the previous content, and includes the complete current file. If precedence changes from one candidate to another, the message also names the previous path and says it no longer applies. If no candidate remains, the plugin appends `Instructions removed: <path>` and states that the previously loaded instructions no longer apply.
|
||||
|
||||
@@ -50,7 +50,7 @@ Shell commands are not discovery triggers. Local bash calls start fresh shells,
|
||||
|
||||
Every workspace context event stores versioned metadata with `{ action, scope, path, digest? }`, where `digest` is SHA-1 over the loaded content. Complete baselines additionally carry `baseline: true` and `baselineIdentity`. The model-facing prompt has no HTML comments, hidden markers, or headings that are parsed back into state.
|
||||
|
||||
At reconciliation time the plugin scans workspace-sourced `user/message` events and derives the latest state for each visible scope. A short per-session pending map begins only after the immutable top-level `tools/result` proves an `additionalContexts` entry survived every post-execute listener, then covers the interval before the loop appends that context to the log. Each entry records the open `{ turn, step }`: an equal durable `user/message` at or after its sequence boundary confirms and removes it, while a matching `step/end` arriving first means the loop discarded its context buffer, so the plugin removes both the pending entry and its version-cache fast path. A nested Code Mode result stages its changes under the parent's opaque execution token so repeated sub-dispatches in one run do not duplicate them; the parent result rolls that provisional state back and commits only contexts retained by outer policy.
|
||||
At reconciliation time the plugin scans workspace-sourced `user/message` events and derives the latest state for each visible scope. Successful nested touches aggregate under their parent execution token, including when a later composite result is blocked; the top-level result transfers them either to the open session step or directly to a per-agent projection queue. A `step/end` releases its staged touches only after that boundary is durable, and the next `agent/pre-step` waits for the serialized projections. Each projection composes against visible history plus the current inbox and replaces the single pending workspace context instead of accumulating intermediate renderings.
|
||||
|
||||
An unchanged path and digest is suppressed. A logged removal is a tombstone, so a reappearing candidate becomes a new `set`. Resume works from persisted metadata: a compatible visible baseline supplies comparison state rather than causing another complete baseline to be appended. If compaction removes an instruction event from the visible surface, that state no longer suppresses a later load, matching the fact that the model can no longer see it. Only changes actually included under the byte budget enter metadata or pending state, so an omitted file remains eligible on a later touch.
|
||||
|
||||
@@ -62,7 +62,7 @@ There is intentionally no watcher. Detection occurs at the next successful struc
|
||||
|
||||
`maxBytes` is required and applies separately to a rendered baseline or one dynamic reconciliation batch; there is no implicit or unbounded render budget. Non-positive and non-finite values disable loading. When content exceeds the budget, broader files are omitted before the most-specific file is truncated. A visible `Workspace instruction budget ...` notice names omitted and truncated paths and byte counts, and output never exceeds the configured bytes.
|
||||
|
||||
`maxSourceBytes` is a positive per-file cap with a 1 MiB default. The loader checks reported size before reading and still consumes content through `streamText()` with a running UTF-8 byte count, so missing/stale metadata cannot force an unbounded allocation. An oversized winning candidate is unavailable rather than a reason to fall through to another same-directory name. The plugin deliberately keeps no process-wide cache and never retains instruction prose. It keeps only `{ path, version, digest }` per effective scope in a `WeakMap<Session, Map<scope, state>>`: a matching provider `FsVersion` plus matching effective prompt state skips the read, while a changed version triggers a bounded read and SHA-1 confirmation. SHA-1 remains the cross-provider content identity persisted in visible structured metadata; provider versions are only an in-memory invalidation fast path. Cache transitions for model-visible changes commit only when the corresponding context survives the complete tool-result policy chain, and are invalidated if that accepted context is later dropped with its aborted step before reaching the log.
|
||||
`maxSourceBytes` is a positive per-file cap with a 1 MiB default. The loader checks reported size before reading and still consumes content through `streamText()` with a running UTF-8 byte count, so missing/stale metadata cannot force an unbounded allocation. An oversized winning candidate is unavailable rather than a reason to fall through to another same-directory name. The plugin deliberately keeps no process-wide cache and never retains instruction prose. It keeps only `{ path, version, digest }` per effective scope in a `WeakMap<Session, Map<scope, state>>`: a matching provider `FsVersion` plus matching effective prompt state skips the read, while a changed version triggers a bounded read and SHA-1 confirmation. SHA-1 remains the cross-provider content identity persisted in visible structured metadata; provider versions are only an in-memory invalidation fast path. Dynamic cache transitions occur while a serialized projection composes the one desired inbox context, and the next pre-step waits for that projection before deciding what enters the request.
|
||||
|
||||
## Alternatives considered
|
||||
|
||||
@@ -78,7 +78,7 @@ There is intentionally no watcher. Detection occurs at the next successful struc
|
||||
|
||||
## Consequences
|
||||
|
||||
Workspace guidance is isolated per session and shared by the demo front doors, Web Host, and every tool presentation mode. Initial, nested, and changed instructions are durable and replayable. The generic session/agent context contract carries typed source data through injected messages and post-tool `additionalContexts` arrays without flattening entries.
|
||||
Workspace guidance is isolated per session and shared by the demo entry points, Web Host, and every tool presentation mode. Initial, nested, and changed instructions are durable and replayable. The generic session/agent context contract carries typed source data through inbox-staged and durably entered user messages without flattening entries.
|
||||
|
||||
Repository text remains untrusted input. Lower-authority user-role framing, explicit precedence language, and delimiter escaping reduce risk but do not eliminate prompt injection. Following a candidate symlink to its target widens that surface to off-tree content, so the permission and sandbox layers that confine `ctx.fs` to trusted roots are the boundary that treats workspace files as data rather than authority (the [instruction-symlink follow note](2026-07-21-follow-instruction-symlinks.md) owns the residual risk).
|
||||
|
||||
|
||||
@@ -14,7 +14,7 @@ Status: implemented
|
||||
|
||||
## 决策
|
||||
|
||||
该实现在 `packages/context/workspace-context` 中，包（package）名为 `@deepseek-ai/dsh-workspace-context`。它是请求上下文扩展，不是核心服务或文件系统后端。共享 demo 主干与 Host Runtime 根据显式的 `{ maxBytes } | false` 部署选择挂载它；`dsh web` 启用 65,536 字节预算，Host Runtime 的 headless 消费方则禁用它。该插件使用 `agent/pre-step`、`tools/post-execute` 和可选的 `ctx.fs` 功能。
|
||||
该实现在 `packages/context/workspace-context` 中，包名为 `@deepseek-ai/dsh-workspace-context`。它是请求上下文扩展，不是核心服务或文件系统后端。共享 demo 主干与 Host Runtime 根据显式的 `{ maxBytes } | false` 部署选择挂载它；`dsh web` 启用 65,536 字节预算，Host Runtime 的 headless 消费方则禁用它。该插件使用 `agent/pre-step`、不可变的 `tools/result` 结果、`session/event` 边界和可选的 `ctx.fs` 功能。
|
||||
|
||||
插件不会静态注入 `fs`。因此，不带提供方的产品树仍能正常启动；在文件系统提供方出现之前，插件保持无操作。所有生产读取都通过该提供方完成。候选项探测会解析每个路径并对结果执行 stat，因此会跟随最终路径组件的符号链接至其目标：指向普通文件的链接会被加载，缺失路径或非文件目标则确认为不存在。允许仓库拥有的链接跨越信任边界，是对最初不跟随探测方式的刻意反转；[跟随指令符号链接记录](2026-07-21-follow-instruction-symlinks.md)负责说明该决策及其残余风险。步骤信号与动态工具执行信号会贯穿解析、元数据探测和流式读取，因此取消不会等待无关的文件系统扫描。解析或 stat 异常归类为不可用：它只跳过该候选项，绝不被解释为已经加载的作用域被删除。
|
||||
|
||||
@@ -22,7 +22,7 @@ Status: implemented
|
||||
|
||||
默认的逐目录候选列表是 `['AGENTS.md', 'CLAUDE.md']`。该列表可通过 `instructionFileCandidates` 配置；`AGENTS.md` 是普通的第一候选项，而不是隐藏优先级。一个目录中只加载第一个存在的普通文件候选项。使用默认值时，`AGENTS.md` 是原生文件，`CLAUDE.md` 是兼容性回退。第二个列表 `localInstructionFileCandidates`（默认为 `['AGENTS.local.md', 'CLAUDE.local.md']`）会在同一目录的基础文件后加载叠加式本地覆盖层；[默认本地覆盖层记录](2026-07-21-local-instruction-overlay.md)负责说明该决策。
|
||||
|
||||
候选条目必须是同一目录中的文件名。空条目、`.`／`..`，以及包含 `/` 或 `\` 的条目会被忽略。其他同目录名称可以显式选择加入；规则目录和导入语义不属于本契约。
|
||||
候选条目必须是同一目录中的文件名。空条目、`.`／`..`，以及包含 `/` 或 `\` 的条目会被忽略。其他同目录名称可以显式选择加入；规则目录和导入语义不属于本约定。
|
||||
|
||||
用户全局文件固定为 `$DSH_HOME/AGENTS.md`，不受任一候选列表影响，也没有本地覆盖层。`$DSH_HOME` 默认为 `~/.dsh`，与 `~/.codex` 或 `~/.claude` 在 harness 层的 home 角色一致，而不会引入插件专用 home。波浪号展开与默认值位于 `dsh-paths` 中，以便未来的 harness 功能共享同一约定。
|
||||
|
||||
@@ -38,7 +38,7 @@ Status: implemented
|
||||
|
||||
### 动态发现与刷新
|
||||
|
||||
第一方 `read`、`write` 或 `edit` 调用成功后，`tools/post-execute` 监听器会协调被触及的后代路径链，以及该会话已经知道的每个作用域。新到达的作用域通过 `additionalContexts` 返回，并在下一次请求中使用 `Additional instructions from: <path>` system-reminder。在 Code Mode 下，`run_code` 会把子分发上下文延后至其外层结果，因此同一更新只会在父结果之后追加，而不会在调用中途注入。
|
||||
第一方 `read`、`write` 或 `edit` 调用成功后，不可变的 `tools/result` 观察器会协调被触及的后代路径链，以及该会话已经知道的每个作用域，然后在 agent inbox 中排入一条 `Additional instructions from: <path>` system-reminder，供下一次请求使用。在 Code Mode 下，成功的子分派 touch 会沿不透明的父级执行 token 逐层上浮，直到顶层结果落定。在 agent loop 步骤内产生的 touch，须等持久 `step/end` 后才开始异步投影；打开的步骤之外直接执行工具时，则立即投影。这两个边界在不让工具流水线等待文件系统发现的前提下，保证结果／步骤的相邻关系具有确定性。
|
||||
|
||||
内容编辑会追加 `Updated instructions from: <path>`，说明新内容取代先前内容，并包含当前的完整文件。如果优先级从一个候选项变为另一个，消息还会指出先前路径并说明它不再适用。如果没有候选项保留，插件会追加 `Instructions removed: <path>`，并说明先前加载的指令不再适用。
|
||||
|
||||
@@ -50,7 +50,7 @@ shell 命令不会触发发现。本地 bash 调用会启动全新的 shell，
|
||||
|
||||
每个工作区上下文事件都会存储带版本的元数据，其形态为 `{ action, scope, path, digest? }`；`digest` 是对已加载内容计算的 SHA-1。完整基线还会额外携带 `baseline: true` 和 `baselineIdentity`。模型可见提示词中没有 HTML 注释、隐藏标记，也没有会被解析回状态的标题。
|
||||
|
||||
协调时，插件扫描带工作区来源的 `user/message` 事件，并派生每个可见作用域的最新状态。一个简短的逐会话待处理映射只会在不可变的顶层 `tools/result` 证明某个 `additionalContexts` 条目经过所有 post-execute 监听器后仍然保留时开始记录；随后，它覆盖循环将该上下文追加到日志之前的间隔。每个条目记录开启状态的 `{ turn, step }`：如果相同的持久 `user/message` 出现在其序列边界或之后，该条目得到确认并被移除；如果匹配的 `step/end` 先到达，则说明循环丢弃了上下文缓冲区，插件会同时移除待处理条目及其版本缓存快速路径。嵌套的 Code Mode 结果会把变更暂存在父级的不透明执行 token 下，确保一次运行中的重复子分发不会产生重复项；父级结果会回滚这份临时状态，并且只提交外层策略保留的上下文。
|
||||
协调时，插件扫描带工作区来源的 `user/message` 事件，并派生每个可见作用域的最新状态。即使后续复合结果被拦截，成功的嵌套 touch 也会聚合到父级执行 token 下；顶层结果会将它们交给打开的会话步骤，或直接交给逐 agent 投影队列。`step/end` 只会在自身边界持久化后释放其暂存的 touch；下一次 `agent/pre-step` 会等待串行投影完成。每次投影都会根据可见历史和当前 inbox 进行组合，并替换唯一一条待处理工作区上下文，而不会累积中间渲染结果。
|
||||
|
||||
路径和 digest 均未变化时会被抑制。日志中的移除操作是一条墓碑记录，因此重新出现的候选项会成为新的 `set`。恢复操作从持久化元数据继续工作：兼容的可见基线会提供比较状态，而不会导致再次追加完整基线。如果压缩从可见表面移除某条指令事件，该状态不再抑制后续加载，这与模型已经无法看见它的事实一致。只有真正纳入字节预算的变更才会进入元数据或待处理状态，因此被省略的文件在之后的触碰中仍有资格加载。
|
||||
|
||||
@@ -62,7 +62,7 @@ shell 命令不会触发发现。本地 bash 调用会启动全新的 shell，
|
||||
|
||||
`maxBytes` 是必填项，分别作用于渲染后的基线或单个动态协调批次；系统不存在隐式或无界的渲染预算。非正数或非有限值会禁用加载。内容超过预算时，系统会先省略较宽泛的文件，再截断最具体的文件。可见的 `Workspace instruction budget ...` 提示会指出被省略和截断的路径与字节数，并且输出绝不超过配置字节数。
|
||||
|
||||
`maxSourceBytes` 是正数的逐文件上限，默认为 1 MiB。loader 会在读取前检查报告的大小，同时仍通过 `streamText()` 消费内容并持续统计 UTF-8 字节数，因此缺失／陈旧的元数据无法迫使其进行无界分配。过大的胜出候选项会被视为不可用，而不是改为同目录中的下一个名称。插件刻意不保留进程级缓存，也绝不保留指令正文。它只为每个有效作用域保存 `{ path, version, digest }`，并将这些状态放在 `WeakMap<Session, Map<scope, state>>` 中：提供方 `FsVersion` 与有效提示词状态同时匹配时跳过读取；版本变化则触发有界读取和 SHA-1 确认。SHA-1 仍是持久化在可见结构化元数据中的跨提供方内容标识；提供方版本只作为内存中的失效快速路径。模型可见变更的缓存转换只有在相应上下文通过完整的工具结果策略链后才会提交；如果该已接受上下文随后与中止步骤一起被丢弃、未能进入日志，缓存转换就会失效。
|
||||
`maxSourceBytes` 是正数的逐文件上限，默认为 1 MiB。loader 会在读取前检查报告的大小，同时仍通过 `streamText()` 消费内容并持续统计 UTF-8 字节数，因此缺失／陈旧的元数据无法迫使其进行无界分配。过大的胜出候选项会被视为不可用，而不是改为同目录中的下一个名称。插件刻意不保留进程级缓存，也绝不保留指令正文。它只为每个有效作用域保存 `{ path, version, digest }`，并将这些状态放在 `WeakMap<Session, Map<scope, state>>` 中：提供方 `FsVersion` 与有效提示词状态同时匹配时跳过读取；版本变化则触发有界读取和 SHA-1 确认。SHA-1 仍是持久化在可见结构化元数据中的跨提供方内容标识；提供方版本只作为内存中的失效快速路径。动态缓存转换发生在串行投影组合唯一一条目标 inbox 上下文时；下一次 pre-step 会等待该投影完成，再决定哪些内容进入请求。
|
||||
|
||||
## 考虑过的替代方案
|
||||
|
||||
@@ -78,7 +78,7 @@ shell 命令不会触发发现。本地 bash 调用会启动全新的 shell，
|
||||
|
||||
## 后果
|
||||
|
||||
工作区指引按会话隔离，并由 demo 入口、Web Host 与每一种工具展示模式共享。初始、嵌套与变更指令都保持持久且可回放。通用的会话／agent 上下文契约通过注入消息与工具执行后的 `additionalContexts` 数组携带带类型的来源数据，而不会把条目展平。
|
||||
工作区指引按会话隔离，并由 demo 入口、Web Host 与每一种工具展示模式共享。初始、嵌套与变更指令都保持持久且可回放。通用的会话／agent 上下文约定通过先在 inbox 中暂存、再持久进入的 user 消息携带带类型的来源数据，而不会把条目展平。
|
||||
|
||||
仓库文本仍是不受信任的输入。低权威 user 角色框架、显式优先级说明和分隔符转义可以降低风险，但无法消除提示词注入。跟随候选符号链接到目标，会把该攻击面扩大至树外内容；因此，把 `ctx.fs` 限制在可信根目录内的权限与沙箱层才是真正的边界，它们让系统把工作区文件当作数据而不是权威（[跟随指令符号链接记录](2026-07-21-follow-instruction-symlinks.md)负责说明残余风险）。
|
||||
|
||||
|
||||
@@ -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/2026-06-29-todo-write-tool.md
|
||||
2026-06-29-todo-write-tool.md: c4cf64b7876bd8b80df80fe6fc27005715f96b5e
|
||||
2026-06-29-todo-write-tool.zh.md: 1f797c5517df8affd66addecf2a8db43c1da3332
|
||||
2026-06-29-todo-write-tool.md: 74af8a66ea86a474533b9c53d6431f7e0026192c
|
||||
2026-06-29-todo-write-tool.zh.md: ec2b7c8d59d65a44018425de81aa410890d8c208
|
||||
|
||||
@@ -42,7 +42,7 @@ The schema enforces type/required/enum. Beyond that, `execute` rejects empty or
|
||||
|
||||
## Testing
|
||||
|
||||
Four tiers, designed up front:
|
||||
Four tiers:
|
||||
- **Unit** — the session event (append/snapshot-clone/last-write-wins/not-on-surface); the tool (schema shape, arg validation via the real `ctx.tools.execute`, value validation, the event append + replacement, no-agent rejection, `presentCall`, HMR-safety); and TUI folding.
|
||||
- **Real-Loader path** — the plugin run through `Loader.unwrapExports`, asserting the namespace export shape survives (it HAS `inject`, so a stray default would crash at load — postmortem/0001).
|
||||
- **Full-loop integration** — a scripted mock model calls `todo_write` through the real agent loop; the `todo/write` event lands and a second call replaces it.
|
||||
|
||||
@@ -6,7 +6,7 @@ Status: implemented
|
||||
|
||||
## 问题
|
||||
|
||||
harness 为模型提供了 bash 和 subagent 工具，却没有办法记录结构化的任务列表。todo 列表有两个同等重要的用途：引导模型规划多步骤工作并保持当前活跃任务明确；同时为交互式宿主提供实时进度清单。调研的所有参考编码 agent（智能体），包括 claude-code、opencode、codex、oh-my-pi 和 pi，都提供了某种形式的此功能；本 harness 此前没有。
|
||||
harness 为模型提供了 bash 和 subagent 工具，却没有办法记录结构化的任务列表。todo 列表有两个同等重要的用途：引导模型规划多步骤工作并保持当前活跃工作明确；同时为交互式宿主提供实时进度清单。调研的所有参考编码 agent（智能体），包括 claude-code、opencode、codex、oh-my-pi 和 pi，都提供了某种形式的此功能；本 harness 此前没有。
|
||||
|
||||
## 决策
|
||||
|
||||
@@ -14,7 +14,7 @@ harness 为模型提供了 bash 和 subagent 工具，却没有办法记录结
|
||||
|
||||
### 整列表替换，三态 status
|
||||
|
||||
模型每次调用发送完整列表；新列表替换旧列表（回放时 last-write-wins）。这是 claude-code V1、opencode 和 codex `update_plan` 共同采用的形状，也是模型训练最多的形状——没有逐项 id，没有 delta 协议。`status` 恰好是 `pending | in_progress | completed`，与 codex `update_plan` 相同的三元组；在 bridge 还把 todo 列表投影为 `plan` 更新时，它也与 ACP `PlanEntryStatus` 1:1 对应，该映射已随[仅面向自动化的 ACP 契约](../simplification/2026-07-23-acp-automation-only-protocol.md)退役。
|
||||
模型每次调用发送完整列表；新列表替换旧列表（回放时 last-write-wins）。这是 claude-code V1、opencode 和 codex `update_plan` 共同采用的形状，也是模型训练最多的形状——没有逐项 id，没有 delta 协议。`status` 恰好是 `pending | in_progress | completed`，与 codex `update_plan` 相同的三元组；在 bridge 还把 todo 列表投影为 `plan` 更新时，它也与 ACP `PlanEntryStatus` 1:1 对应，该映射已随[仅面向自动化的 ACP 约定](../simplification/2026-07-23-acp-automation-only-protocol.md)退役。
|
||||
|
||||
### 状态在会话日志上，而非服务
|
||||
|
||||
@@ -34,7 +34,7 @@ claude-code V1 的条目是 `{ content, status, activeForm }`；后来（V2）
|
||||
|
||||
### 校验：低成本的中间路线
|
||||
|
||||
schema 强制 type/required/enum。在此之上，`execute` 拒绝为空或重复的 `content`，并在 `allowParallelInProgress` 为 `false` 时拒绝超过一个活跃任务。排序和保持列表最新仍通过工具描述交给模型。被拒绝的写入返回 `isError` 结果，使模型自行修正。必填的部署策略及持久日志不变式独立于该策略这一约定，由[并行 in-progress Agent Note](2026-07-26-todo-parallel-in-progress.md) 负责。
|
||||
schema 强制 type/required/enum。在此之上，`execute` 拒绝为空或重复的 `content`，并在 `allowParallelInProgress` 为 `false` 时拒绝超过一个活跃任务。排序和保持列表最新仍通过工具描述交给模型。被拒绝的写入返回 `isError` 结果，使模型自行修正。必须采用的部署策略，以及持久不变式独立于该策略这一点，均由[并行 in-progress Agent Note](2026-07-26-todo-parallel-in-progress.md)负责。
|
||||
|
||||
## 为何没有 cordis-catalog 条目 / 没有 `@mode`
|
||||
|
||||
@@ -42,7 +42,7 @@ schema 强制 type/required/enum。在此之上，`execute` 拒绝为空或重
|
||||
|
||||
## 测试
|
||||
|
||||
四个层级，预先设计：
|
||||
四个层级：
|
||||
- **单元测试**——会话事件（append/snapshot-clone/last-write-wins/not-on-surface）；工具（schema 形状、通过真实 `ctx.tools.execute` 的参数校验、值校验、事件追加与替换、非 agent 拒绝、`presentCall`、HMR（热模块替换）安全性）；以及 TUI 折叠。
|
||||
- **真实 Loader 路径**——插件通过 `Loader.unwrapExports` 运行，断言命名空间导出形状存活（它有 `inject`，因此一个意外的 default 导出会在加载时崩溃——事故复盘（postmortem）0001）。
|
||||
- **全循环集成**——一个脚本化的 mock 模型通过真实 agent loop（智能体循环）调用 `todo_write`；`todo/write` 事件落地，第二次调用替换它。
|
||||
|
||||
@@ -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/2026-06-30-hook-bridges.md
|
||||
2026-06-30-hook-bridges.md: a31116818c57e18d04e656f371efd1101a63b6af
|
||||
2026-06-30-hook-bridges.zh.md: 8827408b67e2dd19f867a8658309f00231ba06c5
|
||||
2026-06-30-hook-bridges.md: eecc1fc75c10618481231083f890e0e4b122c1ee
|
||||
2026-06-30-hook-bridges.zh.md: dcc8f496cb3bc6ea7857ce804a9159cbfcbc3f08
|
||||
|
||||
@@ -6,9 +6,9 @@ English | [中文](2026-06-30-hook-bridges.zh.md)
|
||||
|
||||
## Problem
|
||||
|
||||
The harness's extension surface is its typed interception seams ([the interception-seams Agent Note](2026-06-30-interception-seams.md)): a "native hook" is just an ordinary cordis plugin subscribing to `agent/session-start`, `agent/pre-step`, `tools/pre-execute`, `tools/post-execute`, `agent/turn-stopping`, `subagent/start`, or `subagent/end`. But users arrive with **existing** Claude Code (CC) and Codex hook configs — a `hooks.json` (or a settings file's `hooks` key) full of shell-command hooks — and want those to run unmodified. This Agent Note introduces the two **bridge plugins** that translate that external shell-hook protocol onto the typed seams, built on the shared wire-protocol library ([the hook-protocol-lib Agent Note](2026-06-30-hook-protocol-lib.md)).
|
||||
The harness's extension surface is its typed interception points ([the interception extension-points Agent Note](2026-06-30-interception-extension-points.md)): a "native hook" is just an ordinary cordis plugin subscribing to `agent/session-start`, `agent/pre-step`, `tools/pre-execute`, `tools/post-execute`, `agent/turn-stopping`, `subagent/start`, or `subagent/end`. But users arrive with **existing** Claude Code (CC) and Codex hook configs — a `hooks.json` (or a settings file's `hooks` key) full of shell-command hooks — and want those to run unmodified. This Agent Note introduces the two **bridge plugins** that translate that external shell-hook protocol onto the typed extension points, built on the shared wire-protocol library ([the hook-protocol-lib Agent Note](2026-06-30-hook-protocol-lib.md)).
|
||||
|
||||
The framing that shapes the whole design: **a bridge is a compatibility adapter, not a power tool.** Anything a bridge does (block a tool, inject context, force continuation, observe a subagent) a native cordis plugin does more powerfully — typed returns, full `ctx`, no serialization boundary. The bridge's reason to exist is to run the explicitly supported subset of external CC/Codex command hooks. That keeps each bridge thin: parse the config, pick a matcher mode, build the per-event payload, call `runHook` + `mergeHookOutputs` from the shared lib, and map the neutral outcome onto a seam Decision. The package READMEs own the exact current unsupported-event and partial-field inventory against the official protocols.
|
||||
The framing that shapes the whole design: **a bridge is a compatibility adapter, not a power tool.** Anything a bridge does (block a tool, inject context, force continuation, observe a subagent) a native cordis plugin does more powerfully — typed returns, full `ctx`, no serialization boundary. The bridge's reason to exist is to run the explicitly supported subset of external CC/Codex command hooks. That keeps each bridge thin: parse the config, pick a matcher mode, build the per-event payload, call `runHook` + `mergeHookOutputs` from the shared lib, and map the neutral outcome to a typed Decision. The package READMEs own the exact current unsupported-event and partial-field inventory against the official protocols.
|
||||
|
||||
## Decision
|
||||
|
||||
@@ -19,9 +19,9 @@ Two independent plugins in the `packages/hooks/` group, each a function/namespac
|
||||
|
||||
### Outcome → Decision mapping
|
||||
|
||||
Each bridge maps the neutral `MergedHookOutcome` from the shared lib onto the seam's typed Decision:
|
||||
Each bridge maps the neutral `MergedHookOutcome` from the shared lib onto each extension point's typed Decision:
|
||||
|
||||
| Seam | CC | Codex |
|
||||
| Extension point | CC | Codex |
|
||||
|---|---|---|
|
||||
| `agent/session-start` (emit) | additionalContext → `agent.inject()` | plain-stdout output → additionalContext → `agent.inject()` |
|
||||
| `agent/pre-step` | `deny`→`reject`; context-only→delegate+fold into `enter` | `block`→`reject`; context-only→delegate+fold into `enter` |
|
||||
@@ -59,9 +59,9 @@ Hooks run in the agent's session workspace, so relative paths target the user's
|
||||
|
||||
- **Tool-input rewrite.** A CC/Codex `updatedInput` is logged + warned, not honored — input rewrite is a deferred consistency-design problem ([the pre-tool-input-rewrite Agent Note](../../proposed/feature/2026-06-30-pre-tool-input-rewrite.md)), because the pre-execution args are read by `tool/call` audit + `assistant/message` history + tool presentation, so an honest rewrite is a design unit, not a field.
|
||||
- **Stop loop-guard** (`TODO(stop-loop-guard)`). Claude Code supplies `stop_hook_active` and overrides a hook after eight consecutive blocks; Codex supplies `stop_hook_active` but documents no equivalent cap. Both bridges always report `false`, so a Stop hook that unconditionally blocks force-continues every step — a hook author must self-limit until state tracking lands.
|
||||
- **Hook `continue:false` (hard halt).** A hook can ask to halt the whole run (CC/Codex `continue:false`); the shared merge folds it into `MergedHookOutcome.stop`/`stopReason`, but no bridge acts on it (`TODO(hook-continue-false)`) — the interception seams have no "hard-halt the agent" primitive yet (a Decision blocks/steers a single point, not the run). Deferred with the loop-guard work; mid-turn requests record the halt in `hook/result`, and the hook keeps its per-point effect (decision/context) meanwhile.
|
||||
- **Hook `continue:false` (hard halt).** A hook can ask to halt the whole run (CC/Codex `continue:false`); the shared merge folds it into `MergedHookOutcome.stop`/`stopReason`, but no bridge acts on it (`TODO(hook-continue-false)`) — the interception points have no "hard-halt the agent" primitive yet (a Decision blocks/steers a single point, not the run). Deferred with the loop-guard work; mid-turn requests record the halt in `hook/result`, and the hook keeps its per-point effect (decision/context) meanwhile.
|
||||
- **Config discovery.** The path is explicit in `cordis.yml` and process-level (see above); the full multi-layer CC/Codex precedence walk, per-session project-local discovery, and the trust/hash model are not reimplemented (`TODO(per-session-hook-config)`).
|
||||
- **Session-start / subagent-start context is best-effort (`TODO(session-start-gating)`).** Both hooks run detached from startup, so their context is injected when ready but may miss the first request or a short-lived child. Guaranteeing first-request delivery requires an awaited startup seam.
|
||||
- **Session-start / subagent-start context is best-effort (`TODO(session-start-gating)`).** Both hooks run detached from startup, so their context is injected when ready but may miss the first request or a short-lived child. Guaranteeing first-request delivery requires an awaited startup extension point.
|
||||
|
||||
## Alternatives considered
|
||||
|
||||
|
||||
@@ -6,9 +6,9 @@ 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/pre-step`、`tools/pre-execute`、`tools/post-execute`、`agent/turn-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)）。
|
||||
harness 的扩展面是其类型化拦截点（见[拦截扩展点 Agent Note](2026-06-30-interception-extension-points.md)）：所谓「原生钩子」不过是一个普通的 Cordis 插件，订阅 `agent/session-start`、`agent/pre-step`、`tools/pre-execute`、`tools/post-execute`、`agent/turn-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扩展点上，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。
|
||||
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类型化 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。
|
||||
|
||||
## 决策
|
||||
|
||||
@@ -19,9 +19,9 @@ harness 的扩展面是其类型化的拦截 seam（见[拦截 seam Agent Note](
|
||||
|
||||
### Outcome → Decision 映射
|
||||
|
||||
每个桥接将共享库返回的中性 `MergedHookOutcome` 映射到 seam 的类型化 Decision：
|
||||
每个桥接将共享库返回的中性 `MergedHookOutcome` 映射到各扩展点的类型化 Decision：
|
||||
|
||||
| Seam | CC | Codex |
|
||||
| 扩展点 | CC | Codex |
|
||||
|---|---|---|
|
||||
| `agent/session-start`（emit） | additionalContext → `agent.inject()` | 纯 stdout 输出 → additionalContext → `agent.inject()` |
|
||||
| `agent/pre-step` | `deny`→`reject`；仅上下文→委托并折叠到 `enter` | `block`→`reject`；仅上下文→委托并折叠到 `enter` |
|
||||
@@ -37,7 +37,7 @@ CC 桥接的 `ask` 结果是一条真正的权限路径，而非终态桥接决
|
||||
|
||||
每个桥接的 `inject()` 和 additional-context 输入都显式传入 `{ kind: 'plugin', plugin: 'hooks-claude' | 'hooks-codex' }`。单元测试固定验证结果中的 `user/message.source` 为插件而非用户。
|
||||
|
||||
`UserPromptSubmit` 在 `turn/start` 之后的 pre-step 运行，因此每次调用都会写入轮次范围的 `hook/invoked` / `hook/result` 对。reject 会让已领取输入保持删除，将轮次关闭为 blocked 且不包含步骤，并保留该 hook 对作为持久决策证据。Codex payload 会收到这个已打开轮次的 `turn_id`。
|
||||
`UserPromptSubmit` 在 `turn/start` 之后的 pre-step 运行，因此每次调用都会写入轮次范围的 `hook/invoked` / `hook/result` 对。拒绝会使已领取的输入维持移除状态，将轮次关闭为已阻止状态且不包含步骤，并保留该钩子对作为持久决策证据。Codex payload 会收到这个已打开轮次的 `turn_id`。
|
||||
|
||||
### 添加上下文不是否决——先 delegate，再 prepend
|
||||
|
||||
@@ -59,9 +59,9 @@ 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` 历史和工具展示共同读取，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；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）。
|
||||
- **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)`）——拦截点尚无「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，不阻塞启动流程，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。
|
||||
- **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，不阻塞启动流程，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 的启动扩展点。
|
||||
|
||||
## 曾考虑的替代方案
|
||||
|
||||
|
||||
@@ -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/2026-06-30-hook-protocol-lib.md
|
||||
2026-06-30-hook-protocol-lib.md: 2edff0d501cd7695873c68054eeb3a1e9942eced
|
||||
2026-06-30-hook-protocol-lib.zh.md: 42e526fdf8073465d5f6faf99a6c92fbe09505f5
|
||||
2026-06-30-hook-protocol-lib.md: e6938f88b2b587ef97c135d6482ae9ce0e3a94c1
|
||||
2026-06-30-hook-protocol-lib.zh.md: 4a4efae9a8950368d4db0309bc2c89a3f8c6d0d0
|
||||
|
||||
@@ -6,7 +6,7 @@ English | [中文](2026-06-30-hook-protocol-lib.zh.md)
|
||||
|
||||
## Problem
|
||||
|
||||
The hooks subsystem ships two bridge plugins: one that runs a user's existing Claude Code (CC) hooks, one for Codex hooks. Studying the reference implementations (`~/repos/refs/claude-code`, `~/repos/refs/codex`) surfaced a decisive fact: **Codex deliberately reimplements a SUBSET of the CC hook protocol.** Its engine reads the same `hooks.json`, uses the same matcher-group shape, the same exit-code/structured-stdout output contract, and the same command-hook execution model — Codex's source even names the engine after Claude's and comments where it "intentionally diverges." So the two bridges would otherwise duplicate the bulk of the protocol.
|
||||
The hooks subsystem ships two bridge plugins: one that runs a user's existing Claude Code (CC) hooks, one for Codex hooks. The reference implementations (`~/repos/refs/claude-code`, `~/repos/refs/codex`) show a decisive fact: **Codex deliberately reimplements a SUBSET of the CC hook protocol.** Its engine reads the same `hooks.json`, uses the same matcher-group shape, the same exit-code/structured-stdout output contract, and the same command-hook execution model — Codex's source even names the engine after Claude's and comments where it "intentionally diverges." So the two bridges would otherwise duplicate the bulk of the protocol.
|
||||
|
||||
This Agent Note introduces `@deepseek-ai/dsh-hook-protocol`, a **library** (not a plugin — it registers and injects nothing) holding the genuinely-identical primitives both bridges build on. The split between shared and per-dialect is the design's center of gravity.
|
||||
|
||||
@@ -21,7 +21,7 @@ A new `packages/hooks/` group with `hook-protocol` as a pure library. It owns fo
|
||||
- **Merge** — `mergeHookOutputs(outputs)`, folding multiple matched hooks into one most-restrictive `MergedHookOutcome`: permission precedence **deny > ask > allow**, halt sticky on the first `continue:false`, block reasons joined `\n\n`, context/system-messages accumulated in order.
|
||||
- **`hook/*` session events** — `hook/invoked` / `hook/result`, declaration-merged into `SessionEventMap` (log-only, like `compact/*` — NOT `SurfaceEventType`s), with `appendHookInvoked`/`appendHookResult` helpers so the invoked/result pairing and owner-defined execution relation stay consistent across bridges. `appendHookResult` also owns the durable record's semantics — the decision string (the hook's parsed decision, else `'stop'` on `continue:false`, else `'pass'`) and the 500-character `stderrSummary` truncation derive from the `HookOutput` here, not per-bridge.
|
||||
|
||||
**Per-dialect (the bridge plugins):** building each event's stdin payload (CC's base+per-event field sets vs Codex's snake_case with `turn_id`/`model` extras), the dialect's env + `${CLAUDE_PLUGIN_ROOT}` substitution (CC) vs none (Codex), and mapping the neutral `HookOutput`/`MergedHookOutcome` onto the harness's seam-specific typed Decisions (`PreToolDecision`, `PreStepDecision`, `ContinuationDecision`, `PostToolDecision`).
|
||||
**Per-dialect (the bridge plugins):** building each event's stdin payload (CC's base+per-event field sets vs Codex's snake_case with `turn_id`/`model` extras), the dialect's env + `${CLAUDE_PLUGIN_ROOT}` substitution (CC) vs none (Codex), and mapping the neutral `HookOutput`/`MergedHookOutcome` onto the harness's extension-point-specific typed Decisions (`PreToolDecision`, `PreStepDecision`, `ContinuationDecision`, `PostToolDecision`).
|
||||
|
||||
## Alternatives considered
|
||||
|
||||
|
||||
@@ -6,7 +6,7 @@ Status: implemented
|
||||
|
||||
## 问题
|
||||
|
||||
钩子子系统提供两个桥接插件：一个运行用户既有的 Claude Code（CC）钩子，另一个运行 Codex 钩子。研究参考实现（`~/repos/refs/claude-code`、`~/repos/refs/codex`）后发现一个决定性事实：**Codex 有意重新实现了 CC 钩子协议的一个子集。** 它的引擎读取相同的 `hooks.json`，使用相同的 matcher-group 形状、相同的 exit-code/structured-stdout 输出契约，以及相同的命令钩子执行模型。Codex 的源码甚至以 Claude 的引擎命名，并在注释中标注了「有意偏离」之处。因此，如果不做抽取，两个桥接插件将大量重复协议逻辑。
|
||||
钩子子系统提供两个桥接插件：一个运行用户既有的 Claude Code（CC）钩子，另一个运行 Codex 钩子。参考实现（`~/repos/refs/claude-code`、`~/repos/refs/codex`）表明一个决定性事实：**Codex 有意重新实现了 CC 钩子协议的一个子集。** 它的引擎读取相同的 `hooks.json`，使用相同的 matcher-group 形状、相同的 exit-code/structured-stdout 输出约定，以及相同的命令钩子执行模型。Codex 的源码甚至以 Claude 的引擎命名，并在注释中标注了「有意偏离」之处。因此，如果不做抽取，两个桥接插件将大量重复协议逻辑。
|
||||
|
||||
本 Agent Note 引入 `@deepseek-ai/dsh-hook-protocol`，一个**库**（不是插件——它不注册也不注入任何东西），持有两个桥接插件共同依赖的真正相同的原语。共享与方言专属之间的分界是本设计的重心。
|
||||
|
||||
@@ -17,11 +17,11 @@ Status: implemented
|
||||
**共享（本库）：**
|
||||
- **Matcher** — `matcherDiagnostic(pattern, mode)` 与 `matchesMatcher(pattern, query, mode)`。两种方言的唯一差异收敛到 `mode` 参数：`claude` 将纯 `[A-Za-z0-9_|]+` pattern 视为字面量（管道符表示多个精确匹配备选项），其他 pattern 视为正则；`codex` 始终使用未锚定正则。缺省/`''`/`'*'` 匹配一切。每个桥接插件会在解析 group 前忽略不支持的事件，丢弃受支持但没有 matcher 匹配对象的事件所带字段，校验其余可运行 group；其中任何无效正则都会导致整份配置加载失败，并给出包含方言／pattern／事件的稳定诊断，不会注册任何钩子监听器。运行时匹配仍会将无效正则隔离为不匹配，因此直接调用本库绝不向 agent loop（智能体循环）抛异常。
|
||||
- **执行** — `runHook(bash, hook, options)`。通过 `ctx.bash` seam 而非自建 `spawn` 运行命令钩子：执行器已提供清洗但可覆盖的 env、进程组 kill 和超时，正是协议所需的能力；`dsh-bash` 的 `stdin`/`env` 字段（正是为此添加的）是进程内桥接插件被允许使用的受信插件接口。它将桥接插件构建的 payload 序列化到 stdin（仅 CC 时追加尾部换行），遵守钩子的 `timeoutSec`（否则使用 `DEFAULT_HOOK_TIMEOUT_MS`，即两种方言共享的 10 分钟参考默认值），且从不抛异常（执行器拒绝变为 non-blocking-error 的 `HookOutput`）。
|
||||
- **解码** — `parseHookOutput(exit, stdout, stderr)`，exit-code + structured-stdout 编解码器，产出方言无关的 `HookOutput`。Exit `0` → 宽松 JSON 解析 stdout；exit `2` → blocking error，`stderr` 为原因（以 `decision: 'block'` 呈现，调用方无需单独处理 exit-code 分支）；其他 → non-blocking error。解析 CC structured-stdout 中在某条路径上有消费方的字段（`continue`/`stopReason`/`decision`/`hookSpecificOutput.{permissionDecision,additionalContext,updatedInput}`/`systemMessage`）；桥接插件只采纳对其方言有意义的子集。在任何路径上都没有消费方的字段不予解析（CC 的 `suppressOutput`——钩子 stdout 在此处从不进入 transcript（文本记录），因此无需抑制；见 [收紧钩子协议契约 Agent Note](../simplification/2026-07-04-tighten-hook-protocol-contract.md)）。
|
||||
- **解码** — `parseHookOutput(exit, stdout, stderr)`，exit-code + structured-stdout 编解码器，产出方言无关的 `HookOutput`。Exit `0` → 宽松 JSON 解析 stdout；exit `2` → blocking error，`stderr` 为原因（以 `decision: 'block'` 呈现，调用方无需单独处理 exit-code 分支）；其他 → non-blocking error。解析 CC structured-stdout 中在某条路径上有消费方的字段（`continue`/`stopReason`/`decision`/`hookSpecificOutput.{permissionDecision,additionalContext,updatedInput}`/`systemMessage`）；桥接插件只采纳对其方言有意义的子集。在任何路径上都没有消费方的字段不予解析（CC 的 `suppressOutput`——钩子 stdout 在此处从不进入 transcript（文本记录），因此无需抑制；见 [收紧钩子协议约定 Agent Note](../simplification/2026-07-04-tighten-hook-protocol-contract.md)）。
|
||||
- **合并** — `mergeHookOutputs(outputs)`，将多个匹配钩子的输出折叠为一个最严格的 `MergedHookOutcome`：权限优先级 **deny > ask > allow**，halt 在首个 `continue:false` 时粘滞，阻止原因以 `\n\n` 拼接，context/system-messages 按序累积。
|
||||
- **`hook/*` 会话事件** — `hook/invoked` / `hook/result`，通过声明合并进入 `SessionEventMap`（仅日志，如 `compact/*`——不是 `SurfaceEventType`），配有 `appendHookInvoked`/`appendHookResult` 辅助函数，确保 invoked/result 配对与由所有者定义的执行关系在各桥接插件间保持一致。`appendHookResult` 还负责定义持久化记录的语义：decision 字符串（钩子解析出的 decision，否则 `continue:false` 时为 `'stop'`，否则为 `'pass'`）和 500 字符的 `stderrSummary` 截断均从本库的 `HookOutput` 派生，而非各桥接插件各自实现。
|
||||
|
||||
**方言专属（桥接插件）：** 构建每个事件的 stdin payload（CC 的 base+per-event 字段集 vs Codex 的 snake_case 加 `turn_id`/`model` 额外字段）、方言的 env 与 `${CLAUDE_PLUGIN_ROOT}` 替换（CC）vs 无替换（Codex），以及将方言无关的 `HookOutput`/`MergedHookOutcome` 映射为 harness seam 专属的类型化 Decision（`PreToolDecision`、`PreStepDecision`、`ContinuationDecision`、`PostToolDecision`）。
|
||||
**方言专属（桥接插件）：** 构建每个事件的 stdin payload（CC 的 base+per-event 字段集 vs Codex 的 snake_case 加 `turn_id`/`model` 额外字段）、方言的 env 与 `${CLAUDE_PLUGIN_ROOT}` 替换（CC）vs 无替换（Codex），以及将方言无关的 `HookOutput`/`MergedHookOutcome` 映射为 harness 各扩展点专属的类型化 Decision（`PreToolDecision`、`PreStepDecision`、`ContinuationDecision`、`PostToolDecision`）。
|
||||
|
||||
## 曾考虑的替代方案
|
||||
|
||||
|
||||
@@ -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/feature/2026-06-30-interception-extension-points.md
|
||||
2026-06-30-interception-extension-points.md: 68be3c94f55ae13155e9b22cb91ef1ad10b1e0ed
|
||||
2026-06-30-interception-extension-points.zh.md: 262793dd7a297f343391a22fb8d9f1d57a9ff531
|
||||
@@ -1,18 +1,18 @@
|
||||
# Agent Note: Interception seams — the typed-Decision surface a hook programs against
|
||||
# Agent Note: Interception extension points — the typed-Decision surface a hook programs against
|
||||
|
||||
Status: implemented
|
||||
|
||||
English | [中文](2026-06-30-interception-seams.zh.md)
|
||||
English | [中文](2026-06-30-interception-extension-points.zh.md)
|
||||
|
||||
## Problem
|
||||
|
||||
The harness needs a hooks subsystem: users extend or gate the agent at lifecycle points the way Claude Code (CC) and Codex do. The key reframe driving this design is that **"native hooks" are not a package** — a native hook is just an ordinary Cordis plugin subscribing to the canonical lifecycle events. So the real product is a *powerful, well-typed canonical event surface*; the CC/Codex bridges (the `dsh-hooks-claude` / `dsh-hooks-codex` packages) are merely translators that map an external shell-hook protocol onto that same surface. Anything a bridge can do, a plain plugin can do directly — more powerfully (no serialization boundary, full `ctx`, typed returns).
|
||||
|
||||
The surface needs distinct contracts for per-prompt policy (CC's `UserPromptSubmit`), session-start observation (CC's `SessionStart`), pre-tool policy, around-dispatch control, post-tool transformation, final-result observation, and continuation with a model-facing reason. Conflating those phases gives plugins mutation channels they do not need and makes finality depend on listener ordering. The [event-domain-semantics Agent Note](../architecture/2026-06-30-event-domain-semantics.md) supplies the three-domain rule and the typed-Decision idiom; this Agent Note applies them to the lifecycle seams.
|
||||
The surface needs distinct contracts for per-prompt policy (CC's `UserPromptSubmit`), session-start observation (CC's `SessionStart`), pre-tool policy, around-dispatch control, post-tool transformation, final-result observation, and continuation with a model-facing reason. Conflating those phases gives plugins mutation channels they do not need and makes finality depend on listener ordering. The [event-domain-semantics Agent Note](../architecture/2026-06-30-event-domain-semantics.md) supplies the three-domain rule and the typed-Decision idiom; this Agent Note applies them to the lifecycle extension points.
|
||||
|
||||
## Decision
|
||||
|
||||
The canonical surface separates transformable policy, around-dispatch control, and observe-only notification. Policy waterfalls return small seam-specific **typed Decision unions**; wrappers return normalized results; notifications receive immutable snapshots and cannot affect the outcome. The set covers the hook points in scope (`session-start`, `prompt-submit`, `pre-tool`, `post-tool`, `stop`-via-continuation) while leaving non-hook execution policy independently composable.
|
||||
The canonical surface separates transformable policy, around-dispatch control, and observe-only notification. Policy waterfalls return small extension-point-specific **typed Decision unions**; wrappers return normalized results; notifications receive immutable snapshots and cannot affect the outcome. The set covers the hook points in scope (`session-start`, `prompt-submit`, `pre-tool`, `post-tool`, `stop`-via-continuation) while leaving non-hook execution policy independently composable.
|
||||
|
||||
**Agent events** (`dsh-agent`):
|
||||
- `agent/session-start({ agent, source })` — emit, once before turn 1, carrying a `SessionStartSource` (`startup` for a fresh/forked create, `resume` for a reloaded persisted session; `clear`/`compact` reserved). A pure notification — it CANNOT block startup (a deliberate gap: a bridge logs/injects, it does not gate startup). A listener seeds context via `agent.inject()`.
|
||||
@@ -47,13 +47,13 @@ Core dispatch and the tool body sit inside normalization boundaries, so tool, li
|
||||
|
||||
### Boundaries
|
||||
|
||||
The seam package does **not** declare `hook/*` session events (the durable hook-invocation log); those belong to `dsh-hook-protocol`, because a native plugin uses typed decisions without an external hook log. The native-plugin integration test (`packages/core/agent-loop/tests/interception.spec.ts`) composes the seams through the real loop with no `hook/*` protocol. Compaction (`PreCompact`/`PostCompact`), Notification, and Codex `PermissionRequest` remain outside this decision. The [approval seam](2026-07-06-approval-seam.md) resolves `ask` decisions through `ctx.approval`; terminal monotonic stopping is expressed by tool-result data, while `agent/turn-stopping` is the last chance to steer another step.
|
||||
The Service Definition package does **not** declare `hook/*` session events (the durable hook-invocation log); those belong to `dsh-hook-protocol`, because a native plugin uses typed decisions without an external hook log. The native-plugin integration test (`packages/core/agent-loop/tests/interception.spec.ts`) composes the extension points through the real loop with no `hook/*` protocol. Compaction (`PreCompact`/`PostCompact`), Notification, and Codex `PermissionRequest` remain outside this decision. The [approval seam](2026-07-06-approval-seam.md) resolves `ask` decisions through `ctx.approval`; terminal monotonic stopping is expressed by tool-result data, while `agent/turn-stopping` is the last chance to steer another step.
|
||||
|
||||
## Alternatives considered
|
||||
|
||||
- **Shipping pre-tool INPUT rewrite as part of this seam set** — deferred as the over-reach signal; the section above carries the consistency problem (audit, history, and presentation all read `tool/call.arguments` logged before execution), and [the pre-tool input-rewrite proposal](../../proposed/feature/2026-06-30-pre-tool-input-rewrite.md) owns the design.
|
||||
- **Declaring the durable `hook/*` SessionEvents alongside the seams** — rejected: a native plugin uses the typed Decisions with no hook log at all (the worked example proves it), so the durable log belongs to [the hook-protocol library](2026-06-30-hook-protocol-lib.md), not the seam surface.
|
||||
- **Shipping pre-tool INPUT rewrite as part of this extension-point set** — deferred as the over-reach signal; the section above carries the consistency problem (audit, history, and presentation all read `tool/call.arguments` logged before execution), and [the pre-tool input-rewrite proposal](../../proposed/feature/2026-06-30-pre-tool-input-rewrite.md) owns the design.
|
||||
- **Declaring the durable `hook/*` SessionEvents alongside the extension points** — rejected: a native plugin uses the typed Decisions with no hook log at all (the worked example proves it), so the durable log belongs to [the hook-protocol library](2026-06-30-hook-protocol-lib.md), not the extension surface.
|
||||
|
||||
## Consequences
|
||||
|
||||
The canonical interception surface is uniformly typed without giving every extension the same power: hooks return decisions, execution wrappers wrap, terminal guards only deny, and final observers only observe. The loop owns session-start, pre-step claim settlement, post-tool context buffering, and stopping; `dsh-tools` owns identity sealing and the five-phase execution pipeline. Their contracts are documented in [architecture.md](../../../../docs/architecture.md), package READMEs, [core interception decisions](../../../../docs/core-data-structures/core.md#interception-decisions), and [tool structures](../../../../docs/core-data-structures/tools.md). The ACP bridge settles an initial pre-step rejection from its blocked no-step turn as `end_turn`, while hook-driven snapshots verify the observable bridge behavior end to end.
|
||||
The canonical interception surface is uniformly typed without giving every extension the same power: hooks return decisions, execution wrappers wrap, terminal guards only deny, and final observers only observe. The loop owns session-start, pre-step claim settlement, post-tool context buffering, and stopping; `dsh-tools` owns identity sealing and the five-phase execution pipeline. Their contracts are documented in [architecture.md](../../../../docs/architecture.md), package READMEs, [core interception decisions](../../../../docs/subsystems/core.md#interception-decisions), and [tool structures](../../../../docs/subsystems/tools.md). The ACP bridge settles an initial pre-step rejection from its blocked no-step turn as `end_turn`, while hook-driven snapshots verify the observable bridge behavior end to end.
|
||||
@@ -1,18 +1,18 @@
|
||||
# Agent Note: 拦截 seam——钩子编程所面对的类型化 Decision 表面
|
||||
# Agent Note: 拦截扩展点——钩子编程所面对的类型化 Decision 表面
|
||||
|
||||
Status: implemented
|
||||
|
||||
[English](2026-06-30-interception-seams.md) | 中文
|
||||
[English](2026-06-30-interception-extension-points.md) | 中文
|
||||
|
||||
## 问题
|
||||
|
||||
harness 需要一套钩子子系统：用户像 Claude Code（CC）和 Codex 那样在生命周期节点扩展或管控 agent（智能体）。驱动本设计的关键视角转换是：**「原生钩子」不是一个包**——原生钩子只是一个普通的 Cordis 插件，订阅规范的生命周期事件。因此真正的产品是一个*强大、类型完备的规范事件表面*；CC/Codex 桥接（`dsh-hooks-claude` / `dsh-hooks-codex` 包）只是将外部 shell 钩子协议映射到同一表面的翻译层。桥接能做的事，普通插件可以直接做——而且更强大（无序列化边界、完整 `ctx`、类型化返回值）。
|
||||
|
||||
该表面需要为以下场景提供各自独立的契约：逐提示词策略（CC 的 `UserPromptSubmit`）、会话启动观测（CC 的 `SessionStart`）、工具执行前策略、环绕调度控制、工具执行后变换、最终结果观测，以及携带面向模型的原因的继续执行。如果把这些阶段混为一谈，插件就会获得不需要的 mutation 通道，而终结性将依赖监听器的注册顺序。[事件域语义 Agent Note](../architecture/2026-06-30-event-domain-semantics.md) 提供了三域规则与类型化 Decision 惯用法；本 Agent Note 将其应用于生命周期 seam。
|
||||
该表面需要为以下场景提供各自独立的约定：逐提示词策略（CC 的 `UserPromptSubmit`）、会话启动观测（CC 的 `SessionStart`）、工具执行前策略、环绕调度控制、工具执行后变换、最终结果观测，以及携带面向模型的原因的继续执行。如果把这些阶段混为一谈，插件就会获得不需要的 mutation 通道，而终结性将依赖监听器的注册顺序。[事件域语义 Agent Note](../architecture/2026-06-30-event-domain-semantics.md) 提供了三域规则与类型化 Decision 惯用法；本 Agent Note 将其应用于生命周期扩展点。
|
||||
|
||||
## 决策
|
||||
|
||||
规范表面将可变换策略、环绕调度控制与仅观测通知分离。策略 waterfall（瀑布式事件）返回小型的、seam 专属的**类型化 Decision 联合类型**；包装层返回规范化结果；通知接收不可变快照，无法影响结果。覆盖的钩子点包括 `session-start`、`prompt-submit`、`pre-tool`、`post-tool`、通过 continuation 实现的 `stop`，同时将非钩子的执行策略留作独立可组合。
|
||||
规范表面将可变换策略、环绕调度控制与仅观测通知分离。策略 waterfall（瀑布式事件）返回小型的、扩展点专属的**类型化 Decision 联合类型**；包装层返回规范化结果；通知接收不可变快照，无法影响结果。覆盖的钩子点包括 `session-start`、`prompt-submit`、`pre-tool`、`post-tool`、通过 continuation 实现的 `stop`，同时将非钩子的执行策略留作独立可组合。
|
||||
|
||||
**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。
|
||||
@@ -31,7 +31,7 @@ harness 需要一套钩子子系统：用户像 Claude Code（CC）和 Codex 那
|
||||
- **`ToolDefinition.finalizeContent`** 是一个可选、同步、对所有输入都有定义且仅能处理内容的边界，在调用创建时随可见定义一起被快照。注册表将候选结果规范化并创建无损快照后，它恰好运行一次；候选结果包括绕过后续 waterfall 的 pre、around 或 post 监听器失败，以及为另一个结果字段创建快照时发现的错误。它可以替换 `content`，也可返回 `undefined` 保留原内容，但不能重写 `isError`、结构化错误身份、上下文或呈现元数据。工具在此执行自身最后一道内容不变式，而无需将策略失败转换为更弱的阻止 decision。
|
||||
- **`tools/result`** 是在所有变换、无损 JSON 实体化和外层错误边界之后的同步且故障受控的通知。它接收相同的冻结执行身份和权威结果的不可变快照；观测者的失败按监听器隔离，无法改变或拒绝 `ToolRegistry.execute()` 返回的结果。
|
||||
|
||||
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；由工具定义负责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。
|
||||
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；由工具定义负责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。[规范工具输出约定](../architecture/2026-07-20-canonical-tool-output-contract.md)定义值／投影与持久性规则。
|
||||
|
||||
### 三个承重的循环决策
|
||||
|
||||
@@ -43,17 +43,17 @@ harness 需要一套钩子子系统：用户像 Claude Code（CC）和 Codex 那
|
||||
|
||||
### 工具执行前输入重写是一个独立的一致性决策
|
||||
|
||||
`PreToolDecision` 不能重写参数。历史和审计调用在执行前记录，UI 展示读取相同的输入，因此注册表在策略之前封存参数。有效的重写必须在身份创建之前同时更新历史、审计、展示和执行；该契约属于[输入重写提案](../../proposed/feature/2026-06-30-pre-tool-input-rewrite.md)。
|
||||
`PreToolDecision` 不能重写参数。历史和审计调用在执行前记录，UI 展示读取相同的输入，因此注册表在策略之前封存参数。有效的重写必须在身份创建之前同时更新历史、审计、展示和执行；该约定属于[输入重写提案](../../proposed/feature/2026-06-30-pre-tool-input-rewrite.md)。
|
||||
|
||||
### 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；终结性的单调停止由工具结果数据表达，而 `agent/turn-stopping` 是引导再执行一步的最后机会。
|
||||
Service Definition 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扩展点，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/turn-stopping` 是引导再执行一步的最后机会。
|
||||
|
||||
## 曾考虑的替代方案
|
||||
|
||||
- **将工具执行前输入重写作为本 seam 集的一部分发布**：推迟，视为越界信号；上文已阐述一致性问题（审计、历史和展示都读取执行前记录的 `tool/call.arguments`），[工具执行前输入重写提案](../../proposed/feature/2026-06-30-pre-tool-input-rewrite.md)负责该设计。
|
||||
- **将持久的 `hook/*` SessionEvents 与 seam 一起声明**：否决。原生插件使用类型化 Decision 而完全不需要钩子日志（实际示例已证明），因此持久日志属于[钩子协议库](2026-06-30-hook-protocol-lib.md)，而非 seam 表面。
|
||||
- **将工具执行前输入重写作为本扩展点集合的一部分发布**：推迟，视为越界信号；上文已阐述一致性问题（审计、历史和展示都读取执行前记录的 `tool/call.arguments`），[工具执行前输入重写提案](../../proposed/feature/2026-06-30-pre-tool-input-rewrite.md)负责该设计。
|
||||
- **将持久的 `hook/*` SessionEvents 与扩展点一起声明**：否决。原生插件使用类型化 Decision 而完全不需要钩子日志（实际示例已证明），因此持久日志属于[钩子协议库](2026-06-30-hook-protocol-lib.md)，而非扩展表面。
|
||||
|
||||
## 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、pre-step 领取结算、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 桥接会把 blocked 无步骤轮次中的首次 pre-step reject 结算为 `end_turn`，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、pre-step 领取结算、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。它们的约定记录在 [architecture.md](../../../../docs/architecture.md)、各包 README、[核心拦截 decision](../../../../docs/subsystems/core.md#interception-decisions) 与[工具结构](../../../../docs/subsystems/tools.md)中。ACP 桥接会把 blocked 无步骤轮次中的首次 pre-step reject 结算为 `end_turn`，而钩子驱动的快照端到端验证可观测的桥接行为。
|
||||
@@ -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/2026-06-30-session-store-fork-api.md
|
||||
2026-06-30-session-store-fork-api.md: 69ff85e1f137f4f263bf951af0a3f655411c606a
|
||||
2026-06-30-session-store-fork-api.zh.md: 75262c8ceca40745feba1d4384cb949b95f3c677
|
||||
2026-06-30-session-store-fork-api.md: 85e748ba4e42919eac49cae583a08c72e0c3c0a0
|
||||
2026-06-30-session-store-fork-api.zh.md: f985c93085cbc2dbb1b8a768dac82a40025ea54d
|
||||
|
||||
@@ -36,7 +36,7 @@ The Host creates the child through the agent registry with the selected seed and
|
||||
|
||||
## Alternatives considered
|
||||
|
||||
**Separate `ctx.sessionFork` service.** This was the first implementation, but review showed it overfit the capability-seam pattern. The code had no swappable backend, no extra event surface, no independent ownership lifecycle, and no durable behavior beyond `ctx.sessions.create({ seed, meta })`. Keeping a separate package would make callers discover and install a second service just to perform policy around a session-store primitive.
|
||||
**Separate `ctx.sessionFork` service.** An earlier iteration shipped this as a separate service; it overfit the capability-seam pattern. The code had no swappable backend, no extra event surface, no independent ownership lifecycle, and no durable behavior beyond `ctx.sessions.create({ seed, meta })`. Keeping a separate package would make callers discover and install a second service just to perform policy around a session-store primitive.
|
||||
|
||||
**Two functions: `snapshot()` plus `fork()`.** This preserved a reusable seed/metadata computation, but the only supported consumer created a session immediately. It also made the surface feel more abstract than the concrete operation users need. A single `fork()` with an explicit `boundary` keeps the API direct while still supporting previous-point forks.
|
||||
|
||||
|
||||
@@ -36,7 +36,7 @@ Host 通过 agent（智能体）注册表，以选定的种子和谱系创建子
|
||||
|
||||
## 曾考虑的替代方案
|
||||
|
||||
**独立的 `ctx.sessionFork` 服务。** 这是最初的实现，但评审表明它过度套用了能力 seam 模式。代码没有可替换的后端、没有额外的事件面、没有独立的所有权生命周期，也没有超出 `ctx.sessions.create({ seed, meta })` 的持久化行为。保留独立包会迫使调用方为了在会话存储原语之上执行一层策略而去发现并安装第二个服务。
|
||||
**独立的 `ctx.sessionFork` 服务。** 较早的一版迭代曾把它作为独立服务交付；它过度套用了能力 seam 模式。代码没有可替换的后端、没有额外的事件面、没有独立的所有权生命周期，也没有超出 `ctx.sessions.create({ seed, meta })` 的持久化行为。保留独立包会迫使调用方为了在会话存储原语之上执行一层策略而去发现并安装第二个服务。
|
||||
|
||||
**两个函数：`snapshot()` 加 `fork()`。** 这保留了一个可复用的种子／元数据计算，但唯一支持的消费方会立即创建会话。它还使接口看起来比用户实际需要的具体操作更抽象。单一的 `fork()` 加显式 `boundary` 使 API 保持直接，同时仍支持对先前时间点的 fork。
|
||||
|
||||
@@ -46,4 +46,4 @@ Host 通过 agent（智能体）注册表，以选定的种子和谱系创建子
|
||||
|
||||
公开接口保持精简且易于发现：活跃会话分支是 `ctx.sessions` 的一部分，紧邻 `create({ seed })`，而非一个独立服务或一对两步辅助函数。持久化继续通过现有的 `session/created` 和 `session/flush` 行为运作：fork 出的子会话创建时便带有种子事件，因此现有后端只需持久化该种子一次，并在 header 中保存 `parentSession`／`seedLength`。
|
||||
|
||||
v1 范围仍然排除 ACP（Agent Client Protocol） `session/fork`、对未加载的已持久化会话的 fork、面向模型的工具，以及 subagent 重构。如果未来添加 ACP 方法，应在具备协议与快照覆盖后才声明支持该能力；本 Agent Note 不添加任何 ACP 协议行为，因此不需要 ACP 快照。fork 子会话的回放仍由现有的[种子边界测试 Agent Note](../testing/2026-06-22-fork-child-replay-seed-boundary.md) 覆盖；store、Host、载体与客户端的专项测试固定边界和对账契约，真实 Chromium 场景则固定组装后的消息操作与谱系树。
|
||||
v1 范围仍然排除 ACP（Agent Client Protocol） `session/fork`、对未加载的已持久化会话的 fork、面向模型的工具，以及 subagent 重构。如果未来添加 ACP 方法，应在具备协议与快照覆盖后才声明支持该能力；本 Agent Note 不添加任何 ACP 协议行为，因此不需要 ACP 快照。fork 子会话的回放仍由现有的[种子边界测试 Agent Note](../testing/2026-06-22-fork-child-replay-seed-boundary.md) 覆盖；store、Host、载体与客户端的专项测试固定边界和对账约定，真实 Chromium 场景则固定组装后的消息操作与谱系树。
|
||||
|
||||
@@ -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/2026-07-05-dynamic-workflows.md
|
||||
2026-07-05-dynamic-workflows.md: bba62098c66477a3f1929f9029e81c645bfc4d41
|
||||
2026-07-05-dynamic-workflows.zh.md: 2005ca14883ae137148541273900c7f3e65769a5
|
||||
2026-07-05-dynamic-workflows.md: 3e491478286eb77b56872fcbbdd5ebb6b62a5545
|
||||
2026-07-05-dynamic-workflows.zh.md: 7888d83f981a96ac5eb31d5ca6f1f8d0b4930ec7
|
||||
|
||||
@@ -10,7 +10,7 @@ The harness can delegate ONE task to ONE child (`dsh-tool-subagent`), but work t
|
||||
|
||||
## Decision
|
||||
|
||||
A workflow capability family at `packages/workflow/` in the bash seam shape (interface / implementation / consumer), plus the structured-output foundation it needs on the subagent seam.
|
||||
A workflow capability family at `packages/workflow/` in the bash seam shape (Service Definition / Service provider / Consumer), plus the structured-output foundation it needs on the subagent seam.
|
||||
|
||||
### The script contract (Claude Code-compatible)
|
||||
|
||||
@@ -20,7 +20,7 @@ One deliberate strictness DIVERGENCE from CC: hook misuse — unknown or deferre
|
||||
|
||||
### The seam (dsh-workflow)
|
||||
|
||||
`ctx.workflows` is an abstract `WorkflowService` in the bash shape — one engine per context, no named-provider registry (engines are deployment swaps, not co-residents). `start(request)` throws synchronously for a script that cannot begin; a returned `WorkflowRun`'s `result` NEVER rejects (failures resolve as `stopReason: 'error' | 'cancelled'`). The `workflow/*` events are observe-only emits carrying DATA SNAPSHOTS (id + meta; `workflow/end` omits the result value), per-listener contained, mirroring `subagent/start`/`subagent/end` — control stays with the run's holder. Vocabulary details: [core-data-structures/workflow.md](../../../../docs/core-data-structures/workflow.md).
|
||||
`ctx.workflows` is an abstract `WorkflowService` in the bash shape — one engine per context, no named-provider registry (engines are deployment swaps, not co-residents). `start(request)` throws synchronously for a script that cannot begin; a returned `WorkflowRun`'s `result` NEVER rejects (failures resolve as `stopReason: 'error' | 'cancelled'`). The `workflow/*` events are observe-only emits carrying DATA SNAPSHOTS (id + meta; `workflow/end` omits the result value), per-listener contained, mirroring `subagent/start`/`subagent/end` — control stays with the run's holder. Vocabulary details: [subsystems/workflow.md](../../../../docs/subsystems/workflow.md).
|
||||
|
||||
### The engine (dsh-workflow-workerthread): one worker thread per run
|
||||
|
||||
@@ -36,7 +36,7 @@ The engine exposes an in-process `MessageChannel` test path because main-process
|
||||
|
||||
**Value boundary**: `materializeFromRealm` copies outbound values and rejects functions, symbols, nested `undefined`, exotic prototypes, cycles, sparse arrays, and non-finite numbers. Data-property copies make `"__proto__"` safe; getters are read normally and a throwing getter fails loudly. `args` crosses through `workerData` and is cloned again before exposure. Realm functions are invoked rather than copied, and thrown values use a total renderer so `result` cannot reject. Hook errors are host-realm `WorkflowError`s, so scripts branch on `name` or `code` rather than `instanceof Error`, as documented in the engine README. Concurrency, total-agent, item, timeout, and grace limits are validated config.
|
||||
|
||||
### The consumer (dsh-tool-workflow)
|
||||
### The Consumer (`dsh-tool-workflow`)
|
||||
|
||||
A `workflow` tool mirroring `dsh-tool-subagent`'s synchronous shape: start, await, `try/finally` dispose, abort-bridge `exec.signal`, non-`completed` → `isError`. Render intent: a `generic` card titled by the call's `meta.name` parameter (presentation is a pure function of args). The tool description IS the model-facing authoring spec. The usage policy ships with the tool as its own `tool:<toolName>` prompt section (explicit-ask-only guidance — tool guidance lives in tool plugins, never in the deployment persona); the harness has no ultracode-style effort gate.
|
||||
|
||||
@@ -52,7 +52,7 @@ An output schema makes a schema-valid committed capture mandatory for successful
|
||||
|
||||
Worker-side logic runs through an in-process `MessageChannel` so V8 coverage measures it. Unit tests cover script helpers, fatal and nullable failures, JSON boundaries, caps, cancellation, child ownership, and structured output through real loops. A built-bin smoke runs the separately bundled `lib/worker.cjs` under plain Node, a with-key e2e drives real child agents, and model-facing workflow behavior is snapshot-covered through its owning example.
|
||||
|
||||
## Deferred (documented non-goals of this cut)
|
||||
## Deferred (documented non-goals)
|
||||
|
||||
- **Background collection** (start tool → run id → completion notice → collect), designed alongside bash/subagent background unification.
|
||||
- **Journaling + resume** (`resumeFromRunId`, cached agent() prefixes) — implementing it reintroduces CC's determinism bans as a script-contract tightening (scripts may read the clock today).
|
||||
|
||||
@@ -10,9 +10,9 @@ harness 可以将一个任务委派给一个子 agent（`dsh-tool-subagent`）
|
||||
|
||||
## 决策
|
||||
|
||||
在 `packages/workflow/` 下以 bash seam 的形态（接口／实现／消费方）提供一组工作流能力，以及它在 subagent seam 上所需的结构化输出基础。
|
||||
在 `packages/workflow/` 下以 bash seam 的形态（Service Definition／Service provider／Consumer）提供一组工作流能力，以及它在 subagent seam 上所需的结构化输出基础。
|
||||
|
||||
### 脚本契约（兼容 Claude Code）
|
||||
### 脚本约定（兼容 Claude Code）
|
||||
|
||||
一次工作流调用包含 JSON `meta`（`name`、`description`，以及可选的 `whenToUse`/`phases`）和一段支持顶层 `await` 并返回 JSON 值的 JavaScript `script` 正文。元数据作为数据校验，从不被执行。正文接收 `agent(prompt, options)`、`parallel(thunks)`、`pipeline(items, ...stages)`、`phase(title)`、`log(message)` 和 `args`。流水线各阶段接收 `(prev, item, index)`，阶段之间无屏障；失败的子 agent 和普通阶段错误将受影响的 item 结算为 `null` 并跳过其剩余阶段。Claude Code 的确定性限制随日志机制一并延后实现，因此兼容的脚本正文在将 meta 头移入参数后可以使用时钟和随机数。
|
||||
|
||||
@@ -20,7 +20,7 @@ harness 可以将一个任务委派给一个子 agent（`dsh-tool-subagent`）
|
||||
|
||||
### seam（dsh-workflow）
|
||||
|
||||
`ctx.workflows` 是 bash 形态的抽象 `WorkflowService`——每个上下文一个引擎，无命名提供方注册表（引擎是部署级替换，不是共存者）。`start(request)` 对无法启动的脚本同步抛出；返回的 `WorkflowRun` 的 `result` 永不 reject（失败时结算为 `stopReason: 'error' | 'cancelled'`）。`workflow/*` 事件是仅观察的 emit，携带数据快照（id + meta；`workflow/end` 省略 result 值），按监听器隔离，与 `subagent/start`/`subagent/end` 对称——控制权留在 run 的持有者手中。词汇详情见 [core-data-structures/workflow.md](../../../../docs/core-data-structures/workflow.md)。
|
||||
`ctx.workflows` 是 bash 形态的抽象 `WorkflowService`——每个上下文一个引擎，无命名提供方注册表（引擎是部署级替换，不是共存者）。`start(request)` 对无法启动的脚本同步抛出；返回的 `WorkflowRun` 的 `result` 永不 reject（失败时结算为 `stopReason: 'error' | 'cancelled'`）。`workflow/*` 事件是仅观察的 emit，携带数据快照（id + meta；`workflow/end` 省略 result 值），按监听器隔离，与 `subagent/start`/`subagent/end` 对称——控制权留在 run 的持有者手中。词汇详情见 [subsystems/workflow.md](../../../../docs/subsystems/workflow.md)。
|
||||
|
||||
### 引擎（dsh-workflow-workerthread）：每次运行一个 worker 线程
|
||||
|
||||
@@ -28,7 +28,7 @@ harness 可以将一个任务委派给一个子 agent（`dsh-tool-subagent`）
|
||||
|
||||
**为何选择 `node:worker_threads`**：每次运行获得一个非池化的 worker。vm 上下文限定了文档中说明的脚本接口范围，而消息端口 RPC 将 `agent()` 桥接到宿主侧的子循环。worker 防止脚本的同步工作阻塞宿主，提供序列化边界，并允许取消后强制终止。`isolated-vm` 因其维护状态和部署要求被否决。
|
||||
|
||||
宿主在发布前校验元数据并解析正文。私有枚举键 payload 映射定义协议格式；待启动记录、已发布子记录、单一取消信号、worker 死亡回收、结果优先级与 dispose 完全停稳，在此协议上保持 subagent run 契约。这些竞态算法由 [agent 作用域运行时设计 Agent Note](../architecture/2026-07-12-agent-scope-runtime-design.md#workflow-children-are-pending-starts-or-published-records) 定义。
|
||||
宿主在发布前校验元数据并解析正文。私有枚举键 payload 映射定义协议格式；待启动记录、已发布子记录、单一取消信号、worker 死亡回收、结果优先级与 dispose 完全停稳，在此协议上保持 subagent run 约定。这些竞态算法由 [agent 作用域运行时设计 Agent Note](../architecture/2026-07-12-agent-scope-runtime-design.md#workflow-children-are-pending-starts-or-published-records) 定义。
|
||||
|
||||
引擎暴露一条进程内 `MessageChannel` 测试路径，因为主进程 V8 覆盖率无法观测 worker 执行。
|
||||
|
||||
@@ -36,7 +36,7 @@ harness 可以将一个任务委派给一个子 agent（`dsh-tool-subagent`）
|
||||
|
||||
**值边界**：`materializeFromRealm` 复制出站值，并拒绝函数、symbol、嵌套 `undefined`、异域原型、循环引用、稀疏数组和非有限数字。数据属性复制使 `"__proto__"` 安全；getter 正常读取，抛出异常的 getter 会明确报错。`args` 通过 `workerData` 传入，暴露前再次克隆。realm 函数被调用而非复制，抛出的值使用对所有输入均有定义的渲染器，因此 `result` 不会 reject。钩子错误是宿主 realm 的 `WorkflowError`，脚本应基于 `name` 或 `code` 分支而非 `instanceof Error`，如引擎 README 所述。并发、total-agent、item、超时和宽限限制均为经校验的配置。
|
||||
|
||||
### 消费方（dsh-tool-workflow）
|
||||
### Consumer（`dsh-tool-workflow`）
|
||||
|
||||
一个 `workflow` 工具，镜像 `dsh-tool-subagent` 的同步形态：启动、await、`try/finally` dispose、abort 桥接 `exec.signal`、非 `completed` → `isError`。渲染意图：一张以调用的 `meta.name` 参数为标题的 `generic` 卡片（展示是参数的纯函数）。工具描述即面向模型的编写规范。使用策略以工具自身的 `tool:<toolName>` 提示词段落随工具发布（显式请求才使用的引导——工具引导存在于工具插件中，从不在部署 persona 中）；harness 没有 ultracode 风格的 effort 门控。
|
||||
|
||||
@@ -52,10 +52,10 @@ harness 可以将一个任务委派给一个子 agent（`dsh-tool-subagent`）
|
||||
|
||||
worker 侧逻辑通过进程内 `MessageChannel` 运行，使 V8 覆盖率能够度量它。单元测试覆盖脚本辅助函数、fatal 与 nullable 失败、JSON 边界、上限、取消、子 agent 所有权和通过真实循环的结构化输出。构建后二进制文件的冒烟测试在纯 Node 下运行单独打包的 `lib/worker.cjs`，带密钥的 e2e 驱动真实子 agent，面向模型的工作流行为通过其所属示例进行快照覆盖。
|
||||
|
||||
## 延迟（本轮明确的非目标）
|
||||
## 延迟（明确的非目标）
|
||||
|
||||
- **后台收集**（启动工具 → run id → 完成通知 → 收集），与 bash/subagent 后台统一一起设计。
|
||||
- **日志化 + 恢复**（`resumeFromRunId`、缓存的 agent() 前缀）：实现它会以脚本契约收紧的形式重新引入 CC 的确定性禁令（脚本目前可以读取时钟）。
|
||||
- **日志化 + 恢复**（`resumeFromRunId`、缓存的 agent() 前缀）：实现它会以脚本约定收紧的形式重新引入 CC 的确定性禁令（脚本目前可以读取时钟）。
|
||||
- **保存/打包的工作流**（`.deepseek/workflows/` 注册表、斜杠命令界面）和**脚本持久化到运行目录**（工具调用事件已经持久记录了脚本）。
|
||||
- **嵌套 `workflow()`**、**token `budget`**，以及 `effort`/`isolation`/`agentType` agent 选项（每个都会明确拒绝，并在消息中注明其已延迟实现）。
|
||||
- **整体运行的挂钟超时**：取消总能释放调用方（result 在宽限期内 settle），因此总运行时间上限是后台重设计的策略旋钮，不是此处的正确性需求。
|
||||
|
||||
@@ -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/2026-07-05-skill-system.md
|
||||
2026-07-05-skill-system.md: dd2fb1d22949f55ea7cb2c9f280e7cfbfcbbb226
|
||||
2026-07-05-skill-system.zh.md: 96656a8e1dfc2ae1ce7301ba29e7739349b6aab6
|
||||
2026-07-05-skill-system.md: c4b177d84c97e5c541bffb6dfeb2135aedb8d5b8
|
||||
2026-07-05-skill-system.zh.md: d0ca688e96c10e674c9b92da8805d653ce5fd063
|
||||
|
||||
@@ -14,19 +14,21 @@ DeepSeek Harness uses the same primitive so project-specific review, plugin-auth
|
||||
|
||||
`@deepseek-ai/dsh-skill` is the pure provider registry (`ctx.skills`), `@deepseek-ai/dsh-skill-local` is the shipped local filesystem provider, and `@deepseek-ai/dsh-tool-skill` owns the durable session catalog and model-facing loader tool. `dsh-agent-spine-demo` loads the registry, local provider, and consumer by default so TUI, headless, and ACP apps get the same behavior while embedded or remote providers contribute skills without changing the registry or consumer. Its `skills` config forwards `registry`, `local`, and `tool` branches to those owners.
|
||||
|
||||
Dedicated packaged providers can contribute immutable skills without filesystem discovery. The shipped CLI declares `@deepseek-ai/dsh-skill-badge` disabled by default; enabling its composition row contributes the official badge instructions through the same registry and consumer ([decision](2026-08-06-bundled-dsh-badge-skill.md)).
|
||||
|
||||
Provider plugins register synchronously during `apply()`. Provider membership is direct effect-owned state: registration and disposal invalidate completed catalogs synchronously, and discovery reads the current provider map on demand rather than observing registry-change events. Provider catalogs return ranked candidates from awaited `list()` calls, where remote providers perform initialization, authentication, and discovery while honoring the lookup abort signal. The registry validates each candidate, resolves same-name skills first-wins by rank, provider registration order, and provider-local order, then sorts summaries by skill name for deterministic consumers. It caches only completed catalog snapshots and retries when a provider/runtime revision changes during discovery, so an unload cannot freeze a stale, unresolvable skill into a session catalog. Runtime `ctx.skills.register(...)` remains a convenience for embedded in-process skills and uses project-over-user priority; `runtime` is reserved as the registry-owned provider name.
|
||||
|
||||
The local provider scans cwd-sensitive project roots, custom roots, and user roots in first-wins rank order: project `.dsh`, project `.agents`, `customSkillDirs`, user `.dsh`, then user `.agents`. The user `.dsh/skills` scan skips `.system` so a system-owned directory is not treated as normal user content. DeepSeek Harness does not ship built-in system skills; embedded or remote providers supply additional skills when configured.
|
||||
The local provider scans cwd-sensitive project roots, custom roots, and user roots in first-wins rank order: project `.dsh`, project `.agents`, `customSkillDirs`, user `.dsh`, then user `.agents`. The user `.dsh/skills` scan skips `.system` so a system-owned directory is not treated as normal user content. The local provider does not synthesize built-in system skills; configured bundled roots and dedicated providers supply additional skills.
|
||||
|
||||
Each skill is either `<name>/SKILL.md` or `<name>.md` with YAML frontmatter. `name` and `description` are required; `whenToUse`, `metadata`, `disable-model-invocation`, and `user-invocable` are optional. Names are kebab-case. The invocation fields project into a typed nested policy as defined by the [independent model and user invocation decision](2026-07-28-skill-invocation-policy.md); the parser rejects the old camel-case spellings. YAML frontmatter is parsed with the `yaml` package instead of `js-yaml` or a hand-written parser: `yaml` is the already-declared modern parser for this package's limited frontmatter needs, and a narrow parser would either reject valid YAML users expect to work or grow into an unreviewed YAML subset.
|
||||
|
||||
Local skill filesystem I/O goes through `ctx.fs` when a filesystem service is loaded: project-root lookup probes `.git` with `resolve` and `stat`, root discovery uses `listDir`, and skill reads use `readText`. The Node filesystem remains a fallback for minimal contexts that mount `dsh-skill-local` without the fs seam. Missing roots, unreadable or malformed skill files, and transient provider `list()` failures degrade to warn-and-skip so one bad source does not make every agent request fail; malformed candidates still fail fast because they are provider contract violations.
|
||||
|
||||
`dsh-tool-skill` injects one durable user-role `<system-reminder>` catalog as a sourced `user/message` at the session's first `agent/pre-step`, and only when that agent's tool view resolves this plugin's exact `skill` registration. The catalog contains sorted skill name and description only; it excludes bodies, paths, sources, providers, and routing hints. Descriptions are whitespace-normalized, XML-escaped, and capped by `catalogDescriptionMaxLength`, whose default is `500` and minimum is `3`. Full skill bodies are never included in the catalog. (The catalog originally rode the request-only [session-prefix seam](../../archived/feature/2026-07-07-session-prefix.md), archived; the [unified sourced-message decision](../architecture/2026-07-22-unified-send-and-coalesced-user-messages.md) moved it into durable history.)
|
||||
`dsh-tool-skill` injects one durable user-role `<system-reminder>` catalog as a sourced `user/message` at the session's first `agent/pre-step`, and only when that agent's tool view resolves this plugin's exact `skill` registration. The catalog contains sorted skill name and description only; it excludes bodies, paths, sources, providers, and routing hints. Descriptions are whitespace-normalized, XML-escaped, and capped by `catalogDescriptionMaxLength`, whose default is `500` and minimum is `3`. Full skill bodies are never included in the catalog. (The catalog originally rode the request-only [session-prefix extension point](../../archived/feature/2026-07-07-session-prefix.md), archived; the [unified sourced-message decision](../architecture/2026-07-22-unified-send-and-coalesced-user-messages.md) moved it into durable history.)
|
||||
|
||||
The registry's `list()` returns every winning summary, while model and user consumers apply the invocation predicates owned by the [independent invocation-policy decision](2026-07-28-skill-invocation-policy.md). The `skill({ name })` tool loads one model-invocable skill for the current agent cwd and returns a tool result containing `<skill_content name="...">`, `<skill_resources>`, and `<skill_instructions>`. `resourceBase` supplies a directory, URL, or opaque provider-managed base for explicitly referenced scripts, references, and assets; resources load only as needed, without directory enumeration. An unresolved name reports that the skill is unknown or no longer available; invalid names and skills with `invocation.modelInvocable: false` retain distinct tool errors. The tool result is the model-visible disclosure path.
|
||||
|
||||
The data structures and catalog/tool contract are documented in [skills.md](../../../../docs/core-data-structures/skills.md), with service signatures in the generated [services catalog](../../../../docs/cordis-catalog/services.md).
|
||||
The data structures and catalog/tool contract are documented in [skills.md](../../../../docs/subsystems/skills.md), with service signatures in the generated [services catalog](../../../../docs/subsystems/skills.md#cordis-surface).
|
||||
|
||||
## Alternatives considered
|
||||
|
||||
@@ -36,7 +38,7 @@ The data structures and catalog/tool contract are documented in [skills.md](../.
|
||||
|
||||
**Put local filesystem scanning directly inside `ctx.skills`.** Rejected because coding agents, web agents, and future plugin ecosystems need different skill sources. A provider registry mirrors the subagent seam: the registry owns conflict resolution and consumers, while implementations own loading.
|
||||
|
||||
**Use a system-prompt section.** Rejected because the rendered system prompt is a single string, while the catalog is a user-role `<system-reminder>` message. The [request-only session-prefix seam](../../archived/feature/2026-07-07-session-prefix.md) (archived) was the original mechanism; after the unified sourced-message decision removed that seam, the catalog became a durable sourced injection with the same message shape.
|
||||
**Use a system-prompt section.** Rejected because the rendered system prompt is a single string, while the catalog is a user-role `<system-reminder>` message. The [request-only session-prefix extension point](../../archived/feature/2026-07-07-session-prefix.md) (archived) was the original mechanism; after the unified sourced-message decision removed it, the catalog became a durable sourced injection with the same message shape.
|
||||
|
||||
**Materialize built-in DSH authoring skills under `~/.dsh/skills/.system`.** Rejected because bundled skills do not write user home on startup, and embedded or remote providers supply configured skills.
|
||||
|
||||
@@ -48,7 +50,7 @@ The data structures and catalog/tool contract are documented in [skills.md](../.
|
||||
|
||||
The agent-core spine includes one catalog contributor, one local provider, and one model-facing tool. Skill discovery is cwd-sensitive, so callers that create agents with different session cwd values can observe different project skill overrides by design.
|
||||
|
||||
The catalog is deterministic for a fixed root set and runtime registration revision, but disk changes are not watched; discovery is memoized until runtime registration invalidates the cache or the process restarts.
|
||||
The catalog is deterministic for a fixed root set and runtime registration revision. The local provider watches configured roots and invalidates completed catalogs after relevant disk changes; runtime registration and provider disposal also invalidate them.
|
||||
|
||||
## Deferred
|
||||
|
||||
|
||||
@@ -14,19 +14,21 @@ DeepSeek Harness 使用同一原语，使项目特定的评审、插件编写和
|
||||
|
||||
`@deepseek-ai/dsh-skill` 是纯提供方注册表（`ctx.skills`），`@deepseek-ai/dsh-skill-local` 是随附的本地文件系统提供方，`@deepseek-ai/dsh-tool-skill` 负责持久化会话目录与面向模型的 loader 工具。`dsh-agent-spine-demo` 默认加载注册表、本地提供方和消费方，使 TUI、headless 与 ACP（Agent Client Protocol）应用获得相同行为，同时嵌入式或远程提供方可在不修改注册表或消费方的前提下贡献 skill。其 `skills` 配置将 `registry`、`local` 和 `tool` 分支分别转发给对应的所有者。
|
||||
|
||||
专用的随包提供方可以贡献不可变的 skill，无需文件系统发现。交付的 CLI（命令行界面）默认将 `@deepseek-ai/dsh-skill-badge` 声明为禁用；启用其组合配置行，就会通过同一个注册表和消费方贡献官方徽章指令（见[决策](2026-08-06-bundled-dsh-badge-skill.md)）。
|
||||
|
||||
提供方插件在 `apply()` 期间同步注册。提供方成员资格是由直接 effect 持有的状态：注册与 dispose（资源释放）同步地使已完成的目录失效，发现操作按需读取当前提供方映射而非监听注册表变更事件。提供方目录从等待的 `list()` 调用返回排序后的候选项，远程提供方在此过程中执行初始化、认证和发现，同时遵守查找的 abort 信号。注册表校验每个候选项，按排名、提供方注册顺序和提供方内部顺序以先到先得方式解决同名 skill 冲突，然后按 skill 名称排序摘要以保证消费方获得确定性结果。它仅缓存已完成的目录快照，并在发现过程中提供方/运行时修订版本发生变化时重试，因此卸载操作不会将一个陈旧且不可解析的 skill 冻结到会话目录中。运行时 `ctx.skills.register(...)` 仍作为嵌入式进程内 skill 的便捷方式保留，使用 project 优先于 user 的优先级；`runtime` 保留为注册表拥有的提供方名称。
|
||||
|
||||
本地提供方按先到先得的排名顺序扫描 cwd 敏感的项目根目录、自定义根目录和用户根目录：项目 `.dsh`、项目 `.agents`、`customSkillDirs`、用户 `.dsh`，然后是用户 `.agents`。用户 `.dsh/skills` 扫描跳过 `.system`，以免系统拥有的目录被当作普通用户内容处理。DeepSeek Harness 不随附内置系统 skill；嵌入式或远程提供方在配置后提供额外 skill。
|
||||
本地提供方按先到先得的排名顺序扫描 cwd 敏感的项目根目录、自定义根目录和用户根目录：项目 `.dsh`、项目 `.agents`、`customSkillDirs`、用户 `.dsh`，然后是用户 `.agents`。用户 `.dsh/skills` 扫描跳过 `.system`，以免系统拥有的目录被当作普通用户内容处理。本地提供方不会合成内置系统 skill；已配置的 bundled 根目录和专用提供方会提供额外 skill。
|
||||
|
||||
每个 skill 是 `<name>/SKILL.md` 或带 YAML frontmatter 的 `<name>.md`。`name` 和 `description` 为必填；`whenToUse`、`metadata`、`disable-model-invocation` 和 `user-invocable` 为可选。名称采用 kebab-case。调用字段会投影到类型化的嵌套策略中，具体由[模型与用户独立调用决策](2026-07-28-skill-invocation-policy.md)定义；解析器会拒绝旧的驼峰拼写。YAML frontmatter 使用 `yaml` 包（package）解析，而非 `js-yaml` 或手写解析器：`yaml` 是本包有限 frontmatter 需求已声明的现代解析器，窄解析器要么拒绝用户预期可用的合法 YAML，要么膨胀为一个未经评审的 YAML 子集。
|
||||
|
||||
本地 skill 的文件系统 I/O 在加载了文件系统服务时通过 `ctx.fs` 进行：项目根目录查找使用 `resolve` 和 `stat` 探测 `.git`，根目录发现使用 `listDir`，skill 读取使用 `readText`。Node 文件系统作为后备，供在不挂载 fs seam 的最小上下文中加载 `dsh-skill-local` 时使用。缺失的根目录、不可读或格式错误的 skill 文件、以及提供方 `list()` 的瞬态失败均降级为警告并跳过，使一个坏源不会导致所有 agent 请求失败；格式错误的候选项仍然快速失败，因为它们违反了提供方契约。
|
||||
本地 skill 的文件系统 I/O 在加载了文件系统服务时通过 `ctx.fs` 进行：项目根目录查找使用 `resolve` 和 `stat` 探测 `.git`，根目录发现使用 `listDir`，skill 读取使用 `readText`。Node 文件系统作为后备，供在不挂载 fs seam 的最小上下文中加载 `dsh-skill-local` 时使用。缺失的根目录、不可读或格式错误的 skill 文件、以及提供方 `list()` 的瞬态失败均降级为警告并跳过，使一个坏源不会导致所有 agent 请求失败；格式错误的候选项仍然快速失败，因为它们违反了提供方约定。
|
||||
|
||||
`dsh-tool-skill` 在会话的第一个 `agent/pre-step` 注入一个持久化的 user-role `<system-reminder>` 目录，作为带来源的 `user/message`，且仅当该 agent 的工具视图解析到本插件精确的 `skill` 注册时才注入。该目录仅包含排序后的 skill 名称与描述；不包含正文、路径、来源、提供方和路由提示。描述经过空白规范化、XML 转义，并受 `catalogDescriptionMaxLength` 上限约束，其默认值为 `500`，最小值为 `3`。完整的 skill 正文从不包含在目录中。（目录最初通过仅请求的[会话前缀 seam](../../archived/feature/2026-07-07-session-prefix.md)（已归档）传递；[统一带来源消息的决策](../architecture/2026-07-22-unified-send-and-coalesced-user-messages.md)将其移入持久化历史。）
|
||||
`dsh-tool-skill` 在会话的第一个 `agent/pre-step` 注入一个持久化的 user-role `<system-reminder>` 目录，作为带来源的 `user/message`，且仅当该 agent 的工具视图解析到本插件精确的 `skill` 注册时才注入。该目录仅包含排序后的 skill 名称与描述；不包含正文、路径、来源、提供方和路由提示。描述经过空白规范化、XML 转义，并受 `catalogDescriptionMaxLength` 上限约束，其默认值为 `500`，最小值为 `3`。完整的 skill 正文从不包含在目录中。（目录最初通过仅请求的[会话前缀扩展点](../../archived/feature/2026-07-07-session-prefix.md)（已归档）传递；[统一带来源消息的决策](../architecture/2026-07-22-unified-send-and-coalesced-user-messages.md)将其移入持久化历史。）
|
||||
|
||||
注册表的 `list()` 返回全部胜出摘要，而模型与用户消费方应用[独立调用策略决策](2026-07-28-skill-invocation-policy.md)定义的调用判定。`skill({ name })` 工具为当前 agent cwd 加载一个模型可调用的 skill，返回包含 `<skill_content name="...">`、`<skill_resources>` 和 `<skill_instructions>` 的工具结果。`resourceBase` 提供一个目录、URL 或不透明的提供方管理的基路径，用于显式引用的脚本、参考资料和资产；资源仅按需加载，不进行目录枚举。无法解析的名称报告该 skill 未知或不再可用；无效名称和 `invocation.modelInvocable` 为 `false` 的 skill 保留不同的工具错误。工具结果是面向模型的可见披露路径。
|
||||
|
||||
数据结构与目录/工具契约记录在 [skills.md](../../../../docs/core-data-structures/skills.md) 中，服务签名见生成的[服务目录](../../../../docs/cordis-catalog/services.md)。
|
||||
数据结构与目录/工具约定记录在 [skills.md](../../../../docs/subsystems/skills.md) 中，服务签名见生成的[服务目录](../../../../docs/subsystems/skills.md#cordis-surface)。
|
||||
|
||||
## 曾考虑的替代方案
|
||||
|
||||
@@ -36,7 +38,7 @@ DeepSeek Harness 使用同一原语，使项目特定的评审、插件编写和
|
||||
|
||||
**将本地文件系统扫描直接放入 `ctx.skills`。** 否决，因为编码 agent、Web agent 和未来的插件生态需要不同的 skill 来源。提供方注册表与 subagent seam 镜像：注册表拥有冲突解决和消费方，实现拥有加载。
|
||||
|
||||
**使用系统提示词段落。** 否决，因为渲染后的系统提示词是单一字符串，而目录是一条 user-role `<system-reminder>` 消息。[仅请求的会话前缀 seam](../../archived/feature/2026-07-07-session-prefix.md)（已归档）是最初的机制；统一带来源消息的决策移除该 seam 后，目录改为具有相同消息形状的持久化带来源注入。
|
||||
**使用系统提示词段落。** 否决，因为渲染后的系统提示词是单一字符串，而目录是一条 user-role `<system-reminder>` 消息。[仅请求的会话前缀扩展点](../../archived/feature/2026-07-07-session-prefix.md)（已归档）是最初的机制；统一带来源消息的决策移除该扩展点后，目录改为具有相同消息形状的持久化带来源注入。
|
||||
|
||||
**在 `~/.dsh/skills/.system` 下物化内置 DSH 编写 skill。** 否决，因为打包的 skill 不应在启动时写入用户主目录，嵌入式或远程提供方在配置后提供 skill。
|
||||
|
||||
@@ -48,8 +50,8 @@ DeepSeek Harness 使用同一原语，使项目特定的评审、插件编写和
|
||||
|
||||
agent-core 主干包含一个目录贡献者、一个本地提供方和一个面向模型的工具。Skill 发现是 cwd 敏感的，因此以不同会话 cwd 值创建 agent 的调用方可以按设计观察到不同的项目 skill 覆盖。
|
||||
|
||||
目录对于固定的根目录集合和运行时注册修订版本是确定性的，但不监视磁盘变化；发现结果被缓存，直到运行时注册使缓存失效或进程重启。
|
||||
目录对于固定的根目录集合和运行时注册修订版本是确定性的。本地提供方会监视已配置的根目录，并在发生相关磁盘变化后使已完成的目录失效；运行时注册和提供方释放也会使其失效。
|
||||
|
||||
## 延后
|
||||
|
||||
Fork 的 skill 上下文（`context: fork`）、参数声明与提示（`arguments` 和 `argument-hint`）、以及逐 skill 的工具约束（`allowed-tools` 和 `disallowed-tools`）不在已交付的契约范围内。注册表、本地提供方和面向模型的工具不解析、不广播、也不执行这些字段。直接用户调用曾作为 TUI 功能交付，基于共享调用策略和受信的 `get()` 原语；见[已归档的 TUI skill 斜杠命令](../../archived/feature/2026-07-21-tui-skill-slash-command.md)。
|
||||
Fork 的 skill 上下文（`context: fork`）、参数声明与提示（`arguments` 和 `argument-hint`）、以及逐 skill 的工具约束（`allowed-tools` 和 `disallowed-tools`）不在已交付的约定范围内。注册表、本地提供方和面向模型的工具不解析、不广播、也不执行这些字段。直接用户调用曾作为 TUI 功能交付，基于共享调用策略和受信的 `get()` 原语；见[已归档的 TUI skill 斜杠命令](../../archived/feature/2026-07-21-tui-skill-slash-command.md)。
|
||||
|
||||
@@ -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/2026-07-06-approval-seam.md
|
||||
2026-07-06-approval-seam.md: ae143a41302b7bcd6029345fa91ca4eda837c141
|
||||
2026-07-06-approval-seam.zh.md: 2f95f67ecd33b4c659e56d5f3cc6168bf01e35ce
|
||||
2026-07-06-approval-seam.md: 7c830d93f19a40ab193cfebabca854882ab68d62
|
||||
2026-07-06-approval-seam.zh.md: 9dedfddadc23b0da44b28e8750508653ee20bb83
|
||||
|
||||
@@ -12,7 +12,7 @@ The routing problem is ownership: a permission request must reach the channel th
|
||||
|
||||
## Decision
|
||||
|
||||
One package, `dsh-user-approval` (`packages/ui/user-approval`), owns the vocabulary and the `ctx.approval` service — the mechanism. The policy — who answers, and whether a session is asked at all — lives outside it: answerers are `approval/request` waterfall listeners registered by channel-owning plugins (the ACP bridge, host adapters, and test scripts), and a per-session policy tier can decide before a channel is involved. Consumers (`dsh-tools`' ask routing and the sandbox escalation gate) resolve a question to a closed outcome and derive their own tool results from it. This is deliberately one package, not the capability-seam three (see Alternatives).
|
||||
One package, `dsh-user-approval` (`packages/interaction/user-approval`), owns the vocabulary and the `ctx.approval` service — the mechanism. The policy — who answers, and whether a session is asked at all — lives outside it: answerers are `approval/request` waterfall listeners registered by channel-owning plugins (the ACP bridge, host adapters, and test scripts), and a per-session policy tier can decide before a channel is involved. Consumers (`dsh-tools`' ask routing and the sandbox escalation gate) resolve a question to a closed outcome and derive their own tool results from it. This is deliberately one package, not the capability-seam three (see Alternatives).
|
||||
|
||||
### How a deployment uses it
|
||||
|
||||
@@ -95,9 +95,9 @@ Snapshots record allowed and rejected sandbox escalation through `session/reques
|
||||
|
||||
- **A single registered provider instead of waterfall listeners** — rejected: a `registerProvider()` surface forces every composition question — allowlist pre-filters, external hook deciders, scripted test answers, a policy gate in front of a human — inside one provider implementation. The waterfall gets composition, fail-closed absence, and HMR disposal from machinery the runtime already has; the seam's JSDoc pins the single-decision-slot convention instead of inventing a provider registry.
|
||||
- **An inline `tools/pre-execute` permission gate in the ACP bridge** — rejected: prompting for every bridge-owned call hardwires the asking policy into the transport, cannot serve a second asker (sandbox escalation happens after execution starts, with no pre-execute moment), and leaves hook-produced `ask` decisions without a shared mechanism.
|
||||
- **The generic user-interaction seam (`ctx.userInteraction`)** — rejected as the approval mechanism: the two share a skeleton (route by agent, block for a human, handle absence), but approval's contract is narrower in every dimension that matters: a closed outcome vocabulary instead of free text, a protocol-native prompt attached to a tool call instead of a generic form, mandatory fail-closed absence, and audit events. Approval therefore does not ride the shipped `packages/ui/user-interaction` / `ask_user_question` elicitation path — an elicitation form is not a permission prompt, and a free-text answer is not a closed outcome; sharing provider plumbing stays open if the two ever converge.
|
||||
- **The generic user-interaction seam (`ctx.userInteraction`)** — rejected as the approval mechanism: the two share a skeleton (route by agent, block for a human, handle absence), but approval's contract is narrower in every dimension that matters: a closed outcome vocabulary instead of free text, a protocol-native prompt attached to a tool call instead of a generic form, mandatory fail-closed absence, and audit events. Approval therefore does not ride the shipped `packages/interaction/user-interaction` / `ask_user_question` elicitation path — an elicitation form is not a permission prompt, and a free-text answer is not a closed outcome; sharing provider plumbing stays open if the two ever converge.
|
||||
- **Static optional injection in `dsh-tools`** — rejected: the vendored cordis `Inject` type has no optional flag — the object form maps service names to intercept config, and a declared inject gates the fiber. `ctx.get('approval')` is the documented opportunistic-consumption pattern (the `tool-bash` owner-token lookup, the loop's persistence probe), reads presence per call, and degrades correctly across HMR without extra machinery.
|
||||
- **The capability-seam three-package split** — rejected: interface/implementation/consumer fits a seam whose implementation is swappable (bash-local vs bash-sandbox). Here the service body is fixed mechanism and the variable part is listeners that live with their owners — splitting would manufacture an implementation package with nothing in it ("don't split preemptively").
|
||||
- **The capability-seam three-package split** — rejected: Service Definition / Service provider / Consumer fits a seam whose Service provider is swappable (bash-local vs bash-sandbox). Here the service body is fixed mechanism and the variable part is listeners that live with their owners — splitting would manufacture a Service provider package with nothing in it ("don't split preemptively").
|
||||
- **Offering `allow_always` now** — rejected: the protocol can express it, but honoring it means designing grant storage, scope identity, and revocation (§ Deferred). Advertising an option the harness cannot honor manufactures doomed grants.
|
||||
|
||||
## Consequences
|
||||
@@ -134,6 +134,6 @@ In-repo precedents this design copies or contrasts with:
|
||||
|
||||
- The `fs/write-intent` gate (`packages/fs/fs/`) — the documented single-occupancy decision-slot waterfall semantics (first answer wins, delegate via `next()`) the answerer contract reuses.
|
||||
- `hook/invoked`/`hook/result` — the log-only audit-pair precedent `approval/asked`/`approval/decided` follows; [the hook-bridges Agent Note](2026-06-30-hook-bridges.md) ships `permissionDecision: ask`, the first producer.
|
||||
- [The interception-seams Agent Note](2026-06-30-interception-seams.md) — the `tools/pre-execute` `allow`/`deny`/`ask` vocabulary whose `ask` this seam services.
|
||||
- [The interception extension-points Agent Note](2026-06-30-interception-extension-points.md) — the `tools/pre-execute` `allow`/`deny`/`ask` vocabulary whose `ask` this seam services.
|
||||
- [The automation-only ACP Agent Note](../simplification/2026-07-23-acp-automation-only-protocol.md) — the exact-agent ownership check against the session map that the answerer routes through; [the multi-session Agent Note](2026-06-14-acp-multi-session.md) — the per-session permission-ownership blocker this implements.
|
||||
- The opportunistic `ctx.get()` consumption pattern (`tool-bash`'s owner-token lookup, the loop's persistence probe) — how `dsh-tools` consumes the seam without gating its fiber on it.
|
||||
|
||||
@@ -12,7 +12,7 @@ Status: implemented
|
||||
|
||||
## 决策
|
||||
|
||||
一个包`dsh-user-approval`（`packages/ui/user-approval`）负责定义词汇表和 `ctx.approval` 服务——即机制。策略——谁来应答、某个会话是否需要被询问——不在其中：应答者是 `approval/request` waterfall 监听器，由拥有通道的插件注册（ACP（Agent Client Protocol）桥、宿主适配器、测试脚本），而每会话的策略层可以在任何通道介入之前做出决定。消费方（`dsh-tools` 的 ask 路由和沙箱升级门禁）将问题解析为一个封闭结果，并从中派生各自的工具结果。刻意设计为一个包，而非能力 seam 的三包拆分（见「替代方案」）。
|
||||
一个包`dsh-user-approval`（`packages/interaction/user-approval`）负责定义词汇表和 `ctx.approval` 服务——即机制。策略——谁来应答、某个会话是否需要被询问——不在其中：应答者是 `approval/request` waterfall 监听器，由拥有通道的插件注册（ACP（Agent Client Protocol）桥、宿主适配器、测试脚本），而每会话的策略层可以在任何通道介入之前做出决定。消费方（`dsh-tools` 的 ask 路由和沙箱升级门禁）将问题解析为一个封闭结果，并从中派生各自的工具结果。刻意设计为一个包，而非能力 seam 的三包拆分（见「替代方案」）。
|
||||
|
||||
### 部署如何使用它
|
||||
|
||||
@@ -77,7 +77,7 @@ ACP 桥只应答其会话映射所拥有的精确 agent 对象。它携带既有
|
||||
|
||||
#### 实体与依赖
|
||||
|
||||
`dsh-user-approval` 依赖 Cordis，以及会话、agent 和带 brand 的调用契约；`dsh-tools` 与 `dsh-acp` 消费它。沙箱执行器保持独立，因为升级请求归 `dsh-tool-bash` 所有。固定的派发与审计服务仍是一个包；可替换的应答者留在各自的通道所有者中。静态能力授权和 `subagent-acp` 子侧权限应答仍是独立关注点。
|
||||
`dsh-user-approval` 依赖 Cordis，以及会话、agent 和带 brand 的调用约定；`dsh-tools` 与 `dsh-acp` 消费它。沙箱执行器保持独立，因为升级请求归 `dsh-tool-bash` 所有。固定的派发与审计服务仍是一个包；可替换的应答者留在各自的通道所有者中。静态能力授权和 `subagent-acp` 子侧权限应答仍是独立关注点。
|
||||
|
||||
### 测试
|
||||
|
||||
@@ -95,14 +95,14 @@ ACP 桥只应答其会话映射所拥有的精确 agent 对象。它携带既有
|
||||
|
||||
- **单一注册提供方而非 waterfall 监听器**：否决。`registerProvider()` 接口迫使所有组合问题——允许列表预过滤、外部钩子决策者、脚本化测试应答、人类前面的策略门禁——都塞进一个提供方实现。waterfall 直接复用运行时已有的组合能力、缺失时默认拒绝行为和 HMR（热模块替换）资源释放机制；seam 的 JSDoc 以约定固定单决策槽语义，而非发明一个提供方注册表。
|
||||
- **在 ACP 桥中内联 `tools/pre-execute` 权限门禁**：否决。对桥拥有的每次调用都弹出提示，会将请求策略硬编码进传输层，无法服务第二个发起方（沙箱升级发生在执行开始之后，没有 pre-execute 时刻），且钩子产生的 `ask` 决策没有共享机制。
|
||||
- **通用用户交互 seam（`ctx.userInteraction`）**：否决作为审批机制。二者骨架相似（按 agent 路由、阻塞等待人类、处理缺失），但审批的契约在每个关键维度上都更窄：封闭的结果词汇而非自由文本、附着在工具调用上的协议原生提示而非通用表单、强制的缺失时失败关闭、以及审计事件。因此审批不走已交付的 `packages/ui/user-interaction` / `ask_user_question` 信息征集路径——信息征集表单不是权限提示，自由文本应答不是封闭结果；如果二者将来趋同，共享提供方管道仍然开放。
|
||||
- **通用用户交互 seam（`ctx.userInteraction`）**：否决作为审批机制。二者骨架相似（按 agent 路由、阻塞等待人类、处理缺失），但审批的约定在每个关键维度上都更窄：封闭的结果词汇而非自由文本、附着在工具调用上的协议原生提示而非通用表单、强制的缺失时失败关闭、以及审计事件。因此审批不走已交付的 `packages/interaction/user-interaction` / `ask_user_question` 信息征集路径——信息征集表单不是权限提示，自由文本应答不是封闭结果；如果二者将来趋同，共享提供方管道仍然开放。
|
||||
- **`dsh-tools` 中的静态可选注入**：否决。vendor 的 Cordis `Inject` 类型没有 optional 标志——对象形式将服务名映射到拦截配置，声明的 inject 会阻塞 fiber。`ctx.get('approval')` 是文档化的机会性消费模式（`tool-bash` 的 owner-token 查找、loop 的持久化探测），按调用读取存在性，跨 HMR 正确降级，无需额外机制。
|
||||
- **能力 seam 的三包拆分**：否决。接口/实现/消费方适合实现可替换的 seam（bash-local vs bash-sandbox）。此处服务体是固定机制，可变部分是留在各自通道拥有者插件中的监听器——拆分只会制造一个空的实现包（「不要预防性拆分」）。
|
||||
- **能力 seam 的三包拆分**：否决。Service Definition/Service provider/Consumer 适合 Service provider 可替换的 seam（bash-local vs bash-sandbox）。此处服务体是固定机制，可变部分是留在各自通道拥有者插件中的监听器——拆分只会制造一个空的 Service provider 包（「不要预防性拆分」）。
|
||||
- **现在就提供 `allow_always`**：否决。协议能表达它，但兑现它意味着设计授权存储、作用域标识和撤销（§ 延后）。展示 harness 无法兑现的选项只会制造注定失败的授权。
|
||||
|
||||
## 后果
|
||||
|
||||
实现后的契约由「测试」一节所列套件固定：
|
||||
实现后的约定由「测试」一节所列套件固定：
|
||||
|
||||
- `allowed-once` 派发一次操作；其他所有结果都以不同原因拒绝，而 `'never'` 会在提示前拒绝。
|
||||
- 缺失、外部、无 agent、抛异常、无效或断开连接的应答路径都会失败关闭。
|
||||
@@ -113,7 +113,7 @@ ACP 桥只应答其会话映射所拥有的精确 agent 对象。它携带既有
|
||||
|
||||
- **两个都会直接作出决策的应答者会竞争同一槽位。** 兄弟插件的监听器顺序不确定，seam 无法仲裁竞争的终端应答者。通过约定缓解（每个部署一个终端应答者；仅对「先决策或委派」门禁使用 `prepend`），而非事件总线不具备的优先级机制。
|
||||
- **生产路径仅在一种组合下得到验证。** `ask` 有两个生产者家族——钩子桥通过 `tools/pre-execute`，沙箱升级通过自己的门禁——协议格式录制在沙箱示例的快照套件中；因此在更多部署组合它之前，seam 的真实覆盖面就是这一种组合。
|
||||
- **归属以 `Agent` 对象标识为键。** 应答者先在 `agent.session.id` 处解析会话映射记录，再要求该记录拥有精确的 agent 对象；当前所有路径在 loop 和各 seam 之间传递同一对象，但未来如果某个边界克隆或代理了 agent，桥会委派并失败关闭，届时需要另一种归属契约。
|
||||
- **归属以 `Agent` 对象标识为键。** 应答者先在 `agent.session.id` 处解析会话映射记录，再要求该记录拥有精确的 agent 对象；当前所有路径在 loop 和各 seam 之间传递同一对象，但未来如果某个边界克隆或代理了 agent，桥会委派并失败关闭，届时需要另一种归属约定。
|
||||
|
||||
## FAQ
|
||||
|
||||
@@ -132,8 +132,8 @@ ACP 桥只应答其会话映射所拥有的精确 agent 对象。它携带既有
|
||||
|
||||
本设计复用或对照的仓库内先例：
|
||||
|
||||
- `fs/write-intent` 门禁（`packages/fs/fs/`）——文档化的单占用决策槽 waterfall 语义（先到先得，通过 `next()` 委派），应答者契约复用了它。
|
||||
- `fs/write-intent` 门禁（`packages/fs/fs/`）——文档化的单占用决策槽 waterfall 语义（先到先得，通过 `next()` 委派），应答者约定复用了它。
|
||||
- `hook/invoked`/`hook/result`——仅日志审计对先例，`approval/asked`/`approval/decided` 沿用了它；[钩子桥 Agent Note](2026-06-30-hook-bridges.md) 交付了 `permissionDecision: ask`，即第一个生产者。
|
||||
- [拦截 seam Agent Note](2026-06-30-interception-seams.md)——`tools/pre-execute` 的 `allow`/`deny`/`ask` 词汇，本 seam 服务其中的 `ask`。
|
||||
- [拦截扩展点 Agent Note](2026-06-30-interception-extension-points.md)——`tools/pre-execute` 的 `allow`/`deny`/`ask` 词汇，本 seam 服务其中的 `ask`。
|
||||
- [仅面向自动化的 ACP Agent Note](../simplification/2026-07-23-acp-automation-only-protocol.md)——应答者路由时对会话映射执行的精确 agent 归属检查；[多会话 Agent Note](2026-06-14-acp-multi-session.md)——本设计实现的每会话权限归属阻塞项。
|
||||
- 机会性 `ctx.get()` 消费模式（`tool-bash` 的 owner-token 查找、loop 的持久化探测）——`dsh-tools` 消费该 seam 而不阻塞其 fiber 的方式。
|
||||
|
||||
@@ -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/2026-07-06-explicit-tool-order.md
|
||||
2026-07-06-explicit-tool-order.md: bd6d0a04aa470ca33e618957ae1f08c1ef15fcfe
|
||||
2026-07-06-explicit-tool-order.zh.md: 88955aaaa55b18ac94153b34d4e514ecc1fa1100
|
||||
2026-07-06-explicit-tool-order.md: 7a4553b50da409b531a9fe14fcfbb201a5165fc4
|
||||
2026-07-06-explicit-tool-order.zh.md: a78a38a6ada3ed0a2f3a756830747916446e188c
|
||||
|
||||
@@ -39,7 +39,7 @@ Config plumbing follows the `persona` precedent, and `toolOrder` sits beside it:
|
||||
## Consequences
|
||||
|
||||
- Every registry-built assembly starts with a deterministic tool order on every host; absent an expert listener that deliberately changes it, every `request/header` event and model request inherits that order. The CI-vs-local registration-order flip is structurally gone, and the default is lexicographic.
|
||||
- The initial `PromptAssembly.tools` is canonical, so waterfall listeners start from the model-facing order; provider registration order is observable nowhere before that cooperative seam.
|
||||
- The initial `PromptAssembly.tools` is canonical, so waterfall listeners start from the model-facing order; provider registration order is observable nowhere before that cooperative extension point.
|
||||
- The snapshot suite's single pinned request-header fixture (`text-turn`) carries the new canonical tool order; every other ACP snapshot keeps the header bulk scrubbed as `{{system}}`/`{{tools}}`, per the pinned-header design.
|
||||
- A pure tool reordering between steps is logged like any other header change: a full `request/header` snapshot with reason `'change'`. Stable canonical order prevents registration timing from creating such changes in the ordinary path.
|
||||
- The `toolOrder` key rides the app → `agent-core` → `SystemPrompt` forwarding chain, so deployments set it next to `persona` in the app config; `dsh-llm` and the agent loop are untouched.
|
||||
|
||||
@@ -21,7 +21,7 @@ Status: implemented
|
||||
|
||||
`assemble()` 在 `system-prompt/assemble` waterfall（瀑布式事件）之前将提供方工具归一为权威顺序，从源头消除注册顺序的差异。waterfall 从这个确定性列表开始；不变的顺序随后流入请求头、冻结的请求和重建检查，无需 loop 特有的排序逻辑。
|
||||
|
||||
范围刻意收窄：本 Agent Note 修复的是注册顺序竞态，而非插件行为。`system-prompt/assemble` 的监听器仍然可以添加、移除或重排工具——正如它可以在 section 排序之后编辑 section——并对自身输出的确定性负责；waterfall 契约已经要求监听器是确定性的（可重建性不变式会捕获在构建与回放之间行为不一致的监听器）。
|
||||
范围刻意收窄：本 Agent Note 修复的是注册顺序竞态，而非插件行为。`system-prompt/assemble` 的监听器仍然可以添加、移除或重排工具——正如它可以在 section 排序之后编辑 section——并对自身输出的确定性负责；waterfall 约定已经要求监听器是确定性的（可重建性不变式会捕获在构建与回放之间行为不一致的监听器）。
|
||||
|
||||
配置传递沿用 `persona` 的先例，`toolOrder` 与之并列：TUI、Headless 和 ACP 应用配置接受该键，并通过 `dsh-agent-spine-demo`（其 schema 是各所有者 schema 的交集）转发给 `SystemPrompt` 子服务。有一个 schemastery 细节至关重要：schemastery 数组默认为 `[]`，但省略的 `toolOrder` 必须保持 ABSENT（= 字典序），而不是变成一个显式配置的空列表（无效——缺少 rest 条目），因此链路上每个 schema 都将默认值强制为 `undefined`。
|
||||
|
||||
@@ -39,12 +39,12 @@ Status: implemented
|
||||
## 后果
|
||||
|
||||
- 每个由注册表构建的组装在任何宿主上都以确定性工具顺序开始；在没有专家监听器刻意改变的情况下，每个 `request/header` 事件和模型请求都继承该顺序。CI 与本地之间的注册顺序翻转从结构上被消除，默认为字典序。
|
||||
- 初始 `PromptAssembly.tools` 是权威的，因此 waterfall 监听器从模型侧顺序开始；提供方注册顺序在该协作 seam 之前无处可观测。
|
||||
- 初始 `PromptAssembly.tools` 是权威的，因此 waterfall 监听器从模型侧顺序开始；提供方注册顺序在该协作扩展点之前无处可观测。
|
||||
- 快照套件中唯一锁定请求头的 fixture（`text-turn`）携带新的权威工具顺序；按照锁定请求头的设计，其他 ACP 快照仍将大段 header 替换为 `{{system}}`/`{{tools}}`。
|
||||
- 步骤之间的纯工具重排与其他 header 变更一样记录：一份原因是 `'change'` 的完整 `request/header` 快照。稳定的权威顺序会防止注册时序在普通路径上制造这类变化。
|
||||
- `toolOrder` 键沿 app → `agent-core` → `SystemPrompt` 的转发链传递，因此部署时将其放在 app 配置中 `persona` 旁边即可；`dsh-llm` 和 agent loop 无需改动。
|
||||
- `toolOrder` 中拼错或未加载的工具名称在提示词组装时使轮次失败，而非启动时：loop 在轮次内部组装（`turn/start` 之后、`step/start` 之前），因此拒绝到达轮次的外层 catch——轮次以 `error` 原因完整结束并携带错误消息，`agent/error` 复现该消息，不打开步骤，不记录 `request/header`，不向适配器发出请求，agent 回到空闲状态。每个轮次都以相同方式失败，直到配置被修正；进程本身保持运行（符合仓库规则：显式配置引用不得被静默忽略——执行点是组装，因为不存在更早的通用时刻）。
|
||||
- 工具提供方返回保留的 rest 条目名称时，其提示词组装失败形态与未知的已列名称相同。这防止哨兵值变成一个歧义的真实工具，并保持「从不丢弃工具」的排序契约。
|
||||
- 工具提供方返回保留的 rest 条目名称时，其提示词组装失败形态与未知的已列名称相同。这防止哨兵值变成一个歧义的真实工具，并保持「从不丢弃工具」的排序约定。
|
||||
|
||||
## 测试
|
||||
|
||||
|
||||
@@ -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/2026-07-06-sandbox.md
|
||||
2026-07-06-sandbox.md: aed5ac1ceb02130ce97a8c83c0f77869fdc32146
|
||||
2026-07-06-sandbox.zh.md: db95b1a5b7a7cae1e0fcdd8deba9dcb6ad020a67
|
||||
2026-07-06-sandbox.md: 0214a202a41983c76fa25e3a82e1cfaec70a0d55
|
||||
2026-07-06-sandbox.zh.md: bd8dcdb74f723a955ea2a1cc5b224ef2ded4a8d5
|
||||
|
||||
@@ -38,7 +38,7 @@ Four `cordis.yml` entries turn an unconfined coding agent into the sandboxed pro
|
||||
|
||||
The swap is invisible to every consumer of `ctx.bash`: the bash tools, hook commands, and background tasks run exactly as before by directly spawning the wrapped argv the provider returns. Deleting the `sandbox` and `permission` entries and replacing `bash` with `@deepseek-ai/dsh-bash-local` is the opt-out — execution is unconfined again and the escalation fields vanish from the tool schema, because they are capability-gated on the mounted executor, not on configuration. Omitting only `approval` keeps confinement but fails every escalation closed with its own error text; `permission` also requires the approval seam and a confining executor, so a partially composed preset layer fails loud at load.
|
||||
|
||||
Misconfiguration fails loud: `mode` outside the closed vocabulary is rejected at plugin load, and a host with no usable backend throws the structured `SANDBOX_UNAVAILABLE` at `confine()` rather than degrading to unconfined execution. If the selected runner rejects with attributable `ENOENT` or `EACCES`, the consumer reports the same infrastructure error from the spawn channel before any command starts; other spawn errors retain local command-start semantics while still running nothing. `runnerCommand` on `dsh-sandbox-local` is the operator's explicit assertion of a bwrap-compatible runner (chain and probes skipped); it doubles as the deterministic fake-runner seam for keyless tests.
|
||||
Misconfiguration fails loud: `mode` outside the closed vocabulary is rejected at plugin load, and a host with no usable backend throws the structured `SANDBOX_UNAVAILABLE` at `confine()` rather than degrading to unconfined execution. If the selected runner rejects with attributable `ENOENT` or `EACCES`, the consumer reports the same infrastructure error from the spawn channel before any command starts; other spawn errors retain local command-start semantics while still running nothing. `runnerCommand` on `dsh-sandbox-local` is the operator's explicit assertion of a bwrap-compatible runner (chain and probes skipped); it doubles as the deterministic fake-runner hook for keyless tests.
|
||||
|
||||
Denied file effects return a `[sandbox: file access denied under <mode> mode]` marker and instructions not to work around the denial. A confining executor adds paired `sandbox_permissions` and `justification` fields for one approved retry that must be strictly wider than the session's effective mode. A grant widens only that retry; rejection executes nothing, returns `the user rejected escalating this command to "<mode>"`, and permits no re-ask. The owner-derived pending policy context states the current file policy without replacing those enforcement boundaries. When `dsh-permission` is composed with a UI adapter, one preset selects both knob values; unmatched values fold to `custom`. The [ACP automation composition](../../../../examples/acp-agent/README.md) does not mount that UI service and selects its deployment mode explicitly.
|
||||
|
||||
@@ -54,7 +54,7 @@ OS subprocess confinement applies to the bash executor, including hook commands,
|
||||
|
||||
Policy rides each CALL, not the provider: two consumers may confine under different policies at the same instant (bash under `read-only` while a confined child agent keeps its state directory writable), and an approved escalated retry is a new call with a wider policy — inexpressible under a config-fixed provider mode.
|
||||
|
||||
The seam confines SAME-WORLD subprocesses only: a backend shares the host's filesystem and kernel. Containers, microVMs, and remote executors are NOT backends of this seam — they replace whole capability implementations (`ctx.bash`, `ctx.fs`) as environment-coherent groups, because an agent whose bash runs in a container while its fs tools write the host lives in two split worlds.
|
||||
The seam confines SAME-WORLD subprocesses only: a backend shares the host's filesystem and kernel. Containers, microVMs, and remote executors are NOT backends of this seam — they replace the Service providers for whole capability seams (`ctx.bash`, `ctx.fs`) as environment-coherent groups, because an agent whose bash runs in a container while its fs tools write the host lives in two split worlds.
|
||||
|
||||
Left open, for the phase that needs them: whether network restriction arrives as a separate `network_mode` or merges into `sandbox_mode` once a runner enforces both, and whether `SandboxPolicy` grows extra writable-root grants now (the launcher already speaks `--rw <path>`) or only when escalation needs them.
|
||||
|
||||
@@ -64,13 +64,13 @@ Left open, for the phase that needs them: whether network restriction arrives as
|
||||
|
||||
The launcher is a ~300-line C program (plain C11 over the raw Landlock UAPI — no libraries beyond a statically linked musl, so the audit surface is that one file plus the kernel's stable syscall contract): `--ro <path>` / `--rw <path>` grants, `--`, the wrapped argv; it installs the ruleset on itself and `exec`s (rulesets are inherited across `execve`, and it sets `no_new_privs` before restricting); `--probe` enforces a maximal ruleset in a short-lived child and exits 0 only when the kernel actually enforces; every launcher failure exits 125 without running the child and prints a fatal `landlock-run:` line. A successfully exec'd child may also return 125, so status alone is not launcher evidence. An older ABI prints the exact `landlock-run: partial enforcement (older Landlock ABI)` notice before it executes the child, so that line is not fatal evidence.
|
||||
|
||||
The Landlock launcher source and package workspace live at `native/landlock-run`, next to the harness consumers. The standalone [`node-addon-landlock-run`](https://github.com/deepseek-harness/node-addon-landlock-run) repository is the release mirror used to pack and publish the npm package family; `native/README.md` owns the export procedure. Platform binaries are selected by npm, and the entry package owns path resolution, probing, CLI flags, the fatal prefix, and the partial-enforcement notice while the harness maps sandbox modes to grants. Versioning the entry point with its binaries keeps probe parsing and launch syntax aligned.
|
||||
The Landlock launcher source and package family live at `native/landlock-run`, next to the harness consumers and inside the root pnpm workspace. The [in-repository Landlock release decision](../process/2026-08-06-in-repository-landlock-release.md) owns the shared lockfile, native build, pack rehearsal, and npm publication boundary. Platform binaries are selected by npm, and the entry package owns path resolution, probing, CLI flags, the fatal prefix, and the partial-enforcement notice while the harness maps sandbox modes to grants. Versioning the entry point with its binaries keeps probe parsing and launch syntax aligned.
|
||||
|
||||
Backend profiles share the mode contract but differ in necessary host grants. Landlock and Seatbelt allow only `/dev/null` in read-only mode; workspace-write also permits their required host temp roots. Each wrap carries backend-specific denial signatures. Landlock reports partial enforcement on older ABIs that cannot govern every operation, while successful bwrap and Seatbelt profiles report full enforcement.
|
||||
|
||||
#### The bash consumer
|
||||
|
||||
`dsh-bash-sandbox` extends `LocalBashExecutor`, hands `ctx.sandbox` the exact `['bash', '-c', command]` argv, and directly spawns the provider result. This leaves shell semantics and `BASH_ENV` on the inner Bash after the shipped native runner establishes confinement. A provider error propagates unchanged. A pre-process rejection is runner-owned only when the caller-owned workdir is independently usable and Node reports `ENOENT` or `EACCES` with positive provenance for provider argv[0]; a bare `syscall: 'spawn'` without an exact error path, other codes, invalid workdirs, resource failures, unrelated syscalls, and unstructured rejections retain local command-start semantics. Foreground execution converts runner-owned rejections to `SANDBOX_UNAVAILABLE` with the original detail; an asynchronous background rejection stamps `runnerFailed: true`, `denied: false`. A `SubprocessService` that synchronously throws the same provenanced shape makes background start throw `SANDBOX_UNAVAILABLE`, while other synchronous errors propagate unchanged. After a process starts, foreground and background use one runner-failure classifier that requires the rule's exit-code gate and a remaining fatal line after informational exclusions. A match outranks denial: foreground execution throws `SANDBOX_UNAVAILABLE` with that fatal line as detail; a settled `BashProcess` stamps `sandbox.runnerFailed`, and the bash producer renders it through generic `task_output`.
|
||||
`dsh-bash-sandbox` extends `LocalBashExecutor`, hands `ctx.sandbox` the exact `['bash', '-c', command]` argv, and directly spawns the provider result. This leaves shell semantics and `BASH_ENV` on the inner Bash after the shipped native runner establishes confinement. A provider error propagates unchanged. A pre-process rejection counts as a runner failure only when the caller-owned workdir is independently usable and Node reports `ENOENT` or `EACCES` with either an `error.path` equal to provider argv[0] or, when `error.path` is absent, an exact `syscall: 'spawn <runner>'`; a present path also requires `syscall: 'spawn'` or the exact `spawn <runner>`. Other codes, invalid workdirs, resource failures, unrelated syscalls, and unstructured rejections retain local command-start semantics. Foreground execution converts runner failures to `SANDBOX_UNAVAILABLE` with the original detail; an asynchronous background rejection stamps `runnerFailed: true`, `denied: false`. A `SubprocessService` that synchronously throws the same runner-identifying shape makes background start throw `SANDBOX_UNAVAILABLE`, while other synchronous errors propagate unchanged. After a process starts, foreground and background use one runner-failure classifier that requires the rule's exit-code check and a remaining fatal line after informational exclusions. A match takes priority over denial: foreground execution throws `SANDBOX_UNAVAILABLE` with that fatal line as detail; a settled `BashProcess` stamps `sandbox.runnerFailed`, and the bash producer renders it through generic `task_output`.
|
||||
|
||||
The model sees the current effective file policy in the owner-derived `sandbox:policy` context, while the static tool description explains the denial marker (`[sandbox: file access denied under <mode> mode]`), encourages attempting commands that may be denied, and forbids retrying around a denial; when the escalation fields are advertised, a denied result additionally carries the escalation hint itself, so the sanctioned same-turn retry is prompted at the decision point rather than depending on the model recalling the description (§ Escalation). [The current-policy decision](2026-07-30-current-sandbox-policy-context.md) owns the context's rationale and boundaries.
|
||||
|
||||
@@ -82,7 +82,7 @@ The model sees the current effective file policy in the owner-derived `sandbox:p
|
||||
|
||||
When a confining executor is mounted, `bash` advertises paired `sandbox_permissions` and `justification` fields. The schema exposes the full closed escalation vocabulary because effective mode is per-session; execution rejects any target that is not strictly wider than that call's effective mode. Approval resolves before execution. `allowed-once` stamps the granted mode onto only that request, while `rejected`, `cancelled`, `unavailable`, a missing approval service, or a missing agent all fail closed with distinct results. No grant is persisted.
|
||||
|
||||
Escalation is a same-turn retry of the denied command with the narrowest sufficient `sandbox_permissions` and a `justification`; the approval prompt is the consent step. It must be grounded in an actual denial, except when the session already observed the same denied access, and a disabled or rejected approval ends that command. The retry, approval decision, and result use existing tool and approval events. `dsh-tool-bash` owns the ask because the executor seam has neither the agent nor call id required for user interaction.
|
||||
Escalation is a same-turn retry of the denied command with the narrowest sufficient `sandbox_permissions` and a `justification`; the approval prompt is the consent step. It must be grounded in an actual denial, except when the session already observed the same denied access, and a disabled or rejected approval ends that command. The retry, approval decision, and result use existing tool and approval events. `dsh-tool-bash` owns the ask because the executor Service Definition has neither the agent nor call id required for user interaction.
|
||||
|
||||
Left open: what a durable grant's scope identity is beyond the sandbox mode — exact call, path, command prefix, session, or time window — before an `allow_always` option can be advertised.
|
||||
|
||||
@@ -113,12 +113,12 @@ Before each proposed step, sandbox and approval policy are rendered as ordered c
|
||||
|
||||
#### In-process tools
|
||||
|
||||
fs/web/todo execute in-process, so their sandbox semantics are policy at their seams. The fs seam now enforces the shared mode vocabulary through a sandboxed provider (`dsh-fs-sandbox` fences write/edit by mode; see [the cross-family fs sandbox RFC](2026-07-14-cross-family-fs-sandbox.md)), so `read-only`/`workspace-write` are real boundaries for the filesystem tools, not a bash-only approximation. web/todo remain unfenced (web's only effect is network, outside the file-effect mode vocabulary). No generic per-tool sandbox runtime: a host-mediated tool leaves the process only by returning declarative effects the host validates, which is a rewrite, not a wrapper — the follow-up settled on one shared policy home (`ctx.sandboxPolicy`) with per-seam enforcement, not a uniform wrapper.
|
||||
fs/web/todo execute in-process, so their sandbox semantics are policy at their capability boundaries. The fs seam now enforces the shared mode vocabulary through a sandboxed provider (`dsh-fs-sandbox` fences write/edit by mode; see [the cross-family fs sandbox RFC](2026-07-14-cross-family-fs-sandbox.md)), so `read-only`/`workspace-write` are real boundaries for the filesystem tools, not a bash-only approximation. web/todo remain unfenced (web's only effect is network, outside the file-effect mode vocabulary). No generic per-tool sandbox runtime: a host-mediated tool leaves the process only by returning declarative effects the host validates, which is a rewrite, not a wrapper — the follow-up settled on one shared policy home (`ctx.sandboxPolicy`) with per-capability enforcement, not a uniform wrapper.
|
||||
|
||||
### Testing
|
||||
|
||||
- **Unit:** pin platform selection and profiles, direct provider-argv handoff, spawn-level failures with invalid-workdir controls, missing/non-executable/missing-interpreter evidence, malformed-runner negative controls, confined `BASH_ENV` ordering, structured runner classification (including partial-Landlock notice-only child outcomes, gated fatal evidence, child exits 126/127, and foreground/background parity), per-call mode/root resolution, per-process facts, escalation validation and outcomes, permission preset folding and write-through, and runtime-context ordering and materialization.
|
||||
- **Keyless real-runner:** exercise bwrap, Landlock, and Seatbelt against real filesystem effects at provider and bash-consumer layers; one real Cordis context concurrently drives two project sessions through shipped bash and fs tools, proving own-root success and sibling-root denial. Packed-install coverage proves the registry launcher remains executable. CI rejects a silent all-skip.
|
||||
- **Keyless real-runner:** exercise bwrap, Landlock, and Seatbelt against real filesystem effects at provider and bash-consumer layers; one real Cordis context concurrently drives two project sessions through shipped bash and fs tools, proving own-root success and sibling-root denial. Packed-install coverage installs the current checkout's native tarballs and proves the launcher remains executable and byte-identical. CI rejects a silent all-skip.
|
||||
- **With-key:** start the real ACP composition in read-only mode, let a model-driven bash write hit the runner's denial marker, then drive the bridge answerer and disk effect through granted and rejected workspace-write retries; unavailable credentials or runners self-skip.
|
||||
- **Snapshot:** pin the atomic current-policy context and both scripted approval branches. A real ACP example scenario places its session under the user home while the deployment fallback points at `/tmp`, then pins both the workspace-write runtime-context message and a successful deployment-selected mutation; this distinguishes session-root resolution from the process fallback without depending on runner-specific denial text. A POSIX fake partial-Landlock provider pins direct bash `false` as an ordinary child result and a missing provider executable as foreground/background infrastructure failure through the assembled app. Other snapshots start unconfined so unrelated fixtures remain platform-independent.
|
||||
|
||||
@@ -128,21 +128,21 @@ Each phase gets its full design when picked up, validated against the code at th
|
||||
|
||||
- **Second consumer** — `subagent-acp` optionally confines child agents (per-call policy; unconfined default — a child agent must write its own persistence).
|
||||
- **More environments** — an environment-coherent capability group example (e.g. bash+fs against one container).
|
||||
- **Windows chain** — `PLATFORM_CHAINS.win32` is reserved and empty (fail-closed); filling it means a confinement runner from the AppContainer/restricted-token family, shipped from its own repository on the `node-addon-landlock-run` template, plus its profile dialect, denial signatures, and runner-failure rules. Wrapping the third-party landstrip runner instead was [considered and rejected](../../rejected/feature/2026-07-26-evaluate-landstrip-for-windows-sandbox-rung.md) — not battle-tested enough for a security invariant.
|
||||
- **Windows chain** — `PLATFORM_CHAINS.win32` is reserved and empty (fail-closed); filling it means a confinement runner from the AppContainer/restricted-token family, shipped from the main repository under `native/` following the `@deepseek-ai/node-addon-landlock-run` template, plus its profile dialect, denial signatures, and runner-failure rules. Wrapping the third-party landstrip runner instead was [considered and rejected](../../rejected/feature/2026-07-26-evaluate-landstrip-for-windows-sandbox-rung.md) — not battle-tested enough for a security invariant.
|
||||
|
||||
## Alternatives considered
|
||||
|
||||
- **Command-string heuristic preflight** — rejected: cannot understand expansion/subprocesses/symlinks; the strict attempt (run it, let the kernel decide) is the only trustworthy denial signal.
|
||||
- **Functionally probe even a platform's sole backend** — rejected: probing arbitrates between candidates; with one there is nothing to decide, and probe cost taxes the first confined command of every session (prohibitive for heavy future backends). The runner's own exec-time fail-closed refusal plus structured `runnerFailureRules` classification carries the safety property instead.
|
||||
- **Commit the built launcher binaries** — rejected: a binary in a diff is unreviewable and churns history; reviewed source + native CI builds + the launcher repo's byte-pinned publish rehearsal keep bytes out of every tree.
|
||||
- **Commit the built launcher binaries** — rejected: a binary in a diff is unreviewable and churns history; reviewed source + native CI builds + the main repository's byte-pinned publish rehearsal keep bytes out of every tree.
|
||||
- **Compile the launcher on install** — rejected: pushes a C toolchain onto every consumer; a fallback that exists only where a compiler happens to be is not a fallback.
|
||||
- **Cross-compile both architectures from one builder** — rejected: requires carrying a pinned cross toolchain (rustup targets, zig, or a container image) solely to rebuild two ~70 KB binaries; per-architecture native runners already exist and each builds its own platform package (the `node-addon-require-builtin` model, the launcher repo's own pipeline).
|
||||
- **Cross-compile both architectures from one builder** — rejected: requires carrying a pinned cross toolchain (rustup targets, zig, or a container image) solely to rebuild two ~70 KB binaries; per-architecture native runners already exist and each builds its own platform package (the `node-addon-require-builtin` model, retained by the main repository's native pipeline).
|
||||
- **No fallback (bwrap or fail closed)** — rejected: concentrates failure on the hosts a sandbox matters most, degrading to `danger-full-access` by resignation.
|
||||
- **Keep the mechanism inside `dsh-bash-sandbox`** — rejected: blocks the existing second consumer, makes future phases read mode out of a bash plugin's config, and cannot express escalation.
|
||||
- **Config-fixed mode on the provider** — rejected: one mode per process; cannot serve concurrent consumers with different policies nor the one-shot widened retry.
|
||||
- **One interface spanning containers/VMs too** — rejected: `confine(argv)` presupposes a shared filesystem; environment isolation is capability-sibling backends deployed as coherent groups.
|
||||
- **Generic ToolRuntime wrapping any tool** — rejected: mechanically false for in-process tools (closures over `ctx`); the declarative-effects rewrite is unjustified for fs/web/todo.
|
||||
- **Ask inside the executor (`dsh-bash-sandbox`)** — rejected: no `agent` to route through, no `callId` to attach the prompt to; adding them teaches a transport seam about sessions and UIs — the tool layer holds both and owns the model-facing vocabulary.
|
||||
- **Ask inside the executor (`dsh-bash-sandbox`)** — rejected: no `agent` to route through, no `callId` to attach the prompt to; adding them teaches a transport boundary about sessions and UIs — the tool layer holds both and owns the model-facing vocabulary.
|
||||
- **Auto-retry inside the same tool call** — rejected: a hidden re-entry the log cannot reconstruct: one `tool/call` would have produced two executions with different policies — the retry is a NEW logged call with its own arguments and result facts.
|
||||
- **Advertise the escalation fields unconditionally** — rejected: under `dsh-bash-local` they are a dead lever — advertising an option the harness cannot honor manufactures doomed grants; capability-gating costs one registration-time read.
|
||||
- **A default-relative escalation ladder (advertise only the modes wider than the executor's registration-time default)** — rejected: per-session overrides make the default the wrong baseline — a session switched narrower than the default loses exactly the lever it needs, and under a `danger-full-access` default the fields vanish entirely while a `read-only`-overridden session stays confined with no escalation path. The enum pins the closed target vocabulary; strict widening is a per-call execution check against the session's effective mode.
|
||||
@@ -175,7 +175,7 @@ Costs and accepted limits:
|
||||
- **The Seatbelt rung leans on Apple's deprecated-but-shipped `sandbox-exec` CLI.** As darwin's sole candidate it is selected without probing, so a future removal under a usable workdir surfaces as a runner-attributable spawn failure and an executable refusal through its fatal signature — both become `SANDBOX_UNAVAILABLE`, and the command never runs; fail closed, never open.
|
||||
- **Landlock confinement is only as complete as the running kernel's ABI.** Reported as `enforcement: 'partial'` rather than refused — the deliberate trade that keeps the fallback available on older-kernel hosts.
|
||||
- **Runner attribution uses an in-band protocol.** Exit status plus stderr cannot cryptographically identify the writer, so a confined child can mimic a fatal runner line and status to cause an availability/diagnostic false attribution. The conjunction and exact notice exclusion reduce accidental matches; this is not a sandbox bypass because the child is already confined.
|
||||
- **The launcher arrives as a registry dependency.** Trusted through its own repository's release pipeline (reviewed C source, native CI builders, byte-pinned publish rehearsal) plus this repo's version pin — the real-kernel e2e legs are what vouch for behavior through the installed bytes.
|
||||
- **The launcher is a workspace dependency in source and an npm dependency after publication.** The main repository tests reviewed C source, native CI builds, and byte-pinned local tarballs together before publishing the same package family; the real-kernel e2e legs vouch for behavior through those installed bytes.
|
||||
- **The model may over-ask.** Escalating without denial grounding, or picking `danger-full-access` where `workspace-write` suffices: the description steers and the enum forces the ladder, but the human prompt is the actual gate; the `approval/asked` reasons make over-asking auditable, and a `prepend` policy answerer can auto-reject patterns a deployment never wants.
|
||||
- **The advertised target set is static while the effective mode is per-session** (schemas are registry-global) — a session already at the widest mode is still offered the fields. Harmless by construction: the strict-wider check at execution, not the enum, is the safety boundary — a non-widening request fails with its own text and never prompts anyone.
|
||||
- **A granted escalation is not a working sandbox.** An unavailable backend still fails closed even for a granted escalation to a confining mode — at `confine()` when the platform has no chain or every probe fails, through the spawn channel when the selected executable cannot start, or through a structured rule when a started runner refuses — while a granted `danger-full-access` run never touches the provider at all: there the grant, not the probe, is the authority.
|
||||
@@ -185,9 +185,9 @@ Costs and accepted limits:
|
||||
## FAQ
|
||||
|
||||
- **A command came back with `[sandbox: file access denied under read-only mode]` — did it fail?** It RAN, and the kernel refused a file effect: the denial is a result fact orthogonal to exit code. The teaching forbids retrying around it; the one sanctioned move is the same command retried once with an escalation request.
|
||||
- **How is a BROKEN sandbox told apart from a failing command?** Any provider-argv spawn rejection proves the confined launch never started, but it identifies a broken runner only when the caller-owned workdir is usable and Node reports attributable `ENOENT` or `EACCES` for that argv[0]. A bare `syscall: 'spawn'` without an exact error path and all other rejections remain ordinary command-start errors. After a process starts, runner failure outranks denial only when one `runnerFailureRules` entry matches both its optional exit-code gate and a fatal stderr line after exact informational exclusions. Foreground failures throw structured `SANDBOX_UNAVAILABLE` with spawn or matched-line detail; an asynchronously rejected or settled background task stamps `sandbox.runnerFailed` and renders its own marker. A `SubprocessService` that synchronously throws the same provenanced `ENOENT`/`EACCES` shape makes background start throw the structured error; other synchronous errors propagate unchanged. A Landlock partial-enforcement notice plus an ordinary child failure remains a command result.
|
||||
- **How is a BROKEN sandbox told apart from a failing command?** Any provider-argv spawn rejection proves the confined launch never started, but it identifies a broken runner only when the caller-owned workdir is usable and Node reports attributable `ENOENT` or `EACCES` for that argv[0]. A bare `syscall: 'spawn'` without an exact error path and all other rejections remain ordinary command-start errors. After a process starts, runner failure outranks denial only when one `runnerFailureRules` entry matches both its optional exit-code gate and a fatal stderr line after exact informational exclusions. Foreground failures throw structured `SANDBOX_UNAVAILABLE` with spawn or matched-line detail; an asynchronously rejected or settled background task stamps `sandbox.runnerFailed` and renders its own marker. A `SubprocessService` that synchronously throws the same `ENOENT`/`EACCES` shape with the runner path makes background start throw the structured error; other synchronous errors propagate unchanged. A Landlock partial-enforcement notice plus an ordinary child failure remains a command result.
|
||||
- **What happens on a platform with no backend — Windows today?** `confine()` throws the fail-closed `SANDBOX_UNAVAILABLE` and the command never spawns; `win32` is a reserved EMPTY chain, pinned by test to fail closed identically until a Windows runner fills it (§ Deferred phases).
|
||||
- **`bwrap` is installed on my host but unusable (disabled unprivileged userns, an LSM denying `mount`) — what happens?** The chain probe is functional — it builds and enforces a real profile rather than checking `--version` — so a present-but-unusable `bwrap` fails its probe, selection falls to the registry-installed Landlock launcher, and the verdict is cached for the provider's lifetime.
|
||||
- **`bwrap` is installed on my host but unusable (disabled unprivileged userns, an LSM denying `mount`) — what happens?** The chain probe is functional — it builds and enforces a real profile rather than checking `--version` — so a present-but-unusable `bwrap` fails its probe, selection falls to the packaged Landlock launcher, and the verdict is cached for the provider's lifetime.
|
||||
- **Does the sandbox restrict network or process visibility?** No — `SandboxMode` claims FILE effects only; the bwrap profile deliberately does not unshare pid, and no backend claims network. Whether network restriction becomes its own knob is left open in § The seam.
|
||||
- **Which tools actually run confined?** OS subprocesses through `ctx.bash` — the bash tools, and hook commands transitively — plus the filesystem tools (`read`/`write`/`edit`) through the sandboxed `ctx.fs` provider (the [cross-family fs sandbox RFC](2026-07-14-cross-family-fs-sandbox.md)): bash confines via the OS runner, fs via an in-process path fence, both keying off the same `ctx.sandboxPolicy` mode. web/todo stay in-process and unfenced (web's only effect is network, outside the file-effect mode vocabulary).
|
||||
- **Does a granted escalation persist?** No. The grant is consumed by the exact foreground or background call that asked; every neighboring call keeps its own effective mode. A later background denial surfaces through `task_output` and may ground a new exact-command retry.
|
||||
@@ -199,8 +199,8 @@ Costs and accepted limits:
|
||||
|
||||
In-repo precedents this design copies or contrasts with:
|
||||
|
||||
- [The capability-seams Agent Note](../architecture/2026-06-13-capability-seams.md) — the interface/implementation/consumer split and the "don't split preemptively" timing rule the second consumer satisfied.
|
||||
- The `dsh-bash` request/spec split ([the bash vocabulary catalog](../../../../docs/core-data-structures/bash.md)) — the complete `sandboxPolicy` rides its per-call carrier, and the explicit-`resolve()` defaulting convention.
|
||||
- [The capability-seams Agent Note](../architecture/2026-06-13-capability-seams.md) — the Service Definition / Service provider / Consumer split and the "don't split preemptively" timing rule the second consumer satisfied.
|
||||
- The `dsh-bash` request/spec split ([the bash vocabulary catalog](../../../../docs/subsystems/bash.md)) — the complete `sandboxPolicy` rides its per-call carrier, and the explicit-`resolve()` defaulting convention.
|
||||
- [The approval seam Agent Note](2026-07-06-approval-seam.md) — the channel escalation asks through; its answerer waterfall, audit pair, and one-package rationale are recorded there.
|
||||
- [Event-sourced sessions](../architecture/2026-06-11-event-sourced-sessions.md) and [standalone log-only events](../simplification/2026-07-28-remove-synthetic-log-only-turns.md) — the log-as-store foundation the per-session modes fold over, and the explicit durability boundary the anchoring design obeys.
|
||||
- [The interception-seams Agent Note](2026-06-30-interception-seams.md) — the `tools/pre-execute` vocabulary the escalation gate deliberately does not reuse (an escalating call has no pre-execute moment of its own).
|
||||
- [The interception extension-points Agent Note](2026-06-30-interception-extension-points.md) — the `tools/pre-execute` vocabulary the escalation gate deliberately does not reuse (an escalating call has no pre-execute moment of its own).
|
||||
|
||||
@@ -38,7 +38,7 @@ harness 是一个 SDK，因此约束必须是开发者可组合的能力：是
|
||||
|
||||
这一替换对 `ctx.bash` 的所有消费方透明：bash 工具、钩子命令和后台任务照常运行，直接使用提供方返回的已包装 argv 启动。删除 `sandbox` 和 `permission` 条目、将 `bash` 替换为 `@deepseek-ai/dsh-bash-local` 即为退出——执行恢复为无约束，升级字段从工具 schema 中消失，因为它们是基于已挂载执行器的能力门控，而非基于配置。仅省略 `approval` 则保留约束但以自身错误文本关闭每次升级；`permission` 还要求 approval seam 和约束执行器同时存在，因此部分组合的 preset 层在加载时即大声失败。
|
||||
|
||||
配置错误会显式导致失败：`mode` 不在封闭词汇中时在插件加载时被拒绝；主机上没有可用后端时在 `confine()` 阶段抛出结构化的 `SANDBOX_UNAVAILABLE`，而非降级为无约束执行。如果所选 runner 以可归因的 `ENOENT` 或 `EACCES` 拒绝，消费方会在任何命令开始前通过 spawn 通道报告同一基础设施错误；其他 spawn 错误仍保留本地命令启动语义，同时也不会运行任何内容。`dsh-sandbox-local` 上的 `runnerCommand` 是运维人员对一个 bwrap 兼容 runner 的显式断言（跳过链和探测）；它同时充当 keyless 测试的确定性 fake-runner seam。
|
||||
配置错误会显式导致失败：`mode` 不在封闭词汇中时在插件加载时被拒绝；主机上没有可用后端时在 `confine()` 阶段抛出结构化的 `SANDBOX_UNAVAILABLE`，而非降级为无约束执行。如果所选 runner 以可归因的 `ENOENT` 或 `EACCES` 拒绝，消费方会在任何命令开始前通过 spawn 通道报告同一基础设施错误；其他 spawn 错误仍保留本地命令启动语义，同时也不会运行任何内容。`dsh-sandbox-local` 上的 `runnerCommand` 是运维人员对一个 bwrap 兼容 runner 的显式断言（跳过链和探测）；它同时充当 keyless 测试的确定性 fake-runner 钩子。
|
||||
|
||||
被拒绝的文件操作返回 `[sandbox: file access denied under <mode> mode]` 标记，并附带不要绕过拒绝的指令。约束执行器添加配对的 `sandbox_permissions` 和 `justification` 字段，用于一次经批准的重试，该重试必须严格宽于会话的有效模式。授权仅放宽该次重试；拒绝则不执行任何内容，返回 `the user rejected escalating this command to "<mode>"`，且不允许再次请求。由归属方派生的待处理策略上下文会说明当前文件策略，但不会取代这些强制执行边界。当 `dsh-permission` 与某个 UI 适配器一起组合时，一个 preset 同时选定两个旋钮值；不匹配的组合折叠为 `custom`。[ACP 自动化组合](../../../../examples/acp-agent/README.md)不挂载该 UI 服务，而是显式选定其部署模式。
|
||||
|
||||
@@ -50,27 +50,27 @@ OS 子进程约束适用于 bash 执行器（包括钩子命令），后续还
|
||||
|
||||
#### seam：`ctx.sandbox`
|
||||
|
||||
`dsh-sandbox` 负责定义词汇和 `SandboxProvider` 契约：`confine(argv, policy)` 返回调用方应当 spawn 的替代 argv（经过包装，使进程及其所有子进程在约束下运行），加上所选后端达到的 `enforcement` 完整度、其拒绝方言（`denialSignatures`，该后端内核在拒绝文件操作时打印到 stderr 的子串），以及其结构化 runner 失败证据（`runnerFailureRules`，可选的允许退出码加上排除整行精确信息性行后按行匹配的致命签名）；没有可用后端时抛出失败关闭的 `SANDBOX_UNAVAILABLE` 错误，绝不静默放行。词汇：`SandboxMode`（`read-only` / `workspace-write` / `danger-full-access`，仅限文件操作——不声称覆盖网络和进程可见性）、`SandboxEnforcement`（`full` / `partial`）、`SandboxExecutionPolicy`（每次能力调用的完整 mode + 工作区根目录）以及 `SandboxPolicy`（提供给约束后端的子集）。
|
||||
`dsh-sandbox` 负责定义词汇和 `SandboxProvider` 约定：`confine(argv, policy)` 返回调用方应当 spawn 的替代 argv（经过包装，使进程及其所有子进程在约束下运行），加上所选后端达到的 `enforcement` 完整度、其拒绝方言（`denialSignatures`，该后端内核在拒绝文件操作时打印到 stderr 的子串），以及其结构化 runner 失败证据（`runnerFailureRules`，可选的允许退出码加上排除整行精确信息性行后按行匹配的致命签名）；没有可用后端时抛出失败关闭的 `SANDBOX_UNAVAILABLE` 错误，绝不静默放行。词汇：`SandboxMode`（`read-only` / `workspace-write` / `danger-full-access`，仅限文件操作——不声称覆盖网络和进程可见性）、`SandboxEnforcement`（`full` / `partial`）、`SandboxExecutionPolicy`（每次能力调用的完整 mode + 工作区根目录）以及 `SandboxPolicy`（提供给约束后端的子集）。
|
||||
|
||||
策略随每次调用而非提供方携带：两个消费方可以在同一时刻以不同策略约束（bash 在 `read-only` 下运行，而一个受约束的子 agent 保持其状态目录可写），且经批准的升级重试是一次带有更宽策略的新调用——在配置固定的提供方模式下无法表达。
|
||||
|
||||
该 seam 仅约束与宿主机共享文件系统和内核的子进程。容器、microVM 和远程执行器不是此 seam 的后端——它们以环境一致的组替换整个能力实现（`ctx.bash`、`ctx.fs`），因为一个 bash 在容器中运行而 fs 工具写主机的 agent 生活在两个割裂的世界中。
|
||||
该 seam 仅约束与宿主机共享文件系统和内核的子进程。容器、microVM 和远程执行器不是此 seam 的后端——它们以环境一致的组替换整个能力 seam（`ctx.bash`、`ctx.fs`）的 Service provider，因为一个 bash 在容器中运行而 fs 工具写主机的 agent 生活在两个割裂的世界中。
|
||||
|
||||
留待需要时再决定：网络限制是作为独立的 `network_mode` 到来，还是在某个 runner 同时强制两者后合并进 `sandbox_mode`；以及 `SandboxPolicy` 是现在就增加额外的可写根授权（launcher 已支持 `--rw <path>`），还是等到升级机制需要时再加。
|
||||
|
||||
#### 本地后端与随附 launcher
|
||||
|
||||
`dsh-sandbox-local` 在提供方生命周期内选择一个平台 runner 并缓存结论。Linux 功能性探测 `bwrap` 然后 Landlock；macOS 使用 Seatbelt。不支持的平台和不可用的 runner 失败关闭。每次包装携带后端特定的拒绝签名和 runner 失败规则，以便 `dsh-bash-sandbox` 区分被拒绝的文件操作与损坏的沙箱。Landlock runner 失败需要退出码 125，加上一行不是通知的 `landlock-run:` 诊断；即使子进程以 1、2 或 125 退出，精确匹配的部分强制执行通知仍只是信息。Bubblewrap 和 Seatbelt 仍仅依据签名，因为两者的公开契约均未保留 launcher 失败状态。`runnerCommand` 保留面向运维人员的 `runnerFailureSignatures` 配置，要求其中条目均为非空单行，并将它们映射为一条内部致命规则。消费方会直接 spawn 每个返回的 argv，因此缺失的 runner、不可执行的 runner，或 shebang 解释器不可用的可执行脚本会通过可归因的 `ENOENT`／`EACCES` spawn 通道失败，而成功启动的子进程以 126 或 127 退出时仍按普通结果处理。运维人员配置的脚本必然要先启动解释器，再应用自身 profile。
|
||||
`dsh-sandbox-local` 在提供方生命周期内选择一个平台 runner 并缓存结论。Linux 功能性探测 `bwrap` 然后 Landlock；macOS 使用 Seatbelt。不支持的平台和不可用的 runner 失败关闭。每次包装携带后端特定的拒绝签名和 runner 失败规则，以便 `dsh-bash-sandbox` 区分被拒绝的文件操作与损坏的沙箱。Landlock runner 失败需要退出码 125，加上一行不是通知的 `landlock-run:` 诊断；即使子进程以 1、2 或 125 退出，精确匹配的部分强制执行通知仍只是信息。Bubblewrap 和 Seatbelt 仍仅依据签名，因为两者的公开约定均未保留 launcher 失败状态。`runnerCommand` 保留面向运维人员的 `runnerFailureSignatures` 配置，要求其中条目均为非空单行，并将它们映射为一条内部致命规则。消费方会直接 spawn 每个返回的 argv，因此缺失的 runner、不可执行的 runner，或 shebang 解释器不可用的可执行脚本会通过可归因的 `ENOENT`／`EACCES` spawn 通道失败，而成功启动的子进程以 126 或 127 退出时仍按普通结果处理。运维人员配置的脚本必然要先启动解释器，再应用自身 profile。
|
||||
|
||||
launcher 是一个约 300 行的 C 程序（纯 C11，直接使用 Landlock UAPI——除静态链接的 musl 外无其他库，因此审计面仅为该文件加内核的稳定 syscall 契约）：`--ro <path>` / `--rw <path>` 授权，`--`，被包装的 argv；它为自身安装规则集并执行 `exec`（规则集跨 `execve` 继承，且它在限制前设置 `no_new_privs`）；`--probe` 在一个短生命周期子进程中强制最大规则集，仅当内核确实强制时才以 0 退出；所有 launcher 失败都会以 125 退出且不运行子进程，并打印一行致命的 `landlock-run:` 诊断。成功完成 exec 的子进程也可能返回 125，因此仅凭退出状态不能作为 launcher 失败的证据。较旧的 ABI 会在执行子进程之前打印精确的 `landlock-run: partial enforcement (older Landlock ABI)` 通知，因此该行不是致命证据。
|
||||
launcher 是一个约 300 行的 C 程序（纯 C11，直接使用 Landlock UAPI——除静态链接的 musl 外无其他库，因此审计面仅为该文件加内核的稳定 syscall 约定）：`--ro <path>` / `--rw <path>` 授权，`--`，被包装的 argv；它为自身安装规则集并执行 `exec`（规则集跨 `execve` 继承，且它在限制前设置 `no_new_privs`）；`--probe` 在一个短生命周期子进程中强制最大规则集，仅当内核确实强制时才以 0 退出；所有 launcher 失败都会以 125 退出且不运行子进程，并打印一行致命的 `landlock-run:` 诊断。成功完成 exec 的子进程也可能返回 125，因此仅凭退出状态不能作为 launcher 失败的证据。较旧的 ABI 会在执行子进程之前打印精确的 `landlock-run: partial enforcement (older Landlock ABI)` 通知，因此该行不是致命证据。
|
||||
|
||||
Landlock launcher 源码和包工作区位于 `native/landlock-run`，与 harness 消费方同仓。独立的 [`node-addon-landlock-run`](https://github.com/deepseek-harness/node-addon-landlock-run) 仓库是用于打包并发布 npm 包族的发布镜像；导出流程归 `native/README.md` 所有。平台二进制由 npm 选择，入口包拥有路径解析、探测、CLI 参数、致命前缀和部分强制执行通知，而 harness 将沙箱模式映射为授权。将入口点与其二进制一起版本化，使探测解析和启动语法保持对齐。
|
||||
Landlock launcher 源码和包家族位于 `native/landlock-run`，与 harness 消费方同仓，并属于根 pnpm workspace。[仓库内 Landlock 发布决策](../process/2026-08-06-in-repository-landlock-release.md)负责共享锁文件、原生构建、打包演练和 npm 发布边界。平台二进制由 npm 选择，入口包拥有路径解析、探测、CLI 参数、致命前缀和部分强制执行通知，而 harness 将沙箱模式映射为授权。将入口点与其二进制一起版本化，使探测解析和启动语法保持对齐。
|
||||
|
||||
后端 profile 共享模式契约但在必要的主机授权上有所不同。Landlock 和 Seatbelt 在 read-only 模式下仅允许 `/dev/null`；workspace-write 还允许各自所需的主机临时目录根。每次包装携带后端特定的拒绝签名。Landlock 在较旧的 ABI 无法管控所有操作时报告 partial enforcement，而成功的 bwrap 和 Seatbelt profile 报告 full enforcement。
|
||||
后端 profile 共享模式约定但在必要的主机授权上有所不同。Landlock 和 Seatbelt 在 read-only 模式下仅允许 `/dev/null`；workspace-write 还允许各自所需的主机临时目录根。每次包装携带后端特定的拒绝签名。Landlock 在较旧的 ABI 无法管控所有操作时报告 partial enforcement，而成功的 bwrap 和 Seatbelt profile 报告 full enforcement。
|
||||
|
||||
#### bash 消费方
|
||||
|
||||
`dsh-bash-sandbox` 扩展 `LocalBashExecutor`，把精确的 `['bash', '-c', command]` argv 交给 `ctx.sandbox`，并直接 spawn 提供方返回的 argv。这样，随附的原生 runner 建立约束后，shell 语义与 `BASH_ENV` 仍由内层 Bash 处理。提供方错误原样传播。进程启动前，只有当调用方拥有的 workdir 经独立验证可用，并且 Node 报告 `ENOENT` 或 `EACCES`，且带有明确指向提供方 argv[0] 的来源信息时，拒绝才会归因于 runner；没有精确错误路径的裸 `syscall: 'spawn'`、其他错误码、无效 workdir、资源失败、无关 syscall 与无结构拒绝保留本地命令启动语义。前台执行会将可归因于 runner 的拒绝转为 `SANDBOX_UNAVAILABLE` 并附上原始详细信息；异步后台拒绝则盖章 `runnerFailed: true`、`denied: false`。如果 `SubprocessService` 同步抛出同样带有来源信息的 `ENOENT`／`EACCES` 形态，后台启动会抛出 `SANDBOX_UNAVAILABLE`；其他同步错误原样传播。进程启动后，前台与后台共用一个 runner 失败分类器：先排除信息性行，再要求规则的退出码门控与余下的一行致命诊断同时匹配。匹配结果优先于拒绝：前台执行抛出 `SANDBOX_UNAVAILABLE`，并以该致命行作为详细信息；结算后的 `BashProcess` 会盖章 `sandbox.runnerFailed`，bash 生产者再通过通用 `task_output` 渲染它。
|
||||
`dsh-bash-sandbox` 扩展 `LocalBashExecutor`，把精确的 `['bash', '-c', command]` argv 交给 `ctx.sandbox`，并直接 spawn 提供方返回的 argv。这样，随附的原生 runner 建立约束后，shell 语义与 `BASH_ENV` 仍由内层 Bash 处理。提供方错误原样传播。进程启动前，只有当调用方拥有的 workdir 经独立验证可用，Node 报告 `ENOENT` 或 `EACCES`，并且错误符合以下一种形态时，才判定为 runner 失败：`error.path` 等于提供方返回的 `argv[0]`，同时 `syscall` 为 `'spawn'` 或精确的 `'spawn <runner>'`；或者 `error.path` 不存在，同时 `syscall` 为精确的 `'spawn <runner>'`。其他错误码、无效 workdir、资源失败、无关 syscall 与无结构拒绝保留本地命令启动语义。前台执行会将 runner 失败转为 `SANDBOX_UNAVAILABLE` 并附上原始详细信息；异步后台拒绝则盖章 `runnerFailed: true`、`denied: false`。如果 `SubprocessService` 同步抛出同样能指明 runner 的形态，后台启动会抛出 `SANDBOX_UNAVAILABLE`；其他同步错误原样传播。进程启动后，前台与后台共用一个 runner 失败分类器：先排除信息性行，再要求规则的退出码检查与余下的一行致命诊断同时匹配。匹配结果优先于拒绝：前台执行抛出 `SANDBOX_UNAVAILABLE`，并以该致命行作为详细信息；结算后的 `BashProcess` 会盖章 `sandbox.runnerFailed`，bash 生产者再通过通用 `task_output` 渲染它。
|
||||
|
||||
模型会在归属方派生的 `sandbox:policy` 上下文中看到当前有效的文件策略；静态工具描述则解释拒绝标记（`[sandbox: file access denied under <mode> mode]`），鼓励尝试可能被拒绝的命令，并禁止绕过拒绝重试。当升级字段被公布时，被拒绝的结果还会携带升级提示本身，使被认可的同轮次重试在决策点获得提示，而非依赖模型回忆描述（§ 升级机制）。[当前策略决策](2026-07-30-current-sandbox-policy-context.md)负责该上下文的理由与边界。
|
||||
|
||||
@@ -82,7 +82,7 @@ Landlock launcher 源码和包工作区位于 `native/landlock-run`，与 harnes
|
||||
|
||||
当约束执行器被挂载时，`bash` 公布配对的 `sandbox_permissions` 和 `justification` 字段。schema 暴露完整的封闭升级词汇，因为有效模式是按会话的；执行拒绝任何不严格宽于该调用有效模式的目标。批准在执行之前解析。`allowed-once` 仅将授权模式盖章到该请求上，而 `rejected`、`cancelled`、`unavailable`、缺失的 approval 服务或缺失的 agent 都以各自不同的结果文本失败关闭。授权不持久化。
|
||||
|
||||
升级是对被拒绝命令的同轮次重试，使用最窄的足够 `sandbox_permissions` 和一个 `justification`；批准提示是同意步骤。它必须基于实际的拒绝，除非会话已观察到相同的被拒绝访问；禁用或被拒绝的批准终结该命令。重试、批准决策和结果使用既有的工具和批准事件。`dsh-tool-bash` 拥有请求动作，因为执行器 seam 既没有 agent 也没有用户交互所需的 call id。
|
||||
升级是对被拒绝命令的同轮次重试，使用最窄的足够 `sandbox_permissions` 和一个 `justification`；批准提示是同意步骤。它必须基于实际的拒绝，除非会话已观察到相同的被拒绝访问；禁用或被拒绝的批准终结该命令。重试、批准决策和结果使用既有的工具和批准事件。`dsh-tool-bash` 拥有请求动作，因为执行器 Service Definition 既没有 agent 也没有用户交互所需的 call id。
|
||||
|
||||
仍未决定：持久授权超出沙箱模式之外的作用域标识是什么——确切调用、路径、命令前缀、会话或时间窗口——这是公布 `allow_always` 选项之前必须回答的问题。
|
||||
|
||||
@@ -113,12 +113,12 @@ interface SessionEventMap {
|
||||
|
||||
#### 进程内工具
|
||||
|
||||
fs/web/todo 在进程内执行，因此它们的沙箱语义是各自 seam 层面的策略。fs seam 现在通过沙箱提供方强制共享模式词汇（`dsh-fs-sandbox` 按模式限制 write/edit；见[跨工具族 fs 沙箱 Agent Note](2026-07-14-cross-family-fs-sandbox.md)），因此 `read-only`/`workspace-write` 对文件系统工具也是真实边界，而非仅限 bash 的近似。web/todo 仍不受限制（web 的唯一效果是网络，不在文件效果模式词汇内）。没有通用的按工具沙箱运行时：主机中介的工具仅通过返回主机验证的声明式效果来离开进程，那是一次重写而非包装——后续设计选择了一个共享策略归属 `ctx.sandboxPolicy`，由各 seam 强制，而不是统一包装器。
|
||||
fs/web/todo 在进程内执行，因此它们的沙箱语义是各自能力边界层面的策略。fs seam 现在通过沙箱提供方强制共享模式词汇（`dsh-fs-sandbox` 按模式限制 write/edit；见[跨工具族 fs 沙箱 Agent Note](2026-07-14-cross-family-fs-sandbox.md)），因此 `read-only`/`workspace-write` 对文件系统工具也是真实边界，而非仅限 bash 的近似。web/todo 仍不受限制（web 的唯一效果是网络，不在文件效果模式词汇内）。没有通用的按工具沙箱运行时：主机中介的工具仅通过返回主机验证的声明式效果来离开进程，那是一次重写而非包装——后续设计选择了一个共享策略归属 `ctx.sandboxPolicy`，由各能力强制，而不是统一包装器。
|
||||
|
||||
### 测试
|
||||
|
||||
- **单元测试：** 固定平台选择和 profile、直接交接提供方返回的 argv、带有无效 workdir 对照的 spawn 层失败、runner 缺失／不可执行／解释器缺失证据、格式错误 runner 阴性对照、受约束的 `BASH_ENV` 求值顺序、结构化 runner 分类（包括只有部分强制执行通知的子进程结果、带门控的致命证据、子进程退出码 126／127，以及前台／后台一致性）、按调用的模式/根目录解析、按进程事实、升级验证和结果、权限 preset fold 和写入透传，以及运行时上下文排序与具体化。
|
||||
- **Keyless 真实 runner：** 在提供方和 bash 消费方层面对 bwrap、Landlock 和 Seatbelt 执行真实文件系统效果测试；一个真实 Cordis 上下文通过已交付的 bash 和 fs 工具并发驱动两个项目会话，证明在自身根目录写入成功、在兄弟根目录写入被拒绝。打包安装测试证明注册表 launcher 保持可执行。CI 拒绝静默全跳过。
|
||||
- **Keyless 真实 runner：** 在提供方和 bash 消费方层面对 bwrap、Landlock 和 Seatbelt 执行真实文件系统效果测试；一个真实 Cordis 上下文通过已交付的 bash 和 fs 工具并发驱动两个项目会话，证明在自身根目录写入成功、在兄弟根目录写入被拒绝。打包安装测试会安装当前 checkout 的原生 tarball，并证明 launcher 保持可执行且字节完全一致。CI 拒绝静默全跳过。
|
||||
- **With-key：** 以只读模式启动真实 ACP 组合，让模型驱动的 bash 写入命中 runner 的拒绝标记，再通过已授权与被拒绝的 workspace-write 重试驱动 bridge 应答器和磁盘效果；不可用的凭证或 runner 自动跳过。
|
||||
- **快照：** 固定原子化的当前策略上下文和两个脚本化的 approval 分支。一个真实 ACP 示例场景把会话放在用户主目录下，同时让部署后备根目录指向 `/tmp`，然后固定 workspace-write 运行时上下文消息与一次成功的、由部署选定的变更；这能区分会话根目录解析与进程后备值，而不依赖 runner 特定的拒绝文本。一个模拟 Landlock 部分强制执行行为的 POSIX 提供方会在组装后的应用中固定直接执行 bash `false` 时仍得到普通子进程结果，并固定提供方可执行文件缺失时在前台／后台均为基础设施失败。其他快照以无约束启动，使无关 fixture（测试前置数据）保持平台无关。
|
||||
|
||||
@@ -128,25 +128,25 @@ fs/web/todo 在进程内执行，因此它们的沙箱语义是各自 seam 层
|
||||
|
||||
- **第二个消费方**——`subagent-acp` 可选地约束子 agent（按调用策略；默认无约束——子 agent 必须写入自己的持久化）。
|
||||
- **更多环境**——环境一致的能力组示例（如 bash+fs 对一个容器）。
|
||||
- **Windows 链**——`PLATFORM_CHAINS.win32` 保留为空（失败关闭）；填充它意味着来自 AppContainer/restricted-token 家族的约束 runner，从其自己的仓库按 `node-addon-landlock-run` 模板交付，加上其 profile 方言、拒绝签名和 runner 失败规则。改为包装第三方 landstrip runner 的方案[经考虑后已驳回](../../rejected/feature/2026-07-26-evaluate-landstrip-for-windows-sandbox-rung.md)——它所经受的实战检验还不足以承载安全不变式。
|
||||
- **Windows 链**——`PLATFORM_CHAINS.win32` 保留为空（失败关闭）；填充它意味着来自 AppContainer/restricted-token 家族的约束 runner，由主仓库在 `native/` 下按 `@deepseek-ai/node-addon-landlock-run` 模板交付，加上其 profile 方言、拒绝签名和 runner 失败规则。改为包装第三方 landstrip runner 的方案[经考虑后已驳回](../../rejected/feature/2026-07-26-evaluate-landstrip-for-windows-sandbox-rung.md)——它所经受的实战检验还不足以承载安全不变式。
|
||||
|
||||
## 曾考虑的替代方案
|
||||
|
||||
- **命令字符串启发式预检**：否决。无法理解展开/子进程/符号链接；严格尝试（运行它，让内核决定）是唯一可信的拒绝信号。
|
||||
- **即使平台仅有一个后端也功能性探测**：否决。探测用于在候选者之间仲裁；只有一个时无需决策，且探测开销对每个会话的首次约束命令征税（对未来重量级后端而言代价过高）。runner 自身执行时的失败关闭拒绝加结构化 `runnerFailureRules` 分类承载了安全属性。
|
||||
- **提交构建好的 launcher 二进制**：否决。diff 中的二进制不可审查且膨胀历史；经审查的源码 + 原生 CI 构建 + launcher 仓库的字节固定发布演练使二进制远离所有代码树。
|
||||
- **提交构建好的 launcher 二进制**：否决。diff 中的二进制不可审查且膨胀历史；经审查的源码 + 原生 CI 构建 + 主仓库的字节固定发布演练使二进制远离所有代码树。
|
||||
- **安装时编译 launcher**：否决。将 C 工具链强加给每个消费方；仅在碰巧有编译器时才存在的备选不是备选。
|
||||
- **从一个构建器交叉编译两种架构**：否决。仅为重建两个约 70 KB 的二进制就需要携带一个固定的交叉工具链（rustup targets、zig 或容器镜像）；每架构的原生 runner 已存在，各自构建自己的平台包（`node-addon-require-builtin` 模式，launcher 仓库自己的流水线）。
|
||||
- **从一个构建器交叉编译两种架构**：否决。仅为重建两个约 70 KB 的二进制就需要携带一个固定的交叉工具链（rustup targets、zig 或容器镜像）；每架构的原生 runner 已存在，各自构建自己的平台包（`node-addon-require-builtin` 模式，由主仓库的原生流水线保留）。
|
||||
- **无备选（bwrap 或失败关闭）**：否决。将失败集中在沙箱最重要的主机上，最终因放弃而降级到 `danger-full-access`。
|
||||
- **将机制保留在 `dsh-bash-sandbox` 内部**：否决。阻塞既有的第二个消费方，使未来阶段从一个 bash 插件的配置中读取模式，且无法表达升级。
|
||||
- **提供方上的配置固定模式**：否决。每进程一个模式；无法服务具有不同策略的并发消费方，也无法表达一次性放宽重试。
|
||||
- **一个接口同时覆盖容器/VM**：否决。`confine(argv)` 预设共享文件系统；环境隔离是作为一致组部署的能力兄弟后端。
|
||||
- **通用 ToolRuntime 包装任何工具**：否决。对进程内工具（闭包了 `ctx`）机械上不成立；声明式效果重写对 fs/web/todo 而言不合理。
|
||||
- **在执行器内部（`dsh-bash-sandbox`）请求批准**：否决。没有可路由的 `agent`，没有可附加提示词的 `callId`；添加它们会让传输 seam 了解会话和 UI——工具层持有两者并拥有面向模型的词汇。
|
||||
- **在执行器内部（`dsh-bash-sandbox`）请求批准**：否决。没有可路由的 `agent`，没有可附加提示词的 `callId`；添加它们会让传输边界了解会话和 UI——工具层持有两者并拥有面向模型的词汇。
|
||||
- **同一工具调用内自动重试**：否决。日志无法重建的隐藏重入：一个 `tool/call` 会产生两次具有不同策略的执行——重试是一次新的带有自身参数和结果事实的已记录调用。
|
||||
- **无条件公布升级字段**：否决。在 `dsh-bash-local` 下它们是死杠杆——公布 harness 无法兑现的选项会制造注定失败的授权；能力门控仅需注册时一次读取。
|
||||
- **默认值相对的升级阶梯（仅公布比执行器注册时默认值更宽的模式）**：否决。按会话覆盖使默认值成为错误的基线——切换到比默认值更窄的会话恰恰失去它需要的杠杆，而在 `danger-full-access` 默认值下字段完全消失，同时一个被覆盖为 `read-only` 的会话仍处于约束中却没有升级路径。枚举固定封闭的目标词汇；严格放宽是针对会话有效模式的按调用执行检查。
|
||||
- **按会话动态工具 schema**：否决。schema 设计上是注册表全局的（一套 assembly 词汇、固定 header 快照契约），按会话重新注册只能买到执行时严格放宽检查已保证的东西，代价是按会话的 schema 表面和每次切换的 header 变动。
|
||||
- **按会话动态工具 schema**：否决。schema 设计上是注册表全局的（一套 assembly 词汇、固定 header 快照约定），按会话重新注册只能买到执行时严格放宽检查已保证的东西，代价是按会话的 schema 表面和每次切换的 header 变动。
|
||||
- **将重试硬匹配到先前的拒绝**：否决。命令字符串同一性脆弱（引号、`workdir`、env 前缀、作为失败阶段重试的管道）——要么误拒诚实的重试，要么被轻易满足；真正的边界是人看到命令 + 理由。仅在 `allow_always` 授权存储需要机器可检查的范围时才重新考虑。
|
||||
- **通用 `env/state` facts map 加拥有者服务**：否决。approval 和沙箱独立组合，因此任何一方的状态都不应拖入第三个包；单键 fold 各自是一个 `findLast`，拥有者服务自然消解；没有跨旋钮的不变式，因此原子多键补丁无收益。
|
||||
- **通过 `agent.inject()` 加总线事件逐次叙述切换**：否决。独立通知会暴露归属方顺序和中间组合，而一次 pre-step 组合可以原子排队完整的当前状态。
|
||||
@@ -175,7 +175,7 @@ fs/web/todo 在进程内执行，因此它们的沙箱语义是各自 seam 层
|
||||
- **Seatbelt 层级依赖 Apple 已弃用但仍交付的 `sandbox-exec` CLI。** 作为 darwin 的唯一候选，它无需探测即被选中，因此在 workdir 可用时，未来移除会表现为可归因于 runner 的 spawn 失败，可执行文件拒绝则通过其致命签名体现——两者都会变为 `SANDBOX_UNAVAILABLE`，且命令绝不会运行；失败关闭，绝不开放。
|
||||
- **Landlock 约束的完整度取决于运行内核的 ABI。** 报告为 `enforcement: 'partial'` 而非拒绝——这是有意的权衡，使备选在旧内核主机上仍可用。
|
||||
- **Runner 归因使用带内协议。** 退出状态与 stderr 无法以密码学方式识别写入者，因此受限子进程可以模仿 runner 的致命诊断行和状态，造成可用性或诊断误归因。多项证据的合取与精确通知排除减少了意外匹配；这不是沙箱绕过，因为子进程已经受到限制。
|
||||
- **launcher 作为注册表依赖到达。** 通过其自身仓库的发布流水线（经审查的 C 源码、原生 CI 构建器、字节固定的发布演练）加上本仓库的版本固定获得信任——真实内核 e2e 测试环节会验证安装产物的实际行为。
|
||||
- **launcher 在源码中是 workspace 依赖，发布后是 npm 依赖。** 主仓库会在发布同一个包家族之前，一起测试经审查的 C 源码、原生 CI 构建和字节固定的本地 tarball；真实内核 e2e 测试环节会验证这些安装字节的实际行为。
|
||||
- **模型可能过度请求。** 在没有拒绝依据的情况下升级，或在 `workspace-write` 足够时选择 `danger-full-access`：描述引导且枚举强制阶梯，但人的提示词是实际门控；`approval/asked` 原因使过度请求可审计，且 `prepend` 策略应答器可以自动拒绝部署永远不想要的模式。
|
||||
- **公布的目标集是静态的，而有效模式是按会话的**（schema 是注册表全局的）——已处于最宽模式的会话仍被提供这些字段。构造上无害：执行时的严格放宽检查（而非枚举）是安全边界——非放宽请求以自身文本失败且不提示任何人。
|
||||
- **授权的升级不等于可工作的沙箱。** 不可用的后端即使对授权升级到约束模式也仍然失败关闭——平台没有链或所有探测失败时在 `confine()` 阶段失败，所选可执行文件无法启动时通过 spawn 通道失败，已启动的 runner 拒绝时则通过结构化规则失败——而授权的 `danger-full-access` 运行根本不触及提供方：此时授权（而非探测）是权威。
|
||||
@@ -185,9 +185,9 @@ fs/web/todo 在进程内执行，因此它们的沙箱语义是各自 seam 层
|
||||
## FAQ
|
||||
|
||||
- **一个命令返回了 `[sandbox: file access denied under read-only mode]`——它失败了吗？** 它运行了，内核拒绝了一个文件操作：拒绝是与退出码正交的结果事实。相关指令禁止通过绕过限制来重试；唯一被认可的动作是以升级请求重试同一命令一次。
|
||||
- **如何区分损坏的沙箱与失败的命令？** 提供方 argv 的任何 spawn 拒绝都能证明受限启动从未开始，但只有在调用方拥有的 workdir 可用，且 Node 为该 argv[0] 报告可归因的 `ENOENT` 或 `EACCES` 时，才能据此判定 runner 损坏。没有精确错误路径的裸 `syscall: 'spawn'` 和其他所有拒绝仍是普通的命令启动错误。进程启动后，只有当 `runnerFailureRules` 中某一条目同时匹配其可选退出码门控，以及排除整行精确信息性行后的一行致命 stderr 诊断时，runner 失败才会优先于拒绝。前台失败会抛出结构化的 `SANDBOX_UNAVAILABLE`，并附带 spawn 错误或匹配行作为详细信息；遭异步拒绝或已结算的后台任务则盖章 `sandbox.runnerFailed` 并渲染自己的标记。如果 `SubprocessService` 同步抛出同样带有来源信息的 `ENOENT`／`EACCES` 形态，后台启动会抛出该结构化错误；其他同步错误原样传播。Landlock 部分强制执行通知加上普通子进程失败时，仍返回命令结果。
|
||||
- **如何区分损坏的沙箱与失败的命令？** 提供方 argv 的任何 spawn 拒绝都能证明受限启动从未开始，但只有在调用方拥有的 workdir 可用，且 Node 为该 argv[0] 报告可归因的 `ENOENT` 或 `EACCES` 时，才能据此判定 runner 损坏。没有精确错误路径的裸 `syscall: 'spawn'` 和其他所有拒绝仍是普通的命令启动错误。进程启动后，只有当 `runnerFailureRules` 中某一条目同时匹配其可选退出码门控，以及排除整行精确信息性行后的一行致命 stderr 诊断时，runner 失败才会优先于拒绝。前台失败会抛出结构化的 `SANDBOX_UNAVAILABLE`，并附带 spawn 错误或匹配行作为详细信息；遭异步拒绝或已结算的后台任务则盖章 `sandbox.runnerFailed` 并渲染自己的标记。如果 `SubprocessService` 同步抛出同样带有 runner 路径的 `ENOENT`／`EACCES` 形态，后台启动会抛出该结构化错误；其他同步错误原样传播。Landlock 部分强制执行通知加上普通子进程失败时，仍返回命令结果。
|
||||
- **在没有后端的平台上会发生什么——今天的 Windows？** `confine()` 抛出失败关闭的 `SANDBOX_UNAVAILABLE`，命令永不 spawn；`win32` 是保留的空链，由测试固定为同样失败关闭，直到 Windows runner 填充它（§ 延迟阶段）。
|
||||
- **`bwrap` 已安装在我的主机上但不可用（禁用了非特权 userns、LSM 拒绝 `mount`）——会发生什么？** 链探测是功能性的——它构建并强制一个真实 profile 而非检查 `--version`——因此存在但不可用的 `bwrap` 探测失败，选择落到注册表安装的 Landlock launcher，结论在提供方生命周期内缓存。
|
||||
- **`bwrap` 已安装在我的主机上但不可用（禁用了非特权 userns、LSM 拒绝 `mount`）——会发生什么？** 链探测是功能性的——它构建并强制一个真实 profile 而非检查 `--version`——因此存在但不可用的 `bwrap` 探测失败，选择落到已打包的 Landlock launcher，结论在提供方生命周期内缓存。
|
||||
- **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。
|
||||
@@ -199,8 +199,8 @@ fs/web/todo 在进程内执行，因此它们的沙箱语义是各自 seam 层
|
||||
|
||||
本设计复制或对比的仓库内先例：
|
||||
|
||||
- [能力 seam Agent Note](../architecture/2026-06-13-capability-seams.md)——接口/实现/消费方拆分与「不要过早拆分」的时机规则（第二个消费方满足了该规则）。
|
||||
- `dsh-bash` 的 request/spec 拆分（[bash 词汇目录](../../../../docs/core-data-structures/bash.md)）——完整的 `sandboxPolicy` 搭载其按调用载体，以及显式 `resolve()` 默认约定。
|
||||
- [能力 seam Agent Note](../architecture/2026-06-13-capability-seams.md)——Service Definition/Service provider/Consumer 拆分与「不要过早拆分」的时机规则（第二个消费方满足了该规则）。
|
||||
- `dsh-bash` 的 request/spec 拆分（[bash 词汇目录](../../../../docs/subsystems/bash.md)）——完整的 `sandboxPolicy` 搭载其按调用载体，以及显式 `resolve()` 默认约定。
|
||||
- [批准 seam Agent Note](2026-07-06-approval-seam.md)——升级请求通过的通道；其应答器 waterfall（瀑布式事件）、审计对和单包理由记录在那里。
|
||||
- [事件溯源会话](../architecture/2026-06-11-event-sourced-sessions.md)与[独立纯日志事件](../simplification/2026-07-28-remove-synthetic-log-only-turns.md)——按会话模式 fold 所依赖的日志即存储基础，以及锚定设计遵守的显式持久性边界。
|
||||
- [拦截 seam Agent Note](2026-06-30-interception-seams.md)——`tools/pre-execute` 词汇，升级门控刻意不复用它（升级调用没有自己的 pre-execute 时刻）。
|
||||
- [拦截扩展点 Agent Note](2026-06-30-interception-extension-points.md)——`tools/pre-execute` 词汇，升级门控刻意不复用它（升级调用没有自己的 pre-execute 时刻）。
|
||||
|
||||
@@ -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/feature/2026-07-07-mcp-client-plugin.md
|
||||
2026-07-07-mcp-client-plugin.md: 756a5c4dc9f1152ecb1955d93b8dc47fcf07c661
|
||||
2026-07-07-mcp-client-plugin.zh.md: 88401ad63bce0b690561acf3bb820b3b758779fa
|
||||
2026-07-07-mcp-client-plugin.zh.md: 9f45203c479379087c5a19eccce3ab7a339d4ed0
|
||||
|
||||
@@ -104,7 +104,7 @@ type Config = StdioConfig | StreamableHttpConfig
|
||||
|
||||
### 公开名称规范化
|
||||
|
||||
MCP 允许工具名最长 128 字符且可包含 `.`；DeepSeek 的函数名契约允许 `[A-Za-z0-9_-]` 且最多 64 字符。公开名称按确定性规则规范化：非法字符替换为 `_`，当替换或截断改变了名称时，追加 `(serverName, rawName)` 标识的 12 位十六进制 SHA-256 hash，确保不同的 MCP 标识永远不会坍缩为同一个公开名称：
|
||||
MCP 允许工具名最长 128 字符且可包含 `.`；DeepSeek 的函数名约定允许 `[A-Za-z0-9_-]` 且最多 64 字符。公开名称按确定性规则规范化：非法字符替换为 `_`，当替换或截断改变了名称时，追加 `(serverName, rawName)` 标识的 12 位十六进制 SHA-256 hash，确保不同的 MCP 标识永远不会坍缩为同一个公开名称：
|
||||
|
||||
```typescript
|
||||
function publicToolName(serverName: string, rawName: string): string {
|
||||
@@ -131,7 +131,7 @@ MCP 仅保证工具名在[单个服务器内](https://modelcontextprotocol.io/sp
|
||||
### 命名不变式
|
||||
|
||||
1. 每个 MCP 工具拥有稳定标识 `(serverName, rawName)`；每个活跃标识恰好对应一个公开名称。
|
||||
2. 公开名称是确定性的、全局唯一的，且满足 DeepSeek 64 字符 `[A-Za-z0-9_-]` 契约。
|
||||
2. 公开名称是确定性的、全局唯一的，且满足 DeepSeek 64 字符 `[A-Za-z0-9_-]` 约定。
|
||||
3. MCP `tools/call` 始终接收原始的 raw name。
|
||||
4. 连接、断开或重新同步不相关的服务器永远不会重命名已有工具。
|
||||
5. 注册顺序永远不决定哪个工具可用。
|
||||
@@ -206,7 +206,7 @@ v1 否决。它能防止跨服务器冲突，但无法将 MCP 注册与原生 ha
|
||||
## 后果
|
||||
|
||||
- 每个 MCP 服务器只需 `cordis.yml` 中的一条配置即完成集成：`serverName: filesystem` 加一条 stdio 命令（或一个 Streamable HTTP URL），就能将 `mcp__filesystem__read_file` 放入模型的工具列表，可调用，协议上使用原始的 `read_file`。
|
||||
- 公开名称是会话历史和权限/配置表面的一部分；命名算法是由测试固定的 v1 契约，发布后变更即为破坏性变更。
|
||||
- 公开名称是会话历史和权限/配置表面的一部分；命名算法是由测试固定的 v1 约定，发布后变更即为破坏性变更。
|
||||
- `mcp__<serverName>__` 限定符在每个名称上消耗 token。已接受：描述和 JSON Schema 在工具定义 token 中占主导，而限定符换来了稳定标识、冲突隔离和 MCP 全局策略匹配模式（`mcp__*`、`mcp__github__*`）。
|
||||
- **MCP SDK 稳定性**：`@modelcontextprotocol/sdk` 仍在演进中；破坏性变更需要更新桥接。版本已固定，且该 SDK 被广泛采用（Claude Desktop、Cursor、VS Code），因此破坏性变更不太可能悄然发生。
|
||||
- **工具 schema 质量**：MCP 服务器可能暴露描述不佳的工具（模糊的描述、不完整的 JSON Schema）。harness 原样透传——垃圾进垃圾出；这是服务器作者的责任，不是桥接的。
|
||||
|
||||
@@ -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/feature/2026-07-08-background-subagent-tasks.md
|
||||
2026-07-08-background-subagent-tasks.md: 679c57c3173a32b8cfccc6611b4ba74487e7f7e3
|
||||
2026-07-08-background-subagent-tasks.zh.md: 487943ab5cfe78226cde912854099fc56a5833a6
|
||||
2026-07-08-background-subagent-tasks.zh.md: c46f3925bc3334ff4cee79e4d9c95589e5361eaf
|
||||
|
||||
@@ -8,7 +8,7 @@ Status: implemented
|
||||
|
||||
[subagent seam](2026-06-21-subagent-capability-seam.md) 会返回 `SubagentRun`，但原先面向模型的工具会同步收集每一次运行。因此，各自独立的慢速委派要么一直占用父调用，要么按串行方式运行。
|
||||
|
||||
subagent 需要与其他长时间运行的工具相同的启动、收集、列出、停止、归属、通知和清理行为，但不应采用进程流语义。子会话仍是详细记录；父级只需最终答案和任务状态。后台子级的存活时间还会超过启动它的工具调用，因此必须明确其取消和拥有者资源释放契约。
|
||||
subagent 需要与其他长时间运行的工具相同的启动、收集、列出、停止、归属、通知和清理行为，但不应采用进程流语义。子会话仍是详细记录；父级只需最终答案和任务状态。后台子级的存活时间还会超过启动它的工具调用，因此必须明确其取消和拥有者资源释放约定。
|
||||
|
||||
## 决策
|
||||
|
||||
@@ -16,7 +16,7 @@ subagent 需要与其他长时间运行的工具相同的启动、收集、列
|
||||
|
||||
后台 subagent 使用[通用后台任务运行时](../architecture/2026-06-20-generic-long-running-tool-runtime.md)。`task_output`、`task_list` 和 `task_kill` 负责收集、列出、取消、完成通知和提示词引导；系统不提供 subagent 专用的配套工具。
|
||||
|
||||
前台调用保留其同步契约：等待提供方启动和 `run.result`；仅当状态为 `completed` 时返回最终文本；将其他终止原因映射为出错的工具结果；并且始终在返回前释放该运行。
|
||||
前台调用保留其同步约定：等待提供方启动和 `run.result`；仅当状态为 `completed` 时返回最终文本；将其他终止原因映射为出错的工具结果；并且始终在返回前释放该运行。
|
||||
|
||||
对于后台调用，工具会验证父级，并在调用 `ctx.tasks.start()` 前拒绝已中止的执行信号。任务运行时会在调用生产者启动器前，预检控制接口和拥有者清理。该启动器创建独立的 `AbortController` 并启动 `ctx.subagents.start()`；返回 id 之后，工具调用的信号不再拥有该子级。
|
||||
|
||||
|
||||
@@ -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/2026-07-08-self-referential-cordis-toolset.md
|
||||
2026-07-08-self-referential-cordis-toolset.md: 335d5e808016ebc37c8457c5dcf4d7da9d8b8c93
|
||||
2026-07-08-self-referential-cordis-toolset.zh.md: 46d492cd92495a1e4d516db3f82c9e75486bc386
|
||||
2026-07-08-self-referential-cordis-toolset.md: 5fc2fb07fcd0b00bf72c818d3806b298312cdc31
|
||||
2026-07-08-self-referential-cordis-toolset.zh.md: 8f34c97d94cad9b79a0e823406c07cdcfb38793f
|
||||
|
||||
@@ -12,7 +12,7 @@ First, model-written registration must be validated where it happens: a malforme
|
||||
|
||||
## Decision
|
||||
|
||||
The toolset ships as [`@deepseek-ai/dsh-tool-cordis`](../../../../packages/cordis/tool-cordis/README.md) and is demoed by `examples/web-cordis`. It gives the model three tools over the live Cordis runtime in the current DSH process: inspect it, mount an in-memory temporary Plugin, and unmount that Plugin to quiescence.
|
||||
The toolset ships as [`@deepseek-ai/dsh-tool-cordis`](../../../../packages/self-modification/tool-cordis/README.md) and is demoed by `examples/web-cordis`. It gives the model three tools over the live Cordis runtime in the current DSH process: inspect it, mount an in-memory temporary Plugin, and unmount that Plugin to quiescence.
|
||||
|
||||
The vm isolates accidental global pollution, and the context façade hides framework internals. Neither restricts the authority of exposed services: a temporary Plugin can call `ctx.bash` with the host executor's privileges and reach the real filesystem and web services. It runs in the shared DSH runtime and may affect other sessions in that process. This is an opt-in development tool with bash-equivalent trust, not a security boundary or product default.
|
||||
|
||||
@@ -75,10 +75,10 @@ The correctness investment therefore goes where it pays for every capability at
|
||||
|
||||
**A hand-maintained service/event reference in the tool.** The first cut of the inspect tool carried a hand-written table of service method signatures. It was replaced by the generated `api-catalog.ts` because a hand table drifts from the JSDoc the moment a signature changes and nothing gates the drift, whereas the generated artifact is freshness-checked against the same AST the docs use.
|
||||
|
||||
**A new `cordis/mount` session event.** A durable provenance event recording each mount (source, name) has clear precedent (`hook/invoked`, `compact/start`). It was declined for v1: mount and unmount are already visible as `tool/call` / `tool/result` pairs and the tool-set change is already logged as a full changed request header, so a dedicated event would only duplicate the record. It remains addable if an audit use case needs mount provenance separable from the tool call.
|
||||
**A new `cordis/mount` session event.** A durable event recording each mount's source and name has clear precedent (`hook/invoked`, `compact/start`). It was declined for v1: mount and unmount are already visible as `tool/call` / `tool/result` pairs and the tool-set change is already logged as a full changed request header, so a dedicated event would only duplicate the record. It remains addable if an audit use case needs the mount source and name outside the tool call.
|
||||
|
||||
**A hardened / capability-restricted sandbox.** Trapping Node built-ins and handing mount code a whitelist façade rather than the raw context might suggest an intent to sandbox for safety. It is explicitly not that: the traps and the façade narrow the *surface* mount code sees — steering it onto cordis services and away from leak-prone Node built-ins and framework internals — for correctness and to close the unguarded-context escape, but the capabilities the façade exposes (`ctx.bash`, `ctx.fs`, `ctx.web`) reach the real runtime, so it is not a security boundary. A real one (separate process, permission prompts) was out of scope for a dev/opt-in toolset and would fight the entire point — handing the model the live runtime.
|
||||
|
||||
## Consequences
|
||||
|
||||
The toolset is a deliberate opt-in with a fully-privileged `ctx`, so a deployment adopts it as consciously as a bash tool. Several facts follow that the tool descriptions warn the model about directly: a waterfall listener (e.g. `tools/pre-execute`) that returns without calling `next()` vetoes the chain, so a mounted listener can lobotomize the agent's own tool dispatch ([waterfall semantics](../../../../docs/cordis-primer.md#cordis-waterfall-semantics)); mount code runs inside a tool call of the current turn, so awaiting anything that resolves only after the turn deadlocks; `vmTimeoutMs` bounds synchronous evaluation only; and mounts do not survive session resume.
|
||||
The toolset is a deliberate opt-in with a fully-privileged `ctx`, so a deployment adopts it as consciously as a bash tool. Several facts follow that the tool descriptions warn the model about directly: a waterfall listener (e.g. `tools/pre-execute`) that returns without calling `next()` short-circuits the chain, so a mounted listener can stop the agent's own tool dispatch ([waterfall semantics](../../../../docs/cordis-primer.md#cordis-waterfall-semantics)); mount code runs inside a tool call of the current turn, so awaiting anything that resolves only after the turn deadlocks; `vmTimeoutMs` bounds synchronous evaluation only; and mounts do not survive session resume.
|
||||
|
||||
@@ -12,19 +12,19 @@ Status: implemented
|
||||
|
||||
## 决策
|
||||
|
||||
该工具集以 [`@deepseek-ai/dsh-tool-cordis`](../../../../packages/cordis/tool-cordis/README.md) 发布，并由 `examples/web-cordis` 演示。它为模型提供三个工具，用于操作当前 DSH 进程中的活跃 Cordis 运行时：检查该运行时、挂载一个仅存于内存的临时 Plugin，再将该 Plugin 卸载至完全停稳。
|
||||
该工具集以 [`@deepseek-ai/dsh-tool-cordis`](../../../../packages/self-modification/tool-cordis/README.md) 发布，并由 `examples/web-cordis` 演示。它为模型提供三个工具，用于操作当前 DSH 进程中的活跃 Cordis 运行时：检查该运行时、挂载一个仅存于内存的临时 Plugin，再将该 Plugin 卸载至完全停稳。
|
||||
|
||||
vm 隔离了意外的全局污染，上下文门面隐藏了框架内部细节。但二者都不限制已暴露服务的权限：临时 Plugin 可以调用 `ctx.bash` 以宿主执行器的权限运行命令，也能访问真实的文件系统和网络服务。它运行在共享 DSH runtime 中，可能影响同一进程的其他 session。这是一个需要显式启用的开发工具，信任等级与 bash 相当，不是安全边界，也不是产品默认配置。
|
||||
|
||||
### 三个工具
|
||||
|
||||
| 工具 | 契约 |
|
||||
| 工具 | 约定 |
|
||||
|---|---|
|
||||
| `cordis_inspect` | 当前进程活跃运行时的只读报告，每个 `what` 值对应一个 Markdown 段落（省略 `what` 则输出全部段落）。`plugins` 列出全部存活 fiber，`temporary` 只列 `cordis_mount` 创建的临时 Plugin。精确 `name` 搭配 `what: "api"` 或 `what: "events"` 可收窄到一个带源码文档的目标。 |
|
||||
| `cordis_mount` | 立即在 `node:vm` 沙箱中把 `code` 作为异步 JavaScript 函数体求值，且不保存到任何位置。返回的 Plugin 挂在内部 `cordis-dynamic` 分组下，并用新的进程内 id（`dyn-1`、`dyn-2`……）跟踪。 |
|
||||
| `cordis_unmount` | 按 id 卸载一个 `cordis_mount` 临时 Plugin，并只在其自有工具、监听器、服务、定时器和其他 effect 完全停稳后返回。它不能删除 Loader、配置或已安装的 Plugin。 |
|
||||
|
||||
`cordis_inspect` 的段落是 `services`（每个已提供的 ctx 服务及所属 fiber）、`plugins`（全部存活 Plugin fiber）、`tools`（模型可调用的工具）、`temporary`（`cordis_mount` 子集，包含 id、running／pending 状态、提供与等待的服务和生命周期）、`api`（活跃服务签名及其引用类型）和 `events`（harness 事件及分发模式和签名）。临时 Plugin 可跨后续 turn 保持活跃，并在 `cordis_unmount`、工具集卸载或 DSH 重启后消失；系统绝不会自动恢复它们。宽泛的 `api` 和 `events` 报告省略完整 JSDoc；精确 `name` 返回一个服务或事件及其原始 JSDoc。其他段落不能搭配 name，未知目标会失败，而 API 目标必须处于活跃状态。[生成的工具目录](../../../../docs/tool-catalog.md)完整呈现面向模型的调用契约。
|
||||
`cordis_inspect` 的段落是 `services`（每个已提供的 ctx 服务及所属 fiber）、`plugins`（全部存活 Plugin fiber）、`tools`（模型可调用的工具）、`temporary`（`cordis_mount` 子集，包含 id、running／pending 状态、提供与等待的服务和生命周期）、`api`（活跃服务签名及其引用类型）和 `events`（harness 事件及分发模式和签名）。临时 Plugin 可跨后续 turn 保持活跃，并在 `cordis_unmount`、工具集卸载或 DSH 重启后消失；系统绝不会自动恢复它们。宽泛的 `api` 和 `events` 报告省略完整 JSDoc；精确 `name` 返回一个服务或事件及其原始 JSDoc。其他段落不能搭配 name，未知目标会失败，而 API 目标必须处于活跃状态。[生成的工具目录](../../../../docs/tool-catalog.md)完整呈现面向模型的调用约定。
|
||||
|
||||
### 沙箱语义
|
||||
|
||||
@@ -32,9 +32,9 @@ vm 隔离了意外的全局污染，上下文门面隐藏了框架内部细节
|
||||
|
||||
沙箱全局变量刻意精简：一个带标签的直写 `console`（在宿主 stdout/stderr 上输出 `[cordis:<id>] …`，这样在挂载调用之后很久才触发的监听器输出仍能落到用户可见的地方）、`harness.defineTool` / `harness.registerTool` 注册对、新 vm 上下文缺少的编码原语（`btoa`/`atob` 作为基于 `Buffer` 的宿主闭包——这是一个经过审批的例外，`Buffer` 本身从不暴露——加上 `TextEncoder`/`TextDecoder`），以及对被扣留的 Node API 的可调用陷阱（`require`、`setTimeout`/`setInterval`/`setImmediate`/`clearTimeout`/`clearInterval`、`fetch`），这些陷阱会抛出一条重定向消息指明 cordis 替代方案。只有函数形态的全局变量才设陷阱；`process` 和 `Buffer` 保持 `undefined`，这样 `typeof` 特性探测保持惰性而不会引爆一个抛异常的访问器。
|
||||
|
||||
挂载代码通过三道控制跨越 vm 边界。双 realm `instanceof` 同时识别宿主和 vm 对象。`harness.defineTool` 在宿主 realm 中重建输出 schema／投影器，将工具体返回值快照为宿主自有的 JSON，并让注册表在观测前强制执行[规范工具输出契约](../architecture/2026-07-20-canonical-tool-output-contract.md)。挂载的插件接收的是一个白名单上下文门面，而非原始或透传的 `Context`；框架管道和以 context 为值的返回会被拒绝。服务读取需要声明 `inject`，保留 Cordis 的激活与卸载语义。`ctx.tools.get` 仅暴露 schema 视图，因此挂载代码无法绕过 `ToolRegistry.execute` 直接调用定义。
|
||||
挂载代码通过三道控制跨越 vm 边界。双 realm `instanceof` 同时识别宿主和 vm 对象。`harness.defineTool` 在宿主 realm 中重建输出 schema／投影器，将工具体返回值快照为宿主自有的 JSON，并让注册表在观测前强制执行[规范工具输出约定](../architecture/2026-07-20-canonical-tool-output-contract.md)。挂载的插件接收的是一个白名单上下文门面，而非原始或透传的 `Context`；框架管道和以 context 为值的返回会被拒绝。服务读取需要声明 `inject`，保留 Cordis 的激活与卸载语义。`ctx.tools.get` 仅暴露 schema 视图，因此挂载代码无法绕过 `ToolRegistry.execute` 直接调用定义。
|
||||
|
||||
边界将无歧义的 JSON-Schema 形式规范化为 `ParameterSchemaSpec`，同时保留 `integer`、原始对象开放性和 required 数组。直接使用 DSL 的对象节点必须声明 `additionalProperties`；无效词汇会报错并给出可接受的替代方案。解析错误、TypeScript 错误、缺少 return、Node API 误用和重复工具名等错误信息包含相关源码行或纠正性契约，不叙述实现内部细节。
|
||||
边界将无歧义的 JSON-Schema 形式规范化为 `ParameterSchemaSpec`，同时保留 `integer`、原始对象开放性和 required 数组。直接使用 DSL 的对象节点必须声明 `additionalProperties`；无效词汇会报错并给出可接受的替代方案。解析错误、TypeScript 错误、缺少 return、Node API 误用和重复工具名等错误信息包含相关源码行或纠正性约定，不叙述实现内部细节。
|
||||
|
||||
### 内部分组与临时 Plugin 生命周期
|
||||
|
||||
@@ -75,10 +75,10 @@ vm 隔离了意外的全局污染，上下文门面隐藏了框架内部细节
|
||||
|
||||
**在工具中手工维护服务/事件参考。** inspect 工具的第一版携带了一份手写的服务方法签名表。它被生成的 `api-catalog.ts` 取代，因为手写表在签名变化的瞬间就会与 JSDoc 脱节且没有门禁约束这种漂移，而生成产物的新鲜度由文档使用的同一套 AST 检查。
|
||||
|
||||
**新增 `cordis/mount` 会话事件。** 一个持久的溯源事件记录每次挂载（源码、名称）有明确先例（`hook/invoked`、`compact/start`）。v1 中予以否决：挂载和卸载已经作为 `tool/call` / `tool/result` 对可见，工具集变化已经作为完整的变更 request header 被记录，因此专用事件只会重复记录。如果审计用例需要将挂载溯源从工具调用中分离出来，日后仍可添加。
|
||||
**新增 `cordis/mount` 会话事件。** 一个持久事件记录每次挂载的源码和名称，有明确先例（`hook/invoked`、`compact/start`）。v1 中予以否决：挂载和卸载已经作为 `tool/call` / `tool/result` 对可见，工具集变化已经作为完整的变更 request header 被记录，因此专用事件只会重复记录。如果审计用例需要在工具调用之外取得挂载的源码和名称，日后仍可添加。
|
||||
|
||||
**加固的/能力受限的沙箱。** 对 Node 内置模块设陷阱并向挂载代码提供白名单门面而非原始上下文，可能暗示意图是为安全而沙箱化。这里明确不是：陷阱和门面收窄的是挂载代码所见的*接口面*——将其引导至 cordis 服务、远离易泄漏的 Node 内置模块和框架内部——目的是正确性和封堵未受保护的上下文逃逸，但门面暴露的能力（`ctx.bash`、`ctx.fs`、`ctx.web`）触及真实运行时，因此它不是安全边界。真正的安全边界（独立进程、权限提示）超出了一个开发/显式启用工具集的范围，且会与其核心目的——将活跃运行时交给模型——相冲突。
|
||||
|
||||
## 后果
|
||||
|
||||
该工具集是刻意的显式启用设计，具有完全特权的 `ctx`，因此部署方采用它的意识程度应与 bash 工具相当。以下几个事实由工具描述直接告知模型：一个 waterfall（瀑布式事件）监听器（如 `tools/pre-execute`）如果不调用 `next()` 就返回，会否决整条链，因此一个挂载的监听器可以瘫痪 agent 自身的工具分发（[waterfall 语义](../../../../docs/cordis-primer.md#cordis-waterfall-semantics)）；挂载代码在当前轮次的工具调用内运行，因此 await 任何只在该轮次结束后才 resolve 的东西会导致死锁；`vmTimeoutMs` 仅约束同步执行；挂载不会在会话恢复后存活。
|
||||
该工具集是刻意的显式启用设计，具有完全特权的 `ctx`，因此部署方采用它的意识程度应与 bash 工具相当。以下几个事实由工具描述直接告知模型：一个 waterfall（瀑布式事件）监听器（如 `tools/pre-execute`）如果不调用 `next()` 就返回，会短路整条链，因此一个挂载的监听器可以阻止 agent 自身的工具分发（[waterfall 语义](../../../../docs/cordis-primer.md#cordis-waterfall-semantics)）；挂载代码在当前轮次的工具调用内运行，因此 await 任何只在该轮次结束后才 resolve 的东西会导致死锁；`vmTimeoutMs` 仅约束同步执行；挂载不会在会话恢复后存活。
|
||||
|
||||
@@ -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/feature/2026-07-10-agent-session-identity-and-log-location.md
|
||||
2026-07-10-agent-session-identity-and-log-location.md: 7b51ae41ac00c12a496940c891092580003646fa
|
||||
2026-07-10-agent-session-identity-and-log-location.zh.md: 46c7c1ce429d66741cffbdd87eb415b90cf32fb3
|
||||
2026-07-10-agent-session-identity-and-log-location.zh.md: b310db258f781cb5326e4bfe9e9daf3a6c1793e7
|
||||
|
||||
@@ -60,9 +60,9 @@ bash 工具说明只讲解持久约定：当前 harness 环境事实通过受管
|
||||
|
||||
## 测试
|
||||
|
||||
单元测试覆盖注册表声明校验、effect 释放、逐次执行收集、`dshHome` 优先级，以及本地执行器清理并重建 `DSH_*` 的顺序。请求录制测试覆盖前台／后台快照、无 agent 调用、持久化不存在或为 JSONL、忽略模型 `env`，以及父子隔离。JSONL／SQLite 定位器契约测试与两套钩子桥接测试均锁定 transcript 可用和不可用两种方言。
|
||||
单元测试覆盖注册表声明校验、effect 释放、逐次执行收集、`dshHome` 优先级，以及本地执行器清理并重建 `DSH_*` 的顺序。请求录制测试覆盖前台／后台快照、无 agent 调用、持久化不存在或为 JSONL、忽略模型 `env`，以及父子隔离。JSONL／SQLite 定位器约定测试与两套钩子桥接测试均锁定 transcript 可用和不可用两种方言。
|
||||
|
||||
一项无密钥的完整循环集成测试会在第一个轮次驱动真实的 agent loop、JSONL 持久化、tool-bash 与 bash-local。子进程打印 `DSH_HOME`、`DSH_SHELL`、会话 id、JSONL 目标和继承的陈旧哨兵值；测试校验当前值、陈旧变量不存在、刷写前文件不存在，并最终检查持久化 header。快照测试会固定录制请求 header 中的通用 bash 说明。该契约属于确定性的本地执行，不涉及模型选择，因此无需带密钥测试。
|
||||
一项无密钥的完整循环集成测试会在第一个轮次驱动真实的 agent loop、JSONL 持久化、tool-bash 与 bash-local。子进程打印 `DSH_HOME`、`DSH_SHELL`、会话 id、JSONL 目标和继承的陈旧哨兵值；测试校验当前值、陈旧变量不存在、刷写前文件不存在，并最终检查持久化 header。快照测试会固定录制请求 header 中的通用 bash 说明。该约定属于确定性的本地执行，不涉及模型选择，因此无需带密钥测试。
|
||||
|
||||
## 考虑过的替代方案
|
||||
|
||||
|
||||
@@ -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/2026-07-10-parallel-tool-call-execution.md
|
||||
2026-07-10-parallel-tool-call-execution.md: 19f5dc189821433052edfa72613980a2e94e2cae
|
||||
2026-07-10-parallel-tool-call-execution.zh.md: 69bff90c11fa132ded325ef610dabf5c609f21af
|
||||
2026-07-10-parallel-tool-call-execution.md: 830691b7596accd1c5746fc51e38a9022f09e501
|
||||
2026-07-10-parallel-tool-call-execution.zh.md: bd336919adbf9b96f64477c1e24964172cde6d92
|
||||
|
||||
@@ -14,7 +14,7 @@ The session log remains authoritative: every started call has an audit event, or
|
||||
|
||||
## Decision
|
||||
|
||||
Each tool may provide an optional `isConcurrencySafe(args)` classifier. It is synchronous and pure: it examines only the current call's parsed arguments and performs no I/O or mutation. Only an explicit `true` opts in; a missing classifier, invalid arguments, a thrown classifier, or any other return value makes the call exclusive. The canonical type contract lives in the [tool data structures](../../../../docs/core-data-structures/tools.md).
|
||||
Each tool may provide an optional `isConcurrencySafe(args)` classifier. It is synchronous and pure: it examines only the current call's parsed arguments and performs no I/O or mutation. Only an explicit `true` opts in; a missing classifier, invalid arguments, a thrown classifier, or any other return value makes the call exclusive. The canonical type contract lives in the [tool data structures](../../../../docs/subsystems/tools.md).
|
||||
|
||||
The classifier is deliberately unary. Returning `true` is the tool's promise that this call may overlap with any sibling call that also returns `true`; the scheduler does not compare calls or prove that their resource accesses are compatible.
|
||||
|
||||
@@ -82,7 +82,7 @@ Snapshot coverage pins the visible multi-call transcript: pending calls may over
|
||||
|
||||
**Parallelize the complete tool pipeline.** This keeps the loop on the public one-call API but runs pre- and post-execute middleware concurrently. Existing guards and hook bridges may carry ordered state, so only dispatch overlaps.
|
||||
|
||||
**Expose staged methods or a scheduling waterfall.** Public `prepare` / `dispatch` / `finalize` methods or a `tools/execution-mode` event add extension surface before another consumer needs it. The loop uses an internal scheduler view, while `executionMode(exec)` leaves an insertion point for a policy seam.
|
||||
**Expose staged methods or a scheduling waterfall.** Public `prepare` / `dispatch` / `finalize` methods or a `tools/execution-mode` event add extension surface before another consumer needs it. The loop uses an internal scheduler view, while `executionMode(exec)` leaves an insertion point for a policy hook.
|
||||
|
||||
**Convert scheduler failures into tool results.** AgentLoop cannot determine whether a rejected dispatch invoked the tool body; ToolRegistry owns body-invocation state and typed tool outcomes. Internal scheduler failures therefore remain terminal instead of being reclassified as `ABORTED` results.
|
||||
|
||||
|
||||
@@ -14,7 +14,7 @@ Status: implemented
|
||||
|
||||
## 决策
|
||||
|
||||
每个工具都可以提供可选的 `isConcurrencySafe(args)` 分类器。该分类器必须是同步纯函数：它只检查当前调用已解析的参数，不执行 I/O 或任何变更。只有显式返回 `true` 才表示选择并行；分类器缺失、参数无效、分类器抛错或返回任何其他值，都会使该调用按独占方式执行。规范类型契约见[工具数据结构](../../../../docs/core-data-structures/tools.md)。
|
||||
每个工具都可以提供可选的 `isConcurrencySafe(args)` 分类器。该分类器必须是同步纯函数：它只检查当前调用已解析的参数，不执行 I/O 或任何变更。只有显式返回 `true` 才表示选择并行；分类器缺失、参数无效、分类器抛错或返回任何其他值，都会使该调用按独占方式执行。规范类型约定见[工具数据结构](../../../../docs/subsystems/tools.md)。
|
||||
|
||||
分类器有意设计为一元函数。返回 `true` 表示工具承诺：此调用可以与任何同样返回 `true` 的并列调用重叠执行。调度器不会比较调用，也不会证明它们的资源访问相容。
|
||||
|
||||
@@ -22,7 +22,7 @@ Status: implemented
|
||||
|
||||
`defineTool()` 先验证参数，再调用类型化分类器。无效参数会被归为独占，且只有该调用真正执行时才会产生常规参数错误。`ctx.tools.executionMode(exec)` 会解析当前有效的工具定义，并返回带标签的 `parallel` 或 `exclusive` 模式；未知工具将按安全侧原则归为独占。
|
||||
|
||||
使用带标签的模式，而不是公开布尔型调度器 API，使得以后可以表达感知资源的变体，无需改变分类器契约。
|
||||
使用带标签的模式，而不是公开布尔型调度器 API，使得以后可以表达感知资源的变体，无需改变分类器约定。
|
||||
|
||||
## 调度与顺序
|
||||
|
||||
@@ -50,7 +50,7 @@ Status: implemented
|
||||
|
||||
Code Mode 仍不使用此调度器，因为模型只会发出一个原生 `run_code` 调用。`run_code` 及其内部派发队列仍按串行方式执行；`mode: 'both'` 中的原生并列调用使用常规调度器。
|
||||
|
||||
## 安全契约
|
||||
## 安全约定
|
||||
|
||||
工具返回 `true` 即承诺：其主体可以与其他并行调用同时运行。它不得直接变更父会话或其他由父级拥有的状态；它将输出返回给循环，由循环按模型顺序提交。
|
||||
|
||||
@@ -78,11 +78,11 @@ Code Mode 仍不使用此调度器，因为模型只会发出一个原生 `run_c
|
||||
|
||||
**使用有状态的分类。** 向分类器提供实时 agent、注册表或 I/O 访问，会使决策依赖分类器的运行时机，并在分类与派发之间留下缺口。可变授权和陈旧状态检查仍属于执行时职责。
|
||||
|
||||
**使用感知并列调用或感知资源的分类。** 调度器可以成对比较调用，或让每个调用声明资源读写要求。这样可以并行化不冲突的写入，却要求不相关工具共享资源标识和冲突语义。一元契约选择放弃这部分并发性，并在安全性取决于调用间关系时按安全侧原则处理。
|
||||
**使用感知并列调用或感知资源的分类。** 调度器可以成对比较调用，或让每个调用声明资源读写要求。这样可以并行化不冲突的写入，却要求不相关工具共享资源标识和冲突语义。一元约定选择放弃这部分并发性，并在安全性取决于调用间关系时按安全侧原则处理。
|
||||
|
||||
**并行执行完整的工具流水线。** 这样可以让循环继续使用公开的单调用 API，但会并发运行 pre-execute 和 post-execute 中间件。现有防护和钩子桥可能承载有序状态，因此只允许派发重叠。
|
||||
|
||||
**公开分阶段方法或调度 waterfall。** 公开的 `prepare` / `dispatch` / `finalize` 方法或 `tools/execution-mode` 事件，会在出现另一个消费方之前扩大扩展接口。循环使用内部调度器视图，而 `executionMode(exec)` 为策略 seam 保留了插入点。
|
||||
**公开分阶段方法或调度 waterfall。** 公开的 `prepare` / `dispatch` / `finalize` 方法或 `tools/execution-mode` 事件，会在出现另一个消费方之前扩大扩展接口。循环使用内部调度器视图，而 `executionMode(exec)` 为策略钩子保留了插入点。
|
||||
|
||||
**将调度器故障转换为工具结果。** AgentLoop 无法判断被拒绝的派发是否已调用工具主体；ToolRegistry 负责工具主体调用状态和类型化工具结果。因此，内部调度器故障保持为终态，而不会被重新分类为 `ABORTED` 结果。
|
||||
|
||||
|
||||
@@ -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/2026-07-10-sqlite-session-query-provider.md
|
||||
2026-07-10-sqlite-session-query-provider.md: 372c21241f9ae5d7300165f016db9b36e6b52855
|
||||
2026-07-10-sqlite-session-query-provider.zh.md: b0789f18f5f334b14fe603ee36924666705136f1
|
||||
2026-07-10-sqlite-session-query-provider.md: 0e15ea15f516091825276c4a9bcde2184c653123
|
||||
2026-07-10-sqlite-session-query-provider.zh.md: caf700fd5979ff64c1445caba7fd44ffc28cb925
|
||||
|
||||
@@ -16,7 +16,7 @@ Splitting those concerns across a provider coordinator and a database implementa
|
||||
|
||||
`@deepseek-ai/dsh-session-query-sqlite` extends the interface service and is the sole concrete owner of `ctx.sessionQuery`. It depends on live `ctx.sessions`, observes optional `ctx.sessionPersistence` dynamically, and owns a dedicated derived SQLite database. There is no search-provider registry, coordinator, persistence event, or agent-loop integration.
|
||||
|
||||
The interface package also owns shared first-party semantic extraction and provider-independent filtering. `SessionResultFilter` covers id, nullable cwd, created-at range, nullable parent, and availability; `ctx.sessionQuery.filterSessions()` applies it without an FTS provider. `SessionEventResultFilter` covers seq/time ranges, event type, surface, and literal semantic text. Arrays are ANDed and list values are ORed. The text clause escapes caller input into a Unicode case-insensitive regular expression whose whitespace runs match one or more whitespace characters; it is available through `ctx.sessionQuery.filterEvents()` and is not delegated to an FTS provider.
|
||||
The Service Definition package also owns shared first-party semantic extraction and provider-independent filtering. `SessionResultFilter` covers id, nullable cwd, created-at range, nullable parent, and availability; `ctx.sessionQuery.filterSessions()` applies it without an FTS provider. `SessionEventResultFilter` covers seq/time ranges, event type, surface, and literal semantic text. Arrays are ANDed and list values are ORed. The text clause escapes caller input into a Unicode case-insensitive regular expression whose whitespace runs match one or more whitespace characters; it is available through `ctx.sessionQuery.filterEvents()` and is not delegated to an FTS provider.
|
||||
|
||||
## Search semantics
|
||||
|
||||
|
||||
@@ -8,7 +8,7 @@ Status: implemented
|
||||
|
||||
精确读取的 `ctx.sessionQuery` 服务有意不维护派生索引。大规模持久化的历史记录需要全文搜索，而不是每次查询都扫描全部事件；当前的活跃会话则需要一个包含上次持久化检查点之后更新的覆盖层。搜索还需要具体的排序、摘要片段、过滤器、分页、取消以及重建行为。
|
||||
|
||||
如果把这些关注点拆分到提供方协调器和数据库实现之间，就会产生两个耦合的对齐状态机。第一个实现既要暴露精简的提供方无关调用契约，也要在同一个生命周期内管理源观察、提取、SQLite 事务、代际与查询执行。
|
||||
如果把这些关注点拆分到提供方协调器和数据库实现之间，就会产生两个耦合的对齐状态机。第一个实现既要暴露精简的提供方无关调用约定，也要在同一个生命周期内管理源观察、提取、SQLite 事务、代际与查询执行。
|
||||
|
||||
## 决策
|
||||
|
||||
@@ -16,7 +16,7 @@ Status: implemented
|
||||
|
||||
`@deepseek-ai/dsh-session-query-sqlite` 扩展接口服务，并且是 `ctx.sessionQuery` 唯一的具体所有者。它依赖实时的 `ctx.sessions`，动态观察可选的 `ctx.sessionPersistence`，并拥有一个专用的派生 SQLite 数据库。系统没有搜索提供方注册表、协调器、持久化事件或 agent loop（智能体循环）集成。
|
||||
|
||||
接口包还拥有共享的第一方语义提取与提供方无关的过滤。`SessionResultFilter` 涵盖 id、可空的 cwd、创建时间范围、可空的父会话与可用性；`ctx.sessionQuery.filterSessions()` 无需 FTS 提供方即可应用这些过滤器。`SessionEventResultFilter` 涵盖 seq/时间范围、事件类型、surface 与字面语义文本。过滤器数组内各项按逻辑与（AND）组合，列表值按逻辑或（OR）组合。文本子句会将调用方输入转义为不区分大小写的 Unicode 正则表达式，其中每段连续空白都匹配一个或多个空白字符；该子句通过 `ctx.sessionQuery.filterEvents()` 提供，不会委托给 FTS 提供方。
|
||||
Service Definition 包还拥有共享的第一方语义提取与提供方无关的过滤。`SessionResultFilter` 涵盖 id、可空的 cwd、创建时间范围、可空的父会话与可用性；`ctx.sessionQuery.filterSessions()` 无需 FTS 提供方即可应用这些过滤器。`SessionEventResultFilter` 涵盖 seq/时间范围、事件类型、surface 与字面语义文本。过滤器数组内各项按逻辑与（AND）组合，列表值按逻辑或（OR）组合。文本子句会将调用方输入转义为不区分大小写的 Unicode 正则表达式，其中每段连续空白都匹配一个或多个空白字符；该子句通过 `ctx.sessionQuery.filterEvents()` 提供，不会委托给 FTS 提供方。
|
||||
|
||||
## 搜索语义
|
||||
|
||||
@@ -38,7 +38,7 @@ Status: implemented
|
||||
|
||||
持久化文档在重启后仍然存在。实时会话使用连接本地的 TEMP 表，遮蔽相同 id 的持久化基础行，并在实时所有者分离时重新显露该基础行。关闭数据库会删除实时行。卸载持久化服务会隐藏持久化行，但不会把缺失视为权威删除；重新挂载后，系统会再次观察并对齐后端。实时会话头与持久化会话头的不可变字段发生冲突时，系统会失败，而不会合并两个来源。
|
||||
|
||||
派生 schema 拥有独立的 application id 与单调递增的 schema 版本。持久化与 TEMP 会话元数据均遵循 `SessionHeader.createdAt` 的整数契约，将其存入严格的 `INTEGER` 列。系统识别到不兼容版本时，只会重置该派生数据库。如果数据库具有不属于本应用的 application id 或无法识别的用户表，系统会在修改日志模式前拒绝该数据库，防止意外配置的规范会话数据库遭到修改。在 POSIX 文件系统上，缺失的目录与数据库文件会以仅所有者可访问的权限创建，使新的 SQLite 伴随文件沿用该模式；现有权限模式保持不变。一个进程中的一个服务独占一条派生索引路径；代际与实时 TEMP 遮蔽状态都归连接所有，因此不支持跨进程写入方。
|
||||
派生 schema 拥有独立的 application id 与单调递增的 schema 版本。持久化与 TEMP 会话元数据均遵循 `SessionHeader.createdAt` 的整数约定，将其存入严格的 `INTEGER` 列。系统识别到不兼容版本时，只会重置该派生数据库。如果数据库具有不属于本应用的 application id 或无法识别的用户表，系统会在修改日志模式前拒绝该数据库，防止意外配置的规范会话数据库遭到修改。在 POSIX 文件系统上，缺失的目录与数据库文件会以仅所有者可访问的权限创建，使新的 SQLite 伴随文件沿用该模式；现有权限模式保持不变。一个进程中的一个服务独占一条派生索引路径；代际与实时 TEMP 遮蔽状态都归连接所有，因此不支持跨进程写入方。
|
||||
|
||||
取消会使排队中的操作及时被拒绝。异步源观察一旦开始，调用方必须等待该后端 Promise 结算后才会收到拒绝；系统不会提交已中止的观察结果，也不会启动更多源观察或索引工作。Node 的同步 `DatabaseSync` 元数据与 MATCH 调用一旦开始在 JavaScript 线程上执行就无法中断，因此服务会在这些调用前后检查信号，但不承诺在语句执行期间抢占。
|
||||
|
||||
@@ -56,4 +56,4 @@ Status: implemented
|
||||
|
||||
选定的分词器以较小的索引体积支持短 token，但不承诺子串召回。字面短语使查询语法安全且可预测，代价是不支持布尔表达式或完整 MATCH 表达式。取消在操作排队或等待数据源期间有效，但同步 SQLite 执行仍是不可抢占区段。
|
||||
|
||||
单元测试将以下行为固化为契约：提取、过滤器、两种搜索范围、所有默认 surface、先过滤元数据再排序、摘要片段、字面量转义、确定性平局处理、完整分页、按范围的游标失效、动态挂载/卸载持久化服务、重启对齐、实时遮蔽、显露与重新打开、schema 安全、回滚重试，以及排队中或进行中的数据源等待取消。一个无需密钥的真实 Loader 路径测试会将该包与真实的 SQLite 持久化后端组合使用。
|
||||
单元测试将以下行为固化为约定：提取、过滤器、两种搜索范围、所有默认 surface、先过滤元数据再排序、摘要片段、字面量转义、确定性平局处理、完整分页、按范围的游标失效、动态挂载/卸载持久化服务、重启对齐、实时遮蔽、显露与重新打开、schema 安全、回滚重试，以及排队中或进行中的数据源等待取消。一个无需密钥的真实 Loader 路径测试会将该包与真实的 SQLite 持久化后端组合使用。
|
||||
|
||||
@@ -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/2026-07-12-subagent-persona-tool-filter-and-depth.md
|
||||
2026-07-12-subagent-persona-tool-filter-and-depth.md: c690f4701a54272205eedf719fbfe0863bac566c
|
||||
2026-07-12-subagent-persona-tool-filter-and-depth.zh.md: e14214b16c413eaa05bcea7bcdf9bca996e8d616
|
||||
2026-07-12-subagent-persona-tool-filter-and-depth.md: 2c5eaf8829e01536a2de34cc190573ff35e4ab77
|
||||
2026-07-12-subagent-persona-tool-filter-and-depth.zh.md: ae64e26d95e42ca6c933892348e22d3cbf0dc722
|
||||
|
||||
@@ -53,7 +53,7 @@ The depth limit bounds recursive delegation independently of tool visibility. A
|
||||
|
||||
The effective parent depth is the greater of durable `SessionHeader.delegationDepth` and runtime `AgentOptions.subagentDepth`. An in-process child records its derived depth in the session header, and resume restores that header, so a restart cannot lower the recursion count.
|
||||
|
||||
Every public entry validates the domain rather than relying on one model-facing configuration path. Negative values, fractions, negative zero, non-finite values, unsafe integers, malformed stored parent depth, and derived overflow all reject. A direct `SubagentStartRequest` may omit the cap to leave depth unbounded; loader-resolved `dsh-tool-subagent` configuration instead defaults to `3`, accepts a numeric override, and uses explicit `'provider-managed'` to omit the cap for an out-of-process provider whose deployment owns its recursion budget. Three is a small finite default that still permits a root plus three descendant generations: the [SDK helper's generated subagent entries](../../../../packages/sdk/helper/src/features/builtin/index.ts) and [JSON-RPC example](../../../../examples/jsonrpc-agent/cordis.yml) use that general policy, while the shipped interactive ACP, headless, and REPL examples pin one. A numeric tool cap fails at provider mount when the provider lacks `depthLimit`.
|
||||
Every public entry validates the domain rather than relying on one model-facing configuration path. Negative values, fractions, negative zero, non-finite values, unsafe integers, malformed stored parent depth, and derived overflow all reject. A direct `SubagentStartRequest` may omit the cap to leave depth unbounded; loader-resolved `dsh-tool-subagent` configuration instead defaults to `3`, accepts a numeric override, and uses explicit `'provider-managed'` to omit the cap for an out-of-process provider whose deployment owns its recursion budget. Three is a small finite default that still permits a root plus three descendant generations: the [SDK helper's generated subagent entries](../../../../packages/scaffold/helper/src/features/builtin/index.ts) and [JSON-RPC example](../../../../examples/jsonrpc-agent/cordis.yml) use that general policy, while the shipped interactive ACP, headless, and REPL examples pin one. A numeric tool cap fails at provider mount when the provider lacks `depthLimit`.
|
||||
|
||||
A deployment can combine depth and filtering, but the numeric cap does not synthesize a filter. The delegation tool stays visible at the cap because authorization may depend on runtime state; every attempted start checks the calling agent's current durable and runtime depth, and a rejected start returns an errored tool result without publishing a child. A deployment may separately deny delegation tools in children when its visibility policy is static. Neither choice changes the provider's conversation-history behavior.
|
||||
|
||||
|
||||
@@ -53,7 +53,7 @@ subagent 启动有三个独立的组合控制：`persona`、`toolFilter` 和 `ma
|
||||
|
||||
有效父级深度取持久 `SessionHeader.delegationDepth` 与运行时 `AgentOptions.subagentDepth` 中的较大值。进程内子 agent 把推导出的深度记录在会话 header 中，恢复时会重新载入该 header，因此重启无法降低递归计数。
|
||||
|
||||
每个公开入口都自行验证值域，而非依赖单一的面向模型配置路径。负值、小数、负零、非有限值、不安全整数、格式错误的存储父级深度以及推导溢出均被拒绝。直接的 `SubagentStartRequest` 可以省略上限，让此机制不约束深度；经 loader 解析的 `dsh-tool-subagent` 配置则默认值为 `3`、接受数值覆盖，并使用显式的 `'provider-managed'` 来省略由进程外提供方部署拥有递归预算时的上限。三是一个较小的有限默认值，仍允许 root 加三代后代：[SDK 辅助函数生成的 subagent 条目](../../../../packages/sdk/helper/src/features/builtin/index.ts)和 [JSON-RPC 示例](../../../../examples/jsonrpc-agent/cordis.yml)采用这项通用策略，而已交付的交互式 ACP、headless 和 REPL 示例固定为一。提供方缺少 `depthLimit` 时，数值工具上限会在提供方挂载阶段失败。
|
||||
每个公开入口都自行验证值域，而非依赖单一的面向模型配置路径。负值、小数、负零、非有限值、不安全整数、格式错误的存储父级深度以及推导溢出均被拒绝。直接的 `SubagentStartRequest` 可以省略上限，让此机制不约束深度；经 loader 解析的 `dsh-tool-subagent` 配置则默认值为 `3`、接受数值覆盖，并使用显式的 `'provider-managed'` 来省略由进程外提供方部署拥有递归预算时的上限。三是一个较小的有限默认值，仍允许 root 加三代后代：[SDK 辅助函数生成的 subagent 条目](../../../../packages/scaffold/helper/src/features/builtin/index.ts)和 [JSON-RPC 示例](../../../../examples/jsonrpc-agent/cordis.yml)采用这项通用策略，而已交付的交互式 ACP、headless 和 REPL 示例固定为一。提供方缺少 `depthLimit` 时，数值工具上限会在提供方挂载阶段失败。
|
||||
|
||||
部署可以组合深度与过滤，但数值上限不会合成过滤器。委派工具在上限处仍然可见，因为授权可能依赖运行时状态；每次尝试启动都会检查调用方 agent 当前的持久与运行时深度，被拒绝的启动返回错误工具结果，且不发布子 agent。可见性策略固定的部署可以另外在子 agent 中 deny 委派工具。两种选择都不改变提供方的对话历史行为。
|
||||
|
||||
@@ -81,7 +81,7 @@ subagent 启动有三个独立的组合控制：`persona`、`toolFilter` 和 `ma
|
||||
|
||||
**为每种人设或工具集创建一个提供方。** 这会使共享相同传输和生命周期实现的提供方成倍增加，使动态部署配置变得笨拙，且仍需要递归机制。提供方的职责是执行传输；请求承载每个子 agent 的组合。
|
||||
|
||||
**复制父级的完整工具视图。** 注册作用域设计上是扁平的，生命周期所有权不意味着可见性继承。复制已解析视图还会冻结动态全局注册，并在未完整定义任一契约的情况下混淆组合与授权。
|
||||
**复制父级的完整工具视图。** 注册作用域设计上是扁平的，生命周期所有权不意味着可见性继承。复制已解析视图还会冻结动态全局注册，并在未完整定义任一约定的情况下混淆组合与授权。
|
||||
|
||||
**在子 agent 创建时快照允许的全局工具。** 冻结的 allow 集合使未来注册统一不可用，但它改变了热注册语义并开启了授权设计。已实现的过滤器保持为活跃的注册表谓词，并直接记录 allow 与 deny 的行为。
|
||||
|
||||
|
||||
@@ -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/2026-07-13-session-query-tracing.md
|
||||
2026-07-13-session-query-tracing.md: 47c12824a331546676d3bc79920f861afe648431
|
||||
2026-07-13-session-query-tracing.zh.md: 88ff93048db0e763888ce6f7fee60918be3675a7
|
||||
2026-07-13-session-query-tracing.md: 66ec68cff116c973c723ee086cdb273f9375842b
|
||||
2026-07-13-session-query-tracing.zh.md: 6a39a9857d30ea7911a313bff5504d4f5ae04562
|
||||
|
||||
@@ -6,7 +6,7 @@ English | [中文](2026-07-13-session-query-tracing.zh.md)
|
||||
|
||||
## Problem
|
||||
|
||||
Session relationships are encoded across immutable headers, positional surface operations, and logged provenance arrays. A consumer reconstructing those relationships directly would need to duplicate corpus precedence, surface folding, malformed-log handling, deterministic lineage ordering, and cloning. Positional replacement and provenance are different graphs, so collapsing them into one generic edge type would also lose meaning.
|
||||
Session relationships are encoded across immutable headers, positional surface operations, and logged arrays of cited source-event seqs. A consumer reconstructing those relationships directly would need to duplicate corpus precedence, surface folding, malformed-log handling, deterministic lineage ordering, and cloning. Positional replacement and cited-source relationships mean different things, so collapsing them into one generic edge type would also lose meaning.
|
||||
|
||||
## Decision
|
||||
|
||||
@@ -14,20 +14,20 @@ Session relationships are encoded across immutable headers, positional surface o
|
||||
|
||||
`SessionLineageTrace` returns the target, known parents in immediate-to-outward order, and recursive descendant trees whose siblings sort by creation time and then session id. `complete: true` carries the known root; `complete: false` carries the first unresolved parent id. A cycle connected to the target fails with `SESSION_QUERY_INVALID_LINEAGE`.
|
||||
|
||||
`SessionEventTrace` keeps positional and provenance relationships separate. `replacedBy` is the immediate positional replacer, `replacementChain` follows replacers to the final node, and `replacedEventSeqs` lists the actual surface nodes directly removed by the target. `sourceEventSeqs` preserves direct logged source order, while `derivedEventSeqs` lists later direct reverse references in log order. Provenance is not expanded transitively.
|
||||
`SessionEventTrace` keeps positional replacements separate from cited source-event relationships. `replacedBy` is the immediate positional replacer, `replacementChain` follows replacers to the final node, and `replacedEventSeqs` lists the actual surface nodes directly removed by the target. `sourceEventSeqs` preserves direct logged source order, while `derivedEventSeqs` lists later direct reverse references in log order. The query does not follow cited source events transitively.
|
||||
|
||||
## Validation boundary
|
||||
|
||||
Event tracing checks target existence before surface analysis. Both event listing and tracing then use `dsh-session`'s one-pass surface fold, which accepts or rejects the loaded log as a whole: event seqs are zero-based and contiguous, surface markers obey event-type eligibility, provenance belongs only to surface event types, present arrays are nonempty and duplicate-free, every source is an earlier seq, and every positional replacement names and cites all surface nodes it removes. Every contract failure uses `SESSION_QUERY_INVALID_SURFACE`; there is no weaker classification-only surface standard.
|
||||
Event tracing checks target existence before surface analysis. Both event listing and tracing then use `dsh-session`'s one-pass surface fold, which accepts or rejects the loaded log as a whole: event seqs are zero-based and contiguous, surface markers obey event-type eligibility, only surface event types may cite source-event seqs, present arrays are nonempty and duplicate-free, every source is an earlier seq, and every positional replacement names and cites all surface nodes it removes. Every contract failure uses `SESSION_QUERY_INVALID_SURFACE`; there is no weaker classification-only surface standard.
|
||||
|
||||
All returned records and arrays are detached. A known live event trace never consults persistence; persisted event traces preserve the exact-read list/load consistency check. Session lineage is necessarily a cross-corpus operation and therefore preserves cross-corpus persistence failure semantics.
|
||||
|
||||
## Alternatives considered
|
||||
|
||||
- **Expose standalone tracing helpers** — rejected because the source-precedence and detachment boundary belongs to `ctx.sessionQuery`; public helpers would invite callers to bypass it.
|
||||
- **Combine replacement and provenance edges** — rejected because a positional replacement can shadow surface nodes while also citing non-surface construction inputs, and consumers need to distinguish those meanings.
|
||||
- **Return transitive provenance closure** — rejected because it obscures logged direct evidence, increases result size, and lets one malformed distant edge alter otherwise local output.
|
||||
- **Best-effort traces over malformed provenance** — rejected because a structurally plausible partial graph would look authoritative. Exact inspection fails loudly when the canonical relationship contract is broken.
|
||||
- **Combine replacement and cited-source edges** — rejected because a positional replacement can shadow surface nodes while also citing non-surface construction inputs, and consumers need to distinguish those meanings.
|
||||
- **Return all transitively cited source events** — rejected because it obscures logged direct evidence, increases result size, and lets one malformed distant edge alter otherwise local output.
|
||||
- **Best-effort traces over malformed source-event lists** — rejected because a structurally plausible partial result would look authoritative. Exact inspection fails loudly when the canonical relationship contract is broken.
|
||||
|
||||
## Consequences
|
||||
|
||||
|
||||
@@ -6,7 +6,7 @@ Status: implemented
|
||||
|
||||
## 问题
|
||||
|
||||
会话关系分散编码在不可变 header、位置式表面操作和已记录的来源数组中。消费方如果直接重建这些关系，就必须重复实现语料优先级、表面折叠、格式错误日志的处理、确定性的谱系顺序和克隆。位置替换与来源属于不同的图，因此把两者合并为一种通用边类型也会丢失含义。
|
||||
会话关系分散编码在不可变 header、位置式表面操作和已记录的来源事件 seq 引用数组中。消费方如果直接重建这些关系，就必须重复实现语料优先级、表面折叠、格式错误日志的处理、确定性的谱系顺序和克隆。位置替换关系与来源事件引用关系表示不同含义，因此把两者合并为一种通用边类型也会丢失含义。
|
||||
|
||||
## 决策
|
||||
|
||||
@@ -14,20 +14,20 @@ Status: implemented
|
||||
|
||||
`SessionLineageTrace` 返回目标、按从直接父级到外层父级排序的已知父级，以及递归的后代树；同级节点先按创建时间排序，再按 session id 排序。`complete: true` 会携带已知根节点；`complete: false` 会携带第一个无法解析的父级 id。与目标相连的循环会以 `SESSION_QUERY_INVALID_LINEAGE` 失败。
|
||||
|
||||
`SessionEventTrace` 将位置关系与来源关系分开保留。`replacedBy` 是直接的位置替换者，`replacementChain` 沿替换者追踪至最终节点，`replacedEventSeqs` 则列出目标直接移除的真实表面节点。`sourceEventSeqs` 保留日志中直接来源的顺序，而 `derivedEventSeqs` 按日志顺序列出后续的直接反向引用。来源关系不会传递展开。
|
||||
`SessionEventTrace` 将位置替换与来源事件引用关系分开保留。`replacedBy` 是直接的位置替换者，`replacementChain` 沿替换者追踪至最终节点，`replacedEventSeqs` 则列出目标直接移除的真实表面节点。`sourceEventSeqs` 保留日志中直接来源的顺序，而 `derivedEventSeqs` 按日志顺序列出后续的直接反向引用。查询不会继续传递追踪被引用的来源事件。
|
||||
|
||||
## 校验边界
|
||||
|
||||
事件追踪会在分析表面之前检查目标是否存在。随后，事件列表与追踪都会使用 `dsh-session` 的单遍表面折叠，对加载的日志整体进行接受或拒绝：事件 seq 从零开始且连续；表面标记符合事件类型的适用范围；只有表面事件类型可以携带来源；存在的数组必须非空且没有重复项；每个来源必须是更早的 seq；每次位置替换必须指明并引用它所移除的全部表面节点。任何契约违例都使用 `SESSION_QUERY_INVALID_SURFACE`；系统不存在只用于分类、要求更弱的表面标准。
|
||||
事件追踪会在分析表面之前检查目标是否存在。随后，事件列表与追踪都会使用 `dsh-session` 的单遍表面折叠，对加载的日志整体进行接受或拒绝：事件 seq 从零开始且连续；表面标记符合事件类型的适用范围；只有表面事件类型可以引用来源事件 seq；存在的数组必须非空且没有重复项；每个来源必须是更早的 seq；每次位置替换必须指明并引用它所移除的全部表面节点。任何约定违例都使用 `SESSION_QUERY_INVALID_SURFACE`；系统不存在只用于分类、要求更弱的表面标准。
|
||||
|
||||
所有返回的记录与数组都与内部状态分离。已知的实时事件追踪绝不查询持久化；持久化事件追踪保留精确读取所要求的列表／加载一致性检查。会话谱系必然属于跨语料操作，因此也保留跨语料的持久化失败语义。
|
||||
|
||||
## 考虑过的替代方案
|
||||
|
||||
- **公开独立的追踪辅助函数**：不予采纳，因为源优先级与状态分离边界属于 `ctx.sessionQuery`；公开辅助函数会诱使调用方绕过该边界。
|
||||
- **合并替换边与来源边**：不予采纳，因为位置替换可以遮蔽表面节点，同时引用不在表面上的构造输入，而消费方需要区分这两种含义。
|
||||
- **返回传递来源闭包**：不予采纳，因为这会掩盖日志中直接记录的证据、增大结果，并让一条遥远的格式错误边改变原本局部的输出。
|
||||
- **在格式错误的来源关系上返回尽力而为的追踪结果**：不予采纳，因为结构上看似合理的局部图会显得具有权威性。当规范的关系契约损坏时，精确检查会明确报错。
|
||||
- **合并替换边与来源事件引用边**：不予采纳，因为位置替换可以遮蔽表面节点，同时引用不在表面上的构造输入，而消费方需要区分这两种含义。
|
||||
- **返回所有传递引用的来源事件**：不予采纳，因为这会掩盖日志中直接记录的证据、增大结果，并让一条遥远的格式错误边改变原本局部的输出。
|
||||
- **对格式错误的来源事件列表返回尽力而为的追踪结果**：不予采纳，因为结构上看似合理的局部结果会显得具有权威性。当规范的关系约定损坏时，精确检查会明确报错。
|
||||
|
||||
## 后果
|
||||
|
||||
|
||||
@@ -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/2026-07-14-cross-family-fs-sandbox.md
|
||||
2026-07-14-cross-family-fs-sandbox.md: e8a59be345b52f7684c574134b37f48bc49843fc
|
||||
2026-07-14-cross-family-fs-sandbox.zh.md: f816bc88db3d7624892fb057e63dd5f24381275e
|
||||
2026-07-14-cross-family-fs-sandbox.md: 1c734a583403d1c1c9ea132a1e089362a9de4707
|
||||
2026-07-14-cross-family-fs-sandbox.zh.md: fdde507e002ac8dac452bb0f783ba8915bfcc30f
|
||||
|
||||
@@ -49,7 +49,7 @@ The [`examples/acp-agent`](../../../../examples/acp-agent/cordis.yml) compositio
|
||||
|
||||
### The enforcement point: provider, not intent gate
|
||||
|
||||
The sandbox Agent Note's original cross-family sketch put fs enforcement on the `fs/write-intent`/`fs/edit-intent` events. This Agent Note enforces in the provider instead, on two mechanical facts: the intent slots are single-decision first-wins (occupied by `dsh-fs-policy`, whose contract names a second decider a misconfiguration), and the intent events are dispatched only by `dsh-tool-fs` — a direct `ctx.fs` caller (a cordis-mounted plugin, a custom tool) bypasses them, where provider-level enforcement covers every caller by construction. The sandbox Agent Note's deferred-phase wording is updated to match in the same change.
|
||||
The sandbox Agent Note's original cross-family sketch put fs enforcement on the `fs/write-intent`/`fs/edit-intent` events. This Agent Note enforces in the provider instead, on two mechanical facts: the intent slots are single-decision first-wins (occupied by `dsh-fs-policy`, whose contract names a second decider a misconfiguration), and the intent events are dispatched only by `dsh-tool-fs` — a direct `ctx.fs` caller (a cordis-mounted plugin, a custom tool) bypasses them, where provider-level enforcement covers every caller by construction.
|
||||
|
||||
### Out of scope
|
||||
|
||||
|
||||
@@ -49,7 +49,7 @@ Status: implemented
|
||||
|
||||
### 强制执行点：提供方，而非 intent gate
|
||||
|
||||
沙箱 Agent Note 最初的跨家族草图把 fs 强制执行放在 `fs/write-intent`/`fs/edit-intent` 事件上。本 Agent Note 改为在提供方中强制执行，基于两个机制性事实:intent 槽是单决策、先到先得(已被 `dsh-fs-policy` 占据,其契约称第二个决策者为配置错误),且 intent 事件只由 `dsh-tool-fs` 派发——一个直连 `ctx.fs` 的调用方(一个 cordis 挂载插件、一个自定义工具)会绕过它们,而提供方级强制执行按构造覆盖每一个调用方。沙箱 Agent Note 的暂缓阶段措辞在同一变更中被更新以匹配。
|
||||
沙箱 Agent Note 最初的跨家族草图把 fs 强制执行放在 `fs/write-intent`/`fs/edit-intent` 事件上。本 Agent Note 改为在提供方中强制执行，基于两个机制性事实:intent 槽是单决策、先到先得(已被 `dsh-fs-policy` 占据,其约定称第二个决策者为配置错误),且 intent 事件只由 `dsh-tool-fs` 派发——一个直连 `ctx.fs` 的调用方(一个 cordis 挂载插件、一个自定义工具)会绕过它们,而提供方级强制执行按构造覆盖每一个调用方。
|
||||
|
||||
### 范围之外
|
||||
|
||||
|
||||
@@ -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/feature/2026-07-16-durable-per-step-time-context.md
|
||||
2026-07-16-durable-per-step-time-context.md: e1a5c65894913ad93f46db8ae45e5ef5ead215f3
|
||||
2026-07-16-durable-per-step-time-context.zh.md: 9cbf653f5d43060e99502b640eed7907ffbd3840
|
||||
2026-07-16-durable-per-step-time-context.zh.md: 129920a02dc21a91ddc92de3d920ddad24968656
|
||||
|
||||
@@ -12,9 +12,9 @@ Status: implemented
|
||||
|
||||
## 决策
|
||||
|
||||
`@deepseek-ai/dsh-time-context` 是位于 `packages/context/time-context/`、需要显式启用的函数插件。`context/` 分组容纳有界的请求上下文增强，这些增强既不定义工具也不定义服务；已交付示例不挂载此插件，因为时区披露与 token 成本属于部署策略。它注册一个前置的 `agent/pre-step` 监听器；需要读数且下游决策 enter 时，返回一条额外的 `UserMessage`。该消息携带来源 `{ kind: 'plugin', plugin: 'time-context' }`；受间隔抑制、reject 或失败的尝试不会追加任何内容。
|
||||
`@deepseek-ai/dsh-time-context` 是位于 `packages/context/time-context/`、需要显式启用的函数插件。`context/` 分组容纳有界的请求上下文增强，这些增强既不定义工具也不定义服务；已交付示例不挂载此插件，因为时区披露与 token 成本属于部署策略。它注册一个前置的 `agent/pre-step` 监听器；当应生成读数且下游决策为进入时，返回一条额外的 `UserMessage`。该消息携带来源 `{ kind: 'plugin', plugin: 'time-context' }`；被抑制、被拒绝或失败的尝试不会追加任何内容。
|
||||
|
||||
监听器在 `step/start` 之前采样，并只在最终 enter 决策中结算读数。AgentLoop 会在 `step/start` 之后、请求派生之前记录它。因此，下游 reject 或失败会阻止读数进入持久历史。
|
||||
监听器在 `step/start` 之前采样，并仅在最终决定进入时确定该读数。AgentLoop 会在 `step/start` 之后、请求派生之前记录它。因此，下游拒绝或失败会阻止读数进入持久历史。
|
||||
|
||||
省略可选配置 `timeZone` 时，插件在加载时解析一次 Node 进程的 IANA 时区；显式值由 `Intl.DateTimeFormat` 校验。时间戳包含数字 UTC 偏移和解析后的 IANA 时区。
|
||||
|
||||
@@ -44,7 +44,7 @@ Elapsed since the preceding step context: <duration-or-unavailable>.
|
||||
|
||||
每个读数都作为普通表层节点保留，直至压缩将其隐藏；正数间隔调度绝不会移除已有读数。因此，后续请求会看到影响先前准备过程和步骤且尚未被隐藏的累计读数，而不是一个被原地改写的系统提示词值。
|
||||
|
||||
插件不向系统提示词组装贡献任何内容。`request/header` 不包含时间上下文文本；请求重建从每个 `step/start` 取得完整的持久表层前缀。读数与请求无需一一对应，因为间隔抑制可以让请求进入步骤而不追加读数，reject 或失败则两者都不追加。插件通过 agent 注册表使用生命周期监听器，运行时不需要系统提示词服务。
|
||||
插件不向系统提示词组装贡献任何内容。`request/header` 不包含时间上下文文本；请求重建从每个 `step/start` 取得完整的持久表层前缀。读数与请求无需一一对应，因为间隔抑制可以让请求进入步骤而不追加读数，拒绝或失败则两者都不追加。插件通过 agent 注册表使用生命周期监听器，运行时不需要系统提示词服务。
|
||||
|
||||
## 测试
|
||||
|
||||
@@ -66,4 +66,4 @@ Elapsed since the preceding step context: <duration-or-unavailable>.
|
||||
- 省略 `refreshIntervalMs` 或设为 `0` 时，每次符合条件的准备尝试都会留下记录；正数间隔会减少追加频率和历史增长，同时使持久调度在恢复后继续生效。
|
||||
- 时间上下文仅追加并保留到压缩隐藏旧表层节点为止，其中也包括后续取消或失败所留下的准备读数。
|
||||
- 第一个步骤的时长通常从开启轮次的提示词起算，后续步骤的时长则反映自上一条步骤上下文以来的模型与工具处理时间。
|
||||
- 省略 `timeZone` 时仍采用部署进程而非远程用户的时区，时长仍采用 harness 的持久追加边界而非客户端来源时间戳。若要支持客户端来源的时间，需要另行建立持久输入契约。
|
||||
- 省略 `timeZone` 时仍采用部署进程而非远程用户的时区，时长仍采用 harness 的持久追加边界而非客户端来源时间戳。若要支持客户端来源的时间，需要另行建立持久输入约定。
|
||||
|
||||
@@ -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/2026-07-16-harness-level-loop.md
|
||||
2026-07-16-harness-level-loop.md: 36a567204ee1082d48126369ee0b7277c9f24ca8
|
||||
2026-07-16-harness-level-loop.zh.md: cb8d29b4c77848613a6718ea3a343b0ee3294ea4
|
||||
2026-07-16-harness-level-loop.md: e5dd94fbf76e27f0843666f29622969635ef2fc3
|
||||
2026-07-16-harness-level-loop.zh.md: 773b5ff1f4b07206d0d817c29774435ce24407b4
|
||||
|
||||
@@ -14,12 +14,12 @@ The repository therefore needs goal-based execution above the turn/step loop, bu
|
||||
|
||||
## Decision
|
||||
|
||||
This proposal is implemented in amended form as two explicit plugin policies over existing seams:
|
||||
Two explicit plugin policies over existing seams:
|
||||
|
||||
1. **Same-session goals** retain one durable objective in the current session and admit goal-attributed continuation turns only while live activation is armed.
|
||||
2. **Fresh-agent Ralph runs** execute a fixed foreground workflow whose rounds each spawn a new structured child with no conversation seed.
|
||||
|
||||
There is no `packages/loop/` family, `LoopDriver`, `LoopId`, universal `StopCondition`, or model-facing generic `loop` tool. The two policies share the repository's ordinary agent, session, tools, workflow, subagent, and UI extension seams, but they do not pretend that one lifecycle fits both.
|
||||
There is no `packages/loop/` family, `LoopDriver`, `LoopId`, universal `StopCondition`, or model-facing generic `loop` tool. The two policies share the repository's ordinary agent, session, tools, workflow, subagent, and UI extension points, but they do not pretend that one lifecycle fits both.
|
||||
|
||||
### Vocabulary and policy boundary
|
||||
|
||||
@@ -36,9 +36,9 @@ Time-based `/loop` or scheduled execution is a third policy and is not implement
|
||||
| Package | Repository category | Owned structures and verbs |
|
||||
|---|---|---|
|
||||
| `@deepseek-ai/dsh-goal` | `packages/goal/goal/`, domain service | Owns `GoalId`, compare-and-set `GoalRef`, `GoalSnapshot`, four-state `GoalPhase`, structured `GoalBlockReason`, process-local `GoalActivation`, replay folding, and `get`, `create`, `edit`, `pause`, `resume`, `complete`, `block`, `clear`, and `disarm` verbs. |
|
||||
| `@deepseek-ai/dsh-tool-goal` | `packages/goal/tool-goal/`, model-facing consumer | Registers exclusive `get_goal`, `create_goal`, and `update_goal`; authenticates live turn provenance and narrows autonomous-round authority to completion or blocking reports with machine-routable reason codes. |
|
||||
| `@deepseek-ai/dsh-tool-goal` | `packages/goal/tool-goal/`, model-facing consumer | Registers exclusive `get_goal`, `create_goal`, and `update_goal`; requires a direct human message in a live root-agent turn and narrows autonomous-round authority to completion or blocking reports with machine-routable reason codes. |
|
||||
| `@deepseek-ai/dsh-goal-session` | `packages/goal/goal-session/`, continuation policy | Reserves, fences, admits, attributes, settles, cancels, and quiescently drains same-session goal rounds without importing the concrete loop. |
|
||||
| `@deepseek-ai/dsh-commands` | `packages/ui/commands/`, UI registry | Owns `CommandDefinition`, discovery, scoped registration, direct dispatch, `CommandResult`, and request cancellation for human-only commands. |
|
||||
| `@deepseek-ai/dsh-commands` | `packages/interaction/commands/`, UI registry | Owns `CommandDefinition`, discovery, scoped registration, direct dispatch, `CommandResult`, and request cancellation for human-only commands. |
|
||||
| `@deepseek-ai/dsh-command-goal` | `packages/goal/command-goal/`, human-command producer | Registers `/goal` status, creation, edit, pause, resume, and clear over the goal domain for TUI. |
|
||||
| `@deepseek-ai/dsh-tool-ralph` | `packages/workflow/tool-ralph/`, fixed workflow consumer | Registers `ralph({ objective, maxRounds? })`, validates the fresh structured provider and bounded `RalphRoundReport`, and returns `complete`, `blocked`, or `budget-limited`. |
|
||||
|
||||
@@ -68,9 +68,9 @@ Normal turn completion schedules another round only while the goal remains activ
|
||||
|
||||
The human UX follows the compact Codex shape in the [public OpenAI Codex TUI dispatcher at commit `678157a`](https://github.com/openai/codex/blob/678157acaa819d5510adfe359abb5d0392cfe461/codex-rs/tui/src/chatwidget/slash_dispatch.rs#L750-L805): `/goal` shows status, `/goal <objective>` creates, and `edit`, `pause`, `resume`, or `clear` perform direct lifecycle actions. The commit permalink keeps the researched grammar verifiable as Codex evolves. Status includes durable phase, admitted/capped rounds, and live armed/disarmed activation. Direct status and command output do not enter model history; accepted domain mutations remain reconstructable because the goal service records them.
|
||||
|
||||
The model receives only `get_goal`, `create_goal`, and `update_goal`. It may create a goal when a direct human request clearly asks for substantial multi-round work, and it may infer that intent in any language. It must not turn routine one-turn work into a goal. Direct-human provenance is enforced in code; semantic interpretation remains model judgment. An autonomous goal round may report `complete` or `blocked` for the exact current goal round but cannot edit, pause, resume, or replace the human objective.
|
||||
The model receives only `get_goal`, `create_goal`, and `update_goal`. It may create a goal when a direct human request clearly asks for substantial multi-round work, and it may infer that intent in any language. It must not turn routine one-turn work into a goal. Code requires a direct human message in the current live root-agent turn; semantic interpretation remains model judgment. An autonomous goal round may report `complete` or `blocked` for the exact current goal round but cannot edit, pause, resume, or replace the human objective.
|
||||
|
||||
TUI mounts the shared command registry and complete goal stack by default and exposes `/goal` through one producer. ACP mounts the goal domain, model tools, and same-session driver but deliberately omits the human command plane. Every effective registered command is discoverable and invocable through every composed command adapter; a plugin incompatible with an application omits its command producer from that composition rather than relying on registry-level surface masks. The UI-less agent spine is opt-in so one-shot callers do not silently become multi-round operations. The headless CLI and JSON-RPC front doors do not consume the command plane; ordinary human text can still authorize model goal tools when that stack is composed.
|
||||
TUI mounts the shared command registry and complete goal stack by default and exposes `/goal` through one producer. ACP mounts the goal domain, model tools, and same-session driver but deliberately omits the human command plane. Every effective registered command is discoverable and invocable through every composed command adapter; a plugin incompatible with an application omits its command producer from that composition rather than relying on registry-level surface masks. The UI-less agent spine is opt-in so one-shot callers do not silently become multi-round operations. The headless CLI and JSON-RPC entry points do not consume the command plane; ordinary human text can still authorize model goal tools when that stack is composed.
|
||||
|
||||
### Fresh-agent Ralph execution
|
||||
|
||||
@@ -98,11 +98,11 @@ The six owning Agent Notes record unit, integration, process, snapshot, cancella
|
||||
|
||||
## Alternatives considered
|
||||
|
||||
- **Implement the original universal loop capability seam** — rejected because `Evaluator`, `BudgetPolicy`, `RoundHandoff`, `GoalReflector`, background task ownership, persistence, and scheduling do not form one coherent mandatory abstraction. Building all of them before their first concrete consumers would create broad speculative surface and duplicate existing session, workflow, subagent, and task machinery.
|
||||
- **Implement the original universal loop capability** — rejected because `Evaluator`, `BudgetPolicy`, `RoundHandoff`, `GoalReflector`, background task ownership, persistence, and scheduling do not form one coherent mandatory abstraction. Building all of them before their first concrete consumers would create broad speculative surface and duplicate existing session, workflow, subagent, and task machinery.
|
||||
- **Implement only same-session goals** — rejected because fresh-context iteration is materially different and is a valuable demonstration of the plugin architecture. Ralph belongs as a fixed workflow consumer with explicit context reset.
|
||||
- **Put Ralph inside the goal-round driver** — rejected because same-session goals deliberately preserve one conversation while Ralph deliberately removes it. Combining them would make activation, replay, handoff, and UI state ambiguous.
|
||||
- **Treat a fork as a fresh Ralph child** — rejected because a fork carries a conversation prefix. Fresh children plus workspace state and one explicit report are easier to bound and replay without a synthetic cancel record.
|
||||
- **Copy Claude Code's evaluator into the first goal implementation** — rejected because a transcript-only model evaluator is one useful policy, not a generally trustworthy completion certificate. Deterministic evaluation and isolation must remain possible, so the evaluator is deferred until its authority and provider seam are designed.
|
||||
- **Copy Claude Code's evaluator into the first goal implementation** — rejected because a transcript-only model evaluator is one useful policy, not a generally trustworthy completion certificate. Deterministic evaluation and isolation must remain possible, so the evaluator is deferred until its authority and provider contract are designed.
|
||||
- **Automatically continue after session restore** — rejected because opening a session is observation, not authority to spend resources. Durable state is restored while activation waits for a new human prompt.
|
||||
- **Route `/goal` through the model** — rejected because status and explicit lifecycle controls should be deterministic, token-free UI actions; ordinary natural-language prompts remain the semantic model path.
|
||||
- **Modify the concrete agent loop with goal or Ralph modes** — rejected because public queue, prompt, session, cancellation, workflow, and subagent seams already support both policies. The generic cancel-requested observation is the only core coordination addition.
|
||||
@@ -111,7 +111,7 @@ The six owning Agent Notes record unit, integration, process, snapshot, cancella
|
||||
|
||||
- Goal-based execution ships without one overloaded “loop” object: same-session continuation and fresh-agent iteration have explicit, separately testable contracts.
|
||||
- Durable goal history is replayable and forkable, while process-local activation prevents accidental work on resume.
|
||||
- Humans receive a small Codex-shaped UX; models receive a compact provenance-checked tool surface; deployments can remove either independently.
|
||||
- Humans receive a small Codex-shaped UX; models receive a compact tool set whose mutating calls require a direct human message in the current live root-agent turn; deployments can remove either independently.
|
||||
- Ralph demonstrates a nontrivial fixed policy entirely as a plugin over existing workflow and subagent primitives.
|
||||
- Round limits are generous by default but remain deployment-controlled. They bound iterations, not tokens, price, elapsed time, or external side effects.
|
||||
- The original proposal's evaluator, budget, reflector, background-task, CLI, and generic loop-session architecture is intentionally not part of the implemented public surface.
|
||||
@@ -125,5 +125,5 @@ The six owning Agent Notes record unit, integration, process, snapshot, cancella
|
||||
- **No generic loop journal or execution-world rewind** — session replay reconstructs goal history, not prior files, processes, environment, credentials, or external side effects. Ralph treats the current workspace as authority and carries no cross-run journal.
|
||||
- **No goal reflector** — concern events, automatic no-progress heuristics, goal revision by an independent reflector, stuck-pattern detection, and `loop_split` are not implemented. Humans can edit, pause, clear, or resume the goal directly.
|
||||
- **Ralph policy remains narrow** — one round creates one fresh child; within-round fan-out, evaluator/worker role separation, dynamic provider/model selection, and structural recursive-Ralph tool denial need separate policy surfaces. Prompt guidance is not enforcement.
|
||||
- **Ralph does not retry a failed child** — an ordinary failure preserves the failed round and last good handoff, while fatal workflow infrastructure failures can end before that state is available. Retry count, backoff, and richer failure transport need separate policy and seam design.
|
||||
- **Ralph does not retry a failed child** — an ordinary failure preserves the failed round and last good handoff, while fatal workflow infrastructure failures can end before that state is available. Retry count, backoff, and richer failure transport need separate policy and boundary design.
|
||||
- **Portable UI remains modest** — TUI renders plain-text goal status and generic Ralph cards. ACP carries only committed assistant text; there is no continuous status widget, reconnectable command output, modal goal editor, or command plane in ACP, the headless CLI, or JSON-RPC.
|
||||
|
||||
@@ -14,12 +14,12 @@ Status: implemented
|
||||
|
||||
## 决策
|
||||
|
||||
本提案以修订后的形式实现为构建在现有 seam 之上的两项显式插件策略：
|
||||
构建在现有 seam 之上的两项显式插件策略：
|
||||
|
||||
1. **同会话目标**在当前会话中保留一个持久目标，并且只在实时激活态已激活时接纳带目标归属的续行轮次。
|
||||
2. **全新 agent Ralph 运行**执行一个固定前台工作流，其中每个 Round 都生成一个不带对话种子的全新结构化子 agent。
|
||||
|
||||
系统中没有 `packages/loop/` 包族、`LoopDriver`、`LoopId`、通用 `StopCondition` 或面向模型的通用 `loop` 工具。两项策略共享本仓库普通的 agent、会话、工具、工作流、subagent 与 UI 扩展 seam，但不会假装一种生命周期可以同时适配两者。
|
||||
系统中没有 `packages/loop/` 包族、`LoopDriver`、`LoopId`、通用 `StopCondition` 或面向模型的通用 `loop` 工具。两项策略共享本仓库普通的 agent、会话、工具、工作流、subagent 与 UI 扩展点，但不会假装一种生命周期可以同时适配两者。
|
||||
|
||||
### 词汇与策略边界
|
||||
|
||||
@@ -36,17 +36,17 @@ Status: implemented
|
||||
| 包 | 仓库类别 | 所属结构与动词 |
|
||||
|---|---|---|
|
||||
| `@deepseek-ai/dsh-goal` | `packages/goal/goal/`，领域服务 | 拥有 `GoalId`、比较并交换 `GoalRef`、`GoalSnapshot`、四状态 `GoalPhase`、结构化 `GoalBlockReason`、进程本地 `GoalActivation`、重放折叠，以及 `get`、`create`、`edit`、`pause`、`resume`、`complete`、`block`、`clear` 与 `disarm` 动词。 |
|
||||
| `@deepseek-ai/dsh-tool-goal` | `packages/goal/tool-goal/`，面向模型消费方 | 注册互斥的 `get_goal`、`create_goal` 与 `update_goal`；认证实时 Turn 来源，并把自治 Round 权限收窄到带机器可路由原因代码的完成或阻塞报告。 |
|
||||
| `@deepseek-ai/dsh-tool-goal` | `packages/goal/tool-goal/`，面向模型消费方 | 注册互斥的 `get_goal`、`create_goal` 与 `update_goal`；要求实时根 agent Turn 中有一条人类直接发送的消息，并把自治 Round 权限收窄到带机器可路由原因代码的完成或阻塞报告。 |
|
||||
| `@deepseek-ai/dsh-goal-session` | `packages/goal/goal-session/`，续行策略 | 在不导入具体 loop 的情况下，预留、设围栏、接纳、归属、结算、取消并排空同会话 Goal Round，直至完全停稳。 |
|
||||
| `@deepseek-ai/dsh-commands` | `packages/ui/commands/`，UI 注册表 | 拥有面向人类专用命令的 `CommandDefinition`、发现、作用域注册、直接分发、`CommandResult` 与请求取消。 |
|
||||
| `@deepseek-ai/dsh-commands` | `packages/interaction/commands/`，UI 注册表 | 拥有面向人类专用命令的 `CommandDefinition`、发现、作用域注册、直接分发、`CommandResult` 与请求取消。 |
|
||||
| `@deepseek-ai/dsh-command-goal` | `packages/goal/command-goal/`，人类命令生产方 | 为 TUI 注册构建在目标领域之上的 `/goal` 状态、创建、编辑、暂停、恢复与清除。 |
|
||||
| `@deepseek-ai/dsh-tool-ralph` | `packages/workflow/tool-ralph/`，固定工作流消费方 | 注册 `ralph({ objective, maxRounds? })`，验证全新结构化 provider 与有界 `RalphRoundReport`，并返回 `complete`、`blocked` 或 `budget-limited`。 |
|
||||
|
||||
详细契约分别由[目标领域](2026-07-19-persisted-same-session-goal-domain.md)、[Goal 自有事件](../architecture/2026-07-31-goal-owned-durable-events.md)、[模型目标工具](2026-07-19-model-facing-goal-tools.md)、[目标回合驱动器](2026-07-19-same-session-goal-round-driver.md)、[命令注册表](2026-07-19-plugin-command-registration.md)、[人类目标命令](2026-07-19-human-goal-command.md)与 [Ralph 工作流工具](2026-07-19-fresh-agent-ralph-workflow-tool.md) Agent Note 拥有。
|
||||
详细约定分别由[目标领域](2026-07-19-persisted-same-session-goal-domain.md)、[目标自有事件](../architecture/2026-07-31-goal-owned-durable-events.md)、[模型目标工具](2026-07-19-model-facing-goal-tools.md)、[目标回合驱动器](2026-07-19-same-session-goal-round-driver.md)、[命令注册表](2026-07-19-plugin-command-registration.md)、[人类目标命令](2026-07-19-human-goal-command.md)与 [Ralph 工作流工具](2026-07-19-fresh-agent-ralph-workflow-tool.md) Agent Note 拥有。
|
||||
|
||||
### 持久目标状态与实时权限
|
||||
|
||||
一个会话至多有一个当前 goal。每次变更都通过持久 `goal/change` 事件提交，并携带带版本的完整快照或带修订号的 clear 墓碑；inbox 状态不参与其中。会话日志是唯一持久真源，因此普通持久化、恢复与 `SessionStore.fork()` 会携带 goal，无需第二个数据库或人为取消记录。
|
||||
一个会话至多有一个当前目标。每次变更都通过持久的 `goal/change` 事件提交；该事件携带带版本的完整快照或带修订号的清除墓碑，收件箱状态不参与其中。会话日志是唯一持久真源，因此普通持久化、恢复与 `SessionStore.fork()` 会携带目标，无需第二个数据库或人为取消记录。
|
||||
|
||||
持久阶段只有 `active`、`paused`、`blocked` 与 `complete`。阻塞目标必须携带 `GoalBlockReason`，其中包含稳定的小写 kebab-case `code` 与非空的人类可读 `message`；用量限制、Round 耗尽、模型失败与策略拒绝都是原因代码，而不是额外生命周期阶段。独立激活态是 `armed` 或 `disarmed`，且永不持久化。创建与显式恢复会激活目标；停止转换、会话启动、fork 回放、驱动器替换和驱动器拆卸都会让目标保持未激活。
|
||||
|
||||
@@ -58,9 +58,9 @@ fork 会话会继承持久目标前缀，因为这是自然的重放结果。for
|
||||
|
||||
### 同会话续行
|
||||
|
||||
Goal Round 驱动器为每个准确实时 agent 至多拥有一个待定预留。只有 goal 处于活跃且已激活状态、agent 空闲、不存在竞争性人类工作、最新变更已经通过持久性检查点、准确 goal id／revision／Round 仍匹配，并且下游 pre-step 策略接受时，它才会接纳预留。其 `agent/pre-step` 围栏会在下游监听器前后检查这些事实，防止编辑、暂停、人类消息或卸载竞争接纳陈旧工作。
|
||||
Goal Round 驱动器为每个特定的实时 agent 至多拥有一个待定预留。只有目标处于活跃且已激活状态、agent 空闲、不存在竞争性人类工作、最新变更已经通过持久性检查点、确切的目标 id／修订号／Round 仍匹配，并且下游 pre-step 策略接受时，它才会接纳预留。其 `agent/pre-step` 围栏会在下游监听器前后检查这些事实，防止编辑、暂停、人类消息或卸载竞争接纳过时工作。
|
||||
|
||||
只有已准入、Round 为正数且来源为 goal 的 `user/message` 会计入一个 Round。陈旧预留会关闭一个 blocked 的无步骤轮次，不会消耗上限。并发 goal revision 会胜过旧 Round 的结算。
|
||||
只有已接纳、Round 为正数且带目标来源的 `user/message` 会计入一个 Round。陈旧预留会结束一个阻塞的零步骤轮次，不会消耗上限。并发目标修订会胜过旧 Round 的结算。
|
||||
|
||||
普通 Turn 完成后，只有目标仍活跃、已激活且低于上限时才会安排另一个 Round。取消会暂停。速率限制或配额耗尽以代码 `usage-limited` 阻塞；上限耗尽使用 `round-limit`；队列失败使用 `queue-failed`；Turn 错误、max-token 停止、策略拒绝与未知终止结果使用各自对应的阻塞代码。独立组合的请求恢复插件可以在同一个 Turn 内重试暂时性 provider 失败；目标驱动器绝不会在异常终止结果后凭空发起另一个 Round。人类随后可以通过普通语言或 `/goal resume` 授权恢复。
|
||||
|
||||
@@ -68,9 +68,9 @@ Goal Round 驱动器为每个准确实时 agent 至多拥有一个待定预留
|
||||
|
||||
人类 UX 遵循 [OpenAI Codex 在提交 `678157a` 时的公开 TUI 分发器](https://github.com/openai/codex/blob/678157acaa819d5510adfe359abb5d0392cfe461/codex-rs/tui/src/chatwidget/slash_dispatch.rs#L750-L805)中的紧凑形态：`/goal` 显示状态，`/goal <objective>` 创建目标，而 `edit`、`pause`、`resume` 或 `clear` 执行直接生命周期操作。该提交永久链接让研究所得语法在 Codex 演进时仍可验证。状态包含持久阶段、已接纳/上限 Round 数以及实时已激活/未激活状态。直接状态与命令输出不会进入模型历史；已接受领域变更仍可重建，因为目标服务会记录它们。
|
||||
|
||||
模型只接收 `get_goal`、`create_goal` 和 `update_goal`。当直接人类请求清楚要求大量多 Round 工作时，模型可以创建目标，并且可以从任何语言推断该意图。它不得把日常单 Turn 工作变成目标。直接人类来源由代码强制执行；语义解释仍是模型判断。自治目标 Round 可以为确切的当前 Goal Round 报告 `complete` 或 `blocked`，但不能编辑、暂停、恢复或替换人类目标。
|
||||
模型只接收 `get_goal`、`create_goal` 和 `update_goal`。当直接人类请求清楚要求大量多 Round 工作时，模型可以创建目标，并且可以从任何语言推断该意图。它不得把日常单 Turn 工作变成目标。代码要求当前实时根 agent Turn 中有一条人类直接发送的消息；语义解释仍是模型判断。自治目标 Round 可以为确切的当前 Goal Round 报告 `complete` 或 `blocked`，但不能编辑、暂停、恢复或替换人类目标。
|
||||
|
||||
TUI 默认挂载共享命令注册表和完整目标栈，并通过一个生产方暴露 `/goal`。ACP（Agent Client Protocol）挂载目标领域、模型工具和同会话驱动器，但有意省略人类命令平面。每条有效已注册命令都能被每个已组合的命令适配器发现和调用；若插件与某应用不兼容，该应用组合会省略其命令生产方，而不是依赖注册表层面的表面掩码。无 UI 的 agent 主干要求显式选择加入，以免单次调用方静默变成多 Round 操作。无头 CLI（命令行界面）与 JSON-RPC 前端不消费命令平面；挂载目标栈后，普通人类文本仍可授权模型目标工具。
|
||||
TUI 默认挂载共享命令注册表和完整目标栈，并通过一个生产方暴露 `/goal`。ACP（Agent Client Protocol）挂载目标领域、模型工具和同会话驱动器，但有意省略人类命令平面。每条有效已注册命令都能被每个已组合的命令适配器发现和调用；若插件与某应用不兼容，该应用组合会省略其命令生产方，而不是依赖注册表层面的表面掩码。无 UI 的 agent 主干要求显式选择加入，以免单次调用方静默变成多 Round 操作。无头 CLI（命令行界面）与 JSON-RPC 运行入口不消费命令平面；挂载目标栈后，普通人类文本仍可授权模型目标工具。
|
||||
|
||||
### 全新 agent Ralph 执行
|
||||
|
||||
@@ -88,7 +88,7 @@ Ralph 是位于自有插件中的一等模型工具，展示了复杂固定执
|
||||
|
||||
Codex 提供了这里采用的最小可观察目标 UX：一个附着于聊天的持久目标，以及设置、查看、编辑、暂停、恢复与清除控制。本实现采用这种可发现性，但使用本仓库的事件溯源目标记录、插件作用域与运行时权限检查。
|
||||
|
||||
当前 [Claude Code goals](https://code.claude.com/docs/en/goal) 进一步验证了“前一 Turn 后启动另一 Turn 的目标”和定时 `/loop` 之间的区别。Claude Code 还会在每个 Turn 后使用独立小模型评估器。本实现采用策略区分，但有意不复制该评估器：评估器输入、工具访问、确定性检查、provider 选择、隔离与权限需要单独设计的插件契约，而不是隐式自我认证层。
|
||||
当前 [Claude Code goals](https://code.claude.com/docs/en/goal) 进一步验证了“前一 Turn 后启动另一 Turn 的目标”和定时 `/loop` 之间的区别。Claude Code 还会在每个 Turn 后使用独立小模型评估器。本实现采用策略区分，但有意不复制该评估器：评估器输入、工具访问、确定性检查、provider 选择、隔离与权限需要单独设计的插件约定，而不是隐式自我认证层。
|
||||
|
||||
外部产品只是比较对象，不是兼容目标。本地源码研究帮助确定边界，而交付接口遵循本仓库“一切皆插件”、模型可见内容均记入日志、显式解析默认值与完全停稳后拆卸规则。
|
||||
|
||||
@@ -98,32 +98,32 @@ Codex 提供了这里采用的最小可观察目标 UX：一个附着于聊天
|
||||
|
||||
## 考虑过的替代方案
|
||||
|
||||
- **实现原始通用 loop 能力 seam**——不予采纳，因为 `Evaluator`、`BudgetPolicy`、`RoundHandoff`、`GoalReflector`、后台任务所有权、持久化与调度并不构成一项一致的必选抽象。在出现首个具体消费者前全部构建，会产生宽泛推测性表面，并重复现有 session、workflow、subagent 与 task 机制。
|
||||
- **实现原始通用 loop 能力**——不予采纳，因为 `Evaluator`、`BudgetPolicy`、`RoundHandoff`、`GoalReflector`、后台任务所有权、持久化与调度并不构成一项一致的必选抽象。在出现首个具体消费者前全部构建，会产生宽泛推测性表面，并重复现有 session、workflow、subagent 与 task 机制。
|
||||
- **只实现同会话目标**——不予采纳，因为全新上下文迭代在实质上不同，也是插件架构的重要示范。Ralph 应作为带显式上下文重置的固定工作流消费者。
|
||||
- **把 Ralph 放进目标回合驱动器**——不予采纳，因为同会话目标有意保留一段对话，而 Ralph 有意移除对话。合并两者会让激活、重放、交接与 UI 状态含糊不清。
|
||||
- **把 fork 当成全新 Ralph 子 agent**——不予采纳，因为 fork 会携带对话前缀。全新子 agent 加工作区状态与一份显式报告更容易限制和重放，并且无需合成取消记录。
|
||||
- **把 Claude Code 评估器复制进首个目标实现**——不予采纳，因为只读取转录的模型评估器是一项有用策略，但不是普遍可信的完成证书。系统必须仍能支持确定性评估与隔离，因此评估器延期到其权限与 provider seam 完成设计之后。
|
||||
- **把 Claude Code 评估器复制进首个目标实现**——不予采纳，因为只读取转录的模型评估器是一项有用策略，但不是普遍可信的完成证书。系统必须仍能支持确定性评估与隔离，因此评估器延期到其权限与提供方约定完成设计之后。
|
||||
- **会话恢复后自动续行**——不予采纳，因为打开会话是观察行为，不是花费资源的权限。系统恢复持久状态，而激活态等待新的人类提示词。
|
||||
- **通过模型路由 `/goal`**——不予采纳，因为状态与显式生命周期控制应是确定性且零 token 的 UI 操作；普通自然语言提示词仍是语义模型路径。
|
||||
- **为具体 agent loop 增加目标或 Ralph 模式**——不予采纳，因为公开队列、提示词、会话、取消、工作流与 subagent seam 已经支持两项策略。通用 cancel-requested 观察是唯一核心协调新增项。
|
||||
|
||||
## 后果
|
||||
|
||||
- 目标式执行在没有单个过载「loop」对象的情况下交付：同会话续行与全新 agent 迭代拥有显式、可独立测试的契约。
|
||||
- 目标式执行在没有单个过载「loop」对象的情况下交付：同会话续行与全新 agent 迭代拥有显式、可独立测试的约定。
|
||||
- 持久目标历史可以重放和 fork，而进程本地激活态会防止恢复时意外开始工作。
|
||||
- 人类获得小型 Codex 形态 UX；模型获得紧凑、带来源检查的工具表面；部署可以独立移除任一能力。
|
||||
- 人类获得小型 Codex 形态 UX；模型获得一组紧凑工具，其中的修改操作要求当前实时根 agent Turn 中有一条人类直接发送的消息；部署可以独立移除任一能力。
|
||||
- Ralph 展示了非平凡固定策略可以完全作为现有 workflow 与 subagent 原语之上的插件实现。
|
||||
- Round 上限默认宽裕，但仍由部署控制。它限制迭代次数，不限制 token、价格、耗时或外部副作用。
|
||||
- 原始提案中的评估器、预算、反思器、后台任务、CLI 与通用 loop-session 架构有意不进入已实现公开表面。
|
||||
|
||||
## 已知限制与暂缓事项
|
||||
|
||||
- **独立评估**——同会话完成/阻塞和 Ralph 终止状态都是模型或工作者声明。独立评估器、评估器驱动反馈 Round、完成证书、确定性检查器、对抗式 verifier 与 criteria/executor/isolation 契约均予以延期。
|
||||
- **独立评估**——同会话完成/阻塞和 Ralph 终止状态都是模型或工作者声明。独立评估器、评估器驱动反馈 Round、完成证书、确定性检查器、对抗式 verifier 与 criteria/executor/isolation 约定均予以延期。
|
||||
- **聚合预算**——`maxGoalRounds` 与 Ralph `maxRounds` 是唯一聚合工作量限制。token、货币、耗时、provider 用量与逐 Round 价格准入策略均不存在。
|
||||
- **没有持久自治运行器**——同会话目标事实会持久化，但激活与调度只存在于进程内，并且有意在恢复后等待人类输入。Ralph 位于前台，进程丢失后无法恢复。后台收集、重启恢复与无人值守常驻执行均予以延期。
|
||||
- **没有时间调度器**——间隔 `/loop`、cron、主动维护以及云端或桌面调度不在本决策范围内。
|
||||
- **没有通用 loop 日志或执行世界回退**——会话重放会重建目标历史，而不会恢复此前文件、进程、环境、凭据或外部副作用。Ralph 把当前工作区作为权威，并且没有跨运行日志。
|
||||
- **没有目标反思器**——concern 事件、自动无进展启发式、由独立反思器执行的目标修订、卡住模式检测与 `loop_split` 均未实现。人类可以直接编辑、暂停、清除或恢复目标。
|
||||
- **Ralph 策略仍然狭窄**——一个 Round 创建一个全新子 agent；Round 内扇出、评估器/工作者角色分离、动态 provider/模型选择与从结构上禁止递归调用 Ralph 工具都需要独立策略表面。提示词指导不是强制执行。
|
||||
- **Ralph 不会重试失败的子 agent**——普通失败会保留失败 Round 与上一份有效交接，而致命工作流基础设施错误可能在该状态可用前结束。重试次数、退避与更丰富的失败传输需要独立的策略与 seam 设计。
|
||||
- **Ralph 不会重试失败的子 agent**——普通失败会保留失败 Round 与上一份有效交接，而致命工作流基础设施错误可能在该状态可用前结束。重试次数、退避与更丰富的失败传输需要独立的策略与边界设计。
|
||||
- **可移植 UI 仍较朴素**——TUI 渲染纯文本目标状态和通用 Ralph 卡片。ACP 只承载已提交的助手文本；系统没有持续状态组件、可重连命令输出、模态目标编辑器，ACP、无头 CLI 与 JSON-RPC 也没有命令平面。
|
||||
|
||||
@@ -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/2026-07-16-persistent-pty-sessions.md
|
||||
2026-07-16-persistent-pty-sessions.md: d7d06dc8517780a37889e4f94dd0b99475dc5432
|
||||
2026-07-16-persistent-pty-sessions.zh.md: 84ef8988ba657a87137f904df38e45808d32b483
|
||||
2026-07-16-persistent-pty-sessions.md: fb9cd06bade7bc357baa738f0d9dd03b7f5b7936
|
||||
2026-07-16-persistent-pty-sessions.zh.md: 55a5848c1ab1e8c2cd3b29f2d4748ea4abbe088c
|
||||
|
||||
@@ -23,10 +23,10 @@ The implementation supports interactive shells and line-oriented REPLs on Linux
|
||||
| Package | Role | ctx key |
|
||||
|---|---|---|
|
||||
| `dsh-pty` | `PtyService`, branded `PtySessionId`, backend registry, owner-scoped session contract, and result types | `ctx.pty` |
|
||||
| `dsh-pty-local` | [`node-pty`](https://github.com/microsoft/node-pty)-based local backend, platform process inspection, bounded terminal buffer, sandbox resolution, and process-tree supervision | registers a backend on `ctx.pty` |
|
||||
| `dsh-pty-local` | Persistent-shell backend over `ctx.subprocess.spawnTerminal()`: readiness, bounded terminal buffers, sandbox resolution, and owner-aware session lifecycle | registers a backend on `ctx.pty` |
|
||||
| `dsh-tool-pty` | Six model-facing tools, task-runtime integration for background sends, guidance, and UI render intents | registers on `ctx.tools` |
|
||||
|
||||
Idle detection is backend behavior, not a second public seam. A remote or container backend may have authoritative readiness signals that do not resemble local `/proc` inspection; every `PtyBackend` therefore returns the common send result while owning its detection mechanism internally.
|
||||
Readiness remains PTY-backend behavior, not a second public contract. The terminal-process provider supplies only substrate facts such as the foreground process group and whether it can prove that group is waiting on input; `dsh-pty-local` combines those facts with prompt and silence evidence into the common send result.
|
||||
|
||||
### Agent ownership and identity
|
||||
|
||||
@@ -40,12 +40,12 @@ Agent-scope disposal closes registrations first, then awaits quiescent teardown
|
||||
|
||||
A registered `shell` backend constrains how a terminal starts; it does not constrain commands typed after startup. `dsh-pty-local` therefore applies two protections before spawning:
|
||||
|
||||
- It builds a scrubbed child environment using the same credential-shaped-name policy as `bash-local`, removing ambient `*KEY*`, `*PASSWORD*`, `*SECRET*`, `*TOKEN*`, and harness-managed variables unless an explicit trusted mapping supplies them.
|
||||
- It requires `ctx.sandbox` and the shared `ctx.sandboxPolicy`. At spawn, the backend resolves the owner's effective session mode over the deployment default and wraps the shell argv once; that mode and workspace root remain the process boundary for the PTY lifetime. A write that would change the effective `sandbox/mode` is rejected before commit while the owner has any open PTY or unpublished spawn, with an instruction to wait for creation to settle and close those sessions first; same-effective-mode writes remain valid. The pending reservation spans backend setup through publication, so there is no race in which a wider terminal appears after a downgrade. `danger-full-access` is the existing explicit unconfined choice rather than a PTY-specific bypass.
|
||||
- It supplies only terminal-specific environment overrides; the mounted subprocess provider applies the shared credential-shaped-name scrub before merging them.
|
||||
- It requires the shared `ctx.sandboxPolicy`. At spawn, the backend resolves the owner's effective session mode over the deployment default; `danger-full-access` starts the shell directly, while confined modes require a same-world `ctx.sandbox` provider and wrap the shell argv once. That mode and workspace root remain the process boundary for the PTY lifetime. A write that would change the effective `sandbox/mode` is rejected before commit while the owner has any open PTY or unpublished spawn, with an instruction to wait for creation to settle and close those sessions first; same-effective-mode writes remain valid. The pending reservation spans backend setup through publication, so there is no race in which a wider terminal appears after a downgrade. `danger-full-access` is the existing explicit unconfined choice rather than a PTY-specific bypass.
|
||||
|
||||
Sandboxing confines local process effects but does not make arbitrary shell input safe: network calls and other external side effects remain governed by deployment policy. Tool descriptions state that PTY sessions are less auditable than one-shot tools and should be used only when persistence or interactive stdin is necessary.
|
||||
|
||||
The implementation uses only public `node-pty` capabilities: child PID, `data` and `exit` notifications, `write`, `resize`, and `kill`. It does not assume access to the native master fd or call `waitpid` from TypeScript. Platform process inspectors derive foreground process groups and parent/child identity from `/proc` on Linux and `ps` on macOS.
|
||||
The local subprocess terminal primitive uses only public `node-pty` capabilities: child PID, `data` and `exit` notifications, `write`, and `kill`. It does not assume access to the native master fd or call `waitpid` from TypeScript. Platform process inspectors below that primitive derive foreground process groups and parent/child identity from `/proc` on Linux and `ps` on macOS. The [portable execution-world decision](../architecture/2026-07-28-portable-execution-world-consumers.md) owns this process/consumer split.
|
||||
|
||||
### Six model-facing tools
|
||||
|
||||
@@ -60,11 +60,11 @@ The implementation uses only public `node-pty` capabilities: child PID, `data` a
|
||||
|
||||
The UI render contract is exact and location-free. `terminal_send` uses terminal call/result cards only for foreground sends; its background form is generic `execute`. `terminal_open`, `terminal_read`, `terminal_signal`, `terminal_close`, and `terminal_list` use generic `execute`, `read`, `execute`, `delete`, and `read` cards respectively. No PTY tool emits `locations`.
|
||||
|
||||
`terminal_send({ sessionId, text, submit?, run_in_background? })` treats `text` as UTF-8 bytes and resolves `submit` to `true` in the tool implementation. When `submit` is true it writes the platform Enter sequence after the text; when false it writes only the text, allowing control characters and REPL fragments without hidden content heuristics. `enableRunInBackground` defaults to true; false removes `run_in_background` from the schema and rejects the same undeclared argument if a caller forces it through execution.
|
||||
`terminal_send({ sessionId, text, submit?, run_in_background? })` treats `text` as UTF-8 bytes and resolves `submit` to `true` in the tool implementation. When `submit` is true it writes the platform Enter sequence after the text; when false it writes only the text, allowing control characters and REPL fragments without hidden content heuristics. Cancellation marks queued input before signaling the real foreground group, so input cannot execute if an asynchronous pre-write inspection settles afterward. The canceled send retains its reservation until asynchronous foreground signalling settles, so a successor cannot become that signal's target. `enableRunInBackground` defaults to true; false removes `run_in_background` from the schema and rejects the same undeclared argument if a caller forces it through execution.
|
||||
|
||||
Foreground sends return a bounded rendered delta and two independent facts: `waitReason` (`stdin_read | inferred_idle | timeout | session_exit`) and `sessionStatus` (`running` or `exited` with exit code or signal). `session_exit` refers to the PTY's top-level shell process, not an arbitrary foreground command whose status the shell consumes. A timeout never implies process exit. `dsh-tool-pty.maxResultBytes` defaults to 262144, rejects values below 64 so creation acknowledgements retain registry-issued ids, and caps each single-text UTF-8 result after normalized tool or pipeline errors, wait, session, pagination, truncation, generic task-status wrappers, policy denials or short-circuits, and post-execute replacements or blocks; the terminal definitions' last-mile `finalizeContent` callback leaves deliberately structured multi-block policy content unchanged. The renderer reserves suffix space and preserves code-point boundaries instead of treating the backend payload cap as the final model bound.
|
||||
|
||||
With `run_in_background: true`, `dsh-tool-pty` registers the in-flight send on `ctx.tasks` and returns immediately with `taskId`. The producer places `maxResultBytes` on the task snapshot so `task_output`, terminal kill status, and completion notices enforce the same complete-result cap after generic metadata. `task_output(wait: true)` waits, reads incremental output, and records the final result; `task_kill` resolves the current foreground PGID and delivers a real `SIGINT`, including when the application has disabled terminal `ISIG`, and escalates only through the PTY backend's owned teardown path. If the task surface is absent, background mode fails before writing input. No PTY-specific `sleep` tool or general wake-up seam is added.
|
||||
With `run_in_background: true`, `dsh-tool-pty` registers the in-flight send on `ctx.tasks` and returns immediately with `taskId`. The producer places `maxResultBytes` on the task snapshot so `task_output`, terminal kill status, and completion notices enforce the same complete-result cap after generic metadata. `task_output(wait: true)` waits, reads incremental output, and records the final result; `task_kill` resolves the current foreground PGID and delivers a real `SIGINT`, including when the application has disabled terminal `ISIG`, and escalates only through the PTY backend's owned teardown path. If the task surface is absent, background mode fails before writing input. No PTY-specific `sleep` tool or general wake-up API is added.
|
||||
|
||||
`terminal_read` pages backward from the newest retained line. The backend enforces both line and UTF-8 byte caps on retained scrollback and the returned page payload, so one oversized line cannot bypass the backend bound; the tool then caps the fully rendered page including pagination and truncation metadata. `truncated` distinguishes retention loss from an ordinary viewport delta.
|
||||
|
||||
@@ -72,7 +72,7 @@ With `run_in_background: true`, `dsh-tool-pty` registers the in-flight send on `
|
||||
|
||||
### Local readiness detection
|
||||
|
||||
The local backend first recognizes a private OSC prompt marker emitted by its controlled bash startup, then requires printable prompt text after that marker before declaring prompt readiness and runs three bounded fallback tiers. Carrying that state across data callbacks covers macOS delivery where the OSC marker and `PS1` arrive separately; the marker alone can no longer publish an empty MOTD. The marker is removed before output reaches the model and avoids a fixed silence delay for ordinary shell commands on both platforms. Unpublished startup does not accept zero-output silence as readiness; timeout rejects the spawn. If caller cancellation wins during startup, the backend closes the private session and propagates the exact `AbortSignal.reason`; a foreground PGID that is not observable yet cannot replace cancellation with a lookup error. All timings are validated config fields: `pollIntervalMs`, `exactProbeAfterMs`, `idleSilenceMs`, `handoffGraceMs`, and `timeoutMs`.
|
||||
The local backend first recognizes a private OSC prompt marker emitted by its controlled bash startup, then requires the printable tail after the latest marker to exactly equal the controlled `PS1` before declaring prompt readiness and runs three bounded fallback tiers. Carrying that tail across data callbacks covers delivery where the marker and prompt arrive separately; requiring the exact tail rejects a delayed earlier prompt once echoed input or output follows it, so it cannot settle the current send. The marker is removed before output reaches the model and avoids a fixed silence delay for ordinary shell commands on both platforms. Unpublished startup does not accept zero-output silence as readiness; timeout rejects the spawn. If caller cancellation wins during startup, the backend closes the private session and propagates the exact `AbortSignal.reason`; a foreground PGID that is not observable yet cannot replace cancellation with a lookup error. All timings are validated config fields: `pollIntervalMs`, `exactProbeAfterMs`, `idleSilenceMs`, `handoffGraceMs`, and `timeoutMs`.
|
||||
|
||||
On Linux, the inspector reads the shell's terminal foreground PGID from `/proc/<shellPid>/stat`, enumerates every process and thread in that process group, and probes their current syscalls. A positive Tier 1 result requires an observed stdin wait: direct `read(0)`, a permitted read of a `select`/`pselect6` or `poll`/`ppoll` argument containing fd 0, or an epoll interest list containing fd 0. A wait already present before terminal input is not post-write readiness: the same PGID must be observed outside that wait before re-entering it, while a changed foreground PGID is new evidence. Unreadable process memory and unrecognized syscalls are misses, never positive guesses. Architecture tables contain only syscall numbers defined by the corresponding Linux UAPI; unsupported architectures skip Tier 1.
|
||||
|
||||
@@ -92,9 +92,9 @@ Background sends use the existing task completion notice and `task_output` resul
|
||||
|
||||
### Process-tree teardown
|
||||
|
||||
The top-level `node-pty` child is the ownership anchor. On close, the backend stops callbacks, snapshots its transitive descendants by parent PID in children-first order, sends `SIGTERM`, waits, rescans for children forked during shutdown, sends `SIGKILL` to the remaining descendant tree, and verifies that every non-zombie descendant left the process table while the shell is still alive. A matching Linux zombie has no executable work and therefore counts as quiescent, allowing shell shutdown to reap or reparent it. Only then does the backend stop the shell with its own TERM/grace/KILL sequence. Every captured PID includes process-start identity so reuse cannot redirect escalation.
|
||||
The subprocess terminal handle owns the top-level terminal process and its session. On close it snapshots transitive descendants by parent PID in children-first order, sends `SIGTERM`, waits, rescans for children forked during shutdown, sends `SIGKILL` to the union, and verifies every non-zombie descendant left the process table before stopping the top-level process. A matching Linux zombie has no executable work and therefore counts as quiescent. Every captured PID includes process-start identity so reuse cannot redirect escalation.
|
||||
|
||||
Teardown reports root exit and survivor cleanup independently. It does not claim success merely because the shell exited; disposal resolves only after no captured non-quiescent tree member remains or returns a cleanup failure naming the survivors. A failed close is not cached forever: the registry and local session each clear the fence only when it still names that failed attempt, so a later explicit or lifecycle close retries after the external survivor condition changes without disturbing a newer concurrent attempt. Service disposal still clears its backend, reservation, and owner-detacher registries when a close fails. It never broadens ownership to every member of the root PID's POSIX session.
|
||||
Teardown reports top-level exit and survivor cleanup independently. The PTY session does not claim success merely because the shell exited: it calls `SubprocessTerminalHandle.terminate()` and awaits whole-session quiescence, propagating a cleanup failure that names survivors. A failed close is not cached forever: the registry and local session clear the fence only when it still names that failed attempt, so a later explicit or lifecycle close retries without disturbing a newer concurrent attempt. Service disposal still clears its backend, reservation, and owner-detacher registries when a close fails.
|
||||
|
||||
### Composition and rollout
|
||||
|
||||
@@ -108,6 +108,7 @@ plugins:
|
||||
mode: workspace-write
|
||||
workspaceRoot: .
|
||||
'@deepseek-ai/dsh-pty':
|
||||
'@deepseek-ai/dsh-subprocess-local':
|
||||
'@deepseek-ai/dsh-pty-local':
|
||||
config:
|
||||
scrollbackLines: 10000
|
||||
@@ -141,26 +142,25 @@ The package ships concise tool guidance explaining persistent state, owner isola
|
||||
|
||||
**Add persistent mode to `bash`.** Rejected. Returning on readiness rather than process exit, retaining a process tree across calls, and exposing interactive stdin create a different ownership and failure contract.
|
||||
|
||||
**Require native master-fd access from `node-pty`.** Rejected. Its public API exposes no master fd. The local backend instead derives foreground groups and descendants from supported OS process metadata and treats unreadable metadata as a detector miss.
|
||||
**Require native master-fd access from `node-pty`.** Rejected. Its public API exposes no master fd. The local subprocess terminal adapter derives foreground groups and descendants from supported OS process metadata and treats unreadable metadata as a detector miss.
|
||||
|
||||
**Signal every member of the root PID's POSIX session.** Rejected. `node-pty` may expose a helper PID whose session belongs to the launcher, so SID-wide teardown can signal unrelated harness or desktop processes. A PID-identity-fenced descendant tree is narrower and safe by construction.
|
||||
|
||||
**Publish `PtyIdleDetector` as a replaceable registry.** Rejected. Only the local backend needs these platform probes, while remote backends may receive readiness over their own protocol. Backend replacement already provides the necessary extension point.
|
||||
**Publish `PtyIdleDetector` as a replaceable registry.** Rejected. Substrate-specific foreground facts come from the mounted terminal-process primitive, while prompt/silence readiness remains one private policy in `dsh-pty-local`. The filesystem/subprocess execution-world replacement is the necessary extension point.
|
||||
|
||||
**Add a PTY-specific `sleep` tool.** Rejected. `ctx.tasks` already owns bounded waiting, cancellation, completion notices, and model-facing collection. A second general wake mechanism would cross the agent-loop boundary and duplicate that contract.
|
||||
|
||||
**Include TUI sequences and BEL handling.** Rejected. The source prototype treats those paths as timing-sensitive and still records unresolved alternate-screen and interaction failures. Line-oriented PTY use proves the core value without making those unverified behaviors foundational.
|
||||
|
||||
**Use an out-of-process daemon immediately.** Rejected for the initial in-process capability because current persistent front doors already keep a Cordis context alive. A daemon becomes justified by cross-process restoration or multi-client attachment, both deferred here.
|
||||
**Use an out-of-process daemon immediately.** Rejected for the initial in-process capability because current long-lived entry points already keep a Cordis context alive. A daemon becomes justified by cross-process restoration or multi-client attachment, both deferred here.
|
||||
|
||||
## Verification
|
||||
|
||||
- Per-file coverage pins owner fencing, concurrent reservations, unpublished-spawn cancellation and awaited teardown, sandbox-mode change rejection, retriable lifecycle cleanup, readiness tiers, rejection of pre-write stdin waits, the configured handoff grace holding the idle fallback past one poll and its rejection below `pollIntervalMs`, sanitizer carry state, complete UTF-8 bounds, task integration, schemas, and exact render intents.
|
||||
- Linux process fixtures cover non-leader and non-main-thread stdin waits, zombie quiescence, unreadable process state, supported syscall tables, unsupported architectures, and false-positive rejection; macOS inspector logic is injected into the same unit suite.
|
||||
- Real `node-pty` tests exercise shell state, shared sandbox policy, environment scrubbing, raw-mode foreground `SIGINT` after deliberately delayed child readiness under scenario-owned timing bounds, a TERM-ignoring descendant, and immediate post-disposal quiescence on supported hosts.
|
||||
- Per-file coverage pins owner fencing, concurrent reservations, cancellation during pre-write inspection, unpublished-spawn cancellation and awaited teardown, sandbox-mode change rejection, retriable lifecycle cleanup, readiness tiers, rejection of pre-write stdin waits and delayed earlier prompts, the configured handoff grace holding the idle fallback past one poll and its rejection below `pollIntervalMs`, sanitizer carry state, complete UTF-8 bounds, task integration, schemas, and exact render intents.
|
||||
- Subprocess process fixtures cover non-leader and non-main-thread stdin waits, zombie quiescence, unreadable process state, supported syscall tables, unsupported architectures, and false-positive rejection; macOS inspector logic is injected into the same unit suite.
|
||||
- Real `node-pty` and PTY-consumer tests jointly exercise shell state, shared sandbox policy, environment scrubbing, raw-mode foreground `SIGINT`, a TERM-ignoring descendant, and immediate post-disposal quiescence on supported hosts.
|
||||
- A Loader-driven `cordis.yml` test mounts the real three-package composition. ACP and headless snapshots pin the six schemas, bounded results, and errors through opt-in overlays; TUI snapshots pin terminal and generic card presentation.
|
||||
- Package contracts, the architecture map, core data structures, generated catalogs, and the website API describe the same shipped surface.
|
||||
- The repository CI-equivalent sequence owns type, lint, coverage, snapshot, documentation, build, hygiene, demo, and built-entry verification.
|
||||
- Package contracts, the architecture map, subsystem pages, generated catalogs, and the website API describe the same shipped surface.
|
||||
|
||||
## Consequences
|
||||
|
||||
@@ -172,10 +172,10 @@ The package ships concise tool guidance explaining persistent state, owner isola
|
||||
|
||||
**Persistent state can drift from the model's belief.** The model may forget its cwd or active REPL. Session summaries and retained output help recovery, but no prompt can make state persistence deterministic.
|
||||
|
||||
**A daemonized descendant can leave the captured tree.** A process that reparents before teardown is no longer discoverable from the `node-pty` root. The implementation accepts that cleanup gap instead of risking SID-wide signals to unrelated processes.
|
||||
**A daemonized descendant can leave the local provider's captured tree.** A process that reparents before teardown is no longer discoverable from the `node-pty` root. The local terminal primitive accepts that cleanup gap instead of risking SID-wide signals to unrelated processes.
|
||||
|
||||
**A shell can cause external side effects.** Session sandboxing and environment scrubbing reduce local exposure but do not undo pushes, API calls, or messages. Deployments that cannot tolerate those effects must omit PTY or add network policy.
|
||||
|
||||
**Process loss destroys terminal state.** In-process sessions do not survive a harness crash or restart, and raw scrollback is not durable. Important work must be committed to files or another durable system.
|
||||
|
||||
**`node-pty` is a native dependency.** Installation, supported Node versions, prebuild availability, and platform behavior require built-artifact smokes on every supported OS.
|
||||
**`node-pty` is a native dependency of `dsh-subprocess-local`.** Installation, supported Node versions, prebuild availability, and platform behavior require built-artifact smokes on every supported OS.
|
||||
|
||||
@@ -14,7 +14,7 @@ harness 可以运行前台与后台命令、编辑文件和委派工作，但无
|
||||
|
||||
## 决策
|
||||
|
||||
可选的 `packages/pty/` 能力家族提供由 agent 拥有、持久化且面向行式交互的 PTY 会话。它遵循仓库的 [capability pattern](../../implemented/architecture/2026-06-13-capability-seams.md)，与现有命令和文件系统工具并存，并且不修改 `agent-loop`。
|
||||
可选的 `packages/pty/` 功能家族提供由 agent 拥有、持久化且面向行式交互的 PTY 会话。它遵循仓库的 [capability pattern](../../implemented/architecture/2026-06-13-capability-seams.md)，与现有命令和文件系统工具并存，并且不修改 `agent-loop`。
|
||||
|
||||
当前实现在 Linux 和 macOS 上支持交互式 shell 与行式 REPL。全屏终端应用、按键序列、BEL 触发的控制流、进程丢失后的会话恢复以及跨 agent 共享会话都明确推迟。
|
||||
|
||||
@@ -22,11 +22,11 @@ harness 可以运行前台与后台命令、编辑文件和委派工作，但无
|
||||
|
||||
| 包 | 角色 | ctx key |
|
||||
|---|---|---|
|
||||
| `dsh-pty` | `PtyService`、branded `PtySessionId`、后端注册表、按 owner 隔离的会话契约和结果类型 | `ctx.pty` |
|
||||
| `dsh-pty-local` | 基于 [`node-pty`](https://github.com/microsoft/node-pty) 的本地后端、平台进程检查、有界终端缓冲、沙箱解析和进程树监管 | 在 `ctx.pty` 上注册后端 |
|
||||
| `dsh-pty` | `PtyService`、branded `PtySessionId`、后端注册表、按 owner 隔离的会话约定和结果类型 | `ctx.pty` |
|
||||
| `dsh-pty-local` | 基于 `ctx.subprocess.spawnTerminal()` 的持久 shell 后端：就绪状态、有界终端缓冲、沙箱解析和感知 owner 的会话生命周期 | 在 `ctx.pty` 上注册后端 |
|
||||
| `dsh-tool-pty` | 6 个面向模型的工具、后台发送的 task 运行时集成、使用指引和 UI 渲染意图 | 注册到 `ctx.tools` |
|
||||
|
||||
idle 检测属于后端行为，不是第二条公共 seam。远程或容器后端可能拥有完全不同于本地 `/proc` 检查的权威就绪信号；因此每个 `PtyBackend` 都返回统一的发送结果，同时在内部拥有自己的检测机制。
|
||||
就绪判定仍属于 PTY 后端行为，不是第二条公共约定。终端进程提供方只提供基底事实，例如前台进程组，以及能否证明该组正在等待输入；`dsh-pty-local` 将这些事实与提示符和静默证据组合成统一的发送结果。
|
||||
|
||||
### agent 所有权与身份
|
||||
|
||||
@@ -34,18 +34,18 @@ idle 检测属于后端行为，不是第二条公共 seam。远程或容器后
|
||||
|
||||
实现不提供插件加载期 auto-start 会话。`terminal_open` 只在 agent 工具调用期间创建会话，此时所有权和所属的事件溯源会话都已确定。未来的声明式启动功能必须通过尚未发布的 agent setup 组合，而不能创建全局共享终端。
|
||||
|
||||
agent scope dispose（资源释放）时先关闭注册，再等待全部所属 PTY 完全停稳。未发布的后端 setup 同样是受追踪的生命周期操作：owner 或服务 dispose 会中止服务自有的 signal，等待后端结算与回滚完成后才返回。即使后端 reject，或返回的会话在回滚 close 时失败，调用方取消仍会原样保留其 `AbortSignal.reason`；该清理失败不会替换调用方原因，而会继续受追踪，留待后续 owner 或服务 dispose 处理。由 lifecycle dispose 触发的回滚 close 失败会使 spawn 与该 lifecycle dispose 都 reject，而 `PtyBackendCleanupError` 让后端在不替换调用方取消的前提下，为该 lifecycle dispose 保留自身的启动清理失败。若调用方取消已完成结算，而 dispose 尚未发生，该清理失败会继续作为受追踪的 owner activity 保留，直到后续 owner 或服务 dispose 消费并报告它，因此沙箱模式策略不会把清理失败误判为完全停稳。后端或工具插件 reload 不会遗留会话：所有权持续存放在 `PtyService` 中，直到 agent 结束，与 [`ctx.tasks`](../../../../packages/tasks/tasks/README.md) 的服务持有记录模式一致。服务会先同步把会话预留给一次活跃发送，再返回该操作；后台发送同样会在 task id 对外可见前完成预留。第二次发送会以 `SEND_ACTIVE` 失败，因此输出与取消无法跨越操作所有权。
|
||||
agent scope dispose 时先关闭注册，再等待全部所属 PTY 静默退出。未发布的后端 setup 同样是受追踪的生命周期操作：owner 或服务 dispose 会中止服务自有的 signal，等待后端结算与回滚完成后才返回。即使后端 reject，或返回的会话在回滚 close 时失败，调用方取消仍会原样保留其 `AbortSignal.reason`；该清理失败不会替换调用方原因，而会继续受追踪，留待后续 owner 或服务 dispose 处理。由 lifecycle dispose 触发的回滚 close 失败会使 spawn 与该 lifecycle dispose 都 reject，而 `PtyBackendCleanupError` 让后端在不替换调用方取消的前提下，为该 lifecycle dispose 保留自身的启动清理失败。若调用方取消先于 dispose 完成结算，该清理失败会继续作为受追踪的 owner activity 保留，直到后续 owner 或服务 dispose 消费并报告它，因此沙箱模式策略不会把清理失败误判为静默。后端或工具插件 reload 不会遗留会话：所有权持续存放在 `PtyService` 中，直到 agent 结束，与 [`ctx.tasks`](../../../../packages/tasks/tasks/README.md) 的服务持有记录模式一致。服务会先同步把会话预留给一次活跃发送，再返回该操作；后台发送同样会在 task id 对外可见前完成预留。第二次发送会以 `SEND_ACTIVE` 失败，因此输出与取消无法跨越操作所有权。
|
||||
|
||||
### 安全与进程边界
|
||||
|
||||
注册的 `shell` 后端只约束终端如何启动，不约束启动后输入的命令。因此 `dsh-pty-local` 在 spawn 前应用两层保护：
|
||||
|
||||
- 它使用与 `bash-local` 相同的凭证形态名称策略构建清洗后的子进程环境，移除环境中的 `*KEY*`、`*PASSWORD*`、`*SECRET*`、`*TOKEN*` 和 harness 管理的变量，除非显式的可信映射提供这些值。
|
||||
- 它要求 `ctx.sandbox` 和共享的 `ctx.sandboxPolicy`。后端在 spawn 时，以部署默认值为底折叠 owner 的有效 session mode，并只包装一次 shell argv；该 mode 与 workspace root 在 PTY 的整个生命周期中充当进程边界。只要 owner 有任何已打开的 PTY 或尚未发布的 spawn，任何会改变生效 `sandbox/mode` 的写入都会在提交前被拒绝，并提示先等待创建操作结算，再关闭这些会话；不会改变生效模式的写入仍然有效。这项进行中的预留从后端 setup 持续到发布完成，因此不存在降级后又出现权限更宽的终端这一竞态。`danger-full-access` 是现有的显式无约束选择，不另设 PTY 私有 bypass。
|
||||
- 它只提供终端专用的环境覆盖；挂载的子进程提供方先清除名称形似凭据的环境变量，再合并这些覆盖。
|
||||
- 它要求共享的 `ctx.sandboxPolicy`。后端在 spawn 时，以部署默认值为底折叠 owner 的有效 session mode；`danger-full-access` 会直接启动 shell，受限模式则要求同一执行世界中存在 `ctx.sandbox` 提供方，并只包装一次 shell argv。该 mode 与 workspace root 在 PTY 的整个生命周期中充当进程边界。只要 owner 有任何已打开的 PTY 或尚未发布的 spawn，任何会改变生效 `sandbox/mode` 的写入都会在提交前被拒绝，并提示先等待创建操作结算，再关闭这些会话；不会改变生效模式的写入仍然有效。这项进行中的预留从后端 setup 持续到发布完成，因此不存在降级后又出现权限更宽的终端这一竞态。`danger-full-access` 是现有的显式无约束选择，不另设 PTY 私有 bypass。
|
||||
|
||||
沙箱限制本地进程副作用，但不会让任意 shell 输入自动安全：网络调用和其他外部副作用仍由部署策略治理。工具描述会说明 PTY 会话比一次性工具更难审计，只应在确实需要持久状态或交互式 stdin 时使用。
|
||||
|
||||
实现只使用 `node-pty` 的公共功能：子进程 PID、`data` 与 `exit` 通知、`write`、`resize` 和 `kill`。它不假设能访问原生 master fd，也不从 TypeScript 调用 `waitpid`。平台进程检查器在 Linux 上通过 `/proc`、在 macOS 上通过 `ps` 推导前台进程组和父子进程身份。
|
||||
本地子进程终端原语只使用 `node-pty` 的公共功能：子进程 PID、`data` 与 `exit` 通知、`write` 和 `kill`。它不假设能访问原生 master fd，也不从 TypeScript 调用 `waitpid`。该原语下的平台进程检查器在 Linux 上通过 `/proc`、在 macOS 上通过 `ps` 推导前台进程组和父子进程身份。[可移植执行环境决策](../architecture/2026-07-28-portable-execution-world-consumers.md)负责定义这种进程／消费方拆分。
|
||||
|
||||
### 6 个面向模型的工具
|
||||
|
||||
@@ -55,28 +55,28 @@ agent scope dispose（资源释放）时先关闭注册，再等待全部所属
|
||||
| `terminal_send` | 发送文本、可选提交 Enter，并等待就绪或注册一个后台任务 | 有界 viewport、等待状态和会话状态；后台模式还返回 `taskId` |
|
||||
| `terminal_read` | 从保留的 scrollback 读取一个有界页 | `{ text, totalLines, lineBegin, lineEnd, truncated }` |
|
||||
| `terminal_signal` | 向当前前台进程组发送一种允许的信号 | `{ delivered, targetPgid }` |
|
||||
| `terminal_close` | 关闭一个会话并等待进程树完全停稳 | `{ killed }` |
|
||||
| `terminal_close` | 关闭一个会话并等待进程树静默退出 | `{ killed }` |
|
||||
| `terminal_list` | 列出调用方的活会话 | 按 owner 隔离的会话摘要 |
|
||||
|
||||
UI 渲染契约精确且不携带位置信息。`terminal_send` 只为前台发送使用 terminal 调用卡片和结果卡片；后台形式使用通用 `execute` 卡片。`terminal_open`、`terminal_read`、`terminal_signal`、`terminal_close` 和 `terminal_list` 分别使用通用 `execute`、`read`、`execute`、`delete` 和 `read` 卡片。所有 PTY 工具都不发出 `locations`。
|
||||
UI 渲染约定精确且不携带位置信息。`terminal_send` 只为前台发送使用 terminal 调用卡片和结果卡片；后台形式使用通用 `execute` 卡片。`terminal_open`、`terminal_read`、`terminal_signal`、`terminal_close` 和 `terminal_list` 分别使用通用 `execute`、`read`、`execute`、`delete` 和 `read` 卡片。所有 PTY 工具都不发出 `locations`。
|
||||
|
||||
`terminal_send({ sessionId, text, submit?, run_in_background? })` 将 `text` 视为 UTF-8 字节，并由工具实现在解析阶段把 `submit` 默认成 `true`。`submit` 为 true 时先写入文本，再写入平台 Enter 序列；为 false 时只写文本，使控制字符和 REPL 片段无需隐藏的内容启发式即可发送。`enableRunInBackground` 默认为 true；设为 false 时，schema 中会移除 `run_in_background`，调用方即使强行把这个未声明参数传入执行流程，也会被拒绝。
|
||||
`terminal_send({ sessionId, text, submit?, run_in_background? })` 将 `text` 视为 UTF-8 字节，并由工具实现在解析阶段把 `submit` 默认成 `true`。`submit` 为 true 时先写入文本，再写入平台 Enter 序列；为 false 时只写文本，使控制字符和 REPL 片段无需隐藏的内容启发式即可发送。取消会在向真实前台进程组发送信号前将排队输入标记为已取消，因此即使异步的写入前检查随后才结算，该输入也无法执行。被取消的发送会保留其预留，直至异步前台信号发送结算，因此后续发送不会成为该信号的目标。`enableRunInBackground` 默认为 true；设为 false 时，schema 中会移除 `run_in_background`，调用方即使强行把这个未声明参数传入执行流程，也会被拒绝。
|
||||
|
||||
前台发送返回有界的渲染增量和两个独立事实：`waitReason`（`stdin_read | inferred_idle | timeout | session_exit`）与 `sessionStatus`（`running`，或携带退出码或信号的 `exited`）。`session_exit` 指 PTY 顶层 shell 进程退出，不指由 shell 消费状态的任意前台命令。timeout 从不意味着进程已经退出。`dsh-tool-pty.maxResultBytes` 默认为 262144；低于 64 的值会被拒绝，以确保创建确认保留 registry 签发的 id；每个单文本 UTF-8 结果在加入规范化的工具或流水线错误、等待、会话、分页、截断、通用 task 状态包装、策略拒绝或短路以及 post-execute 替换或阻断后，仍受该值限制；终端定义自有的末端 `finalizeContent` callback 会原样保留策略刻意返回的结构化多 block 内容。渲染器会为后缀预留空间并保持代码点边界，而不会把后端载荷上限当作面向模型结果的最终上限。
|
||||
|
||||
当 `run_in_background: true` 时，`dsh-tool-pty` 在 `ctx.tasks` 上注册进行中的发送，并立即返回 `taskId`。生产方把 `maxResultBytes` 写入 task 快照，使 `task_output`、kill 返回的终态状态和完成通知在加上通用元数据后，仍对完整结果执行同一上限。`task_output(wait: true)` 负责等待、读取增量输出并记录最终结果；`task_kill` 会解析当前前台 PGID 并发送真正的 `SIGINT`，即使应用已禁用终端 `ISIG` 也同样如此，且后续升级仍只通过 PTY 后端拥有的 teardown 路径进行。若 task 对外接口不存在，后台模式必须在写入输入前失败。设计不新增 PTY 专用的 `sleep` 工具或通用唤醒 seam。
|
||||
当 `run_in_background: true` 时，`dsh-tool-pty` 在 `ctx.tasks` 上注册进行中的发送，并立即返回 `taskId`。生产方把 `maxResultBytes` 写入 task 快照，使 `task_output`、kill 返回的终态状态和完成通知在加上通用元数据后，仍对完整结果执行同一上限。`task_output(wait: true)` 负责等待、读取增量输出并记录最终结果；`task_kill` 会解析当前前台 PGID 并发送真正的 `SIGINT`，即使应用已禁用终端 `ISIG` 也同样如此，且后续升级仍只通过 PTY 后端拥有的 teardown 路径进行。若 task 对外接口不存在，后台模式必须在写入输入前失败。设计不新增 PTY 专用的 `sleep` 工具或通用唤醒 API。
|
||||
|
||||
`terminal_read` 从最新保留行起，朝更早的行分页。后端同时对保留的 scrollback 和返回页载荷执行行数与 UTF-8 字节上限，因此单个超长行无法绕过后端上限；工具随后再限制包含分页与截断元数据的完整渲染页。`truncated` 用于区分保留数据丢失与普通 viewport 增量。
|
||||
`terminal_read` 从最新保留行向后分页。后端同时对保留的 scrollback 和返回页载荷执行行数与 UTF-8 字节上限，因此单个超长行无法绕过后端上限；工具随后再限制包含分页与截断元数据的完整渲染页。`truncated` 用于区分保留数据丢失与普通 viewport 增量。
|
||||
|
||||
`terminal_signal` 接受闭合集 `SIGINT | SIGTERM | SIGKILL | SIGTSTP | SIGHUP`。后端在执行时解析终端前台进程组。当目标组是顶层 shell 时拒绝 `SIGKILL`，并指引调用方使用 `terminal_close`；进程组解析失败时操作直接失败，而不是向猜测的 PID 发送信号。
|
||||
|
||||
### 本地就绪检测
|
||||
|
||||
本地后端先识别受控 bash 启动时发出的私有 OSC prompt marker，并且只有在该 marker 后出现可打印的 prompt 文本时才据此声明 prompt 就绪；除此之外，它还运行 3 个有界 fallback 层级。在 data callback 之间保留这项状态，可以适配 macOS 分开交付 OSC marker 与 `PS1` 的情况；单独的 marker 不会发布空 MOTD。marker 在输出到达模型前被移除，使两个平台上的普通 shell 命令都无需固定等待静默阈值。尚未发布的 startup 不会把零输出静默视为就绪；timeout 会拒绝 spawn。若调用方取消在 startup 期间胜出，后端会关闭私有会话并原样抛出 `AbortSignal.reason`；尚不可观察的前台 PGID 不会再用查找错误覆盖取消原因。所有时间参数都是经校验的配置字段：`pollIntervalMs`、`exactProbeAfterMs`、`idleSilenceMs`、`handoffGraceMs` 和 `timeoutMs`。
|
||||
本地后端先识别受控 bash 启动时发出的私有 OSC prompt marker，并且只有在最近一个 marker 后的可打印尾部与受控 `PS1` 完全相等时才声明 prompt 就绪；除此之外，它还运行 3 个有界 fallback 层级。在 data callback 之间保留该尾部，可以适配 marker 与 prompt 被分开交付的情况；如果回显的输入或输出跟在延迟到达的先前 prompt 之后，要求尾部完全相等会拒绝该 prompt，使其无法完成当前 send。marker 在输出到达模型前被移除，使两个平台上的普通 shell 命令都无需固定等待静默阈值。尚未发布的 startup 不会把零输出静默视为就绪；timeout 会拒绝 spawn。若调用方取消在 startup 期间胜出，后端会关闭私有会话并原样抛出 `AbortSignal.reason`；尚不可观察的前台 PGID 不会再用查找错误覆盖取消原因。所有时间参数都是经校验的配置字段：`pollIntervalMs`、`exactProbeAfterMs`、`idleSilenceMs`、`handoffGraceMs` 和 `timeoutMs`。
|
||||
|
||||
在 Linux 上，检查器从 `/proc/<shellPid>/stat` 读取 shell 的终端前台 PGID，枚举该进程组中的每个进程与线程，并检查它们当前的 syscall。Tier 1 只有观察到 stdin 等待才返回正结果：直接 `read(0)`、获准读取且含 fd 0 的 `select`/`pselect6` 或 `poll`/`ppoll` 参数，或者含 fd 0 的 epoll interest list。终端输入前就已存在的等待并不代表写入后就绪：必须先观察到同一 PGID 脱离该等待，之后再次进入等待才能使该次 send 完成；前台 PGID 发生变化则构成新的证据。无法读取的进程内存和未识别的 syscall 都是 miss，绝不作为正向猜测。架构表只包含对应 Linux UAPI 定义的 syscall number；不支持的架构跳过 Tier 1。
|
||||
|
||||
macOS 没有精确 syscall 层。任何前台进程组输出静默都会返回 `inferred_idle`，包括 Python 和 `gdb`；从 `ps` 推导的终端 PGID 只用于发送信号，不作为「只有 shell 才能 idle」的证明。纯进程检查逻辑可注入，并在 Linux 上进行单元测试，同时由 macOS CI job 驱动真实 PTY 和进程表路径。
|
||||
macOS 没有精确 syscall 层。任何前台进程组输出静默都会返回 `inferred_idle`，包括 Python 和 `gdb`；从 `ps` 推导的终端 PGID 只用于发送信号，不作为「只有 shell 才能 idle」的证明。纯进程检查逻辑可注入并在 Linux 上完成 unit 覆盖率，同时由 macOS CI job 驱动真实 PTY 和进程表路径。
|
||||
|
||||
Tier 2 在持续 `idleSilenceMs` 没有输出后返回 `inferred_idle`，因此 sleep 或网络阻塞的命令可能看似 ready。如果此前已经见过 prompt marker，Tier 2 会再等待 `handoffGraceMs`，使恰好落在静默边界上的 bash 前台交接仍然以精确的 `stdin_read` 归因结束，而不是退到较弱的推断；该宽限是由部署方拥有的配置字段，并被校验为至少覆盖一个 `pollIntervalMs`——短于轮询周期的宽限装不下一次就绪轮询，因此不可能改变任何结果。它只约束见过 marker 的 send，代价是这一种情况的交互返回延迟，而不是每一次 send。Tier 3 在 `timeoutMs` 后返回 `timeout`，避免前台工具调用无限占住 agent。结果保留这些区别；调用方可以通过 `ctx.tasks` 等待、向前台组发信号，或从另一个会话排查。
|
||||
|
||||
@@ -88,13 +88,13 @@ Tier 2 在持续 `idleSilenceMs` 没有输出后返回 `inferred_idle`，因此
|
||||
|
||||
现有持久化 `tool/call` 与 `tool/result` 事件是模型发送文本和返回给模型的渲染输出的真源。`terminal_open` 通过已记录的工具结果返回 MOTD；前台 `send`/`read`/`list`/`signal`/`close` 结果走同一路径记录。PTY 包不会把原始字节流重复写入自定义会话事件。
|
||||
|
||||
后台发送复用现有后台任务完成通知和 `task_output` 结果路径，因此进入后续模型请求的任何输出同样持久化。原始终端字节只作为有界的进程内状态存在，既不持久化也不可恢复。未来的 opt-in transcript（文本记录）sink 必须拥有独立的保留、凭证和隐私契约。
|
||||
后台发送复用现有后台任务完成通知和 `task_output` 结果路径，因此进入后续模型请求的任何输出同样持久化。原始终端字节只作为有界的进程内状态存在，既不持久化也不可恢复。未来的 opt-in transcript sink 必须拥有独立的保留、凭证和隐私约定。
|
||||
|
||||
### 进程树 teardown
|
||||
|
||||
顶层 `node-pty` 子进程是所有权锚点。关闭时，后端先停止 callback，再按父 PID 以子进程优先顺序捕获其传递子进程、发送 `SIGTERM` 并等待，然后重新扫描关停期间 fork 出的子进程，向剩余子孙进程树发送 `SIGKILL`，并在 shell 仍存活时验证每个非僵尸子孙进程都已离开进程表。身份匹配的 Linux 僵尸进程已无可执行工作，因此视为完全停稳；shell 关闭时会回收它或将其重新挂接给负责回收的父进程。完成这些步骤后，后端才用 shell 自身的 TERM、宽限等待、KILL 序列停止 shell。每个捕获的 PID 都包含进程启动身份，避免 PID 复用把升级信号发给无关进程。
|
||||
子进程终端句柄拥有顶层终端进程及其会话。关闭时，它按父 PID 以子进程优先顺序捕获传递后代、发送 `SIGTERM` 并等待，然后重新扫描关停期间 fork 出的子进程，向二者并集发送 `SIGKILL`，并在停止顶层进程前验证每个非僵尸后代都已离开进程表。身份匹配的 Linux 僵尸进程已无可执行工作，因此视为完全停稳。每个捕获的 PID 都包含进程启动身份，避免 PID 复用把升级信号发给无关进程。
|
||||
|
||||
teardown 独立报告根进程退出与存活进程清理。它不会只因 shell 退出就声称成功；dispose 只有在已捕获的进程树中不再存在尚未完全停稳的成员后才完成，否则返回清理失败并列出存活者。失败的 close 不会永久缓存：注册表与本地会话各自仅在关闭围栏仍指向该次失败尝试时才将其清除，因此外部存活进程状态改变后，后续的显式 close 或生命周期 close 会重试，且不会干扰较新的并发尝试。即使某个 close 失败，服务 dispose 仍会清空其后端、预留与 owner detacher 注册表。所有权绝不会扩大到根 PID 所属 POSIX 会话的全部成员。
|
||||
teardown 独立报告顶层进程退出与存活进程清理。PTY 会话不会只因 shell 退出就声称成功：它会调用 `SubprocessTerminalHandle.terminate()` 并等待整个会话完全停稳，若清理失败则向外传播并列出存活者。失败的 close 不会永久缓存：注册表与本地会话各自仅在关闭围栏仍指向该次失败尝试时才将其清除，因此后续的显式 close 或生命周期 close 会重试，且不会干扰较新的并发尝试。即使某个 close 失败，服务 dispose 仍会清空其后端、预留与 owner detacher 注册表。
|
||||
|
||||
### 组合与推行
|
||||
|
||||
@@ -108,6 +108,7 @@ plugins:
|
||||
mode: workspace-write
|
||||
workspaceRoot: .
|
||||
'@deepseek-ai/dsh-pty':
|
||||
'@deepseek-ai/dsh-subprocess-local':
|
||||
'@deepseek-ai/dsh-pty-local':
|
||||
config:
|
||||
scrollbackLines: 10000
|
||||
@@ -129,7 +130,7 @@ plugins:
|
||||
|
||||
### 推迟的工作
|
||||
|
||||
- 全屏 TUI 支持、命名按键序列、BEL 中断、终端 resize 工具和 alternate-screen 快照需要另行验证面向模型的契约。
|
||||
- 全屏 TUI 支持、命名按键序列、BEL 中断、终端 resize 工具和 alternate-screen 快照需要另行验证面向模型的约定。
|
||||
- 声明式 per-agent 启动需要 agent-setup 组合点；仍然禁止插件加载期全局会话。
|
||||
- harness 进程丢失后的会话恢复需要进程外 owner 和版本化协议。
|
||||
- 网络出口策略与外部副作用回滚超出 PTY 范围，继续作为独立安全工作。
|
||||
@@ -137,34 +138,33 @@ plugins:
|
||||
|
||||
## 备选方案
|
||||
|
||||
**用 PTY 替换 `bash`、文件系统工具或 task 工具。**拒绝。一次性工具拥有更强的校验、审批、沙箱、输出上限和回放契约。PTY 只服务交互式状态。
|
||||
**用 PTY 替换 `bash`、文件系统工具或 task 工具。**拒绝。一次性工具拥有更强的校验、审批、沙箱、输出上限和回放约定。PTY 只服务交互式状态。
|
||||
|
||||
**给 `bash` 增加持久模式。**拒绝。按就绪而不是进程退出返回、跨调用保留进程树、暴露交互式 stdin 会形成不同的所有权和失败契约。
|
||||
**给 `bash` 增加持久模式。**拒绝。按就绪而不是进程退出返回、跨调用保留进程树、暴露交互式 stdin 会形成不同的所有权和失败约定。
|
||||
|
||||
**要求从 `node-pty` 获取原生 master fd。**拒绝。它的公共 API 不暴露 master fd。本地后端改为从受支持的 OS 进程元数据推导前台组与子孙进程，并把不可读元数据视为 detector miss。
|
||||
**要求从 `node-pty` 获取原生 master fd。**拒绝。它的公共 API 不暴露 master fd。本地子进程终端适配器改为从受支持的 OS 进程元数据推导前台组与子孙进程，并把不可读元数据视为 detector miss。
|
||||
|
||||
**向根 PID 所属 POSIX 会话的全部成员发送信号。**拒绝。`node-pty` 可能暴露属于启动器会话的 helper PID，因此按 SID 清理可能向无关的 harness 或桌面进程发送信号。带 PID 启动身份校验的子孙进程树范围更窄，其安全边界由结构保证。
|
||||
|
||||
**发布可替换注册表 `PtyIdleDetector`。**拒绝。只有本地后端需要这些平台 probe，远程后端可能通过自己的协议接收就绪状态。替换后端已经提供所需扩展点。
|
||||
**发布可替换注册表 `PtyIdleDetector`。**拒绝。基底专用的前台事实来自挂载的终端进程原语，提示符／静默就绪判定则仍是 `dsh-pty-local` 内部的一项私有策略。替换文件系统／子进程执行环境就是所需扩展点。
|
||||
|
||||
**新增 PTY 专用 `sleep` 工具。**拒绝。`ctx.tasks` 已经拥有有界等待、取消、完成通知和面向模型的收集。第二套通用唤醒机制会跨越 agent loop（智能体循环）边界并重复该契约。
|
||||
**新增 PTY 专用 `sleep` 工具。**拒绝。`ctx.tasks` 已经拥有有界等待、取消、完成通知和面向模型的收集。第二套通用唤醒机制会跨越 agent loop（智能体循环）边界并重复该约定。
|
||||
|
||||
**包含 TUI sequence 与 BEL 处理。**拒绝。源 prototype 将这些路径视为 timing-sensitive，且仍记录未解决的 alternate-screen 和交互失败。行式 PTY 已能证明核心价值，无需把未经验证的行为放进基础层。
|
||||
|
||||
**立即采用进程外 daemon。**初始的进程内功能不采用，因为当前持久 front door 已能维持 Cordis context。跨进程恢复或多客户端 attach 会让 daemon 变得合理，但两者都已推迟。
|
||||
**立即采用进程外 daemon。**初始的进程内功能不采用，因为当前长驻的运行入口已能维持 Cordis context。跨进程恢复或多客户端 attach 会让 daemon 变得合理，但两者都已推迟。
|
||||
|
||||
## 验证
|
||||
|
||||
- 逐文件测试覆盖并固定 owner 隔离、并发预留、未发布 spawn 的取消与等待式 teardown、沙箱模式变更拒绝、可重试的生命周期清理、就绪层级、对写入前 stdin 等待的拒绝、配置化交接宽限把 idle fallback 顶过一次轮询以及低于 `pollIntervalMs` 时的拒绝、sanitizer carry state、完整 UTF-8 结果上限、task 集成、schema 和精确 render intent。
|
||||
- Linux 进程 fixture（测试前置数据）覆盖非 leader 与非主线程的 stdin 等待、僵尸进程的完全停稳、不可读进程状态、受支持的 syscall 表、不支持的架构和误报拒绝；同一单元测试套件通过注入覆盖 macOS 检查器逻辑。
|
||||
- 真实 `node-pty` 测试在受支持宿主上覆盖 shell 状态、共享沙箱策略、环境清洗、在由场景掌控的时间界限内先有意延迟子进程就绪，再对 raw mode 前台进程发送 `SIGINT`、忽略 `SIGTERM` 的子进程，以及 dispose 返回后立即完全停稳。
|
||||
- 每文件覆盖率固定 owner 隔离、并发预留、写入前检查期间的取消、未发布 spawn 的取消与等待式 teardown、沙箱模式变更拒绝、可重试的生命周期清理、就绪层级、对写入前 stdin 等待与延迟到达的先前 prompt 的拒绝、配置化交接宽限把 idle fallback 顶过一次轮询以及低于 `pollIntervalMs` 时的拒绝、sanitizer carry state、完整 UTF-8 结果上限、task 集成、schema 和精确 render intent。
|
||||
- 子进程 fixture 覆盖非 leader 与非主线程的 stdin 等待、僵尸进程完全停稳、不可读进程状态、受支持的 syscall 表、不支持的架构和误报拒绝；同一单元测试套件通过注入覆盖 macOS 检查器逻辑。
|
||||
- 真实 `node-pty` 与 PTY 消费方测试共同在受支持宿主上覆盖 shell 状态、共享沙箱策略、环境清洗、raw mode 前台 `SIGINT`、忽略 `SIGTERM` 的后代进程，以及 dispose 返回后立即完全停稳。
|
||||
- Loader 驱动的 `cordis.yml` 测试挂载真实三包组合。ACP 与 headless 快照通过 opt-in overlay 固定 6 个 schema、有界结果和错误；TUI 快照固定 terminal 与 generic 卡片展示。
|
||||
- 包契约、架构图、核心数据结构、生成目录和 website API 描述同一个已发布接口。
|
||||
- 仓库 CI 等价序列负责类型、lint、覆盖率、快照、文档、构建、hygiene、demo 和 built-entry 验证。
|
||||
- 包约定、架构图、子系统页面、生成目录和 website API 描述同一个已发布接口。
|
||||
|
||||
## 后果
|
||||
|
||||
**无需削弱一次性工具即可获得持久终端状态。**Shell 与 REPL 状态可以跨工具调用保留，而 `bash`、`read`、`write` 和 `edit` 继续拥有更窄的校验、审批与回放契约。
|
||||
**无需削弱一次性工具即可获得持久终端状态。**Shell 与 REPL 状态可以跨工具调用保留，而 `bash`、`read`、`write` 和 `edit` 继续拥有更窄的校验、审批与回放约定。
|
||||
|
||||
**Linux Tier 1 之外的 idle 都是启发式结果。**输出静默无法区分 prompt、sleep 和网络 I/O。类型化结果保留不确定性，有界 timeout、task 等待与信号让模型仍能掌握控制权。
|
||||
|
||||
@@ -172,10 +172,10 @@ plugins:
|
||||
|
||||
**持久状态可能偏离模型认知。**模型可能忘记 cwd 或活跃 REPL。会话摘要和保留输出有助恢复，但任何 prompt 都无法让状态持久化变成确定行为。
|
||||
|
||||
**daemonized 子进程可能离开捕获树。**在 teardown 前 reparent 的进程无法再从 `node-pty` 根进程发现。实现接受这个清理缺口，不冒险按 SID 向无关进程发送信号。
|
||||
**daemonized 后代进程可能离开本地提供方捕获的进程树。**在 teardown 前 reparent 的进程无法再从 `node-pty` 根进程发现。本地终端原语接受这个清理缺口，不冒险按 SID 向无关进程发送信号。
|
||||
|
||||
**Shell 可以造成外部副作用。**会话沙箱和环境清洗降低本地暴露，但无法撤销 push、API 调用或消息发送。无法容忍这些副作用的部署必须省略 PTY 或增加网络策略。
|
||||
|
||||
**进程丢失会销毁终端状态。**进程内会话无法跨 harness crash 或 restart 存活，原始 scrollback 也不持久化。重要工作必须提交到文件或其他持久系统。
|
||||
|
||||
**`node-pty` 是原生依赖。**安装、支持的 Node 版本、prebuild 可用性和平台行为都需要在每个支持 OS 上运行构建产物冒烟测试。
|
||||
**`node-pty` 是 `dsh-subprocess-local` 的原生依赖。**安装、支持的 Node 版本、prebuild 可用性和平台行为都需要在每个支持 OS 上运行 built-artifact smoke。
|
||||
|
||||
@@ -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/2026-07-19-fresh-agent-ralph-workflow-tool.md
|
||||
2026-07-19-fresh-agent-ralph-workflow-tool.md: 6fe96587c49ef0316d1618fda2ee26b015b1ce87
|
||||
2026-07-19-fresh-agent-ralph-workflow-tool.zh.md: 03e5e4a705674b49c14cbb456b06d82fbd38f013
|
||||
2026-07-19-fresh-agent-ralph-workflow-tool.md: bbc8aba54bbd2cbfe9d9ba1fcc8cf9ad5c257d4f
|
||||
2026-07-19-fresh-agent-ralph-workflow-tool.zh.md: 7ac405c2f6f80fa3151fb8b88c266ae2b83ea3eb
|
||||
|
||||
@@ -12,7 +12,7 @@ Adding Ralph behavior to `dsh-agent-loop`, the goal driver, or the public model-
|
||||
|
||||
## Decision
|
||||
|
||||
Add `@deepseek-ai/dsh-tool-ralph` as a separate consumer package under `packages/workflow/`. It registers `ralph({ objective, maxRounds? })`, owns a fixed workflow script, and depends only on `ctx.tools`, `ctx.systemPrompt`, `ctx.workflows`, and `ctx.subagents`. A Ralph run is not a session goal, creates no goal state, and requires no branch in the concrete agent loop.
|
||||
Add `@deepseek-ai/dsh-tool-ralph` as a separate Consumer package under `packages/workflow/`. It registers `ralph({ objective, maxRounds? })`, owns a fixed workflow script, and depends only on `ctx.tools`, `ctx.systemPrompt`, `ctx.workflows`, and `ctx.subagents`. A Ralph run is not a session goal, creates no goal state, and requires no branch in the concrete agent loop.
|
||||
|
||||
The tool is foreground-only. The calling agent parents every child for cwd and lineage, the parent tool call waits for the complete run, and the parent step's abort signal cancels the workflow. `run.dispose()` is awaited on every path, so cancellation reaches the worker engine's bounded settlement and child quiescence before the call returns.
|
||||
|
||||
@@ -70,5 +70,5 @@ A keyless real-stack integration drives the fixed script through the actual work
|
||||
- Runs are foreground and process-local. Background collection, persistence/resume, scheduling, and restart recovery are absent.
|
||||
- Round count is the only aggregate budget. Token, currency, elapsed-time, and provider-usage budgets remain separate future policy.
|
||||
- One round creates one child. Within-round fan-out, evaluator/worker role separation, dynamic provider or model selection, and cross-run journals are deferred.
|
||||
- An ordinary child failure ends the run without retry, while preserving the failed round and last successful handoff. Fatal workflow infrastructure failures can end before the fixed script returns that state; adding retry or richer failure transport requires separate policy and seam design.
|
||||
- An ordinary child failure ends the run without retry, while preserving the failed round and last successful handoff. Fatal workflow infrastructure failures can end before the fixed script returns that state; adding retry or richer failure transport requires separate policy and boundary design.
|
||||
- Prompt guidance asks models not to invoke Ralph recursively; a structural child-tool restriction would require a separately designed workflow child-policy surface.
|
||||
|
||||
@@ -12,7 +12,7 @@ Status: implemented
|
||||
|
||||
## 决策
|
||||
|
||||
在 `packages/workflow/` 下新增独立的消费方包 `@deepseek-ai/dsh-tool-ralph`。它注册 `ralph({ objective, maxRounds? })`，拥有固定工作流脚本，并且只依赖 `ctx.tools`、`ctx.systemPrompt`、`ctx.workflows` 和 `ctx.subagents`。Ralph 运行不是会话目标，不会创建目标状态，也不要求在具体 agent loop 中增加分支。
|
||||
在 `packages/workflow/` 下新增独立的 Consumer 包 `@deepseek-ai/dsh-tool-ralph`。它注册 `ralph({ objective, maxRounds? })`，拥有固定工作流脚本，并且只依赖 `ctx.tools`、`ctx.systemPrompt`、`ctx.workflows` 和 `ctx.subagents`。Ralph 运行不是会话目标，不会创建目标状态，也不要求在具体 agent loop 中增加分支。
|
||||
|
||||
该工具仅以前台方式运行。调用 agent 作为每个子 agent 的父级以提供 cwd 和谱系，父工具调用等待整次运行结束，父步骤的中止信号会取消工作流。每条路径都会等待 `run.dispose()`，因此调用返回前，取消会经过工作线程引擎的有界收敛并使子 agent 完全停稳。
|
||||
|
||||
@@ -52,7 +52,7 @@ Ralph 插件的 `subagentProvider` 默认为 `spawn`。每次调用前，它要
|
||||
|
||||
- **把 Ralph 放进同会话目标驱动器** — 拒绝，因为 Goal Round 有意保留同一段对话，而 Ralph 的定义性属性是每个 Round 使用全新上下文；合并两者会让目标生命周期与子 agent 编排无法分离。
|
||||
- **在通用工作流工具上暴露 `fresh` 或循环标志** — 拒绝，因为模型编写的脚本表面应保持通用且与提供方无关；Ralph 的固定报告协议和停止策略值得拥有一个可评审消费方。
|
||||
- **为了方便重放而使用 `subagent_fork`** — 拒绝，因为继承的已完成轮次是隐式、不断增长的交接状态，并违反全新上下文契约。工作区加一份结构化报告即可重放，无需插入人为取消记录。
|
||||
- **为了方便重放而使用 `subagent_fork`** — 拒绝，因为继承的已完成轮次是隐式、不断增长的交接状态，并违反全新上下文约定。工作区加一份结构化报告即可重放，无需插入人为取消记录。
|
||||
- **让工具直接调用 subagent seam** — 拒绝，因为现有工作流引擎已经拥有前台编排、结构化子 agent、取消传播、工作线程终止、事件和完全停稳后的 dispose。复用它可以展示插件组合，而不是构建第二个循环运行时。
|
||||
- **静默截断大型报告** — 拒绝，因为截断可能删除状态证据或下一步，却仍看似权威交接。生产者必须在配置边界内发出有效报告。
|
||||
|
||||
@@ -70,5 +70,5 @@ Ralph 插件的 `subagentProvider` 默认为 `spawn`。每次调用前，它要
|
||||
- 运行位于前台且只存在于进程内。后台收集、持久化/恢复、调度和重启恢复均不存在。
|
||||
- Round 数是唯一聚合预算。token、货币、耗时和提供方用量预算仍属于未来的独立策略。
|
||||
- 每个 Round 创建一个子 agent。Round 内扇出、evaluator/工作者角色分离、动态提供方或模型选择，以及跨运行日志均被推迟。
|
||||
- 普通子 agent 失败会结束运行且不重试，同时保留失败 Round 与上一份成功交接。致命工作流基础设施错误可能在固定脚本返回该状态前结束；增加重试或更丰富的失败传输需要独立的策略与 seam 设计。
|
||||
- 普通子 agent 失败会结束运行且不重试，同时保留失败 Round 与上一份成功交接。致命工作流基础设施错误可能在固定脚本返回该状态前结束；增加重试或更丰富的失败传输需要独立的策略与边界设计。
|
||||
- 提示指导模型不要递归调用 Ralph；结构化的子 agent 工具限制需要另行设计工作流子策略表面。
|
||||
|
||||
@@ -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/2026-07-19-human-goal-command.md
|
||||
2026-07-19-human-goal-command.md: 5fdd80f7423b80e84e58f7379130ee59a2e8a723
|
||||
2026-07-19-human-goal-command.zh.md: 74dd0a2bec923687c91ddf4ce7efe4cc5b25bfc9
|
||||
2026-07-19-human-goal-command.md: d68e4025a4d37d07211f15ddfc6069bc7c637124
|
||||
2026-07-19-human-goal-command.zh.md: dbda35c731ccdc7aff2d4213a3df8b78070319df
|
||||
|
||||
@@ -68,5 +68,5 @@ The producer suite uses the real command registry, goal service, agent registry,
|
||||
- The portable command contract has no modal editor or confirmation interaction; inline edit and explicit clear are intentional until a general cross-surface interaction primitive exists.
|
||||
- `/goal` does not accept a per-command round cap. Deployment config owns the default, and the authorized model tool can edit a cap after direct human instruction.
|
||||
- TUI renders portable plain text rather than a continuously updated goal status widget. Reconnectable command output and adapter-specific status indicators are deferred.
|
||||
- The ACP automation server, headless CLI, and JSON-RPC front doors do not consume the command registry.
|
||||
- The ACP automation server, headless CLI, and JSON-RPC entry points do not consume the command registry.
|
||||
- The command observes and mutates state but does not certify completion or blockers. Evaluator-backed certification remains deferred to a separate policy layer with an explicit authority and isolation contract.
|
||||
|
||||
@@ -22,7 +22,7 @@ Status: implemented
|
||||
|
||||
`/goal <objective>` 创建活跃且已激活的目标。已完成目标可以被替换，此时通过现有领域规则创建新的目标身份。任何未完成目标都会让命令直接失败，并提示用户使用行内编辑或明确清除。通用命令服务有意不提供模态确认 API；若静默执行清除再创建两条持久记录，就等于凭空制造破坏性同意，并暴露一个非原子的失败窗口。
|
||||
|
||||
`/goal edit <objective>` 编辑当前未完成目标，但不改变其阶段或激活态。若目标已经完成，则创建一个新的活跃目标，因为领域不允许恢复已完成状态，而新的目标描述应拥有新的目标身份。单独使用 `edit` 会返回错误而不是启动编辑器，因为可移植的非结构化命令契约没有模态编辑器。
|
||||
`/goal edit <objective>` 编辑当前未完成目标，但不改变其阶段或激活态。若目标已经完成，则创建一个新的活跃目标，因为领域不允许恢复已完成状态，而新的目标描述应拥有新的目标身份。单独使用 `edit` 会返回错误而不是启动编辑器，因为可移植的非结构化命令约定没有模态编辑器。
|
||||
|
||||
`/goal pause`、`/goal resume` 与 `/goal clear` 使用当前视图调用相应的比较并交换领域动词。恢复既适用于停止的持久阶段，也适用于会话恢复、fork 或驱动器替换后处于活跃但未激活状态的目标。领域规则仍会拒绝已耗尽的 Round 上限、对已活跃且已激活目标的重复恢复、非法阶段转换与陈旧身份。清除会移除当前指针，而会话日志保留带修订号的墓碑和此前快照。
|
||||
|
||||
@@ -34,7 +34,7 @@ Status: implemented
|
||||
|
||||
预期的 `GoalError` 失败会变为一个稳定且不含品牌化 id 的 `CommandResult.error`，使领域诊断不会向面向人类的界面泄露比较并交换内部细节，非法操作也绝不会进入模型历史。当前状态负责提供针对具体状态且可执行的恢复路径。其他异常仍是适配器可见的命令失败；若把程序缺陷当成普通领域错误，就会隐藏问题。命令处理器只执行同步领域变更，因此请求取消会在变更开始前由命令注册表决定，不存在需要回滚的外逸异步副作用。
|
||||
|
||||
通用斜杠输入、状态文本与错误不会持久化。成功的 goal 变更会追加领域自有的 `goal/change` 事件，而且不会把模型上下文排队。该命令不会引入可能与领域事件不一致的第二份审计记录。
|
||||
通用斜杠输入、状态文本与错误不会持久化。成功的目标变更会追加领域自有的 `goal/change` 事件，而且不会将模型上下文加入队列。该命令不会引入可能与领域事件不一致的第二份审计记录。
|
||||
|
||||
### 应用组合
|
||||
|
||||
@@ -50,10 +50,10 @@ TUI 应用包作出相反的产品选择。它默认让 `goals` 使用所有者
|
||||
|
||||
- **让模型把 `/goal` 当作普通文本处理**——不予采纳，因为状态与直接生命周期操作会消耗模型轮次、可能被重新解释，也无法提供确定性的命令发现。
|
||||
- **在各 UI 中分别实现处理器**——不予采纳，因为语法、错误行为与目标状态格式会发生偏差，可选部署也无法把该功能作为一个 effect 统一增删。
|
||||
- **为 `ctx.commands` 添加模态编辑与替换确认**——不予采纳，因为现有跨界面契约是非结构化输入加直接输出；通用交互协议所需的设计远超这一个生产方。
|
||||
- **为 `ctx.commands` 添加模态编辑与替换确认**——不予采纳，因为现有跨界面约定是非结构化输入加直接输出；通用交互协议所需的设计远超这一个生产方。
|
||||
- **静默替换未完成目标**——不予采纳，因为这会在没有原子性或明确破坏性意图的情况下组合清除与创建。
|
||||
- **在人类状态中暴露目标 id 与修订号**——不予采纳，因为人类操作始终在一个同步处理器内针对确切的当前视图；这些字段只会增加实现噪声，无法避免另一处竞态。
|
||||
- **在无 UI 主干中无条件启用目标**——不予采纳，因为单次 SDK/CLI 的结束契约是物理轮次 API，而不是目标操作 API。
|
||||
- **在无 UI 主干中无条件启用目标**——不予采纳，因为单次 SDK/CLI 的结束约定是物理轮次 API，而不是目标操作 API。
|
||||
|
||||
## 后果
|
||||
|
||||
@@ -61,12 +61,12 @@ TUI 应用包作出相反的产品选择。它默认让 `goals` 使用所有者
|
||||
- 人类状态会区分持久阶段与实时激活态，并报告准确的目标 Round 上限。
|
||||
- 直接暂停、恢复、清除、创建与编辑不消耗模型轮次，而其已接受变更仍可从会话日志重建。
|
||||
- 恢复后的会话等待人类决策；`/goal resume` 是字面命令路径，任何语言的普通提示词则可以授权模型工具路径。
|
||||
- 无头组合保持单轮行为，除非明确选择加入目标并定义自己的长时间运行结束契约。
|
||||
- 无头组合保持单轮行为，除非明确选择加入目标并定义自己的长时间运行结束约定。
|
||||
|
||||
## 已知限制与暂缓事项
|
||||
|
||||
- 可移植命令契约没有模态编辑器或确认交互；在出现通用跨界面交互原语之前，行内编辑与明确清除是有意选择。
|
||||
- 可移植命令约定没有模态编辑器或确认交互；在出现通用跨界面交互原语之前，行内编辑与明确清除是有意选择。
|
||||
- `/goal` 不接受逐命令 Round 上限。部署配置拥有默认值；得到直接人类指示后，已授权模型工具可以编辑上限。
|
||||
- TUI 渲染可移植纯文本，而不是持续更新的目标状态组件。可重连命令输出和适配器专用状态指示器予以延期。
|
||||
- ACP 自动化服务器、无头 CLI 与 JSON-RPC 前端不消费命令注册表。
|
||||
- 该命令观察并改变状态，但不认证完成或阻塞。基于评估器的认证延期到具有明确权限与隔离契约的独立策略层。
|
||||
- ACP 自动化服务器、无头 CLI 与 JSON-RPC 运行入口不消费命令注册表。
|
||||
- 该命令观察并改变状态，但不认证完成或阻塞。基于评估器的认证延期到具有明确权限与隔离约定的独立策略层。
|
||||
|
||||
@@ -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/2026-07-19-model-facing-goal-tools.md
|
||||
2026-07-19-model-facing-goal-tools.md: 0271194a38503711de77290c915010c26a9de74b
|
||||
2026-07-19-model-facing-goal-tools.zh.md: 235c3c5369871a8cdf731eee822abc4a3e6b58d1
|
||||
2026-07-19-model-facing-goal-tools.md: c2f1210ea636b61e99111d261cf9302c77576b46
|
||||
2026-07-19-model-facing-goal-tools.zh.md: fd8ca90ba3b6809a7225b118ec6d311fb193cc8f
|
||||
|
||||
@@ -12,7 +12,7 @@ The surface also needs to preserve the separation between durable state and live
|
||||
|
||||
## Decision
|
||||
|
||||
`@deepseek-ai/dsh-tool-goal` in `packages/goal/tool-goal/` contributes three exclusive tools and one system-prompt policy section over `ctx.goals`: `get_goal`, `create_goal`, and `update_goal`. The names and read-create-update shape follow Codex's compact goal tool surface while the authority rules use this repository's public agent, session, tool, and goal seams.
|
||||
`@deepseek-ai/dsh-tool-goal` in `packages/goal/tool-goal/` contributes three exclusive tools and one system-prompt policy section over `ctx.goals`: `get_goal`, `create_goal`, and `update_goal`. The names and read-create-update shape follow Codex's compact goal tool surface while the authority rules use this repository's public agent, session, tool, and goal services.
|
||||
|
||||
### Tools and model contract
|
||||
|
||||
@@ -28,7 +28,7 @@ An autonomous goal round that successfully reports completion or blocking defers
|
||||
|
||||
Every call requires an `exec.agent` that is the exact running object in `AgentRegistry`, is the current inherited driver initiator, and has an open turn. These are execution-time checks and cannot be bypassed by prompt injection or hand-authored tool arguments.
|
||||
|
||||
Create, edit, pause, and resume additionally require an accepted user message or user steering event in the current turn of a runtime-root agent. Root ownership is derived from the live agent graph rather than durable fork ancestry: a resumed fork can receive direct human authority, while a live child remains a subagent and cannot mutate these states. User source is a host attestation: every `Agent.followup()` or `steer()` input requires an explicit source, so the host labels direct human content `{ kind: 'user' }` and non-human producers label their own provenance. The runtime proves provenance, not whether the human's wording semantically warrants creation or resumption; that interpretation remains with the model.
|
||||
Create, edit, pause, and resume additionally require an accepted user message or user steering event in the current turn of a runtime-root agent. Root ownership is derived from the live agent graph rather than durable fork ancestry: a resumed fork can receive direct human authority, while a live child remains a subagent and cannot mutate these states. User source is a host attestation: every `Agent.followup()` or `steer()` input requires an explicit source, so the host labels direct human content `{ kind: 'user' }` and non-human producers identify themselves in their source fields. The runtime proves that the current turn contains a direct human message, not whether the human's wording semantically warrants creation or resumption; that interpretation remains with the model.
|
||||
|
||||
Complete and blocked accept either direct-human authority or the exact current goal round. Goal-round authority requires a goal-sourced `user/message` whose goal id, revision, and round all equal the folded current goal. It grants only the two terminal reports. Direct human authority may stop a goal immediately.
|
||||
|
||||
@@ -44,7 +44,7 @@ Unit coverage pins registration and disposal, exclusive scheduling, generated pr
|
||||
|
||||
- **Rely on prompt instructions for authority** — rejected because text can guide model judgment but cannot authenticate the live caller, turn, or source event.
|
||||
- **Expose every goal-service verb as a separate tool** — rejected because a compact read/create/update surface reduces schema cost and keeps compare-and-set behavior uniform.
|
||||
- **Require exact command phrases** — rejected because natural-language intent, including languages other than English, should be interpreted by the model; execution authority depends on provenance rather than spelling.
|
||||
- **Require exact command phrases** — rejected because natural-language intent, including languages other than English, should be interpreted by the model; execution authority depends on a direct human message in the current turn rather than spelling.
|
||||
- **Authorize from persisted root or fork metadata** — rejected because a fork that becomes an independently resumed top-level session should accept new human authority, while a currently owned child should not.
|
||||
- **Let autonomous rounds edit or resume the goal** — rejected because continuation authority is narrower than authority to redefine or restart the human objective.
|
||||
- **Treat the blocked threshold as an evaluator** — rejected because event counts cannot prove that an obstacle is semantically unchanged or truly terminal.
|
||||
@@ -53,7 +53,7 @@ Unit coverage pins registration and disposal, exclusive scheduling, generated pr
|
||||
## Consequences
|
||||
|
||||
- Models receive a stable, compact lifecycle surface without direct access to the goal service.
|
||||
- State-changing calls are constrained by live runtime provenance as well as durable compare-and-set references.
|
||||
- State-changing calls require a live runtime-root agent and a direct human message in the current turn, as well as durable compare-and-set references.
|
||||
- Human requests can create and rearm goals through ordinary natural language, while restored sessions remain inert until such input arrives.
|
||||
- Goal rounds can finish or report a repeated blocker but cannot broaden their own mandate.
|
||||
- Deployment policy selects the blocking lower bound; the same resolved value controls enforcement and prompt guidance.
|
||||
|
||||
@@ -12,9 +12,9 @@ Status: implemented
|
||||
|
||||
## 决策
|
||||
|
||||
位于 `packages/goal/tool-goal/` 的 `@deepseek-ai/dsh-tool-goal` 在 `ctx.goals` 之上贡献三个独占工具和一个系统提示词策略段：`get_goal`、`create_goal` 与 `update_goal`。工具名称和读取—创建—更新形态遵循 Codex 的紧凑目标工具表面，而权限规则使用本仓库公共的 agent（智能体）、会话、工具与目标 seam。
|
||||
位于 `packages/goal/tool-goal/` 的 `@deepseek-ai/dsh-tool-goal` 在 `ctx.goals` 之上贡献三个独占工具和一个系统提示词策略段：`get_goal`、`create_goal` 与 `update_goal`。工具名称和读取—创建—更新形态遵循 Codex 的紧凑目标工具表面，而权限规则使用本仓库公共的 agent（智能体）、会话、工具与目标服务。
|
||||
|
||||
### 工具与模型契约
|
||||
### 工具与模型约定
|
||||
|
||||
`get_goal()` 返回当前目标或 `null`。非空结果包含用于比较并交换的 id 与修订号、目标描述、持久阶段、已接纳和最大 Goal Round 数、可能存在的阻塞原因，以及进程本地激活态观察。`create_goal(objective, max_goal_rounds?)` 创建一个长时间运行的同会话目标。`update_goal(goal_id, revision, action, objective?, max_goal_rounds?, blocked_reason?)` 支持 `edit`、`pause`、`resume`、`complete` 和 `blocked`；替换字段仅对 `edit` 有效，非空的 `blocked_reason` 仅在 `blocked` 时必填，并以稳定代码 `model-reported` 持久化。执行器把值恰好为空字符串的可选字段和值为 0 的 `max_goal_rounds` 视为严格 schema 占位值：这些值等同于省略；编辑时仍必须提供至少一个有实际意义的替换字段；所有非占位值仍受对应操作的限制。
|
||||
|
||||
@@ -28,7 +28,7 @@ Status: implemented
|
||||
|
||||
每次调用都要求存在 `exec.agent`，且它必须是 `AgentRegistry` 中完全相同的运行中对象、当前继承的驱动发起者，并处于开放轮次内。这些检查在执行时进行，不能通过提示词注入或手写工具参数绕过。
|
||||
|
||||
创建、编辑、暂停与恢复还要求运行时根 agent 的当前轮次已经接纳一条用户消息或用户 steering 事件。根所有权来自实时 agent 图，而非持久的 fork 祖先关系：恢复后的派生会话可以接收新的直接人类权限，实时子级则仍是 subagent，不能改变这些状态。用户来源是宿主的证明：每个 `Agent.followup()` 或 `steer()` 输入都必须显式提供来源，因此宿主把直接人类内容标为 `{ kind: 'user' }`，非人类生产者则标注自己的来源信息。运行时证明来源，而不判断人类措辞在语义上是否足以创建或恢复目标；该解释仍由模型完成。
|
||||
创建、编辑、暂停与恢复还要求运行时根 agent 的当前轮次已经接纳一条用户消息或用户 steering 事件。根所有权来自实时 agent 图，而非持久的 fork 祖先关系：恢复后的派生会话可以接收新的直接人类权限，实时子级则仍是 subagent，不能改变这些状态。用户来源是宿主的证明：每个 `Agent.followup()` 或 `steer()` 输入都必须显式提供来源，因此宿主把直接人类内容标为 `{ kind: 'user' }`，非人类生产者则在来源字段中注明自己。运行时证明当前轮次包含人类直接发送的消息，而不判断人类措辞在语义上是否足以创建或恢复目标；该解释仍由模型完成。
|
||||
|
||||
完成与阻塞既接受直接人类权限，也接受准确的当前 Goal Round。Goal Round 权限要求存在一条来源为目标的 `user/message`，其中目标 id、修订号和 Round 都与折叠后的当前目标相等。它只授予这两种终止报告权限。直接人类权限可以立即停止目标。
|
||||
|
||||
@@ -44,7 +44,7 @@ Status: implemented
|
||||
|
||||
- **依赖提示词指令实施权限**——不予采纳，因为文本可以指导模型判断，却不能认证实时调用者、轮次或来源事件。
|
||||
- **把每个目标服务动词分别暴露为工具**——不予采纳，因为紧凑的读取/创建/更新表面可以降低模式成本，并保持统一的比较并交换行为。
|
||||
- **要求精确命令短语**——不予采纳，因为自然语言意图（包括英语以外的语言）应由模型解释；执行权限取决于来源，而不是拼写。
|
||||
- **要求精确命令短语**——不予采纳，因为自然语言意图（包括英语以外的语言）应由模型解释；执行权限取决于当前轮次中人类直接发送的消息，而不是拼写。
|
||||
- **根据持久的根或派生元数据授权**——不予采纳，因为成为独立恢复顶层会话的派生应接受新的人类权限，而当前仍受所有权约束的子智能体则不应接受。
|
||||
- **允许自主回合编辑或恢复目标**——不予采纳，因为继续执行权限比重新定义或重启人类目标的权限更窄。
|
||||
- **把阻塞阈值当作评估器**——不予采纳，因为事件计数无法证明障碍在语义上未改变或确实不可继续。
|
||||
@@ -53,7 +53,7 @@ Status: implemented
|
||||
## 后果
|
||||
|
||||
- 模型获得稳定而紧凑的生命周期表面，无需直接访问目标服务。
|
||||
- 改变状态的调用同时受到实时运行时来源与持久比较并交换引用的约束。
|
||||
- 改变状态的调用要求实时运行时根 agent、当前轮次中人类直接发送的消息，以及持久比较并交换引用。
|
||||
- 人类可以通过普通自然语言请求创建和重新激活目标，而恢复后的会话在收到此类输入前保持静止。
|
||||
- Goal Round 可以完成或报告重复阻塞，但不能自行扩大任务权限。
|
||||
- 部署策略选择阻塞下限；同一个解析后的值同时控制执行与提示词指导。
|
||||
|
||||
@@ -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/2026-07-19-persisted-same-session-goal-domain.md
|
||||
2026-07-19-persisted-same-session-goal-domain.md: ce93a652f3910912fbf6afc28061de4d13eb2de2
|
||||
2026-07-19-persisted-same-session-goal-domain.zh.md: 7fb8dc3a6c76b91e0abf495782d51b30d3cd5b53
|
||||
2026-07-19-persisted-same-session-goal-domain.md: cdbbdd55c8c9b73851d5e729492656eda1380430
|
||||
2026-07-19-persisted-same-session-goal-domain.zh.md: 7c8af321ec78779ecbf4e5e00805ef6f152b2aa1
|
||||
|
||||
@@ -8,7 +8,7 @@ English | [中文](2026-07-19-persisted-same-session-goal-domain.zh.md)
|
||||
|
||||
A long-running objective outlives one prompt, turn, or model request. Treating that objective as an in-memory loop variable loses it on process restart, while putting it only in UI state makes model behavior impossible to reconstruct. Treating every session turn as progress also charges unrelated human messages against an automatic-work budget.
|
||||
|
||||
Durable lifecycle and permission to continue are different facts. A session may retain an active objective after restart or fork, but silently starting work when a user opens that session is surprising. The domain needs replayable state without persisted auto-execution authority, and it must remain a plugin on the public agent/session seams rather than a special case in the concrete loop.
|
||||
Durable lifecycle and permission to continue are different facts. A session may retain an active objective after restart or fork, but silently starting work when a user opens that session is surprising. The domain needs replayable state without persisted auto-execution authority, and it must remain a plugin on the public agent and session services rather than a special case in the concrete loop.
|
||||
|
||||
## Decision
|
||||
|
||||
|
||||
@@ -8,7 +8,7 @@ Status: implemented
|
||||
|
||||
长时间运行的目标会跨越单个提示词、轮次或模型请求。若把该目标视为内存中的循环变量，进程重启时就会丢失；若只存放在 UI 状态中，又无法重建模型行为。若把会话中的每个轮次都视为目标进度，与自动工作无关的人类消息也会消耗预算。
|
||||
|
||||
持久化的生命周期与继续执行的权限是两个不同事实。会话在重启或 fork（派生）后可以保留活跃目标，但用户打开会话时静默启动工作并不符合直觉。该领域需要可回放的状态，却不能持久化自动执行权限；它还必须作为公共 agent（智能体）与会话 seam 上的插件存在，而不是具体循环中的特例。
|
||||
持久化的生命周期与继续执行的权限是两个不同事实。会话在重启或 fork（派生）后可以保留活跃目标，但用户打开会话时静默启动工作并不符合直觉。该领域需要可回放的状态，却不能持久化自动执行权限；它还必须作为公共 agent（智能体）与会话服务上的插件存在，而不是具体循环中的特例。
|
||||
|
||||
## 决策
|
||||
|
||||
@@ -18,9 +18,9 @@ Status: implemented
|
||||
|
||||
### 持久记录与回放
|
||||
|
||||
每次变更都会追加带版本的 `goal/change` 会话事件，其中包含完整快照；clear 则包含带修订号的墓碑。会话日志是唯一的持久真源，因此持久化和 fork 会继承 goal 记录，而无需另设数据库或头字段。[Goal 自有持久事件决策](../architecture/2026-07-31-goal-owned-durable-events.md)负责 goal 状态与 inbox 状态、模型上下文之间的职责分离。
|
||||
每次变更都会追加带版本的 `goal/change` 会话事件，其中包含完整快照；清除时则包含带修订号的墓碑。会话日志是唯一的持久真源，因此持久化和 fork 会继承目标记录，而无需另设数据库或头字段。[目标自有持久事件决策](../architecture/2026-07-31-goal-owned-durable-events.md)负责将目标持久事件与收件箱状态和模型上下文分离。
|
||||
|
||||
回放折叠只从 `goal/change` 派生生命周期变更，并校验 JSON 形状、新 id、修订连续性、生命周期转换、计数器以及单个 goal 内单调递增的时间戳。只有当前活跃修订上带正数且连续编号、已准入的 `user/message` 来源才会推进 Goal Round，且不能超过 `maxGoalRounds`；普通会话轮次不会影响该计数器。当前格式的畸形记录会使回放失败，而不会被忽略或修复。
|
||||
回放折叠只从 `goal/change` 派生生命周期变更，并校验 JSON 形状、新 id、修订连续性、生命周期转换、计数器以及单个目标内单调递增的时间戳。只有当前活跃修订上带正数且连续编号、已接纳的 `user/message` 来源才会推进 Goal Round，且不能超过 `maxGoalRounds`；普通会话轮次不会影响该计数器。当前格式的畸形记录会使回放失败，而不会被忽略或修复。
|
||||
|
||||
增量回放会在每个有效事件后推进游标，并停留在首个损坏事件处，因此后续读取会报告同一个持久故障。重启后仍以持久日志为准。
|
||||
|
||||
@@ -36,12 +36,12 @@ Status: implemented
|
||||
|
||||
## 测试
|
||||
|
||||
单元测试固定创建默认值、精确实时 agent 校验、比较并交换拒绝、所有生命周期转换、阻塞原因校验与保留、恢复时的上限执行、清除与替换、种子回放和 `SessionStore.fork()` 继承、会话启动与生命周期所有者解除激活、活跃目标重新激活、持久事件折叠、inbox 独立性、损坏事件的稳定回放、服务与监听器销毁、监听器隔离、挂钟后退钳制、严格记录解码、生命周期连续性，以及连续 Goal Round 归属。无密钥 Loader/stdio 进程测试通过测试专用 `cordis.yml` 挂载服务与生命周期消费方，再从外部读取持久 JSONL，以验证 goal 记录以及不存在未经请求的 Goal Round。包源码受仓库逐文件 100% 覆盖率门禁约束。
|
||||
单元测试固定创建默认值、精确实时 agent 校验、比较并交换拒绝、所有生命周期转换、阻塞原因校验与保留、恢复时的上限执行、清除与替换、种子回放和 `SessionStore.fork()` 继承、会话启动与生命周期所有者解除激活、活跃目标重新激活、持久事件折叠、收件箱独立性、损坏事件的稳定回放、服务与监听器销毁、监听器隔离、挂钟后退钳制、严格记录解码、生命周期连续性，以及连续 Goal Round 归属。无密钥 Loader/stdio 进程测试通过测试专用 `cordis.yml` 挂载服务与生命周期消费方，再从外部读取持久 JSONL，以验证目标记录以及不存在未经请求的 Goal Round。包源码受仓库逐文件 100% 覆盖率门禁约束。
|
||||
|
||||
## 考虑过的替代方案
|
||||
|
||||
- **把目标存入独立数据库或会话头**——不予采纳，因为会话日志已经提供顺序、持久化、fork 前缀与可重建性；第二份存储会引入原子性和谱系问题。
|
||||
- **把每次持久变更与排队的模型上下文绑定。** 后续的 [Goal 自有持久事件决策](../architecture/2026-07-31-goal-owned-durable-events.md)不采用这一方案：goal 工具与已调度的继续执行提示词会在需要时暴露状态，而领域持久化不依赖队列结果。
|
||||
- **把每次持久变更与排队的模型上下文绑定。** 后续的 [Goal 自有持久事件决策](../architecture/2026-07-31-goal-owned-durable-events.md)不采用这一方案：目标工具与已调度的继续执行提示词会在需要时暴露状态，而领域持久化不依赖队列结果。
|
||||
- **持久化激活态并自动重启**——不予采纳，因为打开或恢复会话时必须等待人类输入；持久阶段记录状态，而不是再次消耗资源的授权。
|
||||
- **把所有会话轮次都计为 Goal Round**——不予采纳，因为同一会话可以包含人类澄清、检查和无关工作；只有归属于目标的继续执行轮次才消耗该预算。
|
||||
- **向 `dsh-agent-loop` 添加目标状态或通用循环抽象**——不予采纳，因为状态与继续执行策略可以通过现有插件、`Agent` 动词和事件组合，而无需赋予默认循环实现特权。
|
||||
|
||||
@@ -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/2026-07-19-plugin-command-registration.md
|
||||
2026-07-19-plugin-command-registration.md: 5233ce511dc9798733513ccbf6824f3e1b68d2e6
|
||||
2026-07-19-plugin-command-registration.zh.md: 7f41b9d2d00373901b51e3338fa51e1cadf886a9
|
||||
2026-07-19-plugin-command-registration.md: 76feba84492bd6b245246a6f1fb1e8f68d555684
|
||||
2026-07-19-plugin-command-registration.zh.md: e89cb79ba1e15dfefa527fe7bc37c09c3449f5b4
|
||||
|
||||
@@ -12,7 +12,7 @@ A shared mechanism must remain a UI concern rather than a model tool or agent-lo
|
||||
|
||||
## Decision
|
||||
|
||||
`@deepseek-ai/dsh-commands` in `packages/ui/commands/` is the product command registry. The TUI app bundle mounts it beside its consuming front door; the [automation-only ACP app](../simplification/2026-07-23-acp-automation-only-protocol.md) and the executor-less, UI-less agent spine omit it. TUI injects the service, while command producers depend only on the registry and any domain they operate.
|
||||
`@deepseek-ai/dsh-commands` in `packages/interaction/commands/` is the product command registry. The TUI app bundle mounts it beside its consuming front end; the [automation-only ACP app](../simplification/2026-07-23-acp-automation-only-protocol.md) and the executor-less, UI-less agent spine omit it. TUI injects the service, while command producers depend only on the registry and any domain they operate.
|
||||
|
||||
### Registry contract
|
||||
|
||||
@@ -50,7 +50,7 @@ TUI tests exercise all migrated built-ins, live plugin discovery, help/autocompl
|
||||
|
||||
- **Keep adapter-local switches** — rejected because optional plugins cannot contribute discovery and behavior without editing the TUI.
|
||||
- **Represent human commands as model tools** — rejected because discovery and direct invocation are human UI behavior; routing through the model adds latency, token cost, and reinterpretation.
|
||||
- **Put the registry in the core agent spine** — rejected because UI-less front doors do not consume it, while TUI can compose it explicitly.
|
||||
- **Put the registry in the core agent spine** — rejected because UI-less entry points do not consume it, while TUI can compose it explicitly.
|
||||
- **Make `dsh-agent-loop` inject commands** — rejected because the loop does not execute or discover human commands. Agent-scoped producers declare the UI dependency in a child plugin instead.
|
||||
- **Attach adapter masks to each definition** — rejected because support is a composition fact, not command-domain state. Every composed adapter exposes a registered command; an incompatible plugin omits registration in that deployment.
|
||||
- **Send unknown slash input to the model** — rejected because typoed or unavailable direct actions must fail predictably rather than change execution planes.
|
||||
@@ -68,4 +68,4 @@ TUI tests exercise all migrated built-ins, live plugin discovery, help/autocompl
|
||||
- Input metadata is limited to an unstructured text hint. Typed forms, argument schemas, and completion providers remain command-owned or require a later registry or consumer extension.
|
||||
- Generic command output is live-only and is not reconstructed after TUI restart.
|
||||
- Registry cancellation stops awaiting immediately, but external work stops only when a handler cooperates with its signal.
|
||||
- The ACP automation server, headless CLI, and JSON-RPC SDK front doors do not expose the command plane; only TUI consumes it.
|
||||
- The ACP automation server, headless CLI, and JSON-RPC SDK entry points do not expose the command plane; only TUI consumes it.
|
||||
|
||||
@@ -12,9 +12,9 @@ TUI 拥有斜杠命令。如果命令名、帮助文本、自动补全、分派
|
||||
|
||||
## 决策
|
||||
|
||||
位于 `packages/ui/commands/` 的 `@deepseek-ai/dsh-commands` 是产品命令注册表。TUI 应用 bundle（组合包）把它挂载在消费该服务的入口旁；[仅面向自动化的 ACP（Agent Client Protocol）应用](../simplification/2026-07-23-acp-automation-only-protocol.md)和无执行器、无 UI 的智能体 spine（主干）都省略该服务。TUI 注入该服务，命令生产者只依赖注册表及其操作的领域。
|
||||
位于 `packages/interaction/commands/` 的 `@deepseek-ai/dsh-commands` 是产品命令注册表。TUI 应用 bundle（组合包）把它挂载在消费该服务的前端旁；[仅面向自动化的 ACP（Agent Client Protocol）应用](../simplification/2026-07-23-acp-automation-only-protocol.md)和无执行器、无 UI 的智能体 spine（主干）都省略该服务。TUI 注入该服务，命令生产者只依赖注册表及其操作的领域。
|
||||
|
||||
### 注册表契约
|
||||
### 注册表约定
|
||||
|
||||
`CommandDefinition` 包含不带 `/` 的小写名称、非空描述、可选的非结构化输入提示，以及可取消处理器。注册会校验元数据并复制一份与调用方脱离的副本、冻结最终生效的定义，并返回对应 Cordis effect 的精确 disposer（资源释放器）。同一层中的重复名称会失败。每个消费方都能看到所有有效定义；若命令插件无法在某种部署中运行，它就不在该部署中注册，而不是把消费方身份编码进共享领域。
|
||||
|
||||
@@ -30,7 +30,7 @@ TUI 拥有斜杠命令。如果命令名、帮助文本、自动补全、分派
|
||||
|
||||
### 直接分派与取消
|
||||
|
||||
命令在仅面向人类的命令平面中运行。注册表不会把输入转成 `user/message`，输出不会成为会话事件，两者都不会隐式发送给模型。处理器接收对应的同一个目标 agent、原始输入和本次请求持有的 `AbortSignal`；生产者可以通过该智能体显式调度单独的模型可见工作，随后由生产者负责其日志记录和生命周期契约。信号中止时，注册表不再等待不合作的处理器；处理器仍负责停止已经启动的外部副作用。
|
||||
命令在仅面向人类的命令平面中运行。注册表不会把输入转成 `user/message`，输出不会成为会话事件，两者都不会隐式发送给模型。处理器接收对应的同一个目标 agent、原始输入和本次请求持有的 `AbortSignal`；生产者可以通过该智能体显式调度单独的模型可见工作，随后由生产者负责其日志记录和生命周期约定。信号中止时，注册表不再等待不合作的处理器；处理器仍负责停止已经启动的外部副作用。
|
||||
|
||||
预期的处理器失败返回 `CommandResult.error`。抛出的异常或格式错误的结果仍是适配器可见的命令失败，而不是模型消息。该边界有意分离 UI 输出与持久领域变更：例如目标命令可以改变 `ctx.goals`，但持久状态由目标服务拥有。
|
||||
|
||||
@@ -50,7 +50,7 @@ TUI 测试覆盖全部迁移后的内置命令、实时插件发现、帮助与
|
||||
|
||||
- **保留适配器本地 switch**——不予采纳，因为可选插件无法贡献发现与行为，除非修改 TUI。
|
||||
- **把人类命令表示为模型工具**——不予采纳，因为发现与直接调用属于人类 UI 行为；经由模型路由会增加延迟、token 成本和重新解释。
|
||||
- **把注册表放入核心智能体主干**——不予采纳，因为无 UI 前端不消费它，而 TUI 可以显式组合它。
|
||||
- **把注册表放入核心智能体主干**——不予采纳，因为无 UI 运行入口不消费它，而 TUI 可以显式组合它。
|
||||
- **让 `dsh-agent-loop` 注入 commands**——不予采纳，因为循环不执行也不发现人类命令。智能体作用域生产者改为在子插件中声明 UI 依赖。
|
||||
- **为每个定义附加适配器掩码**——不予采纳，因为支持能力是组合事实，而不是命令领域状态。每个已组合适配器都暴露已注册命令；不兼容插件不会在该部署中注册。
|
||||
- **把未知斜杠输入发送给模型**——不予采纳，因为输入错误或不可用的直接操作必须可预测地失败，而不能改变执行平面。
|
||||
@@ -58,7 +58,7 @@ TUI 测试覆盖全部迁移后的内置命令、实时插件发现、帮助与
|
||||
|
||||
## 后果
|
||||
|
||||
- 命令生产者是普通的可移除插件，TUI 消费其经过校验的目录与分派契约。
|
||||
- 命令生产者是普通的可移除插件，TUI 消费其经过校验的目录与分派约定。
|
||||
- 智能体特定定义保留现有扁平作用域与遮蔽语义，不引入核心到 UI 的依赖。
|
||||
- 未知斜杠输入与命令输出是确定性 UI 行为，直接模型 token 成本为零。
|
||||
- 直接命令取消与模型轮次取消彼此隔离。
|
||||
@@ -68,4 +68,4 @@ TUI 测试覆盖全部迁移后的内置命令、实时插件发现、帮助与
|
||||
- 输入元数据仅限非结构化文本提示。类型化表单、参数模式和补全提供器仍由命令拥有，或需要后续注册表或消费方扩展。
|
||||
- 通用命令输出仅实时存在，TUI 重启后不会重建。
|
||||
- 注册表取消会立即停止等待，但外部工作只有在处理器配合信号时才会停止。
|
||||
- ACP 自动化服务器、无头 CLI 与 JSON-RPC SDK 前端不暴露命令平面；只有 TUI 消费它。
|
||||
- ACP 自动化服务器、无头 CLI 与 JSON-RPC SDK 运行入口不暴露命令平面；只有 TUI 消费它。
|
||||
|
||||
@@ -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/2026-07-19-same-session-goal-round-driver.md
|
||||
2026-07-19-same-session-goal-round-driver.md: a989b9d3487ebbf8ff11a4e34cb08029f1e4ace4
|
||||
2026-07-19-same-session-goal-round-driver.zh.md: b49a759c8f3577db30b8ab45449bb7faed85a7da
|
||||
2026-07-19-same-session-goal-round-driver.md: 2ca08e4b6f0d16d66663db5275f3bce72bd3a9d7
|
||||
2026-07-19-same-session-goal-round-driver.zh.md: a41d9705e18cddb851c0a99a8dd7fc901f2be81a
|
||||
|
||||
@@ -49,7 +49,7 @@ The driver classifies one closed goal-owned turn as follows:
|
||||
|
||||
No abnormal outcome requests an automatic retry. A later human prompt can ask to continue in any language; the model reads the stopped goal and uses the goal tool's resume action, which records a new revision and arms continuation.
|
||||
|
||||
### Durability and cancellation seam
|
||||
### Durability and cancellation contract
|
||||
|
||||
Every `goal/changed` notification creates a checkpoint obligation. The driver awaits `ctx.sessions.flush(session)` before reserving work, then checks for a newer mutation, agent lifecycle change, or competing prompt. Turn-end flush failure is reported by the existing `agent/error` notification after `turn/end`; the driver finds that exact closed turn even when a concurrent one-shot injection appended a later turn, associates the failure with the exact attempt, and disarms before the next idle decision.
|
||||
|
||||
@@ -75,7 +75,7 @@ The core cancellation test proves notification order and containment: observers
|
||||
|
||||
## Alternatives considered
|
||||
|
||||
- **Add a goal loop inside `dsh-agent-loop`** — rejected because the public queue, prompt, session, cancellation, and status seams are sufficient, and a concrete-loop branch would privilege one policy.
|
||||
- **Add a goal loop inside `dsh-agent-loop`** — rejected because the public queue, prompt, session, cancellation, and status contracts are sufficient, and a concrete-loop branch would privilege one policy.
|
||||
- **Use `agent/turn-continuation` to make every round another step** — rejected because a goal round is an outer policy iteration and must have its own durable user prompt, turn boundary, round count, and failure settlement.
|
||||
- **Persist a pending reservation** — rejected because a crash cannot prove that queued process memory had reached admission; only the durable `user/message` consumes the round.
|
||||
- **Retry provider or persistence errors automatically** — rejected because retry policy spends resources and needs explicit authority; stopped phases plus later human resume are simpler and observable.
|
||||
|
||||
@@ -20,15 +20,15 @@ Status: implemented
|
||||
|
||||
### 预留与接纳
|
||||
|
||||
当 agent 空闲、没有竞争中的排队工作，且当前目标为 `active` 加 `armed` 时，驱动器会先检查点持久化待处理的目标变更，并在等待之后重新校验所有条件。若 `roundsStarted` 已等于 `maxGoalRounds`，它会记录代码为 `round-limit` 的 `blocked`；否则，它会先预留精确身份 `{ goalId, revision, round: roundsStarted + 1 }` 和完整渲染提示词，再以 `GoalMessageSource` 调用 `Agent.followup()`。提示词用 JSON 引号编码目标描述，使多行或类似标签的文本在熟悉框架中仍是无歧义的数据值。
|
||||
当 agent 空闲、没有竞争中的排队工作，且当前目标为 `active` 加 `armed` 时，驱动器会先将待处理的目标变更持久化到检查点，并在等待完成后重新校验所有条件。若 `roundsStarted` 已等于 `maxGoalRounds`，它会记录代码为 `round-limit` 的 `blocked`；否则，它会先预留精确身份 `{ goalId, revision, round: roundsStarted + 1 }` 和完整渲染提示词，再以 `GoalMessageSource` 调用 `Agent.followup()`。提示词用 JSON 引号编码目标描述，使多行或类似标签的文本在熟悉框架中仍是无歧义的数据值。
|
||||
|
||||
`agent/pre-step` 瀑布是进入栅栏。正数目标来源只有在完全匹配驱动器待处理的身份和内容、实时目标仍具有相同 id 与修订号、激活态仍为 armed，并且该回合仍是下一个编号时才会进入步骤。插件在委托下游监听器前检查一次，在下游返回后再检查一次。第二次检查防止异步监听器编辑或暂停目标后，旧提示词仍进入步骤。
|
||||
`agent/pre-step` waterfall（瀑布式事件）是进入栅栏。正数目标来源只有在完全匹配驱动器待处理的身份和内容、实时目标仍具有相同 id 与修订号、激活态仍为 armed，并且该回合仍是下一个编号时才会进入。插件在委托下游监听器前检查一次，在下游返回后再检查一次。第二次检查防止异步监听器编辑或暂停目标后，旧提示词仍会进入。
|
||||
|
||||
只有最终产生的 `user/message` 才是进入步骤的目标回合，并推进目标折叠。陈旧预留会关闭一个 blocked 的无步骤轮次；驱动器会把它标记为陈旧，不消耗回合数。若下游策略拒绝并非由陈旧状态导致，目标会进入 blocked，而不会绕过该策略自动重试。
|
||||
只有最终产生的 `user/message` 才是已进入的目标回合，并推进目标折叠。陈旧预留会关闭一个被阻塞的零步骤轮次；驱动器会把它标记为陈旧，不消耗回合数。若下游策略拒绝并非由陈旧状态导致，目标会进入 blocked，而不会绕过该策略自动重试。
|
||||
|
||||
### 人类工作与修订竞争
|
||||
|
||||
预留的 `MessageId` 会区分驱动器自己的完整记录与其他所有提示词。预留之前已经排队的普通工作会阻止调度；自动提示词待处理时进入的普通工作会使该预留过期，因此混合的已领取批次会 reject 自动提案。目标回合已经进入步骤后到达的普通工作会保留在队列中，成为下一个独立轮次；只有 agent 再次空闲后才重新考虑继续执行。
|
||||
预留的 `MessageId` 会区分驱动器自己的完整记录与其他所有提示词。预留之前已经排队的普通工作会阻止调度；自动提示词待处理时进入的普通工作会使该预留过期，因此混合的已领取批次会拒绝自动提案。目标回合进入后到达的普通工作会保留在队列中，成为下一个独立轮次；只有 agent 再次空闲后才重新考虑继续执行。
|
||||
|
||||
目标在回合内发生变更时会推进持久修订号。旧修订的结算不得覆盖该变更。驱动器会丢弃旧尝试的结果、读取新投影，并且只在新修订仍为 active 与 armed 时继续。因此，模型记录的完成、暂停、阻塞和编辑相对于物理轮次稍后的关闭原因具有最终权威。
|
||||
|
||||
@@ -49,13 +49,13 @@ Status: implemented
|
||||
|
||||
异常结果都不会请求自动重试。之后的人类提示词可以用任何语言要求继续；模型读取已停止目标并调用目标工具的 resume 动作，记录新修订并重新激活继续执行。
|
||||
|
||||
### 持久性与取消 seam
|
||||
### 持久性与取消约定
|
||||
|
||||
每次 `goal/changed` 通知都会产生一个检查点义务。驱动器在预留工作前等待 `ctx.sessions.flush(session)`，随后检查是否出现了更新的变更、agent 生命周期变化或竞争提示词。轮次结束时的 flush 失败会在 `turn/end` 之后通过现有 `agent/error` 通知报告；即使并发的一次性注入已追加后续轮次，驱动器仍会找到对应的同一个已关闭轮次，把失败关联到对应的同一次尝试，并在下一次空闲决策前解除激活。
|
||||
|
||||
广义取消会清除待处理 inbox 工作，并中止活跃 loop 阶段。目标驱动器通过 inbox 的领取／丢弃事件和持久的 aborted 轮次结束来跟踪预留消息。由于轮次现在会在首次领取前打开，取消可以关闭已领取的无步骤尝试；驱动器会把该尝试标记为已取消，并让随后的 idle 边沿暂停目标，与已准入尝试的处理方式相同。没有匹配目标尝试的取消只会移除进程内激活态。若暂停变更抛错，驱动器会回退到解除激活，避免已取消的自动工作重新启动。
|
||||
广义取消会清除待处理的收件箱工作，并中止活跃的循环阶段。目标驱动器通过收件箱领取／丢弃事件和持久化的 aborted 轮次结束事件来跟踪预留消息。由于轮次现在会在首次领取前打开，取消可以关闭已领取的零步骤尝试；驱动器会把该尝试标记为已取消，并让随后的空闲边沿暂停目标，与已接纳尝试的处理方式相同。没有匹配目标尝试的取消只会移除进程内激活态。若暂停变更抛错，驱动器会回退到解除激活，避免已取消的自动工作重新启动。
|
||||
|
||||
`Agent.cancel()` 仍是唯一的公共广义取消动词。若消费方依赖其顺序，实现该接口的自定义 `Agent` 必须遵守 inbox、轮次结束、status 与完全停稳的顺序。
|
||||
`Agent.cancel()` 仍是唯一的公共广义取消动词。若消费方依赖这些顺序，实现该接口的自定义 `Agent` 必须遵守收件箱、轮次结束、状态与完全停稳的顺序。
|
||||
|
||||
### 进程生命周期
|
||||
|
||||
@@ -75,7 +75,7 @@ Status: implemented
|
||||
|
||||
## 考虑过的替代方案
|
||||
|
||||
- **在 `dsh-agent-loop` 内添加目标循环**——不予采纳，因为公共队列、提示词、会话、取消和状态 seam 已经足够，具体循环分支还会赋予某种策略特权。
|
||||
- **在 `dsh-agent-loop` 内添加目标循环**——不予采纳，因为公共队列、提示词、会话、取消和状态约定已经足够，具体循环分支还会赋予某种策略特权。
|
||||
- **使用 `agent/turn-continuation` 把每个 Round 变成另一个步骤**——不予采纳，因为 Goal Round 是外层策略迭代，必须拥有自己的持久用户提示词、轮次边界、Round 计数和失败结算。
|
||||
- **持久化待处理预留**——不予采纳，因为崩溃无法证明进程内队列已经达到接纳点；只有持久 `user/message` 才消耗回合。
|
||||
- **自动重试提供方或持久化错误**——不予采纳，因为重试会消耗资源，需要显式授权；停止阶段加之后的人类恢复更简单，也可观察。
|
||||
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user