diff --git a/.agents/notes/archived/manifest.json b/.agents/notes/archived/manifest.json index 1adde54c7b..638d87373d 100644 --- a/.agents/notes/archived/manifest.json +++ b/.agents/notes/archived/manifest.json @@ -298,6 +298,9 @@ "process/2026-07-26-gui-pr-gif-evidence-and-assets-branch.i18n.yaml": "sha256:89b6dc255cb0dd9d97ae6f34f37d185412d4260d7bf2f87d6b25e340f01dc26e", "process/2026-07-26-gui-pr-gif-evidence-and-assets-branch.md": "sha256:1742e09435ade4a09349c8843eb381e870a2be2d51b74449f08260422c8096b3", "process/2026-07-26-gui-pr-gif-evidence-and-assets-branch.zh.md": "sha256:220bd53a88617b09ee8970627c46540fa8951724b102acfe296a7ed7d0f7b5fe", + "process/2026-07-27-wine-windows-gates-experiment.i18n.yaml": "sha256:6f4cbc12ee9cddbb297bf7e138ccabcd204f66898a0f7411b1633f03d5a9eab5", + "process/2026-07-27-wine-windows-gates-experiment.md": "sha256:8d37dcdab058098c7de3da1de00ce61bef92bbc8d6ee71add959474c6fb3e936", + "process/2026-07-27-wine-windows-gates-experiment.zh.md": "sha256:77fbf04df36af09e55007a93bd6b22d08ff99869efe8de3e97dac5b4701e0a9e", "simplification/2026-06-20-drop-unconsumed-llm-adapter-change-event.i18n.yaml": "sha256:ad3d1263cb0051b885173bf064de62065e2c646ccaae2d7250723da3b4eab90c", "simplification/2026-06-20-drop-unconsumed-llm-adapter-change-event.md": "sha256:8fb061d51c8c23b47d2367814bab3623c6d5b972f38d207a273caa9030b579bd", "simplification/2026-06-20-drop-unconsumed-llm-adapter-change-event.zh.md": "sha256:2ffeaca91f82844a5616d6dcce6b4af514bb8a7c46f78e47f668b204ac6edc04", diff --git a/.agents/notes/implemented/process/2026-07-27-wine-windows-gates-experiment.i18n.yaml b/.agents/notes/archived/process/2026-07-27-wine-windows-gates-experiment.i18n.yaml similarity index 67% rename from .agents/notes/implemented/process/2026-07-27-wine-windows-gates-experiment.i18n.yaml rename to .agents/notes/archived/process/2026-07-27-wine-windows-gates-experiment.i18n.yaml index cd55f494d7..f7995fd9cf 100644 --- a/.agents/notes/implemented/process/2026-07-27-wine-windows-gates-experiment.i18n.yaml +++ b/.agents/notes/archived/process/2026-07-27-wine-windows-gates-experiment.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/process/2026-07-27-wine-windows-gates-experiment.md -2026-07-27-wine-windows-gates-experiment.md: 1b01fe00dc1588482442a3cedc35eefa7fdb0975 -2026-07-27-wine-windows-gates-experiment.zh.md: 3145a4aa6a06cacbab96dd37714617aeecdfdde0 +2026-07-27-wine-windows-gates-experiment.md: ce2ad1ad4506f59083de5731677d052161849e3d +2026-07-27-wine-windows-gates-experiment.zh.md: a0a5e8e7cce078adf2c961fe4d8cc50edc28355c diff --git a/.agents/notes/implemented/process/2026-07-27-wine-windows-gates-experiment.md b/.agents/notes/archived/process/2026-07-27-wine-windows-gates-experiment.md similarity index 99% rename from .agents/notes/implemented/process/2026-07-27-wine-windows-gates-experiment.md rename to .agents/notes/archived/process/2026-07-27-wine-windows-gates-experiment.md index 1b01fe00dc..ce2ad1ad45 100644 --- a/.agents/notes/implemented/process/2026-07-27-wine-windows-gates-experiment.md +++ b/.agents/notes/archived/process/2026-07-27-wine-windows-gates-experiment.md @@ -1,6 +1,7 @@ # Agent Note: Wine-run Windows blocking gates on Linux runners Status: implemented +Archived: 2026-08-08 English | [中文](2026-07-27-wine-windows-gates-experiment.zh.md) diff --git a/.agents/notes/implemented/process/2026-07-27-wine-windows-gates-experiment.zh.md b/.agents/notes/archived/process/2026-07-27-wine-windows-gates-experiment.zh.md similarity index 98% rename from .agents/notes/implemented/process/2026-07-27-wine-windows-gates-experiment.zh.md rename to .agents/notes/archived/process/2026-07-27-wine-windows-gates-experiment.zh.md index 3145a4aa6a..a0a5e8e7cc 100644 --- a/.agents/notes/implemented/process/2026-07-27-wine-windows-gates-experiment.zh.md +++ b/.agents/notes/archived/process/2026-07-27-wine-windows-gates-experiment.zh.md @@ -1,6 +1,7 @@ # Agent Note: 在 Linux runner 上用 Wine 运行 Windows 阻断门禁 Status: implemented +Archived: 2026-08-08 [English](2026-07-27-wine-windows-gates-experiment.md) | 中文 @@ -14,7 +15,7 @@ Pull request 的 Windows 通道旨在验证两个阻断性 win32 表面，即 wo [ci.yml](../../../../.github/workflows/ci.yml) 中必需的 pull request `windows` 作业（`windows node 24 / wine blocking`）在 `ubuntu-latest` 上通过 Wine 用真实 Windows 二进制运行阻断门禁命令：校验和验证过的 win-x64 Node.js 执行 `tsc -b`、`tsdown` 与 VitePress 生产构建，因此工具链的 win32 分支——反斜杠路径处理、`CreateProcess` 派生语义、`@esbuild/win32-x64` 的 PE 加载、以及 rolldown/rollup 的 MSVC `.node` 插件——都真正执行。master 的 `serial-windows` 作业原封不动：完整的原生内核清单，包括本通道不运行的观察性可移植性门禁，仍在每次 master push 时于真实 `windows-2025` 上执行。 -依赖在 Linux 上原生安装，`supportedArchitectures` 扩展到 win32-x64，使 Windows 平台包物化进同一个 store；通过直接调用各工具的 JavaScript 入口绕开 cmd-shim 层，这正是 `run-gates` 最终派生的那些进程。`nodeLinker: hoisted` 是承重的，不是风格问题：一个独立原型保留了 pnpm 默认的 isolated 布局——包括在 Linux 预取的 store 上忠实地用 Windows pnpm 离线重装——而 Wine 下的 Windows Node 依然无法穿过 isolated 符号链接链解析 `@esbuild/win32-x64` 或加载 koffi 预编译产物，在任何仓库门禁运行前就失败了。扁平的真实文件布局才让门禁变得可达；本通道采纳了该原型的校验和固定，同时明确放弃其「Windows pnpm 安装依赖树」的目标（安装约定在此仍由 Linux 侧验证）。 +依赖在 Linux 上原生安装，`supportedArchitectures` 扩展到 win32-x64，使 Windows 平台包物化进同一个 store；通过直接调用各工具的 JavaScript 入口绕开 cmd-shim 层，这正是 `run-gates` 最终派生的那些进程。`nodeLinker: hoisted` 是承重的，不是风格问题：一个独立原型保留了 pnpm 默认的 isolated 布局——包括在 Linux 预取的 store 上忠实地用 Windows pnpm 离线重装——而 Wine 下的 Windows Node 依然无法穿过 isolated 符号链接链解析 `@esbuild/win32-x64` 或加载 koffi 预编译产物，在任何仓库门禁运行前就失败了。扁平的真实文件布局才让门禁变得可达；本通道采纳了该原型的校验和固定，同时明确放弃其「Windows pnpm 安装依赖树」的目标（安装契约在此仍由 Linux 侧验证）。 该通道靠四个杠杆把墙钟时间保持在与 Linux CI 作业相当的水平：master 刷新的 pnpm store 缓存（只恢复，与 Linux 作业同键）、Wine 供给（apt 安装、Windows Node 下载、`wineboot`）与 `pnpm install` 并发运行、两个阻断表面并发运行——与 `run-gates` 在原生 Windows 上给它们的形状相同——以及按 runner 镜像为键的 apt 归档缓存，由 master 的 `wine apt cache` 作业播种，使每个 pull request 都能从默认分支作用域恢复。 @@ -32,7 +33,7 @@ Pull request 的 Windows 通道旨在验证两个阻断性 win32 表面，即 wo **在 Linux runner 内用 QEMU/KVM 跑完整 Windows 客户机。** 真实 NT 内核，保真度完整，包括大小写不敏感的 NTFS 与 ConPTY——但首个门禁运行前要花数十分钟下载镜像并做无人值守安装（兄弟实验分支 `exp/kvm-windows-ci` 实测端到端 40 分 19 秒）。只有配上会挤压 Actions 缓存预算的磁盘镜像缓存才可投入使用。 -**在 Wine 下由 Windows pnpm 执行安装。** 同一想法的更高保真度变体：把 MinGit 与 pnpm 放进 prefix，用 Linux 预取填充 store，再由 Windows Node 运行 `pnpm install --offline`，让安装约定本身以 win32 身份执行。它到达了安装但没到达门禁——Wine 的网络无法直接访问 registry，且 isolated 的 `node_modules` 布局即便在干净的离线安装后也挫败了 Windows 平台包的解析。本通道牺牲这份保真度（hoisted 布局、Linux 侧安装）来换取门禁可达；两份记录是同一裁决互补的两半。 +**在 Wine 下由 Windows pnpm 执行安装。** 同一想法的更高保真度变体：把 MinGit 与 pnpm 放进 prefix，用 Linux 预取填充 store，再由 Windows Node 运行 `pnpm install --offline`，让安装契约本身以 win32 身份执行。它到达了安装但没到达门禁——Wine 的网络无法直接访问 registry，且 isolated 的 `node_modules` 布局即便在干净的离线安装后也挫败了 Windows 平台包的解析。本通道牺牲这份保真度（hoisted 布局、Linux 侧安装）来换取门禁可达；两份记录是同一裁决互补的两半。 **Linux 上的文件系统语义通道（casefold ext4、文件名 lint）。** 以近零成本捕获最高频的 Windows 故障类别，但对 win32 二进制什么也证明不了。作为兄弟实验分支 `exp/casefold-windows-ci` 探索；与本通道互补而非竞争。 diff --git a/.agents/notes/implemented/architecture/2026-06-11-dev-invariants-over-deep-readonly.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-11-dev-invariants-over-deep-readonly.i18n.yaml index f89d1da013..5027c64154 100644 --- a/.agents/notes/implemented/architecture/2026-06-11-dev-invariants-over-deep-readonly.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-06-11-dev-invariants-over-deep-readonly.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-06-11-dev-invariants-over-deep-readonly.md -2026-06-11-dev-invariants-over-deep-readonly.md: f1a741927cf63b43b1aaf558efc148ff80d2d881 -2026-06-11-dev-invariants-over-deep-readonly.zh.md: ade3e20adb8f5301adb87130d42c2bd7a37f8a47 +2026-06-11-dev-invariants-over-deep-readonly.md: 66980f1ee09c6112f72786d6c3a147aadbc57f6c +2026-06-11-dev-invariants-over-deep-readonly.zh.md: 38a19ee7dd63823b5a5e103908410786c20435c6 diff --git a/.agents/notes/implemented/architecture/2026-06-11-dev-invariants-over-deep-readonly.md b/.agents/notes/implemented/architecture/2026-06-11-dev-invariants-over-deep-readonly.md index f1a741927c..66980f1ee0 100644 --- a/.agents/notes/implemented/architecture/2026-06-11-dev-invariants-over-deep-readonly.md +++ b/.agents/notes/implemented/architecture/2026-06-11-dev-invariants-over-deep-readonly.md @@ -6,7 +6,7 @@ English | [中文](2026-06-11-dev-invariants-over-deep-readonly.zh.md) ## Problem -The session log needs two different protections: immutable ownership of each stored fact, and checks for relationships among facts across time and service seams. Conflating them in an optional development plugin would leave production history vulnerable; trying to express both through TypeScript readonly types would not create a runtime boundary or describe relational rules. +The session log needs two different protections: immutable ownership of each stored fact, and checks for relationships among facts across time and service contracts. Conflating them in an optional development plugin would leave production history vulnerable; trying to express both through TypeScript readonly types would not create a runtime boundary or describe relational rules. The session log is the durable source of truth for replay, request reconstruction, persistence, and user-visible history. Code outside the session package must be able to inspect that history without retaining a reference that can rewrite it later, and inputs accepted from callers must not remain connected to caller-owned mutable objects. diff --git a/.agents/notes/implemented/architecture/2026-06-11-dev-invariants-over-deep-readonly.zh.md b/.agents/notes/implemented/architecture/2026-06-11-dev-invariants-over-deep-readonly.zh.md index ade3e20adb..38a19ee7dd 100644 --- a/.agents/notes/implemented/architecture/2026-06-11-dev-invariants-over-deep-readonly.zh.md +++ b/.agents/notes/implemented/architecture/2026-06-11-dev-invariants-over-deep-readonly.zh.md @@ -6,7 +6,7 @@ Status: implemented ## 问题 -会话日志需要两种不同的保护：对每条已存储事实的不可变所有权，以及对跨时间和服务 seam 的事实之间关系的检查。如果将二者混为一个可选的开发插件，生产环境的历史记录将失去保护；如果试图通过 TypeScript readonly 类型同时表达两者，既无法建立运行时边界，也无法描述关系规则。 +会话日志需要两种不同的保护：对每条已存储事实的不可变所有权，以及对跨时间和服务约定的事实之间关系的检查。如果将二者混为一个可选的开发插件，生产环境的历史记录将失去保护；如果试图通过 TypeScript readonly 类型同时表达两者，既无法建立运行时边界，也无法描述关系规则。 会话日志是回放、请求重建、持久化与用户可见历史的持久真源。会话包外部的代码必须能检视历史，但不能保留一个可在之后改写历史的引用；从调用方接受的输入也不能继续连接到调用方拥有的可变对象。 diff --git a/.agents/notes/implemented/architecture/2026-06-11-event-sourced-sessions.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-11-event-sourced-sessions.i18n.yaml index 0eb64b3107..a061e142cb 100644 --- a/.agents/notes/implemented/architecture/2026-06-11-event-sourced-sessions.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-06-11-event-sourced-sessions.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-06-11-event-sourced-sessions.md -2026-06-11-event-sourced-sessions.md: 01f9628c1cfc000aca8654caf5edeff09411fdcc -2026-06-11-event-sourced-sessions.zh.md: 5de230de9e9f1303943b43f6fdeefaf8264aa3bf +2026-06-11-event-sourced-sessions.md: 1303ee843cd5f9e02eae7a1f9bc51594be4bb407 +2026-06-11-event-sourced-sessions.zh.md: d1800ab3820ba5fc60723d6851fe71eded38134f diff --git a/.agents/notes/implemented/architecture/2026-06-11-event-sourced-sessions.md b/.agents/notes/implemented/architecture/2026-06-11-event-sourced-sessions.md index 01f9628c1c..1303ee843c 100644 --- a/.agents/notes/implemented/architecture/2026-06-11-event-sourced-sessions.md +++ b/.agents/notes/implemented/architecture/2026-06-11-event-sourced-sessions.md @@ -25,4 +25,4 @@ Ordering contract: the loop claims inbox messages before `agent/pre-step`, opens - Replay, trace, and telemetry are structurally guaranteed, not bolted on. - Persistence stays a plugin concern; the in-memory store ships in dsh-session. - The event vocabulary is merge-extensible (plugins add e.g. compaction events); [session persistence](2026-06-14-session-persistence.md) froze its shape once the log became durable. -- Derivation cost grows with log length — compaction (future plugin) is the intended mitigation, not log mutation. +- Derivation cost grows with log length — compaction (dsh-compact) is the intended mitigation, not log mutation. diff --git a/.agents/notes/implemented/architecture/2026-06-11-event-sourced-sessions.zh.md b/.agents/notes/implemented/architecture/2026-06-11-event-sourced-sessions.zh.md index 5de230de9e..d1800ab382 100644 --- a/.agents/notes/implemented/architecture/2026-06-11-event-sourced-sessions.zh.md +++ b/.agents/notes/implemented/architecture/2026-06-11-event-sourced-sessions.zh.md @@ -25,4 +25,4 @@ MVP 要求严格的基于事件的追踪，以及完全可回放的会话（严 - 回放、追踪与遥测在结构上得到保证，而非事后附加。 - 持久化仍是插件关注点；内存存储随 dsh-session 一起提供。 - 事件词汇可通过合并扩展（插件可添加如压缩（compaction）事件）；[会话持久化](2026-06-14-session-persistence.md)在日志具备持久性后固定了其结构。 -- 派生成本随日志长度增长，压缩（未来插件）是预期的缓解手段，而非日志变更。 +- 派生成本随日志长度增长，压缩（dsh-compact）是预期的缓解手段，而非日志变更。 diff --git a/.agents/notes/implemented/architecture/2026-06-11-microkernel-event-taxonomy.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-11-microkernel-event-taxonomy.i18n.yaml index 5a5aa0eaea..6c3244e519 100644 --- a/.agents/notes/implemented/architecture/2026-06-11-microkernel-event-taxonomy.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-06-11-microkernel-event-taxonomy.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-06-11-microkernel-event-taxonomy.md -2026-06-11-microkernel-event-taxonomy.md: fe6c242acbc0b64123711a17a528f35c02d91087 -2026-06-11-microkernel-event-taxonomy.zh.md: aa3db53d640145836817f9835a30c69815f70d23 +2026-06-11-microkernel-event-taxonomy.md: 6cacbc30f29c863de0f8ddfa4df7251a64bc80ca +2026-06-11-microkernel-event-taxonomy.zh.md: 40edfa1ada0c11395e8ff29e0abfcb0c38de096a diff --git a/.agents/notes/implemented/architecture/2026-06-11-microkernel-event-taxonomy.md b/.agents/notes/implemented/architecture/2026-06-11-microkernel-event-taxonomy.md index fe6c242acb..6cacbc30f2 100644 --- a/.agents/notes/implemented/architecture/2026-06-11-microkernel-event-taxonomy.md +++ b/.agents/notes/implemented/architecture/2026-06-11-microkernel-event-taxonomy.md @@ -10,14 +10,14 @@ The product principle is "everything is a plugin": hooks, /goal, /loop, dynamic ## Decision -Pure Cordis event taxonomy. The loop's extension seams are typed events with deliberate dispatch modes: +Pure Cordis event taxonomy. The loop's extension points are typed events with deliberate dispatch modes: - **waterfall** (around-middleware) where plugins transform, short-circuit, recover, or wrap: `agent/pre-step`, `agent/request`, `agent/request-error`, `tools/pre-execute`, `tools/execute`, `tools/post-execute`, `llm/stream`, `system-prompt/assemble`. - **serial** (awaited in listener order) for ordered checkpoints such as `agent/turn-stopping`. - **parallel** (awaited fan-out) where every listener must get an independent chance: the `session/flush` durability checkpoint. - **emit** (synchronous fire-and-forget) for notifications: inbox transitions, lifecycle, errors, and the contained immutable `tools/result` observation. Durable session events own turn and step boundaries. -The event vocabulary lives in interface packages (dsh-agent declares the agent/* events); `@deepseek-ai/dsh-agent-loop` is the only concrete loop plugin and is itself swappable — nothing outside it may depend on it. +The event vocabulary lives in contract packages (`dsh-agent` declares the `agent/*` events); `@deepseek-ai/dsh-agent-loop` is the only concrete loop plugin and is itself swappable — nothing outside it may depend on it. ## Alternatives considered @@ -28,4 +28,4 @@ The event vocabulary lives in interface packages (dsh-agent declares the agent/* - Every MVP feature maps to a listener (the [feature → mechanism map](../../../../docs/cookbook/extension-cookbook.md#the-feature--mechanism-map) is the proof obligation, kept current). - HMR and disposal come free: listeners and registrations are Cordis effects. - Waterfall semantics (call `next()` or short-circuit) are non-obvious and must be taught — documented in AGENTS.md and covered by composition tests. -- The loop must be defensive: plugin exceptions are contained at turn level, steering from any seam is never stranded (regression-tested). +- The loop must be defensive: plugin exceptions are contained at turn level, steering from any extension point is never stranded (regression-tested). diff --git a/.agents/notes/implemented/architecture/2026-06-11-microkernel-event-taxonomy.zh.md b/.agents/notes/implemented/architecture/2026-06-11-microkernel-event-taxonomy.zh.md index aa3db53d64..40edfa1ada 100644 --- a/.agents/notes/implemented/architecture/2026-06-11-microkernel-event-taxonomy.zh.md +++ b/.agents/notes/implemented/architecture/2026-06-11-microkernel-event-taxonomy.zh.md @@ -10,14 +10,14 @@ Status: implemented ## 决策 -纯 Cordis 事件分类体系。agent loop（智能体循环）的扩展 seam 是带类型的事件，具有明确的分发模式： +纯 Cordis 事件分类体系。agent loop（智能体循环）的扩展点是带类型的事件，具有明确的分发模式： - **waterfall（瀑布式事件）**（around-middleware）：插件可变换、短路、恢复或包装：`agent/pre-step`、`agent/request`、`agent/request-error`、`tools/pre-execute`、`tools/execute`、`tools/post-execute`、`llm/stream`、`system-prompt/assemble`。 - **serial**（按监听器顺序依次 await）：用于 `agent/turn-stopping` 等有序检查点。 - **parallel**（await 扇出）：每个监听器都必须获得独立执行的机会：`session/flush` 持久性检查点。 - **emit**（同步 fire-and-forget）：用于通知：inbox 转换、生命周期、错误，以及受错误隔离的 `tools/result` 观测；该观测接收不可变的最终结果。轮次与步骤边界由持久会话事件拥有。 -事件词汇定义在接口包中（dsh-agent 声明 agent/* 事件）；`@deepseek-ai/dsh-agent-loop` 是唯一的具体循环插件，且自身可替换——外部不得依赖它。 +事件词汇定义在约定包中（`dsh-agent` 声明 `agent/*` 事件）；`@deepseek-ai/dsh-agent-loop` 是唯一的具体循环插件，且自身可替换——外部不得依赖它。 ## 曾考虑的替代方案 @@ -28,4 +28,4 @@ Status: implemented - 每个 MVP 功能都映射到一个监听器（[功能→机制映射](../../../../docs/cookbook/extension-cookbook.md#the-feature--mechanism-map)是证明义务，保持更新）。 - HMR 与 dispose 无需额外工作：监听器和注册均为 Cordis effect。 - waterfall 语义（调用 `next()` 或短路）不直观，需要教学——在 AGENTS.md 中记录，并由组合测试覆盖。 -- 循环必须具备防御性：插件异常在轮次级别被隔离，任何 seam 发出的 steering（中途引导）永远不会被搁置（有回归测试保障）。 +- 循环必须具备防御性：插件异常在轮次级别被隔离，任何扩展点发出的 steering（中途引导）永远不会被搁置（有回归测试保障）。 diff --git a/.agents/notes/implemented/architecture/2026-06-11-runtime-arg-validation.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-11-runtime-arg-validation.i18n.yaml index 0697332171..260604acc4 100644 --- a/.agents/notes/implemented/architecture/2026-06-11-runtime-arg-validation.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-06-11-runtime-arg-validation.i18n.yaml @@ -1,6 +1,6 @@ # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: -# pnpm run verify-translation-pairing --write -2026-06-11-runtime-arg-validation.md: e0bca0ff24c5adc7ca58007932dff6580694b01d -2026-06-11-runtime-arg-validation.zh.md: 09958147766b4015d6bebf786c4947b9d2941f74 +# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-06-11-runtime-arg-validation.md +2026-06-11-runtime-arg-validation.md: 520823c76f147205805d306e97b5461f38b84c35 +2026-06-11-runtime-arg-validation.zh.md: ccb9b50d8b8a932d17516e579a5364321b64577b diff --git a/.agents/notes/implemented/architecture/2026-06-11-runtime-arg-validation.md b/.agents/notes/implemented/architecture/2026-06-11-runtime-arg-validation.md index e0bca0ff24..520823c76f 100644 --- a/.agents/notes/implemented/architecture/2026-06-11-runtime-arg-validation.md +++ b/.agents/notes/implemented/architecture/2026-06-11-runtime-arg-validation.md @@ -18,7 +18,7 @@ The validator and compiler therefore share exact semantics: the implicit paramet - The model gets actionable feedback on its own malformed calls instead of an opaque crash, closing the gap between `InferArgs`'s promise and runtime reality. - The validator and `InferArgs` must stay in agreement; [a property test](../testing/2026-06-11-property-based-testing.md) generates args satisfying a spec and asserts they pass `validateArgs` (with targeted corruptions rejected), closing that drift risk mechanically. -- `ToolArgsError` is a plain `Error` with a `code` field for now; if a harness-wide error taxonomy lands it becomes a subclass without changing callers that read `.message`. +- `ToolArgsError` subclasses `HarnessError` from the [structured error taxonomy](2026-06-11-structured-error-taxonomy.md), keeping its `code` field; callers that read `.message` are unaffected by the hierarchy. - Validation cost is negligible next to a model call. diff --git a/.agents/notes/implemented/architecture/2026-06-11-runtime-arg-validation.zh.md b/.agents/notes/implemented/architecture/2026-06-11-runtime-arg-validation.zh.md index 0995814776..ccb9b50d8b 100644 --- a/.agents/notes/implemented/architecture/2026-06-11-runtime-arg-validation.zh.md +++ b/.agents/notes/implemented/architecture/2026-06-11-runtime-arg-validation.zh.md @@ -6,19 +6,19 @@ Status: implemented ## 问题 -`defineTool`（[统一 schema DSL](2026-07-20-unified-json-value-schema-dsl.md)）为工具作者的 `execute(args)` 提供了经 `InferArgs` 映射的类型化参数。但该类型只是对运行时值的编译期声明，而这个值实际上是模型生成的 JSON：没有任何机制强制模型遵守 schema，因此畸形调用（缺少必需键、声明为数字的位置传入字符串，或字面量超出声明的集合）会以「仅名义类型化」的状态到达 `execute`。工具函数体随后要么在错误形状上崩溃，要么静默地行为异常。 +`defineTool`（[统一 schema DSL](2026-07-20-unified-json-value-schema-dsl.md)）为工具作者的 `execute(args)` 提供了经 `InferArgs` 映射的类型化参数。但该类型只是对运行时值的编译期声明，而这个值实际上是模型生成的 JSON：没有任何机制强制模型遵守 schema，因此畸形调用（缺少必需键、声明为数字的位置传入字符串，或字面量超出声明的集合）会以「仅在名义上类型化」的状态到达 `execute`。工具函数体随后要么在错误形状上崩溃，要么静默地行为异常。 ## 决策 `validateArgs(spec, args): string[]` 编译 `ParameterSchemaSpec`，并委托共享的 `validateJsonSchemaValue()` 遍历器，对格式正确的声明返回可读的违规列表。`defineTool` 在定义时对编译后的参数 schema 创建快照，并在调用类型化函数体之前执行校验；存在违规时会抛出 `ToolArgsError`（`INVALID_ARGS`），注册表将其作为模型可据以修正的错误结果返回。 -校验器与编译器因此共享完全一致的语义：隐式参数根是开放对象；必需键仅来自 `required: true`；默认值仍是注解；显式嵌套对象遵循其声明的开放性；数组通过 `items` 递归；标量字面量约束保证类型正确；`oneOf` 仅在恰好一个分支匹配时才接受。原始注册的工具自行负责输入校验。 +校验器与编译器因此共享完全一致的语义：隐式参数根是开放对象；必需键仅来自 `required: true`；默认值仍是注解；显式嵌套对象遵循其声明的开放性；数组通过 `items` 递归；标量字面量约束保证类型正确；`oneOf` 仅在恰好一个分支匹配时才接受。直接注册的工具自行负责输入校验。 ## 后果 - 模型在自身畸形调用上获得可操作的反馈，而非不透明的崩溃，弥合了 `InferArgs` 的承诺与运行时现实之间的鸿沟。 - 校验器与 `InferArgs` 必须保持一致；一项[属性测试](../testing/2026-06-11-property-based-testing.md)生成满足 spec 的参数并断言它们通过 `validateArgs`（同时断言定向破坏的参数被拒绝），以机械方式封堵漂移风险。 -- `ToolArgsError` 目前是带 `code` 字段的普通 `Error`；如果日后引入 harness 级别的错误分类体系，它将变为子类，但不影响读取 `.message` 的调用方。 +- `ToolArgsError` 是[结构化错误分类体系](2026-06-11-structured-error-taxonomy.md)中 `HarnessError` 的子类，保留其 `code` 字段；读取 `.message` 的调用方不受该层级结构影响。 - 校验开销相对于一次模型调用可忽略不计。 diff --git a/.agents/notes/implemented/architecture/2026-06-13-capability-seams.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-13-capability-seams.i18n.yaml index 2a310c8172..ccf15a5c1e 100644 --- a/.agents/notes/implemented/architecture/2026-06-13-capability-seams.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-06-13-capability-seams.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-06-13-capability-seams.md -2026-06-13-capability-seams.md: 7c755dced7825d2831acc0901f6412b8e5afe95a -2026-06-13-capability-seams.zh.md: 31d20bb15f91533ab3c09d337a3cb11f812dbeb4 +2026-06-13-capability-seams.md: ca5071cff1b26ba3b89537a73f40d7ecbde4b2bb +2026-06-13-capability-seams.zh.md: 7790124b980e0525705c2db398802ea6a418685a diff --git a/.agents/notes/implemented/architecture/2026-06-13-capability-seams.md b/.agents/notes/implemented/architecture/2026-06-13-capability-seams.md index 7c755dced7..ca5071cff1 100644 --- a/.agents/notes/implemented/architecture/2026-06-13-capability-seams.md +++ b/.agents/notes/implemented/architecture/2026-06-13-capability-seams.md @@ -1,4 +1,4 @@ -# Agent Note: Capability seams — interface / implementation / consumer split +# Agent Note: Capability seams — Service Definition / Service provider / Consumer roles Status: implemented @@ -12,21 +12,25 @@ This is distinct from "who provides vs. needs a capability at runtime", which Co ## Decision -A swappable capability is **three packages**: +A swappable capability has **three roles**: -1. **Interface** — an abstract service + the vocabulary types, owning the `ctx.` and depending only on its vocabulary dependencies (e.g. `dsh-bash`: `BashExecutor`, `BashRunResult`, `BashProcess`). -2. **Implementation** — a concrete subclass loaded as a plugin (e.g. `dsh-bash-local`: subprocesses, process-group kills, spill-file truncation). Sandboxed/remote backends are sibling packages implementing the same interface. -3. **Consumer** — what the model and plugins see (e.g. `dsh-tool-bash`: the `bash` schema, with background handles registered into the generic task runtime). Consumers `inject` the interface key and never import implementation types. +1. **Service Definition** — the Cordis `Service` and vocabulary types owning `ctx.` and depending only on the vocabulary the contract needs (e.g. `dsh-bash`: `BashExecutor`, `BashRunResult`, `BashProcess`). A definition may be an abstract class or a concrete registry service; it is never a TypeScript `interface`. +2. **Service provider** — a plugin that supplies or registers an implementation (e.g. `dsh-bash-local`: subprocesses, process-group kills, spill-file truncation). Sandboxed and remote providers are sibling packages implementing or registering against the same Service Definition. +3. **Consumer** — what the model and plugins program against (e.g. `dsh-tool-bash`: the `bash` schema, with background handles registered into the generic task runtime). Consumers inject the service key and never import provider-specific types. -Implementation and consumer then evolve independently: a sandboxed executor replaces `dsh-bash-local` without touching a tool schema. +Service providers and Consumers then evolve independently: a sandboxed executor replaces `dsh-bash-local` without touching a tool schema. -The split is not mandatory when the parts are genuinely one concern: the LLM seam folds interface + consumer into `dsh-llm` (the consumer is the loop itself, not a swappable schema surface) with adapters as the implementation packages. Don't split preemptively — a capability with one conceivable implementation and one consumer stays one package until a second appears. +Roles normally use separate packages when they evolve independently, but the split is not mandatory when the roles are genuinely one concern: the LLM seam folds Service Definition and Consumer into `dsh-llm` (the Consumer is the loop itself, not a swappable schema surface) with adapters as Service provider packages. Don't split preemptively — a capability with one conceivable provider and one Consumer stays one package until a second appears. + +## Terminology: "seam" names the trio, not the interface + +A **seam** is the whole capability — the three roles together: a **Service Definition** (the Cordis `Service` that owns `ctx.` and the vocabulary), one or more **Service providers**, and one or more **Consumers**. `packages/bash` is the canonical example — `dsh-bash` / `dsh-bash-local`+`dsh-bash-sandbox` / `dsh-tool-bash`. A package may own multiple roles, but one role alone is not the seam. The term "seam" is reserved for this complete capability; name a constituent by its role, class, service, contract, or extension point. The [glossary](../../../../docs/glossary.md#capability-seam) is the canonical entry. ## Alternatives considered -- **One combined package** — rejected because it recouples the three rates of change the split exists to separate (the whole point). -- **`@cordisjs/plugin-capability`** — a different axis entirely: it is a permission/capability-*security* service (named permissions with inheritance, tested against a session via `ctx.capability.test`), a candidate for the deferred permissions/sandbox work on the `tools/pre-execute` deny/ask seam, NOT a mechanism for swapping implementations. Confusing the two ("capability") is the trap this Agent Note names. +- **Always combine the roles** — rejected because it recouples independently changing Service Definitions, providers, and Consumers. +- **`@cordisjs/plugin-capability`** — a different axis entirely: it is a permission/capability-*security* service (named permissions with inheritance, tested against a session via `ctx.capability.test`), a candidate for the deferred permissions/sandbox work on the `tools/pre-execute` deny/ask gate, NOT a mechanism for swapping implementations. Confusing the two ("capability") is the trap this Agent Note names. ## Consequences -More packages and more boilerplate per capability (a `package.json`/`tsconfig`/README trio, the inject wiring). Bought: implementations and consumers ship and version independently, and a new backend never risks the model-facing contract. The rule is documented in [AGENTS.md](../../../../AGENTS.md) § Conventions ("Capability seams are three packages") and [architecture.md](../../../../docs/architecture.md) § "Capability seams"; the bash trio is the reference template. When to fold vs. split is a judgment call the architecture doc spells out — this Agent Note records *why* the default is to split. +Separating roles adds packages and boilerplate (`package.json`, `tsconfig`, README, and injection wiring). In return, Service providers and Consumers ship and version independently, and a new backend never risks the model-facing contract. [AGENTS.md](../../../../AGENTS.md) and [architecture.md](../../../../docs/architecture.md) carry the rule; the bash trio is the reference template. This Agent Note records why independently changing roles normally split while genuinely shared concerns may remain folded. diff --git a/.agents/notes/implemented/architecture/2026-06-13-capability-seams.zh.md b/.agents/notes/implemented/architecture/2026-06-13-capability-seams.zh.md index 31d20bb15f..7790124b98 100644 --- a/.agents/notes/implemented/architecture/2026-06-13-capability-seams.zh.md +++ b/.agents/notes/implemented/architecture/2026-06-13-capability-seams.zh.md @@ -1,4 +1,4 @@ -# Agent Note: 能力 seam——接口／实现／消费方三分 +# Agent Note: 能力 seam——Service Definition / Service provider / Consumer 角色 Status: implemented @@ -12,21 +12,25 @@ harness 具有可替换的能力：当前是 bash 执行，未来会有沙箱化 ## 决策 -一项可替换的能力由**三个包**构成： +一项可替换的能力包含**三个角色**： -1. **接口**——一个抽象服务加词汇类型，拥有 `ctx.`，仅依赖其词汇依赖（例如 `dsh-bash`：`BashExecutor`、`BashRunResult`、`BashProcess`）。 -2. **实现**——一个具体子类，以插件形式加载（例如 `dsh-bash-local`：子进程、进程组 kill、spill 文件截断）。沙箱化／远程后端是实现同一接口的兄弟包。 -3. **消费方**——模型和插件看到的内容（例如 `dsh-tool-bash`：`bash` schema，后台句柄注册到通用任务运行时）。消费方 `inject` 接口键，从不导入实现类型。 +1. **Service Definition**——拥有 `ctx.` 的 Cordis `Service` 和词汇类型，仅依赖约定所需的词汇（例如 `dsh-bash`：`BashExecutor`、`BashRunResult`、`BashProcess`）。Service Definition 可以是抽象类，也可以是具体的注册表服务；绝不是 TypeScript `interface`。 +2. **Service provider**——提供或注册实现的插件（例如 `dsh-bash-local`：子进程、进程组 kill、spill 文件截断）。沙箱化和远程 Service provider 是依据同一 Service Definition 实现或注册的兄弟包。 +3. **Consumer**——模型和插件编程所面向的内容（例如 `dsh-tool-bash`：`bash` schema，后台句柄注册到通用任务运行时）。Consumer 注入服务键，从不导入 Service provider 特有的类型。 -实现与消费方由此独立演进：沙箱化执行器替换 `dsh-bash-local` 时无需触碰任何工具 schema。 +Service provider 与 Consumer 由此独立演进：沙箱化执行器替换 `dsh-bash-local` 时无需触碰任何工具 schema。 -当各部分确实属于同一个关注点时，三分并非强制：LLM（大语言模型） seam 将接口 + 消费方合并为 `dsh-llm`（消费方是 agent loop（智能体循环）本身，而非可替换的 schema 接口），适配器作为实现包。不要预防性地拆分——如果一项能力只有一种可设想的实现和一个消费方，就保持为一个包，直到出现第二种实现或第二个消费方。 +当角色独立演进时，通常使用不同的包；但当各角色确实属于同一个关注点时，并非必须拆分：LLM（大语言模型） seam 将 Service Definition 和 Consumer 合并为 `dsh-llm`（Consumer 是 agent loop（智能体循环）本身，而非可替换的 schema 接口），适配器作为 Service provider 包。不要预防性地拆分——如果一项能力只有一种可设想的 Service provider 和一个 Consumer，就保持为一个包，直到出现第二个。 + +## 术语：seam 指三者组合，而非接口 + +一个 **seam** 是完整的能力——三个角色合在一起：**Service Definition**（拥有 `ctx.` 和词汇的 Cordis `Service`）、一个或多个 **Service provider**，以及一个或多个 **Consumer**。`packages/bash` 是规范范例——`dsh-bash` / `dsh-bash-local`+`dsh-bash-sandbox` / `dsh-tool-bash`。一个包可以承担多个角色，但单个角色本身不是 seam。「seam」一词严格保留给这种完整能力；命名其中一个组成部分时，应使用其角色、类、服务、约定或扩展点。[术语表](../../../../docs/glossary.md#capability-seam)是规范条目。 ## 曾考虑的替代方案 -- **单一合并包**：否决。因为它重新耦合了三分设计本要分离的三种变化速率（这正是拆分的意义所在）。 -- **`@cordisjs/plugin-capability`**：这是完全不同的维度。它是一个权限／能力*安全*服务（具名权限加继承，通过 `ctx.capability.test` 对会话进行检测），是延后的权限/沙箱工作（`tools/pre-execute` deny/ask seam）的候选方案，不是替换实现的机制。混淆这两个「能力」概念正是本 Agent Note 所指出的陷阱。 +- **始终合并各角色**：否决。因为它会重新耦合独立变化的 Service Definition、Service provider 和 Consumer。 +- **`@cordisjs/plugin-capability`**：这是完全不同的维度。它是一个权限／能力*安全*服务（具名权限加继承，通过 `ctx.capability.test` 对会话进行检测），是延后的权限/沙箱工作（`tools/pre-execute` deny/ask 门）的候选方案，不是替换实现的机制。混淆这两个「能力」概念正是本 Agent Note 所指出的陷阱。 ## 后果 -每项能力需要更多包和更多样板代码（一组 `package.json`/`tsconfig`/README，加上 inject 接线）。换来的是：实现与消费方独立发布和版本管理，新后端永远不会波及面向模型的约定。该规则记录在 [AGENTS.md](../../../../AGENTS.md) § Conventions（「Capability seams are three packages」）和 [architecture.md](../../../../docs/architecture.md) §「Capability seams」中；bash 三件套是参考模板。何时合并、何时拆分是一个判断问题，架构文档对此有详细说明——本 Agent Note 记录的是*为什么*默认选择拆分。 +分离角色会增加包和样板代码（`package.json`、`tsconfig`、README 和注入接线）。换来的是：Service provider 与 Consumer 独立发布和版本管理，新后端永远不会波及面向模型的约定。[AGENTS.md](../../../../AGENTS.md) 和 [architecture.md](../../../../docs/architecture.md) 载有这项规则；bash 三件套是参考模板。本 Agent Note 记录为什么独立变化的角色通常需要拆分，而确实共享的关注点可以保持合并。 diff --git a/.agents/notes/implemented/architecture/2026-06-14-session-persistence.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-14-session-persistence.i18n.yaml index bead51ff09..a28df36350 100644 --- a/.agents/notes/implemented/architecture/2026-06-14-session-persistence.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-06-14-session-persistence.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-06-14-session-persistence.md -2026-06-14-session-persistence.md: 00e129e57c7144fd62eec26f5854ee21dec4e964 -2026-06-14-session-persistence.zh.md: df03dce6bd978f10deb64b8d75ae0685dabab7cd +2026-06-14-session-persistence.md: 6961b8f3f4274587c2920fe2b2602aff5efe4afc +2026-06-14-session-persistence.zh.md: 58c8bb80a1f886c986fc5aa1a0ba6b7f263ad829 diff --git a/.agents/notes/implemented/architecture/2026-06-14-session-persistence.md b/.agents/notes/implemented/architecture/2026-06-14-session-persistence.md index 00e129e57c..6961b8f3f4 100644 --- a/.agents/notes/implemented/architecture/2026-06-14-session-persistence.md +++ b/.agents/notes/implemented/architecture/2026-06-14-session-persistence.md @@ -12,25 +12,25 @@ The [event-sourced model](2026-06-11-event-sourced-sessions.md) makes the append ## Decision -Persistence is an abstract **capability seam** ([capability seams](2026-06-13-capability-seams.md), the `dsh-bash` template), not loop or core logic: +Persistence is a **capability seam** with an abstract Service Definition ([capability seams](2026-06-13-capability-seams.md), the `dsh-bash` template), not loop or core logic: 1. **Interface** (`dsh-session-persistence`, `ctx.sessionPersistence`) — an abstract `SessionPersistence` service: `locate`/`create`/`append`/`prepare`/`load`/`inspect`/`readFrom`/`list`/`listSnapshots`. Its persisted unit IS the existing `SessionEvent` (`{ type, seq, time, data }`), reused verbatim — no conversion type. 2. **Implementation** (`dsh-session-persistence-jsonl`) — an append-only logical JSONL log per session: a `SessionHeader` line followed by storage records that losslessly represent the contiguous `SessionEvent` stream. Eligible `assistant/chunk` delta runs use packed rows by default; [checksummed Zstandard frames](2026-07-19-zstandard-jsonl-session-logs.md) are the default physical encoding, with raw lines configurable. -Key choices recorded here because they are durable, contested, and surprising: +Key durable, contested choices: - **The canonical durable log persists every `SessionEvent` losslessly, including `assistant/chunk`.** JSONL storage may encode a consecutive delta run as one packed row, but logical readers reconstruct the exact event boundaries, sequence numbers, and timestamps. `deriveMessages()` skips chunks, and a chunk-filtered rollout (Codex's `policy.rs`) is tempting — but `seq = log.length` and validation of `events[i].seq === i` require a *contiguous* logical log; filtering chunks out would leave holes and break both the contract and resume. A chunk-filtered projection is possible later as a derived view with its own renumbering, but it is NOT the canonical log. - **Append-only; a crashed turn is closed, never truncated.** Flushed events are never rewritten. The [semantic checkpoint policy](../bug-fix/2026-07-21-semantic-session-checkpoints.md) drains the request before model dispatch, a recorded top-level call before tool dispatch, and the complete response/result batch after a step; the loop drains the final turn boundary. Because one interrupted turn may contain substantial valid work, cold inspection preserves its contiguous, parseable events and adds risk-classified error results for unanswered assistant calls, a missing `step/end`, and `turn/end` with `{ kind: 'interrupted' }` to the in-memory logical view. `prepare` or `load` commits those closers before returning a recoverable view; the synthetic results keep resumed provider transcripts valid. Only an incomplete final record is discarded during committed repair; a parse error or sequence gap at or before the last real `turn/end` is corruption and makes the session unloadable. - **File backend canonical, DB backend a proven drop-in.** `SessionEvent` maps 1:1 onto a row `(session_id, seq, type, time, data)` — `append` is INSERT (in a transaction asserting the contiguous-seq contract), and reads use SELECT … ORDER BY seq. `dsh-session-persistence-sqlite` is exactly this: a `SessionPersistence` subclass with no interface change (opencode runs this exact shape on SQLite/WAL), and it passes the same `runPersistenceContract` suite as the JSONL backend — so the contract holds both backends to identical semantics (lazy materialization, logical interrupted-turn closure, single committed repair, contiguous-seq), expressed once over file bytes and once over rows. Its database carries a dedicated application id and monotonic schema version. A pristine file creates all tables and stamps both header values in one transaction; an unversioned file with any user-defined schema object or application identity, a foreign current-version identity, and every non-current version reject before journal-mode mutation. -- **Metadata is out-of-log.** Format version, cwd, and lineage are storage concerns, not replayable conversation state, so they live in a `SessionHeader` owned by `dsh-session` and attached to a `Session` via a new readonly `session.header` — never in `SessionEventMap`, never reaching `deriveMessages()`. `createdAt` is non-negative safe-integer Unix epoch milliseconds: live creation and persistence registration reject fractional values, JSONL validates the decoded header, and SQLite stores it in a strict `INTEGER` column. The alternative (a merge-extensible `session/meta` event as log line 0) was rejected: an in-log event would ride along with a seeded/forked session for free, but metadata is not replayable state, so the explicit out-of-log header seam is the cleaner cost. (The header was originally split into an immutable `SessionHeader` plus a mutable `SessionSummary` whose union was `SessionMeta`; the mutable summary was later removed as dead state — see [Drop the mutable session summary](../simplification/2026-06-19-drop-mutable-session-summary.md).) +- **Metadata is out-of-log.** Format version, cwd, and lineage are storage concerns, not replayable conversation state, so they live in a `SessionHeader` owned by `dsh-session` and attached to a `Session` via a new readonly `session.header` — never in `SessionEventMap`, never reaching `deriveMessages()`. `createdAt` is non-negative safe-integer Unix epoch milliseconds: live creation and persistence registration reject fractional values, JSONL validates the decoded header, and SQLite stores it in a strict `INTEGER` column. The alternative (a merge-extensible `session/meta` event as log line 0) was rejected: an in-log event would ride along with a seeded/forked session for free, but metadata is not replayable state, so the explicit out-of-log header boundary is the cleaner cost. (The header was originally split into an immutable `SessionHeader` plus a mutable `SessionSummary` whose union was `SessionMeta`; the mutable summary was later removed as dead state — see [Drop the mutable session summary](../simplification/2026-06-19-drop-mutable-session-summary.md).) - **`ctx.agents.create()` and `ctx.agents.resume()` are async factories; resume additionally crosses the persistence boundary.** `ctx.agents.resume({ resumeSessionId })` obtains the exact unpublished Session through `ctx.sessionPersistence.prepare()`, publishes it under the persisted id, and continues its projections. The [Session preparation decision](2026-08-05-session-preparation.md) owns reuse between history inspection and resume. The agent-loop does NOT hard-inject `sessionPersistence` (that would pend non-persistent demos forever); `resume` rejects with a clear error when it is absent. ## Alternatives considered Each key choice above records its rejected alternative where the choice is stated: a **chunk-filtered canonical log** (Codex's `policy.rs` shape) — breaks the contiguous-seq contract; **truncating a crashed turn** — silently destroys a long autonomous run's real work; an **in-log `session/meta` event as line 0** — metadata is not replayable state; **finite fractional `createdAt` values** — have no producer and diverge from integer Unix-millisecond storage and query columns; **adopting a non-pristine unversioned SQLite file** — can overwrite unrelated objects or identity; **hard-injecting `sessionPersistence` into the loop** — would pend non-persistent demos forever. -Format versioning: the header carries a `version`; cold reads reject any non-current version. The pre-release session format stays pinned at `SESSION_FORMAT_VERSION = 0` and carries no broad compatibility promise, while the coordinator may own an explicit narrow import upgrade when persisted user data requires it ([pre-identity message recovery](../bug-fix/2026-07-28-load-pre-identity-session-messages.md)). Stated honestly: append-only + flush is robust to partial trailing writes (tolerated during cold preparation) but not to fsync-less power loss mid-line; a DB/WAL backend is the stronger option later. +Format versioning: the header carries a `version`; cold reads reject any non-current version. The pre-release session format stays pinned at `SESSION_FORMAT_VERSION = 0` and carries no broad compatibility promise, while the coordinator may own an explicit narrow import upgrade when persisted user data requires it ([pre-identity message recovery](../bug-fix/2026-07-28-load-pre-identity-session-messages.md)). Append-only + flush is robust to partial trailing writes (tolerated during cold preparation) but not to fsync-less power loss mid-line; a DB/WAL backend is the stronger option there. ## Consequences -Two new packages and the metadata seam in `dsh-session` (`session.header`, the `create(id?, options?)` signature). Bought: durable resume/fork, a read/replay path, crash tolerance, and host-side session access over the existing event-sourced log, with the backend swappable behind one interface. The reusable `runPersistenceContract` suite holds every backend to the same append-only, contiguous-seq, lazy-materialization, logical-recovery, integer-metadata, and serializability semantics. Persisting the full logical log also settles event fidelity: every `assistant/chunk` survives exactly even when JSONL packs several into one storage row. SQLite initialization either commits its complete owned schema and header identity or leaves no partial schema to strand on the next open. +Two new packages and the metadata contract in `dsh-session` (`session.header`, the `create(id?, options?)` signature). Bought: durable resume/fork, a read/replay path, crash tolerance, and host-side session access over the existing event-sourced log, with the backend swappable behind one interface. The reusable `runPersistenceContract` suite holds every backend to the same append-only, contiguous-seq, lazy-materialization, logical-recovery, integer-metadata, and serializability semantics. Persisting the full logical log also settles event fidelity: every `assistant/chunk` survives exactly even when JSONL packs several into one storage row. SQLite initialization either commits its complete owned schema and header identity or leaves no partial schema to strand on the next open. diff --git a/.agents/notes/implemented/architecture/2026-06-14-session-persistence.zh.md b/.agents/notes/implemented/architecture/2026-06-14-session-persistence.zh.md index df03dce6bd..58c8bb80a1 100644 --- a/.agents/notes/implemented/architecture/2026-06-14-session-persistence.zh.md +++ b/.agents/notes/implemented/architecture/2026-06-14-session-persistence.zh.md @@ -12,25 +12,25 @@ Status: implemented ## 决策 -持久化是一个抽象的**能力 seam**（[能力 seam](2026-06-13-capability-seams.md)，`dsh-bash` 模板），而非循环或核心逻辑： +持久化是一个具有抽象 Service Definition 的**能力 seam**（[能力 seam](2026-06-13-capability-seams.md)，`dsh-bash` 模板），而非循环或核心逻辑： 1. **接口**（`dsh-session-persistence`，`ctx.sessionPersistence`）：一个抽象的 `SessionPersistence` 服务，提供 `locate`/`create`/`append`/`prepare`/`load`/`inspect`/`readFrom`/`list`/`listSnapshots`。其持久化单元就是现有的 `SessionEvent`（`{ type, seq, time, data }`），原样复用，无转换类型。 2. **实现**（`dsh-session-persistence-jsonl`）：每个会话一个仅追加的逻辑 JSONL 日志：先是一行 `SessionHeader`，随后是无损表示连续 `SessionEvent` 流的存储记录。符合条件的 `assistant/chunk` 增量连续段默认使用打包行；[带校验和的 Zstandard 帧](2026-07-19-zstandard-jsonl-session-logs.md)是默认物理编码，也可通过配置使用原始行。 -以下关键选择记录于此，因为它们长期有效、存在争议且出人意料： +长期有效、存在争议的关键选择： - **规范的持久日志无损保留每个 `SessionEvent`，包括 `assistant/chunk`。** JSONL 存储可以将一段连续的增量事件编码为一条打包行，但逻辑读取方会重建精确的事件边界、序号与时间戳。`deriveMessages()` 跳过分片，而过滤分片的方案（Codex 的 `policy.rs`）很有吸引力，但 `seq = log.length` 以及 `events[i].seq === i` 验证要求*连续*的逻辑日志；过滤掉分片会留下空洞，同时破坏约定和恢复功能。基于分片过滤的投影可以作为派生视图在后续实现（带有自己的重新编号），但它不是规范日志。 -- **仅追加；崩溃的轮次被关闭，而非截断。** 已刷写的事件永不被重写。[语义检查点策略](../bug-fix/2026-07-21-semantic-session-checkpoints.md)会在模型分发前排空请求、在工具分发前排空已记录的顶层调用，并在步骤结束后排空完整的响应/结果批次；循环则排空最终轮次边界。由于一个被中断的轮次可能包含大量有效工作，冷检查会保留其连续、可解析的事件，并在内存逻辑视图中为未应答的 assistant 调用添加按风险分类的错误结果、补一个缺失的 `step/end`，以及带 `{ kind: 'interrupted' }` 的 `turn/end`。`prepare` 或 `load` 在返回可恢复视图前提交这些收尾事件；合成结果保证恢复后的提供方 transcript（文本记录）仍然有效。只有不完整的最后一条记录会在提交修复时被丢弃；在最后一个真实 `turn/end` 处或之前出现解析错误或序号间隙，属于数据损坏，会使该会话不可加载。 -- **文件后端为规范实现，数据库后端为经过验证的直接替换。** `SessionEvent` 1:1 映射到一行 `(session_id, seq, type, time, data)`：`append` 是 INSERT（在一个断言连续 seq 约定成立的事务中），读取使用 SELECT … ORDER BY seq。`dsh-session-persistence-sqlite` 正是如此：一个 `SessionPersistence` 子类，接口无变化（opencode 在 SQLite/WAL 上运行的正是这个形状），且通过与 JSONL 后端相同的 `runPersistenceContract` 测试套件。该约定以相同的语义约束两个后端（惰性物化、逻辑关闭中断轮次、修复只提交一次、连续 seq），一次表达在文件字节上，一次表达在数据库行上。其数据库拥有专用的 application id 与单调递增的 schema 版本。系统会在一个事务中为全新文件创建所有表并写入这两个 header 值；未版本化文件若带有任何用户定义的 schema 对象或应用标识、当前版本文件若带有外部应用标识，以及任何非当前版本文件，都会在修改日志模式之前被拒绝。 -- **元数据在日志之外。** 格式版本、cwd 和谱系是存储关注点，不是可回放的对话状态，因此它们存放在 `dsh-session` 拥有的 `SessionHeader` 中，并通过新的只读属性 `session.header` 附加到 `Session` 上——永远不进入 `SessionEventMap`，永远不到达 `deriveMessages()`。`createdAt` 是以 Unix epoch 毫秒表示的非负安全整数：运行时创建和持久化注册会拒绝小数值，JSONL 会验证解码后的 header，SQLite 则将其存入严格的 `INTEGER` 列。替代方案（一个可合并扩展的 `session/meta` 事件作为日志第 0 行）被否决：日志内事件会自然随 seed/fork 的会话携带，但元数据不是可回放状态，因此显式的日志外 header seam 是更清晰的取舍。（header 最初被拆分为不可变的 `SessionHeader` 加可变的 `SessionSummary`，二者的联合类型为 `SessionMeta`；可变 summary 后来因属于死状态而被移除——见 [移除可变会话摘要](../simplification/2026-06-19-drop-mutable-session-summary.md)。） -- **`ctx.agents.create()` 和 `ctx.agents.resume()` 是异步工厂；恢复还跨越持久化边界。** `ctx.agents.resume({ resumeSessionId })` 通过 `ctx.sessionPersistence.prepare()` 取得原本那个尚未发布的会话，以持久化 id 发布该会话，并延续其投影。[会话准备决策](2026-08-05-session-preparation.md)负责历史检查与恢复之间的复用。agent loop（智能体循环）不会硬注入 `sessionPersistence`（那样会让非持久化的演示永远挂起）；当它不存在时，`resume` 会以明确的错误拒绝。 +- **仅追加；崩溃的轮次被关闭，而非截断。** 已刷写的事件永不被重写。[语义检查点策略](../bug-fix/2026-07-21-semantic-session-checkpoints.md)会在模型分发前排空请求、在工具分发前排空已记录的顶层调用，并在步骤结束后排空完整的响应/结果批次；循环则排空最终轮次边界。由于一个被中断的轮次可能包含大量有效工作，冷检查会保留其连续、可解析的事件，并在内存逻辑视图中为未应答的 assistant 调用添加按风险分类的错误结果、补一个缺失的 `step/end`，以及带 `{ kind: 'interrupted' }` 的 `turn/end`。`prepare` 或 `load` 在返回可恢复视图前提交这些 closer；合成结果保证恢复后的提供方 transcript（文本记录）仍然有效。只有不完整的最后一条记录会在提交修复时被丢弃；在最后一个真实 `turn/end` 处或之前出现解析错误或序号间隙，属于数据损坏，会使该会话不可加载。 +- **文件后端为规范实现，数据库后端为经过验证的直接替换。** `SessionEvent` 1:1 映射到一行 `(session_id, seq, type, time, data)`：`append` 是 INSERT（在一个断言连续 seq 约定的事务中），读取使用 SELECT … ORDER BY seq。`dsh-session-persistence-sqlite` 正是如此：一个 `SessionPersistence` 子类，接口无变化（opencode 在 SQLite/WAL 上运行的正是这个形状），且通过与 JSONL 后端相同的 `runPersistenceContract` 测试套件。该约定以相同的语义约束两个后端（惰性物化、逻辑关闭中断轮次、修复只提交一次、连续 seq），一次表达在文件字节上，一次表达在数据库行上。其数据库拥有专用的 application id 与单调递增的 schema 版本。系统会在一个事务中为全新文件创建所有表并写入这两个 header 值；未版本化文件若带有任何用户定义的 schema 对象或应用标识、当前版本文件若带有外部应用标识，以及任何非当前版本文件，都会在修改日志模式之前被拒绝。 +- **元数据在日志之外。** 格式版本、cwd 和谱系是存储关注点，不是可回放的对话状态，因此它们存放在 `dsh-session` 拥有的 `SessionHeader` 中，并通过新的只读属性 `session.header` 附加到 `Session` 上——永远不进入 `SessionEventMap`，永远不到达 `deriveMessages()`。`createdAt` 是以 Unix epoch 毫秒表示的非负安全整数：运行时创建和持久化注册会拒绝小数值，JSONL 会验证解码后的 header，SQLite 则将其存入严格的 `INTEGER` 列。替代方案（一个可合并扩展的 `session/meta` 事件作为日志第 0 行）被否决：日志内事件会自然随 seed/fork 的会话携带，但元数据不是可回放状态，因此显式的日志外 header 边界是更清晰的取舍。（header 最初被拆分为不可变的 `SessionHeader` 加可变的 `SessionSummary`，二者的联合类型为 `SessionMeta`；可变 summary 后来因属于死状态而被移除——见 [移除可变会话摘要](../simplification/2026-06-19-drop-mutable-session-summary.md)。） +- **`ctx.agents.create()` 和 `ctx.agents.resume()` 是异步工厂；恢复还跨越持久化边界。** `ctx.agents.resume({ resumeSessionId })` 通过 `ctx.sessionPersistence.prepare()` 取得精确的未发布 Session，以持久化 id 发布它，并继续其投影。[Session 准备阶段决策](2026-08-05-session-preparation.md)定义历史检查与恢复之间的复用。agent loop（智能体循环）不会硬注入 `sessionPersistence`（那样会让非持久化的演示永远挂起）；当它不存在时，`resume` 会以明确的错误拒绝。 ## 曾考虑的替代方案 上述每个关键选择都在陈述处记录了被否决的替代方案：**过滤分片的规范日志**（Codex 的 `policy.rs` 形式）破坏连续 seq 约定；**截断崩溃的轮次**会静默销毁长时间自主运行中的真实工作；**日志内 `session/meta` 事件作为第 0 行**——元数据不是可回放状态；**有限的非整数 `createdAt` 值**没有生产方，且与整数 Unix 毫秒存储及查询列不一致；**接受非全新的未版本化 SQLite 文件**可能覆盖无关对象或应用标识；**将 `sessionPersistence` 硬注入循环**会让非持久化的演示永远挂起。 -格式版本控制：header 携带一个 `version`；冷读取拒绝任何非当前版本。预发布阶段的会话格式仍固定为 `SESSION_FORMAT_VERSION = 0`，不承诺广泛兼容；当持久化用户数据确有需要时，协调器可以负责显式且范围受限的导入升级（[消息标识机制引入前的消息恢复](../bug-fix/2026-07-28-load-pre-identity-session-messages.md)）。坦率地说：仅追加 + 刷写对部分尾部写入是健壮的（冷准备时容忍），但对行写入中途的无 fsync 断电不健壮；数据库/WAL 后端是后续更强的选项。 +格式版本控制：header 携带一个 `version`；冷读取拒绝任何非当前版本。预发布阶段的会话格式仍固定为 `SESSION_FORMAT_VERSION = 0`，不承诺广泛兼容；当持久化用户数据确有需要时，协调器可以负责显式且范围受限的导入升级（[消息标识机制引入前的消息恢复](../bug-fix/2026-07-28-load-pre-identity-session-messages.md)）。仅追加 + 刷写对部分尾部写入是健壮的（冷准备时容忍），但对行写入中途的无 fsync 断电不健壮；数据库/WAL 后端是该场景下更强的选项。 ## 后果 -新增两个包，以及 `dsh-session` 中的元数据 seam（`session.header`，`create(id?, options?)` 签名）。收益：持久恢复/fork、读取/回放路径、崩溃容忍，以及基于现有事件溯源日志的宿主侧会话访问，后端可在同一接口下替换。可复用的 `runPersistenceContract` 测试套件以相同的仅追加、连续 seq、惰性物化、逻辑恢复、整数元数据与可序列化语义约束每个后端。持久化完整的逻辑日志还确定了事件保真度：即使 JSONL 将多个 `assistant/chunk` 打包到一条存储行中，每个事件也会精确保留。SQLite 初始化要么提交完整的自有 schema 与 header 标识，要么不留下任何会使下次打开受阻的部分 schema。 +新增两个包，以及 `dsh-session` 中的元数据约定（`session.header`，`create(id?, options?)` 签名）。收益：持久恢复/fork、读取/回放路径、崩溃容忍，以及基于现有事件溯源日志的宿主侧会话访问，后端可在同一接口下替换。可复用的 `runPersistenceContract` 测试套件以相同的仅追加、连续 seq、惰性物化、逻辑恢复、整数元数据与可序列化语义约束每个后端。持久化完整的逻辑日志还确定了事件保真度：即使 JSONL 将多个 `assistant/chunk` 打包到一条存储行中，每个事件也会精确保留。SQLite 初始化要么提交完整的自有 schema 与 header 标识，要么不留下任何会使下次打开受阻的部分 schema。 diff --git a/.agents/notes/implemented/architecture/2026-06-17-filesystem-capability-seam.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-17-filesystem-capability-seam.i18n.yaml index 4511cefb31..68bcd74197 100644 --- a/.agents/notes/implemented/architecture/2026-06-17-filesystem-capability-seam.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-06-17-filesystem-capability-seam.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-06-17-filesystem-capability-seam.md -2026-06-17-filesystem-capability-seam.md: 7436d2a9402c76f17c7d6571eb489a86e550ebfb -2026-06-17-filesystem-capability-seam.zh.md: a96d513d7f4fa793ebb3427e3f7b290862d0d5e9 +2026-06-17-filesystem-capability-seam.md: 928ad4926e46ed5b6b35552b75882d565d8ad6db +2026-06-17-filesystem-capability-seam.zh.md: 02af77a3cc291eeba2be966a4bc08aa006675e7d diff --git a/.agents/notes/implemented/architecture/2026-06-17-filesystem-capability-seam.md b/.agents/notes/implemented/architecture/2026-06-17-filesystem-capability-seam.md index 7436d2a940..928ad4926e 100644 --- a/.agents/notes/implemented/architecture/2026-06-17-filesystem-capability-seam.md +++ b/.agents/notes/implemented/architecture/2026-06-17-filesystem-capability-seam.md @@ -6,7 +6,7 @@ English | [中文](2026-06-17-filesystem-capability-seam.zh.md) ## Problem -The harness has a concrete `bash` capability seam (`dsh-bash` / `dsh-bash-local` / `dsh-tool-bash`), but filesystem operations are about to be added as model-facing tools without an equivalent seam. If `read`, `write`, and `edit` directly use `node:fs`, the model-facing tool package will own filesystem execution policy, local path resolution, atomic write behavior, text decoding, symlink behavior, and edit semantics all at once. +The harness has a concrete `bash` capability seam (`dsh-bash` / `dsh-bash-local` / `dsh-tool-bash`), but filesystem operations were about to land as model-facing tools without an equivalent seam. If `read`, `write`, and `edit` directly used `node:fs`, the model-facing tool package would own filesystem execution policy, local path resolution, atomic write behavior, text decoding, symlink behavior, and edit semantics all at once. That couples three concerns that change independently: @@ -16,7 +16,7 @@ That couples three concerns that change independently: Without a `ctx.fs` interface, swapping local filesystem access for a sandboxed or remote backend would churn the tool schemas, demos, and prompt guidance even when the model-facing contract should stay stable. It also makes permission/sandbox boundaries harder to reason about: a `cwd` option can look like a sandbox even though it is only a base path unless an explicit backend or `tools/execute` policy enforces containment. -We need the filesystem tools to land in the same capability-seam shape as bash before they become a public package surface. +The filesystem tools must land in the same capability-seam shape as bash before they become a public package surface. ## Decision @@ -26,9 +26,9 @@ Filesystem access is a first-class capability seam following [the capability-sea 2. `@deepseek-ai/dsh-fs-local` (`packages/fs/fs-local`) provides the first implementation, backed by the local filesystem. 3. `@deepseek-ai/dsh-tool-fs` (`packages/fs/tool-fs`) provides the model-facing `read`, `write`, and `edit` tools over `ctx.fs`, and is the executor that dispatches the `fs/*` events. -The consumer package depends only on the interface package, never on `dsh-fs-local`. A deployment that wants a different backend loads a different provider for `ctx.fs` without changing the tool schemas or model-facing prompt guidance. +The Consumer package depends only on the Service Definition package, never on `dsh-fs-local`. A deployment that wants a different backend loads a different provider for `ctx.fs` without changing the tool schemas or model-facing prompt guidance. -The read-before-write/edit and observed-state policy is a fourth package, `@deepseek-ai/dsh-fs-policy` (`packages/fs/fs-policy`), contributed through the `fs/*` event gate rather than living on `ctx.fs`; a deployment loading `dsh-tool-fs` also loads `dsh-fs-policy` to get read-before-write/edit. This Agent Note established the three-package seam; the split of policy off the provider base class is decided by [the split-fs-seam Agent Note](../simplification/2026-06-26-fsspec-style-fs-seam.md), and its realization as an event-gate plugin (not a method service) by [the event-gate Agent Note](2026-06-26-file-context-as-event-gate.md). This document is updated to describe that landed four-package shape. +The read-before-write/edit and observed-state policy is a fourth package, `@deepseek-ai/dsh-fs-policy` (`packages/fs/fs-policy`), contributed through the `fs/*` event gate rather than living on `ctx.fs`; a deployment loading `dsh-tool-fs` also loads `dsh-fs-policy` to get read-before-write/edit. This decision established the three-package boundary; the split of policy off the provider base class is decided by [the split-fs-seam Agent Note](../simplification/2026-06-26-fsspec-style-fs-seam.md), and its realization as an event-gate plugin (not a method service) by [the event-gate Agent Note](2026-06-26-file-context-as-event-gate.md). The first backend is deliberately local-only: `dsh-fs-local` implements `ctx.fs` against the host filesystem. Future sibling backends can provide sandboxed, remote, virtual, or project-scoped filesystems behind the same interface. @@ -53,7 +53,7 @@ The filesystem seam uses the same dependency direction as the bash trio: `@deepseek-ai/dsh-tool-fs` depends on `@deepseek-ai/dsh-fs`, `@deepseek-ai/dsh-tools`, `@deepseek-ai/dsh-system-prompt`, and `cordis`. It registers model-facing tools and prompt sections. It must not import `node:fs`, `node:path`, or `@deepseek-ai/dsh-fs-local`; filesystem execution always goes through `ctx.fs`. If the implementation needs concrete agent or session helper types, those dependencies belong in `tool-fs`; they must not leak back into `dsh-fs`. -The root `tool-fs` plugin registers the full filesystem tool suite (`read`, `write`, and `edit`) by composing the per-tool registration helpers. It injects `fs` and never imports an implementation package. +The root `tool-fs` plugin registers the full filesystem tool suite (`read`, `write`, and `edit`) by composing the per-tool registration helpers. It injects `fs` and never imports a Service provider package. ## `ctx.fs` contract @@ -68,13 +68,13 @@ The interface covers these semantic operations: - Create or replace a UTF-8 text file. - Edit an existing UTF-8 text file by literal replacement. -The provider seam also carries the freshness hooks that policy builds on — but the observed-state store and owner derivation live in the `dsh-fs-policy` plugin, not on `ctx.fs`: +The provider contract also carries the freshness hooks that policy builds on — but the observed-state store and owner derivation live in the `dsh-fs-policy` plugin, not on `ctx.fs`: - The backend mints an opaque `version` token per target (in `stat` and in every read/mutation outcome). - `writeText`/`editText` take an OPTIONAL version expectation: omit it for an unconditional bare-provider mutation, or supply it to guard the mutation inside the backend's atomic critical section. - The `dsh-fs-policy` plugin decides that expectation on `fs/write-intent`/`fs/edit-intent` and records observed versions on `fs/observed`, keyed by an owner it derives from the opaque event actor (normally `exec.agent.session`). -Authorization is version freshness, not a full/partial view distinction: any read records the target's version, and a later write/edit is authorized as long as the file is still at that version — so a windowed read of lines 100-150 authorizes an edit of line 120. The observed-state store is a `WeakMap>` inside `dsh-fs-policy`; `dsh-fs` holds none of it and treats the actor as opaque. (This Agent Note first modeled a `FileState` cache with `full`/`partial` views on `ctx.fs`; the split-fs-seam and event-gate Agent Notes replaced that with the freshness-based policy plugin described here.) +Authorization is version freshness, not a full/partial view distinction: any read records the target's version, and a later write/edit is authorized as long as the file is still at that version — so a windowed read of lines 100-150 authorizes an edit of line 120. The observed-state store is a `WeakMap>` inside `dsh-fs-policy`; `dsh-fs` holds none of it and treats the actor as opaque. (This decision first modeled a `FileState` cache with `full`/`partial` views on `ctx.fs`; the split-fs-seam and event-gate notes replaced that with the freshness-based policy plugin described here.) Path resolution is explicit and allowed to be async. Local resolution may only normalize a path, but sandboxed/remote/project-scoped backends may need I/O to resolve a user-supplied path into a stable target identity. @@ -127,7 +127,7 @@ The root plugin registers the full suite by composing the per-tool registration ## Testing -Tests follow the package boundary, not only the user-visible tools: the service seam in `dsh-fs`; real filesystem behavior through the `ctx.fs` interface in `dsh-fs-local` (resolution, symlinks, streaming, binary/UTF-8 rejection, unconditional and version-guarded writes, literal-edit semantics, line-ending preservation, structured `FsError` codes); the consumer surface in `dsh-tool-fs` against the real local provider (mock only the model/clock, never the collaborator); and integration through `ctx.tools.execute()` with and without `dsh-fs-policy`, world-verified by reading files back from disk rather than trusting either the canonical value or rendered content. The observed-state/owner-derivation policy is tested in `dsh-fs-policy`, not here. +Tests follow the package boundary, not only the user-visible tools: the service contract in `dsh-fs`; real filesystem behavior through the `ctx.fs` interface in `dsh-fs-local` (resolution, symlinks, streaming, binary/UTF-8 rejection, unconditional and version-guarded writes, literal-edit semantics, line-ending preservation, structured `FsError` codes); the consumer surface in `dsh-tool-fs` against the real local provider (mock only the model/clock, never the collaborator); and integration through `ctx.tools.execute()` with and without `dsh-fs-policy`, world-verified by reading files back from disk rather than trusting either the canonical value or rendered content. The observed-state/owner-derivation policy is tested in `dsh-fs-policy`, not here. The defensive-pattern classes this repo has been bitten by are pinned directly: @@ -139,7 +139,7 @@ The defensive-pattern classes this repo has been bitten by are pinned directly: ## Alternatives considered - **Model-facing tools directly over `node:fs`** — the tool package would own execution policy, path resolution, atomic writes, text decoding, and edit semantics at once, coupling the three independently-changing concerns the Problem names and churning schemas on any backend swap. -- **One combined `dsh-fs-tools` package** — the pre-seam shape; rejected for the same interface/implementation/consumer split as bash, and the combined name never became public surface. +- **One combined `dsh-fs-tools` package** — the pre-seam shape; rejected for the same Service Definition / Service provider / Consumer split as bash, and the combined name never became public surface. - **Observed-state on `ctx.fs`** — the shape this Agent Note first landed; superseded by [the split-fs-seam Agent Note](../simplification/2026-06-26-fsspec-style-fs-seam.md) and [the event-gate Agent Note](2026-06-26-file-context-as-event-gate.md): a sandboxed/remote backend must not inherit model-facing observation policy, so the provider keeps only the version token and the optional version-guarded mutation. ## Consequences @@ -148,11 +148,11 @@ The defensive-pattern classes this repo has been bitten by are pinned directly: **The interface can become too local.** Returning fields such as `absolutePath` from `ctx.fs` would make remote, sandboxed, or virtual backends awkward. The contract should expose display metadata without requiring consumers to understand host paths. -**The interface can become too thin.** If `ctx.fs` only mirrors `node:fs` primitives, `tool-fs` will reimplement binary detection, pagination, atomic writes, and edit semantics. That recreates the coupling this Agent Note is trying to avoid. +**The interface can become too thin.** If `ctx.fs` only mirrors `node:fs` primitives, `tool-fs` will reimplement binary detection, pagination, atomic writes, and edit semantics. That recreates the coupling this decision avoids. **Edit semantics are race-prone by nature.** Literal edit is a read-modify-write operation; the guard is the backend's atomic mutation critical section plus the optional version expectation, so concurrent edits settle deterministically — one wins, the other gets `FS_STALE_VERSION`. -**Observed state does not belong on `ctx.fs`.** Recording what an execution context has seen is workflow policy, not raw filesystem I/O. This Agent Note first placed it inside the filesystem seam; the split-fs-seam Agent Note then established that a sandboxed/remote backend should not inherit model-facing observation policy, and moved it into the `dsh-fs-policy` plugin. The provider seam keeps only what write/edit safety genuinely needs at the storage layer — a backend-minted version token and an optional version-guarded mutation — while the policy plugin owns owner derivation, observed-state, and read-before-edit gating over the `fs/*` events. +**Observed state does not belong on `ctx.fs`.** Recording what an execution context has seen is workflow policy, not raw filesystem I/O. This decision first placed it inside the filesystem seam; the split-fs-seam note then established that a sandboxed/remote backend should not inherit model-facing observation policy, and moved it into the `dsh-fs-policy` plugin. The provider contract keeps only what write/edit safety genuinely needs at the storage layer — a backend-minted version token and an optional version-guarded mutation — while the policy plugin owns owner derivation, observed-state, and read-before-edit gating over the `fs/*` events. **The `resolve`-then-operate shape costs an extra round-trip per call.** Each tool may resolve a path to an `FsTarget` and then issue the read/write/edit as a separate `ctx.fs` call. For the local backend this is negligible (resolution is in-memory path normalization), but a remote/sandboxed backend may turn each step into its own request, so a single `read` can become two network round-trips. Backends where the round-trip matters can cache or fold resolution internally while preserving the observable contract. diff --git a/.agents/notes/implemented/architecture/2026-06-17-filesystem-capability-seam.zh.md b/.agents/notes/implemented/architecture/2026-06-17-filesystem-capability-seam.zh.md index a96d513d7f..02af77a3cc 100644 --- a/.agents/notes/implemented/architecture/2026-06-17-filesystem-capability-seam.zh.md +++ b/.agents/notes/implemented/architecture/2026-06-17-filesystem-capability-seam.zh.md @@ -6,7 +6,7 @@ Status: implemented ## 问题 -harness 已有一个具体的 `bash` 能力 seam（`dsh-bash` / `dsh-bash-local` / `dsh-tool-bash`），但文件系统操作即将作为面向模型的工具加入，却没有等价的 seam。如果 `read`、`write` 和 `edit` 直接使用 `node:fs`，面向模型的工具包将同时承担文件系统执行策略、本地路径解析、原子写入行为、文本解码、符号链接行为和编辑语义。 +harness 已有一个具体的 `bash` 能力 seam（`dsh-bash` / `dsh-bash-local` / `dsh-tool-bash`），但文件系统操作当时即将作为面向模型的工具落地，却没有等价的 seam。如果 `read`、`write` 和 `edit` 直接使用 `node:fs`，面向模型的工具包就会同时承担文件系统执行策略、本地路径解析、原子写入行为、文本解码、符号链接行为和编辑语义。 这把三个独立变化的关注点耦合在了一起： @@ -16,7 +16,7 @@ harness 已有一个具体的 `bash` 能力 seam（`dsh-bash` / `dsh-bash-local` 如果没有 `ctx.fs` 接口，将本地文件系统访问替换为沙箱或远程后端时，即使面向模型的约定应当保持稳定，工具 schema、演示和提示词引导也会被迫变动。这还使权限/沙箱边界更难推理：一个 `cwd` 选项看起来像沙箱，但除非有显式的后端或 `tools/execute` 策略强制隔离，否则它只是一个基础路径。 -我们需要文件系统工具在成为公开包（package）接口之前，以与 bash 相同的能力 seam 形态落地。 +文件系统工具必须在成为公开包（package）接口之前，以与 bash 相同的能力 seam 形态落地。 ## 决策 @@ -26,9 +26,9 @@ harness 已有一个具体的 `bash` 能力 seam（`dsh-bash` / `dsh-bash-local` 2. `@deepseek-ai/dsh-fs-local`（`packages/fs/fs-local`）提供第一个实现，以本地文件系统为后端。 3. `@deepseek-ai/dsh-tool-fs`（`packages/fs/tool-fs`）通过 `ctx.fs` 提供面向模型的 `read`、`write` 和 `edit` 工具，是分发 `fs/*` 事件的执行器。 -消费方包仅依赖接口包，从不依赖 `dsh-fs-local`。需要不同后端的部署只需为 `ctx.fs` 加载不同的提供方，无需改动工具 schema 或面向模型的提示词引导。 +Consumer 包仅依赖 Service Definition 包，从不依赖 `dsh-fs-local`。需要不同后端的部署只需为 `ctx.fs` 加载不同的提供方，无需改动工具 schema 或面向模型的提示词引导。 -读后写/编辑与观测状态策略是第四个包 `@deepseek-ai/dsh-fs-policy`（`packages/fs/fs-policy`），通过 `fs/*` 事件门控贡献，而非挂在 `ctx.fs` 上；加载 `dsh-tool-fs` 的部署同时加载 `dsh-fs-policy` 以获得读后写/编辑能力。本 Agent Note 确立了由三个包构成的 seam；策略从提供方基类拆出的决策由 [拆分文件系统 seam Agent Note](../simplification/2026-06-26-fsspec-style-fs-seam.md) 做出，其以事件门控插件（而非方法服务）实现的方式由 [事件门控 Agent Note](2026-06-26-file-context-as-event-gate.md) 做出。本文已更新为描述最终落地的四包形态。 +读后写/编辑与观测状态策略是第四个包 `@deepseek-ai/dsh-fs-policy`（`packages/fs/fs-policy`），通过 `fs/*` 事件门控贡献，而非挂在 `ctx.fs` 上；加载 `dsh-tool-fs` 的部署同时加载 `dsh-fs-policy` 以获得读后写/编辑能力。本决策确立了由三个包构成的边界；策略从提供方基类拆出的决策由 [拆分文件系统 seam Agent Note](../simplification/2026-06-26-fsspec-style-fs-seam.md) 做出，其以事件门控插件（而非方法服务）实现的方式由 [事件门控 Agent Note](2026-06-26-file-context-as-event-gate.md) 做出。 第一个后端有意仅限本地：`dsh-fs-local` 基于宿主文件系统实现 `ctx.fs`。未来的兄弟后端可在同一接口之后提供沙箱、远程、虚拟或项目作用域的文件系统。 @@ -53,7 +53,7 @@ harness 已有一个具体的 `bash` 能力 seam（`dsh-bash` / `dsh-bash-local` `@deepseek-ai/dsh-tool-fs` 依赖 `@deepseek-ai/dsh-fs`、`@deepseek-ai/dsh-tools`、`@deepseek-ai/dsh-system-prompt` 和 `cordis`。它注册面向模型的工具和提示词段落。它禁止导入 `node:fs`、`node:path` 或 `@deepseek-ai/dsh-fs-local`；文件系统执行始终通过 `ctx.fs`。如果实现需要具体的 agent 或会话辅助类型，这些依赖属于 `tool-fs`；它们禁止回漏到 `dsh-fs` 中。 -根 `tool-fs` 插件通过组合各工具的注册辅助函数来注册完整的文件系统工具套件（`read`、`write` 和 `edit`）。它注入 `fs`，从不导入实现包。 +根 `tool-fs` 插件通过组合各工具的注册辅助函数来注册完整的文件系统工具套件（`read`、`write` 和 `edit`）。它注入 `fs`，从不导入 Service provider 包。 ## `ctx.fs` 约定 @@ -68,13 +68,13 @@ harness 已有一个具体的 `bash` 能力 seam（`dsh-bash` / `dsh-bash-local` - 创建或替换一个 UTF-8 文本文件。 - 通过字面替换编辑一个已有的 UTF-8 文本文件。 -提供方 seam 还携带策略所依赖的新鲜度钩子——但观测状态存储和 owner 推导位于 `dsh-fs-policy` 插件中，而非 `ctx.fs` 上： +提供方约定还携带策略所依赖的新鲜度钩子——但观测状态存储和 owner 推导位于 `dsh-fs-policy` 插件中，而非 `ctx.fs` 上： - 后端为每个目标铸造一个不透明的 `version` 令牌（在 `stat` 以及每次读取/变更结果中）。 - `writeText`/`editText` 接受一个可选的版本期望：省略它表示无条件的裸提供方变更；提供它则在后端的原子临界区内守护变更。 - `dsh-fs-policy` 插件在 `fs/write-intent`/`fs/edit-intent` 上决定该期望，并在 `fs/observed` 上记录观测版本，以它从不透明事件 actor 推导出的 owner 为键（通常是 `exec.agent.session`）。 -授权基于版本新鲜度，而非完整/部分视图的区分：任何读取都会记录目标的版本，后续的写入/编辑只要文件仍处于该版本就被授权——因此对第 100-150 行的窗口化读取可以授权对第 120 行的编辑。观测状态存储是 `dsh-fs-policy` 内部的 `WeakMap>`；`dsh-fs` 不持有任何此类数据，并将 actor 视为不透明。（本 Agent Note 最初建模了一个带 `full`/`partial` 视图的 `FileState` 缓存放在 `ctx.fs` 上；拆分文件系统 seam 与事件门控两份 Agent Note 将其替换为此处描述的基于新鲜度的策略插件。） +授权基于版本新鲜度，而非完整/部分视图的区分：任何读取都会记录目标的版本，后续的写入/编辑只要文件仍处于该版本就被授权——因此对第 100-150 行的窗口化读取可以授权对第 120 行的编辑。观测状态存储是 `dsh-fs-policy` 内部的 `WeakMap>`；`dsh-fs` 不持有任何此类数据，并将 actor 视为不透明。（本决策最初建模了一个带 `full`/`partial` 视图的 `FileState` 缓存放在 `ctx.fs` 上；拆分文件系统 seam 与事件门控两份笔记将其替换为此处描述的基于新鲜度的策略插件。） 路径解析是显式的，允许异步。本地解析可能只做路径规范化，但沙箱/远程/项目作用域的后端可能需要 I/O 才能将用户提供的路径解析为稳定的目标标识。 @@ -127,7 +127,7 @@ harness 已有一个具体的 `bash` 能力 seam（`dsh-bash` / `dsh-bash-local` ## 测试 -测试遵循包边界，而不仅是用户可见的工具：`dsh-fs` 中的服务 seam；`dsh-fs-local` 中通过 `ctx.fs` 接口测试的真实文件系统行为（解析、符号链接、流式传输、二进制/UTF-8 拒绝、无条件和版本守护的写入、字面编辑语义、行尾保留、结构化 `FsError` 错误码）；`dsh-tool-fs` 中基于真实本地提供方的消费方接口（只 mock 模型/时钟，从不 mock 协作者）；以及通过 `ctx.tools.execute()` 在有和没有 `dsh-fs-policy` 的情况下进行集成测试，通过从磁盘回读文件来验证世界状态，既不信任规范值，也不信任渲染内容。观测状态/owner 推导策略在 `dsh-fs-policy` 中测试，不在此处。 +测试遵循包边界，而不仅是用户可见的工具：`dsh-fs` 中的服务约定；`dsh-fs-local` 中通过 `ctx.fs` 接口测试的真实文件系统行为（解析、符号链接、流式传输、二进制/UTF-8 拒绝、无条件和版本守护的写入、字面编辑语义、行尾保留、结构化 `FsError` 错误码）；`dsh-tool-fs` 中基于真实本地提供方的消费方接口（只 mock 模型/时钟，从不 mock 协作者）；以及通过 `ctx.tools.execute()` 在有和没有 `dsh-fs-policy` 的情况下进行集成测试，通过从磁盘回读文件来验证世界状态，既不信任规范值，也不信任渲染内容。观测状态/owner 推导策略在 `dsh-fs-policy` 中测试，不在此处。 本仓库曾踩过的防御性模式类别被直接固定： @@ -139,7 +139,7 @@ harness 已有一个具体的 `bash` 能力 seam（`dsh-bash` / `dsh-bash-local` ## 曾考虑的替代方案 - **面向模型的工具直接基于 `node:fs`**：工具包将同时承担执行策略、路径解析、原子写入、文本解码和编辑语义，耦合问题部分所列的三个独立变化的关注点，且任何后端替换都会搅动 schema。 -- **单一合并包 `dsh-fs-tools`**：seam 之前的形态；以与 bash 相同的接口/实现/消费方拆分理由否决，且合并名称从未成为公开接口。 +- **单一合并包 `dsh-fs-tools`**：seam 之前的形态；以与 bash 相同的 Service Definition / Service provider / Consumer 拆分理由否决，且合并名称从未成为公开接口。 - **观测状态放在 `ctx.fs` 上**：本 Agent Note 最初落地的形态；被 [拆分文件系统 seam Agent Note](../simplification/2026-06-26-fsspec-style-fs-seam.md) 和 [事件门控 Agent Note](2026-06-26-file-context-as-event-gate.md) 取代：沙箱/远程后端不应继承面向模型的观测策略，因此提供方只保留版本令牌和可选的版本守护变更。 ## 后果 @@ -148,11 +148,11 @@ harness 已有一个具体的 `bash` 能力 seam（`dsh-bash` / `dsh-bash-local` **接口可能变得过于本地化。** 如果 `ctx.fs` 返回 `absolutePath` 之类的字段，远程、沙箱或虚拟后端会变得尴尬。约定应暴露显示元数据，而不要求消费方理解宿主路径。 -**接口可能变得过于薄。** 如果 `ctx.fs` 只镜像 `node:fs` 原语，`tool-fs` 将重新实现二进制检测、分页、原子写入和编辑语义，重新制造本 Agent Note 试图避免的耦合。 +**接口可能变得过于薄。** 如果 `ctx.fs` 只镜像 `node:fs` 原语，`tool-fs` 将重新实现二进制检测、分页、原子写入和编辑语义，重新制造本决策所避免的耦合。 **编辑语义天然易受竞争影响。** 字面编辑是读-改-写操作；守护手段是后端的原子变更临界区加上可选的版本期望，因此并发编辑确定性地收敛——一个赢，另一个得到 `FS_STALE_VERSION`。 -**观测状态不属于 `ctx.fs`。** 记录执行上下文看到了什么是工作流策略，而非原始文件系统 I/O。本 Agent Note 最初将其放在文件系统 seam 内部；拆分文件系统 seam Agent Note 随后确立了沙箱/远程后端不应继承面向模型的观测策略，并将其移入 `dsh-fs-policy` 插件。提供方 seam 只保留写入/编辑安全在存储层真正需要的东西——后端铸造的版本令牌和可选的版本守护变更——而策略插件拥有 owner 推导、观测状态和基于 `fs/*` 事件的读后编辑门控。 +**观测状态不属于 `ctx.fs`。** 记录执行上下文看到了什么是工作流策略，而非原始文件系统 I/O。本决策最初将其放在文件系统 seam 内部；拆分文件系统 seam 笔记随后确立了沙箱/远程后端不应继承面向模型的观测策略，并将其移入 `dsh-fs-policy` 插件。提供方约定只保留写入/编辑安全在存储层真正需要的东西——后端铸造的版本令牌和可选的版本守护变更——而策略插件拥有 owner 推导、观测状态和基于 `fs/*` 事件的读后编辑门控。 **`resolve` 然后操作的形态每次调用多一次往返。** 每个工具可能先将路径解析为 `FsTarget`，再以单独的 `ctx.fs` 调用发起读取/写入/编辑。对本地后端来说这可以忽略（解析是内存中的路径规范化），但远程/沙箱后端可能将每步变成独立请求，使单次 `read` 变为两次网络往返。往返开销重要的后端可以在内部缓存或折叠解析，同时保持可观测约定不变。 diff --git a/.agents/notes/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-contracts.i18n.yaml similarity index 64% rename from .agents/notes/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.i18n.yaml rename to .agents/notes/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-contracts.i18n.yaml index 70c9f791f4..4ea64d5530 100644 --- a/.agents/notes/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-contracts.i18n.yaml @@ -1,6 +1,6 @@ # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: -# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.md -2026-06-18-agent-lifecycle-and-ownership-seams.md: 93247a6da7446a5a67db33423d2b766ce4cf3308 -2026-06-18-agent-lifecycle-and-ownership-seams.zh.md: e17650c7789764dfb4240132f5903795e6f86381 +# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-contracts.md +2026-06-18-agent-lifecycle-and-ownership-contracts.md: ad334d30afcaf1864a1ea3dd42f3c5b7d157603b +2026-06-18-agent-lifecycle-and-ownership-contracts.zh.md: b9240969c9e952c1b38cbd4c088853005e156067 diff --git a/.agents/notes/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.md b/.agents/notes/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-contracts.md similarity index 72% rename from .agents/notes/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.md rename to .agents/notes/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-contracts.md index 93247a6da7..ad334d30af 100644 --- a/.agents/notes/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.md +++ b/.agents/notes/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-contracts.md @@ -1,16 +1,16 @@ -# Agent Note: Agent lifecycle and ownership seams +# Agent Note: Agent lifecycle and ownership contracts Status: implemented -English | [中文](2026-06-18-agent-lifecycle-and-ownership-seams.zh.md) +English | [中文](2026-06-18-agent-lifecycle-and-ownership-contracts.zh.md) ## Problem -Several ACP and tool-bash limitations were symptoms of the same missing seam: plugins could create or resume agents through `ctx.agents`, but they could not own and dispose one agent independently, and long-running bash tasks carried no stable owner in the executor itself. ACP aborted and awaited agents on disconnect but could not unregister just that session's agent; `session/cancel` could not cancel queued-but-not-yet-started work; and `tool-bash` kept task ownership in a plugin-local `Map`, so an HMR reload could make an old task look unowned. +Several ACP and tool-bash limitations were symptoms of the same missing ownership contract: plugins could create or resume agents through `ctx.agents`, but they could not own and dispose one agent independently, and long-running bash tasks carried no stable owner in the executor itself. ACP aborted and awaited agents on disconnect but could not unregister just that session's agent; `session/cancel` could not cancel queued-but-not-yet-started work; and `tool-bash` kept task ownership in a plugin-local `Map`, so an HMR reload could make an old task look unowned. ## Decision -Three seams: the queue-aware cancel, the `AgentHandle` disposer, and the bash owner token. +Three contract changes: the queue-aware cancel, the `AgentHandle` disposer, and the bash owner token. ### 1. Queue-aware `Agent.cancel(cause?)` @@ -22,9 +22,9 @@ A new `cancel()` verb on the `Agent` interface — the single public stop primit **Teardown ORDER is load-bearing for durability**, and the implementation folds the session lifecycle into the agent's SINGLE composite cordis effect (`SessionStore.prepare`/`enter`/`announce`, replacing a sibling-effect split). A fiber unload disposes sibling effects concurrently (`Promise.all`), which would race removing the session store's append publication hooks against the loop's closing `session/flush` and drop the closing `turn/end`; inside one effect the disposers run as an ordered LIFO chain (loop stopped + `await agent.done` BEFORE the session detaches), so the loop's final flush is captured on BOTH the handle's `dispose()` and a fiber unload. The contained `agent/disposed` and `session/disposed` notifications cannot reject the chain or skip later teardown. -### 3. Bash owner token in the seam +### 3. Bash owner token in the Service Definition -Background-task ownership moved from a `tool-bash` plugin-local `Map` into the executor. `BashExecRequest` gains an optional `owner?: string`; the resolved `BashExecSpec` carries it as required-but-nullable `owner: string | undefined` (a forgotten owner is a visible `undefined`, never a silently-absent property). The executor stores the token on its task and exposes it via a new `BashExecutor.ownerOf(id): string | undefined` seam (NOT on the public `BashTask` — one read path, no redundant API). `tool-bash` deletes its `Map` entirely: it stamps `exec.agent?.id` (the shared registry/session id) as the owner at `start`, and `bash_output`/`bash_kill` compare `ctx.bash.ownerOf(id)` to the caller's token with `!== undefined` semantics (an empty-string token is still a real owner). The completion notice finds the live agent by scanning `ctx.get('agents')?.list()` for `agent.id === ownerToken` (read via `ctx.get` — `onTaskDone` runs on the bash fiber, a foreign fiber, where the `ctx.agents` proxy would throw). Because ownership now lives on the task in the executor (disposed with the `dsh-bash` fiber), it SURVIVES a `tool-bash` HMR reload — closing the old `XXX(tool-bash-owner-hmr)` gap. (The `onTaskDone` listener is still effect-scoped to `tool-bash`'s `apply`, so a completion landing during the reload gap still drops its one notice — the pre-existing reload-gap drop — but the ownership fence itself is HMR-proof.) +Background-task ownership moved from a `tool-bash` plugin-local `Map` into the executor. `BashExecRequest` gains an optional `owner?: string`; the resolved `BashExecSpec` carries it as required-but-nullable `owner: string | undefined` (a forgotten owner is a visible `undefined`, never a silently-absent property). The executor stores the token on its task and exposes it via a new `BashExecutor.ownerOf(id): string | undefined` method (NOT on the public `BashTask` — one read path, no redundant API). `tool-bash` deletes its `Map` entirely: it stamps `exec.agent?.id` (the shared registry/session id) as the owner at `start`, and `bash_output`/`bash_kill` compare `ctx.bash.ownerOf(id)` to the caller's token with `!== undefined` semantics (an empty-string token is still a real owner). The completion notice finds the live agent by scanning `ctx.get('agents')?.list()` for `agent.id === ownerToken` (read via `ctx.get` — `onTaskDone` runs on the bash fiber, a foreign fiber, where the `ctx.agents` proxy would throw). Because ownership now lives on the task in the executor (disposed with the `dsh-bash` fiber), it SURVIVES a `tool-bash` HMR reload — closing the old `XXX(tool-bash-owner-hmr)` gap. (The `onTaskDone` listener is still effect-scoped to `tool-bash`'s `apply`, so a completion landing during the reload gap still drops its one notice — the pre-existing reload-gap drop — but the ownership fence itself is HMR-proof.) ## Verification @@ -37,11 +37,11 @@ These invariants hold and are pinned by tests: ## Session owner tokens are unique among live agents -The bash owner-token comparison relies on the shared `Agent.id`/`SessionId` being unique among live agents. Concurrent same-ID operations may both prepare privately, but publication enters the session and agent in order; `SessionStore.enter()` rejects a duplicate live session id, and every losing transaction rolls its private state back. A programmatic caller therefore cannot publish two live agents with one session token. The access *policy* (token comparison) stays in `tool-bash` (the consumer); the bash seam stores only an opaque `owner` string and never interprets it — the correct interface/implementation/consumer split. +The bash owner-token comparison relies on the shared `Agent.id`/`SessionId` being unique among live agents. Concurrent same-ID operations may both prepare privately, but publication enters the session and agent in order; `SessionStore.enter()` rejects a duplicate live session id, and every losing transaction rolls its private state back. A programmatic caller therefore cannot publish two live agents with one session token. The access *policy* (token comparison) stays in `tool-bash` (the Consumer); the bash capability keeps `owner` opaque and never interprets it — the correct Service Definition / Service provider / Consumer split. ## Alternatives considered -- **A public `BashTask.owner` field** instead of the `BashExecutor.ownerOf(id)` seam — rejected: one read path, no redundant API. +- **A public `BashTask.owner` field** instead of the `BashExecutor.ownerOf(id)` Service Definition method — rejected: one read path, no redundant API. - **Sibling cordis effects for the agent's session lifecycle** — rejected: a fiber unload disposes sibling effects concurrently (`Promise.all`), racing removal of the store-owned append publication hooks against the loop's closing `session/flush`; the single composite effect's ordered LIFO chain is what captures the closing `turn/end` on both disposal paths. - **A separate step-only `abort()` beside `cancel()`** — shipped originally, then removed as unused; `cancel()` is the single public stop primitive ([the public-stop-surface Agent Note](../simplification/2026-06-20-public-agent-stop-surface.md)). diff --git a/.agents/notes/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.zh.md b/.agents/notes/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-contracts.zh.md similarity index 71% rename from .agents/notes/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.zh.md rename to .agents/notes/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-contracts.zh.md index e17650c778..b9240969c9 100644 --- a/.agents/notes/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.zh.md +++ b/.agents/notes/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-contracts.zh.md @@ -1,16 +1,16 @@ -# Agent Note: Agent 生命周期与所有权 seam +# Agent Note: Agent 生命周期与所有权约定 Status: implemented -[English](2026-06-18-agent-lifecycle-and-ownership-seams.md) | 中文 +[English](2026-06-18-agent-lifecycle-and-ownership-contracts.md) | 中文 ## 问题 -ACP（Agent Client Protocol）与 tool-bash 的若干限制是同一个缺失 seam 的症状：插件可以通过 `ctx.agents` 创建或恢复 agent（智能体），但无法独立拥有和 dispose（资源释放）单个 agent，而长时间运行的 bash 任务在执行器中也没有稳定的所有者。ACP 在断连时中止并等待 agent，却无法仅注销该会话的 agent；`session/cancel` 无法取消已入队但尚未开始的工作；`tool-bash` 将任务所有权保存在插件本地的 `Map` 中，因此一次 HMR（热模块替换）重载就可能让旧任务看起来无主。 +ACP（Agent Client Protocol）与 tool-bash 的若干限制是同一个所有权约定缺失的症状：插件可以通过 `ctx.agents` 创建或恢复 agent（智能体），但无法独立拥有和 dispose（资源释放）单个 agent，而长时间运行的 bash 任务在执行器中也没有稳定的所有者。ACP 在断连时中止并等待 agent，却无法仅注销该会话的 agent；`session/cancel` 无法取消已入队但尚未开始的工作；`tool-bash` 将任务所有权保存在插件本地的 `Map` 中，因此一次 HMR（热模块替换）重载就可能让旧任务看起来无主。 ## 决策 -三个 seam：队列感知的取消、`AgentHandle` 释放器，以及 bash 所有者令牌。 +三项约定变更：队列感知的取消、`AgentHandle` 释放器，以及 bash 所有者令牌。 ### 1. 队列感知的 `Agent.cancel(cause?)` @@ -22,9 +22,9 @@ ACP（Agent Client Protocol）与 tool-bash 的若干限制是同一个缺失 se **拆除顺序对持久性至关重要**，实现将会话生命周期折叠进 agent 的单个复合 Cordis effect（`SessionStore.prepare`/`enter`/`announce`，取代兄弟 effect 拆分）。fiber 卸载会并发释放兄弟 effect（`Promise.all`），这会让会话存储的 append 发布钩子移除与循环关闭时的 `session/flush` 竞争，从而丢失关闭的 `turn/end`；在一个 effect 内，释放器作为有序的 LIFO 链运行（停止循环 + `await agent.done` 在会话分离之前），因此无论 handle 的 `dispose()` 还是 fiber 卸载，都会捕获循环的最终刷写。被隔离的 `agent/disposed` 和 `session/disposed` 通知无法拒绝该链或跳过后续拆除。 -### 3. Bash seam 中的所有者令牌 +### 3. Service Definition 中的 Bash 所有者令牌 -后台任务所有权从 `tool-bash` 插件本地的 `Map` 移入执行器。`BashExecRequest` 新增可选的 `owner?: string`；解析后的 `BashExecSpec` 将其作为必需但可空的 `owner: string | undefined` 携带（被遗忘的 owner 是可见的 `undefined`，而非静默缺失的属性）。执行器把 token 存在任务上，并通过新的 `BashExecutor.ownerOf(id): string | undefined` seam 暴露它（不放在公开的 `BashTask` 上——只有一条读取路径，没有冗余 API）。`tool-bash` 完全删除其 `Map`：它在 `start` 时将 `exec.agent?.id`（共享的注册表/会话 id）盖章为 owner，`bash_output`/`bash_kill` 则以 `!== undefined` 语义把 `ctx.bash.ownerOf(id)` 与调用方 token 比较（空字符串 token 仍是真实 owner）。完成通知通过扫描 `ctx.get('agents')?.list()` 查找 `agent.id === ownerToken` 的存活 agent（经 `ctx.get` 读取——`onTaskDone` 运行在 bash fiber 这一外部 fiber 上，直接使用 `ctx.agents` proxy 会抛异常）。由于所有权现在保存在执行器的任务上（随 `dsh-bash` fiber dispose），它能跨越 `tool-bash` HMR 重载，关闭旧的 `XXX(tool-bash-owner-hmr)` 缺口。（`onTaskDone` 监听器仍受 `tool-bash` 的 `apply` effect 约束，因此落在重载间隙的完成仍会丢失一条通知——既有的重载间隙丢失——但所有权隔离本身已经不受 HMR 影响。） +后台任务所有权从 `tool-bash` 插件本地的 `Map` 移入执行器。`BashExecRequest` 新增可选的 `owner?: string`；解析后的 `BashExecSpec` 将其作为必需但可空的 `owner: string | undefined` 携带（被遗忘的 owner 是可见的 `undefined`，而非静默缺失的属性）。执行器把 token 存在任务上，并通过新的 `BashExecutor.ownerOf(id): string | undefined` 方法暴露它（不放在公开的 `BashTask` 上——只有一条读取路径，没有冗余 API）。`tool-bash` 完全删除其 `Map`：它在 `start` 时将 `exec.agent?.id`（共享的注册表/会话 id）盖章为 owner，`bash_output`/`bash_kill` 则以 `!== undefined` 语义把 `ctx.bash.ownerOf(id)` 与调用方 token 比较（空字符串 token 仍是真实 owner）。完成通知通过扫描 `ctx.get('agents')?.list()` 查找 `agent.id === ownerToken` 的存活 agent（经 `ctx.get` 读取——`onTaskDone` 运行在 bash fiber 这一外部 fiber 上，直接使用 `ctx.agents` proxy 会抛异常）。由于所有权现在保存在执行器的任务上（随 `dsh-bash` fiber dispose），它能跨越 `tool-bash` HMR 重载，关闭旧的 `XXX(tool-bash-owner-hmr)` 缺口。（`onTaskDone` 监听器仍受 `tool-bash` 的 `apply` effect 约束，因此落在重载间隙的完成仍会丢失一条通知——既有的重载间隙丢失——但所有权隔离本身已经不受 HMR 影响。） ## 验证 @@ -37,11 +37,11 @@ ACP（Agent Client Protocol）与 tool-bash 的若干限制是同一个缺失 se ## 会话所有者令牌在存活 agent 中唯一 -bash 所有者 token 比较依赖共享的 `Agent.id`/`SessionId` 在存活 agent 中唯一。并发的同 ID 操作可以都私下准备，但发布时会依次登记会话和 agent；`SessionStore.enter()` 拒绝重复的存活会话 id，每个失败事务都回滚自己的私有状态。因此程序化调用方无法发布两个共享同一会话 token 的存活 agent。访问*策略*（token 比较）留在消费方 `tool-bash`；bash seam 只存储不透明的 `owner` 字符串且从不解释它——这是正确的接口/实现/消费方拆分。 +bash 所有者 token 比较依赖共享的 `Agent.id`/`SessionId` 在存活 agent 中唯一。并发的同 ID 操作可以都私下准备，但发布时会依次登记会话和 agent；`SessionStore.enter()` 拒绝重复的存活会话 id，每个失败事务都回滚自己的私有状态。因此程序化调用方无法发布两个共享同一会话 token 的存活 agent。访问*策略*（token 比较）留在 Consumer `tool-bash`；bash 能力只存储不透明的 `owner` 字符串且从不解释它——这是正确的 Service Definition / Service provider / Consumer 拆分。 ## 曾考虑的替代方案 -- **公开的 `BashTask.owner` 字段**而非 `BashExecutor.ownerOf(id)` seam：否决。一条读取路径即可，无需冗余 API。 +- **公开的 `BashTask.owner` 字段**而非 `BashExecutor.ownerOf(id)` Service Definition 方法：否决。一条读取路径即可，无需冗余 API。 - **为 agent 的会话生命周期使用兄弟 Cordis effect**：否决。fiber 卸载时并发释放兄弟 effect（`Promise.all`），store 拥有的 append 发布钩子的移除与循环的关闭 `session/flush` 产生竞争；单一复合 effect 的有序 LIFO 链才能在两条释放路径上都捕获关闭的 `turn/end`。 - **在 `cancel()` 之外另设一个仅中止步骤的 `abort()`**：最初发布过，后因无人使用而移除；`cancel()` 是唯一的公开停止原语（见[公开停止接口 Agent Note](../simplification/2026-06-20-public-agent-stop-surface.md)）。 diff --git a/.agents/notes/implemented/architecture/2026-06-18-session-surface.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-18-session-surface.i18n.yaml index ce26042716..6abc3ded93 100644 --- a/.agents/notes/implemented/architecture/2026-06-18-session-surface.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-06-18-session-surface.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-06-18-session-surface.md -2026-06-18-session-surface.md: 1bb3baac5e9bea3f657cbd3be2623223bda78ce2 -2026-06-18-session-surface.zh.md: b967ad467e58ed4f4b4009fe4746f1b8b6b22f25 +2026-06-18-session-surface.md: fd48a4ee4e177b84a235b044b054e4ac266df8ba +2026-06-18-session-surface.zh.md: 86f9c5fdd5d711fb81e03e95329d316bfef29227 diff --git a/.agents/notes/implemented/architecture/2026-06-18-session-surface.md b/.agents/notes/implemented/architecture/2026-06-18-session-surface.md index 1bb3baac5e..fd48a4ee4e 100644 --- a/.agents/notes/implemented/architecture/2026-06-18-session-surface.md +++ b/.agents/notes/implemented/architecture/2026-06-18-session-surface.md @@ -6,7 +6,7 @@ English | [中文](2026-06-18-session-surface.zh.md) ## Problem -The event log is authoritative, but history manipulation had no durable shared mechanism. Plugins such as compaction would otherwise rewrite derived requests through order-sensitive listeners, leave no provenance, and require repeated changes to `deriveMessages()`. +The event log is authoritative, but history manipulation had no durable shared mechanism. Without one, plugins such as compaction would rewrite derived requests through order-sensitive listeners without recording which events each replacement used. Every new history manipulation would also require changes to `deriveMessages()`. ## Decision @@ -16,7 +16,7 @@ Add a **surface** — a derived, cached order of event sequences (the subset of Every `SessionEvent` gains two optional fields (structural metadata, like `seq`/`time`): -- **`sourceEventSeqs?: number[]`** — seq numbers of events that are provenance sources (e.g., the `assistant/chunk` seqs that built an `assistant/message`, or the surface nodes shadowed by a compaction marker). A present `[]` is valid only on `assistant/message` and records a known empty provider stream; omission there means legacy or otherwise unrecorded provenance. Other surface events require a non-empty list when the field is present. Provenance is a core design principle; without it, the replace-range operation cannot be validated on replay. +- **`sourceEventSeqs?: number[]`** — seq numbers of earlier events cited as sources (e.g., the `assistant/chunk` seqs that built an `assistant/message`, or the surface nodes shadowed by a compaction marker). A present `[]` is valid only on `assistant/message` and records a known empty provider stream; when the field is absent, a legacy or foreign event does not record which earlier events produced the message. Other surface events require a non-empty list when the field is present. Without these cited seqs, replay cannot validate that a replace-range operation names every event it removed. - **`surfaceOp?: SurfaceOp`** — how this event entered the surface. Absent for non-surface events. ### SurfaceOp: two operations @@ -49,7 +49,7 @@ The `repair.ts` module synthesizes `tool/result` closers for orphaned tool calls ### Invariants -`Session` validates `sourceEventSeqs` and `surfaceOp` at the always-on seed/append boundary: only `assistant/message` may use an empty provenance list; references are unique, earlier, and known; replacement endpoints exist in surface order; and provenance covers every shadowed node. These are single-record acceptance and storage-projection rules, not optional invariant-service contributions. +`Session` validates `sourceEventSeqs` and `surfaceOp` at the always-on seed/append boundary: only `assistant/message` may use an empty source-event list; references are unique, earlier, and known; replacement endpoints exist in surface order; and `sourceEventSeqs` covers every shadowed node. These are single-record acceptance and storage-projection rules, not optional invariant-service contributions. Every surface-eligible event must carry `surfaceOp` or it would disappear from derived history. Typed `append` overloads enforce this for literal event types; runtime checks in `append` and the seed constructor cover widened unions and loaded logs. Invalid seeds are rejected rather than upgraded under the pre-release format policy. @@ -63,11 +63,11 @@ Every surface-eligible event must carry `surfaceOp` or it would disappear from d ## Consequences - **`packages/core/session`**: `surface.ts` (`SurfaceManager`) maintains one ordered seq array for candidate acceptance and live projection; `SessionSurface` is its readonly public view. `SurfaceOp`/`SurfaceIntent` and the top-level session-event fields record how entries join it. `append()` requires a `SurfaceIntent` for surface events, `deriveMessages()` walks the surface as the sole derivation path, and `repair.ts` emits surface-aware closers. The seed constructor rejects a surface-eligible seed event missing its `surfaceOp` marker (see § Invariants). -- **`packages/core/agent-loop`**: All surface-capable appends pass surface opts. Chunk seqs are collected for `assistant/message` provenance; `tool/call` seqs are captured for `tool/result` provenance. +- **`packages/core/agent-loop`**: All surface-capable appends pass surface opts. Each `assistant/message` cites its chunk seqs; each `tool/result` cites its `tool/call` seq. - **`packages/session/session-persistence-sqlite`**: Two new nullable TEXT columns (`source_event_seqs`, `surface_op`) on the `events` table; `SCHEMA_VERSION` bumped (bump-and-reject, no migration). - **`packages/session/session-persistence-jsonl`**: No changes required. - **`packages/session/session-persistence`**: Abstract interface unchanged. -The surface is the foundation for future history manipulation. A compaction or tool-result-prune plugin appends one of the existing message-producing event types (a `user/message` carrying the summary, say) with `surfaceOp: { op: 'replace', start, end }` and `sourceEventSeqs` covering the shadowed entries — the new event takes the range's place on the surface while the plugin's own trace events (e.g. `compaction/start`, `compaction/end`) stay off it. Replay preserves the decision deterministically. +The surface is the foundation history manipulation ships on — dsh-compact's compaction rides it. A compaction or tool-result-prune plugin appends one of the existing message-producing event types (a `user/message` carrying the summary, say) with `surfaceOp: { op: 'replace', start, end }` and `sourceEventSeqs` covering the shadowed entries — the new event takes the range's place on the surface while the plugin's own trace events (e.g. `compaction/start`, `compaction/end`) stay off it. Replay preserves the decision deterministically. -A `tool/result` replacement may rewrite exactly one current `tool/result` and must preserve every data field except `content`. Session acceptance enforces this rule together with positional range and provenance validation, independent of optional diagnostic plugins. +A `tool/result` replacement may rewrite exactly one current `tool/result` and must preserve every data field except `content`. Session acceptance enforces this rule together with positional range and cited source-event validation, independent of optional diagnostic plugins. diff --git a/.agents/notes/implemented/architecture/2026-06-18-session-surface.zh.md b/.agents/notes/implemented/architecture/2026-06-18-session-surface.zh.md index b967ad467e..86f9c5fdd5 100644 --- a/.agents/notes/implemented/architecture/2026-06-18-session-surface.zh.md +++ b/.agents/notes/implemented/architecture/2026-06-18-session-surface.zh.md @@ -6,7 +6,7 @@ Status: implemented ## 问题 -事件日志是权威数据源，但历史操纵此前没有持久化的共享机制。如果没有这样的机制，上下文压缩（context compaction）等插件只能通过顺序敏感的监听器改写派生请求，不留溯源信息，且每次新增操纵都要反复修改 `deriveMessages()`。 +事件日志是权威数据源，但历史操纵此前没有持久化的共享机制。如果没有这样的机制，上下文压缩（context compaction）等插件会通过顺序敏感的监听器改写派生请求，却不记录每次替换使用了哪些事件。每次新增历史操纵时，还必须修改 `deriveMessages()`。 ## 决策 @@ -16,7 +16,7 @@ Status: implemented 每个 `SessionEvent` 获得两个可选字段（结构性元数据，与 `seq`/`time` 同级）： -- **`sourceEventSeqs?: number[]`**：作为溯源来源的事件 seq 编号（例如构成 `assistant/message` 的各 `assistant/chunk` 的 seq，或被压缩标记遮蔽的 surface 节点）。出现的 `[]` 只在 `assistant/message` 上有效，表示已知为空的提供方流；在该事件上省略字段表示旧数据或未记录的溯源。其他 surface 事件一旦出现此字段，就必须是非空列表。溯源是核心设计原则；没有它，replace-range 操作在回放时无法被验证。 +- **`sourceEventSeqs?: number[]`**：被引用为数据来源的早期事件 seq 编号（例如构成 `assistant/message` 的各 `assistant/chunk` 的 seq，或被压缩标记遮蔽的 surface 节点）。出现的 `[]` 只在 `assistant/message` 上有效，表示已知为空的提供方流；旧格式或外部事件缺少该字段时，没有记录这条消息由哪些早期事件产生。其他 surface 事件一旦出现此字段，就必须是非空列表。如果没有这些引用的 seq，回放就无法验证 replace-range 操作是否列出了它移除的每个事件。 - **`surfaceOp?: SurfaceOp`**：该事件如何进入 surface。非 surface 事件不携带此字段。 ### SurfaceOp：两种操作 @@ -49,7 +49,7 @@ export type SurfaceOp = ### 不变式 -`Session` 在始终启用的 seed/append 边界校验 `sourceEventSeqs` 与 `surfaceOp`：只有 `assistant/message` 可以使用空的溯源列表；引用必须唯一、更早且已知；替换端点必须存在于 surface 顺序中；溯源必须覆盖每个被遮蔽的节点。这些是单记录接纳与存储投影规则，不是由可选的不变式服务提供的规则。 +`Session` 在始终启用的 seed/append 边界校验 `sourceEventSeqs` 与 `surfaceOp`：只有 `assistant/message` 可以使用空的源事件列表；引用必须唯一、更早且已知；替换端点必须存在于 surface 顺序中；`sourceEventSeqs` 必须覆盖每个被遮蔽的节点。这些是单记录接纳与存储投影规则，不是由可选的不变式服务提供的规则。 每个可进入 surface 的事件都必须携带 `surfaceOp`，否则它将从派生历史中消失。类型化的 `append` 重载对字面事件类型强制执行此规则；`append` 和种子构造函数中的运行时检查覆盖宽化联合类型和加载的日志。按照预发布格式策略，无效的种子被拒绝而非升级。 @@ -63,11 +63,11 @@ export type SurfaceOp = ## 后果 - **`packages/core/session`**：`surface.ts`（`SurfaceManager`）维护一个用于候选接纳和实时投影的有序 seq 数组；`SessionSurface` 是其只读公共视图。`SurfaceOp`/`SurfaceIntent` 与顶层会话事件字段记录条目如何加入它。`append()` 要求 surface 事件携带 `SurfaceIntent`，`deriveMessages()` 以遍历 surface 作为唯一派生路径，`repair.ts` 则发出 surface 感知的闭合事件。种子构造函数拒绝缺少 `surfaceOp` 标记的可进入 surface 的种子事件（见「不变式」一节）。 -- **`packages/core/agent-loop`**：所有涉及 surface 事件的追加操作都传入 surface 选项。收集分片 seq 用于 `assistant/message` 溯源；捕获 `tool/call` seq 用于 `tool/result` 溯源。 +- **`packages/core/agent-loop`**：所有涉及 surface 事件的追加操作都传入 surface 选项。每个 `assistant/message` 都引用产生它的分片 seq；每个 `tool/result` 都引用它的 `tool/call` seq。 - **`packages/session/session-persistence-sqlite`**：`events` 表新增两个可空 TEXT 列（`source_event_seqs`、`surface_op`）；`SCHEMA_VERSION` 递增（bump-and-reject，无迁移）。 - **`packages/session/session-persistence-jsonl`**：无需改动。 - **`packages/session/session-persistence`**：抽象接口不变。 -Surface 是未来历史操纵的基础。压缩或 tool-result-prune 插件追加一个既有的消息产出事件类型（例如一条携带摘要的 `user/message`），附带 `surfaceOp: { op: 'replace', start, end }` 和覆盖被遮蔽条目的 `sourceEventSeqs`——新事件在 surface 上取代该范围的位置，而插件自身的 trace 事件（如 `compaction/start`、`compaction/end`）不进入 surface。回放以确定性方式保留该决策。 +Surface 是历史操纵赖以落地的基础——dsh-compact 的压缩就搭载于其上。压缩或 tool-result-prune 插件追加一个既有的消息产出事件类型（例如一条携带摘要的 `user/message`），附带 `surfaceOp: { op: 'replace', start, end }` 和覆盖被遮蔽条目的 `sourceEventSeqs`——新事件在 surface 上取代该范围的位置，而插件自身的 trace 事件（如 `compaction/start`、`compaction/end`）不进入 surface。回放以确定性方式保留该决策。 -一次 `tool/result` 替换只能改写当前的一个 `tool/result`，并且必须保留除 `content` 以外的每个数据字段。Session 接纳会与位置范围和溯源校验一起强制这条规则，不依赖可选的诊断插件。 +一次 `tool/result` 替换只能改写当前的一个 `tool/result`，并且必须保留除 `content` 以外的每个数据字段。Session 接纳会与位置范围和引用的源事件校验一起强制这条规则，不依赖可选的诊断插件。 diff --git a/.agents/notes/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.i18n.yaml index 84edacb9dc..00cff75149 100644 --- a/.agents/notes/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.md -2026-06-18-shared-persistence-write-coordinator.md: 12131ebf8380fb8ba816618f0cbaf72cb004623a -2026-06-18-shared-persistence-write-coordinator.zh.md: 0a7fbf351171d305b3b6245832a0b35a283c7c1d +2026-06-18-shared-persistence-write-coordinator.md: c376bb4a209a250d33274dfd60531475354ba363 +2026-06-18-shared-persistence-write-coordinator.zh.md: 06a2dafc4d14c29bb7758fdc67d3f0f8136983e2 diff --git a/.agents/notes/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.md b/.agents/notes/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.md index 12131ebf83..c376bb4a20 100644 --- a/.agents/notes/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.md +++ b/.agents/notes/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.md @@ -6,13 +6,13 @@ English | [中文](2026-06-18-shared-persistence-write-coordinator.zh.md) ## Problem -`dsh-session-persistence-jsonl` and `dsh-session-persistence-sqlite` intentionally prove the same `SessionPersistence` contract over different storage media, but their write-path orchestration was duplicated: per-session state, `session/created` adoption, backend-specific prefix reads, write-behind control, per-id operation serialization, HMR seeding, and dispose drains. The pure seed-prefix collision and serializability guards had already moved into the seam package; the remaining orchestration was still correctness-heavy and received the same fixes twice. Only the storage primitives (write bytes vs. INSERT rows) differed. +`dsh-session-persistence-jsonl` and `dsh-session-persistence-sqlite` intentionally prove the same `SessionPersistence` contract over different storage media, but their write-path orchestration was duplicated: per-session state, `session/created` adoption, backend-specific prefix reads, write-behind control, per-id operation serialization, HMR seeding, and dispose drains. The pure seed-prefix collision and serializability guards had already moved into the Service Definition package; the remaining orchestration was still correctness-heavy and received the same fixes twice. Only the storage primitives (write bytes vs. INSERT rows) differed. ## Decision Extract a backend-agnostic `PersistenceCoordinator` into `dsh-session-persistence`. The coordinator owns the orchestration once; each first-party backend composes one (`new PersistenceCoordinator(ctx, this)`), implements a small `PersistenceBackend` hook interface, and delegates its stateful public methods (`create`/`append`/`prepare`/`load`/`inspect`/`readFrom`) to it. Backend-owned metadata and revision listing bypass the coordinator. -Composition, not inheritance. The coordinator is a concrete class the backend holds, not a base class the backend extends. The Agent Note's risk — "a coordinator must not make unusual backends fight an inheritance hierarchy" — is avoided: a backend exposes only the hooks and cannot reach the coordinator's private orchestration state. A third-party backend MAY still implement the abstract service directly without the coordinator, including immutable logical inspection and the default preparation fallback through `load`. +Composition, not inheritance. The coordinator is a concrete class the backend holds, not a base class the backend extends. The risk that a coordinator makes unusual backends fight an inheritance hierarchy is avoided: a backend exposes only the hooks and cannot reach the coordinator's private orchestration state. A third-party backend MAY still implement the abstract service directly without the coordinator, including immutable logical inspection and the default preparation fallback through `load`. The coordinator holds one lifecycle entry for each exact live `Session`: initialization plus a package-private write controller that owns pending events, a fixed batching deadline, the active write, failure retention, and the shared flush barrier. Each `session/event` enters that bounded write path, and `session/flush` bypasses the wait to observe quiescence. The [flush-controller simplification](../simplification/2026-07-23-collapse-persistence-flush-state.md) owns controller consolidation; the [bounded batching decision](2026-08-08-bounded-session-persistence-write-batching.md) owns scheduling cadence. diff --git a/.agents/notes/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.zh.md b/.agents/notes/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.zh.md index 0a7fbf3511..06a2dafc4d 100644 --- a/.agents/notes/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.zh.md +++ b/.agents/notes/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.zh.md @@ -6,13 +6,13 @@ Status: implemented ## 问题 -`dsh-session-persistence-jsonl` 与 `dsh-session-persistence-sqlite` 有意在不同存储介质上证明同一份 `SessionPersistence` 约定，但它们重复实现了写入路径编排：每会话状态、`session/created` 接管、后端特定的前缀读取、write-behind 控制、按 id 串行执行操作、HMR（热模块替换）种子注入与 dispose（资源释放）排空。纯粹的种子前缀碰撞检查与可序列化守卫已迁入 seam 包；剩余的编排仍然对正确性要求很高，且同样的修复被应用了两次。唯一的差异在于存储原语（写字节 vs. INSERT 行）。 +`dsh-session-persistence-jsonl` 与 `dsh-session-persistence-sqlite` 有意在不同存储介质上证明同一份 `SessionPersistence` 约定，但它们重复实现了写入路径编排：每会话状态、`session/created` 接管、后端特定的前缀读取、write-behind 控制、按 id 串行执行操作、HMR（热模块替换）种子注入与 dispose（资源释放）排空。纯粹的种子前缀碰撞检查与可序列化守卫已迁入 Service Definition 包；剩余的编排仍然对正确性要求很高，且同样的修复被应用了两次。唯一的差异在于存储原语（写字节 vs. INSERT 行）。 ## 决策 将一个后端无关的 `PersistenceCoordinator` 提取到 `dsh-session-persistence` 中。协调器统一拥有编排逻辑；每个第一方后端组合一个协调器实例（`new PersistenceCoordinator(ctx, this)`），实现一个小型 `PersistenceBackend` 钩子接口，并将其有状态的公开方法（`create`/`append`/`prepare`/`load`/`inspect`/`readFrom`）委托给协调器。由后端拥有的元数据与修订版本列举会绕过协调器。 -组合，而非继承。协调器是后端持有的具体类，不是后端继承的基类。本 Agent Note 的风险——「协调器不得让非常规后端与继承层级作斗争」——由此规避：后端只暴露钩子，无法触及协调器的私有编排状态。第三方后端仍然可以完全不使用协调器、直接实现抽象服务，包括不修改状态的逻辑检查，以及通过 `load` 实现的默认准备回退。 +组合，而非继承。协调器是后端持有的具体类，不是后端继承的基类。协调器让非常规后端与继承层级作斗争的风险由此规避：后端只暴露钩子，无法触及协调器的私有编排状态。第三方后端仍然可以完全不使用协调器、直接实现抽象服务，包括不可变逻辑检查，以及通过 `load` 实现的默认准备回退。 协调器为每个存活的 `Session` 实例持有一个生命周期条目：初始化，加上一个包私有写入控制器，后者负责待处理事件、固定批处理截止时间、活跃写入、失败保留和共享 flush 屏障。每个 `session/event` 都进入这条有界写入路径，`session/flush` 则绕过等待以观察完全停稳。控制器归并由 [flush 控制器简化](../simplification/2026-07-23-collapse-persistence-flush-state.md)定义；调度节奏由[有界批处理决策](2026-08-08-bounded-session-persistence-write-batching.md)定义。 @@ -44,4 +44,4 @@ Status: implemented ## 后果 -协调器增加了一层间接、一个不透明的 torn marker、脱离会话生命周期的退役任务，以及有界的已准备 Session 状态，但将此前每个后端重复的、对正确性要求很高的编排逻辑集中到一处。会话 dispose 仍是仅观察事件，因此会话所有者不会等待持久化退役；协调器会收容失败、在存活控制器中保留待处理事件，并以后端 teardown 为完全停稳边界。其钩子面保持窄小：标识校验、接管、碰撞检查、准备与不修改状态的检查共用 `loadStored`；物化保持在 `appendBatch` 内原子完成；列举绕过协调器。读模型使用 `inspect` 而非 `load`，因此观察已持久化但仍开放的轮次时不会提交中断 closers；复用、预留与发布由 [Session 准备阶段决策](2026-08-05-session-preparation.md)定义。新后端只需实现存储原语，而无需复制有界写入生命周期。 +协调器增加了一层间接、一个不透明的 torn marker、脱离会话生命周期的退役任务，以及有界的已准备 Session 状态，但将此前每个后端重复的、对正确性要求很高的编排逻辑集中到一处。会话 dispose 仍是仅观察事件，因此会话所有者不会等待持久化退役；协调器会收容失败、在存活控制器中保留待处理事件，并以后端 teardown 为完全停稳边界。其钩子面保持窄小：标识校验、接管、碰撞检查、准备与不可变检查共用 `loadStored`；物化保持在 `appendBatch` 内原子完成；列举绕过协调器。读模型使用 `inspect` 而非 `load`，因此观察已持久化但仍开放的轮次时不会提交中断 closers；复用、预留与发布由 [Session 准备阶段决策](2026-08-05-session-preparation.md)定义。新后端只需实现存储原语，而无需复制有界写入生命周期。 diff --git a/.agents/notes/implemented/architecture/2026-06-20-branded-ids.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-20-branded-ids.i18n.yaml index 0af0c0038b..2270bc6f5f 100644 --- a/.agents/notes/implemented/architecture/2026-06-20-branded-ids.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-06-20-branded-ids.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-06-20-branded-ids.md -2026-06-20-branded-ids.md: 7c0b7ca89418e8312ec728223dac519f70edc3ed -2026-06-20-branded-ids.zh.md: 039953754b184af97eb9b4ea3bbb1325d45eda25 +2026-06-20-branded-ids.md: 78242226103fef0eac320cdfac0ccb82292fd9e8 +2026-06-20-branded-ids.zh.md: 613ef81d198f10ec70ca5cb019776e607f4a8a79 diff --git a/.agents/notes/implemented/architecture/2026-06-20-branded-ids.md b/.agents/notes/implemented/architecture/2026-06-20-branded-ids.md index 7c0b7ca894..7824222610 100644 --- a/.agents/notes/implemented/architecture/2026-06-20-branded-ids.md +++ b/.agents/notes/implemented/architecture/2026-06-20-branded-ids.md @@ -8,21 +8,21 @@ English | [中文](2026-06-20-branded-ids.zh.md) The harness brands `CallId` (`packages/llm/llm/src/brand.ts`) and the shared agent/session `SessionId` (`packages/core/session/src/types.ts`) using the `Branded = string & { readonly [BRAND]: B }` machinery (owned by the type-only `@deepseek-ai/dsh-brand` package at `packages/util/brand/` — see its [README](../../../../packages/util/brand/README.md)) and a zero-cost cast factory per type. `dsh-brand` also states the governing policy: *"Branding is for ids that cross package boundaries and could plausibly be confused; not every string needs a brand."* That policy is right; the problem is that it is only half-applied. Two gaps let a structurally-identical-but-semantically-wrong string slip through the type checker today. -**Gap 1 — unbranded cross-boundary IDs in the bash seam.** The background-task id is a plain `string`: `BashTask.id: string` (`packages/bash/bash/src/types.ts`), carried as `string` through the whole executor seam (`BashExecutor.get`/`ownerOf`/`readOutput`/`kill(id: string)` in `packages/bash/bash/src/index.ts`) and validated/passed as `string` by the model-facing tools (`validateTaskId`, `assertTaskAccess`, the `task_id` schema arg in `packages/bash/tool-bash/src/index.ts`). It is generated by a per-executor counter — `` `bash-${this.nextTaskId++}` `` in `packages/bash/bash-local/src/index.ts` — which gives it **exactly the same `name-N` shape as `SessionId`'s default** (`` `session-${++counter}` `` in `packages/core/session/src/index.ts`). A bash task id and a session id are trivially swappable at a call site and the compiler says nothing. This is the headline case the user asked about, and it is a model-facing id (the model passes `task_id` back to `bash_output`/`bash_kill`), so a confusion here is reachable from untrusted input. +**Gap 1 — unbranded cross-boundary IDs in the bash seam.** The background-task id is a plain `string`: `BashTask.id: string` (`packages/bash/bash/src/types.ts`), carried as `string` through the whole executor seam (`BashExecutor.get`/`ownerOf`/`readOutput`/`kill(id: string)` in `packages/bash/bash/src/index.ts`) and validated/passed as `string` by the model-facing tools (`validateTaskId`, `assertTaskAccess`, the `task_id` schema arg in `packages/bash/tool-bash/src/index.ts`). It is generated by a per-executor counter — `` `bash-${this.nextTaskId++}` `` in `packages/bash/bash-local/src/index.ts` — which gives it **exactly the same `name-N` shape as `SessionId`'s default** (`` `session-${++counter}` `` in `packages/core/session/src/index.ts`). A bash task id and a session id are trivially swappable at a call site and the compiler says nothing. It is a model-facing id (the model passes `task_id` back to `bash_output`/`bash_kill`), so a confusion here is reachable from untrusted input. The bash **owner token** is the related sub-case: `BashExecRequest.owner?: string` and `BashExecSpec.owner: string | undefined` (`packages/bash/bash/src/types.ts`) are documented as a deliberately *opaque* isolation key, but in every live caller the value IS the owning agent's shared `Agent.id`/`SessionId` (`callerToken = (exec) => exec.agent?.id` in `packages/bash/tool-bash/src/index.ts`) wearing a different seam-local name. It is compared for access control (`owner !== callerToken(exec)`), so a mismatched-but-well-typed string here is a cross-session isolation bug the type system currently cannot catch. This is the shared id alias covered by the [unified agent/session identity decision](../simplification/2026-06-20-unify-agent-and-session-id.md). -**Gap 2 — brand erosion at the seams of the *already-branded* IDs.** Even `CallId` and `SessionId` decay back to bare `string` at exactly the places confusion is most likely: registry/store key types and public method params. Representative sites include the session store, the agent registry (both keyed by the shared `SessionId`), tool-presentation call-id maps, ACP's session records, and the persistence coordinator. A brand that is dropped at a collection key buys nothing on lookups — the value of the existing brands is partly unrealized. +**Gap 2 — brand erosion at the boundaries of the *already-branded* IDs.** Even `CallId` and `SessionId` decay back to bare `string` at exactly the places confusion is most likely: registry/store key types and public method params. Representative sites include the session store, the agent registry (both keyed by the shared `SessionId`), tool-presentation call-id maps, ACP's session records, and the persistence coordinator. A brand that is dropped at a collection key buys nothing on lookups — the value of the existing brands is partly unrealized. ## Decision -A type-only change. Brands are zero-cost casts; nothing about runtime behavior, serialization, comparison, or the wire format changes. The work is in three parts, all honoring the existing "not every string" policy. +A type-only change. Brands are zero-cost casts; nothing about runtime behavior, serialization, comparison, or the wire format changes. The decision has three parts, all honoring the existing "not every string" policy. -- **Brand the bash task id.** Add `BashTaskId = Branded<'BashTaskId'>` plus its same-named factory in `packages/bash/bash/src/types.ts` (the package that *owns* the id), importing `Branded` from `@deepseek-ai/dsh-brand` exactly as `SessionId` does. The brand primitive lives in the dependency-free `dsh-brand` utility package precisely so `dsh-bash` can brand its ids by depending on it alone — it never pulls in `dsh-llm` (or `dsh-session`) just to reach `Branded`. Thread it through `BashTask.id`, the `BashExecutor` seam methods (`get`/`ownerOf`/`readOutput`/`kill`), the generation site in `dsh-bash-local` (brand the counter output once, at creation), and the `dsh-tool-bash` validate/access surface (`validateTaskId` returns a `BashTaskId`; `task_id` is branded at the tool boundary where the model's string arrives). +- **Brand the bash task id.** Add `BashTaskId = Branded<'BashTaskId'>` plus its same-named factory in `packages/bash/bash/src/types.ts` (the package that *owns* the id), importing `Branded` from `@deepseek-ai/dsh-brand` exactly as `SessionId` does. The brand primitive lives in the dependency-free `dsh-brand` utility package precisely so `dsh-bash` can brand its ids by depending on it alone — it never pulls in `dsh-llm` (or `dsh-session`) just to reach `Branded`. Thread it through `BashTask.id`, the `BashExecutor` Service Definition methods (`get`/`ownerOf`/`readOutput`/`kill`), the generation site in `dsh-bash-local` (brand the counter output once, at creation), and the `dsh-tool-bash` validate/access surface (`validateTaskId` returns a `BashTaskId`; `task_id` is branded at the tool boundary where the model's string arrives). -- **Mint a distinct `OwnerToken` brand.** Add `OwnerToken = Branded<'OwnerToken'>` in `packages/bash/bash/src/types.ts`; type `BashExecRequest.owner` / `BashExecSpec.owner` / `BashExecutor.ownerOf` as `OwnerToken | undefined`. The `dsh-tool-bash` consumer casts the agent's shared `id` (`SessionId`) into an `OwnerToken` at the boundary — the one place the two vocabularies meet. The bash seam never imports `dsh-session`. (Rationale in the next section.) +- **Mint a distinct `OwnerToken` brand.** Add `OwnerToken = Branded<'OwnerToken'>` in `packages/bash/bash/src/types.ts`; type `BashExecRequest.owner` / `BashExecSpec.owner` / `BashExecutor.ownerOf` as `OwnerToken | undefined`. The `dsh-tool-bash` consumer casts the agent's shared `id` (`SessionId`) into an `OwnerToken` at the boundary — the one place the two vocabularies meet. The bash Service Definition never imports `dsh-session`. (Rationale in the next section.) -- **Stop the brand erosion.** Propagate the existing brands to the `Map` key types and public method params listed under Gap 2 — `Map`, `Map`, `get(id: SessionId)`, `Map`, ACP's `SessionId` surface, and the coordinator's `Map`. This is the larger mechanical share of the diff and the part that makes the *existing* brands actually load-bearing on lookups, not just on struct fields. +- **Stop the brand erosion.** Propagate the existing brands to the `Map` key types and public method params listed under Gap 2 — `Map`, `Map`, `get(id: SessionId)`, `Map`, ACP's `SessionId` surface, and the coordinator's `Map`. This is the larger mechanical share of the change and the part that makes the *existing* brands actually load-bearing on lookups, not just on struct fields. Illustrative shape (the factory pattern is identical to the three existing brands): @@ -46,24 +46,24 @@ export function OwnerToken(id: string): OwnerToken { ### Why not typing `owner` as `SessionId`? -The obvious shortcut is to type `owner` as `SessionId` directly — it always *is* one. We reject that. The bash executor seam is a capability seam (interface `dsh-bash`, implementation `dsh-bash-local`, consumer `dsh-tool-bash`) and its owner token is *documented as deliberately opaque*: the executor "never interprets it (no access policy lives in the seam — that is the consumer's job)" (`packages/bash/bash/src/types.ts`). Typing the seam's field as `SessionId` would import `dsh-session`'s vocabulary into a package that must not know what an owner token *means* — it would couple a generic execution backend to the session model and contradict the opaque-token design. A sandboxed or remote executor that replaces `dsh-bash-local` should not inherit a session dependency. The distinct `OwnerToken` brand keeps the seam decoupled: `dsh-bash` knows only "an owner is some opaque branded token," and the `dsh-tool-bash` consumer — which already decides the access policy — is the single boundary that casts its `SessionId` into an `OwnerToken`. The brand still delivers the safety win (you cannot pass a `BashTaskId` or a raw string where an owner is expected) without the coupling. +The obvious shortcut is to type `owner` as `SessionId` directly — it always *is* one. We reject that. The bash executor seam is a capability seam (Service Definition `dsh-bash`, Service provider `dsh-bash-local`, Consumer `dsh-tool-bash`) and its owner token is *documented as deliberately opaque*: the executor "never interprets it (no access policy lives in the seam — that is the consumer's job)" (`packages/bash/bash/src/types.ts`). Typing the Service Definition's field as `SessionId` would import `dsh-session`'s vocabulary into a package that must not know what an owner token *means* — it would couple a generic execution backend to the session model and contradict the opaque-token design. A sandboxed or remote executor that replaces `dsh-bash-local` should not inherit a session dependency. The distinct `OwnerToken` brand keeps the seam decoupled: `dsh-bash` knows only "an owner is some opaque branded token," and the `dsh-tool-bash` consumer — which already decides the access policy — is the single boundary that casts its `SessionId` into an `OwnerToken`. The brand still delivers the safety win (you cannot pass a `BashTaskId` or a raw string where an owner is expected) without the coupling. ## Out of scope / possible extensions Kept deliberately narrow per the "not every string needs a brand" policy. Each of these is a plausible future brand, deferred with a reason, not a commitment: -- **`ModelId`** (`GenerateOptions.model`, the `LlmService` adapter-registry key) — a real cross-package lookup key (config → agent → llm → adapter); a reasonable next brand, left out only to keep this Agent Note's blast radius focused. +- **`ModelId`** (`GenerateOptions.model`, the `LlmService` adapter-registry key) — a real cross-package lookup key (config → agent → llm → adapter); a reasonable next brand, left out only to keep this decision's blast radius focused. - **`ToolName`** (the `ToolRegistry` key) — author-defined, human-readable, and rarely confused with another id; the weakest candidate, likely not worth a brand. - **`ErrorCode`** (`HarnessError.code`) — a closed vocabulary (`ABORTED`, `NO_ADAPTER`, …), not a per-instance id; better served by a string-literal union than a brand, if anything. - **Numeric ordinals** — turn number, step number, and the event `seq` are `number`, not `string`, so `Branded` does not apply; a parallel `number & { readonly [BRAND]: B }` variant could brand them, but they are positional ordinals rarely passed across boundaries, so the payoff is low. -- **Validated construction** — the brand factories are pure casts with no runtime check, and every boundary (ACP `sessionId`, provider-issued `call.id`, the empty-string fallback in `dsh-llm-deepseek`) trusts the raw string today. A `SessionId.parse()` / `isValid()` companion that throws on malformed input at boundaries is a genuine gap, but it is a *runtime-behavior* change with its own design (what is "malformed"? what do we do on failure?) and belongs in its own Agent Note, not bundled into this type-only pass. +- **Validated construction** — the brand factories are pure casts with no runtime check, and every boundary (ACP `sessionId`, provider-issued `call.id`, the empty-string fallback in `dsh-llm-deepseek`) trusts the raw string today. A `SessionId.parse()` / `isValid()` companion that throws on malformed input at boundaries is a genuine gap, but it is a *runtime-behavior* change with its own design (what is "malformed"? what happens on failure?) and belongs in its own decision, not bundled into this type-only change. ## Verification -The landed invariants: `BashTaskId` and `OwnerToken` are defined in `dsh-bash` and threaded end-to-end (executor seam, the `dsh-bash-local` generation site, the `dsh-tool-bash` model-facing surface) with no `dsh-bash` dependency on `dsh-session`; no collection keyed by an in-scope branded id (`CallId`/`SessionId`/`BashTaskId`) is keyed by bare `string`; public method params and exported signatures keep the brand; and brands are constructed via the cast factory at each boundary where a raw string enters (provider call id, ACP session id, model-supplied `task_id`), never as scattered `as` casts. +The landed invariants: `BashTaskId` and `OwnerToken` are defined in `dsh-bash` and threaded end-to-end (Service Definition, the `dsh-bash-local` generation site, the `dsh-tool-bash` model-facing surface) with no `dsh-bash` dependency on `dsh-session`; no collection keyed by an in-scope branded id (`CallId`/`SessionId`/`BashTaskId`) is keyed by bare `string`; public method params and exported signatures keep the brand; and brands are constructed via the cast factory at each boundary where a raw string enters (provider call id, ACP session id, model-supplied `task_id`), never as scattered `as` casts. ## Consequences -- **Mechanical churn across two surfaces.** Propagating brands touches the bash seam (interface + impl + consumer) and the ACP session-id surface plus the persistence coordinator. The churn is broad but low-severity: a missed site is a compile error, not a silent bug. The change is observably type-only — no snapshot or e2e behavioral diff. It sits next to the [unified agent/session identity decision](../simplification/2026-06-20-unify-agent-and-session-id.md) because both touch the session-id / owner-token boundary; `OwnerToken` stays distinct from the unified id for the decoupling reason above. -- **Brands do not validate.** A brand is a confusability guard, not a correctness proof: a *wrong* session id that is still a well-formed string passes the type checker exactly as before. This Agent Note does not close that gap (see Out of scope) — it only stops the *category* error of passing the wrong *kind* of id. -- **The "where to stop" line stays a judgment call.** Branding `BashTaskId` but not `ToolName`, `OwnerToken` but not `ModelId`, is a taste call about which strings "could plausibly be confused." Reasonable reviewers may want more or fewer; the policy in `brand.ts` is the tie-breaker, and this Agent Note errs toward the ids that are model-facing or used for access control. +- **Mechanical churn across two surfaces.** Propagating brands touches the bash seam (Service Definition + Service provider + Consumer) and the ACP session-id surface plus the persistence coordinator. The churn is broad but low-severity: a missed site is a compile error, not a silent bug. The change is observably type-only — no snapshot or e2e behavioral diff. It sits next to the [unified agent/session identity decision](../simplification/2026-06-20-unify-agent-and-session-id.md) because both touch the session-id / owner-token boundary; `OwnerToken` stays distinct from the unified id for the decoupling reason above. +- **Brands do not validate.** A brand is a confusability guard, not a correctness proof: a *wrong* session id that is still a well-formed string passes the type checker exactly as before. This decision does not close that gap (see Out of scope) — it only stops the *category* error of passing the wrong *kind* of id. +- **The "where to stop" line stays a judgment call.** Branding `BashTaskId` but not `ToolName`, `OwnerToken` but not `ModelId`, is a taste call about which strings "could plausibly be confused." Reasonable reviewers may want more or fewer; the policy in `brand.ts` is the tie-breaker, and this decision errs toward the ids that are model-facing or used for access control. diff --git a/.agents/notes/implemented/architecture/2026-06-20-branded-ids.zh.md b/.agents/notes/implemented/architecture/2026-06-20-branded-ids.zh.md index 039953754b..613ef81d19 100644 --- a/.agents/notes/implemented/architecture/2026-06-20-branded-ids.zh.md +++ b/.agents/notes/implemented/architecture/2026-06-20-branded-ids.zh.md @@ -8,21 +8,21 @@ Status: implemented harness 使用 `Branded = string & { readonly [BRAND]: B }` 机制，为 `CallId`（`packages/llm/llm/src/brand.ts`）和 agent/会话共享的 `SessionId`（`packages/core/session/src/types.ts`）做 brand 处理；该机制由纯类型包 `@deepseek-ai/dsh-brand` 拥有，位于 `packages/util/brand/`，见其 [README](../../../../packages/util/brand/README.md)，并为每个类型提供零开销的 cast 工厂。`dsh-brand` 还声明了治理策略：*「Branding 用于跨包边界且可能被混淆的 id；不是每个 string 都需要 brand。」* 这条策略是正确的；问题在于它只落实了一半。两处缺口使得结构相同但语义错误的 string 今天仍能通过类型检查器。 -**缺口 1：bash seam 中未 brand 的跨边界 ID。** 后台 task id 是普通 `string`：`BashTask.id: string`（`packages/bash/bash/src/types.ts`），作为 `string` 贯穿整个执行器 seam（`packages/bash/bash/src/index.ts` 中的 `BashExecutor.get`/`ownerOf`/`readOutput`/`kill(id: string)`），再由面向模型的工具以 `string` 校验并传递（`validateTaskId`、`assertTaskAccess`、`packages/bash/tool-bash/src/index.ts` 中 `task_id` 的 schema 参数）。它由每执行器计数器生成——`packages/bash/bash-local/src/index.ts` 中的 `` `bash-${this.nextTaskId++}` ``——其形状与 `SessionId` 的默认值**完全相同，都是 `name-N`**（`packages/core/session/src/index.ts` 中的 `` `session-${++counter}` ``）。bash task id 和会话 id 在调用点轻易就能互换，而编译器毫无反应。这是用户询问的核心案例，并且它是面向模型的 id（模型会把 `task_id` 传回 `bash_output`/`bash_kill`），所以该混淆可由不受信任的输入触达。 +**缺口 1：bash seam 中未 brand 的跨边界 ID。** 后台 task id 是普通 `string`：`BashTask.id: string`（`packages/bash/bash/src/types.ts`），作为 `string` 贯穿整个执行器 seam（`packages/bash/bash/src/index.ts` 中的 `BashExecutor.get`/`ownerOf`/`readOutput`/`kill(id: string)`），再由面向模型的工具以 `string` 校验并传递（`validateTaskId`、`assertTaskAccess`、`packages/bash/tool-bash/src/index.ts` 中 `task_id` 的 schema 参数）。它由每执行器计数器生成——`packages/bash/bash-local/src/index.ts` 中的 `` `bash-${this.nextTaskId++}` ``——其形状与 `SessionId` 的默认值**完全相同，都是 `name-N`**（`packages/core/session/src/index.ts` 中的 `` `session-${++counter}` ``）。bash task id 和会话 id 在调用点轻易就能互换，而编译器毫无反应。它是面向模型的 id（模型会把 `task_id` 传回 `bash_output`/`bash_kill`），所以该混淆可由不受信任的输入触达。 bash **owner token** 是相关的子情形：`BashExecRequest.owner?: string` 和 `BashExecSpec.owner: string | undefined`（`packages/bash/bash/src/types.ts`）被文档描述为刻意*不透明*的隔离键，但在所有实际调用方中，该值就是所属 agent（智能体）共享的 `Agent.id`/`SessionId`（`callerToken = (exec) => exec.agent?.id`，位于 `packages/bash/tool-bash/src/index.ts`），只是披着另一个 seam 本地名称。它被用于访问控制比较（`owner !== callerToken(exec)`），因此一个不匹配但类型正确的 string 在此处就是跨会话隔离 bug，而当前类型系统无法捕获。这正是[统一 agent/session 标识决策](../simplification/2026-06-20-unify-agent-and-session-id.md)覆盖的共享 id 别名。 -**缺口 2：*已经 brand* 的 ID 在 seam 处被侵蚀。** 就连 `CallId` 和 `SessionId` 也恰好在最容易混淆的地方退化为裸 `string`：注册表/store 键类型和公开方法参数。代表性位置包括会话存储、agent 注册表（二者都以共享的 `SessionId` 为键）、工具展示层的 call-id map、ACP（Agent Client Protocol）的会话记录，以及持久化协调器。在集合键处丢弃 brand，会让既有 brand 在查找时毫无价值；它们的价值只实现了一部分。 +**缺口 2：*已经 brand* 的 ID 在边界处被侵蚀。** 就连 `CallId` 和 `SessionId` 也恰好在最容易混淆的地方退化为裸 `string`：注册表/store 键类型和公开方法参数。代表性位置包括会话存储、agent 注册表（二者都以共享的 `SessionId` 为键）、工具展示层的 call-id map、ACP（Agent Client Protocol）的会话记录，以及持久化协调器。在集合键处丢弃 brand，会让既有 brand 在查找时毫无价值；它们的价值只实现了一部分。 ## 决策 -纯类型变更。Brand 是零开销 cast；运行时行为、序列化、比较和协议格式（wire format）均不变。工作分三部分，全部遵循既有的「不是每个 string 都需要」策略。 +纯类型变更。Brand 是零开销 cast；运行时行为、序列化、比较和协议格式（wire format）均不变。该决策分三部分，全部遵循既有的「不是每个 string 都需要」策略。 -- **为 bash task id 加 brand。** 在 `packages/bash/bash/src/types.ts`（*拥有*该 id 的包）中添加 `BashTaskId = Branded<'BashTaskId'>` 及其同名工厂，从 `@deepseek-ai/dsh-brand` 导入 `Branded`，方式与 `SessionId` 完全一致。brand 原语位于无依赖的 `dsh-brand` 工具包中，正是为了让 `dsh-bash` 仅依赖它就能为自己的 id 加 brand，而无需引入 `dsh-llm`（或 `dsh-session`）来获取 `Branded`。将其贯穿 `BashTask.id`、`BashExecutor` seam 方法（`get`/`ownerOf`/`readOutput`/`kill`）、`dsh-bash-local` 中的生成点（在创建时对计数器输出做一次 brand），以及 `dsh-tool-bash` 的校验/访问面（`validateTaskId` 返回 `BashTaskId`；`task_id` 在模型 string 到达的工具边界处被 brand）。 +- **为 bash task id 加 brand。** 在 `packages/bash/bash/src/types.ts`（*拥有*该 id 的包）中添加 `BashTaskId = Branded<'BashTaskId'>` 及其同名工厂，从 `@deepseek-ai/dsh-brand` 导入 `Branded`，方式与 `SessionId` 完全一致。brand 原语位于无依赖的 `dsh-brand` 工具包中，正是为了让 `dsh-bash` 仅依赖它就能为自己的 id 加 brand，而无需引入 `dsh-llm`（或 `dsh-session`）来获取 `Branded`。将其贯穿 `BashTask.id`、`BashExecutor` Service Definition 方法（`get`/`ownerOf`/`readOutput`/`kill`）、`dsh-bash-local` 中的生成点（在创建时对计数器输出做一次 brand），以及 `dsh-tool-bash` 的校验/访问面（`validateTaskId` 返回 `BashTaskId`；`task_id` 在模型 string 到达的工具边界处被 brand）。 -- **铸造独立的 `OwnerToken` brand。** 在 `packages/bash/bash/src/types.ts` 中添加 `OwnerToken = Branded<'OwnerToken'>`；将 `BashExecRequest.owner` / `BashExecSpec.owner` / `BashExecutor.ownerOf` 的类型标注为 `OwnerToken | undefined`。`dsh-tool-bash` 消费方在边界处将 agent 共享的 `id`（`SessionId`）cast 为 `OwnerToken`——这是两套词汇唯一交汇的地方。bash seam 从不导入 `dsh-session`。（理由见下一节。） +- **铸造独立的 `OwnerToken` brand。** 在 `packages/bash/bash/src/types.ts` 中添加 `OwnerToken = Branded<'OwnerToken'>`；将 `BashExecRequest.owner` / `BashExecSpec.owner` / `BashExecutor.ownerOf` 的类型标注为 `OwnerToken | undefined`。`dsh-tool-bash` 消费方在边界处将 agent 共享的 `id`（`SessionId`）cast 为 `OwnerToken`——这是两套词汇唯一交汇的地方。bash Service Definition 从不导入 `dsh-session`。（理由见下一节。） -- **阻止 brand 侵蚀。** 将既有 brand 传播到缺口 2 列出的 `Map` 键类型和公开方法参数中：`Map`、`Map`、`get(id: SessionId)`、`Map`、ACP 的 `SessionId` surface、协调器的 `Map`。这是 diff 中机械量最大的部分，也是让*既有* brand 在查找处真正发挥作用（而不仅仅标注在结构体字段上）的关键。 +- **阻止 brand 侵蚀。** 将既有 brand 传播到缺口 2 列出的 `Map` 键类型和公开方法参数中：`Map`、`Map`、`get(id: SessionId)`、`Map`、ACP 的 `SessionId` surface、协调器的 `Map`。这是变更中机械量最大的部分，也是让*既有* brand 在查找处真正发挥作用（而不仅仅标注在结构体字段上）的关键。 示意形状（工厂模式与已有的三个 brand 完全一致）： @@ -46,24 +46,24 @@ export function OwnerToken(id: string): OwnerToken { ### 为什么不把 `owner` 类型标注为 `SessionId`？ -显而易见的捷径是直接把 `owner` 类型标注为 `SessionId`——它确实*总是*一个会话 id。我们否决这个方案。bash 执行器 seam 是能力 seam（接口 `dsh-bash`、实现 `dsh-bash-local`、消费方 `dsh-tool-bash`），其 owner token 被*明确记录为刻意不透明*：执行器「从不解释它（seam 中没有访问策略——那是消费方的职责）」（`packages/bash/bash/src/types.ts`）。把 seam 字段类型标注为 `SessionId`，会把 `dsh-session` 的词汇引入一个不应知道 owner token *含义*的包——这会让通用执行后端耦合会话模型，并违背不透明 token 的设计。取代 `dsh-bash-local` 的沙箱或远程执行器不应继承会话依赖。独立的 `OwnerToken` brand 使 seam 保持解耦：`dsh-bash` 只知道「owner 是某种带 brand 的不透明 token」，而已经决定访问策略的 `dsh-tool-bash` 消费方，是把其 `SessionId` cast 为 `OwnerToken` 的唯一边界。该 brand 仍带来安全收益（不能把 `BashTaskId` 或裸 string 传到 owner 位置），且不引入耦合。 +显而易见的捷径是直接把 `owner` 类型标注为 `SessionId`——它确实*总是*一个会话 id。我们否决这个方案。bash 执行器 seam 是能力 seam（Service Definition `dsh-bash`、Service provider `dsh-bash-local`、Consumer `dsh-tool-bash`），其 owner token 被*明确记录为刻意不透明*：执行器「从不解释它（seam 中没有访问策略——那是消费方的职责）」（`packages/bash/bash/src/types.ts`）。把 Service Definition 的字段类型标注为 `SessionId`，会把 `dsh-session` 的词汇引入一个不应知道 owner token *含义*的包——这会让通用执行后端耦合会话模型，并违背不透明 token 的设计。取代 `dsh-bash-local` 的沙箱或远程执行器不应继承会话依赖。独立的 `OwnerToken` brand 使 seam 保持解耦：`dsh-bash` 只知道「owner 是某种带 brand 的不透明 token」，而已经决定访问策略的 `dsh-tool-bash` 消费方，是把其 `SessionId` cast 为 `OwnerToken` 的唯一边界。该 brand 仍带来安全收益（不能把 `BashTaskId` 或裸 string 传到 owner 位置），且不引入耦合。 ## 不在范围内 / 可能的扩展 遵循「不是每个 string 都需要 brand」的策略，刻意保持窄范围。以下每项都是合理的未来 brand 候选，附带推迟理由而非承诺： -- **`ModelId`**（`GenerateOptions.model`，`LlmService` 适配器注册表的键）：一个真正的跨包查找键（config → agent → llm → 适配器）；合理的下一个 brand，仅为控制本 Agent Note 的影响范围而暂不纳入。 +- **`ModelId`**（`GenerateOptions.model`，`LlmService` 适配器注册表的键）：一个真正的跨包查找键（config → agent → llm → 适配器）；合理的下一个 brand，仅为控制本决策的影响范围而暂不纳入。 - **`ToolName`**（`ToolRegistry` 的键）：由作者定义、人类可读，且很少与其他 id 混淆；最弱的候选，可能不值得加 brand。 - **`ErrorCode`**（`HarnessError.code`）：一个封闭词汇（`ABORTED`、`NO_ADAPTER`……），不是逐实例的 id；如果要做，string 字面量联合类型比 brand 更合适。 - **数值序号**：轮次号、步骤号和事件 `seq` 是 `number` 而非 `string`，`Branded` 不适用；可以用并行的 `number & { readonly [BRAND]: B }` 变体来 brand 它们，但它们是位置序号、很少跨边界传递，收益较低。 -- **带校验的构造**：brand 工厂是纯 cast，无运行时检查，且每个边界（ACP `sessionId`、提供方签发的 `call.id`、`dsh-llm-deepseek` 中的空字符串回退）今天都信任裸 string。一个在边界处对格式错误的输入抛异常的 `SessionId.parse()` / `isValid()` 配套工具确实是缺口，但它是*运行时行为*变更，有自己的设计问题（什么算「格式错误」？失败时怎么办？），应在独立 Agent Note 中处理，不应捆绑进这次纯类型变更。 +- **带校验的构造**：brand 工厂是纯 cast，无运行时检查，且每个边界（ACP `sessionId`、提供方签发的 `call.id`、`dsh-llm-deepseek` 中的空字符串回退）今天都信任裸 string。一个在边界处对格式错误的输入抛异常的 `SessionId.parse()` / `isValid()` 配套工具确实是缺口，但它是*运行时行为*变更，有自己的设计问题（什么算「格式错误」？失败时会怎样？），应在独立决策中处理，不应捆绑进这次纯类型变更。 ## 验证 -已落地的不变式：`BashTaskId` 和 `OwnerToken` 定义在 `dsh-bash` 中，并端到端贯穿执行器 seam、`dsh-bash-local` 生成点与 `dsh-tool-bash` 面向模型的 surface，且 `dsh-bash` 未添加对 `dsh-session` 的依赖；没有任何以范围内 brand id（`CallId`/`SessionId`/`BashTaskId`）为键的集合使用裸 `string`；公开方法参数和导出签名保留 brand；每个原始 string 进入的边界（提供方 call id、ACP 会话 id、模型提供的 `task_id`）都通过 cast 工厂构造 brand，而不是散落的 `as` cast。 +已落地的不变式：`BashTaskId` 和 `OwnerToken` 定义在 `dsh-bash` 中，并端到端贯穿 Service Definition、`dsh-bash-local` 生成点与 `dsh-tool-bash` 面向模型的 surface，且 `dsh-bash` 未添加对 `dsh-session` 的依赖；没有任何以范围内 brand id（`CallId`/`SessionId`/`BashTaskId`）为键的集合使用裸 `string`；公开方法参数和导出签名保留 brand；每个原始 string 进入的边界（提供方 call id、ACP 会话 id、模型提供的 `task_id`）都通过 cast 工厂构造 brand，而不是散落的 `as` cast。 ## 后果 -- **两个接口面的机械性改动。** 传播 brand 涉及 bash seam（接口 + 实现 + 消费方）以及 ACP 会话 id 接口和持久化协调器。改动面广但严重度低：遗漏的位置是编译错误而非静默 bug。变更可观察地为纯类型变更——无快照或 e2e 行为差异。它与[统一 agent/会话标识决策](../simplification/2026-06-20-unify-agent-and-session-id.md)相邻，因为二者都触及会话 id / owner-token 边界；`OwnerToken` 出于上述解耦理由仍与统一后的 id 保持独立。 -- **Brand 不做校验。** Brand 是混淆防护，不是正确性证明：一个*错误的*会话 id 只要仍是格式正确的 string，就和以前一样能通过类型检查器。本 Agent Note 不关闭这个缺口（见「不在范围内」）——它只阻止这类*类别*错误：传入错误*种类*的 id。 -- **「在哪里停下」仍是判断题。** 为 `BashTaskId` 加 brand 但不为 `ToolName` 加，为 `OwnerToken` 加但不为 `ModelId` 加，是对哪些 string「可能被混淆」的品味判断。合理的评审者可能想要更多或更少；`brand.ts` 中的策略是裁决依据，本 Agent Note 倾向于面向模型或用于访问控制的 id。 +- **两个接口面的机械性改动。** 传播 brand 涉及 bash seam（Service Definition + Service provider + Consumer）以及 ACP 会话 id 接口和持久化协调器。改动面广但严重度低：遗漏的位置是编译错误而非静默 bug。变更可观察地为纯类型变更——无快照或 e2e 行为差异。它与[统一 agent/会话标识决策](../simplification/2026-06-20-unify-agent-and-session-id.md)相邻，因为二者都触及会话 id / owner-token 边界；`OwnerToken` 出于上述解耦理由仍与统一后的 id 保持独立。 +- **Brand 不做校验。** Brand 是混淆防护，不是正确性证明：一个*错误的*会话 id 只要仍是格式正确的 string，就和以前一样能通过类型检查器。本决策不关闭这个缺口（见「不在范围内」）——它只阻止这类*类别*错误：传入错误*种类*的 id。 +- **「在哪里停下」仍是判断题。** 为 `BashTaskId` 加 brand 但不为 `ToolName` 加，为 `OwnerToken` 加但不为 `ModelId` 加，是对哪些 string「可能被混淆」的品味判断。合理的评审者可能想要更多或更少；`brand.ts` 中的策略是裁决依据，本决策倾向于面向模型或用于访问控制的 id。 diff --git a/.agents/notes/implemented/architecture/2026-06-20-generic-long-running-tool-runtime.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-20-generic-long-running-tool-runtime.i18n.yaml index ebabaccdbb..6da549618b 100644 --- a/.agents/notes/implemented/architecture/2026-06-20-generic-long-running-tool-runtime.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-06-20-generic-long-running-tool-runtime.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-06-20-generic-long-running-tool-runtime.md -2026-06-20-generic-long-running-tool-runtime.md: 8cf6a34c3e4fc042bd73c147d83838734dfc9585 -2026-06-20-generic-long-running-tool-runtime.zh.md: 44241321f6e4da428fe3a6402440af344fd69f10 +2026-06-20-generic-long-running-tool-runtime.md: 0dd49fe60f2c45081973657ff960b780d2d47257 +2026-06-20-generic-long-running-tool-runtime.zh.md: 6e8458aea73536859bf4c81894679d31a5034d3a diff --git a/.agents/notes/implemented/architecture/2026-06-20-generic-long-running-tool-runtime.md b/.agents/notes/implemented/architecture/2026-06-20-generic-long-running-tool-runtime.md index 8cf6a34c3e..0dd49fe60f 100644 --- a/.agents/notes/implemented/architecture/2026-06-20-generic-long-running-tool-runtime.md +++ b/.agents/notes/implemented/architecture/2026-06-20-generic-long-running-tool-runtime.md @@ -17,9 +17,9 @@ The `tasks/` package group owns background-task semantics: - `@deepseek-ai/dsh-tasks` registers running work as `ctx.tasks` and owns task ids, authorization, snapshots, reads, cancellation, waiting, completion listeners, and cleanup. - `@deepseek-ai/dsh-tool-tasks` exposes `task_output`, `task_list`, and `task_kill`, injects completion notices, and supplies the background-task system-prompt guidance. -Long-running tools are producers. `dsh-tool-bash` adapts a `BashProcess` into incremental output and process cancellation; `dsh-tool-subagent` adapts a child run into final output and child disposal. The execution seams remain independent of sessions and the task registry. +Long-running tools are producers. `dsh-tool-bash` adapts a `BashProcess` into incremental output and process cancellation; `dsh-tool-subagent` adapts a child run into final output and child disposal. The bash and subagent capability seams remain independent of sessions and the task registry. -`TaskService` is the abstract seam in `@deepseek-ai/dsh-tasks`; the process-local registry is `LocalTaskService` in `@deepseek-ai/dsh-tasks-local` (the [task-registry seam Agent Note](2026-07-26-task-registry-seam.md) records that split). +`TaskService` is the Service Definition in `@deepseek-ai/dsh-tasks`; the process-local provider is `LocalTaskService` in `@deepseek-ai/dsh-tasks-local` (the [task-registry contract Agent Note](2026-07-26-task-registry-seam.md) records that split). ## Runtime contract @@ -103,7 +103,7 @@ Separate bash and subagent output/stop tools duplicate ids, isolation, cleanup, ### An immediate abstract task-runtime backend -The current `TaskStart.run()` contract passes in-process callbacks and exact `Agent` objects. A durable backend changes identity, restart, ownership, and observation semantics, so at introduction time the registry stayed one concrete service rather than freezing the wrong boundary. The [task-registry seam Agent Note](2026-07-26-task-registry-seam.md) later separated the contract from the process-local implementation without changing these in-process semantics. +The current `TaskStart.run()` contract passes in-process callbacks and exact `Agent` objects. A durable backend changes identity, restart, ownership, and observation semantics, so at introduction time the registry stayed one concrete service rather than freezing the wrong boundary. The [task-registry contract Agent Note](2026-07-26-task-registry-seam.md) later separated the contract from the process-local implementation without changing these in-process semantics. ### Consumer-owned authorization or cleanup events diff --git a/.agents/notes/implemented/architecture/2026-06-20-generic-long-running-tool-runtime.zh.md b/.agents/notes/implemented/architecture/2026-06-20-generic-long-running-tool-runtime.zh.md index 44241321f6..6e8458aea7 100644 --- a/.agents/notes/implemented/architecture/2026-06-20-generic-long-running-tool-runtime.zh.md +++ b/.agents/notes/implemented/architecture/2026-06-20-generic-long-running-tool-runtime.zh.md @@ -17,9 +17,9 @@ Status: implemented - `@deepseek-ai/dsh-tasks` 将运行中的工作注册为 `ctx.tasks`，并拥有 task id、授权、快照、读取、取消、等待、完成监听器与清理。 - `@deepseek-ai/dsh-tool-tasks` 暴露 `task_output`、`task_list` 和 `task_kill`，注入完成通知，并提供后台任务的系统提示词指导。 -长时间运行工具是生产方。`dsh-tool-bash` 将 `BashProcess` 适配为增量输出与进程取消；`dsh-tool-subagent` 将子运行适配为最终输出与子运行释放。执行 seam 保持独立，不依赖会话或任务注册表。 +长时间运行工具是生产方。`dsh-tool-bash` 将 `BashProcess` 适配为增量输出与进程取消；`dsh-tool-subagent` 将子运行适配为最终输出与子运行释放。bash 与 subagent 能力 seam 保持独立，不依赖会话或任务注册表。 -`TaskService` 是 `@deepseek-ai/dsh-tasks` 中的抽象 seam；进程内注册表是 `@deepseek-ai/dsh-tasks-local` 中的 `LocalTaskService`（该拆分记录在[任务注册表 seam Agent Note](2026-07-26-task-registry-seam.md)中）。 +`TaskService` 是 `@deepseek-ai/dsh-tasks` 中的 Service Definition；进程内 Service provider 是 `@deepseek-ai/dsh-tasks-local` 中的 `LocalTaskService`（该拆分记录在[任务注册表约定 Agent Note](2026-07-26-task-registry-seam.md)中）。 ## 运行时约定 @@ -103,7 +103,7 @@ bash seam 暴露 `resolve`、`run` 和 `start`。`start(spec)` 返回一个 `Bas ### 立即抽象任务运行时后端 -当前 `TaskStart.run()` 约定传入进程内回调与确切的 `Agent` 对象。持久化后端会改变身份、重启、所有权与观察语义，因此在引入之时注册表保持为单一具体服务，而非固化错误的边界。[任务注册表 seam Agent Note](2026-07-26-task-registry-seam.md)后来在不改变这些进程内语义的前提下，将约定与进程内实现分离。 +当前 `TaskStart.run()` 约定传入进程内回调与确切的 `Agent` 对象。持久化后端会改变身份、重启、所有权与观察语义，因此在引入之时注册表保持为单一具体服务，而非固化错误的边界。[任务注册表约定 Agent Note](2026-07-26-task-registry-seam.md)后来在不改变这些进程内语义的前提下，将约定与进程内实现分离。 ### 由消费方负责授权或清理事件 diff --git a/.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.i18n.yaml index b8540c3319..16dde8df0e 100644 --- a/.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.md -2026-06-21-bounded-llm-request-recovery.md: 587f2d26eee922e91c8797018964f983890eb8ec -2026-06-21-bounded-llm-request-recovery.zh.md: dfc5e3ab67b62042c37f05199ed39bf47ded0c5d +2026-06-21-bounded-llm-request-recovery.md: 985ac3803b8d35ea9275052946dc2cbb33480a9f +2026-06-21-bounded-llm-request-recovery.zh.md: 8d845cce797d3a17d1223970186a23ffcece1ec8 diff --git a/.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.md b/.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.md index 587f2d26ee..985ac3803b 100644 --- a/.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.md +++ b/.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.md @@ -48,11 +48,11 @@ Adapters extract structured facts before falling back to message inspection. The The shared transient-code set is intentionally small: adapter mappings for `RATE_LIMIT` and `SERVER`, explicit `TIMEOUT` and `TRANSPORT` codes for remote failures, and `EMPTY_RESPONSE` for a completed provider response with no content blocks. Both adapters classify the last case as an error finish; see [empty model responses are retryable](../bug-fix/2026-07-24-empty-model-response-is-retryable.md). Authentication, quota, invalid request, context overflow, protocol, abort, and unknown failures keep distinct stable codes and are not transient by default. Adding a code requires adapter fixtures and a documented policy decision; it does not require expanding a second failure-class enum. -### Put retry policy on the existing failed-step seam +### Put retry policy on the existing failed-step extension point `@deepseek-ai/dsh-llm-retry` is a function plugin that listens to `agent/request-error`. It introduces no service or new loop branch; the agent-loop package changes only the data carried through its existing failed-step recovery control flow. -The `agent/request-error` seam carries the current `LlmFailure`, an immutable list of prior failures that authorized retry turns in the consecutive recovery sequence, and the serving registration's immutable retry policy. The loop transports but does not interpret that policy, owns the consecutive failure history, and clears it after a successful model request. Normal `dsh-llm-retry` policy counts durable retry records scheduled by the same exact-provider policy, while `dsh-compact-basic` keeps its own context-overflow budget. Alternating transient and context-overflow failures therefore consume their owning finite budgets independently; the maximum request count is one plus the sum of the loaded finite budgets. +The `agent/request-error` waterfall carries the current `LlmFailure`, an immutable list of prior failures that authorized retry turns in the consecutive recovery sequence, and the serving registration's immutable retry policy. The loop transports but does not interpret that policy, owns the consecutive failure history, and clears it after a successful model request. Normal `dsh-llm-retry` policy counts durable retry records scheduled by the same exact-provider policy, while `dsh-compact-basic` keeps its own context-overflow budget. Alternating transient and context-overflow failures therefore consume their owning finite budgets independently; the maximum request count is one plus the sum of the loaded finite budgets. The [provider-policy decision](../feature/2026-07-24-provider-retry-policies.md) owns the current configuration shape. Provider adapters register their nested `retryPolicy`; omission uses normal defaults: two transient retries, a 500 millisecond initial delay, a 10 second delay cap, 10 percent jitter, and the five transient codes above. The count and delay bounds match the conservative edge of the inspected implementations: [OpenCode uses two request retries with 500 ms/10 s bounds](https://github.com/anomalyco/opencode/blob/9976269ab1accfc9f9dc98a4a688c516934de422/%70ackages/llm/src/route/executor.ts#L36-L39), [Pi separates three agent-level retries from provider retries and defaults provider retries to zero](https://github.com/earendil-works/pi/blob/3da591ab74ab9ab407e72ed882600b2c851fae21/%70ackages/coding-agent/docs/settings.md#L139-L147), and [Codex uses finite request/stream budgets plus a five-minute idle timeout](https://github.com/openai/codex/blob/0fb559f0f6e231a88ac02ea002d3ecd248e2b515/codex-rs/model-provider-info/src/lib.rs#L25-L33). Ten percent follows [Codex's bounded jitter](https://github.com/openai/codex/blob/0fb559f0f6e231a88ac02ea002d3ecd248e2b515/codex-rs/codex-client/src/retry.rs#L40-L47). @@ -74,9 +74,9 @@ Adapters perform one provider request per `stream()` call. The pi-ai adapter rem ### Bound stalled streams where they can be stopped -Each adapter exposes a validated `streamIdleTimeoutMs` configuration field with the five-minute prior-art default cited above. The interval is capped at Node's maximum timer delay so it cannot be clamped to one millisecond. It covers each outstanding iterator `next()` from demand to the next valid `StreamChunk`; time a consumer spends between `next()` calls is not provider idle time. +Each adapter exposes a validated `streamIdleTimeoutMs` configuration field with the five-minute prior-art default cited above. The interval is capped at Node's maximum timer delay so it cannot be clamped to one millisecond. It covers each outstanding iterator `next()` from demand to adapter-recognized provider activity; time a consumer spends between `next()` calls is not provider idle time. DeepSeek SSE comments count as transport activity but never become `StreamChunk` values or session-log events. -`@deepseek-ai/dsh-timeout` exposes a rearmable idle-watchdog primitive. One stable local `AbortController` is fused with the caller signal and passed to the transport for the whole adapter call; each outstanding `next()` arms the watchdog, resolution disarms it, and the next demand rearms it. Timeout aborts that stable controller with a capability-owned `TimeoutReason`, and `finally` clears the timer. The adapter classifies its watchdog as `TIMEOUT` and an earlier upstream abort as `ABORTED`. The existing one-shot `deadline()` is not presented as a sliding timer. +`@deepseek-ai/dsh-timeout` exposes a rearmable idle-watchdog primitive. One stable local `AbortController` is fused with the caller signal and passed to the transport for the whole adapter call; each outstanding `next()` arms the watchdog, resolution disarms it, and the next demand rearms it. Out-of-band transport activity calls `pulse()` to rearm an outstanding demand without yielding a value. Timeout aborts that stable controller with a capability-owned `TimeoutReason`, and `finally` clears the timer. The adapter classifies its watchdog as `TIMEOUT` and an earlier upstream abort as `ABORTED`. The existing one-shot `deadline()` is not presented as a sliding timer. Boundary tests prove termination at both actual transports. The hand-written adapter aborts its fetch/reader, and the pi-ai adapter maps the stable signal through the SDK and proves the SDK closes the response. A timer that merely rejects a consumer promise while leaving the request running does not satisfy the contract. @@ -113,9 +113,9 @@ If recovery is exhausted, the final failure is stored once on `turn/end.reason` - `agent/request-error` carries current failure facts, immutable prior-retried failure facts, and the serving registration's immutable retry policy; a success clears the history, and alternating transient/context-overflow integration tests prove the two policies consume only their own finite budgets. - Each provider adapter validates its nested retry policy at Loader startup, and `ctx.llm` captures it with the route; normal mode delegates ineligible paths and makes at most `maxRetries + 1` provider requests when no other policy applies. - HMR-during-backoff tests prove disposal unregisters the listener, aborts and awaits its captured callbacks, emits no retry decision after disposal, and leaves no timer or promise alive. -- Pure unit tests cover transient-code selection, exponential backoff and jitter bounds, valid and over-cap `Retry-After`, exhausted budgets, deterministic timer/random seams, and abort during backoff. +- Pure unit tests cover transient-code selection, exponential backoff and jitter bounds, valid and over-cap `Retry-After`, exhausted budgets, deterministic timer/random hooks, and abort during backoff. - Real agent-loop tests cover failure before chunks, partial chunks then failure, thrown and in-band failures, retry to success in a new turn, exhaustion to structured `turn/end.reason`, and composition with `dsh-compact-basic` context-overflow recovery. -- The partial-chunk integration test proves failed chunks remain attributed to the failed step, no assistant message or tool side effect is committed for that step, and the successful retry has distinct provenance. +- The partial-chunk integration test proves failed chunks remain attributed to the failed step, no assistant message or tool side effect is committed for that step, and the successful retry records its own chunk seqs and provider/model route. - The plugin-owned `llm/retry` event is non-surface, survives JSONL and SQLite round trips, is ignored by message derivation, and drives TUI and Web retraction plus scheduled-retry rendering. Client tests cover complete wire validation, clock-independent countdown, cancellation versus completed retry labels, and trajectory attribution; keyless UI snapshots cover Web scheduling and success, a real Web composition test covers partial transport failure through recovery, and ACP automation snapshots confirm that a discarded attempt stays off the wire while the recovered reply is emitted. - Idle-watchdog tests prove the stable signal is rearmed only while `next()` is outstanding, disarmed during consumer think time and in `finally`, and classified separately from a total-call deadline and an earlier caller abort; adapter tests prove the signal stops the underlying request rather than merely detaching it. - Direct `ctx.llm.stream()` callers remain single-attempt and receive the same structured failure facts. @@ -134,5 +134,5 @@ If recovery is exhausted, the final failure is stored once on `turn/end.reason` - [Structured error taxonomy](../../implemented/architecture/2026-06-11-structured-error-taxonomy.md) owns stable machine-routable codes and cause chaining. - [Reconstructable requests](../../implemented/architecture/2026-07-05-reconstructable-requests.md) makes provider/model and complete request inputs durable before dispatch. - [Timeout deadline library](../../implemented/architecture/2026-07-06-timeout-deadline-library.md) separates shared deadline classification from capability-owned termination. -- [After-call compaction pressure and context-overflow recovery](../../implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md) owns the current closed-step request-recovery seam and bounded overflow retry. +- [After-call compaction pressure and context-overflow recovery](../../implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md) owns the current closed-step request-recovery extension point and bounded overflow retry. - [Provider-routed LLM adapters](../../implemented/architecture/2026-07-14-provider-routed-llm-adapters.md) owns explicit provider/model routing and the one-adapter-per-provider invariant. diff --git a/.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.zh.md b/.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.zh.md index dfc5e3ab67..8d845cce79 100644 --- a/.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.zh.md +++ b/.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.zh.md @@ -48,11 +48,11 @@ agent loop（智能体循环）会将终止 finish 的 `LlmFailure` 传给 `agen 共享的暂时性 code 集有意保持很小：适配器针对 `RATE_LIMIT` 和 `SERVER` 的映射，远程失败使用的显式 `TIMEOUT` 和 `TRANSPORT` code，以及提供方响应已完成却没有内容块时使用的 `EMPTY_RESPONSE`。两个适配器都会把最后一种情况归类为错误 finish；详见[空模型响应可重试](../bug-fix/2026-07-24-empty-model-response-is-retryable.md)。身份验证、配额、无效请求、上下文溢出、协议、中止和未知失败都保留不同的稳定 code，且默认不属于暂时性失败。新增 code 需要适配器 fixture（测试前置数据）和已记录的策略决策；无需扩展第二个失败类枚举。 -### 将重试策略放在现有失败步骤 seam 上 +### 将重试策略放在现有失败步骤扩展点上 `@deepseek-ai/dsh-llm-retry` 是监听 `agent/request-error` 的函数插件。它不引入服务或新的循环分支；agent-loop 包仅会更改通过现有失败步骤恢复控制流携带的数据。 -`agent/request-error` seam 携带当前 `LlmFailure`、在连续恢复序列中授权重试轮次的不可变先前失败列表，以及实际服务注册所对应的不可变重试策略。循环只传递而不解释该策略；它拥有连续失败历史，并在模型请求成功后清除。`dsh-llm-retry` 的 normal 策略统计由同一项确切提供方策略安排的持久重试记录，`dsh-compact-basic` 则维护自己的上下文溢出预算。因此，暂时性失败与上下文溢出交替出现时，会各自独立消耗其有限预算；最大请求数等于 1 加上所有已加载有限预算之和。 +`agent/request-error` waterfall 携带当前 `LlmFailure`、在连续恢复序列中授权重试轮次的不可变先前失败列表，以及实际服务注册所对应的不可变重试策略。循环只传递而不解释该策略；它拥有连续失败历史，并在模型请求成功后清除。`dsh-llm-retry` 的 normal 策略统计由同一项确切提供方策略安排的持久重试记录，`dsh-compact-basic` 则维护自己的上下文溢出预算。因此，暂时性失败与上下文溢出交替出现时，会各自独立消耗其有限预算；最大请求数等于 1 加上所有已加载有限预算之和。 当前配置形状由[提供方策略决策](../feature/2026-07-24-provider-retry-policies.md)规定。提供方适配器会注册嵌套的 `retryPolicy`；省略时使用 normal 默认值：两次暂时性重试、500 毫秒初始延迟、10 秒延迟上限、10% 抖动，以及上述五个暂时性 code。计数与延迟边界参考了所调查实现中较保守的一端：[OpenCode 使用两次请求重试，延迟边界为 500 毫秒／10 秒](https://github.com/anomalyco/opencode/blob/9976269ab1accfc9f9dc98a4a688c516934de422/%70ackages/llm/src/route/executor.ts#L36-L39)；[Pi 将三次 agent 级重试与提供方重试分开，且提供方重试默认为零](https://github.com/earendil-works/pi/blob/3da591ab74ab9ab407e72ed882600b2c851fae21/%70ackages/coding-agent/docs/settings.md#L139-L147)；[Codex 使用有限请求／流预算以及五分钟空闲超时](https://github.com/openai/codex/blob/0fb559f0f6e231a88ac02ea002d3ecd248e2b515/codex-rs/model-provider-info/src/lib.rs#L25-L33)。10% 抖动参考 [Codex 的有界抖动](https://github.com/openai/codex/blob/0fb559f0f6e231a88ac02ea002d3ecd248e2b515/codex-rs/codex-client/src/retry.rs#L40-L47)。 @@ -74,9 +74,9 @@ agent-spine 演示组合包加载该插件，因此共享的 stdio/TUI、一次 ### 在能够终止停滞流的位置施加边界 -每个适配器都公开一个经过验证的 `streamIdleTimeoutMs` 配置字段，默认值采用上文引用的五分钟先例。该间隔不超过 Node 的最大定时器延迟，因此不会被钳制为 1 毫秒。它覆盖每个尚未完成的迭代器 `next()`：从消费方请求下一项开始，到下一条有效 `StreamChunk` 到达为止；消费方在两次 `next()` 调用之间花费的时间不属于提供方空闲时间。 +每个适配器都公开一个经过验证的 `streamIdleTimeoutMs` 配置字段，默认值采用上文引用的五分钟先例。该间隔不超过 Node 的最大定时器延迟，因此不会被钳制为 1 毫秒。它覆盖每个尚未完成的迭代器 `next()`：从消费方请求下一项开始，到适配器识别到提供方活动为止；消费方在两次 `next()` 调用之间花费的时间不属于提供方空闲时间。DeepSeek SSE（Server-Sent Events）注释计为传输活动，但绝不会成为 `StreamChunk` 值或会话日志事件。 -`@deepseek-ai/dsh-timeout` 公开一个可重新布防的空闲看门狗原语。一个稳定的局部 `AbortController` 会与调用方信号融合，并在整个适配器调用期间传给传输层；每个尚未完成的 `next()` 都会布防看门狗，该调用完成时解除布防，下一次请求数据时再重新布防。超时会使用能力自身拥有的 `TimeoutReason` 中止这个稳定控制器，`finally` 则会清除定时器。适配器将自身看门狗归类为 `TIMEOUT`，将更早发生的上游中止归类为 `ABORTED`。现有的一次性 `deadline()` 不会被描述为滑动计时器。 +`@deepseek-ai/dsh-timeout` 公开一个可重新布防的空闲看门狗原语。一个稳定的局部 `AbortController` 会与调用方信号融合，并在整个适配器调用期间传给传输层；每个尚未完成的 `next()` 都会布防看门狗，该调用完成时解除布防，下一次请求数据时再重新布防。带外传输活动会调用 `pulse()`，在不产生值的情况下为尚未完成的需求重新布防。超时会使用能力自身拥有的 `TimeoutReason` 中止这个稳定控制器，`finally` 则会清除定时器。适配器将自身看门狗归类为 `TIMEOUT`，将更早发生的上游中止归类为 `ABORTED`。现有的一次性 `deadline()` 不会被描述为滑动计时器。 边界测试证明两个实际传输层都能终止。手写适配器会中止其 fetch／reader，pi-ai 适配器会把稳定信号映射到 SDK，并证明 SDK 会关闭响应。如果定时器只拒绝消费方 promise，却让请求继续运行，就不满足此约定。 @@ -113,9 +113,9 @@ agent-spine 演示组合包加载该插件，因此共享的 stdio/TUI、一次 - `agent/request-error` 携带当前失败事实、不可变的先前已重试失败事实，以及实际服务注册所对应的不可变重试策略；成功会清除历史，暂时性失败／上下文溢出交替发生的集成测试证明两种策略只消耗各自的有限预算。 - 每个提供方适配器都在 Loader 启动时验证其嵌套重试策略，`ctx.llm` 则将该策略与路由一同捕获；normal mode 会委托不合格路径，而且在没有其他策略时最多发起 `maxRetries + 1` 次提供方请求。 - 退避期间执行 HMR 的测试证明：dispose 过程会注销监听器、中止并等待其捕获的回调，dispose 后不发出重试决策，也不留下存活的定时器或 promise。 -- 纯单元测试覆盖暂时性 code 选择、指数退避和抖动边界、有效及超出上限的 `Retry-After`、耗尽的预算、确定性定时器／随机数 seam，以及退避期间中止。 +- 纯单元测试覆盖暂时性 code 选择、指数退避和抖动边界、有效及超出上限的 `Retry-After`、耗尽的预算、确定性定时器／随机数钩子，以及退避期间中止。 - 真实 agent-loop 测试覆盖分片前失败、部分分片后失败、抛出及带内失败、在新轮次中重试至成功、耗尽后写入结构化 `turn/end.reason`，以及与 `dsh-compact-basic` 上下文溢出恢复的组合。 -- 部分分片集成测试证明：失败分片仍归属于失败步骤，该步骤不会提交 assistant 消息或工具副作用，成功的重试具有不同的来源信息。 +- 部分分片集成测试证明：失败分片仍归属于失败步骤，该步骤不会提交 assistant 消息或工具副作用，成功的重试会记录自己的分片 seq 和提供方／模型路由。 - 插件拥有的不进入表层的 `llm/retry` 事件可在 JSONL 和 SQLite 往返后保留，被消息派生忽略，并驱动 TUI 和 Web 撤回及计划重试渲染。客户端测试覆盖完整的 wire 验证、独立于时钟的倒计时、已取消与已完成重试标签的区别以及轨迹归属；无密钥 UI 快照覆盖 Web 的调度与成功，真实 Web 组合测试覆盖部分传输失败直至恢复，ACP 自动化快照确认，被丢弃的尝试不会通过协议发出，而恢复后的回复会正常发出。 - 空闲看门狗测试证明：只有 `next()` 尚未完成时才会重新布防稳定信号；在消费方思考期间及 `finally` 中会解除布防；它与总调用 deadline 以及更早发生的调用方中止分开分类。适配器测试证明该信号会终止底层请求，而不只是与其脱离。 - `ctx.llm.stream()` 的直接调用方仍只尝试一次，并收到相同的结构化失败事实。 @@ -134,5 +134,5 @@ agent-spine 演示组合包加载该插件，因此共享的 stdio/TUI、一次 - [结构化错误分类体系](../../implemented/architecture/2026-06-11-structured-error-taxonomy.md)负责稳定、可供机器路由的 code 与 cause chaining。 - [可重建请求](../../implemented/architecture/2026-07-05-reconstructable-requests.md)使提供方／模型和完整请求输入在分发前持久化。 - [超时 deadline 库](../../implemented/architecture/2026-07-06-timeout-deadline-library.md)将共享的 deadline 分类与能力自身拥有的终止操作分开。 -- [调用后压缩压力与上下文溢出恢复](../../implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md)负责当前已关闭步骤的请求恢复 seam 与有界溢出重试。 +- [调用后压缩压力与上下文溢出恢复](../../implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md)负责当前已关闭步骤的请求恢复扩展点与有界溢出重试。 - [提供方路由的 LLM（大语言模型）适配器](../../implemented/architecture/2026-07-14-provider-routed-llm-adapters.md)负责显式提供方／模型路由与每个提供方仅有一个适配器的不变量。 diff --git a/.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.i18n.yaml index 6303b1e77a..21c6e32e11 100644 --- a/.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.md -2026-06-21-mandatory-app-attribution-headers.md: de9125bc891cc62798480e2eccb2c90cb633de3a -2026-06-21-mandatory-app-attribution-headers.zh.md: 6f0d0199f859fd462fdecc24e4063cbd27311bab +2026-06-21-mandatory-app-attribution-headers.md: 12482ca80d19e5cd1e62b8860865db6cccea61ab +2026-06-21-mandatory-app-attribution-headers.zh.md: 43f356887948b88d34ba41d46ed1cd2f1c89a1e2 diff --git a/.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.md b/.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.md index de9125bc89..12482ca80d 100644 --- a/.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.md +++ b/.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.md @@ -6,7 +6,7 @@ English | [中文](2026-06-21-mandatory-app-attribution-headers.zh.md) ## Problem -LLM provider requests should identify the product making them. That is useful for provider-side support, abuse investigation, compatibility debugging, and traffic analytics. Before this Agent Note the harness only partially did this: the hand-rolled DeepSeek adapter sent a hand-copied `User-Agent` constant (`packages/llm/llm-deepseek/src/adapter.ts`), while the pi-ai-backed twin sent no harness-owned headers at all (`packages/llm/llm-pi-ai/src/adapter.ts`). New adapters could therefore omit attribution silently, and a library-backed adapter could drift from the hand-rolled adapter even though [the twin-adapter Agent Note](2026-06-13-twin-llm-adapters.md) exists to keep the provider seam honest across both implementations. +LLM provider requests should identify the product making them. That is useful for provider-side support, abuse investigation, compatibility debugging, and traffic analytics. Before this Agent Note the harness only partially did this: the hand-rolled DeepSeek adapter sent a hand-copied `User-Agent` constant (`packages/llm/llm-deepseek/src/adapter.ts`), while the pi-ai-backed twin sent no harness-owned headers at all (`packages/llm/llm-pi-ai/src/adapter.ts`). New adapters could therefore omit attribution silently, and a library-backed adapter could drift from the hand-rolled adapter even though [the twin-adapter Agent Note](2026-06-13-twin-llm-adapters.md) exists to keep the provider contract honest across both implementations. The immediate prompt came from OpenRouter's [App Attribution](https://openrouter.ai/docs/app-attribution) docs. OpenRouter creates app pages and rankings from `HTTP-Referer` plus display/category headers. That is valuable, but it is not the HTTP standard for application identity. The risk is adopting OpenRouter's exact header set as if it were universal, then leaking provider-specific headers to direct DeepSeek requests, future OpenAI/Anthropic/Vertex adapters, test servers, or proxies that log unknown fields indefinitely. @@ -26,15 +26,15 @@ The immediate prompt came from OpenRouter's [App Attribution](https://openrouter Provider request attribution is mandatory at the LLM adapter boundary, using the standard `User-Agent` header only. The rule: every product LLM adapter sends a static, non-secret application identity on every provider HTTP request, and every adapter has tests proving that `User-Agent` reaches the wire (a mock server asserting received headers; for a library-backed adapter, the library's header hook feeding the same mock-server assertion). -Do **not** implement OpenRouter app attribution in this Agent Note. `HTTP-Referer`, `X-OpenRouter-Title`, `X-Title`, and `X-OpenRouter-Categories` are OpenRouter-specific product-surface headers, not provider-neutral model-request attribution. They can be proposed later by an OpenRouter adapter or explicit OpenRouter mode, with its own privacy/product decision, tests, and docs. Until then, even requests pointed at OpenRouter send only the shared `User-Agent` attribution from this Agent Note. +OpenRouter app attribution is deliberately not implemented. `HTTP-Referer`, `X-OpenRouter-Title`, `X-Title`, and `X-OpenRouter-Categories` are OpenRouter-specific product-surface headers, not provider-neutral model-request attribution. They can be proposed later by an OpenRouter adapter or explicit OpenRouter mode, with its own privacy/product decision, tests, and docs. Until then, even requests pointed at OpenRouter send only the shared `User-Agent` attribution from this decision. -The provider-neutral identity is owned by `dsh-llm` (`packages/llm/llm/src/attribution.ts`), not by individual adapters. `AppIdentity` contains only public product facts needed to build `User-Agent`, and the default `APP_IDENTITY` settles the values the proposal left open: +The provider-neutral identity is owned by `dsh-llm` (`packages/llm/llm/src/attribution.ts`), not by individual adapters. `AppIdentity` contains only public product facts needed to build `User-Agent`, and the default `APP_IDENTITY` values: - product token for `User-Agent`: `deepseek-harness` (continuity with the pre-Agent Note wire value and the repo/org identity) - version: read from the owning package's manifest via `createRequire`, never a hand-copied constant - app URL: `https://github.com/deepseek-ai/deepseek-harness-sdk` - the planned public home, which must exist before release -The default is mandatory and non-empty. White-label deployments pass their own `AppIdentity` to `attributionHeaders(identity)` - the override seam is the function parameter, with no deployment config plumbing until a consumer needs it - and omission falls back to the harness default rather than suppressing attribution. There is no per-request API for the model, user prompt, session id, cwd, user email, API key owner, or local machine identity to influence these fields. +The default is mandatory and non-empty. White-label deployments pass their own `AppIdentity` to `attributionHeaders(identity)` - the override hook is the function parameter, with no deployment config plumbing until a consumer needs it - and omission falls back to the harness default rather than suppressing attribution. There is no per-request API for the model, user prompt, session id, cwd, user email, API key owner, or local machine identity to influence these fields. Wire mapping (`attributionHeaders`; header names lowercase in code - HTTP field names are case-insensitive on the wire): @@ -42,7 +42,7 @@ Wire mapping (`attributionHeaders`; header names lowercase in code - HTTP field |---|---| | All HTTP-based adapters | `User-Agent: {product}/{version} (+{url})` - the parenthesized `+url` comment stays within RFC 9110's conservative product/comment syntax. | | Direct DeepSeek endpoint | `User-Agent`; do not send OpenRouter-only headers unless DeepSeek documents an equivalent contract. | -| OpenRouter endpoints | `User-Agent` only for now. Do not send `HTTP-Referer`, `X-OpenRouter-Title`, `X-Title`, or `X-OpenRouter-Categories` under this Agent Note. | +| OpenRouter endpoints | `User-Agent` only for now. Do not send `HTTP-Referer`, `X-OpenRouter-Title`, `X-Title`, or `X-OpenRouter-Categories` under this decision. | | Future providers | `User-Agent` only unless a later provider-specific Agent Note accepts additional headers. Do not reuse `HTTP-Referer` by analogy. | Endpoint detection is not part of this Agent Note because no endpoint-specific mapping is accepted here. If OpenRouter support lands later, detection must be explicit: either a dedicated OpenRouter provider package or an explicit `provider: 'openrouter'` / `attributionTarget: 'openrouter'` config, not arbitrary path fragments or model names. @@ -55,13 +55,13 @@ The landed contract: - A shared helper (`attributionHeaders` / `userAgent`) constructs the app identity and the standard `User-Agent` value from package metadata, so adapters do not hand-copy version constants. - `dsh-llm-deepseek` sends the shared `User-Agent` on every request and its mock-server suite asserts the exact value. - `dsh-llm-pi-ai` sends the same `User-Agent` through pi-ai's `StreamOptions.headers` hook and its mock-server suite asserts the exact value. -- No adapter sends OpenRouter-specific attribution headers (`HTTP-Referer`, `X-OpenRouter-Title`, `X-Title`, `X-OpenRouter-Categories`) as part of this Agent Note. +- No adapter sends OpenRouter-specific attribution headers (`HTTP-Referer`, `X-OpenRouter-Title`, `X-Title`, `X-OpenRouter-Categories`) as part of this decision. - No app-attribution field carries secrets, local paths, session ids, prompt text, model output, user email, or per-user stable identifiers. - The adapter READMEs state the `User-Agent` attribution policy and explicitly avoid documenting OpenRouter app attribution as implemented behavior. ## Alternatives considered -**OpenRouter app attribution now.** Rejected for this Agent Note. Sending `HTTP-Referer` plus `X-OpenRouter-Title` would satisfy OpenRouter rankings, but those headers are a provider-specific product feature, not the provider-neutral model-request attribution this Agent Note is trying to standardize. Supporting them should be an explicit OpenRouter adapter/mode decision later, not hidden inside the first shared attribution helper. +**OpenRouter app attribution now.** Rejected for this decision. Sending `HTTP-Referer` plus `X-OpenRouter-Title` would satisfy OpenRouter rankings, but those headers are a provider-specific product feature, not the provider-neutral model-request attribution this decision standardizes. Supporting them should be an explicit OpenRouter adapter/mode decision later, not hidden inside the first shared attribution helper. **OpenRouter headers everywhere.** Rejected. It would treat a custom OpenRouter contract as a universal standard and send fields with misleading semantics to providers that did not ask for them. It also risks using `HTTP-Referer` as a generic app URL field even though standard HTTP already has `User-Agent` for product identity and `Referer` for a different browsing-context concept. diff --git a/.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.zh.md b/.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.zh.md index 6f0d0199f8..43f3568879 100644 --- a/.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.zh.md +++ b/.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.zh.md @@ -6,7 +6,7 @@ Status: implemented ## 问题 -LLM（大语言模型）提供方请求应当标识发出请求的产品。这对提供方侧的技术支持、滥用调查、兼容性调试和流量分析都有价值。在本 Agent Note 之前，harness 只做了部分工作：手写的 DeepSeek 适配器发送了一个手动复制的 `User-Agent` 常量（`packages/llm/llm-deepseek/src/adapter.ts`），而基于 pi-ai 的孪生适配器则完全不发送 harness 自有的头部（`packages/llm/llm-pi-ai/src/adapter.ts`）。因此新适配器可以悄无声息地省略归属标识，而基于库的适配器也可能与手写适配器产生偏差——尽管[孪生适配器 Agent Note](2026-06-13-twin-llm-adapters.md) 的存在正是为了让两种实现在提供方 seam 上保持诚实。 +LLM（大语言模型）提供方请求应当标识发出请求的产品。这对提供方侧的技术支持、滥用调查、兼容性调试和流量分析都有价值。在本 Agent Note 之前，harness 只做了部分工作：手写的 DeepSeek 适配器发送了一个手动复制的 `User-Agent` 常量（`packages/llm/llm-deepseek/src/adapter.ts`），而基于 pi-ai 的孪生适配器则完全不发送 harness 自有的头部（`packages/llm/llm-pi-ai/src/adapter.ts`）。因此新适配器可以悄无声息地省略归属标识，而基于库的适配器也可能与手写适配器产生偏差——尽管[孪生适配器 Agent Note](2026-06-13-twin-llm-adapters.md) 的存在正是为了让两种实现在提供方约定上保持诚实。 直接触发因素来自 OpenRouter 的[应用归属](https://openrouter.ai/docs/app-attribution)文档。OpenRouter 根据 `HTTP-Referer` 加上 display/category 头部来创建应用页面和排名。这有价值，但它不是 HTTP 标准中的应用身份机制。风险在于：把 OpenRouter 的精确头部集当作通用标准来采纳，然后将提供方特有的头部泄漏到直连 DeepSeek 的请求、未来的 OpenAI/Anthropic/Vertex 适配器、测试服务器或无限期记录未知字段的代理中。 @@ -26,15 +26,15 @@ LLM（大语言模型）提供方请求应当标识发出请求的产品。这 在 LLM 适配器边界，提供方请求归属是强制的，且仅使用标准 `User-Agent` 头部。规则：每个产品级 LLM 适配器在每个提供方 HTTP 请求上发送一个静态、非机密的应用身份，且每个适配器都有测试证明 `User-Agent` 到达了线路（mock 服务器断言收到的头部；对于基于库的适配器，通过库的头部钩子馈入同一个 mock 服务器断言）。 -本 Agent Note **不**实现 OpenRouter 应用归属。`HTTP-Referer`、`X-OpenRouter-Title`、`X-Title` 和 `X-OpenRouter-Categories` 是 OpenRouter 特有的产品展示头部，不是提供方无关的模型请求归属。它们可以后续由 OpenRouter 适配器或显式 OpenRouter 模式提出，附带自己的隐私/产品决策、测试和文档。在此之前，即使请求指向 OpenRouter，也只发送本 Agent Note 定义的共享 `User-Agent` 归属。 +OpenRouter 应用归属刻意未实现。`HTTP-Referer`、`X-OpenRouter-Title`、`X-Title` 和 `X-OpenRouter-Categories` 是 OpenRouter 特有的产品展示头部，不是提供方无关的模型请求归属。它们可以后续由 OpenRouter 适配器或显式 OpenRouter 模式提出，附带自己的隐私/产品决策、测试和文档。在此之前，即使请求指向 OpenRouter，也只发送本决策定义的共享 `User-Agent` 归属。 -提供方无关的身份由 `dsh-llm`（`packages/llm/llm/src/attribution.ts`）拥有，而非各适配器。`AppIdentity` 仅包含构建 `User-Agent` 所需的公开产品事实，默认的 `APP_IDENTITY` 确定了提案中留待决定的值： +提供方无关的身份由 `dsh-llm`（`packages/llm/llm/src/attribution.ts`）拥有，而非各适配器。`AppIdentity` 仅包含构建 `User-Agent` 所需的公开产品事实，默认的 `APP_IDENTITY` 取值如下： - `User-Agent` 的产品 token：`deepseek-harness`（与 Agent Note 之前的线路值及仓库/组织身份保持连续性） - 版本：通过 `createRequire` 从所属包的 manifest（元数据清单）读取，绝不手动复制常量 - 应用 URL：`https://github.com/deepseek-ai/deepseek-harness-sdk`——计划中的公开主页，且必须在发布前实际存在 -默认值是强制的且非空。白标部署通过向 `attributionHeaders(identity)` 传入自己的 `AppIdentity` 来覆盖——覆盖 seam 就是函数参数，在有消费方需要之前不做部署配置管道——省略时回退到 harness 默认值而非抑制归属。没有逐请求 API 允许模型、用户提示词、会话 id、cwd、用户邮箱、API key 所有者或本地机器身份影响这些字段。 +默认值是强制的且非空。白标部署通过向 `attributionHeaders(identity)` 传入自己的 `AppIdentity` 来覆盖——覆盖钩子就是函数参数，在有消费方需要之前不做部署配置管道——省略时回退到 harness 默认值而非抑制归属。没有逐请求 API 允许模型、用户提示词、会话 id、cwd、用户邮箱、API key 所有者或本地机器身份影响这些字段。 线路映射（`attributionHeaders`；代码中头部名称小写——HTTP 字段名在线路上不区分大小写）： @@ -42,7 +42,7 @@ LLM（大语言模型）提供方请求应当标识发出请求的产品。这 |---|---| | 所有基于 HTTP 的适配器 | `User-Agent: {product}/{version} (+{url})`——括号中的 `+url` 注释符合 RFC 9110 保守的 product/comment 语法。 | | 直连 DeepSeek 端点 | `User-Agent`；除非 DeepSeek 文档化了等效约定，否则不发送 OpenRouter 特有头部。 | -| OpenRouter 端点 | 目前仅 `User-Agent`。本 Agent Note 下不发送 `HTTP-Referer`、`X-OpenRouter-Title`、`X-Title` 或 `X-OpenRouter-Categories`。 | +| OpenRouter 端点 | 目前仅 `User-Agent`。本决策下不发送 `HTTP-Referer`、`X-OpenRouter-Title`、`X-Title` 或 `X-OpenRouter-Categories`。 | | 未来提供方 | 仅 `User-Agent`，除非后续提供方特有的 Agent Note 接受额外头部。不要类比复用 `HTTP-Referer`。 | 端点检测不在本 Agent Note 范围内，因为此处不接受任何端点特有的映射。如果后续支持 OpenRouter，检测必须是显式的：要么是专门的 OpenRouter 提供方包，要么是显式的 `provider: 'openrouter'` / `attributionTarget: 'openrouter'` 配置，而非任意路径片段或模型名称。 @@ -55,13 +55,13 @@ LLM（大语言模型）提供方请求应当标识发出请求的产品。这 - 共享辅助函数（`attributionHeaders` / `userAgent`）从包元数据构建应用身份和标准 `User-Agent` 值，适配器无需手动复制版本常量。 - `dsh-llm-deepseek` 在每个请求上发送共享的 `User-Agent`，其 mock 服务器套件断言精确值。 - `dsh-llm-pi-ai` 通过 pi-ai 的 `StreamOptions.headers` 钩子发送相同的 `User-Agent`，其 mock 服务器套件断言精确值。 -- 本 Agent Note 下没有适配器发送 OpenRouter 特有的归属头部（`HTTP-Referer`、`X-OpenRouter-Title`、`X-Title`、`X-OpenRouter-Categories`）。 +- 本决策下没有适配器发送 OpenRouter 特有的归属头部（`HTTP-Referer`、`X-OpenRouter-Title`、`X-Title`、`X-OpenRouter-Categories`）。 - 没有应用归属字段携带机密、本地路径、会话 id、提示词文本、模型输出、用户邮箱或逐用户的稳定标识符。 - 适配器 README 声明了 `User-Agent` 归属策略，并明确避免将 OpenRouter 应用归属记录为已实现的行为。 ## 曾考虑的替代方案 -**现在就实现 OpenRouter 应用归属。** 本 Agent Note 否决。发送 `HTTP-Referer` 加 `X-OpenRouter-Title` 可以满足 OpenRouter 排名，但这些头部是提供方特有的产品功能，不是本 Agent Note 试图标准化的提供方无关的模型请求归属。支持它们应当是后续显式的 OpenRouter 适配器/模式决策，而非隐藏在首个共享归属辅助函数中。 +**现在就实现 OpenRouter 应用归属。** 本决策否决。发送 `HTTP-Referer` 加 `X-OpenRouter-Title` 可以满足 OpenRouter 排名，但这些头部是提供方特有的产品功能，不是本决策所标准化的提供方无关的模型请求归属。支持它们应当是后续显式的 OpenRouter 适配器/模式决策，而非隐藏在首个共享归属辅助函数中。 **向所有提供方发送 OpenRouter 头部。** 否决。这会把一项自定义的 OpenRouter 惯例当作通用标准，并向未要求这些字段的提供方发送语义误导的头部。还有风险将 `HTTP-Referer` 当作通用应用 URL 字段使用，尽管标准 HTTP 已有 `User-Agent` 用于产品身份、`Referer` 用于不同的浏览上下文概念。 diff --git a/.agents/notes/implemented/architecture/2026-06-24-web-capability-seam.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-24-web-capability-seam.i18n.yaml index 43259e19b2..2824639954 100644 --- a/.agents/notes/implemented/architecture/2026-06-24-web-capability-seam.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-06-24-web-capability-seam.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-06-24-web-capability-seam.md -2026-06-24-web-capability-seam.md: b705236690859961ed69b307dbb59ebefcbd65ac -2026-06-24-web-capability-seam.zh.md: ea9261b4bc16cbd913c90f5ccb1aeebc1a0d8dea +2026-06-24-web-capability-seam.md: ccf04420425555055ce3810d25bf764db17322bb +2026-06-24-web-capability-seam.zh.md: 73f7d0d9b82c03d41bdc768f22b22316e1bc907f diff --git a/.agents/notes/implemented/architecture/2026-06-24-web-capability-seam.md b/.agents/notes/implemented/architecture/2026-06-24-web-capability-seam.md index b705236690..ccf0442042 100644 --- a/.agents/notes/implemented/architecture/2026-06-24-web-capability-seam.md +++ b/.agents/notes/implemented/architecture/2026-06-24-web-capability-seam.md @@ -6,7 +6,7 @@ English | [中文](2026-06-24-web-capability-seam.zh.md) ## Problem -The harness needs model-facing web tools without binding the model contract to one vendor's API shape. Search is the immediate pressure point: supporting both Exa search and Perplexity search from the start — two deliberately different provider shapes (Exa returns a flat `results[]` of `{title, url, highlights, publishedDate}`; Perplexity returns a generated answer plus citations) — is what proves the normalized seam does not just mirror one vendor. Fetch is a separate capability: an anonymous public HTTP(S) fetch backend has transport, security, redirect, decoding, and size-limit concerns that are not the same as provider-backed search. +The harness needs model-facing web tools without binding the model contract to one vendor's API shape. Search is the immediate pressure point: supporting both Exa search and Perplexity search from the start — two deliberately different provider shapes (Exa returns a flat `results[]` of `{title, url, highlights, publishedDate}`; Perplexity returns a generated answer plus citations) — is what proves the normalized web contract does not just mirror one vendor. Fetch is a separate operation: an anonymous public HTTP(S) fetch backend has transport, security, redirect, decoding, and size-limit concerns that are not the same as provider-backed search. The model-facing surface must stay stable while backends change. A search provider swap should not change how the model asks for a query, and a fetch implementation swap should not change how the model asks for a URL. Conversely, a provider package should not expose its own model-facing tool schema just because it has extra provider-specific knobs. @@ -38,7 +38,7 @@ The seam deliberately exposes no observation surface — no registry-change even ## Package topology -The three-package interface/implementation/consumer split follows bash and filesystem, but the *interface* package is closer to the LLM seam. `LlmService` (`packages/llm/llm/src/index.ts`) is a name-keyed provider registry: `registerAdapter(models, adapter)` stores adapters in a `Map`, returns a disposer, throws `DUPLICATE_ADAPTER` on duplicate keys, and throws `NO_ADAPTER` at resolution time. `ctx.web` follows that registry shape, but has two capability kinds and a richer selection policy (a configured provider id, or auto-select when exactly one usable provider is registered), so the `WebError` an execution throws can explain why a search or fetch capability cannot run. +The three-package Service Definition / Service provider / Consumer split follows bash and filesystem, but the *interface* package is closer to the LLM seam. `LlmService` (`packages/llm/llm/src/index.ts`) is a name-keyed provider registry: `registerAdapter(models, adapter)` stores adapters in a `Map`, returns a disposer, throws `DUPLICATE_ADAPTER` on duplicate keys, and throws `NO_ADAPTER` at resolution time. `ctx.web` follows that registry shape, but has two capability kinds and a richer selection policy (a configured provider id, or auto-select when exactly one usable provider is registered), so the `WebError` an execution throws can explain why a search or fetch capability cannot run. The dependency direction mirrors bash and filesystem: @@ -280,7 +280,7 @@ Tool execution lets these errors flow through `ToolRegistry.execute()`, which al ## Testing -Each layer is pinned at its own seam: the registry/selection/truncation/abort contract and the `WebError` codes in `dsh-web`; per-provider request/response mapping over recorded fixtures (Perplexity fixtures include URL-only citations so the optional source fields stay honest) plus a self-skipping with-key smoke per real provider; real local-HTTP behavior in `web-fetch-local`; and enablement-driven registration, structured execution errors, and result formatting through the real tool registry in `dsh-tool-web`. A real-Loader smoke guards the two export shapes ([postmortem 0001](../../../../docs/postmortem/0001-acp-default-export-drops-inject.md)): `dsh-web` is a default-exported service, while the providers and `tool-web` are namespace plugins where a stray `export default` would drop `inject`. +Each layer is pinned at its own boundary: the registry/selection/truncation/abort contract and the `WebError` codes in `dsh-web`; per-provider request/response mapping over recorded fixtures (Perplexity fixtures include URL-only citations so the optional source fields stay honest) plus a self-skipping with-key smoke per real provider; real local-HTTP behavior in `web-fetch-local`; and enablement-driven registration, structured execution errors, and result formatting through the real tool registry in `dsh-tool-web`. A real-Loader smoke guards the two export shapes ([postmortem 0001](../../../../docs/postmortem/0001-acp-default-export-drops-inject.md)): `dsh-web` is a default-exported service, while the providers and `tool-web` are namespace plugins where a stray `export default` would drop `inject`. ## Alternatives considered @@ -302,7 +302,7 @@ Rejected. Registration order is not a product policy. It can change with config ### Treat Firecrawl/Exa/Tavily/Parallel extraction as fetch -Rejected for the first version. Those providers often return extracted or summarized content rather than a concrete HTTP response. If the product needs extraction, design `web_extract` or deliberately widen the fetch seam later. +Rejected for the first version. Those providers often return extracted or summarized content rather than a concrete HTTP response. If the product needs extraction, design `web_extract` or deliberately widen the fetch operation later. ### Mirror Claude Code's `url + prompt` WebFetch shape @@ -327,10 +327,10 @@ Rejected for the seam. `prompt` turns fetch into LLM summarization and couples p - SSRF / private-network protection for `web_fetch`: block private, loopback, link-local, multicast, and otherwise non-public destinations so `web_fetch` is not an SSRF primitive. Doing it correctly is more than a URL-string check — it needs DNS-resolve-then-connect-to-the-validated-IP (to defeat DNS rebinding / TOCTOU), per-hop re-validation across redirects, and IPv6 edge handling (private ranges, IPv4-mapped addresses). Neither reference implementation surveyed does IP-level blocking (OpenCode does a prefix check then fetches; Claude Code relies on a centralized hostname blocklist plus a "private URLs will fail" prompt), so there is no implementation to copy and this is the harness's only SSRF defense — it warrants its own focused design/spike. Until it lands, `web_fetch` must only be enabled in deployments that cannot reach sensitive internal targets. - A `pdf` `WebFetchBody` kind: the `local-http` provider decodes text-extractable PDFs (best-effort, capped, `truncated`) into a `{ kind: 'pdf'; content; pageCount? }` arm, and `tool-web` renders it. This is fetch, not `web_extract` — PDF retrieval is a concrete HTTP 200 plus deterministic local decoding, not provider-side extraction of a non-HTTP resource. Adding it is a coordinated change across `dsh-web` (declare the arm), the provider (decode + narrow "binary rejection" to "reject binary except text-extractable PDF"; scanned/image PDFs needing OCR stay out of scope), and `tool-web` (render). The closed `WebFetchBody` union makes the consumer side fail to compile until the new arm is handled. - Provider-backed extraction as a separate `web_extract` capability, rather than widening `web_fetch` silently. -- Permission policy integration once the deferred permission system lands. +- Permission policy integration: the permission system now exists ([sandbox and approval](../feature/2026-07-06-sandbox.md), [web permission presets](../feature/2026-07-23-web-permission-and-approval.md)) but bundles only sandbox mode and approval policy; web permission policy remains unintegrated. - Provider-neutral search controls beyond `query` and `maxResults`, once Exa and Perplexity can both honor them honestly. ## Open questions - Should product app packages probe web configuration at startup (treating `WEB_PROVIDER_CONFIGURED_MISSING`, `WEB_PROVIDER_CONFIGURED_UNAVAILABLE`, and `WEB_PROVIDER_AMBIGUOUS` as fatal when web is explicitly configured), or leave misconfiguration to surface at the first execution? -- Where should permission policy for public web access live once the deferred permission system lands: a dedicated web permission plugin on `tools/execute`, provider config, or both? +- Where should permission policy for public web access live in the shipped permission system ([sandbox and approval](../feature/2026-07-06-sandbox.md), [web permission presets](../feature/2026-07-23-web-permission-and-approval.md)): a dedicated web permission plugin on `tools/execute`, provider config, or both? diff --git a/.agents/notes/implemented/architecture/2026-06-24-web-capability-seam.zh.md b/.agents/notes/implemented/architecture/2026-06-24-web-capability-seam.zh.md index ea9261b4bc..73f7d0d9b8 100644 --- a/.agents/notes/implemented/architecture/2026-06-24-web-capability-seam.zh.md +++ b/.agents/notes/implemented/architecture/2026-06-24-web-capability-seam.zh.md @@ -6,7 +6,7 @@ Status: implemented ## 问题 -harness 需要面向模型的 web 工具，但不能将模型约定绑定到某一家厂商的 API 形状上。搜索是当前的压力点：从一开始就同时支持 Exa 搜索和 Perplexity 搜索——两种刻意不同的提供方形状（Exa 返回扁平的 `results[]`，每项包含 `{title, url, highlights, publishedDate}`；Perplexity 返回一段生成式回答加引用列表）——正是用来证明归一化的 seam 并非只是镜像某一家厂商。Fetch 是另一项独立能力：匿名公开 HTTP(S) fetch 后端涉及传输、安全、重定向、解码和大小限制等关注点，与提供方支撑的搜索并不相同。 +harness 需要面向模型的 web 工具，但不能将模型约定绑定到某一家厂商的 API 形状上。搜索是当前的压力点：从一开始就同时支持 Exa 搜索和 Perplexity 搜索——两种刻意不同的提供方形状（Exa 返回扁平的 `results[]`，每项包含 `{title, url, highlights, publishedDate}`；Perplexity 返回一段生成式回答加引用列表）——正是用来证明归一化的 web 约定并非只是镜像某一家厂商。Fetch 是另一项独立操作：匿名公开 HTTP(S) fetch 后端涉及传输、安全、重定向、解码和大小限制等关注点，与提供方支撑的搜索并不相同。 面向模型的接口必须保持稳定，而后端可以更换。更换搜索提供方不应改变模型发起查询的方式；更换 fetch 实现不应改变模型请求 URL 的方式。反过来，提供方包也不应仅仅因为自己有额外的提供方特有旋钮就暴露自己的面向模型工具 schema。 @@ -38,7 +38,7 @@ Web 访问是一个一等能力 seam，遵循[能力 seam Agent Note](2026-06-13 ## 包拓扑 -由三个包构成的接口/实现/消费方拆分沿用 bash 和 filesystem 的模式，但*接口*包更接近 LLM（大语言模型） seam。`LlmService`（`packages/llm/llm/src/index.ts`）是一个按名称键控的提供方注册表：`registerAdapter(models, adapter)` 将适配器存入 `Map`、返回 disposer、对重复键抛出 `DUPLICATE_ADAPTER`、在解析时抛出 `NO_ADAPTER`。`ctx.web` 沿用该注册表形状，但有两种能力类别和更丰富的选择策略（配置的提供方 id，或在恰好只有一个可用提供方注册时自动选择），因此执行时抛出的 `WebError` 能解释搜索或 fetch 能力为何无法运行。 +由三个包构成的 Service Definition / Service provider / Consumer 拆分沿用 bash 和 filesystem 的模式，但*接口*包更接近 LLM（大语言模型） seam。`LlmService`（`packages/llm/llm/src/index.ts`）是一个按名称键控的提供方注册表：`registerAdapter(models, adapter)` 将适配器存入 `Map`、返回 disposer、对重复键抛出 `DUPLICATE_ADAPTER`、在解析时抛出 `NO_ADAPTER`。`ctx.web` 沿用该注册表形状，但有两种能力类别和更丰富的选择策略（配置的提供方 id，或在恰好只有一个可用提供方注册时自动选择），因此执行时抛出的 `WebError` 能解释搜索或 fetch 能力为何无法运行。 依赖方向与 bash 和 filesystem 一致： @@ -280,7 +280,7 @@ SSRF/私有网络防护（阻断私有、回环、链路本地、多播及其他 ## 测试 -每一层在自己的 seam 处固定：`dsh-web` 中的注册/选择/截断/abort 约定与 `WebError` 码；每个提供方基于录制的 fixture（测试前置数据）的请求/响应映射（Perplexity fixture 包含纯 URL 引用，以保持可选 source 字段的诚实性），加上每个真实提供方的自跳过带密钥冒烟测试；`web-fetch-local` 中的真实本地 HTTP 行为；`dsh-tool-web` 中通过真实工具注册表的启用驱动注册、结构化执行错误和结果格式化。一个真实 Loader 冒烟测试守护两种导出形状（[事故复盘（postmortem） 0001](../../../../docs/postmortem/0001-acp-default-export-drops-inject.md)）：`dsh-web` 是默认导出的服务，而提供方和 `tool-web` 是命名空间插件，误加 `export default` 会丢失 `inject`。 +每一层在自己的边界处固定：`dsh-web` 中的注册/选择/截断/abort 约定与 `WebError` 码；每个提供方基于录制的 fixture（测试前置数据）的请求/响应映射（Perplexity fixture 包含纯 URL 引用，以保持可选 source 字段的诚实性），加上每个真实提供方的自跳过带密钥冒烟测试；`web-fetch-local` 中的真实本地 HTTP 行为；`dsh-tool-web` 中通过真实工具注册表的启用驱动注册、结构化执行错误和结果格式化。一个真实 Loader 冒烟测试守护两种导出形状（[事故复盘（postmortem） 0001](../../../../docs/postmortem/0001-acp-default-export-drops-inject.md)）：`dsh-web` 是默认导出的服务，而提供方和 `tool-web` 是命名空间插件，误加 `export default` 会丢失 `inject`。 ## 曾考虑的替代方案 @@ -302,7 +302,7 @@ SSRF/私有网络防护（阻断私有、回环、链路本地、多播及其他 ### 将 Firecrawl/Exa/Tavily/Parallel 提取视为 fetch -在第一版中否决。这些提供方通常返回提取或摘要后的内容，而非具体的 HTTP 响应。如果产品需要提取，日后设计 `web_extract` 或刻意扩展 fetch seam。 +在第一版中否决。这些提供方通常返回提取或摘要后的内容，而非具体的 HTTP 响应。如果产品需要提取，日后设计 `web_extract` 或刻意扩展 fetch 操作。 ### 镜像 Claude Code 的 `url + prompt` WebFetch 形状 @@ -329,10 +329,10 @@ SSRF/私有网络防护（阻断私有、回环、链路本地、多播及其他 - `web_fetch` 的 SSRF/私有网络防护：阻断私有、回环、链路本地、多播及其他非公开目的地，使 `web_fetch` 不再是 SSRF 原语。正确实现不仅仅是 URL 字符串检查——需要先 DNS 解析再连接到已验证的 IP（防御 DNS rebinding/TOCTOU）、跨重定向的每跳重新验证，以及 IPv6 边缘处理（私有范围、IPv4 映射地址）。所调研的参考实现均未做 IP 级阻断（OpenCode 做前缀检查后直接 fetch；Claude Code 依赖集中式主机名黑名单加「私有 URL 会失败」的提示词），因此没有可复制的实现，且这是 harness 唯一的 SSRF 防线——值得一次专门的设计/spike。在其落地之前，`web_fetch` 只能在无法触达敏感内部目标的部署中启用。 - `pdf` `WebFetchBody` 类别：`local-http` 提供方将可文本提取的 PDF 解码（尽力而为、有上限、`truncated`）为 `{ kind: 'pdf'; content; pageCount? }` 分支，`tool-web` 渲染它。这是 fetch 而非 `web_extract`——PDF 获取是具体的 HTTP 200 加确定性的本地解码，不是提供方侧对非 HTTP 资源的提取。添加它是跨 `dsh-web`（声明分支）、提供方（解码 + 将「二进制拒绝」收窄为「拒绝二进制，但可文本提取的 PDF 除外」；需要 OCR 的扫描/图片 PDF 不在范围内）和 `tool-web`（渲染）的协调变更。封闭的 `WebFetchBody` 联合类型使消费方在新分支被处理之前编译失败。 - 提供方支撑的提取作为独立的 `web_extract` 能力，而非静默扩展 `web_fetch`。 -- 推迟的权限系统落地后的权限策略集成。 +- 权限策略集成：权限系统现已存在（[沙箱与审批](../feature/2026-07-06-sandbox.md)、[web 权限预设](../feature/2026-07-23-web-permission-and-approval.md)），但只捆绑了沙箱模式与审批策略；web 权限策略仍未集成。 - `query` 和 `maxResults` 之外的提供方无关搜索控制，待 Exa 和 Perplexity 都能诚实遵守时再添加。 ## 开放问题 - 产品应用包是否应在启动时探测 web 配置（当 web 被显式配置时将 `WEB_PROVIDER_CONFIGURED_MISSING`、`WEB_PROVIDER_CONFIGURED_UNAVAILABLE` 和 `WEB_PROVIDER_AMBIGUOUS` 视为致命错误），还是将配置错误留到首次执行时浮出？ -- 推迟的权限系统落地后，公开 web 访问的权限策略应放在哪里：`tools/execute` 上的专用 web 权限插件、提供方配置，还是两者兼有？ +- 在已交付的权限系统（[沙箱与审批](../feature/2026-07-06-sandbox.md)、[web 权限预设](../feature/2026-07-23-web-permission-and-approval.md)）中，公开 web 访问的权限策略应放在哪里：`tools/execute` 上的专用 web 权限插件、提供方配置，还是两者兼有？ diff --git a/.agents/notes/implemented/architecture/2026-06-26-file-context-as-event-gate.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-26-file-context-as-event-gate.i18n.yaml index 726ab7374d..c2d46de08f 100644 --- a/.agents/notes/implemented/architecture/2026-06-26-file-context-as-event-gate.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-06-26-file-context-as-event-gate.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-06-26-file-context-as-event-gate.md -2026-06-26-file-context-as-event-gate.md: 4700222aa2e0f91d9f355495c228e2eb92825f55 -2026-06-26-file-context-as-event-gate.zh.md: dff5c3e9ea99e73d3d1a86c4012da1e4232021bb +2026-06-26-file-context-as-event-gate.md: 743c8f150a83f2452cb0ff672860b8462a56f762 +2026-06-26-file-context-as-event-gate.zh.md: cd79b44dd3f3b75c5e5addc5be10c02bd1ce0151 diff --git a/.agents/notes/implemented/architecture/2026-06-26-file-context-as-event-gate.md b/.agents/notes/implemented/architecture/2026-06-26-file-context-as-event-gate.md index 4700222aa2..743c8f150a 100644 --- a/.agents/notes/implemented/architecture/2026-06-26-file-context-as-event-gate.md +++ b/.agents/notes/implemented/architecture/2026-06-26-file-context-as-event-gate.md @@ -26,21 +26,23 @@ tool dsh-tool-fs executor: resolves, reads windows, writes/edits policy dsh-fs-policy plugin: listens to fs/write-intent + fs/edit-intent (single-slot waterfall) and fs/observed (emit) events; adds observed-state + freshness. -provider seam dsh-fs ctx.fs: text IO + ATOMIC mutation primitives whose version +provider contract dsh-fs ctx.fs: text IO + ATOMIC mutation primitives whose version guard is OPTIONAL; owns the fs policy event vocabulary provider dsh-fs-local local implementation of ctx.fs ``` The model is additive: bare `ctx.fs` performs atomic, unconstrained text I/O, while `dsh-fs-policy` adds observed state, read-before-edit, and version guards. Removing the policy therefore leaves the tools usable but unconstrained. Shipped agent configs load the policy; the bare mode exists to keep policy optional at the service boundary, not as the normal deployment stance. +The [filesystem absence-observation follow-up](../bug-fix/2026-08-09-filesystem-absence-observation.md) refines the recording payload from a success-only version to explicit present/absent state and requires guarded creation to publish without replacement. The event-gate ownership and no-I/O policy boundary remain unchanged. + `dsh-tool-fs` no longer injects `fileContext`. It injects `fs` and `tools`/`systemPrompt`. ## The policy is enforced by provider CAS, not by `dsh-fs-policy` stat `dsh-fs-policy` enforces "you must write/edit based on the version you read" **without ever calling `stat` or comparing versions itself**. It supplies the observed version as the CAS basis and lets the provider's mutation critical section detect staleness: -- "Have you read this file?" is the one thing `dsh-fs-policy` decides locally — a `WeakMap` lookup, no I/O. No record ⇒ `FS_NOT_OBSERVED`. -- "Is the version you read still current?" is decided **inside `ctx.fs.editText`/`writeText`**, in the same atomic lock that performs the read-match-rename. `dsh-fs-policy` passes `vObserved` as the expectation; the provider raises `FS_STALE_VERSION` if the file has moved on. +- "What did this owner last observe?" is the one thing `dsh-fs-policy` decides locally — a `WeakMap` lookup, no I/O. No record means unseen; an absent record permits only guarded creation; a present record carries the replacement/edit basis. +- "Is the version still current, or is the create target still absent?" is decided **inside the provider's atomic mutation boundary**. `dsh-fs-policy` supplies `replaceIfVersion` or `createIfAbsent`; the provider raises `FS_STALE_VERSION` for a moved version and `FS_NOT_OBSERVED` when a guarded create loses to another creator. This is deliberate. If `dsh-fs-policy` stat-ed and compared versions in its waterfall handler, there would be a TOCTOU gap between that check and the tool's actual write — the file could change in between, so the check would be a false guarantee that the provider's lock has to back up anyway. Putting the version check in the provider's critical section is both race-free and zero extra `stat`. So `dsh-fs-policy` does **no** filesystem I/O; the "must be based on the latest read" guarantee is *realized* by CAS, and `dsh-fs-policy` only chooses the basis (`vObserved`) and gates on prior observation. @@ -68,14 +70,14 @@ The `FsWriteIntent` union itself does not change — the third "unconditional" s The events live in `@deepseek-ai/dsh-fs`, not in `dsh-fs-policy`. This is forced by the decoupling contract: `dsh-tool-fs` is the emitter, so it must reference the event types, and it must keep compiling even though `dsh-fs-policy` no longer provides a method service. `dsh-fs` is the package both `dsh-tool-fs` and `dsh-fs-policy` already depend on, so it is the only home that lets the emitter and the policy listener share a vocabulary without the emitter depending on the policy plugin. -These events carry existing `dsh-fs` vocabulary (`FsTarget`, `FsVersion`, `FsWriteIntent`) plus an opaque actor — not model-facing concepts (no line windows, numbered lines, or rendered footers leak down). +These events carry existing `dsh-fs` vocabulary (`FsTarget`, `FsVersion`, `FsObservation`, `FsWriteIntent`) plus an opaque actor — not model-facing concepts (no line windows, numbered lines, or rendered footers leak down). **The two `fs/*` decision events are single-slot, first-wins waterfalls.** `dsh-fs-policy` returns without calling `next()`, so it owns the slot in the default deployment; a listener registered earlier or with `prepend` would replace that policy. Permission, audit, and sandbox concerns remain on the composable `tools/execute` waterfall. -The actor is typed `object` in `dsh-fs` — a pure opaque carrier the provider seam never reads or narrows. The owner-derivation (`actor.agent?.session`) and the `{ agent?: { session? } }` structural shape stay entirely inside `dsh-fs-policy`, which narrows the `object` actor to that shape in its listeners. `dsh-fs` owns the event names and the fs vocabulary; it does NOT own the policy layer's runtime owner structure. +The actor is typed `object` in `dsh-fs` — a pure opaque carrier the provider contract never reads or narrows. The owner-derivation (`actor.agent?.session`) and the `{ agent?: { session? } }` structural shape stay entirely inside `dsh-fs-policy`, which narrows the `object` actor to that shape in its listeners. `dsh-fs` owns the event names and the fs vocabulary; it does NOT own the policy layer's runtime owner structure. ```ts -import type { FsTarget, FsVersion, FsWriteIntent } from '@deepseek-ai/dsh-fs' +import type { FsObservation, FsTarget, FsVersion, FsWriteIntent } from '@deepseek-ai/dsh-fs' interface Events { /** @@ -95,14 +97,14 @@ interface Events { */ 'fs/edit-intent'(target: FsTarget, actor: object | undefined, next: () => { version: FsVersion } | undefined | Promise<{ version: FsVersion } | undefined>): Promise<{ version: FsVersion } | undefined> /** - * Record that an actor observed a target at a version, after a successful - * read/write/edit. Fire-and-forget (plain emit). Listeners MUST be + * Record that an actor observed a target as present at a version or absent. + * Fire-and-forget (plain emit). Listeners MUST be * synchronous, side-effect-only recorders (`dsh-fs-policy`'s is a WeakMap * write); the tool does not guard the emit, so a throwing listener surfaces as * the tool's isError result. No listener ⇒ nothing recorded. * @mode emit */ - 'fs/observed'(target: FsTarget, version: FsVersion, actor: object | undefined): void + 'fs/observed'(target: FsTarget, observation: FsObservation, actor: object | undefined): void } ``` @@ -110,7 +112,7 @@ The `fs/*` decision events are **unbound waterfalls dispatched by the tool** (li ## Tool contract (`dsh-tool-fs`) -The tool keeps its model-facing schemas (`read`/`write`/`edit`, byte-for-byte unchanged) and prompt sections. The prompt guidance stays policy-first because a deployment loading the fs tools is expected to also load `dsh-fs-policy`: the model is still told to read before overwriting or editing, and any wording that says the "backend" requires that should be corrected to say the fs-policy plugin requires it. The bare-provider fallback does not change the prompt stance. +The tool keeps its model-facing schemas (`read`/`write`/`edit`, byte-for-byte unchanged) and prompt sections. The prompt guidance stays policy-first because a deployment loading the fs tools is expected to also load `dsh-fs-policy`: the model is still told to read before overwriting or editing, and that requirement is the fs-policy plugin's, not the backend's. The bare-provider fallback does not change the prompt stance. `dsh-tool-fs` gains the executor responsibilities relocated from the old `fileContext` method service, including **read rendering** (`read-render.ts`: `buildWindow` + `formatReadOutput`, `READ_MAX_BYTES`, `READ_MAX_LINE_LENGTH`, `FileReadOutcome`/`FileTextLine`, plus `STREAM_MIN_SIZE` in `read.ts`), which is the tool's rendering detail now that the tool owns the read. Those read-rendering types and helpers move into `dsh-tool-fs`; the policy plugin must not remain a type dependency for the tool. @@ -118,25 +120,25 @@ The tool keeps its model-facing schemas (`read`/`write`/`edit`, byte-for-byte un `stat` budget is minimized by letting the waterfall produce the expectation lazily — the bare default returns `undefined` (no guard) and never stats: -- **read** — one `stat` (type + size routing + version), then `readText`/`streamText`, then `buildWindow`, then an `emit('fs/observed', target, info.version, exec)`. The post-read confirming `stat` from the old `fileContext.read` is dropped; a writer racing between the routing stat and the read can at worst make a *later* guarded edit spuriously `FS_STALE_VERSION` (fail-closed: the model re-reads, never writes against the wrong version, since `editText` re-checks in its lock). -- **write** — `expectation = await ctx.waterfall('fs/write-intent', target, exec, () => undefined)`, then `ctx.fs.writeText(target, content, expectation)`, then an `emit('fs/observed', target, outcome.version, exec)`. **Zero stat in the tool** with or without `dsh-fs-policy`. -- **edit** — `expectation = await ctx.waterfall('fs/edit-intent', target, exec, () => undefined)`, then `ctx.fs.editText(target, edit, expectation)`, then an `emit('fs/observed', target, outcome.version, exec)`. **Zero stat in the tool** in both cases: the bare default is `undefined` (unconditional edit), so the tool never stats to manufacture a basis. If the target is absent, the provider reports `FS_STALE_VERSION` even on the unguarded path. +- **read** — one `stat`; a metadata miss emits `{ kind: 'absent' }` before returning `FS_NOT_FOUND`, while a file routes through `readText`/`streamText`, `buildWindow`, then emits `{ kind: 'present', version: info.version }`. The post-read confirming `stat` from the old `fileContext.read` stays dropped; a writer racing between the routing stat and the read can at worst make a later guarded edit spuriously stale. +- **write** — `expectation = await ctx.waterfall('fs/write-intent', target, exec, () => undefined)`, then `ctx.fs.writeText(target, content, expectation)`, then emit the present outcome version. **Zero stat in the tool** with or without `dsh-fs-policy`. +- **edit** — `expectation = await ctx.waterfall('fs/edit-intent', target, exec, () => undefined)`, then `ctx.fs.editText(target, edit, expectation)`, then emit the present outcome version. **Zero stat in the tool** in both cases: the bare default is `undefined` (unconditional edit), so the tool never stats to manufacture a basis. If the target is absent on the bare path, the provider reports `FS_STALE_VERSION`; the policy returns `FS_NOT_FOUND` directly when it already holds an absent observation. The tool passes `exec` (the tool-execution context) as the `actor` argument on every dispatch, so `dsh-fs-policy` can derive its observed-state owner. The tool does not know whether the policy plugin is present: it always provides the bare default behavior in the `next` thunk, and `dsh-fs-policy` short-circuits the thunk before it runs in the default deployment. -**`fs/observed` fires after a successful operation.** Its listeners must be synchronous, non-throwing recorders; the tool does not guard the plain emit, so a throwing listener would report failure after a mutation already succeeded. Async or fallible observation needs a separate event contract. +**`fs/observed` fires after a successful operation and after a metadata probe confirms absence.** Its listeners must be synchronous, non-throwing recorders; the tool does not guard the plain emit, so a throwing listener can replace the pending read error or report failure after a mutation already succeeded. Async or fallible observation needs a separate event contract. ## Policy plugin contract (`dsh-fs-policy`) -`dsh-fs-policy` is a plugin, not a service. It does not register `ctx.fileContext`, has no public method surface, and exposes no `read`/`write`/`edit`/`resolve` methods. It attaches three listeners via `ctx.on()` registrations (each returning a disposer for HMR). It keeps the observed-state `WeakMap>` and the structural owner derivation (narrowing the event's opaque `object` actor to its own `{ agent?: { session? } }` shape), but does not inject `fs` — every handler operates only on its own `WeakMap`, never on `ctx.fs`. +`dsh-fs-policy` is a plugin, not a service. It does not register `ctx.fileContext`, has no public method surface, and exposes no `read`/`write`/`edit`/`resolve` methods. It attaches three listeners via `ctx.on()` registrations (each returning a disposer for HMR). It keeps the observed-state `WeakMap>` and the structural owner derivation (narrowing the event's opaque `object` actor to its own `{ agent?: { session? } }` shape), but does not inject `fs` — every handler operates only on its own `WeakMap`, never on `ctx.fs`. -- `fs/write-intent` listener: `prior = getObserved(owner, key)`; return `prior ? { kind: 'replaceIfVersion', version: prior.version } : { kind: 'createIfAbsent' }`. It does NOT call `next()`: it fully owns the single decision slot. -- `fs/edit-intent` listener: `prior = getObserved(owner, key)`; if no `owner` or no `prior`, throw `FS_NOT_OBSERVED`; else return `{ version: prior.version }`. Also does not call `next()`. -- `fs/observed` listener: `record(owner, key, version)`. +- `fs/write-intent` listener: unseen/absent ⇒ `createIfAbsent`; present ⇒ `replaceIfVersion`. It does NOT call `next()`: it fully owns the single decision slot. +- `fs/edit-intent` listener: unseen ⇒ `FS_NOT_OBSERVED`; absent ⇒ `FS_NOT_FOUND`; present ⇒ its version guard. It does NOT call `next()`. +- `fs/observed` listener: record the present/absent discriminated value. -An observed-state entry is the **prior-observation record**: a successful `read`, `write`, OR `edit` all emit `fs/observed` and record `{ version }`, so the entry's presence means "this owner has observed this target at this version", not narrowly "has read it". This is what lets a create-then-edit or edit-then-edit sequence work without an intervening re-read: the mutation refreshes the recorded version to its own result, so the next edit's basis is the version it just produced. `FS_NOT_OBSERVED` rejects only an edit with NO prior observation of any kind. The owner is derived structurally from `{ agent?: { session? } }`; disposal drops all state (HMR safety). +An observed-state entry is the **prior-observation record**, but its discriminant matters. Successful read/write/edit records present at a version, allowing create-then-edit or edit-then-edit without an intervening read. A read/view that confirms absence replaces any old positive version with absent, allowing only a guarded create; a later successful create replaces it with the new present version. Missing entry alone means unseen and produces `FS_NOT_OBSERVED` for edit. The owner is derived structurally from `{ agent?: { session? } }`; disposal drops all state (HMR safety). -`dsh-fs-policy` is now a pure policy/recording plugin with no service surface — it influences the world only through the event seam. That is what removes the method coupling from `dsh-tool-fs`. +`dsh-fs-policy` is now a pure policy/recording plugin with no service surface — it influences the world only through the event gate. That is what removes the method coupling from `dsh-tool-fs`. ## Bare-provider behavior (no `dsh-fs-policy`) @@ -154,7 +156,7 @@ This amends — does not reverse — [the split-fs-seam Agent Note](../simplific ## Verification -Tests pin both paths: without `dsh-fs-policy`, the root tool plugin boots against `dsh-fs-local`, and read, create, overwrite, and unread edit succeed; with the policy, unread edit returns `FS_NOT_OBSERVED` and unread overwrite is gated by `createIfAbsent`. A later intent listener is not reached after the policy decides. Stale edits fail through provider CAS while the policy performs no `stat`; the tool budgets remain one `stat` for read and zero for write or edit on either path. Model-facing schemas remain byte-for-byte unchanged, so snapshots do not change. +Tests pin both paths: without `dsh-fs-policy`, the root tool plugin boots against `dsh-fs-local`, and read, create, overwrite, and unread edit succeed; with the policy, unread edit returns `FS_NOT_OBSERVED` and unread overwrite is gated by `createIfAbsent`. A later intent listener is not reached after the policy decides. Stale edits fail through provider CAS while the policy performs no `stat`; the tool budgets remain one `stat` for read and zero for write or edit on either path. The deletion recovery path is also assembled: stale mutation, missing reread, guarded recreation. Model-facing schemas remain byte-for-byte unchanged, while the recovered result transcript changes. ## Alternatives considered @@ -166,6 +168,6 @@ Tests pin both paths: without `dsh-fs-policy`, the root tool plugin boots agains - **Event indirection over a method call.** A waterfall + emit is less direct than `await ctx.fileContext.edit(...)`. The payoff is removing the tool-to-policy method dependency while keeping the default policy plugin; the cost is one more event vocabulary to learn. Mitigated by keeping the three events narrow and documenting the default-thunk semantics on each. - **Policy events in the storage seam.** `dsh-fs` gains two version-decision events plus a recording event though it is "just storage". This is the price of decoupling (the emitter cannot depend on the policy plugin). The events carry only `dsh-fs` vocabulary plus an opaque `object` actor and no model-facing concepts, so the seam stays free of line-window/observation policy types and of the agent/session owner structure. -- **Single policy occupant, first-wins by convention.** The `fs/write-intent`/`fs/edit-intent` slots hold exactly one decider; the first-registered (or `prepend`ed) listener wins and the rest are short-circuited. `dsh-fs-policy` owning the slot is a deployment convention, not an event-enforced invariant — a second decider registered first would bypass it. This is acceptable because a second fs-version-policy decider is a misconfiguration, not a feature. If a future need for *layered* fs version policy appears, it is a new Agent Note (a composable value-passing seam), not a silent second listener on these events. Layered permission/audit/sandbox interception already has its home on `tools/execute`. +- **Single policy occupant, first-wins by convention.** The `fs/write-intent`/`fs/edit-intent` slots hold exactly one decider; the first-registered (or `prepend`ed) listener wins and the rest are short-circuited. `dsh-fs-policy` owning the slot is a deployment convention, not an event-enforced invariant — a second decider registered first would bypass it. This is acceptable because a second fs-version-policy decider is a misconfiguration, not a feature. If a future need for *layered* fs version policy appears, it is a new Agent Note (a composable value-passing waterfall), not a silent second listener on these events. Layered permission/audit/sandbox interception already has its home on `tools/execute`. - **Dropping the post-read confirming stat** makes a follow-up *guarded* edit occasionally fail-closed (`FS_STALE_VERSION` → re-read) under a read/write race. This is a UX nicety lost, never a correctness hole; the provider lock still prevents wrong-version writes. - **The bare provider does no read-before-write/edit and no version check.** A deployment without `dsh-fs-policy` lets the model overwrite or edit any existing file unconditionally. This is the deliberate meaning of keeping the tool independent of a policy service: the safety disciplines live in the `dsh-fs-policy` plugin. A deployment that omits it is opting into an unconstrained filesystem on purpose; that is not the intended stance for a config that ships the fs tools. diff --git a/.agents/notes/implemented/architecture/2026-06-26-file-context-as-event-gate.zh.md b/.agents/notes/implemented/architecture/2026-06-26-file-context-as-event-gate.zh.md index dff5c3e9ea..cd79b44dd3 100644 --- a/.agents/notes/implemented/architecture/2026-06-26-file-context-as-event-gate.zh.md +++ b/.agents/notes/implemented/architecture/2026-06-26-file-context-as-event-gate.zh.md @@ -26,21 +26,23 @@ tool dsh-tool-fs executor: resolves, reads windows, writes/edits policy dsh-fs-policy plugin: listens to fs/write-intent + fs/edit-intent (single-slot waterfall) and fs/observed (emit) events; adds observed-state + freshness. -provider seam dsh-fs ctx.fs: text IO + ATOMIC mutation primitives whose version +provider contract dsh-fs ctx.fs: text IO + ATOMIC mutation primitives whose version guard is OPTIONAL; owns the fs policy event vocabulary provider dsh-fs-local local implementation of ctx.fs ``` 该模型是叠加式的：裸 `ctx.fs` 执行原子化、无约束的文本 I/O，而 `dsh-fs-policy` 叠加观测状态、先读后编辑和版本守卫。因此移除策略层后工具仍可用，只是不受约束。正式发布的 agent 配置会加载策略；裸模式的存在是为了让策略在服务边界保持可选，而非作为正常部署姿态。 +[文件系统缺失观测后续决策](../bug-fix/2026-08-09-filesystem-absence-observation.md)把记录载荷从仅表示成功的版本细化为显式的存在/缺失状态，并要求带防护的创建以不替换方式发布。事件门禁归属与无 I/O 策略边界保持不变。 + `dsh-tool-fs` 不再注入 `fileContext`。它注入 `fs` 和 `tools`/`systemPrompt`。 ## 策略由提供方 CAS 强制执行，而非 `dsh-fs-policy` 的 stat `dsh-fs-policy` 强制执行「你必须基于你读到的版本来写入/编辑」，**自身从不调用 `stat` 或比较版本**。它将观测到的版本作为 CAS 基准提供，让提供方的 mutation 临界区检测陈旧性： -- 「你读过这个文件吗？」是 `dsh-fs-policy` 在本地决定的唯一事项——一次 `WeakMap` 查找，无 I/O。无记录 ⇒ `FS_NOT_OBSERVED`。 -- 「你读到的版本是否仍为最新？」由 **`ctx.fs.editText`/`writeText` 内部**决定，在执行 read-match-rename 的同一个原子锁中完成。`dsh-fs-policy` 将 `vObserved` 作为期望值传入；如果文件已变更，提供方抛出 `FS_STALE_VERSION`。 +- 「该所有者最近观测到了什么？」是 `dsh-fs-policy` 在本地决定的唯一事项——一次 `WeakMap` 查找，无 I/O。无记录表示未见；缺失记录只允许带防护的创建；存在记录携带替换/编辑基准。 +- 「版本是否仍然有效，或者创建目标是否仍然缺失？」由**提供方的原子变更边界内部**决定。`dsh-fs-policy` 提供 `replaceIfVersion` 或 `createIfAbsent`；对于已经变化的版本，提供方抛出 `FS_STALE_VERSION`；带防护的创建若败给另一个创建者，则抛出 `FS_NOT_OBSERVED`。 这是有意为之的。如果 `dsh-fs-policy` 在其 waterfall（瀑布式事件）处理器中 stat 并比较版本，该检查与工具实际写入之间会存在 TOCTOU 间隙——文件可能在此期间变化，因此该检查只是一个虚假保证，提供方的锁无论如何都要兜底。将版本检查放在提供方的临界区中既无竞态又无额外 `stat`。所以 `dsh-fs-policy` **不做**任何文件系统 I/O；「必须基于最近一次读取」的保证由 CAS *实现*，`dsh-fs-policy` 只负责选择基准（`vObserved`）并对先前观测进行门控。 @@ -68,14 +70,14 @@ editText(target: FsTarget, edit: FsEditRequest, expected?: { version: FsVersion 事件定义在 `@deepseek-ai/dsh-fs` 中，而非 `dsh-fs-policy` 中。这是解耦约定所迫：`dsh-tool-fs` 是发射方，因此它必须引用事件类型，且即使 `dsh-fs-policy` 不再提供方法服务，它也必须能编译通过。`dsh-fs` 是 `dsh-tool-fs` 和 `dsh-fs-policy` 都已依赖的包，因此它是唯一能让发射方和策略监听方共享词汇而不让发射方依赖策略插件的归属地。 -这些事件携带既有的 `dsh-fs` 词汇（`FsTarget`、`FsVersion`、`FsWriteIntent`）加一个不透明的 actor——不携带面向模型的概念（行窗口、行号或渲染后的页脚不会泄漏到此层）。 +这些事件携带既有的 `dsh-fs` 词汇（`FsTarget`、`FsVersion`、`FsObservation`、`FsWriteIntent`）加一个不透明的 actor——不携带面向模型的概念（行窗口、行号或渲染后的页脚不会泄漏到此层）。 **两个 `fs/*` 决策事件是单槽、先到先得的 waterfall。** `dsh-fs-policy` 不调用 `next()` 直接返回，因此在默认部署中它占据该槽位；更早注册或使用 `prepend` 的监听器会替代该策略。权限、审计和沙箱关注点仍留在可组合的 `tools/execute` waterfall 上。 -actor 在 `dsh-fs` 中类型为 `object`——一个纯粹的不透明载体，提供方 seam 从不读取或收窄它。owner 的推导（`actor.agent?.session`）和 `{ agent?: { session? } }` 结构形状完全留在 `dsh-fs-policy` 内部，由其在监听器中将 `object` actor 收窄为该形状。`dsh-fs` 拥有事件名和 fs 词汇；它不拥有策略层的运行时 owner 结构。 +actor 在 `dsh-fs` 中类型为 `object`——一个纯粹的不透明载体，提供方约定从不读取或收窄它。owner 的推导（`actor.agent?.session`）和 `{ agent?: { session? } }` 结构形状完全留在 `dsh-fs-policy` 内部，由其在监听器中将 `object` actor 收窄为该形状。`dsh-fs` 拥有事件名和 fs 词汇；它不拥有策略层的运行时 owner 结构。 ```ts -import type { FsTarget, FsVersion, FsWriteIntent } from '@deepseek-ai/dsh-fs' +import type { FsObservation, FsTarget, FsVersion, FsWriteIntent } from '@deepseek-ai/dsh-fs' interface Events { /** @@ -95,14 +97,14 @@ interface Events { */ 'fs/edit-intent'(target: FsTarget, actor: object | undefined, next: () => { version: FsVersion } | undefined | Promise<{ version: FsVersion } | undefined>): Promise<{ version: FsVersion } | undefined> /** - * Record that an actor observed a target at a version, after a successful - * read/write/edit. Fire-and-forget (plain emit). Listeners MUST be + * Record that an actor observed a target as present at a version or absent. + * Fire-and-forget (plain emit). Listeners MUST be * synchronous, side-effect-only recorders (`dsh-fs-policy`'s is a WeakMap * write); the tool does not guard the emit, so a throwing listener surfaces as * the tool's isError result. No listener ⇒ nothing recorded. * @mode emit */ - 'fs/observed'(target: FsTarget, version: FsVersion, actor: object | undefined): void + 'fs/observed'(target: FsTarget, observation: FsObservation, actor: object | undefined): void } ``` @@ -110,7 +112,7 @@ interface Events { ## 工具约定（`dsh-tool-fs`） -工具保留其面向模型的 schema（`read`/`write`/`edit`，逐字节不变）和提示词段落。提示词引导仍以策略优先，因为加载 fs 工具的部署预期也会加载 `dsh-fs-policy`：模型仍被告知在覆写或编辑前先读取，任何声称「后端」要求如此的措辞应修正为 fs-policy 插件要求如此。裸提供方回退不改变提示词立场。 +工具保留其面向模型的 schema（`read`/`write`/`edit`，逐字节不变）和提示词段落。提示词引导仍以策略优先，因为加载 fs 工具的部署预期也会加载 `dsh-fs-policy`：模型仍被告知在覆写或编辑前先读取，而该要求来自 fs-policy 插件，并非后端。裸提供方回退不改变提示词立场。 `dsh-tool-fs` 获得从旧 `fileContext` 方法服务迁移来的执行器职责，包括**读取渲染**（`read-render.ts`：`buildWindow` + `formatReadOutput`、`READ_MAX_BYTES`、`READ_MAX_LINE_LENGTH`、`FileReadOutcome`/`FileTextLine`，以及 `read.ts` 中的 `STREAM_MIN_SIZE`），这些现在是工具的渲染细节，因为读取已由工具拥有。这些读取渲染类型和辅助函数移入 `dsh-tool-fs`；策略插件不得继续作为工具的类型依赖。 @@ -118,25 +120,25 @@ interface Events { 通过让 waterfall 惰性产出期望值来最小化 `stat` 预算——裸默认返回 `undefined`（无守卫），从不 stat： -- **read**——一次 `stat`（类型 + 大小路由 + 版本），然后 `readText`/`streamText`，然后 `buildWindow`，然后 `emit('fs/observed', target, info.version, exec)`。旧 `fileContext.read` 中读后确认的 `stat` 被移除；在路由 stat 和读取之间竞争的写入者最多只能使*后续*有守卫的编辑误报 `FS_STALE_VERSION`（为安全起见拒绝写入：模型会重新读取；由于 `editText` 会在其锁内复查，模型绝不会基于错误版本写入）。 -- **write**——`expectation = await ctx.waterfall('fs/write-intent', target, exec, () => undefined)`，然后 `ctx.fs.writeText(target, content, expectation)`，然后 `emit('fs/observed', target, outcome.version, exec)`。无论是否有 `dsh-fs-policy`，**工具内零 stat**。 -- **edit**——`expectation = await ctx.waterfall('fs/edit-intent', target, exec, () => undefined)`，然后 `ctx.fs.editText(target, edit, expectation)`，然后 `emit('fs/observed', target, outcome.version, exec)`。两种情况下**工具内零 stat**：裸默认为 `undefined`（无条件编辑），因此工具从不 stat 来制造基准。如果目标不存在，提供方即使在无守卫路径上也报告 `FS_STALE_VERSION`。 +- **read**——一次 `stat`；元数据未命中时，在返回 `FS_NOT_FOUND` 前 emit `{ kind: 'absent' }`；目标为文件时，则依次执行 `readText`/`streamText`、`buildWindow`，再 emit `{ kind: 'present', version: info.version }`。旧 `fileContext.read` 中读后确认的 `stat` 仍保持移除；在路由 stat 和读取之间竞争的写入者最多只能使后续带防护的编辑误报陈旧。 +- **write**——`expectation = await ctx.waterfall('fs/write-intent', target, exec, () => undefined)`，然后 `ctx.fs.writeText(target, content, expectation)`，再 emit 表示存在的结果版本。无论是否有 `dsh-fs-policy`，**工具内零 stat**。 +- **edit**——`expectation = await ctx.waterfall('fs/edit-intent', target, exec, () => undefined)`，然后 `ctx.fs.editText(target, edit, expectation)`，再 emit 表示存在的结果版本。两种情况下**工具内零 stat**：裸默认为 `undefined`（无条件编辑），因此工具从不 stat 来制造基准。如果裸路径上的目标不存在，提供方报告 `FS_STALE_VERSION`；策略已持有缺失观测时，则直接返回 `FS_NOT_FOUND`。 工具在每次分发时将 `exec`（工具执行上下文）作为 `actor` 参数传入，以便 `dsh-fs-policy` 推导其观测状态的 owner。工具不知道策略插件是否存在：它始终在 `next` thunk 中提供裸默认行为，而 `dsh-fs-policy` 在默认部署中会在 thunk 运行前短路它。 -**`fs/observed` 在操作成功后触发。** 其监听器必须是同步、不抛异常的记录器；工具不对 plain emit 做保护，因此抛异常的监听器会在 mutation 已成功后报告失败。异步或可失败的观测需要另一份事件约定。 +**`fs/observed` 在操作成功后，以及元数据探测确认缺失后触发。** 其监听器必须是同步、不抛异常的记录器；工具不对 plain emit 做保护，因此抛异常的监听器可能取代待返回的读取错误，或在 mutation 已成功后报告失败。异步或可失败的观测需要另一份事件约定。 ## 策略插件约定（`dsh-fs-policy`） -`dsh-fs-policy` 是插件，不是服务。它不注册 `ctx.fileContext`，没有公开方法面，不暴露 `read`/`write`/`edit`/`resolve` 方法。它通过 `ctx.on()` 注册三个监听器（每个返回一个 disposer 用于 HMR）。它维护观测状态 `WeakMap>`，以及结构化的 owner 推导（将事件中不透明的 `object` actor 收窄为自己的 `{ agent?: { session? } }` 形状），但不注入 `fs`——每个处理器只操作自己的 `WeakMap`，从不操作 `ctx.fs`。 +`dsh-fs-policy` 是插件，不是服务。它不注册 `ctx.fileContext`，没有公开方法面，不暴露 `read`/`write`/`edit`/`resolve` 方法。它通过 `ctx.on()` 注册三个监听器（每个返回一个 disposer 用于 HMR）。它维护观测状态 `WeakMap>`，以及结构化的 owner 推导（将事件中不透明的 `object` actor 收窄为自己的 `{ agent?: { session? } }` 形状），但不注入 `fs`——每个处理器只操作自己的 `WeakMap`，从不操作 `ctx.fs`。 -- `fs/write-intent` 监听器：`prior = getObserved(owner, key)`；返回 `prior ? { kind: 'replaceIfVersion', version: prior.version } : { kind: 'createIfAbsent' }`。它不调用 `next()`：完全占据单一决策槽位。 -- `fs/edit-intent` 监听器：`prior = getObserved(owner, key)`；如果无 `owner` 或无 `prior`，抛出 `FS_NOT_OBSERVED`；否则返回 `{ version: prior.version }`。同样不调用 `next()`。 -- `fs/observed` 监听器：`record(owner, key, version)`。 +- `fs/write-intent` 监听器：未见/缺失 ⇒ `createIfAbsent`；存在 ⇒ `replaceIfVersion`。它不调用 `next()`：完全占据单一决策槽位。 +- `fs/edit-intent` 监听器：未见 ⇒ `FS_NOT_OBSERVED`；缺失 ⇒ `FS_NOT_FOUND`；存在 ⇒ 返回其版本守卫。同样不调用 `next()`。 +- `fs/observed` 监听器：记录存在/缺失的可辨识值。 -一条观测状态条目是**先前观测记录**：成功的 `read`、`write` 或 `edit` 都会 emit `fs/observed` 并记录 `{ version }`，因此条目的存在意味着「此 owner 在此版本观测过此目标」，而非狭义的「已读取过」。这使得 create-then-edit 或 edit-then-edit 序列无需中间重新读取即可工作：mutation 将记录的版本刷新为自身的结果，因此下一次编辑的基准就是它刚产出的版本。`FS_NOT_OBSERVED` 只拒绝完全没有任何先前观测的编辑。owner 从 `{ agent?: { session? } }` 结构化推导；dispose 时丢弃所有状态（HMR 安全）。 +一条观测状态条目是**先前观测记录**，但其可辨识字段会影响决策。成功的 read/write/edit 会记录存在状态及版本，使 create-then-edit 或 edit-then-edit 序列无需中间重新读取即可工作。确认缺失的 read/view 会用缺失状态取代旧的正向版本，因此只允许带防护的创建；随后成功的创建会再用新的存在版本取代缺失状态。只有条目不存在才表示未见，并使 edit 返回 `FS_NOT_OBSERVED`。owner 从 `{ agent?: { session? } }` 结构化推导；dispose 时丢弃所有状态（HMR 安全）。 -`dsh-fs-policy` 现在是一个纯策略/记录插件，没有服务面——它只通过事件 seam 影响外界。这正是移除 `dsh-tool-fs` 方法耦合的关键。 +`dsh-fs-policy` 现在是一个纯策略/记录插件，没有服务面——它只通过事件门控影响外界。这正是移除 `dsh-tool-fs` 方法耦合的关键。 ## 裸提供方行为（无 `dsh-fs-policy`） @@ -154,7 +156,7 @@ interface Events { ## 验证 -测试固定了两条路径：无 `dsh-fs-policy` 时，根工具插件对 `dsh-fs-local` 启动，read、create、overwrite 和未读 edit 均成功；有策略时，未读 edit 返回 `FS_NOT_OBSERVED`，未读 overwrite 被 `createIfAbsent` 门控。策略决定后，后注册的 intent 监听器不会被触达。陈旧编辑通过提供方 CAS 失败，而策略不执行 `stat`；工具预算在两条路径上保持 read 一次 `stat`，write 或 edit 均为零次。面向模型的 schema 逐字节不变，因此快照不变。 +测试固定了两条路径：无 `dsh-fs-policy` 时，根工具插件对 `dsh-fs-local` 启动，read、create、overwrite 和未读 edit 均成功；有策略时，未读 edit 返回 `FS_NOT_OBSERVED`，未读 overwrite 被 `createIfAbsent` 门控。策略决定后，后注册的 intent 监听器不会被触达。陈旧编辑通过提供方 CAS 失败，而策略不执行 `stat`；工具预算在两条路径上保持 read 一次 `stat`，write 或 edit 均为零次。测试也组装了删除恢复路径：陈旧变更、重新读取时确认缺失、带防护的重新创建。面向模型的 schema 逐字节不变，但恢复后的结果 transcript（文本记录）发生变化。 ## 曾考虑的替代方案 @@ -166,6 +168,6 @@ interface Events { - **事件间接层取代方法调用。** 一次 waterfall + emit 不如 `await ctx.fileContext.edit(...)` 直接。收益是移除了工具到策略的方法依赖，同时保留默认策略插件；代价是多一套事件词汇需要学习。通过保持三个事件的窄小范围并在每个事件上记录 default-thunk 语义来缓解。 - **策略事件位于存储 seam 中。** `dsh-fs` 增加了两个版本决策事件和一个记录事件，尽管它「只是存储」。这是解耦的代价（发射方不能依赖策略插件）。这些事件只携带 `dsh-fs` 词汇加一个不透明的 `object` actor，不携带面向模型的概念，因此 seam 不沾染行窗口/观测策略类型，也不沾染 agent/会话所有者结构。 -- **单一策略占位者，按约定先到先得。** `fs/write-intent`/`fs/edit-intent` 槽位恰好容纳一个决策者；先注册（或 `prepend`）的监听器获胜，其余被短路。`dsh-fs-policy` 占据该槽位是部署约定，而非事件系统强制的不变式——一个先注册的第二决策者会绕过它。这是可接受的，因为第二个 fs 版本策略决策者是配置错误，而非功能。如果未来出现*分层* fs 版本策略的需求，那是一个新 Agent Note（可组合的值传递 seam），而非在这些事件上静默添加第二个监听器。分层的权限/审计/沙箱拦截已有其归属：`tools/execute`。 +- **单一策略占位者，按约定先到先得。** `fs/write-intent`/`fs/edit-intent` 槽位恰好容纳一个决策者；先注册（或 `prepend`）的监听器获胜，其余被短路。`dsh-fs-policy` 占据该槽位是部署约定，而非事件系统强制的不变式——一个先注册的第二决策者会绕过它。这是可接受的，因为第二个 fs 版本策略决策者是配置错误，而非功能。如果未来出现*分层* fs 版本策略的需求，那是一个新 Agent Note（可组合的值传递 waterfall），而非在这些事件上静默添加第二个监听器。分层的权限/审计/沙箱拦截已有其归属：`tools/execute`。 - **移除读后确认 stat** 使后续*有守卫*的编辑在 read/write 竞争下偶尔为安全起见拒绝写入（`FS_STALE_VERSION` → 重新读取）。这是丢失的 UX 便利，绝非正确性漏洞；提供方锁仍阻止基于错误版本的写入。 - **裸提供方不做先读后写/编辑，也不做版本检查。** 没有 `dsh-fs-policy` 的部署允许模型无条件覆写或编辑任何已有文件。这正是保持工具独立于策略服务的有意含义：安全纪律存在于 `dsh-fs-policy` 插件中。省略它的部署是有意选择无约束的文件系统；对于发布 fs 工具的配置而言，这不是预期的姿态。 diff --git a/.agents/notes/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.i18n.yaml index 459ffa188c..a1fac69cf4 100644 --- a/.agents/notes/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md -2026-06-30-bash-stdin-env-trusted-plugin-surface.md: aa0c785be84bcb8a49f8a2670afa0f6bed6277db -2026-06-30-bash-stdin-env-trusted-plugin-surface.zh.md: 48108fdd5b8217263590fba336480f1b487e882f +2026-06-30-bash-stdin-env-trusted-plugin-surface.md: d8193b47ff16da7efb5f6bf1c3f34c0e1251572c +2026-06-30-bash-stdin-env-trusted-plugin-surface.zh.md: 7f5bb62d92f27c49b0f7f262dc64dce39c89f2cd diff --git a/.agents/notes/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md b/.agents/notes/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md index aa0c785be8..d8193b47ff 100644 --- a/.agents/notes/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md +++ b/.agents/notes/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md @@ -6,9 +6,9 @@ English | [中文](2026-06-30-bash-stdin-env-trusted-plugin-surface.zh.md) ## Problem -The hooks subsystem runs external hook commands the way Claude Code and Codex do: a hook is a shell command that receives its event payload as **JSON on stdin** and reads context from a handful of **environment variables** (`CLAUDE_PROJECT_DIR`, `CLAUDE_PLUGIN_ROOT`, `PLUGIN_ROOT`, …). The harness already has a perfectly good command runner behind the `ctx.bash` capability seam ([dsh-bash](../../../../packages/bash/bash) → [dsh-bash-local](../../../../packages/bash/bash-local)), with process-group kills, output truncation/spill, and a credential scrub. Reusing it for hook execution means a hook bridge does not re-implement subprocess plumbing — but the seam had no way to write stdin or set extra env. This Agent Note adds those two inputs. +The hooks subsystem runs external hook commands the way Claude Code and Codex do: a hook is a shell command that receives its event payload as **JSON on stdin** and reads context from a handful of **environment variables** (`CLAUDE_PROJECT_DIR`, `CLAUDE_PLUGIN_ROOT`, `PLUGIN_ROOT`, …). The harness already has a perfectly good command runner behind the `ctx.bash` capability seam ([dsh-bash](../../../../packages/bash/bash) → [dsh-bash-local](../../../../packages/bash/bash-local)), with process-group kills, output truncation/spill, and a credential scrub. Reusing it for hook execution means a hook bridge does not re-implement subprocess plumbing — but the seam had no way to write stdin or set extra env. This change adds those two inputs. -`stdin` and `env` do not create a new model capability because ordinary shell syntax already supplies both. Ambient credentials are protected by `dsh-bash-local`'s child-environment scrub, not by hiding these seam fields; model tool arguments are static JSON and do not expand shell variables. The fields therefore serve trusted in-process callers, such as hook bridges, that need to pass structured input and `CLAUDE_*` variables without embedding them in model-visible shell text. See [defensive-patterns.md](../../../../docs/defensive-patterns.md) for the ambient-environment rule. +`stdin` and `env` do not create a new model capability because ordinary shell syntax already supplies both. Ambient credentials are protected by `dsh-bash-local`'s child-environment scrub, not by hiding these Service Definition fields; model tool arguments are static JSON and do not expand shell variables. The fields therefore serve trusted in-process callers, such as hook bridges, that need to pass structured input and `CLAUDE_*` variables without embedding them in model-visible shell text. See [defensive-patterns.md](../../../../docs/defensive-patterns.md) for the ambient-environment rule. ## Decision @@ -16,7 +16,7 @@ Add `stdin?: string` and `env?: Record` to **both** `BashExecReq Three deliberate choices: -1. **The model-facing tool omits `stdin` and `env`.** Shell syntax already covers those needs, so duplicate parameters would add surface without authority separation. The tool builds requests only from declared model arguments, signal, and owner; trusted in-process callers may set the seam fields directly. Harness-owned variables use the separate `dshEnv` channel from the [managed environment decision](../feature/2026-07-10-agent-session-identity-and-log-location.md), so ordinary `env` cannot replace them. +1. **The model-facing tool omits `stdin` and `env`.** Shell syntax already covers those needs, so duplicate parameters would add surface without authority separation. The tool builds requests only from declared model arguments, signal, and owner; trusted in-process callers may set the request fields directly. Harness-owned variables use the separate `dshEnv` channel from the [managed environment decision](../feature/2026-07-10-agent-session-identity-and-log-location.md), so ordinary `env` cannot replace them. 2. **`env` merges AFTER the credential scrub, so an explicit caller entry wins even on a credential-shaped name.** The later managed-namespace decision manages `DSH_*`: ambient entries are removed, and trusted `dshEnv` merges last, so an ordinary `env` entry can never displace a managed value. The complete order is `scrub(process.env, including DSH_*)` → `ENV_OVERRIDES` → ordinary `env` → `dshEnv`. diff --git a/.agents/notes/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.zh.md b/.agents/notes/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.zh.md index 48108fdd5b..7f5bb62d92 100644 --- a/.agents/notes/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.zh.md +++ b/.agents/notes/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.zh.md @@ -6,9 +6,9 @@ Status: implemented ## 问题 -钩子子系统以 Claude Code 和 Codex 的方式运行外部钩子命令：钩子是一条 shell 命令，通过 **stdin 上的 JSON** 接收事件载荷，并从若干**环境变量**（`CLAUDE_PROJECT_DIR`、`CLAUDE_PLUGIN_ROOT`、`PLUGIN_ROOT`……）读取上下文。harness 已经在 `ctx.bash` 能力 seam 后面有一个完善的命令执行器（[dsh-bash](../../../../packages/bash/bash) → [dsh-bash-local](../../../../packages/bash/bash-local)），具备进程组终止、输出截断/溢出处理和凭证擦除功能。复用它来执行钩子意味着钩子桥接层无需重新实现子进程管道——但该 seam 此前无法写入 stdin 或设置额外 env。本 Agent Note 添加这两个输入。 +钩子子系统以 Claude Code 和 Codex 的方式运行外部钩子命令：钩子是一条 shell 命令，通过 **stdin 上的 JSON** 接收事件载荷，并从若干**环境变量**（`CLAUDE_PROJECT_DIR`、`CLAUDE_PLUGIN_ROOT`、`PLUGIN_ROOT`……）读取上下文。harness 已经在 `ctx.bash` 能力 seam 后面有一个完善的命令执行器（[dsh-bash](../../../../packages/bash/bash) → [dsh-bash-local](../../../../packages/bash/bash-local)），具备进程组终止、输出截断/溢出处理和凭证擦除功能。复用它来执行钩子意味着钩子桥接层无需重新实现子进程管道——但该 seam 此前无法写入 stdin 或设置额外 env。本次变更添加这两个输入。 -`stdin` 和 `env` 不构成新的模型能力，因为普通 shell 语法已经能提供两者。环境凭证由 `dsh-bash-local` 的子环境擦除机制保护，而非靠隐藏这些 seam 字段；模型工具参数是静态 JSON，不会展开 shell 变量。因此这些字段服务于受信的进程内调用方（如钩子桥接层），它们需要传递结构化输入和 `CLAUDE_*` 变量，而不必将其嵌入模型可见的 shell 文本。环境变量规则见 [defensive-patterns.md](../../../../docs/defensive-patterns.md)。 +`stdin` 和 `env` 不构成新的模型能力，因为普通 shell 语法已经能提供两者。环境凭证由 `dsh-bash-local` 的子环境擦除机制保护，而非靠隐藏这些 Service Definition 字段；模型工具参数是静态 JSON，不会展开 shell 变量。因此这些字段服务于受信的进程内调用方（如钩子桥接层），它们需要传递结构化输入和 `CLAUDE_*` 变量，而不必将其嵌入模型可见的 shell 文本。环境变量规则见 [defensive-patterns.md](../../../../docs/defensive-patterns.md)。 ## 决策 @@ -16,7 +16,7 @@ Status: implemented 三个有意为之的选择： -1. **模型侧工具不暴露 `stdin` 和 `env`。** Shell 语法已覆盖这些需求，重复参数只会增加接口面而不带来权限隔离。工具仅从声明的模型参数、signal 和 owner 构建请求；受信的进程内调用方可以直接设置 seam 字段。harness 自有变量使用[托管环境决策](../feature/2026-07-10-agent-session-identity-and-log-location.md)规定的独立 `dshEnv` 通道，因此普通 `env` 无法替换它们。 +1. **模型侧工具不暴露 `stdin` 和 `env`。** Shell 语法已覆盖这些需求，重复参数只会增加接口面而不带来权限隔离。工具仅从声明的模型参数、signal 和 owner 构建请求；受信的进程内调用方可以直接设置请求字段。harness 自有变量使用[托管环境决策](../feature/2026-07-10-agent-session-identity-and-log-location.md)规定的独立 `dshEnv` 通道，因此普通 `env` 无法替换它们。 2. **`env` 在凭证擦除之后合并，因此调用方显式设置的条目即使具有凭证形态的名称也会胜出。** 后续的托管命名空间决策负责管理 `DSH_*`：这类环境条目会被移除，受信的 `dshEnv` 最后合并，因此普通 `env` 条目永远无法顶掉托管值。完整顺序为 `scrub(process.env, including DSH_*)` → `ENV_OVERRIDES` → 普通 `env` → `dshEnv`。 diff --git a/.agents/notes/implemented/architecture/2026-06-30-event-domain-semantics.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-30-event-domain-semantics.i18n.yaml index 2e69991c33..8916c347d9 100644 --- a/.agents/notes/implemented/architecture/2026-06-30-event-domain-semantics.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-06-30-event-domain-semantics.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-06-30-event-domain-semantics.md -2026-06-30-event-domain-semantics.md: 14102b105e7bcaa6a00ac9c406933f772fc45a6f -2026-06-30-event-domain-semantics.zh.md: 2607e59490d8ba139bb1289d0f2941894281f6c6 +2026-06-30-event-domain-semantics.md: dbb3ef49979b7eeaa9a43b7db4a2d5a5839b5569 +2026-06-30-event-domain-semantics.zh.md: 93fe14adeaa47d276219a316ff1250a9982f5f14 diff --git a/.agents/notes/implemented/architecture/2026-06-30-event-domain-semantics.md b/.agents/notes/implemented/architecture/2026-06-30-event-domain-semantics.md index 14102b105e..dbb3ef4997 100644 --- a/.agents/notes/implemented/architecture/2026-06-30-event-domain-semantics.md +++ b/.agents/notes/implemented/architecture/2026-06-30-event-domain-semantics.md @@ -10,9 +10,9 @@ The harness extends the agent loop through a Cordis event taxonomy (see [the mic - `session/*` carries the durable, event-sourced log (`SessionEventMap`). - `agent/*` carries live runtime signals that hand a plugin the `Agent` handle. -- `tools/*` carries the tool registry + execution seam. +- `tools/*` carries the tool registry and execution pipeline. -Two problems motivated pinning the semantics down. First, several turn/step boundaries existed BOTH as a durable `SessionEvent` (`turn/start`, `turn/end`, `step/start`, `step/end`) AND as a mirrored `agent/*` emit (`agent/turn-start`, `agent/turn-end`, `agent/step-start`, `agent/step-end`). A consumer had two sources of truth for the same fact, and every lifecycle change had to update both. Second, the upcoming Hooks subsystem needs ONE coherent, documented surface to subscribe to — a plugin author (and the Claude Code / Codex hook bridges built on top) must know, without reading the loop, whether to listen on a session event or an agent event, and why. +Two problems motivated pinning the semantics down. First, several turn/step boundaries existed BOTH as a durable `SessionEvent` (`turn/start`, `turn/end`, `step/start`, `step/end`) AND as a mirrored `agent/*` emit (`agent/turn-start`, `agent/turn-end`, `agent/step-start`, `agent/step-end`). A consumer had two sources of truth for the same fact, and every lifecycle change had to update both. Second, the Hooks subsystem needs ONE coherent, documented surface to subscribe to — a plugin author (and the Claude Code / Codex hook bridges built on top) must know, without reading the loop, whether to listen on a session event or an agent event, and why. This vocabulary is the foundation for interception decisions, the durable `hook/*` log, and the Claude Code and Codex bridges. @@ -22,7 +22,7 @@ This vocabulary is the foundation for interception decisions, the durable `hook/ - **`session/*` — the durable, replayable FACT log.** Owns `SessionEventMap`; every entry is JSON-only (no live objects). One `session/event` emit per append, plus the `session/flush` parallel durability checkpoint. It is also the live transcript feed: a consumer that wants to render or react to what happened subscribes here, so live rendering and replay projections share one path. - **`agent/*` — the LIVE runtime surface.** Always carries the live `Agent`. Interception waterfalls (`agent/pre-step`, `agent/request`, `agent/request-error`) transform, reject, or recover; awaited `agent/turn-stopping` observes the stop boundary; transient emits report lifecycle, status, inbox insertion/claim/discard, and errors. Turn and step BOUNDARIES are NOT here — they are durable session events read off `session/event`, as are the token stream (`assistant/chunk`) and mid-turn steering (a `user/message`). -- **`tools/*` — the tool registry + execution seam.** +- **`tools/*` — the tool registry and execution pipeline.** **The boundary rule:** a durable, replayable fact is a `SessionEvent`; a live interception or a transient/live-object signal is an `agent`/`tools` Cordis event. A turn or step boundary is a durable fact, so it lives in the session log and is read off the `session/event` feed — it is NOT mirrored as an `agent/*` emit. @@ -34,6 +34,6 @@ This vocabulary is the foundation for interception decisions, the durable `hook/ - Tests that observed boundaries via the removed emits now observe the durable `turn/start`/`turn/end`/`step/start`/`step/end` session events — the behavior they pin (boundary ordering, step counting) is unchanged; only the feed they read moved to the canonical one. The tests that exercised a *throwing turn-boundary emit listener* were deleted, because that code path no longer exists (there is no emit to throw from). Per [AGENTS.md "tests document behavior, not golden truth"](../../../../AGENTS.md), the behavior and its test moved (or died) together. - The loop marks the step open (`stepOpen = true`) only after `append('step/start')` returns. Internal dispatch validation runs before the log push and may reject without opening a step; post-commit `session/event` observer failures are contained inside `Session.append`. The marker therefore represents exactly the committed boundary that owes a later `step/end`. - The full realization of this is [the simplification Agent Note "Stop mirroring durable boundaries as agent events"](../simplification/2026-06-20-remove-agent-boundary-mirror-events.md): all four boundary mirrors are removed and every consumer reads boundaries off `session/event`. `agent/steering` (not a boundary mirror) stayed outside that Agent Note's scope and was removed by its own follow-up, [Remove the `agent/steering` mirror emit](../../archived/simplification/2026-07-04-remove-agent-steering-mirror.md) — it mirrored the durable mid-turn steering `user/message`. -- The cordis events catalog (`docs/cordis-catalog/events.md`) is regenerated to drop the mirror events. +- The generated cordis event surface (the `docs/subsystems/` pages) no longer lists the mirror events. diff --git a/.agents/notes/implemented/architecture/2026-06-30-event-domain-semantics.zh.md b/.agents/notes/implemented/architecture/2026-06-30-event-domain-semantics.zh.md index 2607e59490..93fe14adea 100644 --- a/.agents/notes/implemented/architecture/2026-06-30-event-domain-semantics.zh.md +++ b/.agents/notes/implemented/architecture/2026-06-30-event-domain-semantics.zh.md @@ -10,9 +10,9 @@ harness 通过 Cordis 事件分类体系扩展 agent loop（智能体循环） - `session/*` 承载持久的、事件溯源的日志（`SessionEventMap`）。 - `agent/*` 承载运行时实时信号，向插件传递 `Agent` 句柄。 -- `tools/*` 承载工具注册表与执行 seam。 +- `tools/*` 承载工具注册表与执行流水线。 -两个问题促使我们固定语义。第一，若干轮次/步骤边界同时作为持久的 `SessionEvent`（`turn/start`、`turn/end`、`step/start`、`step/end`）和镜像的 `agent/*` emit（`agent/turn-start`、`agent/turn-end`、`agent/step-start`、`agent/step-end`）存在。消费方对同一事实有两个真源，每次生命周期变更都必须同时更新两处。第二，即将到来的钩子子系统需要一个连贯且有文档的订阅表面——插件作者（以及基于其上构建的 Claude Code / Codex 钩子桥接）必须在不阅读循环代码的情况下知道应该监听会话事件还是 agent 事件，以及原因。 +两个问题促使我们固定语义。第一，若干轮次/步骤边界同时作为持久的 `SessionEvent`（`turn/start`、`turn/end`、`step/start`、`step/end`）和镜像的 `agent/*` emit（`agent/turn-start`、`agent/turn-end`、`agent/step-start`、`agent/step-end`）存在。消费方对同一事实有两个真源，每次生命周期变更都必须同时更新两处。第二，钩子子系统需要一个连贯且有文档的订阅表面——插件作者（以及基于其上构建的 Claude Code / Codex 钩子桥接）必须在不阅读循环代码的情况下知道应该监听会话事件还是 agent 事件，以及原因。 这套词汇是拦截决策、持久的 `hook/*` 日志，以及 Claude Code 和 Codex 桥接的基础。 @@ -21,8 +21,8 @@ harness 通过 Cordis 事件分类体系扩展 agent loop（智能体循环） **三个域，各司其职，以一条边界规则统一。** - **`session/*`——持久的、可回放的事实日志。** 拥有 `SessionEventMap`；每条记录仅含 JSON（无活对象）。每次追加触发一次 `session/event` emit，加上 `session/flush` 并行持久性检查点。它同时也是实时 transcript（文本记录）源：想渲染或响应已发生事件的消费方在此订阅，因此实时渲染与回放投影共享同一路径。 -- **`agent/*`——运行时实时表面。** 始终携带活的 `Agent`。拦截 waterfall（瀑布式事件）（`agent/pre-step`、`agent/request`、`agent/request-error`）负责变换、拒绝或恢复；awaited `agent/turn-stopping` 观察停止边界；瞬态 emit 报告生命周期、状态、inbox 插入／领取／丢弃与错误。轮次和步骤边界不在此处——它们是持久的会话事件，从 `session/event` 读取；token 流（`assistant/chunk`）和作为一条 `user/message` 的轮次中途 steering（中途引导）同理。 -- **`tools/*`——工具注册表与执行 seam。** +- **`agent/*`——运行时实时表面。** 始终携带活的 `Agent`。拦截 waterfall（瀑布式事件）（`agent/pre-step`、`agent/request`、`agent/request-error`）负责变换、拒绝或恢复；awaited `agent/turn-stopping` 观察停止边界；瞬态 emit 报告生命周期、状态、inbox 插入／领取／丢弃与错误。轮次和步骤边界不在此处——它们是持久的会话事件，从 `session/event` 读取；token 流（`assistant/chunk`）和中途 steering（以 `user/message` 呈现）同理。 +- **`tools/*`——工具注册表与执行流水线。** **边界规则：** 持久的、可回放的事实是 `SessionEvent`；实时拦截或瞬态/活对象信号是 `agent`/`tools` Cordis 事件。轮次或步骤边界是持久事实，因此存在于会话日志中并从 `session/event` 源读取——不会被镜像为 `agent/*` emit。 @@ -34,6 +34,6 @@ harness 通过 Cordis 事件分类体系扩展 agent loop（智能体循环） - 之前通过已移除 emit 观察边界的测试，现在观察持久的 `turn/start`/`turn/end`/`step/start`/`step/end` 会话事件——它们所锁定的行为（边界顺序、步骤计数）不变；只是读取的源移到了规范源。那些测试*抛出异常的轮次边界 emit 监听器*的用例被删除，因为该代码路径不再存在（没有 emit 可供抛出）。按照 [AGENTS.md「测试记录行为，而非黄金真相」](../../../../AGENTS.md)，行为与其测试一同迁移（或一同消亡）。 - 循环仅在 `append('step/start')` 返回后才标记步骤已打开（`stepOpen = true`）。内部分发校验在日志推入之前运行，可能在不打开步骤的情况下拒绝；post-commit `session/event` observer 的失败被隔离在 `Session.append` 内部。因此该标记精确表示已提交的、欠一个后续 `step/end` 的边界。 - 完整实现见[简化 Agent Note「停止将持久边界镜像为 agent 事件」](../simplification/2026-06-20-remove-agent-boundary-mirror-events.md)：全部四个边界镜像被移除，所有消费方从 `session/event` 读取边界。`agent/steering`（不是边界镜像）不在该 Agent Note 范围内，由其后续 Agent Note [移除 `agent/steering` 镜像 emit](../../archived/simplification/2026-07-04-remove-agent-steering-mirror.md) 单独移除——它镜像的是持久的中途 steering `user/message`。 -- Cordis 事件目录（`docs/cordis-catalog/events.md`）重新生成以移除镜像事件。 +- 生成的 cordis 事件表面（`docs/subsystems/` 各页）不再列出镜像事件。 diff --git a/.agents/notes/implemented/architecture/2026-07-02-fs-per-session-cwd.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-02-fs-per-session-cwd.i18n.yaml index da7848d581..ceccf93631 100644 --- a/.agents/notes/implemented/architecture/2026-07-02-fs-per-session-cwd.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-02-fs-per-session-cwd.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-02-fs-per-session-cwd.md -2026-07-02-fs-per-session-cwd.md: d3f54e89e735016a373fa14c60123c681b3e7adf -2026-07-02-fs-per-session-cwd.zh.md: 86058437a14f64cc7faf6e6ad413c52efba5fd39 +2026-07-02-fs-per-session-cwd.md: 23c9f414590df8c79109e46f24af031b765b8f58 +2026-07-02-fs-per-session-cwd.zh.md: 5e429bbda16c2c7e29114e6d8586c13b658cac0a diff --git a/.agents/notes/implemented/architecture/2026-07-02-fs-per-session-cwd.md b/.agents/notes/implemented/architecture/2026-07-02-fs-per-session-cwd.md index d3f54e89e7..23c9f41459 100644 --- a/.agents/notes/implemented/architecture/2026-07-02-fs-per-session-cwd.md +++ b/.agents/notes/implemented/architecture/2026-07-02-fs-per-session-cwd.md @@ -26,7 +26,7 @@ Thread the caller's session cwd into path resolution, exactly as `dsh-tool-bash` ### Why the caller supplies the cwd (not the provider) -The provider seam must not depend on `dsh-agent` / `dsh-session` — it is a text-storage backend that a sandboxed or remote implementation also satisfies, and those have no notion of an "agent session". The tool already receives the `ToolExecution` (`exec`), which carries the agent, so the tool is the right place to project `exec → cwd` and hand the provider a plain string. This is the "explicit > implicit at package seams" convention: the base directory arrives as an explicit argument the provider acts on, not smuggled in by having the provider reach into a session it should not know about. It also matches `dsh-tool-bash` one-to-one, so the two model-facing file surfaces resolve paths identically. +The provider contract must not depend on `dsh-agent` / `dsh-session` — it is a text-storage backend that a sandboxed or remote implementation also satisfies, and those have no notion of an "agent session". The tool already receives the `ToolExecution` (`exec`), which carries the agent, so the tool is the right place to project `exec → cwd` and hand the provider a plain string. This is the "explicit > implicit at package boundaries" convention: the base directory arrives as an explicit argument the provider acts on, not smuggled in by having the provider reach into a session it should not know about. It also matches `dsh-tool-bash` one-to-one, so the two model-facing file surfaces resolve paths identically. The default lives in ONE place — the provider's `config.cwd`. `sessionCwd` returns `undefined` rather than `process.cwd()` when there is no session, so the tool never manufactures a base the provider would otherwise choose. diff --git a/.agents/notes/implemented/architecture/2026-07-02-fs-per-session-cwd.zh.md b/.agents/notes/implemented/architecture/2026-07-02-fs-per-session-cwd.zh.md index 86058437a1..5e429bbda1 100644 --- a/.agents/notes/implemented/architecture/2026-07-02-fs-per-session-cwd.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-02-fs-per-session-cwd.zh.md @@ -26,7 +26,7 @@ ACP（Agent Client Protocol）桥接层为每个会话提供独立的工作区 ### 为何由调用方（而非提供方）提供 cwd -提供方 seam 不得依赖 `dsh-agent`／`dsh-session`——它是一个文本存储后端，沙箱或远程实现同样满足该接口，而这些实现没有「agent 会话」的概念。工具已经接收了 `ToolExecution`（`exec`），其中携带 agent，因此工具是将 `exec → cwd` 投影并向提供方传递一个纯字符串的正确位置。这遵循「包边界处显式优于隐式」的约定：基准目录作为显式参数传入，提供方据此行动，而非让提供方越界去读取它不应知晓的会话。这也与 `dsh-tool-bash` 一一对应，使两个面向模型的文件操作接口以相同方式解析路径。 +提供方约定不得依赖 `dsh-agent`／`dsh-session`——它是一个文本存储后端，沙箱或远程实现同样满足该接口，而这些实现没有「agent 会话」的概念。工具已经接收了 `ToolExecution`（`exec`），其中携带 agent，因此工具是将 `exec → cwd` 投影并向提供方传递一个纯字符串的正确位置。这遵循「包边界处显式优于隐式」的约定：基准目录作为显式参数传入，提供方据此行动，而非让提供方越界去读取它不应知晓的会话。这也与 `dsh-tool-bash` 一一对应，使两个面向模型的文件操作接口以相同方式解析路径。 默认值只存在于一个地方——提供方的 `config.cwd`。`sessionCwd` 在没有会话时返回 `undefined` 而非 `process.cwd()`，因此工具永远不会自行制造一个提供方本应自行选择的基准目录。 diff --git a/.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.i18n.yaml index f80e5c3c77..759fecb3b9 100644 --- a/.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md -2026-07-05-prompt-variables-and-tool-guidance-ownership.md: a3b5021daf323971308760bde4f97651db8edbda -2026-07-05-prompt-variables-and-tool-guidance-ownership.zh.md: 0b84f188e6637d8b1b42ed2e6df3cd7e4061d75d +2026-07-05-prompt-variables-and-tool-guidance-ownership.md: 8f8b40a44314fc6add97842d48273e49927f92e2 +2026-07-05-prompt-variables-and-tool-guidance-ownership.zh.md: 6fc71e2ab866822cee389c0c54efe1731847cbb7 diff --git a/.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md b/.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md index a3b5021daf..8f8b40a443 100644 --- a/.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md +++ b/.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md @@ -18,7 +18,7 @@ The assembled system prompt had four defects, all of one family: facts the harne ## Decision -**One principle: every fact in the prompt has exactly one owner.** The model name and workspace are config/session facts → the harness exposes them as variables and the persona references them. Per-tool semantics and when-to-use → the tool's `description`. Cross-call habits a description cannot carry → the tool package's prompt section. Harness provenance → the static `harness:identity` section. Deployment role and behavior → the deployment's persona. +**One principle: every fact in the prompt has exactly one owner.** The model name and workspace are config/session facts → the harness exposes them as variables and the persona references them. Per-tool semantics and when-to-use → the tool's `description`. Cross-call habits a description cannot carry → the tool package's prompt section. The product name and SDK identity line → the static `harness:identity` section. Deployment role and behavior → the deployment's persona. ### Assemble context @@ -46,9 +46,9 @@ Per-tool semantics and selection guidance live in tool descriptions. Prompt sect - **The loop composes an identity line itself** — hardcodes model-facing prose in the one package that must stay thin ("plugins, not loop changes"), and outside the section pipeline it would be a second composition path. (The identity DOES ship as a code literal — but as an ordinary section registered by `dsh-system-prompt`, whose `system-prompt/assemble` waterfall remains the escape valve for a deployment that must drop it.) - **Inject the model name via the `agent/request` waterfall** — prompt text would be composed in two places and the earlier rendered persona could disagree with the final routed header. The request plugin that owns late routing must also own any earlier prompt claim about that model. -- **Hand-write the model name in each persona** — duplicates the `model:` key one line above and silently lies after a config edit; the exact disease this Agent Note cures. +- **Hand-write the model name in each persona** — duplicates the `model:` key one line above and silently lies after a config edit; the exact disease this decision cures. - **Lenient interpolation (leave unknown refs verbatim, or substitute empty)** — a typo ships `{{modle}}` (or a hole) to the model and nobody notices until transcript review. -- **Per-instance subagent wording in config** — returns model-facing prose to every deployment × instance, the P2 disease again. **Keying wording off the provider NAME** — `providerName` is itself config, so a renamed provider silently gets the wrong words. +- **Per-instance subagent wording in config** — returns model-facing prose to every deployment × instance, reviving the hand-written-guidance-in-leaf-YAML drift. **Keying wording off the provider NAME** — `providerName` is itself config, so a renamed provider silently gets the wrong words. - **Resolving the provider at `apply` time (a load-order requirement)** and **section-only subagent wording (lazily resolved at assemble)** — the alternatives to the provider-lifecycle events; both rejected in [the provider-lifecycle-events Agent Note](2026-07-05-subagent-provider-lifecycle-events.md). ## Out of scope diff --git a/.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.zh.md b/.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.zh.md index 0b84f188e6..6fc71e2ab8 100644 --- a/.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.zh.md @@ -18,7 +18,7 @@ Status: implemented ## 决策 -**一条原则：提示词中的每个事实恰好有一个归属方。** 模型名称和工作区是配置/会话事实 → harness 将它们暴露为变量，persona 引用它们。每个工具的语义和何时使用 → 工具的 `description`。description 无法承载的跨调用习惯 → 包的提示词 section。harness 来源标识 → 静态的 `harness:identity` section。部署角色与行为 → 部署的 persona。 +**一条原则：提示词中的每个事实恰好有一个归属方。** 模型名称和工作区是配置/会话事实 → harness 将它们暴露为变量，persona 引用它们。每个工具的语义和何时使用 → 工具的 `description`。description 无法承载的跨调用习惯 → 包的提示词 section。产品名称和 SDK 身份说明 → 静态的 `harness:identity` section。部署角色与行为 → 部署的 persona。 ### 组装上下文 @@ -46,9 +46,9 @@ Status: implemented - **循环自行组合一行 identity 文本**：在必须保持精简的那个包（「用插件，不改循环」）中硬编码面向模型的行文，且在 section 流水线之外构成第二条组合路径。（identity 确实以代码字面量交付——但作为 `dsh-system-prompt` 注册的普通 section，其 `system-prompt/assemble` waterfall 仍是部署需要移除它时的逃生阀。） - **通过 `agent/request` waterfall 注入模型名称**：提示词文本会在两处组合，更早渲染的 persona 也可能与最终已路由 header 不一致。拥有延迟路由的请求插件还必须拥有该模型在提示词中更早出现的声明。 -- **在每个 persona 中手写模型名称**：与上方一行的 `model:` 键重复，配置修改后静默失实；正是本 Agent Note 要治愈的病症。 +- **在每个 persona 中手写模型名称**：与上方一行的 `model:` 键重复，配置修改后静默失实；正是本决策要治愈的病症。 - **宽松插值（未知引用保留原样或替换为空）**：一个拼写错误 `{{modle}}`（或一个空洞）会被发送给模型，直到 transcript（文本记录）审查时才会被发现。 -- **在配置中为每个 subagent 实例编写措辞**：面向模型的行文回到每个部署 × 实例中，重蹈 P2 病症。**根据提供方名称选择措辞**：`providerName` 本身是配置，重命名提供方后会静默获得错误的措辞。 +- **在配置中为每个 subagent 实例编写措辞**：面向模型的行文回到每个部署 × 实例中，重蹈在 leaf YAML 中手写指导的漂移。**根据提供方名称选择措辞**：`providerName` 本身是配置，重命名提供方后会静默获得错误的措辞。 - **在 `apply` 时解析提供方（加载顺序要求）**与**仅用 section 承载 subagent 措辞（在 assemble 时惰性解析）**：提供方生命周期事件的替代方案；两者均在[提供方生命周期事件 Agent Note](2026-07-05-subagent-provider-lifecycle-events.md)中被否决。 ## 不在范围内 diff --git a/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.i18n.yaml index 1b5962f672..54935a491e 100644 --- a/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.md -2026-07-05-reconstructable-requests.md: ebca9b99cad791159302da9c2bbce9f4df147aab -2026-07-05-reconstructable-requests.zh.md: e7ed83bbc553e86d53d88e442b0fd8992973c9e7 +2026-07-05-reconstructable-requests.md: c13e40b5b22e5d6fe19f6b5bd137db3a48350390 +2026-07-05-reconstructable-requests.zh.md: 746bcd37dabada949873d394776c1ca43eff4ea2 diff --git a/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.md b/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.md index ebca9b99ca..c13e40b5b2 100644 --- a/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.md +++ b/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.md @@ -30,9 +30,9 @@ Each proposed step first claims its inbox batch and runs `agent/pre-step`. Rejec **Enforcement.** The `dsh-agent-loop/invariant` companion registers with `ctx.invariants` and, when selected, independently rebuilds each loop request through a fresh `Session`, so the live cache cannot vouch for itself, then compares messages and folded header fields at `llm/stream`. The loop records the exact frozen request through `markAgentLoopRequest()` in `dsh-llm`; the process-local identity lets the companion and other request observers recognize conversation work, while direct one-shots remain excluded regardless of their frozen shape or session id. Correctness depends on sequence-bounded reconstruction rather than listener order. A with-key e2e requires positive cache-read tokens after the first request; per-step usage is the production signal, and a header change or compaction appears as a cache-read drop on the next step. -### The MiniCode shape: adopted, with the provenance arrow inverted +### The MiniCode shape: adopted, with the event log as the source -Like MiniCode, the conversation advances append-only and resets only when model-visible state changes. Unlike MiniCode, the event log remains the source of truth because it also owns persistence, recovery, boundaries, tool pairing, and provenance. `Session` caches message and header folds derived from that log, making every request independently checkable. +Like MiniCode, the conversation advances append-only and resets only when model-visible state changes. Unlike MiniCode, the event log remains the source of truth because it also owns persistence, recovery, boundaries, tool pairing, and links from derived events to their inputs. `Session` caches message and header folds derived from that log, making every request independently checkable. ## Alternatives considered @@ -49,7 +49,7 @@ Like MiniCode, the conversation advances append-only and resets only when model- - A request that is not explained by the log cannot be constructed by accident — not by the loop, not by a listener; mutating a built request throws; every header change is a durable, diffable log event. - Model-visible context uses logged message channels. `agent.inject()` and tool `additionalContexts` enter the inbox for a later claim, while `agent/pre-step` returns context that must settle with the current claimed batch. Each entered value is a durable sourced `user/message`, paid once and prefix-cached thereafter at the price of accumulating in history until compaction. - What still costs full price at the provider is inherent and logged: compaction (its `compact/*` events and replacement entry), a real prompt, tool, or config change (`request/header` with reason `change`), or a process boundary with drift (a differing `resume` snapshot). The provider's own reasoning-content exclusion is managed server-side. -- `agent/pre-step` is the current-request message seam; direct inbox mutation is the eventual later-request seam. -- Tool-result trimming (planned) needs no new mechanism: a logged single-entry surface replace (`start === end`) carrying a trimmed `tool/result` under the same `callId` — compaction-family, replay-correct, cache-bust batched by the same pressure logic. +- `agent/pre-step` is the current-request message channel; direct inbox mutation is the eventual later-request channel. +- Tool-result trimming needs no new mechanism: a logged single-entry surface replace (`start === end`) carrying a trimmed `tool/result` under the same `callId` — compaction-family, replay-correct, cache-bust batched by the same pressure logic. - Session logs grow one `request/header` snapshot per loop instance plus snapshots on real changes. This is larger than a delta codec but small beside chunk-heavy logs and retains one replay representation. `SESSION_FORMAT_VERSION` stays `0`; legacy delta events are rejected rather than migrated. - Snapshot expected outputs changed once (every transcript gains its header events); the fs-writing fixtures are stored in the normalized authored form with cwd-relative tool arguments, because replay only round-trips cwd-independent argument paths. diff --git a/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.zh.md b/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.zh.md index e7ed83bbc5..746bcd37da 100644 --- a/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.zh.md @@ -30,9 +30,9 @@ Status: implemented **强制执行。** `dsh-agent-loop/invariant` 配套插件向 `ctx.invariants` 注册，并在被选用时通过一个全新的 `Session` 独立重建每个循环请求，使活跃缓存无法为自身背书，然后在 `llm/stream` 处比较消息和折叠后的 header 字段。循环通过 `dsh-llm` 的 `markAgentLoopRequest()` 记录精确的冻结请求；这一进程内标识让配套插件和其他请求观察者识别对话工作，而直接的一次性调用无论其冻结形状或会话 id 如何都保持排除。正确性依赖于序列有界的重建，而非监听器顺序。带密钥的 e2e 要求首次请求之后有正值的 cache-read token；逐步骤用量是生产信号，header 变更或压缩表现为下一步骤的 cache-read 下降。 -### MiniCode 形态：采纳，但溯源箭头反转 +### MiniCode 形态：采纳，以事件日志为真源 -与 MiniCode 相同，对话仅追加推进，仅在模型可见状态变更时重置。与 MiniCode 不同，事件日志仍是真源，因为它同时拥有持久化、恢复、边界、工具配对和溯源。`Session` 缓存从日志推导的消息和 header 折叠结果，使每个请求都可独立检查。 +与 MiniCode 相同，对话仅追加推进，仅在模型可见状态变更时重置。与 MiniCode 不同，事件日志仍是真源，因为它同时拥有持久化、恢复、边界、工具配对，并记录派生事件到其输入事件的关联。`Session` 缓存从日志推导的消息和 header 折叠结果，使每个请求都可独立检查。 ## 曾考虑的替代方案 @@ -47,9 +47,9 @@ Status: implemented ## 后果 - 一个日志无法解释的请求不可能被意外构造——无论是循环还是监听器；变异已构建的请求会抛异常；每个 header 变更都是持久的、可 diff 的日志事件。 -- 模型可见上下文使用已记录消息通道。`agent.inject()` 与工具 `additionalContexts` 进入 inbox，等待后续领取；必须与当前已领取批次一起结算的上下文由 `agent/pre-step` 返回。每个进入步骤的值都是带来源的持久 `user/message`，只付出一次代价，此后即被前缀缓存，代价是会在历史中累积直至压缩。 -- 在提供方处仍需全价计算的内容是固有的且已记录的：压缩（其 `compact/*` 事件和替换条目）、真正的提示词、工具或配置变更（reason 为 `change` 的 `request/header`），或带漂移的进程边界（不同的 `resume` 快照）。提供方自身对思考内容的排除由服务端管理。 -- `agent/pre-step` 是当前请求的消息 seam；直接修改 inbox 则是最终进入后续请求的 seam。 -- 工具结果裁剪（计划中）无需新机制：一个已记录的单条目 surface replace（`start === end`），携带同一 `callId` 下裁剪后的 `tool/result`——属压缩家族，回放正确，缓存失效由相同的压力逻辑批量处理。 +- 模型可见上下文使用已记录消息通道。`agent.inject()` 与工具 `additionalContexts` 进入 inbox，等待后续领取；必须与当前已领取批次一起结算的上下文由 `agent/pre-step` 返回。每个进入步骤的值都是带来源的持久 `user/message`，只付出一次代价并在后续成为可缓存前缀，代价是会在历史中累积直至压缩。 +- 在提供方处仍需全价计算的内容是固有的且已记录的：压缩（其 `compact/*` 事件和替换条目）、真正的提示词、工具或配置变更（reason 为 `change` 的 `request/header`），或带漂移的进程边界（不同的 `resume` 快照）。提供方自身的 reasoning-content 排除由服务端管理。 +- `agent/pre-step` 是当前请求的消息通道；直接修改 inbox 则是最终进入后续请求的通道。 +- 工具结果裁剪无需新机制：一个已记录的单条目 surface replace（`start === end`），携带同一 `callId` 下裁剪后的 `tool/result`——属压缩家族，回放正确，缓存击穿由相同的压力逻辑批量处理。 - 会话日志每个循环实例增长一个 `request/header` 快照，并在真正变更时增加快照。它比 delta 编解码器更大，但相对分片密集型日志仍然很小，并只保留一种回放表示。`SESSION_FORMAT_VERSION` 保持 `0`；旧的 delta 事件被拒绝而非迁移。 - 快照预期输出变更一次（每个 transcript（文本记录）增加其 header 事件）；写入文件系统的 fixture（测试前置数据）以规范化的撰写形式存储，工具参数使用 cwd 相对路径，因为回放只对 cwd 无关的参数路径做往返。 diff --git a/.agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.i18n.yaml index 24a047b540..fa9304ec09 100644 --- a/.agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.md -2026-07-06-timeout-deadline-library.md: 63463a76a65743436d4e78479800c19e257a42de -2026-07-06-timeout-deadline-library.zh.md: c47e6d4e6ed0bec368fca8857e5bd4d7229b6b0e +2026-07-06-timeout-deadline-library.md: b7c7ac07ce0acec819fa7e88b32b3b6d624f3e6e +2026-07-06-timeout-deadline-library.zh.md: e4ec6b9a9e07b55faf9f44f2b99b765620e626c4 diff --git a/.agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.md b/.agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.md index 63463a76a6..b7c7ac07ce 100644 --- a/.agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.md +++ b/.agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.md @@ -57,10 +57,11 @@ export function deadline( export interface IdleWatchdog { readonly signal: AbortSignal next(iterator: AsyncIterator): Promise> + pulse(): void [Symbol.dispose](): void } -/** Arm only while one iterator `next()` is outstanding, then rearm on later demand. */ +/** Arm only while one iterator `next()` is outstanding; rearm on later demand or out-of-band activity. */ export function idleWatchdog( upstream: AbortSignal | undefined, timeoutMs: number, @@ -71,7 +72,7 @@ export function idleWatchdog( export function timeoutOf(x: AbortSignal | { reason?: unknown }, code?: string): TimeoutReason | undefined ``` -`deadline` fuses an upstream signal with a one-shot timer through `AbortSignal.any`, adds a typed `TimeoutReason`, and exposes disposable timer cleanup. Non-positive timeouts are an internal no-timeout sentinel for backend-owned background work; external hints pass through `clampTimeout` and must be positive and finite. Without a timer or upstream signal, the function returns a never-aborting signal with the same disposal shape. `idleWatchdog` instead requires a positive finite interval, keeps one stable fused signal for the entire stream, and arms its timer only while one iterator `next()` is outstanding; resolution disarms it, later demand rearms it, concurrent demand fails, and disposal clears the active arm. Providers translate timeout reasons into seam-specific results. `timeoutOf(signal, code)` scopes classification so an outer nested deadline is treated as upstream cancellation rather than the inner capability's timeout. +`deadline` fuses an upstream signal with a one-shot timer through `AbortSignal.any`, adds a typed `TimeoutReason`, and exposes disposable timer cleanup. Non-positive timeouts are an internal no-timeout sentinel for backend-owned background work; external hints pass through `clampTimeout` and must be positive and finite. Without a timer or upstream signal, the function returns a never-aborting signal with the same disposal shape. `idleWatchdog` instead requires a positive finite interval, keeps one stable fused signal for the entire stream, and arms its timer only while one iterator `next()` is outstanding; resolution disarms it, later demand rearms it, and `pulse()` rearms that same outstanding demand after out-of-band transport activity. A pulse outside outstanding demand or after disposal is a no-op; concurrent demand fails, and disposal clears the active arm. Providers translate timeout reasons into seam-specific results. `timeoutOf(signal, code)` scopes classification so an outer nested deadline is treated as upstream cancellation rather than the inner capability's timeout. ### The division of labor @@ -79,7 +80,7 @@ export function timeoutOf(x: AbortSignal | { reason?: unknown }, code?: string): |---|---| | Validate request hint and clamp default/max | `dsh-timeout` (`clampTimeout`) — pure arithmetic plus the shared positive-finite request contract | | Arm one-shot timer, abort on deadline, carry reason, fuse with upstream cancel | `dsh-timeout` (`deadline`) | -| Arm and rearm only around outstanding iterator demand | `dsh-timeout` (`idleWatchdog`) | +| Arm and rearm only around outstanding iterator demand, including out-of-band activity | `dsh-timeout` (`idleWatchdog`) | | Clear the timer | `dsh-timeout` (`[Symbol.dispose]` on either primitive) | | Classify the first abort reason after abort | `dsh-timeout` (`timeoutOf`) | | **Actually terminate the work** | the capability's implementation | @@ -92,17 +93,17 @@ The signal only *notifies*; termination is always the listener's job, and the li - **web_fetch** — the tool stays validate-and-forward; the provider's hand-rolled controller + `setTimeout` + manual listener + `finally` + `signal.reason` recovery is replaced by provider-owned `deadline`/`timeoutOf`. A pre-aborted upstream signal still throws `WEB_ABORTED` up front; otherwise `fetch` runs against the fused `d.signal`, and `translateAbortOrNetwork` classifies a thrown error by the signal (`timeoutOf` → `WEB_FETCH_TIMEOUT`, else aborted → `WEB_ABORTED`, else network → `WEB_PROVIDER_ERROR`). The public error-code contract is unchanged, and `TimeoutReason` never crosses the web seam as the public error. - **bash** — `resolve()` clamps the request into an explicit spec. Foreground `run()` creates the deadline and passes its signal to process execution, whose existing abort listener performs the process-group kill. The executor classifies the first abort as timeout or cancellation. Background starts remain timeout-free and forward only upstream cancellation. -- **LLM adapters** — `dsh-llm-deepseek` and `dsh-llm-pi-ai` wrap actual transport iteration with `idleWatchdog`. The five-minute configured interval covers only outstanding provider demand, not time the downstream consumer spends between chunks. The stable signal reaches `fetch` or the SDK for the whole call, so timeout closes the underlying request and maps to `TIMEOUT`, while an earlier caller abort maps to `ABORTED`. +- **LLM adapters** — `dsh-llm-deepseek` and `dsh-llm-pi-ai` wrap actual transport iteration with `idleWatchdog`. The five-minute configured interval covers only outstanding provider demand, not time the downstream consumer spends between chunks. The direct DeepSeek adapter also pulses that outstanding demand when its SSE parser observes a comment, without yielding the comment as a `StreamChunk` or writing it to the session log. The pi-ai SDK does not expose comment activity to its adapter, so that path can rearm only when the SDK yields. The stable signal reaches `fetch` or the SDK for the whole call, so timeout closes the underlying request and maps to `TIMEOUT`, while an earlier caller abort maps to `ABORTED`. ## Consequences -- `runBash`'s outcome no longer independently latches `timedOut` and `aborted`; a timeout and a user abort racing before process close now report a single first-abort cause instead of both being true. The uniform SIGTERM→grace→SIGKILL kill is unchanged, and the seam type `BashRunResult` keeps both booleans (now mutually exclusive), so `dsh-tool-bash`'s result rendering is untouched. -- `SpawnSpec.timeoutMs` and `SpawnOutcome.timedOut`/`aborted` were removed rather than kept as always-zero/always-false vestiges: with `runBash` owning no timer and the executor owning classification, they were read nowhere. This is the one deviation from the literal proposal shape (which passed `timeoutMs: 0` into `runBash`); an always-0 field read by nothing is dead weight under the per-file coverage gate. +- `runBash`'s outcome no longer independently latches `timedOut` and `aborted`; a timeout and a user abort racing before process close now report a single first-abort cause instead of both being true. The uniform SIGTERM→grace→SIGKILL kill is unchanged, and the Service Definition type `BashRunResult` keeps both booleans (now mutually exclusive), so `dsh-tool-bash`'s result rendering is untouched. +- `SpawnSpec.timeoutMs` and `SpawnOutcome.timedOut`/`aborted` were removed rather than kept as always-zero/always-false vestiges: with `runBash` owning no timer and the executor owning classification, they were read nowhere. An always-0 field read by nothing is dead weight under the per-file coverage gate. - web_fetch shed its bespoke controller/timer/listener/reason-recovery; the classifier now keys off the deadline signal (`timeoutOf` + `aborted`) rather than the thrown error's shape, which is robust across both the request-phase reject-with-reason and the read-phase bare-`AbortError`. - `AbortSignal.any` and `using`/`Symbol.dispose` enter the repo for the first time here (Node ≥ 24 baseline, already met). -- Model streams now share one rearmable timer contract without turning a sliding idle interval into a total-call deadline or charging consumer think time. The primitive still only notifies; adapter tests prove their transports observe its stable signal and terminate. +- Model streams now share one rearmable timer contract without turning a sliding idle interval into a total-call deadline or charging consumer think time. Adapters that can observe out-of-band transport activity may pulse an outstanding demand; suppressed activity remains invisible to the watchdog. The primitive still only notifies; adapter tests prove their transports observe its stable signal and terminate. -Out of scope, named to mark the boundary: `web_search` can gain an optional model-facing `timeout_ms` once its tool-schema/snapshot coverage is planned; future ripgrep-backed fs discovery tools can consume the same provider-owned deadline shape once they exist; a `tools/execute` waterfall middleware could arm a default deadline for every tool call by driving `exec.signal` — that would be a plugin that *consumes* this library and still only notifies, the hard kill remaining each capability's job. +Out of scope, named to mark the boundary: `web_search` can gain an optional model-facing `timeout_ms` once its tool-schema/snapshot coverage is planned; the ripgrep-backed fs discovery tools ([packaged ripgrep search](2026-08-01-packaged-ripgrep-search.md)) consume the same provider-owned deadline shape through `dsh-timeout-policy` and `exec.signal`; a `tools/execute` waterfall middleware could arm a default deadline for every tool call by driving `exec.signal` — that would be a plugin that *consumes* this library and still only notifies, the hard kill remaining each capability's job. ## Alternatives considered diff --git a/.agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.zh.md b/.agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.zh.md index c47e6d4e6e..e4ec6b9a9e 100644 --- a/.agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.zh.md @@ -57,10 +57,11 @@ export function deadline( export interface IdleWatchdog { readonly signal: AbortSignal next(iterator: AsyncIterator): Promise> + pulse(): void [Symbol.dispose](): void } -/** Arm only while one iterator `next()` is outstanding, then rearm on later demand. */ +/** Arm only while one iterator `next()` is outstanding; rearm on later demand or out-of-band activity. */ export function idleWatchdog( upstream: AbortSignal | undefined, timeoutMs: number, @@ -71,7 +72,7 @@ export function idleWatchdog( export function timeoutOf(x: AbortSignal | { reason?: unknown }, code?: string): TimeoutReason | undefined ``` -`deadline` 通过 `AbortSignal.any` 将上游信号与一次性定时器融合，附加一个类型化的 `TimeoutReason`，并暴露可 dispose（资源释放）的定时器清理。非正数超时是内部的「无超时」哨兵，用于后端拥有的后台任务；外部提示经过 `clampTimeout`，必须为正有限值。既无定时器也无上游信号时，函数返回一个永不中止的信号，具有相同的 disposal 形状。`idleWatchdog` 则要求正有限的间隔，在整个流期间保持一个稳定的融合信号，并且只在一个迭代器 `next()` 尚未结算时启动定时器；结算会解除定时器，后续 demand 会重新启动，并发 demand 会失败，dispose 会清除当前 arm。提供方将超时原因转译为 seam 特定的结果。`timeoutOf(signal, code)` 限定分类范围，使外层嵌套的 deadline 被视为上游取消而非内层能力自身的超时。 +`deadline` 通过 `AbortSignal.any` 将上游信号与一次性定时器融合，附加一个类型化的 `TimeoutReason`，并暴露可 dispose（资源释放）的定时器清理。非正数超时是内部的「无超时」哨兵，用于后端拥有的后台任务；外部提示经过 `clampTimeout`，必须为正有限值。既无定时器也无上游信号时，函数返回一个永不中止的信号，具有相同的 disposal 形状。`idleWatchdog` 则要求正有限的间隔，在整个流期间保持一个稳定的融合信号，并且只在一个迭代器 `next()` 尚未结算时启动定时器；结算会解除定时器，后续 demand 会重新启动，带外传输活动发生后，`pulse()` 则会为同一个尚未结算的 demand 重新启动定时器。若没有尚未结算的 demand，或已经 dispose，pulse 不执行任何操作；并发 demand 会失败，dispose 会清除当前 arm。提供方将超时原因转译为 seam 特定的结果。`timeoutOf(signal, code)` 限定分类范围，使外层嵌套的 deadline 被视为上游取消而非内层能力自身的超时。 ### 职责划分 @@ -79,7 +80,7 @@ export function timeoutOf(x: AbortSignal | { reason?: unknown }, code?: string): |---|---| | 校验请求提示并钳位默认值/最大值 | `dsh-timeout`（`clampTimeout`）：纯算术加共享的正有限请求约定 | | 启动一次性定时器、到期中止、携带 reason、与上游取消融合 | `dsh-timeout`（`deadline`） | -| 仅围绕未结算的迭代器 demand 启动和重启 | `dsh-timeout`（`idleWatchdog`） | +| 仅围绕未结算的迭代器 demand 启动和重启，带外活动也会触发重启 | `dsh-timeout`（`idleWatchdog`） | | 清除定时器 | `dsh-timeout`（任一原语的 `[Symbol.dispose]`） | | 中止后对首个 abort reason 进行分类 | `dsh-timeout`（`timeoutOf`） | | **实际终止工作** | 各能力的实现 | @@ -92,17 +93,17 @@ export function timeoutOf(x: AbortSignal | { reason?: unknown }, code?: string): - **web_fetch**：工具层保持校验并转发；提供方手写的 controller + `setTimeout` + 手动监听器 + `finally` + `signal.reason` 恢复被替换为提供方自有的 `deadline`/`timeoutOf`。已预先中止的上游信号仍然立即抛出 `WEB_ABORTED`；否则 `fetch` 使用融合后的 `d.signal` 运行，`translateAbortOrNetwork` 根据信号分类抛出的错误（`timeoutOf` → `WEB_FETCH_TIMEOUT`，否则已中止 → `WEB_ABORTED`，否则网络错误 → `WEB_PROVIDER_ERROR`）。公开的错误码约定不变，`TimeoutReason` 永远不会作为公开错误跨越 web seam。 - **bash**：`resolve()` 将请求钳位为显式规格。前台 `run()` 创建 deadline 并将其信号传给进程执行，后者既有的 abort 监听器执行进程组 kill。执行器将首个 abort 分类为超时或取消。后台启动保持无超时，仅转发上游取消。 -- **LLM（大语言模型）适配器**：`dsh-llm-deepseek` 和 `dsh-llm-pi-ai` 用 `idleWatchdog` 包装实际的传输迭代。配置的五分钟间隔只覆盖尚未结算的提供方 demand，不包括下游消费方在分片之间花费的时间。稳定信号在整个调用期间传给 `fetch` 或 SDK，因此超时会关闭底层请求并映射为 `TIMEOUT`，而更早的调用方中止映射为 `ABORTED`。 +- **LLM（大语言模型）适配器**：`dsh-llm-deepseek` 和 `dsh-llm-pi-ai` 用 `idleWatchdog` 包装实际的传输迭代。配置的五分钟间隔只覆盖尚未结算的提供方 demand，不包括下游消费方在分片之间花费的时间。DeepSeek 直连适配器还会在其 SSE（Server-Sent Events）解析器观察到注释时，对该项尚未结算的 demand 调用 `pulse()`；该注释既不会作为 `StreamChunk` 产出，也不会写入会话日志。pi-ai SDK 不会向其适配器暴露注释活动，因此该路径只能在 SDK 产出值时重新启动定时器。稳定信号在整个调用期间传给 `fetch` 或 SDK，因此超时会关闭底层请求并映射为 `TIMEOUT`，而更早的调用方中止映射为 `ABORTED`。 ## 后果 -- `runBash` 的结果不再独立锁存 `timedOut` 和 `aborted`；超时与用户中止在进程关闭前竞争时，现在报告单一的首个 abort 原因，而非两者同时为 true。统一的 SIGTERM→宽限期→SIGKILL 终止路径不变，seam 类型 `BashRunResult` 保留两个布尔值（现在互斥），因此 `dsh-tool-bash` 的结果渲染不受影响。 -- `SpawnSpec.timeoutMs` 和 `SpawnOutcome.timedOut`/`aborted` 被移除，而非作为始终为零/始终为 false 的残余保留：由于 `runBash` 不再拥有定时器且执行器负责分类，这些字段无处被读取。这是与字面提案形状（向 `runBash` 传入 `timeoutMs: 0`）的唯一偏差；一个始终为 0 且无处读取的字段在逐文件覆盖率门禁下属于死代码。 +- `runBash` 的结果不再独立锁存 `timedOut` 和 `aborted`；超时与用户中止在进程关闭前竞争时，现在报告单一的首个 abort 原因，而非两者同时为 true。统一的 SIGTERM→宽限期→SIGKILL 终止路径不变，Service Definition 类型 `BashRunResult` 保留两个布尔值（现在互斥），因此 `dsh-tool-bash` 的结果渲染不受影响。 +- `SpawnSpec.timeoutMs` 和 `SpawnOutcome.timedOut`/`aborted` 被移除，而非作为始终为零/始终为 false 的残余保留：由于 `runBash` 不再拥有定时器且执行器负责分类，这些字段无处被读取。一个始终为 0 且无处读取的字段在逐文件覆盖率门禁下属于死代码。 - web_fetch 去除了其定制的 controller/timer/listener/reason-recovery；分类器现在基于 deadline 信号（`timeoutOf` + `aborted`）而非抛出错误的形状来判断，这在请求阶段的 reject-with-reason 和读取阶段的裸 `AbortError` 两种情况下都是健壮的。 - `AbortSignal.any` 和 `using`/`Symbol.dispose` 在此首次进入本仓库（Node ≥ 24 基线，已满足）。 -- 模型流现在共享一个可重启的定时器约定，不会把滑动的空闲间隔变成总调用截止时间，也不会计入消费方思考时间。该原语仍然只做通知；适配器测试证明其传输观察到稳定信号并终止。 +- 模型流现在共享一个可重启的定时器约定，不会把滑动的空闲间隔变成总调用截止时间，也不会计入消费方思考时间。能够观察到带外传输活动的适配器可以对尚未结算的 demand 调用 `pulse()`；被屏蔽的活动对 watchdog 仍不可见。该原语仍然只做通知；适配器测试证明其传输观察到稳定信号并终止。 -以下内容不在本次范围内，列出以标明边界：`web_search` 可以在其工具 schema 和快照覆盖规划完成后获得可选的面向模型的 `timeout_ms`；未来基于 ripgrep 的文件系统发现工具可以在实现后消费同样的提供方自有 deadline 形状；`tools/execute` waterfall（瀑布式事件）中间件可以通过驱动 `exec.signal` 为每次工具调用设置默认 deadline——那将是一个*消费*本库的插件，仍然只做通知，硬终止仍是各能力自己的事。 +以下内容不在本次范围内，列出以标明边界：`web_search` 可以在其工具 schema 和快照覆盖规划完成后获得可选的面向模型的 `timeout_ms`；基于 ripgrep 的文件系统发现工具（[打包的 ripgrep 搜索](2026-08-01-packaged-ripgrep-search.md)）通过 `dsh-timeout-policy` 和 `exec.signal` 消费同样的提供方自有 deadline 形状；`tools/execute` waterfall（瀑布式事件）中间件可以通过驱动 `exec.signal` 为每次工具调用设置默认 deadline——那将是一个*消费*本库的插件，仍然只做通知，硬终止仍是各能力自己的事。 ## 曾考虑的替代方案 diff --git a/.agents/notes/implemented/architecture/2026-07-07-tool-call-timeout-policy.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-07-tool-call-timeout-policy.i18n.yaml index 6e7aa8291a..4ac6aa8cdd 100644 --- a/.agents/notes/implemented/architecture/2026-07-07-tool-call-timeout-policy.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-07-tool-call-timeout-policy.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-07-tool-call-timeout-policy.md -2026-07-07-tool-call-timeout-policy.md: b85a4d2d60ef60d9f75bd47d4d405aa55c132af6 -2026-07-07-tool-call-timeout-policy.zh.md: f6a85c13a66689c48b10f160890ce3825125aec1 +2026-07-07-tool-call-timeout-policy.md: f17834332b2e661b6811c2264d5e8de4e1642663 +2026-07-07-tool-call-timeout-policy.zh.md: 3be8614f209b2896f0754cadd868f6e66b78f834 diff --git a/.agents/notes/implemented/architecture/2026-07-07-tool-call-timeout-policy.md b/.agents/notes/implemented/architecture/2026-07-07-tool-call-timeout-policy.md index b85a4d2d60..f17834332b 100644 --- a/.agents/notes/implemented/architecture/2026-07-07-tool-call-timeout-policy.md +++ b/.agents/notes/implemented/architecture/2026-07-07-tool-call-timeout-policy.md @@ -32,7 +32,7 @@ ctx.tools.execute(exec) The default behavior is conservative: a tool that declares no `timeoutMs` receives no `TOOL_TIMEOUT` deadline from the plugin. -### The `tools/execute` around seam +### The `tools/execute` around-dispatch extension point `@deepseek-ai/dsh-tools` declares a `tools/execute` waterfall whose base `next()` is the dispatch-with-normalization thunk — the same inner `try`/`catch` that turns a thrown tool (or unknown tool) into an `isError` `ToolExecutionResult`. A listener receives `(exec, next)`: it calls `next()` to delegate to dispatch (returning its result, optionally wrapped) or returns a replacement result to short-circuit dispatch. The whole pipeline still sits inside `execute`'s outer try/catch, so a throwing listener becomes an `isError` result, never a turn failure. @@ -85,7 +85,7 @@ No new session event is needed for reconstructability: `TOOL_TIMEOUT` is the fin `read`, `write`, `edit`, `todo_write`, `task_list`, and `task_kill` do not opt into tool-call timeout. `task_output` owns its bounded wait because a wait timeout is a successful live-status result, not a tool failure. -A future model-facing grep/glob tool can be implemented on top of `ctx.bash` without importing `@deepseek-ai/dsh-timeout`: it forwards `exec.signal` to `ctx.bash`, and declares its own `timeoutMs` (from its plugin's config) for the enforcer to apply. If bash-local's backend timeout becomes a problem for such a tool, the bash seam can later add a caller-owned-deadline mode; that is outside this cut. +A future model-facing grep/glob tool can be implemented on top of `ctx.bash` without importing `@deepseek-ai/dsh-timeout`: it forwards `exec.signal` to `ctx.bash`, and declares its own `timeoutMs` (from its plugin's config) for the enforcer to apply. If bash-local's backend timeout becomes a problem for such a tool, the bash seam can later add a caller-owned-deadline mode; that is a separate decision. ## Alternatives considered @@ -101,14 +101,13 @@ A future model-facing grep/glob tool can be implemented on top of `ctx.bash` wit **Let `timeout-policy` match tool arguments itself.** A rule engine such as "disable timeout when `bash.run_in_background` is true" would make the policy plugin know tool-specific argument semantics. Avoided by not migrating bash to tool-call timeout. -**Use `tools/pre-execute` plus `tools/post-execute` instead of a new around seam.** A pre listener could arm a deadline and mutate `exec.signal`; a post listener could classify and replace. That loses because the deadline lifetime would cross two independent waterfalls: a call-id map, cleanup on every pre-deny/tool-throw/post-throw/dispose path, and ordering rules with every other listener. `tools/pre-execute` is also the allow/deny gate, not an execution wrapper. `tools/execute` gives the timeout one lexical scope: arm, delegate, classify, dispose. +**Use `tools/pre-execute` plus `tools/post-execute` instead of a new around-dispatch extension point.** A pre listener could arm a deadline and mutate `exec.signal`; a post listener could classify and replace. That loses because the deadline lifetime would cross two independent waterfalls: a call-id map, cleanup on every pre-deny/tool-throw/post-throw/dispose path, and ordering rules with every other listener. `tools/pre-execute` is also the allow/deny gate, not an execution wrapper. `tools/execute` gives the timeout one lexical scope: arm, delegate, classify, dispose. **Use `Promise.race` to enforce timeouts for non-cooperative tools.** Rejected for the same reason as the timeout-library Agent Note: it returns control to the caller while the underlying process, fetch, or provider operation may still be running. The plugin only sends a signal; termination remains the implementation's responsibility. ## Consequences -- `@deepseek-ai/dsh-tools` gains an around-dispatch surface after the interception seams deliberately split pre/post tool hooks. Its contract is narrow — wrap registry dispatch, not replace the pre-gate or post-result policy — and the base `next()` is dispatch-with-normalization so a wrapper never sees a raw tool throw. +- `@deepseek-ai/dsh-tools` gains an around-dispatch surface after the interception points deliberately split pre/post tool hooks. Its contract is narrow — wrap registry dispatch, not replace the pre-gate or post-result policy — and the base `next()` is dispatch-with-normalization so a wrapper never sees a raw tool throw. - Multiple `tools/execute` listeners compose by ordinary Cordis waterfall order: a listener that calls `next()` wraps downstream listeners plus dispatch; one that returns without `next()` short-circuits them. A deployment combining timeout with a future retry/sandbox/metrics wrapper chooses semantics by registration order ("timeout covers the whole retry" vs "timeout covers each attempt"). - Opt-in by declaration is a deliberate misconfiguration risk: a tool can declare a `timeoutMs` without honoring `exec.signal`, and that tool will not stop on timeout. The registry awaits that non-quiescent body rather than racing it, while the plugin contract states that declaring a budget means cooperative; the web tools prove the pattern on tools that already forward the signal. - During the transition `bash` and the migrated web tools use different timeout paths on purpose: `TOOL_TIMEOUT` is the model-facing tool-call budget, while `BASH_TIMEOUT` remains the bash backend timeout used by bash and hooks. -- Deviation from the literal proposal, recorded per the implemented-Agent Note rule: the plugin package is `@deepseek-ai/dsh-timeout-policy` (not `tool-timeout`), signal replacement is in-place `exec.signal` mutation before `next()` (not `next({ ...exec, signal })`, which cordis ignores), and the per-tool budget is declared on the `ToolDefinition` (`timeoutMs`, set by the owning tool plugin from its config) rather than mapped by tool name in this plugin's config — so the enforcer is zero-config and a mistyped tool name is impossible. All three are described in `## Decision` above. diff --git a/.agents/notes/implemented/architecture/2026-07-07-tool-call-timeout-policy.zh.md b/.agents/notes/implemented/architecture/2026-07-07-tool-call-timeout-policy.zh.md index f6a85c13a6..3be8614f20 100644 --- a/.agents/notes/implemented/architecture/2026-07-07-tool-call-timeout-policy.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-07-tool-call-timeout-policy.zh.md @@ -32,7 +32,7 @@ ctx.tools.execute(exec) 默认行为是保守的：未声明 `timeoutMs` 的工具不会从该插件收到 `TOOL_TIMEOUT` 截止信号。 -### `tools/execute` 环绕 seam +### `tools/execute` 环绕分发扩展点 `@deepseek-ai/dsh-tools` 声明了一个 `tools/execute` waterfall，其基础 `next()` 是带规范化的分发 thunk——即同一个内部 `try`/`catch`，将抛出的工具错误（或未知工具错误）转换为 `isError` 的 `ToolExecutionResult`。监听器接收 `(exec, next)`：调用 `next()` 委托给分发（返回其结果，可选地包装），或返回替代结果以短路分发。整个流水线仍位于 `execute` 的外层 try/catch 内，因此抛出异常的监听器会变成 `isError` 结果，而非轮次失败。 @@ -85,7 +85,7 @@ function toolTimeoutResult(timeoutMs: number): ToolExecutionResult { `read`、`write`、`edit`、`todo_write`、`task_list` 和 `task_kill` 不加入工具调用超时。`task_output` 自己拥有有界等待，因为等待超时是成功的实时状态结果，而非工具失败。 -未来面向模型的 grep/glob 工具可以基于 `ctx.bash` 实现而无需导入 `@deepseek-ai/dsh-timeout`：它将 `exec.signal` 转发给 `ctx.bash`，并声明自己的 `timeoutMs`（来自其插件配置）供执行器应用。如果 bash-local 的后端超时对这类工具造成问题，bash seam 可以后续添加调用方自有截止模式；这不在本次范围内。 +未来面向模型的 grep/glob 工具可以基于 `ctx.bash` 实现而无需导入 `@deepseek-ai/dsh-timeout`：它将 `exec.signal` 转发给 `ctx.bash`，并声明自己的 `timeoutMs`（来自其插件配置）供执行器应用。如果 bash-local 的后端超时对这类工具造成问题，bash seam 可以后续添加调用方自有截止模式；那是一项独立的决策。 ## 曾考虑的替代方案 @@ -101,14 +101,13 @@ function toolTimeoutResult(timeoutMs: number): ToolExecutionResult { **让 `timeout-policy` 自行匹配工具参数。** 诸如「当 `bash.run_in_background` 为 true 时禁用超时」之类的规则引擎会让策略插件了解工具特定的参数语义。通过不将 bash 迁移到工具调用超时来规避此问题。 -**使用 `tools/pre-execute` 加 `tools/post-execute` 代替新的环绕 seam。** pre 监听器可以启动截止时间并修改 `exec.signal`；post 监听器可以分类并替换。这样做的问题是截止时间的生命周期会跨越两个独立的 waterfall：需要 call-id 映射、在每条 pre-deny/tool-throw/post-throw/dispose（资源释放）路径上清理，以及与其他监听器的排序规则。`tools/pre-execute` 也是允许/拒绝门禁，而非执行包装器。`tools/execute` 给超时一个词法作用域：启动、委托、分类、释放。 +**使用 `tools/pre-execute` 加 `tools/post-execute` 代替新的环绕分发扩展点。** pre 监听器可以启动截止时间并修改 `exec.signal`；post 监听器可以分类并替换。这样做的问题是截止时间的生命周期会跨越两个独立的 waterfall：需要 call-id 映射、在每条 pre-deny/tool-throw/post-throw/dispose（资源释放）路径上清理，以及与其他监听器的排序规则。`tools/pre-execute` 也是允许/拒绝门禁，而非执行包装器。`tools/execute` 给超时一个词法作用域：启动、委托、分类、释放。 **使用 `Promise.race` 对非协作工具强制超时。** 与超时库 Agent Note 相同的理由否决：它在底层进程、fetch 或提供方操作可能仍在运行时就将控制权返回给调用方。插件只发送信号；终止仍是实现方的责任。 ## 后果 -- `@deepseek-ai/dsh-tools` 在有意拆分 pre/post 工具钩子的拦截 seam 之后，获得了一个环绕分发接口。其约定是狭窄的——包装注册表分发，而非替代 pre 门禁或 post 结果策略——且基础 `next()` 是带规范化的分发，因此包装器永远不会看到未经处理的工具异常。 +- `@deepseek-ai/dsh-tools` 在拦截点有意拆分 pre/post 工具钩子之后，获得了一个环绕分发接口。其约定是狭窄的——包装注册表分发，而非替代 pre 门禁或 post 结果策略——且基础 `next()` 是带规范化的分发，因此包装器永远不会看到未经处理的工具异常。 - 多个 `tools/execute` 监听器按普通 Cordis waterfall 顺序组合：调用 `next()` 的监听器包装下游监听器加分发；不调用 `next()` 直接返回的监听器短路它们。一个同时组合超时与未来重试/沙箱/指标包装器的部署通过注册顺序选择语义（「超时覆盖整个重试」vs「超时覆盖每次尝试」）。 - 按声明加入是一个有意的误配置风险：工具可以声明 `timeoutMs` 但不遵循 `exec.signal`，这样的工具在超时时不会停止。注册表会等待这个尚未完全停稳的工具体结束，而不是与它竞速；同时插件约定声明：声明预算意味着协作；web 工具在已转发信号的工具上验证了这一模式。 - 过渡期间 `bash` 和已迁移的 web 工具有意使用不同的超时路径：`TOOL_TIMEOUT` 是面向模型的工具调用预算，而 `BASH_TIMEOUT` 仍是 bash 和钩子使用的 bash 后端超时。 -- 与字面提案的偏差，按 implemented-Agent Note 规则记录：插件包为 `@deepseek-ai/dsh-timeout-policy`（而非 `tool-timeout`）；信号替换是在 `next()` 之前就地修改 `exec.signal`（而非 `next({ ...exec, signal })`，Cordis 会忽略后者）；逐工具预算声明在 `ToolDefinition` 上（`timeoutMs`，由拥有该工具的插件从其配置中设置），而非在本插件配置中按工具名映射——因此执行器是零配置的，拼错工具名不可能发生。以上三点均在上文 `## Decision` 中描述。 diff --git a/.agents/notes/implemented/architecture/2026-07-08-agent-scope-contexts.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-08-agent-scope-contexts.i18n.yaml index 8f9fb5e270..efed9ca5ea 100644 --- a/.agents/notes/implemented/architecture/2026-07-08-agent-scope-contexts.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-08-agent-scope-contexts.i18n.yaml @@ -3,4 +3,4 @@ # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-08-agent-scope-contexts.md 2026-07-08-agent-scope-contexts.md: eb3f6f247bac1a1d81aa2644132c7b9cc04d602c -2026-07-08-agent-scope-contexts.zh.md: a6dcd421cb2e8a64cdbe6393253355ad8554303e +2026-07-08-agent-scope-contexts.zh.md: fe82ac18d07de97330e86461e6bdf86edc37d2ae diff --git a/.agents/notes/implemented/architecture/2026-07-08-agent-scope-contexts.zh.md b/.agents/notes/implemented/architecture/2026-07-08-agent-scope-contexts.zh.md index a6dcd421cb..fe82ac18d0 100644 --- a/.agents/notes/implemented/architecture/2026-07-08-agent-scope-contexts.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-08-agent-scope-contexts.zh.md @@ -25,7 +25,7 @@ Cordis 是 SDK 底层的插件框架。Cordis **上下文**是插件用来访问 | 在哪里为某个 agent 注册行为？ | 通过 `agent.ctx` 调用普通注册 API | | 某个 agent 的操作能看到什么？ | 部署全局加上该 agent 的层，按所属服务的合并规则 | | 哪些作用域监听器会运行？ | 无作用域监听器加上为该操作所属 agent 注册的监听器 | -| 该层存在多久？ | setup 在发布前完成；dispose 保留该层直到工作完全停稳 | +| 该层存在多久？ | setup 在发布前完成；dispose（资源释放）保留该层直到工作完全停稳 | 作用域是扁平的。解析永远不会遍历父级或兄弟作用域，生命周期所有权也不意味着注册继承。 @@ -49,7 +49,7 @@ flowchart LR ### 注册来源决定可见性与清理 -通过普通插件上下文进行的注册是部署全局的，随该插件一起 dispose（资源释放）。同一方法通过 `agent.ctx` 调用则贡献给一个 agent，随该 agent 的作用域一起 dispose。 +通过普通插件上下文进行的注册是部署全局的，随该插件一起 dispose。同一方法通过 `agent.ctx` 调用则贡献给一个 agent，随该 agent 的作用域一起 dispose。 | 注册来源 | 默认可见性 | 随谁 dispose | |---|---|---| @@ -108,13 +108,13 @@ setup 接收一个完整的受信 Cordis 上下文，因此可以组合普通插 ### 创建最后发布，dispose 最后撤销 -`ctx.agents.create()` 和 `resume()` 构建未发布的会话、作用域、agent 和驱动器。它们等待 `setup`，同步调用其可选的 `AgentSetupCommit`，准入最终的会话和 agent 条目，按序公告，启动循环，然后才返回 handle。该提交操作让可变的配置状态在所有 setup 的 await 均结算后，于确切的发布边界重新校验；若其抛出异常，则会在公告任何一个身份前回滚私有事务，而成功提交后的撤销属于普通的实时拆卸。 +`ctx.agents.create()` 和 `resume()` 构建未发布的会话、作用域、agent 和驱动器。它们等待 `setup`，同步调用其可选的 `AgentSetupCommit`，准入最终的会话和 agent 条目，按序公告，启动循环，然后才返回 handle。该提交操作让可变的配置状态在所有 setup 的 await 均结算后，于确切的发布边界重新校验；若其抛出异常，则会在公告任何一个身份前回滚私有事务，而成功提交后的撤销属于普通的存活期拆除。 可选的创建信号仅在创建或恢复挂起期间取消工作。promise resolve 后，返回的 `AgentHandle` 拥有显式 dispose 权。 如果加载、setup、可选的 setup 提交、准入或发布失败，私有事务回滚其准备的一切。使用同一个调用方提供的存活 ID 的并发操作可能都到达 setup，但最终注册表条目只准入一个；每个失败者拒绝并清理其私有资源。在等待 dispose 完成后的顺序复用仍然有效。 -`AgentHandle.dispose()` 反转边界。它停用创建或驱动，等待同步发布解除，停止并排空驱动器和最终会话刷写，分离 agent 和会话，最后 dispose 作用域。重复或竞争的 dispose 请求合并为一个完成 promise。 +`AgentHandle.dispose()` 反转边界。它停用创建或驱动，等待同步发布完成退栈，停止并排空驱动器和最终会话刷写，分离 agent 和会话，最后 dispose 作用域。重复或竞争的 dispose 请求合并为一个完成 promise。 调用方的 Cordis 上下文和具体的 AgentLoop 工厂是结构性共同所有者。卸载任一方都会 dispose 事务或存活 agent。 @@ -152,7 +152,7 @@ agent 作用域组合的是受信的同进程注册。它不沙箱化插件、 ### 向每个注册传递 agent 选项 -类似 `tools.register(definition, { agent })` 的 API 在每个注册表中重复作用域管道，且允许可见性所有权与清理所有权漂移。通过 `agent.ctx` 注册使两个事实跟随同一个 Cordis effect owner。 +类似 `tools.register(definition, { agent })` 的 API 在每个注册表中重复作用域传递逻辑，且允许可见性所有权与清理所有权漂移。通过 `agent.ctx` 注册使两个事实跟随同一个 Cordis effect owner。 ### 过滤事件但保持注册表全局 @@ -160,7 +160,7 @@ agent 作用域组合的是受信的同进程注册。它不沙箱化插件、 ### 为每个 agent 创建独立的服务图 -所需的视图是共享部署服务加上一个本地注册层。每 agent 一个图会重复适配器，并使共享持久化、提供方注册表和应用启动复杂化。 +所需的视图是共享部署服务加上一个本地注册层。每个 agent 一个服务图会重复适配器，并使共享持久化、提供方注册表和应用启动复杂化。 ### 继承父级注册作用域 diff --git a/.agents/notes/implemented/architecture/2026-07-08-tool-output-spill-files.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-08-tool-output-spill-files.i18n.yaml index dbac0c0688..34abd78451 100644 --- a/.agents/notes/implemented/architecture/2026-07-08-tool-output-spill-files.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-08-tool-output-spill-files.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-08-tool-output-spill-files.md -2026-07-08-tool-output-spill-files.md: 7c0ca90452645d251559be25108d12883210d00e -2026-07-08-tool-output-spill-files.zh.md: 628023a9d12fec17d32749f9d17a3b701ca3a475 +2026-07-08-tool-output-spill-files.md: 0c8e5e25fc8a229db8fca36512ba781e548b5256 +2026-07-08-tool-output-spill-files.zh.md: 771253335bf5822cb855c63e7dd0bbf0d517bab3 diff --git a/.agents/notes/implemented/architecture/2026-07-08-tool-output-spill-files.md b/.agents/notes/implemented/architecture/2026-07-08-tool-output-spill-files.md index 7c0ca90452..0c8e5e25fc 100644 --- a/.agents/notes/implemented/architecture/2026-07-08-tool-output-spill-files.md +++ b/.agents/notes/implemented/architecture/2026-07-08-tool-output-spill-files.md @@ -22,7 +22,7 @@ A thin spill storage seam plus a default spill policy plugin, in a new `packages | `@deepseek-ai/dsh-spill-local` | Local backend: private, session-scoped file storage on the host filesystem. | | `@deepseek-ai/dsh-spill-policy` | Tool-result policy plugin: wraps final text results after dispatch and replaces oversized results with a retained preview plus a spill locator. | -There is no dedicated model-facing consumer package. The consumer is the existing `ctx.tools` execution pipeline: `dsh-spill-policy` consumes final tool results through the `tools/post-execute` waterfall, and the model follows the backend-supplied retrieval hint for the returned locator. +There is no dedicated model-facing Consumer package. The Consumer is the existing `ctx.tools` execution pipeline: `dsh-spill-policy` consumes final tool results through the `tools/post-execute` waterfall, and the model follows the backend-supplied retrieval hint for the returned locator. ### Spill seam diff --git a/.agents/notes/implemented/architecture/2026-07-08-tool-output-spill-files.zh.md b/.agents/notes/implemented/architecture/2026-07-08-tool-output-spill-files.zh.md index 628023a9d1..771253335b 100644 --- a/.agents/notes/implemented/architecture/2026-07-08-tool-output-spill-files.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-08-tool-output-spill-files.zh.md @@ -22,7 +22,7 @@ Status: implemented | `@deepseek-ai/dsh-spill-local` | 本地后端：在宿主文件系统中提供私有、会话作用域的文件存储。 | | `@deepseek-ai/dsh-spill-policy` | 工具结果策略插件：包装分发后的最终文本结果，并以保留预览和落盘定位符替换超大结果。 | -系统不增加专用的面向模型消费方包。消费方是现有 `ctx.tools` 执行流水线：`dsh-spill-policy` 通过 `tools/post-execute` waterfall（瀑布式事件）使用最终工具结果，模型则按照后端随定位符返回的检索提示读取内容。 +系统不增加专用的面向模型 Consumer 包。Consumer 是现有 `ctx.tools` 执行流水线：`dsh-spill-policy` 通过 `tools/post-execute` waterfall（瀑布式事件）使用最终工具结果，模型则按照后端随定位符返回的检索提示读取内容。 ### 落盘 seam diff --git a/.agents/notes/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.i18n.yaml index 03acf306b4..d658f71140 100644 --- a/.agents/notes/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md -2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md: 6fbd5e2c9d57da3f25c72c652ca50eb45b84323c -2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md: 8a480999038cf892842290e3ea3902683d87e431 +2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md: 08715d3ad6ad7a2346327861e7134b10da184f00 +2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md: 77b57274d0d931f0ec58fecd3d5f9ca5bba3f624 diff --git a/.agents/notes/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md b/.agents/notes/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md index 6fbd5e2c9d..08715d3ad6 100644 --- a/.agents/notes/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md +++ b/.agents/notes/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md @@ -6,7 +6,7 @@ English | [中文](2026-07-10-after-call-compaction-pressure-and-overflow-recove ## Problem -`agent/pre-step` runs before final request routing and before assistant output, tool results, buffered context, and steering exist. Even with the assembled prompt and session prefix, its pressure view is provisional because `agent/request` can still change routing or call configuration and tool schemas are not frozen with those inputs. Adding fields cannot make pre-call state describe a completed call and couples the generic seam to compaction. +`agent/pre-step` runs before final request routing and before assistant output, tool results, buffered context, and steering exist. Even with the assembled prompt and session prefix, its pressure view is provisional because `agent/request` can still change routing or call configuration and tool schemas are not frozen with those inputs. Adding fields cannot make pre-call state describe a completed call and couples the generic extension point to compaction. Successful calls are not the only pressure signal. A provider can reject a request for exceeding its context window before it returns usage, and some successful calls omit usage. The system therefore needs replayable post-call pressure plus a narrow failure-recovery path that preserves the provider error whenever compaction cannot prove useful progress. @@ -32,7 +32,7 @@ If cancellation lands after assistant tool calls are durable but before all call `CompactService.compactIfNeeded(agent, trigger, signal)` accepts `trigger: 'pressure' | 'context-overflow'`. The interface gains no estimation methods or token types; `ctx.tokenMeter` remains the reusable accounting owner. -For `pressure`, compact-basic resolves the durable provider/model target's adapter-owned capacity and exact-target policy, then applies the resulting threshold and retained-tail budgets to one unified `ctx.tokenMeter.measure()` result. Below pressure it returns without pruning. Once pressure qualifies, optional `ctx.toolResultPrune` rewrites oversized current results and compact-basic remeasures through the same meter; safe pressure skips the model call, while remaining pressure selects and summarizes from the pruned surface. The same singleton meter owns range pricing, provenance, shadowed token counts, and non-shrinking-summary rejection. Common defaults remain threshold ratio `0.8`, retained-history ratio `0.16`, summarization provider/model `''`, `maxTokens: 8192`, `compactionRetries: 1`, and `auto: true`; optional `modelPolicies` entries override them for an exact provider/model pair. +For `pressure`, compact-basic resolves the durable provider/model target's adapter-owned capacity and exact-target policy, then applies the resulting threshold and retained-tail budgets to one unified `ctx.tokenMeter.measure()` result. Below pressure it returns without pruning. Once pressure qualifies, optional `ctx.toolResultPrune` rewrites oversized current results and compact-basic remeasures through the same meter; safe pressure skips the model call, while remaining pressure selects and summarizes from the pruned surface. The same singleton meter owns range pricing, cited source-event accounting, shadowed token counts, and non-shrinking-summary rejection. Common defaults remain threshold ratio `0.8`, retained-history ratio `0.16`, summarization provider/model `''`, `maxTokens: 8192`, `compactionRetries: 1`, and `auto: true`; optional `modelPolicies` entries override them for an exact provider/model pair. For canonical overflow, compact-basic requires no capacity metadata and bypasses scalar pressure and the normal retained-token budget. It prunes first, then chooses the maximal tool-balanced head range while leaving the newest indivisible unit and attempts one shrinking summary compaction under the same signal when a range exists. The automatic listener snapshots `session.surface.replaceGeneration` and returns `{ kind: 'retry' }` whenever pruning or summarization increases it. This remains true when pruning lands before later summary work throws; cancellation still wins. A backend returning a result without replacement cannot authorize retry, while pruning-only progress can authorize a retry without a `CompactionResult`. diff --git a/.agents/notes/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md b/.agents/notes/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md index 8a48099903..77b57274d0 100644 --- a/.agents/notes/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md @@ -6,7 +6,7 @@ Status: implemented ## 问题 -`agent/pre-step` 运行在最终请求路由之前，也早于 assistant 输出、工具结果、缓冲上下文与 steering（中途引导）的产生。即使它接收已装配提示词与会话前缀，压力视图仍是临时的，因为 `agent/request` 还可以改变路由或调用配置，工具 schema 也没有与这些输入一同冻结。增加字段无法让调用前状态描述已完成调用，还会把通用 seam 与压缩耦合。 +`agent/pre-step` 运行在最终请求路由之前，也早于 assistant 输出、工具结果、缓冲上下文与 steering（中途引导）的产生。即使它接收已装配提示词与会话前缀，压力视图仍是临时的，因为 `agent/request` 还可以改变路由或调用配置，工具 schema 也没有与这些输入一同冻结。增加字段无法让调用前状态描述已完成调用，还会把通用扩展点与压缩耦合。 成功调用也不是唯一的压力信号。提供方可能在返回 usage 之前就因上下文窗口超限拒绝请求，一些成功调用也不提供 usage。因此，系统需要可回放的调用后压力，以及一条狭窄的失败恢复路径；当压缩无法证明取得有效进展时，必须保留原始提供方错误。 @@ -32,7 +32,7 @@ Compact-basic 会在每个拟议请求之前包装 `agent/pre-step`。在续步 `CompactService.compactIfNeeded(agent, trigger, signal)` 接收 `trigger: 'pressure' | 'context-overflow'`。接口不增加估算方法或 token 类型；`ctx.tokenMeter` 继续作为可复用的核算所有者。 -对于 `pressure`，compact-basic 先解析持久提供方/模型目标对应适配器所维护的容量与精确目标策略，再把得到的阈值与保留尾部预算应用到一次统一的 `ctx.tokenMeter.measure()` 结果。未达到压力阈值时直接返回，不执行剪枝。压力达到条件后，可选的 `ctx.toolResultPrune` 会改写当前表层中过大的工具结果，compact-basic 再通过同一个 meter 重新计量；若压力已降至安全水平则跳过模型调用，否则从已剪枝表层选择范围并生成摘要。范围定价、来源、被遮蔽 token 数与非缩小摘要拒绝也由同一个单例 meter 完成。通用默认值保持为阈值比例 `0.8`、保留历史比例 `0.16`、摘要提供方/模型 `''`、`maxTokens: 8192`、`compactionRetries: 1` 与 `auto: true`；可选 `modelPolicies` 项可以按精确提供方/模型组合覆盖这些值。 +对于 `pressure`，compact-basic 先解析持久提供方/模型目标对应适配器所维护的容量与精确目标策略，再把得到的阈值与保留尾部预算应用到一次统一的 `ctx.tokenMeter.measure()` 结果。未达到压力阈值时直接返回，不执行剪枝。压力达到条件后，可选的 `ctx.toolResultPrune` 会改写当前表层中过大的工具结果，compact-basic 再通过同一个 meter 重新计量；若压力已降至安全水平则跳过模型调用，否则从已剪枝表层选择范围并生成摘要。范围定价、引用的源事件计量、被遮蔽 token 数与非缩小摘要拒绝也由同一个单例 meter 完成。通用默认值保持为阈值比例 `0.8`、保留历史比例 `0.16`、摘要提供方/模型 `''`、`maxTokens: 8192`、`compactionRetries: 1` 与 `auto: true`；可选 `modelPolicies` 项可以按精确提供方/模型组合覆盖这些值。 对于规范化溢出，compact-basic 不要求容量元数据，并绕过标量压力与普通保留 token 预算。它先执行剪枝，再在保留最新不可分割单元的同时选择最大的工具配对平衡头部范围；存在范围时，才在同一 signal 下尝试一次缩小摘要压缩。自动监听器先记录 `session.surface.replaceGeneration`，剪枝或摘要让 generation 增加时就返回 `{ kind: 'retry' }`。即使剪枝先落盘而后续摘要工作抛错，这条规则仍然成立；取消依然优先。后端若只返回结果但没有替换表层，不能授权重试；只有剪枝取得进展时，即使没有 `CompactionResult` 也可以授权重试。 diff --git a/.agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.i18n.yaml index aa1d2c9d6f..8bef07d042 100644 --- a/.agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md -2026-07-10-single-file-executable-sdk-runtime-distribution.md: fe09e1b83f4f0a9f867f78351f643b1bd26d7c9d -2026-07-10-single-file-executable-sdk-runtime-distribution.zh.md: 0279e0cf032928e96bad9da02340cae753a0927f +2026-07-10-single-file-executable-sdk-runtime-distribution.md: a45678c9bb5fcae340ff7134687890879f56c630 +2026-07-10-single-file-executable-sdk-runtime-distribution.zh.md: f1fccc508471356dd6434da0e126ed38f15ed3ba diff --git a/.agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md b/.agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md index fe09e1b83f..a45678c9bb 100644 --- a/.agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md +++ b/.agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md @@ -76,7 +76,7 @@ Manual-driving caveat: the bin treats stdin EOF as "the client is gone" and disp **jsonrpc-agent carrying the full closure dependencies.** The app bin would declare 53+ dependencies it never imports — a "packaging manifest" masquerading as real dependency relationships — and would force constraints to open two exceptions for it, cordis-in-dependencies and a files wildcard. With the closure manifest landing on the python-side manifest package, constraints needs no exception at all and the bin keeps the normal package shape isomorphic to acp-agent. -**An open plugin set (loading user plugins from disk).** This round ships a closed set; the PoC incidentally confirmed that on-disk ESM import outside the VFS works (through the `ctx.baseUrl` relative-path channel). It is listed as a future evolution, which must separately solve sharing the cordis instance inside the exe with external plugins. +**An open plugin set (loading user plugins from disk).** The shipped set is closed; the PoC incidentally confirmed that on-disk ESM import outside the VFS works (through the `ctx.baseUrl` relative-path channel). It is listed as a future evolution, which must separately solve sharing the cordis instance inside the exe with external plugins. ## Consequences diff --git a/.agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.zh.md b/.agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.zh.md index 0279e0cf03..f1fccc5084 100644 --- a/.agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.zh.md @@ -76,7 +76,7 @@ exe 内支持 `dsh-workflow-workerthread` 与 `dsh-code-runtime-worker`。两个 **让 jsonrpc-agent 承担完整闭包依赖。** 应用入口将声明 53 个以上自身并不 `import()` 的依赖，使「打包 manifest」伪装成真实依赖关系，还会迫使 `constraints` 为其增加 `cordis-in-dependencies` 与 `files` 通配符两个例外。将闭包清单放在 Python 侧的 manifest 包后，`constraints` 不需要任何例外，`bin` 也能保持与 acp-agent 同构的正常包形状。 -**开放插件集（从磁盘加载用户插件）。** 本期采用封闭集；PoC 同时证实，可以通过 `ctx.baseUrl` 相对路径通道从 VFS 外的磁盘 `import()` ESM。该能力列为后续演进，届时还需解决外部插件与 exe 内 Cordis 实例的共享问题。 +**开放插件集（从磁盘加载用户插件）。** 交付的集合是封闭的；PoC 同时证实，可以通过 `ctx.baseUrl` 相对路径通道从 VFS 外的磁盘 `import()` ESM。该能力列为后续演进，届时还需解决外部插件与 exe 内 Cordis 实例的共享问题。 ## 后果 diff --git a/.agents/notes/implemented/architecture/2026-07-12-agent-scope-runtime-design.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-12-agent-scope-runtime-design.i18n.yaml index f5fdd4e906..91deb7153c 100644 --- a/.agents/notes/implemented/architecture/2026-07-12-agent-scope-runtime-design.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-12-agent-scope-runtime-design.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-12-agent-scope-runtime-design.md -2026-07-12-agent-scope-runtime-design.md: b8f265551c4ebbb94d32b3599959fe6cc4da974d -2026-07-12-agent-scope-runtime-design.zh.md: 22cd35a601bc011c27a748098be11990f5ee4653 +2026-07-12-agent-scope-runtime-design.md: 8903a2fefa83dba042f8105b182e590783a9adde +2026-07-12-agent-scope-runtime-design.zh.md: d86ab3d8cb9a051d4664aedac812b10b53521f22 diff --git a/.agents/notes/implemented/architecture/2026-07-12-agent-scope-runtime-design.md b/.agents/notes/implemented/architecture/2026-07-12-agent-scope-runtime-design.md index b8f265551c..8903a2fefa 100644 --- a/.agents/notes/implemented/architecture/2026-07-12-agent-scope-runtime-design.md +++ b/.agents/notes/implemented/architecture/2026-07-12-agent-scope-runtime-design.md @@ -226,7 +226,7 @@ After post-execute or outer pipeline normalization, the registry losslessly snap SystemPrompt first resolves the global-plus-agent sections, variables, and tool providers into a deterministic registry contribution. The scope-filtered `system-prompt/assemble` waterfall may then reorder, replace, add, or remove any section, variable, or schema. Its returned assembly is authoritative; there is no later restoration pass and no finality metadata on ordinary prompt sections, tool definitions, or provider results. -This is a trusted same-process extension seam, not an authority boundary. A listener that changes Code Mode's `run_code` schema or `tools:sdk` instructions, or a structured child's capture schema or instruction, owns preserving a coherent protocol in the assembly it returns. ToolRegistry still reserves `run_code` against ordinary tool registration and restriction because those are registry invariants, but assembly middleware remains free to transform the final model-visible surface. +This is a trusted same-process extension point, not an authority boundary. A listener that changes Code Mode's `run_code` schema or `tools:sdk` instructions, or a structured child's capture schema or instruction, owns preserving a coherent protocol in the assembly it returns. ToolRegistry still reserves `run_code` against ordinary tool registration and restriction because those are registry invariants, but assembly middleware remains free to transform the final model-visible surface. Scope solves the real isolation problem directly. Structured-output contributions register in the child's exact scope, while Code Mode derives its transport and SDK from the same resolved tool view. A second named-protection system would need another ownership and collision rule across arbitrary schema providers—including providers that intentionally contribute duplicate names—without creating a new trust boundary. @@ -360,7 +360,7 @@ This splits provider acceptance from publication and forces every consumer to re ### Restore selected prompt or tool contributions after assembly -A post-waterfall restoration pass would create a second composition rule after the documented cooperative seam. Correctly assigning canonical presence or absence would also require provider ownership and collision rules for arbitrary tool-schema providers, whose ordinary output may contain duplicate names. Scoped registration already supplies the required per-agent isolation, and trusted assembly listeners own the protocol consistency of what they return, so named restoration adds machinery without establishing an independent boundary. +A post-waterfall restoration pass would create a second composition rule after the documented cooperative waterfall. Correctly assigning canonical presence or absence would also require provider ownership and collision rules for arbitrary tool-schema providers, whose ordinary output may contain duplicate names. Scoped registration already supplies the required per-agent isolation, and trusted assembly listeners own the protocol consistency of what they return, so named restoration adds machinery without establishing an independent boundary. ### Remove worker/process lifecycle guards with same-process hardening diff --git a/.agents/notes/implemented/architecture/2026-07-12-agent-scope-runtime-design.zh.md b/.agents/notes/implemented/architecture/2026-07-12-agent-scope-runtime-design.zh.md index 22cd35a601..d86ab3d8cb 100644 --- a/.agents/notes/implemented/architecture/2026-07-12-agent-scope-runtime-design.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-12-agent-scope-runtime-design.zh.md @@ -30,7 +30,7 @@ Status: implemented 本 Agent Note 余下部分按依赖顺序展开这些选择：Cordis 机制、作用域路由、创建与会话提交、工具与提示词、subagent 与工作流，最后是可执行检查。 -[7 月 8 日 Agent Note](2026-07-08-agent-scope-contexts.md)仍然是贡献者约定。独立的 [subagent 组合控制 Agent Note](../feature/2026-07-12-subagent-persona-tool-filter-and-depth.md)拥有 `persona`、`toolFilter` 和 `maxDepth`；本文仅讨论它们的 setup 如何融入生命周期。 +[7 月 8 日 Agent Note](2026-07-08-agent-scope-contexts.md) 仍然是贡献者约定。独立的 [subagent 组合控制 Agent Note](../feature/2026-07-12-subagent-persona-tool-filter-and-depth.md) 拥有 `persona`、`toolFilter` 和 `maxDepth`；本文仅讨论它们的 setup 如何融入生命周期。 ## Cordis 模型：上下文、fiber、effect、receiver 与 waterfall @@ -208,7 +208,7 @@ Session 头部、种子和追加的事件是无损 JSON 数据。Session 构造 私有解析器应用当前展示模式、活跃的全局限制、精确的局部叠加和局部遮蔽。Schema、查找、执行、Code Mode SDK 生成和限制验证都使用该解析器或其限制前的全局名称视图。 -[subagent 组合控制 Agent Note](../feature/2026-07-12-subagent-persona-tool-filter-and-depth.md#tool-filtering-is-one-live-global-view-rule)拥有用户可见的 allow/deny 语义。实现要求是一致性：被过滤掉的全局工具不能通过另一条查找路径仍可执行，局部遮蔽的定义就是被展示和执行的同一个定义。 +[subagent 组合控制 Agent Note](../feature/2026-07-12-subagent-persona-tool-filter-and-depth.md#tool-filtering-is-one-live-global-view-rule) 拥有用户可见的 allow/deny 语义。实现要求是一致性：被过滤掉的全局工具不能通过另一条查找路径仍可执行，局部遮蔽的定义就是被展示和执行的同一个定义。 `ToolRestriction` 接受 readonly 的 allow/deny 名称并将其编译为内部集合。多个限制取交集。公开的 `visible()` 和 `knownNames()` 方法是不必要的，因为只有注册表需要中间视图。 @@ -226,7 +226,7 @@ Session 头部、种子和追加的事件是无损 JSON 数据。Session 构造 SystemPrompt 首先将全局加 agent 的段、变量和工具提供方解析为确定性的注册表贡献。作用域过滤的 `system-prompt/assemble` waterfall 随后可以重排、替换、添加或移除任何段、变量或 schema。其返回的组装结果即为权威；没有后续的恢复步骤，普通提示词段、工具定义或提供方结果上也没有终态元数据。 -这是一个可信的同进程扩展 seam，而非权限边界。修改 Code Mode 的 `run_code` schema 或 `tools:sdk` 指令，或结构化子级的捕获 schema 或指令的监听器，有责任在其返回的组装中保持协议的一致性。ToolRegistry 仍然保留 `run_code` 不受普通工具注册和限制影响，因为那些是注册表不变式，但 assembly 中间件仍然可以自由变换最终的模型可见表面。 +这是一个可信的同进程扩展点，而非权限边界。修改 Code Mode 的 `run_code` schema 或 `tools:sdk` 指令，或结构化子级的捕获 schema 或指令的监听器，有责任在其返回的组装中保持协议的一致性。ToolRegistry 仍然保留 `run_code` 不受普通工具注册和限制影响，因为那些是注册表不变式，但 assembly 中间件仍然可以自由变换最终的模型可见表面。 Scope 直接解决了真正的隔离问题。结构化输出贡献注册在子级的精确作用域中，而 Code Mode 从同一个已解析的工具视图派生其传输和 SDK。第二套命名保护系统需要另一套所有权和碰撞规则来覆盖任意 schema 提供方（包括有意贡献重复名称的提供方），却不创建新的信任边界。 @@ -330,13 +330,13 @@ TypeScript 无法管控 JavaScript 强制转换、直接 Cordis dispatch、进 ### 生成的产物使公开约定保持对齐 -事件目录、服务目录、生产者/消费方矩阵、配置目录、模块图、工具目录、type-equiv 块和作用域事件解析器映射都是从源码生成或受新鲜度门禁约束的。[TypeScript 语义门禁 Agent Note](../process/2026-07-14-typescript-program-backed-semantic-gates.md)拥有 Program 构造、语义事件发现和解析器生成规则。 +事件目录、服务目录、生产者/消费方矩阵、配置目录、模块图、工具目录、type-equiv 块和作用域事件解析器映射都是从源码生成或受新鲜度门禁约束的。[TypeScript 语义门禁 Agent Note](../process/2026-07-14-typescript-program-backed-semantic-gates.md) 拥有 Program 构造、语义事件发现和解析器生成规则。 行为测试固定了作用域路由和 dispose、最终写入注册表时的碰撞清理、发布回滚、有序完全停稳、持久化前/后提交行为、跨展示和执行的活跃工具过滤、协作式提示词组装、原生和 Code Mode 中的结构化输出提交、异步 subagent 启动和信号取消、worker 终端仲裁、ACP 结算和进程拆除。 ## 曾考虑的替代方案 -[7 月 8 日 Agent Note](2026-07-08-agent-scope-contexts.md#alternatives-considered)拥有公开扁平作用域约定的替代方案。此处的替代方案关注实现形态。 +[7 月 8 日 Agent Note](2026-07-08-agent-scope-contexts.md#alternatives-considered) 拥有公开扁平作用域约定的替代方案。此处的替代方案关注实现形态。 ### 使用透明代理作为作用域载体 @@ -360,7 +360,7 @@ TypeScript 无法管控 JavaScript 强制转换、直接 Cordis dispatch、进 ### 在 assembly 之后恢复选定的提示词或工具贡献 -Waterfall 之后的恢复步骤会在文档化的协作式 seam 之后创建第二套组合规则。正确分配规范的存在或缺失还需要为任意工具 schema 提供方制定所有权和碰撞规则，而这些提供方的普通输出可能包含重复名称。作用域注册已经提供了所需的按 agent 隔离，可信的 assembly 监听器拥有其返回内容的协议一致性，因此命名恢复增加了机制却不建立独立边界。 +Waterfall 之后的恢复步骤会在文档化的协作式 waterfall 之后创建第二套组合规则。正确分配规范的存在或缺失还需要为任意工具 schema 提供方制定所有权和碰撞规则，而这些提供方的普通输出可能包含重复名称。作用域注册已经提供了所需的按 agent 隔离，可信的 assembly 监听器拥有其返回内容的协议一致性，因此命名恢复增加了机制却不建立独立边界。 ### 用同进程加固替代 worker/进程生命周期守卫 diff --git a/.agents/notes/implemented/architecture/2026-07-14-provider-routed-llm-adapters.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-14-provider-routed-llm-adapters.i18n.yaml index 2d39db2332..dd7ff64291 100644 --- a/.agents/notes/implemented/architecture/2026-07-14-provider-routed-llm-adapters.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-14-provider-routed-llm-adapters.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-14-provider-routed-llm-adapters.md -2026-07-14-provider-routed-llm-adapters.md: 9039334370ba5d71eb71879970c2e572a5b023df -2026-07-14-provider-routed-llm-adapters.zh.md: eff33496e1a61472534009533270f8f943ccc1f8 +2026-07-14-provider-routed-llm-adapters.md: 8bd34126d05140e486cd170bfc9255f0962dc413 +2026-07-14-provider-routed-llm-adapters.zh.md: 09d9032da5845d3e416dcfa047fde8e6527025b4 diff --git a/.agents/notes/implemented/architecture/2026-07-14-provider-routed-llm-adapters.md b/.agents/notes/implemented/architecture/2026-07-14-provider-routed-llm-adapters.md index 9039334370..8bd34126d0 100644 --- a/.agents/notes/implemented/architecture/2026-07-14-provider-routed-llm-adapters.md +++ b/.agents/notes/implemented/architecture/2026-07-14-provider-routed-llm-adapters.md @@ -10,7 +10,7 @@ English | [中文](2026-07-14-provider-routed-llm-adapters.zh.md) The conflation prevents a provider gateway from serving an open-ended model catalog. OpenRouter, for example, is one provider with many model ids, while a private OpenAI-compatible endpoint may add models without changing the Harness plugin tree. Every newly selected model currently needs to have been registered during plugin startup. The same model id can also exist at multiple providers, so model-only registration cannot state which provider the caller intended. -`dsh-llm-pi-ai` exposed none of pi-ai's provider abstraction. It constructed an inline DeepSeek `openai-completions` model, applied DeepSeek-specific payload patches, and stamped every replayed assistant message as DeepSeek. pi-ai itself has a provider/model catalog, selects APIs such as `openai-responses`, `anthropic-messages`, and `google-generative-ai`, and preserves provider-specific response ids and reasoning/tool signatures for later turns. The Harness conversion dropped that provenance, so simply replacing the inline model with a catalog lookup would have made same-model replay and cross-provider handoff incomplete. +`dsh-llm-pi-ai` exposed none of pi-ai's provider abstraction. It constructed an inline DeepSeek `openai-completions` model, applied DeepSeek-specific payload patches, and stamped every replayed assistant message as DeepSeek. pi-ai itself has a provider/model catalog, selects APIs such as `openai-responses`, `anthropic-messages`, and `google-generative-ai`, and preserves provider-specific response ids and reasoning/tool signatures for later turns. The Harness conversion dropped the provider/model route and provider response fields, so simply replacing the inline model with a catalog lookup would have made same-model replay and cross-provider handoff incomplete. The adapter configuration also assumes one DeepSeek API key and endpoint. A generic backend needs independent credentials and endpoint overrides per provider while leaving AWS, Google ADC, OAuth, and other ambient authentication mechanisms to pi-ai. @@ -28,7 +28,7 @@ A provider has exactly one adapter owner in a Cordis context. `dsh-llm-deepseek` ### Explicit pi-ai provider profiles -`dsh-llm-pi-ai` takes one non-empty list of provider profiles. Provider names must be unique within the list and present in pi-ai's `getProviders()` result. Each profile contains the provider name plus optional `apiKey`, `baseURL`, headers, reasoning level and budgets, cache retention, transport, SDK timeouts, a Harness stream-idle timeout, and a provider-owned `retryPolicy`. The adapter forces pi-ai's `maxRetries` to zero so one `stream()` call makes one visible provider attempt, while `dsh-llm-retry` executes the resolved policy at the agent failed-step seam. Credentials are never global: an explicit key applies only to its profile, while an absent key lets pi-ai resolve its standard environment variable, OAuth token, AWS credential chain, Google ADC, or other provider-native ambient authentication. An explicitly empty key is invalid configuration rather than an environment fallback. +`dsh-llm-pi-ai` takes one non-empty list of provider profiles. Provider names must be unique within the list and present in pi-ai's `getProviders()` result. Each profile contains the provider name plus optional `apiKey`, `baseURL`, headers, reasoning level and budgets, cache retention, transport, SDK timeouts, a Harness stream-idle timeout, and a provider-owned `retryPolicy`. The adapter forces pi-ai's `maxRetries` to zero so one `stream()` call makes one visible provider attempt, while `dsh-llm-retry` executes the resolved policy at the agent failed-step extension point. Credentials are never global: an explicit key applies only to its profile, while an absent key lets pi-ai resolve its standard environment variable, OAuth token, AWS credential chain, Google ADC, or other provider-native ambient authentication. An explicitly empty key is invalid configuration rather than an environment fallback. The plugin registers all configured provider names against one `PiAiAdapter` in one all-or-nothing call. A request uses its provider to select the matching profile and finds its model in `getModels(provider)` to obtain the catalog descriptor. An unknown provider fails at plugin load; an unknown model fails before network I/O with `UNKNOWN_MODEL`. The catalog object is never mutated. When a profile supplies `baseURL`, the adapter clones the selected descriptor and overrides only `baseUrl`, so a private endpoint can retain pi-ai's API, capabilities, compatibility flags, context limits, and reasoning map. The private endpoint must implement the selected provider's protocol, and the model id must still exist in the installed pi-ai catalog. @@ -36,15 +36,15 @@ The adapter calls pi-ai's `streamSimple()` so each catalog model chooses its reg pi-ai's common stream options do not expose stop sequences. `dsh-llm-pi-ai` rejects a defined Harness `stop` option with `UNSUPPORTED_OPTION` rather than silently ignoring it or growing a second provider-specific payload implementation. `dsh-llm-deepseek` continues to support `stop` through its native request serializer. -### Durable assistant provenance and replay state +### Recorded assistant route and replay state -Assistant messages carry provider-neutral provenance containing the request's `provider` and `model`, plus an optional JSON-serializable adapter replay state. A successful `assistant/message` session event records this provenance and `deriveMessages()` returns it with the assistant message. User, system, context, and tool-result messages carry no assistant provenance. The provider/model fields are authoritative loop data; an adapter owns only its opaque replay-state payload. +Assistant messages carry the request's `provider` and `model`, plus an optional JSON-serializable adapter replay state. A successful `assistant/message` session event records those fields and `deriveMessages()` returns them with the assistant message. User, system, context, and tool-result messages carry no assistant route fields. The provider/model fields are authoritative loop data; an adapter owns only its opaque replay-state payload. -A terminal successful `finish` chunk may carry replay state, and `BlockAssembler` retains it alongside usage and finish reason. The loop attaches that state to the assembled assistant provenance without exposing a response-rewrite hook. Error and aborted responses do not produce a normal assistant message and therefore do not enter future model history. +A terminal successful `finish` chunk may carry replay state, and `BlockAssembler` retains it alongside usage and finish reason. The loop attaches that state to the assembled assistant message's model source without exposing a response-rewrite hook. Error and aborted responses do not produce a normal assistant message and therefore do not enter future model history. -The pi-ai replay state is a versioned, minimal projection of its successful `AssistantMessage`: source API/provider/model, response id/model, stop reason, and index-aligned text, thinking, and tool-call signatures. It does not duplicate text or tool arguments already carried by Harness content blocks, and it omits diagnostics, timestamps, usage, and errors. On a later request, `LlmService` gives replay state to the target adapter only when the historical provider and target provider are currently owned by the same adapter instance. That adapter combines the logged Harness content with replay state when it can restore the historical response, and owns any required cross-model or cross-provider conversion. An adapter receiving replay state with an unknown version or mismatched block shape fails explicitly; a different adapter receives only provider-neutral content and provenance. +The pi-ai replay state is a versioned, minimal projection of its successful `AssistantMessage`: source API/provider/model, response id/model, stop reason, and index-aligned text, thinking, and tool-call signatures. It does not duplicate text or tool arguments already carried by Harness content blocks, and it omits diagnostics, timestamps, usage, and errors. On a later request, `LlmService` gives replay state to the target adapter only when the historical provider and target provider are currently owned by the same adapter instance. That adapter combines the logged Harness content with replay state when it can restore the historical response, and owns any required cross-model or cross-provider conversion. An adapter receiving replay state with an unknown version or mismatched block shape fails explicitly; a different adapter receives only provider-neutral content plus provider/model fields. -This state is model-visible replay input and therefore follows the existing [reconstructable-request rule](2026-07-05-reconstructable-requests.md): it is present in both the terminal `finish` chunk and the assembled `assistant/message` provenance that drives derivation. Resume and fork preserve it verbatim. Compaction that shadows the assistant message also removes its replay state from the active surface; the summary is ordinary provider-neutral content. +This state is model-visible replay input and therefore follows the existing [reconstructable-request rule](2026-07-05-reconstructable-requests.md): it is present in both the terminal `finish` chunk and the assembled `assistant/message` model source that drives derivation. Resume and fork preserve it verbatim. Compaction that shadows the assistant message also removes its replay state from the active surface; the summary is ordinary provider-neutral content. ### Propagate the target through every request producer @@ -54,7 +54,7 @@ Compaction configuration gains `summarizationProvider` beside `summarizationMode The JSON-RPC runtime receives provider and model explicitly. Its convenience fallback mounts `dsh-llm-deepseek` only for provider `deepseek` when that provider has no registered owner; other missing providers fail without guessing an adapter. -The on-disk session format remains the pre-release pinned version `0`, with no compatibility promise. Seed/load validation rejects request headers lacking provider and assistant messages lacking required provenance instead of accepting an old shape that can no longer reconstruct the request. +The on-disk session format remains the pre-release pinned version `0`, with no compatibility promise. Seed/load validation rejects request headers and assistant messages that omit required provider/model fields instead of accepting an old shape that can no longer reconstruct the request. ## Alternatives considered @@ -78,7 +78,7 @@ The on-disk session format remains the pre-release pinned version `0`, with no c - pi-ai credentials, transport knobs, SDK timeouts, and the five-minute-default `streamIdleTimeoutMs` watchdog are scoped per provider profile. Hidden provider retries are disabled; bounded retries belong to the separately composed agent recovery policy. - `dsh-llm-pi-ai` rejects stop sequences because pi-ai's common stream API cannot express them; the native DeepSeek adapter retains its stop support. - Replay state is portable only within the adapter instance that owns both the historical and target providers. Cross-provider and cross-model restoration is an adapter responsibility, and another adapter receives provider-neutral history without the opaque state. -- Current pre-release session JSONL requires provider/model request headers and assistant provenance. Older shapes remain version `0` but are rejected rather than migrated. +- Current pre-release session JSONL requires provider/model on request headers and assistant messages. Older shapes remain version `0` but are rejected rather than migrated. ## Testing diff --git a/.agents/notes/implemented/architecture/2026-07-14-provider-routed-llm-adapters.zh.md b/.agents/notes/implemented/architecture/2026-07-14-provider-routed-llm-adapters.zh.md index eff33496e1..09d9032da5 100644 --- a/.agents/notes/implemented/architecture/2026-07-14-provider-routed-llm-adapters.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-14-provider-routed-llm-adapters.zh.md @@ -10,7 +10,7 @@ Status: implemented 这种混淆使提供方网关无法提供开放的模型目录。例如，OpenRouter 是一个包含大量模型 ID 的提供方，私有 OpenAI 兼容端点也可能在不修改 Harness 插件树的情况下增加模型。目前，每个新选择的模型都必须在插件启动期间完成注册。同一个模型 ID 还可能存在于多个提供方中，因此仅按模型注册无法表达调用方预期使用的提供方。 -`dsh-llm-pi-ai` 没有暴露 pi-ai 的提供方抽象。它以内联方式构造 DeepSeek `openai-completions` 模型，应用 DeepSeek 专用的 payload 补丁，并将每条回放的助手消息标记为 DeepSeek。pi-ai 自身提供提供方/模型目录，能够选择 `openai-responses`、`anthropic-messages`、`google-generative-ai` 等 API，并保留提供方专用的响应 ID，以及后续轮次所需的推理和工具签名。Harness 转换丢弃了这些来源信息，因此仅将内联模型替换为目录查询，会导致同模型回放与跨提供方移交不完整。 +`dsh-llm-pi-ai` 没有暴露 pi-ai 的提供方抽象。它以内联方式构造 DeepSeek `openai-completions` 模型，应用 DeepSeek 专用的 payload 补丁，并将每条回放的助手消息标记为 DeepSeek。pi-ai 自身提供提供方/模型目录，能够选择 `openai-responses`、`anthropic-messages`、`google-generative-ai` 等 API，并保留提供方专用的响应 ID，以及后续轮次所需的推理和工具签名。Harness 转换丢弃了提供方／模型路由和提供方响应字段，因此仅将内联模型替换为目录查询，会导致同模型回放与跨提供方移交不完整。 适配器配置同样假定只存在一个 DeepSeek API 密钥和端点。通用后端需要为各提供方分别配置凭据和端点覆盖，同时继续由 pi-ai 处理 AWS、Google ADC、OAuth 等环境认证机制。 @@ -28,7 +28,7 @@ Status: implemented ### 显式 pi-ai 提供方配置 -`dsh-llm-pi-ai` 接受一个非空的提供方配置列表。列表内的提供方名称必须唯一，并且存在于 pi-ai 的 `getProviders()` 结果中。每项配置包含提供方名称，以及可选的 `apiKey`、`baseURL`、headers、推理级别和预算、缓存保留设置、传输方式、SDK 超时、Harness 流空闲超时，以及由提供方拥有的 `retryPolicy`。适配器强制将 pi-ai 的 `maxRetries` 设为零，使一次 `stream()` 调用只发起一次可见的提供方请求；`dsh-llm-retry` 则在 agent 失败步骤 seam 上执行解析后的策略。凭据不设全局值：显式密钥仅对所属配置生效；未提供密钥时，pi-ai 使用标准环境变量、OAuth token、AWS 凭据链、Google ADC 或其他提供方原生环境认证。显式空密钥属于无效配置，不会回退到环境认证。 +`dsh-llm-pi-ai` 接受一个非空的提供方配置列表。列表内的提供方名称必须唯一，并且存在于 pi-ai 的 `getProviders()` 结果中。每项配置包含提供方名称，以及可选的 `apiKey`、`baseURL`、headers、推理级别和预算、缓存保留设置、传输方式、SDK 超时、Harness 流空闲超时，以及由提供方拥有的 `retryPolicy`。适配器强制将 pi-ai 的 `maxRetries` 设为零，使一次 `stream()` 调用只发起一次可见的提供方请求；`dsh-llm-retry` 则在 agent 失败步骤扩展点上执行解析后的策略。凭据不设全局值：显式密钥仅对所属配置生效；未提供密钥时，pi-ai 使用标准环境变量、OAuth token、AWS 凭据链、Google ADC 或其他提供方原生环境认证。显式空密钥属于无效配置，不会回退到环境认证。 插件通过一次全有或全无调用，将所有已配置的提供方名称注册到同一个 `PiAiAdapter`。请求按 provider 选择对应配置，并在 `getModels(provider)` 中查找模型以取得目录描述符。未知提供方会在插件加载时失败；未知模型会在网络 I/O 前以 `UNKNOWN_MODEL` 失败。适配器不会修改目录对象。当配置提供 `baseURL` 时，适配器复制选中的描述符，仅覆盖 `baseUrl`，使私有端点保留 pi-ai 的 API、能力、兼容标志、上下文限制与推理映射。私有端点必须实现所选提供方的协议，模型 ID 也仍须存在于已安装的 pi-ai 目录中。 @@ -36,15 +36,15 @@ Status: implemented pi-ai 的通用流选项不支持停止序列。若 Harness `stop` 选项已定义，`dsh-llm-pi-ai` 会以 `UNSUPPORTED_OPTION` 拒绝请求，不会静默忽略，也不会增加第二套提供方专用 payload 实现。`dsh-llm-deepseek` 继续通过原生请求序列化器支持 `stop`。 -### 持久化助手来源信息与回放状态 +### 已记录的助手路由与回放状态 -助手消息携带提供方无关的来源信息，其中包含请求的 `provider` 和 `model`，以及可选的 JSON 可序列化适配器回放状态。成功的 `assistant/message` 会话事件记录这些来源信息，`deriveMessages()` 返回助手消息时也会包含这些信息。用户、system、context 与工具结果消息不携带助手来源信息。provider/model 字段是 agent loop 的权威数据；适配器仅拥有其不透明回放状态 payload。 +助手消息携带请求的 `provider` 和 `model`，以及可选的 JSON 可序列化适配器回放状态。成功的 `assistant/message` 会话事件记录这些字段，`deriveMessages()` 返回助手消息时也会包含它们。用户、system、context 与工具结果消息不携带助手路由字段。provider/model 字段是 agent loop 的权威数据；适配器仅拥有其不透明回放状态 payload。 -成功的终止 `finish` 分片可以携带回放状态，`BlockAssembler` 会将其与 token 用量和结束原因一起保留。只有当 `agent/step-result` 处理后的内容与提供方组装输出在结构上相等时，agent loop 才会把回放状态附加到助手来源信息。监听器重写内容后，provider/model 来源信息仍会保留，但已经陈旧的回放状态会被移除。错误或中止响应不会生成正常助手消息，因此不会进入后续模型历史。 +成功的终止 `finish` 分片可以携带回放状态，`BlockAssembler` 会将其与 token 用量和结束原因一起保留。agent loop 会把该状态附加到已组装助手消息的模型来源中，但不公开响应改写钩子。错误或中止响应不会生成正常助手消息，因此不会进入后续模型历史。 -pi-ai 回放状态是其成功 `AssistantMessage` 的带版本最小投影，包含源 API/provider/model、响应 ID/model、停止原因，以及按索引对齐的文本、thinking 和工具调用签名。它不会重复 Harness 内容块中已有的文本或工具参数，也不包含诊断信息、时间戳、用量或错误。后续请求中，只有历史提供方和目标提供方当前归同一个适配器实例所有时，`LlmService` 才会把回放状态交给目标适配器。适配器在能够恢复历史响应时，将 Harness 记录的内容与回放状态组合，并负责所需的跨模型或跨提供方转换。适配器收到未知版本或块形状不匹配的回放状态时会显式失败；其他适配器只能收到提供方无关的内容与来源信息。 +pi-ai 回放状态是其成功 `AssistantMessage` 的带版本最小投影，包含源 API/provider/model、响应 ID/model、停止原因，以及按索引对齐的文本、thinking 和工具调用签名。它不会重复 Harness 内容块中已有的文本或工具参数，也不包含诊断信息、时间戳、用量或错误。后续请求中，只有历史提供方和目标提供方当前归同一个适配器实例所有时，`LlmService` 才会把回放状态交给目标适配器。适配器在能够恢复历史响应时，将 Harness 记录的内容与回放状态组合，并负责所需的跨模型或跨提供方转换。适配器收到未知版本或块形状不匹配的回放状态时会显式失败；其他适配器只能收到提供方无关的内容以及 provider/model 字段。 -该状态属于模型可见的回放输入，因此遵循现有的[请求可重建规则](2026-07-05-reconstructable-requests.md)：它同时存在于终止 `finish` 分片和驱动派生的已组装 `assistant/message` 来源信息中。恢复和 fork 会原样保留该状态。压缩（compaction）遮蔽助手消息时，也会从活动 surface 中移除其回放状态；摘要属于普通的提供方无关内容。 +该状态属于模型可见的回放输入，因此遵循现有的[请求可重建规则](2026-07-05-reconstructable-requests.md)：它同时存在于终止 `finish` 分片和驱动派生的已组装 `assistant/message` 模型来源中。恢复和 fork 会原样保留该状态。压缩（compaction）遮蔽助手消息时，也会从活动 surface 中移除其回放状态；摘要属于普通的提供方无关内容。 ### 在所有请求生产方中传播目标 @@ -54,7 +54,7 @@ pi-ai 回放状态是其成功 `AssistantMessage` 的带版本最小投影，包 JSON-RPC 运行时显式接收 provider 与 model。仅当 `deepseek` 提供方没有注册所有者时，其便利回退才会挂载 `dsh-llm-deepseek`；其他缺失的提供方会直接失败，不会猜测适配器。 -磁盘会话格式仍使用预发布阶段固定的版本 `0`，且不承诺兼容性。seed/load 验证会拒绝缺少 provider 的请求头，以及缺少必需来源信息的助手消息，不会接受已无法重建请求的旧格式。 +磁盘会话格式仍使用预发布阶段固定的版本 `0`，且不承诺兼容性。seed/load 验证会拒绝省略必需 provider/model 字段的请求头和助手消息，不会接受已无法重建请求的旧格式。 ## 考虑过的替代方案 @@ -78,7 +78,7 @@ JSON-RPC 运行时显式接收 provider 与 model。仅当 `deepseek` 提供方 - pi-ai 凭据、传输选项、SDK 超时，以及默认五分钟的 `streamIdleTimeoutMs` 空闲超时机制均按提供方配置隔离。系统禁用隐藏的提供方重试；有界重试由单独组合的 agent 恢复策略负责。 - pi-ai 的通用流 API 无法表达停止序列，因此 `dsh-llm-pi-ai` 会拒绝停止序列；原生 DeepSeek 适配器仍支持停止序列。 - 仅当历史提供方与目标提供方归同一个适配器实例所有时，回放状态才可移植。适配器负责跨提供方和跨模型恢复；其他适配器只接收不含不透明状态的提供方无关历史。 -- 当前预发布会话 JSONL 要求请求头包含 provider/model，助手消息包含来源信息。旧格式仍使用版本 `0`，但会被拒绝，不执行迁移。 +- 当前预发布会话 JSONL 要求请求头和助手消息都包含 provider/model。旧格式仍使用版本 `0`，但会被拒绝，不执行迁移。 ## 测试 diff --git a/.agents/notes/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.i18n.yaml index faade67459..02d531f642 100644 --- a/.agents/notes/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.md -2026-07-15-llm-model-catalog-and-acp-selection.md: 9edc723b0dfafeaf395eb9325373835138ddbc41 -2026-07-15-llm-model-catalog-and-acp-selection.zh.md: aefd0af3e4de8fac4f5819e0ee279d3343aec6be +2026-07-15-llm-model-catalog-and-acp-selection.md: 77f8e379e2b07ecf4e67fa7197752543cfedd6dd +2026-07-15-llm-model-catalog-and-acp-selection.zh.md: ce4a04a66e345834bc2b16b743be89dc7a0b9424 diff --git a/.agents/notes/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.md b/.agents/notes/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.md index 9edc723b0d..77f8e379e2 100644 --- a/.agents/notes/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.md +++ b/.agents/notes/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.md @@ -8,7 +8,7 @@ English | [中文](2026-07-15-llm-model-catalog-and-acp-selection.zh.md) ## Problem -Provider-routed adapters let every request choose `provider + model`, but `LlmService` exposed only routing and streaming. A UI could not discover which providers were registered or which models an adapter was prepared to recommend. ACP clients therefore received no `model` session config option, so Zed, JetBrains, and VS Code integrations had no model list even though the request seam already supported runtime switching. +Provider-routed adapters let every request choose `provider + model`, but `LlmService` exposed only routing and streaming. A UI could not discover which providers were registered or which models an adapter was prepared to recommend. ACP clients therefore received no `model` session config option, so Zed, JetBrains, and VS Code integrations had no model list even though the LLM service already supported runtime switching. Model discovery cannot become request validation. The hand-written DeepSeek adapter deliberately forwards arbitrary model ids to a public or private endpoint, while pi-ai has a finite installed catalog that is authoritative for its own request resolution. Treating one shared catalog as a whitelist would remove the private-endpoint behavior that provider routing was designed to preserve. @@ -34,9 +34,9 @@ The ACP automation transport is not a catalog consumer. Its deployment config su ### Prompt/request consistency and durability -`installAgentLlmTarget` (in `dsh-agent`) installs scoped `system-prompt/assemble` and `agent/request` listeners for a front-door-owned target. Prompt assembly snapshots the selected pair once per step, overwrites the assembled `provider` and `model` variables after downstream prompt listeners, and the request listener applies that same snapshot after downstream request listeners. A selection during asynchronous assembly therefore starts on the next step rather than splitting prompt text from routing. Other call-config fields remain untouched. +`installModelSelection` (in `dsh-agent`) installs scoped `system-prompt/assemble` and `agent/request` listeners for a front-door-owned selection. Prompt assembly snapshots the selected pair once per step, overwrites the assembled `provider` and `model` variables after downstream prompt listeners, and the request listener applies that same snapshot after downstream request listeners. A selection during asynchronous assembly therefore starts on the next step rather than splitting prompt text from routing. Other call-config fields remain untouched. -The request header remains the durable source of truth. When a selected target is actually used, the existing full `request/header` snapshot records it, and a front door initializes its selection from the folded last request header before falling back to creation options. A selection that is never used by a request is intentionally in-memory only because it never became model-visible state. +The request header remains the durable source of truth. When a selection is actually used, the existing full `request/header` snapshot records it, and a front door initializes its selection from the folded last request header before falling back to creation options. A selection that is never used by a request is intentionally in-memory only because it never became model-visible state. ## Alternatives considered @@ -50,7 +50,7 @@ The request header remains the durable source of truth. When a selected target i ## Consequences -- Any adapter can expose a dynamic model list without leaking provider-library types into the core seam. +- Any adapter can expose a dynamic model list without leaking provider-library types into the LLM Service Definition. - Catalog consumers must treat absence as “not advertised,” never “invalid request.” - pi-ai adapters expose their installed provider catalogs; hand-written DeepSeek deployments list known choices explicitly and retain arbitrary model support. - Human-facing catalog consumers own their selection interaction. ACP uses its fixed deployment target and does not widen the protocol with model discovery. diff --git a/.agents/notes/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.zh.md b/.agents/notes/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.zh.md index aefd0af3e4..ce4a04a66e 100644 --- a/.agents/notes/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.zh.md @@ -8,7 +8,7 @@ Status: implemented ## 问题 -基于提供方路由的适配器允许每次请求选择 `provider + model`，但 `LlmService` 只暴露路由和流式调用。UI 无法发现已注册的提供方，也无法知道适配器愿意推荐哪些模型。因此，ACP 客户端收不到 `model` 会话配置项；即使请求 seam 已经支持运行时切换，Zed、JetBrains 和 VS Code 集成仍没有模型列表。 +基于提供方路由的适配器允许每次请求选择 `provider + model`，但 `LlmService` 只暴露路由和流式调用。UI 无法发现已注册的提供方，也无法知道适配器愿意推荐哪些模型。因此，ACP 客户端收不到 `model` 会话配置项；即使 LLM 服务已经支持运行时切换，Zed、JetBrains 和 VS Code 集成仍没有模型列表。 模型发现不能变成请求校验。手写 DeepSeek 适配器会把任意模型 ID 原样转发给公开或私有端点，而 pi-ai 的有限安装目录则是其自身请求解析的权威依据。将共享目录视为白名单，会破坏提供方路由需要保留的私有端点能力。 @@ -34,9 +34,9 @@ ACP 自动化传输层不是目录消费方。它通过部署配置为新创建 ### 提示词／请求一致性与持久化 -`installAgentLlmTarget`（位于 `dsh-agent`）为前门拥有的目标安装 agent 作用域的 `system-prompt/assemble` 与 `agent/request` 监听器。提示词组装在每个步骤对所选组合做一次快照，在下游提示词监听器之后覆写组装出的 `provider` 与 `model` 变量；请求监听器在下游请求监听器之后应用同一快照。因此，发生在异步组装期间的选择会从下一个步骤生效，而不会让提示词文本与路由分裂。其他调用配置字段保持不变。 +`installModelSelection`（位于 `dsh-agent`）为前门拥有的选择安装 agent 作用域的 `system-prompt/assemble` 与 `agent/request` 监听器。提示词组装在每个步骤对所选组合做一次快照，在下游提示词监听器之后覆写组装出的 `provider` 与 `model` 变量；请求监听器在下游请求监听器之后应用同一快照。因此，发生在异步组装期间的选择会从下一个步骤生效，而不会让提示词文本与路由分裂。其他调用配置字段保持不变。 -请求头仍是持久化的真源。当所选目标真正被使用时，现有的完整 `request/header` 快照会记录它；前门先从折叠后的最后一个请求头初始化其选择，然后才回退到创建选项。从未被请求使用的选择有意只保留在内存中，因为它从未成为模型可见状态。 +请求头仍是持久化的真源。当某个选择真正被使用时，现有的完整 `request/header` 快照会记录它；前门先从折叠后的最后一个请求头初始化其选择，然后才回退到创建选项。从未被请求使用的选择有意只保留在内存中，因为它从未成为模型可见状态。 ## 考虑过的替代方案 @@ -50,7 +50,7 @@ ACP 自动化传输层不是目录消费方。它通过部署配置为新创建 ## 结果 -- 任意适配器都能暴露动态模型列表，无需把提供方库类型泄漏到核心 seam。 +- 任意适配器都能暴露动态模型列表，无需把提供方库类型泄漏到 LLM Service Definition。 - 目录消费方必须把缺失理解为「未展示」，而不是「请求无效」。 - pi-ai 适配器会暴露其已安装的提供方目录；手写 DeepSeek 部署显式列出已知选项，同时保留对任意模型的支持。 - 面向人类的目录消费方拥有各自的选择交互。ACP 使用固定部署目标，不会为模型发现扩大协议范围。 diff --git a/.agents/notes/implemented/architecture/2026-07-15-lsp-capability-seam.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-15-lsp-capability-seam.i18n.yaml index ebf474f78b..91c9baf2a0 100644 --- a/.agents/notes/implemented/architecture/2026-07-15-lsp-capability-seam.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-15-lsp-capability-seam.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-15-lsp-capability-seam.md -2026-07-15-lsp-capability-seam.md: 63cec0a4e349ffc5be27a84e955b15e9168f898b -2026-07-15-lsp-capability-seam.zh.md: fa82e29e0252b612ae38357c363478f1cbad9ead +2026-07-15-lsp-capability-seam.md: a461432fe5f218ea6c3ff3e031b52f7ebffbd7a5 +2026-07-15-lsp-capability-seam.zh.md: bfbd8d04f71b154d2833c86f2a6dc84d7e13fff4 diff --git a/.agents/notes/implemented/architecture/2026-07-15-lsp-capability-seam.md b/.agents/notes/implemented/architecture/2026-07-15-lsp-capability-seam.md index 63cec0a4e3..a461432fe5 100644 --- a/.agents/notes/implemented/architecture/2026-07-15-lsp-capability-seam.md +++ b/.agents/notes/implemented/architecture/2026-07-15-lsp-capability-seam.md @@ -32,7 +32,7 @@ The prompt positions LSP as a precision aid: `Use search/read for ordinary navig The seam exposes one `query(request, signal?)` operation because no fields need implementation defaulting: `workspaceRoot` is required, `languageId` comes from the registration, and consumers own timeouts and result limits. `query()` selects and derives without hidden `??` fallbacks, leaving no executable spec to resolve. `dsh-tool-lsp` validates model arguments and passes only `exec.signal` as a bare `AbortSignal`, matching web and keeping `dsh-lsp` independent of `dsh-tools`. Removal before selection fails as unavailable; later disposal follows the selected provider's cancellation lifecycle without rerouting. -The intended contract shape is: +The contract shape: ```ts import type { Branded } from '@deepseek-ai/dsh-brand' @@ -79,7 +79,7 @@ interface LspService { Mapping keys normalize to lowercase, leading-dot extensions selected from `filePath`'s final extension; language ids only synchronize documents. Seam positions and ranges are zero-based UTF-16. `findReferences` always includes declarations: providers enforce this internally, the local mapping sets `context.includeDeclaration: true`, and callers get no flag. Closed result unions normalize navigation to locations and hover to content or `null`; navigation results carry the provider's canonical workspace URI so consumers relativize file URIs in the execution world's namespace. The seam exposes no protocol types, process or document controls, or generic request escape hatch. -`dsh-lsp-local` owns server configuration, JSON-RPC, process and transient-document state, and protocol translation. It reads through `ctx.fs` and launches through `ctx.subprocess`, depending on their interface packages rather than concrete providers; the [portable execution-world decision](2026-07-28-portable-execution-world-consumers.md) owns that pairing. The server-table key is its provider id. The plugin resolves every server-local setting before registration, rolls back earlier registrations if a later mapping is invalid or conflicts, and retains an independent process pool per provider. `dsh-tool-lsp` runtime-injects only `tools`, `lsp`, and `systemPrompt`, obtains the workspace from `exec.agent?.session.header.cwd` through a package-local `sessionCwd(exec)` helper matching the filesystem tools' lookup, and imports no provider. +`dsh-lsp-local` owns server configuration, JSON-RPC, process and transient-document state, and protocol translation. It reads through `ctx.fs` and launches through `ctx.subprocess`, depending on their Service Definition packages rather than concrete providers; the [portable execution-world decision](2026-07-28-portable-execution-world-consumers.md) owns that pairing. The server-table key is its provider id. The plugin resolves every server-local setting before registration, rolls back earlier registrations if a later mapping is invalid or conflicts, and retains an independent process pool per provider. `dsh-tool-lsp` runtime-injects only `tools`, `lsp`, and `systemPrompt`, obtains the workspace from `exec.agent?.session.header.cwd` through a package-local `sessionCwd(exec)` helper matching the filesystem tools' lookup, and imports no provider. ## Model-facing contract @@ -147,7 +147,7 @@ The provider trusts its configured server. Its filesystem visibility and process ## Alternatives considered -**Copy Claude Code's unified schema.** Its cursor operations validate the core use case, but symbols and call hierarchy need different arguments. Copying all nine operations would freeze speculative surface, so the proposal aligns only on the four semantic queries. +**Copy Claude Code's unified schema.** Its cursor operations validate the core use case, but symbols and call hierarchy need different arguments. Copying all nine operations would freeze speculative surface, so the seam aligns only on the four semantic queries. **Let providers register tools.** Loaded servers would then control model schema and prompts, preventing one stable contract across local and remote providers. @@ -155,7 +155,7 @@ The provider trusts its configured server. Its filesystem visibility and process **Expose `resolve(request)` / `query(spec)`.** With no defaulted fields, resolution would only expose provider selection, and a public spec could outlive provider disposal or replacement. One operation keeps selection and invocation atomic to the registration lifetime. -**Wrap the signal in a per-seam execution-context object.** Web passes a bare `AbortSignal`; wrapping this single field would add unexplained asymmetry. `query()` gains a context object only when another field requires it. +**Wrap the signal in an LSP execution-context object.** Web passes a bare `AbortSignal`; wrapping this single field would add unexplained asymmetry. `query()` gains a context object only when another field requires it. **Read through the model-facing `read` tool.** Rejected because tool output is windowed, numbered, transcript-visible, and observed. The provider consumes streamed full text directly through the same `ctx.fs` execution world used by its subprocess. @@ -178,7 +178,7 @@ The provider trusts its configured server. Its filesystem visibility and process - Registry tests pin atomic reservation/release, order-independent selection, and structured unavailable, disposed, conflict, and unsupported-operation errors. - Fake-stdio tests pin exact initialization capabilities, four protocol mappings, `Location`/`LocationLink` and hover normalization, and `findReferences` mapping to `references.includeDeclaration`. - Synchronization tests pin UTF-16 negotiation and conversion, supported and rejected `textDocumentSync` forms, blocked and failed open writes, balanced transient open/close, close-write failure, and malformed-response rejection. -- Timeout tests pin one `TOOL_TIMEOUT` budget, unclassified upstream cancellation, no hidden seam deadline, and bounded awaited teardown. +- Timeout tests pin one `TOOL_TIMEOUT` budget, unclassified upstream cancellation, no hidden LSP deadline, and bounded awaited teardown. - Lifecycle tests pin startup single-flight, complete-lifecycle serialization with fresh queued source reads, cross-workspace parallelism, abortable queues, crash replacement without replay, failed-stdin teardown, and quiescent disposal. - Filesystem-host tests pin session-cwd requirements, provider-owned containment and URI rendering, bounded document reads, unformatted source, and no `fs/observed` event. - A keyless pinned TypeScript real-server e2e exercises all four operations; runnable configuration uses the same explicit provider mapping. diff --git a/.agents/notes/implemented/architecture/2026-07-15-lsp-capability-seam.zh.md b/.agents/notes/implemented/architecture/2026-07-15-lsp-capability-seam.zh.md index fa82e29e02..bfbd8d04f7 100644 --- a/.agents/notes/implemented/architecture/2026-07-15-lsp-capability-seam.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-15-lsp-capability-seam.zh.md @@ -32,7 +32,7 @@ harness 已具备文本搜索与文件读取能力，但二者都无法识别程 服务边界只公开 `query(request, signal?)`，因为没有字段需要实现层填充默认值：`workspaceRoot` 是必填项，`languageId` 来自注册映射，超时与结果限制由消费方负责。`query()` 执行选择与推导时不使用隐藏的 `??` 后备逻辑，因此没有需要 resolve 的可执行 spec。`dsh-tool-lsp` 校验模型参数，并只把 `exec.signal` 作为裸 `AbortSignal` 传递，与 web 一致，并使 `dsh-lsp` 不依赖 `dsh-tools`。提供方在选择前被移除时按不可用失败；之后的释放遵循已选提供方的取消生命周期，不改路由。 -预期约定如下： +约定如下： ```ts import type { Branded } from '@deepseek-ai/dsh-brand' @@ -79,7 +79,7 @@ interface LspService { 映射键规范化为带前导点的小写扩展名，并按 `filePath` 的最后一个扩展名选择；语言 id 仅用于文档同步。服务边界中的位置和范围从零开始按 UTF-16 计数。`findReferences` 始终包含声明：提供方在内部执行该约束，本地映射设置 `context.includeDeclaration: true`，调用方不能配置。封闭结果联合将导航统一为位置，将 `hover` 统一为内容或 `null`；导航结果携带提供方的规范工作区 URI，使消费方在执行世界的命名空间内相对化文件 URI。服务边界不公开协议类型、进程或文档控制，也不提供通用请求逃生口。 -`dsh-lsp-local` 负责服务器配置、JSON-RPC、进程与临时文档状态和协议转换。它通过 `ctx.fs` 读取，通过 `ctx.subprocess` 启动，只依赖二者的接口包而非具体提供方；[可移植执行环境决策](2026-07-28-portable-execution-world-consumers.md)负责定义这种配对。服务器表的键是提供方 id。插件在注册前解析每个服务器的本地设置；如果后续映射无效或发生冲突，插件会撤销此前的注册，并为每个提供方保留独立进程池。`dsh-tool-lsp` 在运行时只注入 `tools`、`lsp` 和 `systemPrompt`，通过包内的 `sessionCwd(exec)` 辅助函数从 `exec.agent?.session.header.cwd` 取得工作区，其取值方式与文件系统工具一致，也不导入提供方。 +`dsh-lsp-local` 负责服务器配置、JSON-RPC、进程与临时文档状态和协议转换。它通过 `ctx.fs` 读取，通过 `ctx.subprocess` 启动，只依赖二者的 Service Definition 包而非具体提供方；[可移植执行环境决策](2026-07-28-portable-execution-world-consumers.md)负责定义这种配对。服务器表的键是提供方 id。插件在注册前解析每个服务器的本地设置；如果后续映射无效或发生冲突，插件会撤销此前的注册，并为每个提供方保留独立进程池。`dsh-tool-lsp` 在运行时只注入 `tools`、`lsp` 和 `systemPrompt`，通过包内的 `sessionCwd(exec)` 辅助函数从 `exec.agent?.session.header.cwd` 取得工作区，其取值方式与文件系统工具一致，也不导入提供方。 ## 面向模型的约定 @@ -147,7 +147,7 @@ interface LspToolInput { ## 备选方案 -**照搬 Claude Code 的统一 schema。** 它的光标操作验证了核心场景，但符号与调用层级需要不同参数。照搬九种操作会固化尚未验证的接口，因此本提案只对齐四种语义查询。 +**照搬 Claude Code 的统一 schema。** 它的光标操作验证了核心场景，但符号与调用层级需要不同参数。照搬九种操作会固化尚未验证的接口，因此该 seam 只对齐四种语义查询。 **允许提供方注册工具。** 已加载服务器会控制模型 schema 和提示词，无法在本地与远程提供方之间维持统一约定。 @@ -155,7 +155,7 @@ interface LspToolInput { **公开 `resolve(request)` / `query(spec)`。** 没有需要填充默认值的字段时，resolve 只会暴露提供方选择，而公开 spec 可能活过提供方释放或替换。单一操作让选择与调用共用注册生命周期。 -**将信号包装为每服务边界的执行上下文对象。** Web 传递裸 `AbortSignal`；仅包装这一个字段会造成无谓的不对称。只有另一个字段确有需要时，`query()` 才引入上下文对象。 +**将信号包装为 LSP 执行上下文对象。** Web 传递裸 `AbortSignal`；仅包装这一个字段会造成无谓的不对称。只有另一个字段确有需要时，`query()` 才引入上下文对象。 **通过面向模型的 `read` 工具读取。**拒绝，因为工具输出带窗口与行号，会进入 transcript 且已被观察。提供方直接通过子进程所用的同一 `ctx.fs` 执行环境消费流式传输的完整文本。 @@ -178,7 +178,7 @@ interface LspToolInput { - 注册表测试固定原子占用/释放、不受顺序影响的选择，以及结构化的不可用、已释放、冲突和不支持操作错误。 - 测试用 stdio server 固定精确的初始化能力、四种协议映射、`Location`/`LocationLink` 与 `hover` 归一化，以及 `findReferences` 到 `references.includeDeclaration` 的映射。 - 同步测试固定 UTF-16 协商与转换、受支持和被拒绝的 `textDocumentSync` 形式、打开写入阻塞与失败、配对的临时打开/关闭、关闭写入失败和错误响应拒绝。 -- 超时测试固定一个 `TOOL_TIMEOUT` 预算、不对上游取消错误分类、服务边界无隐藏截止时间，以及受限且等待完成的清理。 +- 超时测试固定一个 `TOOL_TIMEOUT` 预算、不对上游取消错误分类、LSP 无隐藏截止时间，以及受限且等待完成的清理。 - 生命周期测试固定启动 single-flight、完整生命周期串行化及排队查询读取最新源文件、跨工作区并行、可取消队列、崩溃后不重放的替换、stdin 失败后的进程拆除，以及释放后完全停稳。 - 文件系统宿主测试固定 session cwd 要求、提供方自有的 containment 与 URI 渲染、有界文档读取、无格式源文本和不发送 `fs/observed`。 - 无密钥且固定版本的 TypeScript 真实服务器 e2e 覆盖四种操作；可运行配置使用同一项显式提供方映射。 diff --git a/.agents/notes/implemented/architecture/2026-07-15-replay-token-meter-service.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-15-replay-token-meter-service.i18n.yaml index 80fe86f2bc..8579c7231a 100644 --- a/.agents/notes/implemented/architecture/2026-07-15-replay-token-meter-service.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-15-replay-token-meter-service.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-15-replay-token-meter-service.md -2026-07-15-replay-token-meter-service.md: c0f4b467ad0013dd4ac0a0301281b011ea8c261c -2026-07-15-replay-token-meter-service.zh.md: c1d81dc0e76ee687ced5c23d26197627551e1ced +2026-07-15-replay-token-meter-service.md: 4013cc92f67597a9b87edfc97d14c7f47f0523ac +2026-07-15-replay-token-meter-service.zh.md: 4bee27db2a7d021b25dfdf1feefa148cfb016100 diff --git a/.agents/notes/implemented/architecture/2026-07-15-replay-token-meter-service.md b/.agents/notes/implemented/architecture/2026-07-15-replay-token-meter-service.md index c0f4b467ad..4013cc92f6 100644 --- a/.agents/notes/implemented/architecture/2026-07-15-replay-token-meter-service.md +++ b/.agents/notes/implemented/architecture/2026-07-15-replay-token-meter-service.md @@ -8,7 +8,7 @@ English | [中文](2026-07-15-replay-token-meter-service.zh.md) Context pressure is useful outside compaction. A compaction backend, an overflow guard, or a future request-policy plugin can all need the same answer: how many tokens does the durable request consume? Keeping that fold inside `dsh-compact-basic` duplicates replay logic, makes measurement unavailable without compaction, and encourages callers to reuse stale accounting. -Provider usage is not a complete answer. It describes one successful call under one exact request envelope, while the current surface can grow, shrink, or be replaced afterward. Sessions also switch providers and models, old logs can lack chunk provenance, and usage fields separate input, cache-read, cache-write, output, and reasoning counts. A useful service therefore combines the latest exact anchor with conservative heuristic repricing and exposes the log revision consumed by each result. +Provider usage is not a complete answer. It describes one successful call under one exact request envelope, while the current surface can grow, shrink, or be replaced afterward. Sessions also switch providers and models, old logs can omit the chunk seqs behind an assistant message, and usage fields separate input, cache-read, cache-write, output, and reasoning counts. A useful service therefore combines the latest exact anchor with conservative heuristic repricing and exposes the log revision consumed by each result. ## Decision @@ -20,17 +20,17 @@ The service has no configuration. Estimation uses a fixed four-characters-per-to ### Per-session replay folds -Each session owns one isolated incremental fold. Active folds advance from `session/event`; every read catches up through the durable tail, so listener ordering, seeded sessions, and service reload do not change the answer. The fold tracks canonical full request-header snapshots, step boundaries, surface appends and replacements, assistant usage, and assistant-chunk provenance. A malformed next event fails transactionally and remains unread rather than partially mutating state. +Each session owns one isolated incremental fold. Active folds advance from `session/event`; every read catches up through the durable tail, so listener ordering, seeded sessions, and service reload do not change the answer. The fold tracks canonical full request-header snapshots, step boundaries, surface appends and replacements, assistant usage, and the chunk seqs cited by each assistant message. A malformed next event fails transactionally and remains unread rather than partially mutating state. `measure(session, requestHeader?)` synchronizes the fold once and returns scalar pressure together with positional per-node prices. `totalTokens` remains request-and-response pressure; `surfaceTokens` is the surface-only heuristic total and equals the sum of `nodes[].tokens`. A `requestHeader` override changes pressure pricing only, while the surface fields always describe the current session. `estimateMessage(message)` applies the fixed heuristic without session state. Each result is one detached, deeply immutable snapshot carrying one `logRevision`. Every measurement clones the current nodes and is therefore O(surface). Provider usage is reused only when the measured canonical request envelope equals the latest successful-call anchor. Any provider, model, system, prefix, tool, or call-config change causes complete heuristic repricing. Surface changes remain a signed delta from a matching anchor, including negative values after a shrinking replacement. A later successful request replaces the earlier anchor, including across provider or model switches. -Usage sums the disjoint input, cache-read, cache-write, and output buckets. Reasoning is not added a second time. Every successful model call records an `assistant/message`, including content-less and max-token calls, with its exact earlier chunk seqs. An explicit empty provenance list means a known empty provider stream; absent legacy provenance conservatively treats the durable assistant output as provider output. +Usage sums the disjoint input, cache-read, cache-write, and output buckets. Reasoning is not added a second time. Every successful model call records an `assistant/message`, including content-less and max-token calls, with its exact earlier chunk seqs. An explicit empty `sourceEventSeqs` list means a known empty provider stream; an absent legacy list conservatively treats the durable assistant output as provider output. ### Compact-basic consumes, but does not own, measurement -`dsh-compact-basic` requires `ctx.tokenMeter`; `CompactService` gains no token methods or types. Configuration, the region transaction, and summarization stay in separate modules; the service registers automatic listeners itself, while `summarize()` remains its sole subclass hook. The singleton meter consistently prices pressure, retention, shadowed content, provenance, and non-shrinking-summary rejection. +`dsh-compact-basic` requires `ctx.tokenMeter`; `CompactService` gains no token methods or types. Configuration, the region transaction, and summarization stay in separate modules; the service registers automatic listeners itself, while `summarize()` remains its sole subclass hook. The singleton meter consistently prices pressure, retention, shadowed content, cited source events, and non-shrinking-summary rejection. Automatic compaction uses one unified measurement for each threshold-and-retention decision. The region transaction measures after appending its durable `compact/start` lock and again after asynchronous summarization, then compares the detached surface-node vectors. An intervening surface mutation prevents replacement; `logRevision` may advance for unrelated log-only facts without invalidating an unchanged selected span. diff --git a/.agents/notes/implemented/architecture/2026-07-15-replay-token-meter-service.zh.md b/.agents/notes/implemented/architecture/2026-07-15-replay-token-meter-service.zh.md index c1d81dc0e7..4bee27db2a 100644 --- a/.agents/notes/implemented/architecture/2026-07-15-replay-token-meter-service.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-15-replay-token-meter-service.zh.md @@ -8,7 +8,7 @@ Status: implemented 上下文压力并不只对压缩（compaction）有用。压缩后端、溢出保护或未来的请求策略插件都可能需要回答同一个问题：持久请求消耗了多少 token？如果把该折叠逻辑留在 `dsh-compact-basic` 内部，就会重复实现回放逻辑，使未加载压缩的调用方无法使用计量，并诱使调用方复用陈旧的核算结果。 -提供方 usage 也不是完整答案。它只描述某个精确请求信封下的一次成功调用，而当前表层之后还可能增长、缩小或被替换。会话也可能切换提供方与模型，旧日志可能缺少分片来源，usage 字段还会分别报告输入、缓存读取、缓存写入、输出与推理计数。因此，可用的服务必须把最新精确锚点与保守的启发式重新定价结合起来，并公开每个结果已经消费的日志修订号。 +提供方 usage 也不是完整答案。它只描述某个精确请求信封下的一次成功调用，而当前表层之后还可能增长、缩小或被替换。会话也可能切换提供方与模型，旧日志可能缺少构成 assistant 消息的分片 seq，usage 字段还会分别报告输入、缓存读取、缓存写入、输出与推理计数。因此，可用的服务必须把最新精确锚点与保守的启发式重新定价结合起来，并公开每个结果已经消费的日志修订号。 ## 决策 @@ -20,17 +20,17 @@ Status: implemented ### 逐会话回放折叠 -每个会话都有一个隔离的增量折叠。活跃折叠通过 `session/event` 前进；每次读取都会追到持久日志尾部，因此监听器顺序、种子会话与服务重载不会改变答案。折叠跟踪规范的完整请求头快照、步骤边界、表层追加与替换、assistant usage，以及 assistant 分片来源。下一个畸形事件会以事务方式失败并保持未读，不会让状态只修改一半。 +每个会话都有一个隔离的增量折叠。活跃折叠通过 `session/event` 前进；每次读取都会追到持久日志尾部，因此监听器顺序、种子会话与服务重载不会改变答案。折叠跟踪规范的完整请求头快照、步骤边界、表层追加与替换、assistant usage，以及每条 assistant 消息引用的分片 seq。下一个畸形事件会以事务方式失败并保持未读，不会让状态只修改一半。 `measure(session, requestHeader?)` 只同步一次折叠，并在返回标量压力的同时给出逐位置节点价格。`totalTokens` 仍表示请求与响应压力；`surfaceTokens` 是仅针对表层的启发式总量，并等于 `nodes[].tokens` 之和。`requestHeader` 覆盖只改变压力定价，表层字段始终描述当前会话。`estimateMessage(message)` 不依赖会话状态，直接应用固定启发式规则。每个结果都是一个分离且深度不可变的快照，只携带一个 `logRevision`。每次计量都会复制当前节点，因此成本为 O(surface)。 只有当待计量的规范请求信封等于最近一次成功调用的锚点时，服务才复用提供方 usage。提供方、模型、系统提示词、前缀、工具或调用配置任一变化都会触发完整的启发式重新定价。表层变化相对匹配锚点保留有符号增量，包括缩小替换后的负值。后续成功请求会替换先前锚点，提供方或模型切换时也一样。 -Usage 会对互不重叠的输入、缓存读取、缓存写入与输出 bucket 求和，不会再次加入推理计数。每次成功模型调用都会记录 `assistant/message`，包括无内容调用与达到 token 上限的调用，并带上精确的更早分片 seq。显式空来源列表表示已知为空的提供方流；旧日志中缺失的来源则保守地把持久 assistant 输出视为提供方输出。 +Usage 会对互不重叠的输入、缓存读取、缓存写入与输出 bucket 求和，不会再次加入推理计数。每次成功模型调用都会记录 `assistant/message`，包括无内容调用与达到 token 上限的调用，并带上精确的更早分片 seq。显式的空 `sourceEventSeqs` 列表表示已知为空的提供方流；旧日志中缺失的列表则保守地把持久 assistant 输出视为提供方输出。 ### compact-basic 消费计量，但不拥有计量 -`dsh-compact-basic` 要求 `ctx.tokenMeter`；`CompactService` 不增加 token 方法或类型。配置、区域事务与摘要分别保留在独立模块中，服务自身注册自动监听器，而 `summarize()` 仍是唯一的子类钩子。单例计量器一致用于压力、保留、被遮蔽内容、来源以及非缩小摘要拒绝的定价。 +`dsh-compact-basic` 要求 `ctx.tokenMeter`；`CompactService` 不增加 token 方法或类型。配置、区域事务与摘要分别保留在独立模块中，服务自身注册自动监听器，而 `summarize()` 仍是唯一的子类钩子。单例计量器一致用于压力、保留、被遮蔽内容、引用的源事件以及非缩小摘要拒绝的定价。 自动压缩的每次阈值与保留联合决策只使用一次统一计量。区域事务会在追加持久 `compact/start` 锁后执行计量，在异步摘要完成后再次计量，随后比较分离的表层节点向量。期间发生的表层变更会阻止替换；`logRevision` 可以因无关的纯日志事实而推进，而不会使未变的选定范围失效。 diff --git a/.agents/notes/implemented/architecture/2026-07-16-explicit-turn-cancellation.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-16-explicit-turn-cancellation.i18n.yaml index f683189f93..19f77344e1 100644 --- a/.agents/notes/implemented/architecture/2026-07-16-explicit-turn-cancellation.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-16-explicit-turn-cancellation.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-16-explicit-turn-cancellation.md -2026-07-16-explicit-turn-cancellation.md: 2b7cb8cc77184edf1331764d28aefe748c1614a1 -2026-07-16-explicit-turn-cancellation.zh.md: 0b9a06c0ae340a41eab9d6bff6126996bfc63bcf +2026-07-16-explicit-turn-cancellation.md: 5d7b5856ceebd3dc49564c1800004188da162fd8 +2026-07-16-explicit-turn-cancellation.zh.md: ba20b80f3c280087d71688ef4596fb075fa5782b diff --git a/.agents/notes/implemented/architecture/2026-07-16-explicit-turn-cancellation.md b/.agents/notes/implemented/architecture/2026-07-16-explicit-turn-cancellation.md index 2b7cb8cc77..5d7b5856ce 100644 --- a/.agents/notes/implemented/architecture/2026-07-16-explicit-turn-cancellation.md +++ b/.agents/notes/implemented/architecture/2026-07-16-explicit-turn-cancellation.md @@ -12,7 +12,7 @@ The [initiating Agent scope decision](2026-07-15-agent-initiator-scope.md) inten ## Decision -Agent owns the runtime-only `AgentCancelCause` union `{ kind: 'user' } | { kind: 'parent' }`; `agent.cancel()` defaults to `user`. TypeScript enforces that vocabulary at this typed same-process seam, with no runtime validator, fallback, or special compatibility contract for untyped callers. An active `TurnCancellation` copies the typed discriminant into a fresh frozen signal reason; idle cancellation has no holder to mutate and does not arm later work. +Agent owns the runtime-only `AgentCancelCause` union `{ kind: 'user' } | { kind: 'parent' }`; `agent.cancel()` defaults to `user`. TypeScript enforces that vocabulary at this typed same-process boundary, with no runtime validator, fallback, or special compatibility contract for untyped callers. An active `TurnCancellation` copies the typed discriminant into a fresh frozen signal reason; idle cancellation has no holder to mutate and does not arm later work. An interrupted live turn ends with the coarse durable `{ kind: 'aborted' }` outcome. The terminal event records what happened to the turn, while the runtime signal identifies who requested cancellation; it does not duplicate `user` or `parent` into replay. Session seed/load rejects legacy aborted records with a reason or any other extra field, so replay cannot reintroduce caller-owned cancellation detail. The process-local `agent/cancel-requested` notification is not durable; a future audit requirement uses a separate durable control-request event so a request and its eventual outcome remain distinct. Durable events contain no stack, signal, error object, free-form cancellation text, or backend-private detail. @@ -20,7 +20,7 @@ AgentLoop privately owns one `TurnCancellation` per prospective turn. It install The driver keeps only a cause-less pre-run marker for queued work cancelled before a turn is claimed. An effective `cancel()` emits the observe-only `agent/cancel-requested` notification with its resolved typed cause before clearing queued and steering work or aborting the holder; notification failures cannot veto the stop, and an idle call emits nothing. Work synchronously queued by a notification observer is included in that clear, while work queued by a later signal abort observer is latched and runs when the aborted activity converges to idle — a `disposed` cancel leaves it parked ([cancel-convergence wake latch](../bug-fix/2026-08-07-cancel-convergence-wake-latch.md)). If a `running` listener synchronously cancels old work and sends a replacement, the driver discards the aborted holder and creates a fresh one for the replacement. Repeated cancellation is first-wins for the active holder, while later calls may still clear newly queued pending work. -The explicit event signatures pass a single payload object: agent-scoped events carry `agent` and `signal` in the payload with `next` last, and the remaining seams keep `signal` immediately before a waterfall's final `next`. `PreStepContext` and `RequestFailureContext` are retired, with their fields folded into the `agent/pre-step` and `agent/request-error` payloads ([payload-object events](2026-08-06-agent-event-payload-objects.md)). Pre-step entry, request configuration, request-error recovery, model generation, tool execution, approval, turn stopping, and subagent or workflow requests all receive the current signal. Hook bridges must also supply `RunHookOptions.signal`, so a turn cancellation reaches the bash executor's process-group kill and join boundary. `SystemPrompt.assemble()` carries `signal?: AbortSignal` in `AssembleContext` because that object is an explicit request value that can also represent signal-less assembly outside a turn. Listeners may cooperate with the signal but must not retain it to control another turn. +The explicit event signatures pass a single payload object: agent-scoped events carry `agent` and `signal` in the payload with `next` last, and the remaining APIs keep `signal` immediately before a waterfall's final `next`. `PreStepContext` and `RequestFailureContext` are retired, with their fields folded into the `agent/pre-step` and `agent/request-error` payloads ([payload-object events](2026-08-06-agent-event-payload-objects.md)). Pre-step entry, request configuration, request-error recovery, model generation, tool execution, approval, turn stopping, and subagent or workflow requests all receive the current signal. Hook bridges must also supply `RunHookOptions.signal`, so a turn cancellation reaches the bash executor's process-group kill and join boundary. `SystemPrompt.assemble()` carries `signal?: AbortSignal` in `AssembleContext` because that object is an explicit request value that can also represent signal-less assembly outside a turn. Listeners may cooperate with the signal but must not retain it to control another turn. `ctx.agents` continues to carry only the initiating Agent. Ambient Agent presence does not imply liveness, a current turn, or cancellation authority. The cause reader is private to the loop and states the machine-private slot invariant (only `cancel()` aborts a turn controller, always with a canonical frozen cause) instead of re-validating the reason structurally; no public helper reads a cause off an arbitrary signal. Concurrent Agents isolate both their initiator identities and their turn signals; a child driver shadows the parent initiator while its parent request signal still travels through the subagent seam. @@ -46,10 +46,10 @@ Initiator-scope tests assert that every hook still observes the exact Agent and **Expose public turn or step context wrappers.** Existing seams already identify Agent, turn, and step. A wrapper would widen every API, duplicate ownership, and tempt callers to treat a captured object as durable authority. -**Abandon uncooperative work after a grace period.** Returning idle while same-process work still runs breaks teardown and resource-ownership guarantees. Hard termination requires a worker or process isolation boundary and is outside this control seam. +**Abandon uncooperative work after a grace period.** Returning idle while same-process work still runs breaks teardown and resource-ownership guarantees. Hard termination requires a worker or process isolation boundary and is outside this control boundary. ## Consequences -Cancellation has one runtime owner, one signal per live turn, and one typed runtime caller vocabulary. Session retains the coarse `aborted` outcome that its consumers actually use, rejects reason-bearing legacy forms, and stays isolated from runtime objects. Cooperative cancellation reaches every asynchronous turn seam, including work before the first step and after the last one, while terminal publication and persistence remain outside its authority. +Cancellation has one runtime owner, one signal per live turn, and one typed runtime caller vocabulary. Session retains the coarse `aborted` outcome that its consumers actually use, rejects reason-bearing legacy forms, and stays isolated from runtime objects. Cooperative cancellation reaches every asynchronous turn extension point, including work before the first step and after the last one, while terminal publication and persistence remain outside its authority. The explicit signal adds parameters to several public events and requires plugins to forward cancellation deliberately. This is intentional: authority is visible at the call boundary, lifetime matches the turn, and stale ambient descendants cannot acquire control. Uncooperative in-process work may delay cancellation, but the reported quiescent state remains truthful. diff --git a/.agents/notes/implemented/architecture/2026-07-16-explicit-turn-cancellation.zh.md b/.agents/notes/implemented/architecture/2026-07-16-explicit-turn-cancellation.zh.md index 0b9a06c0ae..ba20b80f3c 100644 --- a/.agents/notes/implemented/architecture/2026-07-16-explicit-turn-cancellation.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-16-explicit-turn-cancellation.zh.md @@ -12,7 +12,7 @@ Status: implemented ## 决策 -Agent 拥有仅用于运行时的 `AgentCancelCause` 联合类型 `{ kind: 'user' } | { kind: 'parent' }`；`agent.cancel()` 默认使用 `user`。TypeScript 在这个类型化的同进程 seam 中强制执行该词汇，不提供运行时校验器、后备行为，也不为无类型调用方提供特殊兼容性约定。活跃的 `TurnCancellation` 会把类型化判别字段复制为一个全新且已冻结的 signal 原因；空闲状态下没有可修改的持有者，也不会让后续工作预先进入取消状态。 +Agent 拥有仅用于运行时的 `AgentCancelCause` 联合类型 `{ kind: 'user' } | { kind: 'parent' }`；`agent.cancel()` 默认使用 `user`。TypeScript 在这个类型化的同进程边界中强制执行该词汇，不提供运行时校验器、后备行为，也不为无类型调用方提供特殊兼容性约定。活跃的 `TurnCancellation` 会把类型化判别字段复制为一个全新且已冻结的 signal 原因；空闲状态下没有可修改的持有者，也不会让后续工作预先进入取消状态。 正在运行的轮次被中断后，以粗粒度的持久化结果 `{ kind: 'aborted' }` 结束。终态事件记录轮次发生了什么，运行时 signal 标识谁请求了取消；回放不会重复保存 `user` 或 `parent`。会话 seed/load 会拒绝携带取消原因或任何其他额外字段的旧式中止记录，因此回放无法重新引入由调用方持有的取消细节。仅限进程内的 `agent/cancel-requested` 通知不会持久化；未来若有审计需求，应使用独立的持久化控制请求事件，让请求与最终结果保持为两项事实。持久化事件不包含调用栈、signal、错误对象、自由文本取消原因或后端私有细节。 @@ -20,7 +20,7 @@ AgentLoop 为每个待启动轮次私有地持有一个 `TurnCancellation`。它 对于轮次被认领前已取消的排队工作，驱动器只保留一个不携带取消原因的运行前标记。实际生效的 `cancel()` 会先发出仅供观察的 `agent/cancel-requested` 通知并携带最终确定的类型化取消原因，然后才清除排队工作和 steering（中途引导）工作或中止持有者；通知失败不能阻止此次停止，空闲状态下调用则不发出任何通知。通知观察者同步加入队列的工作也会被这次清除，而稍后由 signal 中止观察者加入队列的工作会被锁存，并在被中止的活动收敛到空闲时执行——`disposed` 取消则将其停放（[取消收敛窗口唤醒锁存](../bug-fix/2026-08-07-cancel-convergence-wake-latch.md)）。若 `running` 监听器同步取消旧工作并发送替代提示词，驱动器会丢弃已中止的持有者，并为替代提示词创建全新的持有者。同一活跃持有者上的重复取消遵循首次请求优先，后续调用仍可清除新入队的待处理工作。 -显式事件签名传递单个 payload 对象：agent 作用域事件在 payload 中携带 `agent` 和 `signal`，`next` 位于最后；其余 seam 保持 `signal` 紧邻 waterfall（瀑布式事件）的最终 `next` 之前。`PreStepContext` 与 `RequestFailureContext` 已退役，其字段并入 `agent/pre-step` 与 `agent/request-error` 的 payload（[payload-object 事件](2026-08-06-agent-event-payload-objects.md)）。步骤前处理入口、请求配置、请求错误恢复、模型生成、工具执行、审批、轮次停止以及 subagent 或工作流请求都会收到当前 signal。钩子桥接器也必须提供 `RunHookOptions.signal`，使轮次取消能够到达 Bash 执行器终止进程组并等待其退出的边界。`SystemPrompt.assemble()` 在 `AssembleContext` 中携带 `signal?: AbortSignal`，因为该对象是显式请求值，也可表示轮次之外不携带 signal 的组装。监听器可以配合该 signal 取消，但不得保留它来控制其他轮次。 +显式事件签名传递单个 payload 对象：agent 作用域事件在 payload 中携带 `agent` 和 `signal`，`next` 位于最后；其余 API 保持 `signal` 紧邻 waterfall（瀑布式事件）的最终 `next` 之前。`PreStepContext` 与 `RequestFailureContext` 已退役，其字段并入 `agent/pre-step` 与 `agent/request-error` 的 payload（[payload-object 事件](2026-08-06-agent-event-payload-objects.md)）。pre-step 进入决策、请求配置、请求错误恢复、模型生成、工具执行、审批、轮次停止以及 subagent 或工作流请求都会收到当前 signal。钩子桥接器也必须提供 `RunHookOptions.signal`，使轮次取消能够到达 Bash 执行器终止进程组并等待其退出的边界。`SystemPrompt.assemble()` 在 `AssembleContext` 中携带 `signal?: AbortSignal`，因为该对象是显式请求值，也可表示轮次之外不携带 signal 的组装。监听器可以配合该 signal 取消，但不得保留它来控制其他轮次。 `ctx.agents` 仍只携带发起 Agent。环境中的 Agent 并不代表存活、当前轮次或取消权限。cause 读取器是 loop 私有的，它直接陈述机器私有的 slot 不变量（只有 `cancel()` 会中止轮次控制器，且总是携带规范的冻结 cause），而不是对 reason 做结构化再校验；不存在从任意 signal 读取 cause 的公开辅助函数。并发 Agent 会同时隔离各自的发起方身份和轮次 signal；子驱动会遮蔽父发起方，而父请求 signal 仍通过 subagent seam 传递。 @@ -30,7 +30,7 @@ Agent dispose（资源释放）会在活跃持有者上请求仅用于运行时 ## 验证 -约定测试验证类型化调用方联合类型、冻结且与调用方分离、默认行为与首次请求优先行为、粗粒度的会话 JSON 往返与旧式记录拒绝、ACP `user`、进程内 subagent `parent` 以及 dispose 优先级。AgentLoop 测试让协作式监听器在步骤前处理、系统提示词组装、请求、模型流、请求错误恢复、工具执行和轮次停止处等待 signal；并断言同一轮次使用一个 signal，不同轮次使用全新的 signal，终态发布期间和持久化刷新受阻期间不存在取消权限。真实钩子桥接器测试会在报告空闲状态前取消并回收受阻的提示词钩子。 +约定测试验证类型化调用方联合类型、冻结且与调用方分离、默认行为与首次请求优先行为、粗粒度的会话 JSON 往返与旧式记录拒绝、ACP `user`、进程内 subagent `parent` 以及 dispose 优先级。AgentLoop 测试让协作式监听器在 pre-step、系统提示词组装、请求、模型流、请求错误恢复、工具执行和轮次停止处等待 signal；并断言同一轮次使用一个 signal，不同轮次使用全新的 signal，终态发布期间和持久化刷新受阻期间不存在取消权限。真实钩子桥接器测试会在报告空闲状态前取消并回收受阻的提示词钩子。 发起方作用域测试断言所有钩子仍观察到同一个 Agent 且没有环境中的轮次 signal，并发 Agent 保持独立的身份与 signal，嵌套子驱动只遮蔽身份。竞态测试覆盖空闲状态取消、运行前取消、从 `running` 监听器提交替代提示词、重复取消以及取消与 dispose 竞争下的完全停稳。 @@ -46,10 +46,10 @@ Agent dispose（资源释放）会在活跃持有者上请求仅用于运行时 **公开轮次或步骤上下文包装类型。** 现有 seam 已经标识 Agent、轮次和步骤。包装类型会加宽所有 API、重复归属，并诱导调用方把捕获的对象当成持久权限。 -**在宽限期后放弃不协作的工作。** 同进程工作仍在运行时就报告空闲状态，会破坏资源清理与资源归属保证。硬终止需要 worker 或进程隔离边界，不属于该控制 seam。 +**在宽限期后放弃不协作的工作。** 同进程工作仍在运行时就报告空闲状态，会破坏资源清理与资源归属保证。硬终止需要 worker 或进程隔离边界，不属于该控制边界。 ## 后果 -取消拥有一个运行时归属方、每个活跃轮次一个 signal，以及一套类型化的运行时调用方词汇。会话保留其消费方实际使用的粗粒度 `aborted` 结果，拒绝携带原因的旧式形式，并与运行时对象保持隔离。协作式取消覆盖每个异步轮次 seam，包括第一个步骤之前和最后一个步骤之后的工作，而终态发布和持久化仍在其权限范围之外。 +取消拥有一个运行时归属方、每个活跃轮次一个 signal，以及一套类型化的运行时调用方词汇。会话保留其消费方实际使用的粗粒度 `aborted` 结果，拒绝携带原因的旧式形式，并与运行时对象保持隔离。协作式取消覆盖每个异步轮次扩展点，包括第一个步骤之前和最后一个步骤之后的工作，而终态发布和持久化仍在其权限范围之外。 显式 signal 会给多个公开事件增加参数，并要求插件有意识地转发取消。这是有意设计：权限在调用边界可见，生命周期与轮次匹配，陈旧的环境异步后代无法获得控制能力。不协作的进程内工作可能延迟取消，但所报告的完全停稳仍然真实。 diff --git a/.agents/notes/implemented/architecture/2026-07-19-cooperative-tool-cancellation.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-19-cooperative-tool-cancellation.i18n.yaml index a0956af598..a1f8d14b76 100644 --- a/.agents/notes/implemented/architecture/2026-07-19-cooperative-tool-cancellation.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-19-cooperative-tool-cancellation.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-19-cooperative-tool-cancellation.md -2026-07-19-cooperative-tool-cancellation.md: 4e82452cd6883593d4693766bea803c97fa4c977 -2026-07-19-cooperative-tool-cancellation.zh.md: aa94fd9f3d32167dc7d6b906ff14a6afd36ccb32 +2026-07-19-cooperative-tool-cancellation.md: 781202688a5cbcd7076ee694fc7dd9489683d8e8 +2026-07-19-cooperative-tool-cancellation.zh.md: 8e61d6fb4eb99c5d6726e1b1af15765b84c34b03 diff --git a/.agents/notes/implemented/architecture/2026-07-19-cooperative-tool-cancellation.md b/.agents/notes/implemented/architecture/2026-07-19-cooperative-tool-cancellation.md index 4e82452cd6..781202688a 100644 --- a/.agents/notes/implemented/architecture/2026-07-19-cooperative-tool-cancellation.md +++ b/.agents/notes/implemented/architecture/2026-07-19-cooperative-tool-cancellation.md @@ -42,7 +42,7 @@ The registry first creates the call token, snapshots the visible definition's op Once a tool body starts, the registry awaits it. Cancellation reaches the body through the fused signal but never races or abandons its promise. A cooperative implementation stops or forwards cancellation and settles after its owned work reaches quiescence; an uncooperative same-process implementation can keep the registry pending indefinitely. Process, worker, network, and provider layers retain responsibility for their own termination mechanisms. -This decision requires cancellation at the tool invocation seam only. Making signals required on asynchronous capabilities reachable from tool bodies is a separate migration proposed in [Required cancellation through tool-reachable capability seams](../../proposed/architecture/2026-07-19-required-cancellation-through-tool-capability-seams.md). +This decision requires cancellation at the tool invocation boundary only. Making signals required on asynchronous capabilities reachable from tool bodies is a separate migration proposed in [Required cancellation through tool-reachable capability seams](../../proposed/architecture/2026-07-19-required-cancellation-through-tool-capability-seams.md). ## Verification @@ -54,7 +54,7 @@ No registry test can prove that arbitrary third-party same-process code observes **Keep the signal optional and synthesize a fallback.** Rejected because a registry-owned fallback has no caller lifetime to represent and preserves the exact omission the type should prevent. -**Validate `AbortSignal` at runtime.** Rejected because this is a typed same-process seam, not a serialization boundary. Runtime checks would duplicate the static contract without making cooperative use enforceable. +**Validate `AbortSignal` at runtime.** Rejected because this is a typed same-process boundary, not a serialization boundary. Runtime checks would duplicate the static contract without making cooperative use enforceable. **Add `supportsCancellation` metadata, callback-arity checks, or signal-use linting.** Rejected because none proves that asynchronous work observes or correctly forwards cancellation. Availability is a type contract; behavior remains a tool and capability responsibility. diff --git a/.agents/notes/implemented/architecture/2026-07-19-cooperative-tool-cancellation.zh.md b/.agents/notes/implemented/architecture/2026-07-19-cooperative-tool-cancellation.zh.md index aa94fd9f3d..8e61d6fb4e 100644 --- a/.agents/notes/implemented/architecture/2026-07-19-cooperative-tool-cancellation.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-19-cooperative-tool-cancellation.zh.md @@ -42,7 +42,7 @@ Status: implemented 工具主体一旦启动，注册表就会等待它完成。取消通过融合信号到达工具主体，但注册表不会与其 promise 竞速或丢弃该 promise。协作式实现会停止自身工作或继续转发取消，并在所持有的工作完全停稳后完成；不协作的同进程实现可能让注册表无限期保持等待。进程、worker、网络和提供方层仍负责各自的终止机制。 -这项决策只要求工具调用 seam 携带取消信号。让工具主体可达的异步能力也必须接收信号，属于另一项迁移，见提议中的[工具可达能力 seam 中的必填取消](../../proposed/architecture/2026-07-19-required-cancellation-through-tool-capability-seams.md)。 +这项决策只要求工具调用边界携带取消信号。让工具主体可达的异步能力也必须接收信号，属于另一项迁移，见提议中的[工具可达能力 seam 中的必填取消](../../proposed/architecture/2026-07-19-required-cancellation-through-tool-capability-seams.md)。 ## 验证 @@ -54,7 +54,7 @@ Status: implemented **保留可选信号并生成后备值。** 不予采纳，因为注册表持有的后备信号不代表任何调用方生命周期，也会保留类型系统本应阻止的缺失情况。 -**在运行时校验 `AbortSignal`。** 不予采纳，因为这是类型化同进程 seam，不是序列化边界。运行时检查只会重复静态约定，仍无法强制实现协作式使用信号。 +**在运行时校验 `AbortSignal`。** 不予采纳，因为这是类型化同进程边界，不是序列化边界。运行时检查只会重复静态约定，仍无法强制实现协作式使用信号。 **添加 `supportsCancellation` 元数据、回调参数数量检查或信号使用 lint。** 不予采纳，因为这些方法都无法证明异步工作会观察或正确转发取消。信号可用性属于类型约定；具体行为仍由工具和能力负责。 diff --git a/.agents/notes/implemented/architecture/2026-07-19-gui-layering-and-rpc-protocol.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-19-gui-layering-and-rpc-protocol.i18n.yaml index 4578e9e268..87c65807b8 100644 --- a/.agents/notes/implemented/architecture/2026-07-19-gui-layering-and-rpc-protocol.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-19-gui-layering-and-rpc-protocol.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-19-gui-layering-and-rpc-protocol.md -2026-07-19-gui-layering-and-rpc-protocol.md: 8e020e4fe9b60100671c0cf0e98e28532d850f94 -2026-07-19-gui-layering-and-rpc-protocol.zh.md: 49ebd642264c663377f16b8669fedc112d3bb6c7 +2026-07-19-gui-layering-and-rpc-protocol.md: 7997a682c8745f7b3d0a9721acfa9355603f9b2e +2026-07-19-gui-layering-and-rpc-protocol.zh.md: cb36b5cb725128e1c5067e5e69e52aa851668e52 diff --git a/.agents/notes/implemented/architecture/2026-07-19-gui-layering-and-rpc-protocol.md b/.agents/notes/implemented/architecture/2026-07-19-gui-layering-and-rpc-protocol.md index 8e020e4fe9..7997a682c8 100644 --- a/.agents/notes/implemented/architecture/2026-07-19-gui-layering-and-rpc-protocol.md +++ b/.agents/notes/implemented/architecture/2026-07-19-gui-layering-and-rpc-protocol.md @@ -4,7 +4,7 @@ Status: implemented English | [中文](2026-07-19-gui-layering-and-rpc-protocol.zh.md) -> Division of labor: this document = the layering model + the channel-independent RPC protocol; the protocol's Web implementation combines HTTP uplink with the [WebSocket downlink carrier](2026-08-04-websocket-downlink-carrier.md), while the browser object layer is in the [web client architecture RFC](2026-07-19-gui-web-client-architecture.md). +> Division of labor: this document = the layering model + the channel-independent RPC protocol; the protocol's Web implementation combines HTTP uplink with the [WebSocket downlink carrier](2026-08-04-websocket-downlink-carrier.md), while the browser object layer is in the [web client architecture note](2026-07-19-gui-web-client-architecture.md). ## Problem @@ -25,13 +25,13 @@ Directories layer as follows: - `packages/host/*`: packages provide host-side capability only (representing the Node.js engineering core built on the existing harness plugin system), and additionally - the unified backend protocol (fetch, HTTP, streaming interfaces…) — definitions and support, see the "Message protocol" sections below -- `packages/client/*`: packages provide client-side capability only; every package stays single-sided. Three kinds live here (the axes are owned by the [client plugin loading RFC](2026-07-23-client-plugin-loading-model.md)): +- `packages/client/*`: packages provide client-side capability only; every package stays single-sided. Three kinds live here (the axes are owned by the [client plugin loading note](2026-07-23-client-plugin-loading-model.md)): - **Pure libraries** (`ui-slots`, `web-react`, `ui-primitives`, plus the `loader` kernel package): ordinary root-index packages, statically bundled into the shell; the first three are seeded into the module table. - **Static-arrival entry packages** (`connection`, `runtime`, `ui-theme`, `i18n`, `hmr`): no `dshClient` key and no browser bundle — the shell bundles their `src/client/` half and registers it with `ctx.modules`; they are governed as entries of the host-authored graph like everything else. - **Fetch-arrival plugin packages** (`ui-layout`, `ui-sidebar`, `ui-conversation`, `ui-trajectory`): dual-entry — the root index is the node half (an empty `apply`, existing so the host Loader governs lifecycle and the web plugin registry discovers the package.json `dshClient` declaration); the implementation lives under `src/client/`, shipped as the `./client` subpath (a tsdown closure-factory bundle). Cross-plugin consumption of `/client` is type-only; value cooperation goes through cordis services. - `apps/` holds the externally exported application shapes, assembled from Client / Host mixtures. - `apps/web` (`dsh-frontend`) is the vite application: a thin `main.ts` over the shell surface exported by `dsh-client-web`. - - `apps/cli` (`@deepseek-ai/dsh`) dispatches shapes: `dsh web` = startHost + webserver + the built `dsh-frontend` dist; `dsh run` = headless in-process calls, zero HTTP. + - `apps/cli` (`@deepseek-ai/dsh`) dispatches shapes: `dsh web` = Host + webserver + the built `dsh-frontend` dist; `dsh run` = [a direct core Agent/Session front door](2026-08-09-headless-direct-core-front-door.md), with zero Host, HTTP, or browser layer. - A future Electron shape reuses the same web client packages over an IPC fetch carrier. ``` @@ -52,7 +52,7 @@ Direction discipline (every rule auditable from package deps): - `runtime → apiproxy` is one-way; apiproxy depends only on type definitions. - Client-side packages **never import** host-side package runtime (they consume only the two browser-safe subpaths `/api` and `/client`). - `webserver` does not depend on `runtime`: it provides a `{ fetch }`-shaped implementation — "webserver ← runtime" is a runtime injection relationship, not a package dependency. -- Cross-package client imports use the `/client` subpath for plugin packages, and between plugin packages they are type-only — a cross-plugin value import is a build error at the tsdown purity gate (value cooperation goes through cordis services; the [client plugin loading RFC](2026-07-23-client-plugin-loading-model.md) owns the edge rules). +- Cross-package client imports use the `/client` subpath for plugin packages, and between plugin packages they are type-only — a cross-plugin value import is a build error at the tsdown purity gate (value cooperation goes through cordis services; the [client plugin loading note](2026-07-23-client-plugin-loading-model.md) owns the edge rules). TypeScript checks in **two aggregate programs** referenced by a solution root (`tsconfig.json` = solution; `tsconfig.host.json` = host side + tests, excluding `packages/client`; `tsconfig.client.json` = client packages and their tests): both sides merge the cordis `Context` interface under the same keys (`sessions`, `loader`) with different services, so one program would see both declaration merges and report a collision. Shared leaves (session/llm/tools/apiproxy…) build once and are referenced by both programs ([topology](../process/2026-07-22-tsconfig-solution-root-two-aggregates.md)). @@ -66,7 +66,7 @@ On the protocol side: TS interfaces (`packages/host/apiproxy/src/api/`, zero Nod | Assembly layer | `dsh-host-runtime` | Plugin composition + ApiProxy integration + the web UI plugin mount (in-memory Loader tree over the eight dshClient packages); home of host-level configuration (defaults/persistenceRoot, future user profile) | Which plugins mount and with what defaults is decided only here; shells must not alter the assembly | | Carrier layer | `dsh-host-webserver` | Web-shape HTTP and upgrade: static serving + `/api/*`→handler forwarding + WebSocket upgrade route + close semantics; plugin bundle endpoint + `__DSH_BOOT__` manifest injection (fed by the web plugin registry) | Web (browser access) only; zero workspace dependencies (the registry arrives by structural injection); Electron does not reuse it | | Client libraries | `dsh-client-ui-slots` / `dsh-client-web-react` / `dsh-client-ui-primitives` | Slot registry core / ctx↔React glue / pure React atoms | Zero cordis runtime dependency in components; seeded into the loader module table by the shell | -| Client plugins | `dsh-client-connection` / `dsh-client-runtime` / `dsh-client-ui-theme` / `dsh-client-i18n` / `dsh-client-ui-layout` / `dsh-client-ui-sidebar` / `dsh-client-ui-conversation` / `dsh-client-ui-trajectory` | Browser-side cordis plugin tree (wire consumer, core services, theme, i18n, layout, sidebar, conversation, trajectory) — see the web client architecture RFC | Dual entry (node half = empty apply; implementation in `src/client/`); the consumption face goes exclusively through ApiProxy | +| Client plugins | `dsh-client-connection` / `dsh-client-runtime` / `dsh-client-ui-theme` / `dsh-client-i18n` / `dsh-client-ui-layout` / `dsh-client-ui-sidebar` / `dsh-client-ui-conversation` / `dsh-client-ui-trajectory` | Browser-side cordis plugin tree (wire consumer, core services, theme, i18n, layout, sidebar, conversation, trajectory) — see the web client architecture note | Dual entry (node half = empty apply; implementation in `src/client/`); the consumption face goes exclusively through ApiProxy | | Application shape | `@deepseek-ai/dsh` (apps/cli) + `dsh-frontend` (apps/web, the vite application) | Coarse bin dispatch + one assembly module per shape (web.ts / headless.ts); the vite app is a thin main over the `dsh-client-web` shell surface | Shapes dynamic-import so they never load each other; workspace knowledge like dist location stays in the app | #### Naming rule @@ -79,7 +79,7 @@ Packages under `packages/host/*` and `packages/client/*` **must carry the direct 2. **Write an assembly module under `apps/`**: `startHost()` + a client subclass + the shape's private signal/print/exit semantics; a mixture never becomes a package — assembly is written in the app. 3. **Import `dsh-host-webserver` only if you need HTTP carriage**, otherwise zero ports. -The two existing shapes are the template: `apps/cli/src/web.ts` (startHost + dist location + startWebServer + signal shutdown) and `headless.ts` (startHost + InProcessApiClient isomorphic direct calls, zero HTTP zero ports). ACP-class protocol bridges do not follow this checklist: they expose core to the external ecosystem, mount via `ctx.plugin(front-door plugin)` directly, and wear no fetch. +The two existing shapes preserve the boundary: the Web shape mounts Host, carrier, and browser composition, while `dsh run` mounts a direct core runner with zero Host, HTTP, or ports. ACP-class protocol bridges do not follow the client-carrier checklist: they expose core to the external ecosystem, mount via `ctx.plugin(front-door plugin)` directly, and wear no fetch. ## Message protocol @@ -175,7 +175,7 @@ Two logical streams: the mux stream (`/api/events.mux`, all-session aggregate) a |---|---|---| | `session/event` | `{ sessionId; event: SessionEvent }` | core passthrough: core events pass verbatim, `assistant/chunk` IS the token stream, no separate delta frame | -The remaining frame types are not re-copied here; the full unions are `MuxFrame`/`HostFrame` in `api/events.ts`. Three semantic points to know: `session/subscribed` carries lastSeq for history seam-race detection; the `approval/question` requested frames are answerable (stable rpcId) and the resolved frames are the convergence surface; `host/agent-error` is the only outlet for live failures with no turn position. +The remaining frame types are not re-copied here; the full unions are `MuxFrame`/`HostFrame` in `api/events.ts`. Three semantic points to know: `session/subscribed` carries lastSeq for history-race detection; the `approval/question` requested frames are answerable (stable rpcId) and the resolved frames are the convergence surface; `host/agent-error` is the only outlet for live failures with no turn position. **Passthrough discipline**: events/messages/content blocks on the wire ARE the core types (`SessionEvent`/`ContentBlock`) — no second DTO set; types reach the browser through the `import type` dependency chain. `SessionEventMap` is merge-extensible: the client applies its documented default (ignore) to unknown types, and the event schema keeps a "valid envelope + unknown type" branch — the envelope stays strict; this is not field-level passthrough. @@ -183,11 +183,11 @@ The remaining frame types are not re-copied here; the full unions are `MuxFrame` - **History = event replay**: one fold (client side); history pagination and live increments share one code path; the server maintains no second materialized-snapshot system. History **page boundaries align to message boundaries** (never cut mid-message; chunks group with their finalized message), and the tail page includes the in-flight partial's chunks. - **Prompt correlation**: the prompt's rpcId rides MessageSource (`'user-rpc'`) into the `user/message` event; the client uses it to promote the optimistic echo. -- **Reconnect = rebuild**: no resume cursor (`mux`'s `since` signature is a reserved seat, ignored if passed); on disconnect reopen the stream + refetch history; compare `subscribed.lastSeq` with the history tail seq and backfill once if there is a seam. +- **Reconnect = rebuild**: no resume cursor (`mux`'s `since` signature is a reserved seat, ignored if passed); on disconnect reopen the stream + refetch history; compare `subscribed.lastSeq` with the history tail seq and backfill once if there is a gap. - **Cold session handling follows ownership**: `session.history` and the source read for `session.fork` inspect persistence without an Agent, while Agent-bound ordinary-session methods such as `prompt` resume through a deduplicated in-flight table. Session-backed subagents reject that generic resume path, and attachment status is not exposed to clients (`running` already covers it). - **Approvals/questions**: the requested frame mints a stable rpcId on acceptance; first answer wins, and the host's in-memory pending table (keyed by rpcId) is the only referee; after a mux reopen, still-pending requested frames replay after the subscribed frame (rpcId reused verbatim — refresh recovery). The audit events `approval/asked`/`decided` continue through the durable log — frames = the live control plane, events = the durable audit. **Status**: the contract and frame types are shipped; the host-side pending table/wire answerer is unimplemented (`respond` in `api-proxy.ts` is a stub, always `not-pending`); PendingCard v1 is display-only. - **No protocol version**: client and host release bound together; `host.describe` has no protocolVersion field; introduce one when an independently released client appears. -- **Reserved-seam discipline**: the map holds only implemented methods; an unknown method fails loud at envelope parse (`bad-request`) — no not-implemented fallback code. The reservation list (implementing = copy the signature into the domain interface + add the map row + add the schema pair): `session.fork`, `prompt.mode` gaining `'inject'`, `task.list`, `host.listModels`, describe gaining `hostInstanceId`. (`session.rename` graduated from this list: it appends a user-source `session/title` event.) +- **Reserved-method discipline**: the map holds only implemented methods; an unknown method fails loud at envelope parse (`bad-request`) — no not-implemented fallback code. The reservation list (implementing = copy the signature into the domain interface + add the map row + add the schema pair): `session.fork`, `prompt.mode` gaining `'inject'`, `task.list`, `host.listModels`, describe gaining `hostInstanceId`. (`session.rename` graduated from this list: it appends a user-source `session/title` event.) ## The client carrier: the AbstractApiClient class family (`fetch/client.ts`) @@ -215,14 +215,14 @@ All four quadrant full forms pass through `onEnvelope`; the base implementation | Subclass | Package | doFetch | Purpose | |---|---|---|---| -| `InProcessApiClient` | apiproxy itself | the injected `{ fetch }` handler | **The isomorphic point**: `new InProcessApiClient(toFetchHandler(api))` never touches the network yet runs the real wire serialization/zod/SSE framing — `dsh run` headless is the protocol's second real consumer | +| `InProcessApiClient` | apiproxy itself | the injected `{ fetch }` handler | **The isomorphic point**: `new InProcessApiClient(toFetchHandler(api))` never touches the network yet runs the real wire serialization/zod/SSE framing; carrier tests and callers can exercise the protocol without opening a port, while product `dsh run` drives core directly | | `WebApiClient` | dsh-client-connection | `globalThis.fetch` uplink + one same-origin WebSocket downlink per logical stream | the browser shape; physical boundary in the [WebSocket downlink carrier](2026-08-04-websocket-downlink-carrier.md) | | `FixtureApiClient` | dsh-client-connection | unused (protocol-layer override) | serverless UI development (`?fixture`): overrides the `callUnary`/`openMux`/`openHost`/`respond` virtuals and is itself the fake server (frame rpcIds minted by it, semantics self-consistent) | -| (future) IPC bridge subclass | apps/electron | IPC serialization round trip | swaps only doFetch; contract and base class unchanged | +| IPC bridge subclass (hypothetical example — no such shell exists) | an Electron shell | IPC serialization round trip | would swap only doFetch; contract and base class unchanged | ## How to extend (operational checklists) -**Add a unary method (5 steps)**: ① add the method signature to the domain interface (parameters/return inline — this is the single source of truth); ② add one `RpcMethodMap` row; ③ add the request/value schema pair in `.schema.ts` (anchored `Wire>`); ④ add one handler `UNARY_ROUTES` row (the handler's Web carriage is in the web client architecture RFC); ⑤ implement in the impl (echo `request.rpcId`). On the client side, add the passthrough row to the `IApiClient`/`AbstractApiClient` domain method tables. +**Add a unary method (5 steps)**: ① add the method signature to the domain interface (parameters/return inline — this is the single source of truth); ② add one `RpcMethodMap` row; ③ add the request/value schema pair in `.schema.ts` (anchored `Wire>`); ④ add one handler `UNARY_ROUTES` row (the handler's Web carriage is in the web client architecture note); ⑤ implement in the impl (echo `request.rpcId`). On the client side, add the passthrough row to the `IApiClient`/`AbstractApiClient` domain method tables. **Add a frame type (3 steps)**: ① add a branch to the `MuxFrame`/`HostFrame` union (answerable frames must note the stable-rpcId semantics); ② add a frame-schema branch; ③ the consumers' fold/routing documented-default already covers unknown types — add an explicit branch as needed. @@ -230,11 +230,11 @@ All four quadrant full forms pass through `onEnvelope`; the base implementation **Plug in a new carrier**: subclass `AbstractApiClient` implementing only `doFetch`; to intercept at the protocol layer (like the fixture), override the `callUnary`/`openMux`/`openHost` virtuals instead. Contract and base class stay unchanged. -**Promote a reserved seam**: copy the reserved signature into the domain interface → add the map row → add the schema pair → add the UNARY_ROUTES row → implement. +**Promote a reserved method**: copy the reserved signature into the domain interface → add the map row → add the schema pair → add the UNARY_ROUTES row → implement. ## Consequences -Every client shape consumes one contract: adding a unary method is a five-step mechanical change radiating from a single signature, swapping a carrier touches only a `doFetch` subclass, and every wire message is zod-validated, observable through the envelope tap, and reconcilable by rpcId. Ordinary unary calls remain bounded, while `host.pickDirectory` and `command.execute` may stay pending until the operation finishes or caller/connection cancellation arrives; this accepts that a non-cooperative user-paced operation can hang its request rather than treating valid operation duration as transport failure. The other accepted costs: two groups of packages need explicit tsconfig paths entries, and the reserved seams (fork/inject/task.list/listModels/hostInstanceId) stay dormant until a real consumer arrives. +Every client shape consumes one contract: adding a unary method is a five-step mechanical change radiating from a single signature, swapping a carrier touches only a `doFetch` subclass, and every wire message is zod-validated, observable through the envelope tap, and reconcilable by rpcId. Ordinary unary calls remain bounded, while `host.pickDirectory` and `command.execute` may stay pending until the operation finishes or caller/connection cancellation arrives; this accepts that a non-cooperative user-paced operation can hang its request rather than treating valid operation duration as transport failure. The other accepted costs: two groups of packages need explicit tsconfig paths entries, and the reserved methods (fork/inject/task.list/listModels/hostInstanceId) stay dormant until a real consumer arrives. ## Alternatives considered @@ -242,7 +242,7 @@ Every client shape consumes one contract: adding a unary method is a five-step m |---|---| | Packaging by "product shape" (a web family, an electron family) | What shapes share is host/client capability, not the shape itself; capability-provider layering means a new shape needs zero new packages | | A package per mixture (e.g. a standalone headless package) | A mixture has exactly one consumer (its own app); packaging it is ownerless abstraction, while assembly in the app is readable and disposable | -| Consuming clients connecting to ctx directly (skipping the apiproxy layer) | A second command plane bypasses the contract, losing wire validation/observability/multi-client consistency; ctx keeps exactly two formal uses — front doors and headless event subscription | +| Consuming clients connecting to ctx directly (skipping the apiproxy layer) | Client shapes require wire validation, observability, and multi-client consistency. Direct headless is a local front door with no client boundary and uses the public Agent/Session seams rather than a client command plane | | webserver depending on runtime (saving the handler injection) | Structural-typing injection keeps webserver reusable by sidecars/tests with zero workspace deps; a package dependency would drag assembly knowledge into the carrier layer | | Package names without the group prefix (continuing dsh-) | `dsh-runtime`/`dsh-web-ui` lose their belonging in the flat npm namespace; the cost is one explicit paths entry per package | | Reusing the in-repo JSON-RPC 2.0 (dsh-jsonrpc) | Numeric error codes degrade to a single fallback code, contracts get aligned by hand in two copies, and naming drifts without a convention | diff --git a/.agents/notes/implemented/architecture/2026-07-19-gui-layering-and-rpc-protocol.zh.md b/.agents/notes/implemented/architecture/2026-07-19-gui-layering-and-rpc-protocol.zh.md index 49ebd64226..cb36b5cb72 100644 --- a/.agents/notes/implemented/architecture/2026-07-19-gui-layering-and-rpc-protocol.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-19-gui-layering-and-rpc-protocol.zh.md @@ -4,12 +4,12 @@ Status: implemented [English](2026-07-19-gui-layering-and-rpc-protocol.md) | 中文 -> 分工线：本篇 = 分层模型 + 通道无关的 RPC 协议；协议的 Web 实现由 HTTP 上行加 [WebSocket 下行载体](2026-08-04-websocket-downlink-carrier.md)组成，浏览器对象层见 [Web 客户端架构 RFC](2026-07-19-gui-web-client-architecture.md)。 +> 分工线：本篇 = 分层模型 + 通道无关的 RPC 协议；协议的 Web 实现由 HTTP 上行加 [WebSocket 下行载体](2026-08-04-websocket-downlink-carrier.md)组成，浏览器对象层见 [Web 客户端架构笔记](2026-07-19-gui-web-client-architecture.md)。 ## Problem -需要提供 UI 对接层，除已有 ACP/stdio基础版本外，还需要 Web(server) 、 Electron 、等其他产品 UI 形态。我们把这些形态统一称为 Client。希望有如下能力支持: -- 以 `dsh` 进程，同时支持 `dsh web`(启动) 和 `dsh run`(headless) ，一个进程两种模式（设计预留） +需要提供 UI 对接层，除已有 ACP（Agent Client Protocol）/stdio 基线外，还需要 Web（server）、Electron 等其他产品 UI 形态。我们把这些形态统一称为 Client。希望具备以下能力： +- 一个 `dsh` 进程同时支持 `dsh web`（启动）和 `dsh run`（headless），一个进程两种模式（设计预留） - 以与 `dsh web` 同构的 Web 技术形态，在 Electron 中启动 那么当前的工程代码需要稳定的分层职责模型，便于以后接入各类 client 形态。 @@ -20,16 +20,16 @@ Status: implemented ### 分层 -目录按照如下分层: +目录按照如下分层： - `packages/host/*`: 包只提供 Host 侧能力（代表了以现在 Harness 实体插件系统为主体的 Node.js 代码核心工程），除此之外，还包含 - 统一后端协议（fetch、HTTP、流式接口等）定义和支持，见本篇「消息协议」起各节 -- `packages/client/*`：包只提供 Client 侧能力，每包单边不混。这里住三类包（两条轴归 [client 插件装载 RFC](2026-07-23-client-plugin-loading-model.md) 所有）： +- `packages/client/*`：包只提供 Client 侧能力，每包单边不混。这里住三类包（两条轴归 [client 插件装载笔记](2026-07-23-client-plugin-loading-model.md) 所有）： - **纯库**（`ui-slots`、`web-react`、`ui-primitives`，外加内核包 `loader`）：普通根入口包，静态打包进壳；前三者播种进模块表。 - **静态到达 entry 包**（`connection`、`runtime`、`ui-theme`、`i18n`、`hmr`）：无 `dshClient` 键、无浏览器 bundle——壳把它们的 `src/client/` 半边打进自己的 bundle 并向 `ctx.modules` 登记；它们与其余单元一样，作为 host 独家撰写的图里的 entry 受治理。 - **fetch 到达插件包**（`ui-layout`、`ui-sidebar`、`ui-conversation`、`ui-trajectory`）：双入口——根入口是 node 半边（空 `apply`，其存在是为了让 host Loader 管辖生命周期、让 web 插件注册表发现 package.json 的 `dshClient` 声明）；实现住在 `src/client/` 下，经 `./client` 子路径发布（tsdown 闭包工厂 bundle）。跨插件消费 `/client` 只限类型；值层面的协作走 cordis 服务。 - `apps/` 作为对外导出的应用形态入口，可以由 Client / Host 混合组装。 - `apps/web`（`dsh-frontend`）是 vite 应用：`dsh-client-web` 导出的壳表面之上的一层薄 `main.ts`。 - - `apps/cli`（`@deepseek-ai/dsh`）做形态分发：`dsh web` = startHost + webserver + 构建出的 `dsh-frontend` dist；`dsh run` = headless 进程内直调，零 HTTP。 + - `apps/cli`（`@deepseek-ai/dsh`）做形态分发：`dsh web` = Host + webserver + 构建出的 `dsh-frontend` dist；`dsh run` = [直接使用核心 Agent／Session 的前门](2026-08-09-headless-direct-core-front-door.md)，不含 Host、HTTP 或浏览器层。 - 将来的 Electron 形态经由 IPC fetch 载体复用同一套 web client 包。 ``` @@ -50,7 +50,7 @@ harness core packages ──────────────────┘ - `runtime → apiproxy` 单向；apiproxy 仅依赖类型定义。 - client 侧包**永不 import** host 侧包的运行时（只吃 `/api`、`/client` 两个浏览器安全子路径）。 - `webserver` 不依赖 `runtime`：它提供 `{ fetch }` 特定实现 ——「webserver ← runtime」只是运行时注入关系，不是包依赖。 -- client 侧跨包 import 插件包一律走 `/client` 子路径，且插件包之间只限类型 import——跨插件值 import 在 tsdown 纯度门禁处即构建错误（值层面的协作走 cordis 服务；边规则归 [client 插件装载 RFC](2026-07-23-client-plugin-loading-model.md) 所有）。 +- client 侧跨包 import 插件包一律走 `/client` 子路径，且插件包之间只限类型 import——跨插件值 import 在 tsdown 纯度门禁处即构建错误（值层面的协作走 cordis 服务；边规则归 [client 插件装载笔记](2026-07-23-client-plugin-loading-model.md) 所有）。 TypeScript 以 solution 根引用的**两个聚合 program** 检查（`tsconfig.json` = solution；`tsconfig.host.json` = host 侧 + 测试，排除 `packages/client`；`tsconfig.client.json` = client 各包及其测试）：两侧在相同键（`sessions`、`loader`）下以不同服务合并 cordis `Context` 接口，单一 program 会同时看到两份声明合并而报冲突。共享叶子包（session/llm/tools/apiproxy 等）只构建一次，由两个 program 共同引用（[拓扑](../process/2026-07-22-tsconfig-solution-root-two-aggregates.md)）。 @@ -64,7 +64,7 @@ TypeScript 以 solution 根引用的**两个聚合 program** 检查（`tsconfig. | 装配层 | `dsh-host-runtime` | 插件组合 + ApiProxy 集成 + web UI 插件挂载（覆盖八个 dshClient 包的内存 Loader 树）；host 级配置归属地（defaults/persistenceRoot，将来用户 profile） | 装什么插件、给什么默认值只在这里定；壳不得改装配 | | 承载层 | `dsh-host-webserver` | Web 形态 HTTP 与 upgrade：静态服务 + `/api/*`→handler 转发 + WebSocket upgrade route + close 语义；插件 bundle 端点 + `__DSH_BOOT__` manifest（元数据清单）注入（由 web 插件注册表供给） | Web（浏览器访问）专用；零 workspace 依赖（注册表经结构注入到达）；Electron 不复用它 | | client 库 | `dsh-client-ui-slots` / `dsh-client-web-react` / `dsh-client-ui-primitives` | slot 注册表核心 / ctx↔React 胶合 / 纯 React 原子组件 | 组件零 cordis 运行时依赖；由壳播种进 loader 模块表 | -| client 插件 | `dsh-client-connection` / `dsh-client-runtime` / `dsh-client-ui-theme` / `dsh-client-i18n` / `dsh-client-ui-layout` / `dsh-client-ui-sidebar` / `dsh-client-ui-conversation` / `dsh-client-ui-trajectory` | 浏览器侧 cordis 插件树（wire 消费者、核心服务、主题、i18n、布局、侧栏、对话、轨迹）——见 Web 客户端架构 RFC | 双入口（node 半边=空 apply；实现在 `src/client/`）；消费面唯一经 ApiProxy | +| client 插件 | `dsh-client-connection` / `dsh-client-runtime` / `dsh-client-ui-theme` / `dsh-client-i18n` / `dsh-client-ui-layout` / `dsh-client-ui-sidebar` / `dsh-client-ui-conversation` / `dsh-client-ui-trajectory` | 浏览器侧 cordis 插件树（wire 消费者、核心服务、主题、i18n、布局、侧栏、对话、轨迹）——见 Web 客户端架构笔记 | 双入口（node 半边=空 apply；实现在 `src/client/`）；消费面唯一经 ApiProxy | | 应用态 | `@deepseek-ai/dsh`（apps/cli）+ `dsh-frontend`（apps/web，vite 应用） | bin 粗分发 + 每形态一个拼装模块（web.ts / headless.ts）；vite 应用是 `dsh-client-web` 壳表面之上的薄 main | 形态间动态 import 互不加载；dist 定位等 workspace 知识留在 app | #### 命名规则 @@ -77,7 +77,7 @@ TypeScript 以 solution 根引用的**两个聚合 program** 检查（`tsconfig. 2. **在 `apps/` 下写拼装模块**：`startHost()` + 客户端子类 + 该形态私有的信号/打印/退出语义；混合体不建包，拼装写在 app 里。 3. **需要 HTTP 承载才 import `dsh-host-webserver`**，否则零端口。 -现有两形态即模板：`apps/cli/src/web.ts`（startHost + dist 定位 + startWebServer + 信号停机）与 `headless.ts`（startHost + InProcessApiClient 同构直调，零 HTTP 零端口）。ACP 类协议桥不走本清单：它把 core 暴露给外部生态，直接 `ctx.plugin(前门插件)` 挂载、不套 fetch。 +现有两种形态保持这一边界：Web 形态挂载 Host、载体与浏览器组合，而 `dsh run` 挂载直接使用核心服务的 runner，不包含 Host、HTTP 或端口。ACP 类协议桥不遵循 client 载体清单：它把 core 暴露给外部生态，直接通过 `ctx.plugin(前门插件)` 挂载，不套 fetch。 ## 消息协议 @@ -173,7 +173,7 @@ export type ResponseValue = |---|---|---| | `session/event` | `{ sessionId; event: SessionEvent }` | 核心透传：core 事件原样过，`assistant/chunk` 即 token 流，无独立 delta 帧 | -其余帧型不在此复写，union 全集见 `api/events.ts` 的 `MuxFrame`/`HostFrame`。语义上须知三点：`session/subscribed` 的 lastSeq 供 history 补缝竞态检测；`approval/question` 的 requested 帧可应答（rpcId 稳定）、resolved 帧是收敛面；`host/agent-error` 是无 turn 位置 live 失败的唯一出口。 +其余帧型不在此复写，union 全集见 `api/events.ts` 的 `MuxFrame`/`HostFrame`。语义上须知三点：`session/subscribed` 的 lastSeq 供 history 竞态检测；`approval/question` 的 requested 帧可应答（rpcId 稳定）、resolved 帧是收敛面；`host/agent-error` 是无 turn 位置 live 失败的唯一出口。 **透传纪律**：wire 上的事件/消息/内容块就是 core 类型（`SessionEvent`/`ContentBlock`），不造第二套 DTO；类型经 `import type` 依赖链直达浏览器。`SessionEventMap` merge-extensible：client 对未知 type documented-default（忽略），事件 schema 留「合法信封+未知类型」分支——信封仍严格，不是字段级 passthrough。 @@ -185,7 +185,7 @@ export type ResponseValue = - **冷会话处理遵循所有权**：`session.history` 与 `session.fork` 的源端读取会在不获取 Agent 的情况下检查持久化存储，而绑定到 Agent 的普通会话方法（如 `prompt`）则通过在途表去重后恢复会话。由会话支撑的 subagent 会拒绝这条通用恢复路径，且附加状态不对客户端暴露（`running` 已经覆盖）。 - **审批/问答**：requested 帧受理时 mint 稳定 rpcId；先到先赢，host 内存 pending 表（keyed by rpcId）是唯一裁判；mux 重开后在 subscribed 帧后重放仍 pending 的 requested 帧（rpcId 原样复用，刷新恢复）。审计事件 `approval/asked`/`decided` 照旧走 durable 日志——帧=live 控制面，事件=durable 审计。**现状**：约定与帧类型已 shipped，host 侧 pending 表/wire answerer 未实现（`api-proxy.ts` 的 `respond` 是 stub，恒回 `not-pending`）；PendingCard v1 只展示。 - **不设协议版本**：client 与 host 绑定发布，`host.describe` 无 protocolVersion 字段；出现独立发布的 client 时再引入。 -- **预留接缝纪律**：map 只含已实现方法，未知 method 在信封 parse 即 fail loud（`bad-request`），不设 not-implemented 兜底码。预留清单（实现时把签名抄进域接口+map 加行+schema 加对即升格）：`session.fork`、`prompt.mode` 加 `'inject'`、`task.list`、`host.listModels`、describe 加 `hostInstanceId`。（`session.rename` 已从本清单毕业：追加 user 来源的 `session/title` 事件。） +- **预留方法纪律**：map 只含已实现方法，未知 method 在信封 parse 即 fail loud（`bad-request`），不设 not-implemented 兜底码。预留清单（实现时把签名抄进域接口+map 加行+schema 加对即升格）：`session.fork`、`prompt.mode` 加 `'inject'`、`task.list`、`host.listModels`、describe 加 `hostInstanceId`。（`session.rename` 已从本清单毕业：追加 user 来源的 `session/title` 事件。） ## 客户端载体：AbstractApiClient 类体系（`fetch/client.ts`） @@ -213,14 +213,14 @@ export type ResponseValue = | 子类 | 所在包 | doFetch | 用途 | |---|---|---|---| -| `InProcessApiClient` | apiproxy 本包 | 注入的 `{ fetch }` handler | **同构点**：`new InProcessApiClient(toFetchHandler(api))` 全程不过网络但真跑 wire 序列化/zod/SSE 帧——`dsh run` headless 即协议第二真实消费者 | +| `InProcessApiClient` | apiproxy 本包 | 注入的 `{ fetch }` handler | **同构点**：`new InProcessApiClient(toFetchHandler(api))` 全程不过网络但真跑 wire 序列化/zod/SSE 帧；载体测试与调用方可以在不打开端口的情况下运行这套协议，而产品 `dsh run` 直接驱动 core | | `WebApiClient` | dsh-client-connection | `globalThis.fetch` 上行 + 每逻辑流一条同源 WebSocket 下行 | 浏览器形态；物理边界见 [WebSocket 下行载体](2026-08-04-websocket-downlink-carrier.md) | | `FixtureApiClient` | dsh-client-connection | 不用（协议层覆写） | 无 server 的 UI 开发（`?fixture`）：覆写 `callUnary`/`openMux`/`openHost`/`respond` 虚方法，自己就是假 server（帧 rpcId 由它 mint，语义自洽） | -| （将来）IPC 桥子类 | apps/electron | IPC 序列化往返 | 仅换 doFetch，约定/基类零改 | +| IPC 桥子类（假想示例——尚无此形态） | Electron 壳 | IPC 序列化往返 | 只需换 doFetch，约定/基类零改 | ## 怎么扩展（操作清单） -**加一个 unary 方法（5 步）**：①域接口加方法签名（参数/返回内联，这是唯一事实源）；②`RpcMethodMap` 加一行；③`<域>.schema.ts` 加 request/value schema 对（锚 `Wire>`）；④handler `UNARY_ROUTES` 加一行（handler 的 Web 承载见 Web 客户端架构 RFC）；⑤impl 实现（回显 `request.rpcId`）。client 侧 `IApiClient`/`AbstractApiClient` 的域方法表同步加一行透传。 +**加一个 unary 方法（5 步）**：①域接口加方法签名（参数/返回内联，这是唯一事实源）；②`RpcMethodMap` 加一行；③`<域>.schema.ts` 加 request/value schema 对（锚 `Wire>`）；④handler `UNARY_ROUTES` 加一行（handler 的 Web 承载见 Web 客户端架构笔记）；⑤impl 实现（回显 `request.rpcId`）。client 侧 `IApiClient`/`AbstractApiClient` 的域方法表同步加一行透传。 **加一个帧型（3 步）**：①`MuxFrame`/`HostFrame` union 加一支（可应答帧须注明 rpcId 稳定语义）；②帧 schema 加一支；③消费端 fold/路由的 documented-default 已兜底未知型，按需加显式分支。 @@ -228,11 +228,11 @@ export type ResponseValue = **接一种新载体**：继承 `AbstractApiClient` 只实现 `doFetch`；需要拦截协议层（如 fixture）再覆写 `callUnary`/`openMux`/`openHost` 虚方法。约定与基类零改。 -**升格一个预留接缝**：把预留签名抄进域接口 → map 加行 → schema 加对 → UNARY_ROUTES 加行 → impl 实现。 +**升格一个预留方法**：把预留签名抄进域接口 → map 加行 → schema 加对 → UNARY_ROUTES 加行 → impl 实现。 ## Consequences -所有 client 形态消费同一约定：加一个 unary 方法是从单一签名辐射的五步机械改动，换载体只动一个 `doFetch` 子类，wire 上每条消息可 zod 校验、可经 envelope tap 观测、可按 rpcId 对账。普通 unary 调用仍受时限约束，而 `host.pickDirectory` 与 `command.execute` 可保持挂起，直到操作完成或调用方／连接取消到来；若由用户掌控节奏的操作不自行结束，请求可能一直挂起，这是为避免把合理的操作时长视为传输失败而接受的代价。其余接受的代价：两组包需要显式 tsconfig paths 条目；预留接缝（fork/inject/task.list/listModels/hostInstanceId）在真实消费者出现前保持休眠。 +所有 client 形态消费同一约定：加一个 unary 方法是从单一签名辐射的五步机械改动，换载体只动一个 `doFetch` 子类，wire 上每条消息可 zod 校验、可经 envelope tap 观测、可按 rpcId 对账。普通 unary 调用仍受时限约束，而 `host.pickDirectory` 与 `command.execute` 可保持挂起，直到操作完成或调用方／连接取消到来；若由用户掌控节奏的操作不自行结束，请求可能一直挂起，这是为避免把合理的操作时长视为传输失败而接受的代价。其余接受的代价：两组包需要显式 tsconfig paths 条目；预留方法（fork/inject/task.list/listModels/hostInstanceId）在真实消费者出现前保持休眠。 ## Alternatives considered @@ -240,7 +240,7 @@ export type ResponseValue = |---|---| | 按「产品形态」分包（web 一族、electron 一族） | 形态间共享的是 host/client 两侧能力而非形态本身；能力支持方分层让新形态零新包 | | 混合体建包（如 headless 独立包） | 混合体只有一个消费者（它自己的 app），建包是无主抽象；拼装写在 app 里可读可弃 | -| 消费型 client 直连 ctx（省 apiproxy 一层） | 第二命令面绕开约定，wire 校验/观测/多端一致性全失；ctx 只留给前门与 headless 事件订阅两个正式用途 | +| 消费型 client 直连 ctx（省 apiproxy 一层） | client 形态需要 wire 校验、观测与多 client 一致性。直接 headless 是没有 client 边界的本地前门，使用公开的 Agent／Session seam，而不是 client 命令面 | | webserver 依赖 runtime（省 handler 注入） | 结构 typing 注入让 webserver 可被 sidecar/测试复用且零 workspace 依赖；包依赖会把装配知识拖进承载层 | | 包名不带组前缀（沿用 dsh-<尾段>） | `dsh-runtime`/`dsh-web-ui` 在扁平 npm 命名空间里失去归属信息；代价只是每包一条显式 paths | | 复用仓内 JSON-RPC 2.0（dsh-jsonrpc） | 数字错误码退化成单码兜底、约定双份人肉对齐、命名无 convention 自然漂移 | diff --git a/.agents/notes/implemented/architecture/2026-07-19-gui-web-client-architecture.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-19-gui-web-client-architecture.i18n.yaml index 5523e6d3b2..269933c1a7 100644 --- a/.agents/notes/implemented/architecture/2026-07-19-gui-web-client-architecture.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-19-gui-web-client-architecture.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-19-gui-web-client-architecture.md -2026-07-19-gui-web-client-architecture.md: e25d002b92df2016faf4073108aa905b65a1b115 -2026-07-19-gui-web-client-architecture.zh.md: 10779107a9dc6dc7335b2c5932c8c4877b531b50 +2026-07-19-gui-web-client-architecture.md: 82b2f85708c423748954644d4991e2d54d42874a +2026-07-19-gui-web-client-architecture.zh.md: c37252d1db291cae11db2a615c9e4005ece717da diff --git a/.agents/notes/implemented/architecture/2026-07-19-gui-web-client-architecture.md b/.agents/notes/implemented/architecture/2026-07-19-gui-web-client-architecture.md index e25d002b92..82b2f85708 100644 --- a/.agents/notes/implemented/architecture/2026-07-19-gui-web-client-architecture.md +++ b/.agents/notes/implemented/architecture/2026-07-19-gui-web-client-architecture.md @@ -4,7 +4,7 @@ Status: implemented English | [中文](2026-07-19-gui-web-client-architecture.zh.md) -> Division of labor: the channel-independent layering model and RPC protocol (message model / type system / contract face / client base class) are in the [layering and RPC protocol RFC](2026-07-19-gui-layering-and-rpc-protocol.md); this document = the browser side: how the client cordis tree loads, how UI plugins compose through slots and services, and how the React-free object layer feeds React through immutable snapshots. +> Division of labor: the channel-independent layering model and RPC protocol (message model / type system / contract face / client base class) are in the [layering and RPC protocol note](2026-07-19-gui-layering-and-rpc-protocol.md); this document = the browser side: how the client cordis tree loads, how UI plugins compose through slots and services, and how the React-free object layer feeds React through immutable snapshots. ## Problem @@ -30,50 +30,50 @@ Both ends run cordis. The host is a cordis plugin tree; the browser runs a secon ## The client cordis tree and the loading chain -The loading chain — the two package kinds (plain vs dshClient plugin), the module-system/plugin-governor split, the two-phase boot over the host-authored entry graph with revisions, and hot reload — is owned by the [client plugin loading RFC](2026-07-23-client-plugin-loading-model.md). The load-bearing facts for this document: the browser boots the same vendored `@cordisjs/plugin-loader` as the host with a client module system (`ctx.modules`, `packages/client/modules`) filling its `internal` seam; every unit with product behavior is an entry in the host-authored `__DSH_BOOT__` graph — every production plugin package (infrastructure included) carries the `dshClient` declaration and arrives as a fetched `./client` tsdown closure bundle, `immediately` rows differing only in boot phase-one prefetch, while plain packages (react family, cordis, the not-yet-promoted libraries) stay shell-bundled, seeded, and invisible to the graph; bundles execute `window.__ModuleLoader__.load({ id, factory })` and their `require` is answered from the lazy CJS module table (seed words + registered factories, materialized and memoized on first require — cross-plugin value imports are a build error, cooperation goes through cordis services); plugin CSS is inlined in the bundle and injected as `