diff --git a/.agents/notes/README.i18n.yaml b/.agents/notes/README.i18n.yaml new file mode 100644 index 0000000000..fa9c0d9a21 --- /dev/null +++ b/.agents/notes/README.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +README.md: 4db9f16956b9c569cf5f9b53f04cb650f6058668 +README.zh.md: 60ec5421e7f271460daebc966aa6548f6ef8a511 diff --git a/.agents/notes/README.md b/.agents/notes/README.md index e62dc18954..4db9f16956 100644 --- a/.agents/notes/README.md +++ b/.agents/notes/README.md @@ -1,5 +1,7 @@ # Agent Notes +English | [中文](README.zh.md) + One kind of design doc lives here. An **Agent Note** records a decision or proposal that shapes this codebase — the *why* and *what we gave up*, the parts code and docs can't carry. This file is the front door and contract: where Agent Notes live, when to write one, and [the in-file format](#the-file-format). ## Layout and naming diff --git a/.agents/notes/README.zh.md b/.agents/notes/README.zh.md new file mode 100644 index 0000000000..60ec5421e7 --- /dev/null +++ b/.agents/notes/README.zh.md @@ -0,0 +1,117 @@ +# Agent Notes + +[English](README.md) | 中文 + +这里存放一类设计文档。**Agent Note(agent 决策记录)** 记录塑造本代码库的决策或提案:代码和文档无法承载的*为什么*以及*放弃了什么*。本文件是入口和契约:Agent Note 存放在哪里、何时需要写一份,以及[文件内格式](#the-file-format)。 + +## 布局与命名 + +每份 Agent Note 有两个维度,都编码在其**路径**中:`{lifecycle}/{class}/yyyy-mm-dd-topic-title.md`。 + +- **生命周期**(顶层文件夹)是 Agent Note 的状态,Agent Note 随状态变化在文件夹之间移动: + - **`proposed/`**:实施前评审的提案;尚未构建(或仅部分构建)。 + - **`implemented/`**:决策已交付。文件记录做了什么决定、否决了什么,并**与实际交付的内容保持同步**:当代码后续移动文件、重命名包(package)或更改键名/默认值时,Agent Note 在同一个变更中同步更新(仅限事实——路径、名称、结构——而非决策本身)。见 [implemented/AGENTS.md](implemented/AGENTS.md)。 + - **`rejected/`**:提案经过讨论后被否决。保留以备查阅,避免同一问题被反复争论。 +- **类别**(嵌套文件夹)是决策的*种类*——见下方[分类](#classification)。 + +文件名中的日期是该主题**首次提出**的时间(以 git 历史为准)。Agent Note 之间的交叉引用使用相对 Markdown 链接(`[topic](../../implemented/architecture/2026-…-….md)`),从不使用纯文字或编号,这样既可机械检查,也能在文件夹间移动时保持有效。 + +目录树就是清单:浏览其生命周期/类别文件夹,或搜索仓库即可。请勿添加集中式 `INDEX.md`;设计理由见[不设索引的 Agent Note](implemented/process/2026-07-19-remove-generated-agent-note-index.md)。 + + + +## 分类 + +每份 Agent Note 属于 `scripts/agent-note-tree.ts` 中封闭集合里的一个路径编码类别;分类门禁拒绝其他文件夹。新增类别需要同时更新规范集合与本节。见[分类 Agent Note](implemented/process/2026-06-20-agent-note-classification.md)。 + +| 类别 | 覆盖范围 | +|---|---| +| `feature` | 面向用户或模型的新功能。 | +| `bug-fix` | 修正缺陷或弥补事故复盘(postmortem)发现的缺口。 | +| `simplification` | 在不增加功能的前提下移除代码、行为或对外表面积。 | +| `architecture` | 关于**交付源码**的结构性决策:包之间的关系、运行时词汇。 | +| `process` | 代码**周边**的工具、策略或工作流——门禁、包管理器、vendor 化——不涉及运行时行为。 | +| `testing` | 测试基础设施与策略。 | + +`architecture` 与 `process` 的界线:**architecture** 关乎我们交付的源码;**process** 关乎围绕源码的工具与工作流。(`refactor` 被有意排除:它与 `simplification` 重叠,而后者的判别标准「可观察行为是否改变」已经覆盖了它。) + +## 何时需要写一份 + +每个非平凡变更都必须在同一 PR(Pull Request)中新增或更新至少一份 Agent Note。如果变更修改了行为、架构、跨文件或跨包契约、流程或工具、测试策略、磁盘、协议或配置格式,或者其他维护者可能合理重新审视的决策,就属于非平凡变更。对未来重大工作的提案从 `proposed/` 开始;已经做出的决策从 `implemented/` 开始。选择与决策匹配的类别文件夹(见[分类](#classification))。 + +更新已经拥有该决策的 Agent Note 即可满足规则;不要创建重复记录。只有不涉及行为、契约、结构、流程或理由变化的纯机械性或局部编辑才可豁免。Agent Note 永远不会被编辑为一个*不同的决策*:用新 Agent Note 取代旧的,并互相链接。编辑 `implemented/` Agent Note 以跟踪其现有决策的所在位置是必需的,而非禁止的;见 [implemented/AGENTS.md](implemented/AGENTS.md)。 + + + +## 文件格式 + +每份 Agent Note 遵循统一的文件内格式,由 `pnpm run verify-agent-note-format`([scripts/verify-agent-note-format.ts](../../scripts/verify-agent-note-format.ts),`doc-sync`(文档同步门禁)的一环)强制执行;该格式的设计动机及其否决的替代方案见[统一格式 Agent Note](implemented/process/2026-07-05-uniform-agent-note-format.md)。 + +### 头部块 + +每份 Agent Note 的前三行严格为: + +```markdown +# Agent Note: + +Status: <status> +``` + +后跟一个空行。`Status:` 的值有三种形式,且必须与文件所在的生命周期文件夹一致——门禁会交叉检查: + +- `Status: proposed` +- `Status: implemented` +- `Status: rejected — <why, in one line>` + +状态行不带日期、不带括号补充说明:文件名记录首次提出日期,git 记录其余一切;「以修订形式接受」之类的说明属于正文内容(在陈述决策的地方说明修订)。拒绝原因是唯一带内容的状态,因为读者查阅被否决的 Agent Note 时,结论正是他们要找的。 + +### 正文骨架 + +每份 Agent Note 的正文以 `## Problem` 开头:动机,写法上不依赖解决方案即可独立成文。后续内容取决于生命周期;固定章节使用以下规范名称且仅限这些名称,而真正独特的技术章节(包拓扑、协议契约、schema 等)在必需章节之间可自由组织。 + +#### `proposed/` + +```markdown +## Problem +## Proposal +…bespoke sections… +## Alternatives considered +## Acceptance criteria +## Risks +``` + +`## Proposal` 描述拟议的变更,可以合理地使用将来时态——计划、迁移步骤和待解决问题在工作尚未完成时属于此处。`## Acceptance criteria` 说明什么可观察状态意味着完成。`## Risks` 涵盖可能出错的事项以及该变更有意放弃的东西。 + +#### `implemented/` + +```markdown +## Problem +## Decision +…bespoke sections… +## Alternatives considered +## Consequences +``` + +`## Decision` 以现在时态描述已交付的现实,整个文件按 [implemented/AGENTS.md](implemented/AGENTS.md) 的要求与之保持同步。`## Consequences` 记录权衡的代价**与**收益。提案阶段的标题在此属于规格用语,门禁会拒绝它们:`## Proposal`、`## Plan`、`## Migration plan` 和 `## Acceptance criteria` 不得出现在 implemented Agent Note 中(原因见 [slop 检查清单](../../docs/AGENTS.md))。`## Testing`、`## Deferred` 或 `## Related` 章节在陈述现在时态的事实时是允许的。 + +#### `rejected/` + +被否决的 Agent Note 是冻结的提案:保留提案时的所有章节(包括 `## Acceptance criteria` 或 `## Plan`),结论写在 `Status:` 行上。仅头部块、`## Problem` 开头、`## Proposal` 章节以及下方的「曾考虑的替代方案」强制要求适用。 + +### 曾考虑的替代方案——必需 + +每份 Agent Note 都必须包含 `## Alternatives considered` 章节:每个真实的替代方案及其落选原因,每个替代方案用一个加粗引导的段落,或对争议较大的替代方案用 `### Why not <X>?` 子节。记录决策时不记录它击败了什么,就是在邀请反复争论——正是这些 Agent Note 存在的意义所要防止的。 + +替代方案是记录下来的,不是凭空编造的。日期早于 2026-07-05 且替代方案无法从记录中重建的 Agent Note,在该章节位置放置以下精确注释,门禁仅对格式规范之前的文件接受此注释: + +```markdown +<!-- agent-note-format: alternatives-not-recorded (pre-format Agent Note) --> +``` + +### 在生命周期之间移动 + +将文件在生命周期文件夹之间移动意味着在同一个变更中更新 `Status:` 行并满足目标文件夹的骨架要求——否则门禁会失败。具体而言,`proposed/` → `implemented/` 将 `## Proposal` 改写为现在时态的 `## Decision`,将 `## Acceptance criteria` 和 `## Risks` 折入 `## Consequences`(或折入一个现在时态的 `## Testing`/`## Verification` 章节,用于描述现在锁定该行为的内容),并用实际交付的内容替换计划——即 [implemented/AGENTS.md](implemented/AGENTS.md) 所要求的改写,使之机械化。`proposed/` → `rejected/` 仅在 `Status:` 行添加原因并冻结文件。 + +### 中文对侧文件 + +`.zh.md` 对侧文件按 [i18n 契约](../../docs/i18n/README.md)逐章节镜像其英文兄弟文件的结构;机器检查的头部标记(`# Agent Note: ` 和 `Status:` 行)保持英文原样不翻译。格式门禁跳过 `.zh.md` 文件——配对门禁负责它们的一致性。 diff --git a/.agents/notes/implemented/architecture/2026-06-11-content-block-vocabulary.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-11-content-block-vocabulary.i18n.yaml new file mode 100644 index 0000000000..01823c55d0 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-06-11-content-block-vocabulary.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-11-content-block-vocabulary.md: 9aad01cee6083b1f380be66869af3137a07d9f1f +2026-06-11-content-block-vocabulary.zh.md: 5720f0742a0729a3f98e4b05ab37acf97ae78db5 diff --git a/.agents/notes/implemented/architecture/2026-06-11-content-block-vocabulary.md b/.agents/notes/implemented/architecture/2026-06-11-content-block-vocabulary.md index 1133b990c3..9aad01cee6 100644 --- a/.agents/notes/implemented/architecture/2026-06-11-content-block-vocabulary.md +++ b/.agents/notes/implemented/architecture/2026-06-11-content-block-vocabulary.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-06-11-content-block-vocabulary.zh.md) + ## Problem The harness needs one internal language for messages that the loop, session log, and all plugins speak. diff --git a/.agents/notes/implemented/architecture/2026-06-11-content-block-vocabulary.zh.md b/.agents/notes/implemented/architecture/2026-06-11-content-block-vocabulary.zh.md new file mode 100644 index 0000000000..5720f0742a --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-06-11-content-block-vocabulary.zh.md @@ -0,0 +1,28 @@ +# Agent Note: 由 dsh-llm 拥有的提供方无关内容块词汇 + +Status: implemented + +[English](2026-06-11-content-block-vocabulary.md) | 中文 + +## 问题 + +harness 需要一套统一的内部消息语言,供 agent loop(智能体循环)、会话日志和所有插件共同使用。 + +## 决策 + +自主拥有词汇:消息是类型化内容块的数组(`text`、`reasoning`、`tool-call`、`tool-result`),其联合类型派生自可合并扩展的 `ContentBlockMap`,插件通过声明合并添加新的块类型。同一可合并扩展映射模式为所有「字符串化」字段提供类型(`MessageSource`、`FinishReason`、`TurnTrigger`、`TurnEndReason`)。流式输出采用原始分片协议;`BlockAssembler` 是唯一的共享组装实现。适配器负责转换为提供方的协议格式(wire format)——映射成本留在适配器中,正是它该在的地方。 + +会话内上下文注入(`context/message`)和轮次中途 steering(`steering/message`)最初渲染为带标签的 user-role 信封(system-reminder 模式),而非引入新角色,因此适配器无需承担额外负担。如今两者都投影为无包装的普通用户内容;见[注入内容信封 Agent Note](../simplification/2026-07-20-unwrap-injected-content-envelopes.md)。实际适配器验证已确认此渲染方式符合当前 DeepSeek 的行为;如果未来某提供方出现不兼容,应在该适配器内处理,而非引入新的规范角色。 + +## 曾考虑的替代方案 + +- **镜像 DeepSeek/OpenAI chat-completions 结构**:对第一个提供方零映射成本,但对富内容(推理、结构化块形式的工具结果)处理不便。 +- **原样采用 Anthropic Messages 块结构**:经过实战检验,但规范类型将镜像一个 harness 并非首要对接的第三方 API。 + +## 后果 + +- 推理(reasoning)在核心层有了归属,无需依赖提供方特有的结构。 +- 多模态块只有在适配器、UI 和上下文压缩(context compaction)三方协同支持后才会回归;见 [drop-image Agent Note](../simplification/2026-07-04-drop-image-content-block.md)。 +- 缓存提示与 assistant prefill 在有实际适配器能兑现之前保持缺席;见[无生产者的词汇变体](../simplification/2026-07-04-prune-producerless-vocabulary-variants.md)与[无端到端可用路径的请求旋钮](../simplification/2026-07-04-drop-inert-request-knobs.md) Agent Note。 +- 每个适配器都需承担翻译成本;首批真实适配器已验证了流式输出协议,新适配器应继续在适配器本地测试中验证其提供方特有的映射。 +- 跨包(package)边界的 ID 使用品牌类型(`CallId`、agent 与会话共享的 `SessionId`)——零运行时开销的名义类型。 diff --git a/.agents/notes/implemented/architecture/2026-06-11-custom-schema-dsl.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-11-custom-schema-dsl.i18n.yaml new file mode 100644 index 0000000000..41265a5b0f --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-06-11-custom-schema-dsl.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-11-custom-schema-dsl.md: 947d53555df078bfa9f3dac48eab4b8c0074007c +2026-06-11-custom-schema-dsl.zh.md: 26ebfe2fb15a6c034e809b3f51187342fa500193 diff --git a/.agents/notes/implemented/architecture/2026-06-11-custom-schema-dsl.md b/.agents/notes/implemented/architecture/2026-06-11-custom-schema-dsl.md index 41b72f1551..947d53555d 100644 --- a/.agents/notes/implemented/architecture/2026-06-11-custom-schema-dsl.md +++ b/.agents/notes/implemented/architecture/2026-06-11-custom-schema-dsl.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-06-11-custom-schema-dsl.zh.md) + ## Problem Tool parameters must reach the model as standard JSON Schema while giving tool authors typed `execute(args)` without casts. Schemastery already serves plugin config, but the tool-author API needs per-property `required: true` booleans rather than JSON Schema's separate `required` array. diff --git a/.agents/notes/implemented/architecture/2026-06-11-custom-schema-dsl.zh.md b/.agents/notes/implemented/architecture/2026-06-11-custom-schema-dsl.zh.md new file mode 100644 index 0000000000..26ebfe2fb1 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-06-11-custom-schema-dsl.zh.md @@ -0,0 +1,23 @@ +# Agent Note: 使用自定义类型化工具 schema DSL 替代 schemastery + +Status: implemented + +[English](2026-06-11-custom-schema-dsl.md) | 中文 + +## 问题 + +工具参数必须以标准 JSON Schema 形式到达模型,同时让工具作者在 `execute(args)` 中获得类型化的参数而无需类型断言。Schemastery 已用于插件配置,但工具作者 API 需要逐属性的 `required: true` 布尔值,而非 JSON Schema 的独立 `required` 数组。 + +## 决策 + +该决策已由[统一 JSON 值 schema DSL](2026-07-20-unified-json-value-schema-dsl.md)取代;新设计保留小型编写接口,同时让参数与类型化值共享一套词汇。`ParameterSchemaSpec` 保留逐属性的 `required: true`;`InferArgs<S>` 将必需键映射为非可选属性;`parameterSchemaSpecToJsonSchema()` 编译隐式开放的对象根;`defineTool()` 则将类型推导、编译与校验串联起来。原始 JSON Schema 的 `ToolDefinition` 仍是 `ToolRegistry.register()` 接受的输入,供 MCP 和其他外部工具使用。 + +## 曾考虑的替代方案 + +**Schemastery**(已作为 vendor 引入,用于插件 Config)经评估后被否决:它面向的是基于 StandardSchema 的校验/转换,而非 JSON Schema *生成*,因此会增加间接层却无法干净地产出协议格式(wire format)。 + +## 后果 + +- 第一方工具作者获得零类型断言的类型化参数;类型体操的成本留在核心包内部(符合 AGENTS.md 的类型安全策略)。 +- 当前节点、字面量约束、联合类型、JSON 值边界与对象开放性规则均由上述统一说明定义。 +- `InferArgs` 映射在类型层面有回归测试,源于早期一个可选性 bug。 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 new file mode 100644 index 0000000000..c6ddb39d01 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-06-11-dev-invariants-over-deep-readonly.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-11-dev-invariants-over-deep-readonly.md: 8f0e79f15af82ce3125b1f6f767d4ea727aa6d29 +2026-06-11-dev-invariants-over-deep-readonly.zh.md: 2f787bbd55b5a9a91bc5342351756e45cb0515d3 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 fb1dc93159..8f0e79f15a 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 @@ -2,6 +2,8 @@ Status: implemented +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. 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 new file mode 100644 index 0000000000..2f787bbd55 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-06-11-dev-invariants-over-deep-readonly.zh.md @@ -0,0 +1,60 @@ +# Agent Note: 源端拥有的会话不可变性与开发模式不变式 + +Status: implemented + +[English](2026-06-11-dev-invariants-over-deep-readonly.md) | 中文 + +## 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。 + +会话日志是回放、请求重建、持久化与用户可见历史的持久真源。会话包(package)外部的代码必须能检视历史,但不能保留一个可在之后改写历史的引用;从调用方接受的输入也不能继续连接到调用方拥有的可变对象。 + +单个值的不可变性只是契约的一半。一份日志可以包含完全不可变的记录,但其序列、轮次/步骤嵌套、工具调用配对、作用域分发或重建的模型请求是错误的。这些规则涉及多条记录或多个服务,无法通过冻结单个对象来建立。 + +TypeScript readonly 类型不是充分的运行时边界。它们在程序运行时消失,类型转换可以绕过它们,而递归的 `DeepReadonly<T>` 会扩散到每个日志和消息消费方,尽管某些下游请求处理 API 有意使用可变值。 + +## 决策 + +职责在始终启用的存储边界与可选的开发断言之间分离。 + +### Session 拥有不可变历史 + +`Session` 仅在一次递归遍历完成无损 JSON 快照的物化之后才接受事件。该遍历拒绝不支持的值,并产出进入日志的确切分离记录,因此验证与存储不会从有状态的 getter 观察到不同的值,也不会保留调用方拥有的嵌套引用。 + +被接受的事件及其所有后代在发布前被深度冻结。`append()` 返回该拥有的冻结事件,`session/event` 观察者接收同一记录,`session.events` 返回冻结的数组快照。先前返回的数组不会因后续 append 而增长。种子记录在构造成功前经过相同的验证、快照与冻结边界。 + +此保证属于 `Session` 而非可选监听器,因为每种组合都依赖可信的历史。无论是否注册了开发支持插件,生产部署、聚焦测试或自定义嵌入都获得相同的存储语义。 + +### 派生请求保持分离 + +`deriveMessages()` 将已记录的表面事件投影为分离的、深度冻结的 `Message` 对象,并返回一份新的数组快照。因此请求组装可以将派生历史与其他输入组合,而不会暴露一条回到日志的路径。缓存复用安全的不可变投影,而非为每次模型调用重新克隆完整历史。 + +### 包拥有的不变式配套插件检查关系 + +`dsh-invariants` 注册可配置的 `ctx.invariants` 服务,本身不包含产品检查。每个包发布一个 `./invariant` 所有权配套插件;`dsh-session`、`dsh-agent`、`dsh-scope` 和 `dsh-agent-loop` 目前添加需要 trace 状态或观察另一个 seam 的规则:单调递增的序列号、轮次与步骤嵌套、工具调用/结果配对、合法的 agent(智能体)状态转换、主体正确的作用域分发,以及循环构建的请求与从其会话日志前缀重建的请求之间的等价性。全局启用和包名 regex 过滤器归该服务所有(见[包拥有的不变式服务](2026-07-19-package-owned-invariant-service.md))。 + +当会话配套插件附加到已有或已播种的会话时,它回放不可变日志以重建跟踪状态。服务为每项贡献提供一个可 dispose(资源释放)的子 fiber,因此轮次中途热重载是安全的,同时不赋予诊断逻辑对会话存储的所有权。 + +## 曾考虑的替代方案 + +### 全面的 deep-readonly 类型 + +[被否决的不可变公共表面提案](../../rejected/architecture/2026-06-11-immutable-public-surfaces.md)会在公共日志和消息表面上应用递归 readonly 类型。这能提供编辑器反馈,但无法提供运行时保证:TypeScript 类型在运行时被擦除,插件代码可以通过类型转换绕过。它还会将 readonly 类型推入有意进行修改的消费方。在 `Session` 边界处的运行时所有权保护所有调用方,无需这种类型传播。 + +### 仅在开发模式冻结 + +仅当不变式插件安装时才冻结历史,会使核心保证依赖于组合方式。代码可能通过开发测试,却在生产环境或省略了该插件的聚焦组合中破坏历史。因此存储不可变性始终启用,而开销更大的关系检查则保持为可选的开发支持。 + +### 仅在派生消息时克隆 + +分离 `deriveMessages()` 能保护最常见的请求路径,但 `session.events` 的其他读取者、append 返回值和会话事件观察者仍能修改持久历史。日志必须保护自身的边界;派生投影是额外的隔离边界,而非替代品。 + +## 后果 + +- 每个被接受的实时或种子会话事件在任何观察者接收之前,都已从调用方拥有的输入中分离并深度不可变。 +- `session.events` 暴露稳定的不可变快照,而非私有的增长数组。 +- 请求侧的修改无法通过派生消息触及已存储的历史。 +- 开发构建可以启用关系断言而不改变存储行为;dispose 或过滤一个配套插件不会削弱日志不可变性。 +- `dsh-invariants` 配置全局启用状态以及包允许/阻止 regex 列表;每项检查仍由其产品包拥有并测试。 +- 运行时边界对每个被接受的事件产生一次递归快照与冻结的开销;后续读取者和缓存投影复用已拥有的不可变记录。 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 new file mode 100644 index 0000000000..6ea6fce11e --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-06-11-event-sourced-sessions.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-11-event-sourced-sessions.md: 15ba7b23d5eae48e7dee2328b5924493d54aeeb0 +2026-06-11-event-sourced-sessions.zh.md: da3be5965a6900076f253cad065b847c6f5ce17e 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 bab36ee783..15ba7b23d5 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 @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-06-11-event-sourced-sessions.zh.md) + ## Problem The MVP requires strict event-based tracing with fully replayable sessions (严格的基于事件的trace、logging系统,session完全可回放). 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 new file mode 100644 index 0000000000..da3be5965a --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-06-11-event-sourced-sessions.zh.md @@ -0,0 +1,28 @@ +# Agent Note: 事件溯源的会话与派生消息历史 + +Status: implemented + +[English](2026-06-11-event-sourced-sessions.md) | 中文 + +## 问题 + +MVP 要求严格的基于事件的追踪,以及完全可回放的会话(严格的基于事件的 trace、logging 系统,会话完全可回放)。 + +## 决策 + +`Session` 是一份仅追加的、类型化的 `SessionEvent` 日志,是唯一的真源。LLM(大语言模型)消息历史从日志*派生*(`deriveMessages()`);原始流分片被记录以保证 token 级别的回放保真度,而组装后的 `assistant/message` 事件才是派生的权威依据。回放/fork = 用已有日志初始化一个新会话。 + +追加操作是同步的(热路径从不阻塞于 I/O);`session/event` 是同步通知;持久化插件在后台缓冲写入,并在每个轮次结束时触发的 `session/flush` 检查点处等待排空。 + +顺序契约:agent loop(智能体循环)*先*追加到会话,再发出对应的 Cordis 事件;`agent/step-result` waterfall(瀑布式事件)在 `assistant/message` 追加之前运行,因此日志记录的是工具调度实际使用的消息。回归测试固定了这一顺序。 + +## 曾考虑的替代方案 + +**可变消息数组 + 事件仅作通知发出**:更简单,但状态与日志可能分歧;采用事件溯源后,日志本身即是状态,分歧在结构上不可能发生。 + +## 后果 + +- 回放、追踪与遥测在结构上得到保证,而非事后附加。 +- 持久化仍是插件关注点;内存存储随 dsh-session 一起提供。 +- 事件词汇可通过合并扩展(插件可添加如压缩(compaction)事件);[会话持久化](2026-06-14-session-persistence.md)在日志变为持久后冻结了其形状。 +- 派生成本随日志长度增长,压缩(未来插件)是预期的缓解手段,而非日志变更。 diff --git a/.agents/notes/implemented/architecture/2026-06-11-microkernel-event-taxonomy.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-11-microkernel-event-taxonomy.i18n.yaml new file mode 100644 index 0000000000..a15ebcfddf --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-06-11-microkernel-event-taxonomy.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-11-microkernel-event-taxonomy.md: 8bf05b7deba5f054d4ec8ecf104c3b8798e42d4e +2026-06-11-microkernel-event-taxonomy.zh.md: 4ff2ab632ca02e98137a15f19a7996a740a519b0 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 abdadb447b..8bf05b7deb 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 @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-06-11-microkernel-event-taxonomy.zh.md) + ## Problem The product principle is "everything is a plugin": hooks, /goal, /loop, dynamic workflows, compaction, sandboxing, permissions, UI, persistence, MCP, skills must all be writable as plugins without modifying the core. 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 new file mode 100644 index 0000000000..4ff2ab632c --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-06-11-microkernel-event-taxonomy.zh.md @@ -0,0 +1,31 @@ +# Agent Note: 微内核——通过 Cordis 事件分类体系实现扩展,唯一具体循环 + +Status: implemented + +[English](2026-06-11-microkernel-event-taxonomy.md) | 中文 + +## 问题 + +产品原则是「一切皆插件」:钩子、/goal、/loop、动态工作流、上下文压缩(context compaction)、沙箱、权限、UI、持久化、MCP、skill(技能)都必须能以插件形式编写,无需修改核心。 + +## 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: + +- **waterfall(瀑布式事件)**(around-middleware):插件可变换、否决、恢复或包装:`agent/prompt-submit`、`agent/request`、`agent/request-error`、`agent/step-result`、`agent/turn-continuation`、`tools/pre-execute`、`tools/execute`、`tools/post-execute`、`llm/stream`、`system-prompt/assemble`。 +- **serial**(按监听器顺序依次 await;bail 值会阻止后续监听器执行):用于有序检查点。所有 `agent/pre-step` 和 `agent/post-step` 监听器在全部弃权时才继续运行,而 `agent/turn-stop` 返回的第一个 stop 值即为最终的终止决策。 +- **parallel**(await 扇出):每个监听器都必须获得独立执行的机会:`session/flush` 持久性检查点。 +- **emit**(同步 fire-and-forget):用于通知:轮次/步骤边界、流分片、生命周期、错误,以及包含不可变 `tools/result` 观测的事件。 + +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。 + +## 曾考虑的替代方案 + +**专用中间件栈(koa-compose 风格)** 与**显式阶段状态机(插件向其中插入阶段)**:两者都需要重新实现 Cordis 原生事件系统已提供的分发、dispose(资源释放)与重载语义;作为 Cordis effect,监听器天然获得 HMR(热模块替换)与 dispose 能力。 + +## 后果 + +- 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)。 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 new file mode 100644 index 0000000000..0697332171 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-06-11-runtime-arg-validation.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-11-runtime-arg-validation.md: e0bca0ff24c5adc7ca58007932dff6580694b01d +2026-06-11-runtime-arg-validation.zh.md: 09958147766b4015d6bebf786c4947b9d2941f74 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 94b0c6af60..e0bca0ff24 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 @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-06-11-runtime-arg-validation.zh.md) + ## Problem `defineTool` ([the unified schema DSL](2026-07-20-unified-json-value-schema-dsl.md)) gives tool authors a typed `execute(args)` via the `InferArgs<S>` mapping. But that type is a compile-time claim about a value that arrives at runtime as model-generated JSON: nothing forced the model to honor the schema, so a malformed call — missing a required key, a string where a number was declared, or a literal outside the declared set — reached `execute` typed-in-name-only. The tool body then either crashed on the bad shape or silently misbehaved. 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 new file mode 100644 index 0000000000..0995814776 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-06-11-runtime-arg-validation.zh.md @@ -0,0 +1,24 @@ +# Agent Note: 模型边界处的运行时参数校验 + +Status: implemented + +[English](2026-06-11-runtime-arg-validation.md) | 中文 + +## 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<S>` 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。 + +## 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。 + +## 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。 +- 校验开销相对于一次模型调用可忽略不计。 + +<!-- agent-note-format: alternatives-not-recorded (pre-format Agent Note) --> diff --git a/.agents/notes/implemented/architecture/2026-06-11-structured-error-taxonomy.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-11-structured-error-taxonomy.i18n.yaml new file mode 100644 index 0000000000..ca9d2117ec --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-06-11-structured-error-taxonomy.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-11-structured-error-taxonomy.md: 9122193b3d01cf5a4c315e6f7a7218153fd4a60a +2026-06-11-structured-error-taxonomy.zh.md: 56a196ccd10a81b51953887f18e522412cd9463b diff --git a/.agents/notes/implemented/architecture/2026-06-11-structured-error-taxonomy.md b/.agents/notes/implemented/architecture/2026-06-11-structured-error-taxonomy.md index b2f4ea66b4..9122193b3d 100644 --- a/.agents/notes/implemented/architecture/2026-06-11-structured-error-taxonomy.md +++ b/.agents/notes/implemented/architecture/2026-06-11-structured-error-taxonomy.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-06-11-structured-error-taxonomy.zh.md) + ## Problem Failures crossed seams as bare strings. A tool error flattened to a text block — name, code, and stack lost — so a future sandbox/retry plugin couldn't tell ENOENT from EACCES, and the model got less actionable feedback than it could. A non-Error throw degraded further: the loop wrapped it in `new Error(String(x))`, dropping any code. And `LlmError` was the only typed error in the system, with no shared base, so there was nothing for a consumer to `instanceof` against generically. diff --git a/.agents/notes/implemented/architecture/2026-06-11-structured-error-taxonomy.zh.md b/.agents/notes/implemented/architecture/2026-06-11-structured-error-taxonomy.zh.md new file mode 100644 index 0000000000..56a196ccd1 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-06-11-structured-error-taxonomy.zh.md @@ -0,0 +1,26 @@ +# Agent Note: 结构化错误分类体系 + +Status: implemented + +[English](2026-06-11-structured-error-taxonomy.md) | 中文 + +## 问题 + +故障跨越 seam 时只是裸字符串。工具错误被扁平化为一个文本块(name、code 和 stack 全部丢失),导致未来的沙箱/重试插件无法区分 ENOENT 和 EACCES,模型得到的反馈也不如本可以那样具有可操作性。非 Error 的 throw 退化更严重:agent loop(智能体循环)将其包装为 `new Error(String(x))`,丢弃了所有 code。而 `LlmError` 是系统中唯一的类型化错误,没有共享基类,消费方无法对其进行通用的 `instanceof` 判断。 + +## 决策 + +在 `dsh-llm`(叶子包,所有其他包都已依赖它,不引入新的依赖边)中引入一个 `HarnessError extends Error` 基类:稳定的 `code`(与 `message` 分离)、通过 `ErrorOptions` 进行 `cause` 链接、`name` 默认为子类名。`isHarnessError` 在 seam 处做类型收窄。 + +- `LlmError` 和 `ToolArgsError`(dsh-tools)继承该基类,保留各自既有的 code。 +- `ToolExecutionResult` 新增可选字段 `error: { name, code }`,在注册表的 catch 中当抛出值为 `HarnessError` 时填充。agent loop 将其转发到 `tool/result` 会话事件(该事件也新增了同一可选字段),使结构化的失败信息存活到日志中,供重试/沙箱插件和回放使用。面向模型的文本块保持不变。 +- agent loop 的 `toError` 将非 Error 的 throw 包装为 `HarnessError`(`code: 'UNKNOWN'`,原始值作为 `cause` 链接),而非裸 `Error`;这样即使是不规范的 throw 也能携带可路由的 code 进入会话的 `error` 事件(该事件此前已暴露 `code`)。 + +## 后果 + +- 错误端到端可机器路由:插件可以基于 `error.code` 分支,而无需对消息做子串匹配。 +- 一个基类被广泛导入,但它位于所有包已经依赖的包中,代价仅是一条 import 语句,而非新的依赖边。 +- `deriveMessages` 不会将 `error` 暴露到模型历史中——模型仍然看到文本块;结构化字段服务于代码和回放。 +- 参数校验保留其既有的 code 和行为;包自有的诊断不变式独立携带稳定 code,使不变式注册表无需导入产品包。共享基类增加了跨 seam 的路由元数据,不改变面向模型的文本。 + +<!-- agent-note-format: alternatives-not-recorded (pre-format Agent Note) --> diff --git a/.agents/notes/implemented/architecture/2026-06-11-tool-schemas-in-prompt-assembly.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-11-tool-schemas-in-prompt-assembly.i18n.yaml new file mode 100644 index 0000000000..61ecb29ca3 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-06-11-tool-schemas-in-prompt-assembly.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-11-tool-schemas-in-prompt-assembly.md: 3643ac3d61be08f629ef0cd0424fef5cb9696c3a +2026-06-11-tool-schemas-in-prompt-assembly.zh.md: 10389fd7c63755e5b00b3c508fd303a541287f2c diff --git a/.agents/notes/implemented/architecture/2026-06-11-tool-schemas-in-prompt-assembly.md b/.agents/notes/implemented/architecture/2026-06-11-tool-schemas-in-prompt-assembly.md index 59ea9117dc..3643ac3d61 100644 --- a/.agents/notes/implemented/architecture/2026-06-11-tool-schemas-in-prompt-assembly.md +++ b/.agents/notes/implemented/architecture/2026-06-11-tool-schemas-in-prompt-assembly.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-06-11-tool-schemas-in-prompt-assembly.zh.md) + ## Problem On the wire, tool schemas travel in a dedicated `tools` field of the model request, not in prompt text. Architecturally, though, "what the model is told it can do" is one coherent concern: prompt sections and the tool list are assembled from the same plugin contributions and consumed at the same moment. diff --git a/.agents/notes/implemented/architecture/2026-06-11-tool-schemas-in-prompt-assembly.zh.md b/.agents/notes/implemented/architecture/2026-06-11-tool-schemas-in-prompt-assembly.zh.md new file mode 100644 index 0000000000..10389fd7c6 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-06-11-tool-schemas-in-prompt-assembly.zh.md @@ -0,0 +1,23 @@ +# Agent Note: 工具 schema 是系统提示词组装的一部分 + +Status: implemented + +[English](2026-06-11-tool-schemas-in-prompt-assembly.md) | 中文 + +## 问题 + +在协议格式(wire format)层面,工具 schema 通过模型请求中专用的 `tools` 字段传输,而非嵌入提示词文本。然而从架构角度看,「模型被告知它能做什么」是一个统一的关注点:提示词段落与工具列表由相同的插件贡献组装,并在同一时刻被消费。 + +## 决策 + +`PromptAssembly { sections, tools }`:系统提示词服务同时收集有序的文本段落和工具 schema(工具注册表自动贡献一个提供方)。agent loop(智能体循环)每个步骤消费一份 assembly;适配器将 `sections` 映射到提供方的 system 槽位,将 `tools` 映射到协议格式的 `tools` 字段。因此 `system-prompt/assemble` waterfall(瀑布式事件)是模型预先获知的所有信息的唯一拦截点:工具过滤(ToolSearch / 渐进式披露)是一次 assembly 重写,与提示词编辑无异。 + +## 曾考虑的替代方案 + +**循环从工具注册表和提示词服务分别查询**:将一个统一的关注点拆到两个 seam 上;任何想影响「模型被告知什么」的拦截(工具过滤、plan 模式)都需要在两个接口上各挂一个监听器,而非一次 assembly 重写即可完成。 + +## 后果 + +- 一条 waterfall 统管模型的常驻上下文;plan 模式等插件可以在一个监听器中同时替换提示词文本和可见工具。 +- assembly 接口通过声明合并实现可扩展(没有无类型的 `extras` 包——扩展即声明合并),为未来的槽位预留空间。 +- 将 schema 放在「提示词」服务中略有概念上的意外感,已在本文及包 README 中加以说明。 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 new file mode 100644 index 0000000000..63063f8d5f --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-06-13-capability-seams.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-13-capability-seams.md: 7c755dced7825d2831acc0901f6412b8e5afe95a +2026-06-13-capability-seams.zh.md: 4148c79cb5e1930dca77eaf3afd2024f508275b5 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 5ca299abc0..7c755dced7 100644 --- a/.agents/notes/implemented/architecture/2026-06-13-capability-seams.md +++ b/.agents/notes/implemented/architecture/2026-06-13-capability-seams.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-06-13-capability-seams.zh.md) + ## Problem The harness has swappable capabilities — bash execution today, sandboxed/remote executors and alternative model providers tomorrow. A capability has three concerns that change at different rates and for different reasons: the *contract* (what the capability is), the *implementation* (how it runs), and the *consumer surface* (what the model and other plugins program against). Bundling them in one package couples those rates of change — swapping a local executor for a sandboxed one would churn the tool schemas the model sees, even though the model-facing contract never changed. 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 new file mode 100644 index 0000000000..4148c79cb5 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-06-13-capability-seams.zh.md @@ -0,0 +1,32 @@ +# Agent Note: 能力 seam——接口/实现/消费方三分 + +Status: implemented + +[English](2026-06-13-capability-seams.md) | 中文 + +## 问题 + +harness 具有可替换的能力:当前是 bash 执行,未来会有沙箱化/远程执行器和替代模型提供方。一项能力涉及三个关注点,它们以不同速率、因不同原因变化:*契约*(这项能力是什么)、*实现*(它如何运行)、*消费方接口*(模型和其他插件面向什么编程)。将三者捆绑在一个包(package)中会耦合这些变化速率——把本地执行器换成沙箱化执行器时,模型看到的工具 schema 也会被搅动,尽管面向模型的契约从未改变。 + +这与「谁在运行时提供、谁需要一项能力」是不同的问题,后者 Cordis 已通过服务 + `inject` 解决(提供方注册 `ctx.bash`;消费方声明 `inject: ['bash']`,其 fiber 挂起直到服务存在)。该机制是必要的,但不决定包的边界;本 Agent Note 决定的是包的边界。 + +## 决策 + +一项可替换的能力由**三个包**构成: + +1. **接口**——一个抽象服务加词汇类型,拥有 `ctx.<key>`,仅依赖其词汇依赖(例如 `dsh-bash`:`BashExecutor`、`BashRunResult`、`BashProcess`)。 +2. **实现**——一个具体子类,以插件形式加载(例如 `dsh-bash-local`:子进程、进程组 kill、溢出文件截断)。沙箱化/远程后端是实现同一接口的兄弟包。 +3. **消费方**——模型和插件看到的内容(例如 `dsh-tool-bash`:`bash` schema,后台句柄注册到通用任务运行时)。消费方 `inject` 接口键,从不导入实现类型。 + +实现与消费方由此独立演进:沙箱化执行器替换 `dsh-bash-local` 时无需触碰任何工具 schema。 + +当各部分确实属于同一个关注点时,三分并非强制:LLM(大语言模型) seam 将接口 + 消费方合并为 `dsh-llm`(消费方是 agent loop(智能体循环)本身,而非可替换的 schema 表面),适配器作为实现包。不要预防性地拆分——如果一项能力只有一种可设想的实现和一个消费方,就保持为一个包,直到第二种出现。 + +## 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。 + +## 后果 + +每项能力需要更多包和更多样板代码(一组 `package.json`/`tsconfig`/README,加上 inject 接线)。换来的是:实现与消费方独立发布和版本管理,新后端永远不会波及面向模型的契约。该规则记录在 [AGENTS.md](../../../../AGENTS.md) § Conventions(「Capability seams are three packages」)和 [architecture.md](../../../../docs/architecture.md) §「Capability seams」中;bash 三件套是参考模板。何时合并、何时拆分是一个判断问题,架构文档对此有详细说明——本 Agent Note 记录的是*为什么*默认选择拆分。 diff --git a/.agents/notes/implemented/architecture/2026-06-13-twin-llm-adapters.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-13-twin-llm-adapters.i18n.yaml new file mode 100644 index 0000000000..f1d2fe1a90 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-06-13-twin-llm-adapters.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-13-twin-llm-adapters.md: 5c3308b281ce71407002e95dd6e794da2a421fa8 +2026-06-13-twin-llm-adapters.zh.md: 93b084973bccaeb802508e4e939a259c281f2608 diff --git a/.agents/notes/implemented/architecture/2026-06-13-twin-llm-adapters.md b/.agents/notes/implemented/architecture/2026-06-13-twin-llm-adapters.md index 7f2f5933ad..5c3308b281 100644 --- a/.agents/notes/implemented/architecture/2026-06-13-twin-llm-adapters.md +++ b/.agents/notes/implemented/architecture/2026-06-13-twin-llm-adapters.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-06-13-twin-llm-adapters.zh.md) + ## Problem `dsh-llm` owns a provider-neutral streaming vocabulary — the `StreamChunk` protocol (`block-start`, `text-delta`, `reasoning-delta`, `tool-call-delta`, `block-end`, `usage`, `finish`) and the content-block types ([the content-block vocabulary](2026-06-11-content-block-vocabulary.md)). A vocabulary defined against a single adapter risks baking that adapter's quirks into the "neutral" contract: anything the one implementation happens to do becomes the de-facto spec, and the abstraction is unverified until a second provider arrives — by which point the leak is expensive to fix. diff --git a/.agents/notes/implemented/architecture/2026-06-13-twin-llm-adapters.zh.md b/.agents/notes/implemented/architecture/2026-06-13-twin-llm-adapters.zh.md new file mode 100644 index 0000000000..93b084973b --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-06-13-twin-llm-adapters.zh.md @@ -0,0 +1,27 @@ +# Agent Note: 以两个 LLM 适配器作为设计验证孪生体 + +Status: implemented + +[English](2026-06-13-twin-llm-adapters.md) | 中文 + +## 问题 + +`dsh-llm` 拥有一套提供方无关的流式词汇:`StreamChunk` 协议(`block-start`、`text-delta`、`reasoning-delta`、`tool-call-delta`、`block-end`、`usage`、`finish`)以及内容块类型([内容块词汇](2026-06-11-content-block-vocabulary.md))。如果词汇仅针对单个适配器定义,就有可能将该适配器的特异行为烘焙进「中立」契约:唯一实现碰巧做了什么,什么就成为事实上的规范;在第二个提供方到来之前,抽象层未经验证——而届时泄漏已代价高昂。 + +## 决策 + +从一开始就针对同一份契约交付**两个**适配器,刻意基于不同的内部实现构建: + +- `dsh-llm-deepseek`:手写 `fetch` + SSE(Server-Sent Events)解析,直接对接 DeepSeek API。 +- `dsh-llm-pi-ai`:通过 `@earendil-works/pi-ai` 库访问同一端点(该库有自己的事件词汇)。 + +二者共同执行的规则是:**凡 StreamChunk 词汇无法为两个实现同时表达的内容,都是核心词汇的缺陷**——立即暴露,而非等到下一个提供方接入时才发现。这对孪生体确定了现已记录在 `dsh-llm/src/types.ts` 中 `StreamChunk` 上的约定:usage 在 finish 之前发出、finish 之后不再有任何事件、工具调用的 `arguments` 全程以原始 JSON 字符串传递,以及消费方必须在两侧都处理的两条合法错误路径(`stream()` 抛异常,*或者*以 `finish {kind:'error'|'aborted'}` 结束)。后一项分歧正是由基于库的适配器暴露出来的,单一手写适配器会将其隐藏。 + +## 曾考虑的替代方案 + +- **单一适配器**:代码更少、e2e 成本减半,但「提供方无关」的声明无从验证;词汇会默默编码 DeepSeek-via-fetch 的假设。 +- **mock 第二适配器**:更便宜,但不会触及真实提供方的协议格式(wire format)怪癖,因此证明力有限。孪生体是真实对真实的验证。 + +## 后果 + +孪生体使适配器和需要密钥的 e2e 维护量翻倍——两者都覆盖 V4 Flash 和 Pro 在各代表性推理(reasoning)模式下的行为——换来的是持续的 seam 中立性验证和第二份实现示例。两个适配器均使用 `apiKey`、`baseURL` 和 `models`;手写适配器暴露 `thinking`/`reasoningEffort`,pi-ai 适配器暴露一个 `reasoning` 级别。未来如果有一致性测试套件,可以通过后续 Agent Note 论证退役其中一个适配器。 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 new file mode 100644 index 0000000000..8b9aaea118 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-06-14-session-persistence.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-14-session-persistence.md: 2683bcd68e1f52fbd2bc78660fbe17e556a9a60d +2026-06-14-session-persistence.zh.md: 28e32925a5866fe520c0d9c3eb7b0647845d36f5 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 4e105ef598..2683bcd68e 100644 --- a/.agents/notes/implemented/architecture/2026-06-14-session-persistence.md +++ b/.agents/notes/implemented/architecture/2026-06-14-session-persistence.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-06-14-session-persistence.zh.md) + ## Problem Sessions lived only in memory. The example `session-jsonl.ts` plugin (duplicated byte-for-byte in both examples) was write-only telemetry: it buffered `session/event` and appended JSON lines, with no read/replay path, no crash-safety (no fsync, no atomic write, a fire-and-forget dispose drain), no listing, and no format versioning. Nothing could rehydrate a past session from disk into a live agent, so durable resume ("continue yesterday's task"), durable forking, and the ACP `session/load` method ([ACP support](../feature/2026-06-14-acp-agent-client-protocol.md)) were all impossible. @@ -19,16 +21,16 @@ Key choices recorded here because they are durable, contested, and surprising: - **The canonical durable log persists every `SessionEvent` verbatim, including `assistant/chunk`.** `deriveMessages()` skips chunks, and a chunk-filtered rollout (Codex's `policy.rs`) is tempting — but `seq = log.length` and the load-validation `events[i].seq === i` require a *contiguous* log; filtering chunks out would leave holes and break both the contract and resume. A chunk-filtered projection is possible later as a derived view with its own renumbering, but it is NOT the canonical log. - **Append-only; a crashed turn is closed, never truncated.** Flushed events are never rewritten. The [semantic checkpoint policy](../bug-fix/2026-07-21-semantic-session-checkpoints.md) drains the request before model dispatch, a recorded top-level call before tool dispatch, and the complete response/result batch after a step; the loop drains the final turn boundary. Because one interrupted turn may contain substantial valid work, `load` preserves its contiguous, parseable events and appends risk-classified error results for unanswered assistant calls, a missing `step/end`, and `turn/end` with `{ kind: 'interrupted' }`. The synthetic results keep resumed provider transcripts valid. Only an incomplete final record is discarded; a parse error or sequence gap at or before the last real `turn/end` is corruption and makes the session unloadable. -- **File backend canonical, DB backend a proven drop-in.** `SessionEvent` maps 1:1 onto a row `(session_id, seq, type, time, data)` — `append` is INSERT (in a transaction asserting the contiguous-seq contract), `load` is SELECT … ORDER BY seq. `dsh-session-persistence-sqlite` is exactly this: a `SessionPersistence` subclass with no interface change (opencode runs this exact shape on SQLite/WAL), and it passes the same `runPersistenceContract` suite as the JSONL backend — so the contract holds both backends to identical semantics (lazy materialization, interrupted-turn close on load, contiguous-seq), expressed once over file bytes and once over rows. -- **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()`. 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).) +- **File backend canonical, DB backend a proven drop-in.** `SessionEvent` maps 1:1 onto a row `(session_id, seq, type, time, data)` — `append` is INSERT (in a transaction asserting the contiguous-seq contract), `load` is SELECT … ORDER BY seq. `dsh-session-persistence-sqlite` is exactly this: a `SessionPersistence` subclass with no interface change (opencode runs this exact shape on SQLite/WAL), and it passes the same `runPersistenceContract` suite as the JSONL backend — so the contract holds both backends to identical semantics (lazy materialization, interrupted-turn close on load, contiguous-seq), expressed once over file bytes and once over rows. Its database carries a dedicated application id and monotonic schema version. A pristine file creates all tables and stamps both header values in one transaction; an unversioned file with any user-defined schema object or application identity, a foreign current-version identity, and every non-current version reject before journal-mode mutation. +- **Metadata is out-of-log.** Format version, cwd, and lineage are storage concerns, not replayable conversation state, so they live in a `SessionHeader` owned by `dsh-session` and attached to a `Session` via a new readonly `session.header` — never in `SessionEventMap`, never reaching `deriveMessages()`. `createdAt` is non-negative safe-integer Unix epoch milliseconds: live creation and persistence registration reject fractional values, JSONL validates the decoded header, and SQLite stores it in a strict `INTEGER` column. The alternative (a merge-extensible `session/meta` event as log line 0) was rejected: an in-log event would ride along with a seeded/forked session for free, but metadata is not replayable state, so the explicit out-of-log header seam is the cleaner cost. (The header was originally split into an immutable `SessionHeader` plus a mutable `SessionSummary` whose union was `SessionMeta`; the mutable summary was later removed as dead state — see [Drop the mutable session summary](../simplification/2026-06-19-drop-mutable-session-summary.md).) - **`ctx.agents.create()` and `ctx.agents.resume()` are async factories; resume additionally crosses the persistence boundary.** `ctx.agents.resume({ resumeSessionId })` awaits `ctx.sessionPersistence.load`, recreates the live session with the loaded events (so `lastTurnNumber`/`deriveMessages` continue), and registers the fresh agent under the exact resumed id. The agent-loop does NOT hard-inject `sessionPersistence` (that would pend non-persistent demos forever); `resume` rejects with a clear error when it is absent. ## 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; **hard-injecting `sessionPersistence` into the loop** — would pend non-persistent demos forever. +Each key choice above records its rejected alternative where the choice is stated: a **chunk-filtered canonical log** (Codex's `policy.rs` shape) — breaks the contiguous-seq contract; **truncating a crashed turn** — silently destroys a long autonomous run's real work; an **in-log `session/meta` event as line 0** — metadata is not replayable state; **finite fractional `createdAt` values** — have no producer and diverge from integer Unix-millisecond storage and query columns; **adopting a non-pristine unversioned SQLite file** — can overwrite unrelated objects or identity; **hard-injecting `sessionPersistence` into the loop** — would pend non-persistent demos forever. Format versioning: the header carries a `version`; `load` rejects any non-current version (no migration — the pre-release session format is pinned at `SESSION_FORMAT_VERSION = 0` and absorbs shape churn, per the AGENTS.md pre-release stance). Stated honestly: append-only + flush is robust to partial trailing writes (tolerated on load) but not to fsync-less power loss mid-line; a DB/WAL backend is the stronger option later. ## 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 the foundation the ACP `session/load` ([ACP support](../feature/2026-06-14-acp-agent-client-protocol.md)) needs — all 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, and serializability semantics. Persisting the full log also settles event fidelity: `assistant/chunk` remains verbatim. +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 the foundation the ACP `session/load` ([ACP support](../feature/2026-06-14-acp-agent-client-protocol.md)) needs — all over the existing event-sourced log, with the backend swappable behind one interface. The reusable `runPersistenceContract` suite holds every backend to the same append-only, contiguous-seq, lazy-materialization, integer-metadata, and serializability semantics. Persisting the full log also settles event fidelity: `assistant/chunk` remains verbatim. 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 new file mode 100644 index 0000000000..28e32925a5 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-06-14-session-persistence.zh.md @@ -0,0 +1,36 @@ +# Agent Note: 会话持久化作为基于现有 `SessionEvent` 的抽象服务 + +Status: implemented + +[English](2026-06-14-session-persistence.md) | 中文 + +## 问题 + +会话此前仅存在于内存中。示例插件 `session-jsonl.ts`(在两个示例中逐字节重复)是只写的遥测:它缓冲 `session/event` 并追加 JSON 行,没有读取/回放路径,没有崩溃安全性(无 fsync、无原子写入、fire-and-forget 的 dispose 排空),没有列表功能,也没有格式版本控制。没有任何机制能将磁盘上的历史会话重新注入到活跃的 agent(智能体)中,因此持久恢复(「继续昨天的任务」)、持久 fork 以及 ACP(Agent Client Protocol)的 `session/load` 方法([ACP 支持](../feature/2026-06-14-acp-agent-client-protocol.md))都无法实现。 + +[事件溯源模型](2026-06-11-event-sourced-sessions.md)将仅追加日志作为唯一真源,并从中派生 LLM(大语言模型)历史。持久化必须忠实于这一设计:直接持久化现有的 `SessionEvent`,不引入需要来回转换的并行「持久化消息」类型。后端也必须可替换——当前用文件存储,以后用数据库存储——统一在一个接口之后。 + +## 决策 + +持久化是一个抽象的**能力 seam**([能力 seam](2026-06-13-capability-seams.md),`dsh-bash` 模板),而非循环或核心逻辑: + +1. **接口**(`dsh-session-persistence`,`ctx.sessionPersistence`):一个抽象的 `SessionPersistence` 服务,提供 `create`/`append`/`load`/`list`。其持久化单元就是现有的 `SessionEvent`(`{ type, seq, time, data }`),原样复用,无转换类型。 +2. **实现**(`dsh-session-persistence-jsonl`):每个会话一个仅追加的逻辑 JSONL 日志(一行 `SessionHeader`,之后每行一个 `SessionEvent`,逐字节保留,**包括 `assistant/chunk`**),默认编码为[带校验和的 Zstandard 帧](2026-07-19-zstandard-jsonl-session-logs.md),也可通过配置使用原始行。 + +以下关键选择记录于此,因为它们是持久性的、有争议的、且出人意料的: + +- **规范的持久日志逐字节保留每个 `SessionEvent`,包括 `assistant/chunk`。** `deriveMessages()` 跳过分片,而过滤分片的方案(Codex 的 `policy.rs`)很有吸引力,但 `seq = log.length` 以及加载验证 `events[i].seq === i` 要求日志是*连续*的;过滤掉分片会留下空洞,同时破坏契约和恢复功能。基于分片过滤的投影可以作为派生视图在后续实现(带有自己的重新编号),但它不是规范日志。 +- **仅追加;崩溃的轮次被关闭,而非截断。** 已刷写的事件永不被重写。[语义检查点策略](../bug-fix/2026-07-21-semantic-session-checkpoints.md)会在模型分发前排空请求、在工具分发前排空已记录的顶层调用,并在步骤结束后排空完整的响应/结果批次;循环则排空最终轮次边界。由于一个被中断的轮次可能包含大量有效工作,`load` 保留其连续、可解析的事件,并为未应答的 assistant 调用追加按风险分类的错误结果、补一个缺失的 `step/end`,以及带 `{ kind: 'interrupted' }` 的 `turn/end`。合成的结果保证恢复后的提供方 transcript(文本记录)仍然有效。只有不完整的最后一条记录会被丢弃;在最后一个真实 `turn/end` 处或之前出现解析错误或序号间隙,属于数据损坏,会使该会话不可加载。 +- **文件后端为规范实现,数据库后端为经过验证的直接替换。** `SessionEvent` 1:1 映射到一行 `(session_id, seq, type, time, data)`:`append` 是 INSERT(在一个断言连续 seq 契约的事务中),`load` 是 SELECT … ORDER BY seq。`dsh-session-persistence-sqlite` 正是如此:一个 `SessionPersistence` 子类,接口无变化(opencode 在 SQLite/WAL 上运行的正是这个形状),且通过与 JSONL 后端相同的 `runPersistenceContract` 测试套件。该契约以相同的语义约束两个后端(惰性物化、加载时关闭中断轮次、连续 seq),一次表达在文件字节上,一次表达在数据库行上。其数据库拥有专用的 application id 与单调递增的 schema 版本。系统会在一个事务中为全新文件创建所有表并写入这两个 header 值;未版本化文件若带有任何用户定义的 schema 对象或应用标识、当前版本文件若带有外部应用标识,以及任何非当前版本文件,都会在修改日志模式之前被拒绝。 +- **元数据在日志之外。** 格式版本、cwd 和谱系是存储关注点,不是可回放的对话状态,因此它们存放在 `dsh-session` 拥有的 `SessionHeader` 中,并通过新的只读属性 `session.header` 附加到 `Session` 上——永远不进入 `SessionEventMap`,永远不到达 `deriveMessages()`。`createdAt` 是以 Unix epoch 毫秒表示的非负安全整数:运行时创建和持久化注册会拒绝小数值,JSONL 会验证解码后的 header,SQLite 则将其存入严格的 `INTEGER` 列。替代方案(一个可合并扩展的 `session/meta` 事件作为日志第 0 行)被否决:日志内事件会随 seed/fork 的会话免费携带,但元数据不是可回放状态,因此显式的日志外 header seam 是更干净的代价。(header 最初被拆分为不可变的 `SessionHeader` 加可变的 `SessionSummary`,二者的联合类型为 `SessionMeta`;可变 summary 后来因属于死状态而被移除——见 [移除可变会话摘要](../simplification/2026-06-19-drop-mutable-session-summary.md)。) +- **`ctx.agents.create()` 和 `ctx.agents.resume()` 是异步工厂;恢复还跨越持久化边界。** `ctx.agents.resume({ resumeSessionId })` 等待 `ctx.sessionPersistence.load`,用加载的事件重建活跃会话(使 `lastTurnNumber`/`deriveMessages` 得以延续),并以原样恢复的 id 注册新 agent。agent loop(智能体循环)不会硬注入 `sessionPersistence`(那样会让非持久化的演示永远挂起);当它不存在时,`resume` 会以明确的错误拒绝。 + +## 曾考虑的替代方案 + +上述每个关键选择都在陈述处记录了被否决的替代方案:**过滤分片的规范日志**(Codex 的 `policy.rs` 形式)破坏连续 seq 契约;**截断崩溃的轮次**会静默销毁长时间自主运行中的真实工作;**日志内 `session/meta` 事件作为第 0 行**——元数据不是可回放状态;**有限的非整数 `createdAt` 值**没有生产方,且与整数 Unix 毫秒存储及查询列不一致;**接受非全新的未版本化 SQLite 文件**可能覆盖无关对象或应用标识;**将 `sessionPersistence` 硬注入循环**会让非持久化的演示永远挂起。 + +格式版本控制:header 携带一个 `version`;`load` 拒绝任何非当前版本(不做迁移——预发布阶段的会话格式固定为 `SESSION_FORMAT_VERSION = 0` 并吸收形状变动,遵循 AGENTS.md 的预发布立场)。坦率地说:仅追加 + 刷写对部分尾部写入是健壮的(加载时容忍),但对行写入中途的无 fsync 断电不健壮;数据库/WAL 后端是后续更强的选项。 + +## 后果 + +新增两个包(package),以及 `dsh-session` 中的元数据 seam(`session.header`,`create(id?, options?)` 签名)。收益:持久恢复/fork、读取/回放路径、崩溃容忍,以及 ACP `session/load`([ACP 支持](../feature/2026-06-14-acp-agent-client-protocol.md))所需的基础——全部基于现有的事件溯源日志,后端在一个接口之后可替换。可复用的 `runPersistenceContract` 测试套件以相同的仅追加、连续 seq、惰性物化、整数元数据与可序列化语义约束每个后端。持久化完整日志还确定了事件保真度:`assistant/chunk` 保持逐字节不变。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/2026-06-15-turn-enclosure-invariant.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-15-turn-enclosure-invariant.i18n.yaml new file mode 100644 index 0000000000..46cb7aaa20 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-06-15-turn-enclosure-invariant.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-15-turn-enclosure-invariant.md: 6e2abd1716f8efc08c06d5ff8faec38282f2a17f +2026-06-15-turn-enclosure-invariant.zh.md: 0921c2574dc171e887664d8a2ea840a4e81f1531 diff --git a/.agents/notes/implemented/architecture/2026-06-15-turn-enclosure-invariant.md b/.agents/notes/implemented/architecture/2026-06-15-turn-enclosure-invariant.md index 00352b01c4..6e2abd1716 100644 --- a/.agents/notes/implemented/architecture/2026-06-15-turn-enclosure-invariant.md +++ b/.agents/notes/implemented/architecture/2026-06-15-turn-enclosure-invariant.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-06-15-turn-enclosure-invariant.zh.md) + ## Problem A durable session-persistence backend (added in a companion change) uses the **turn** as its crash-recovery boundary: a crash can leave an unclosed final turn, which `load` closes with a synthetic `turn/end {kind:'interrupted'}` while preserving the turn's real events (see [session persistence](2026-06-14-session-persistence.md)). This recovery is only well-defined if nothing *legitimately* durable sits OUTSIDE a turn — between the last `turn/end` and the next `turn/start` — since such an event would be swept into the next turn's interrupted close. diff --git a/.agents/notes/implemented/architecture/2026-06-15-turn-enclosure-invariant.zh.md b/.agents/notes/implemented/architecture/2026-06-15-turn-enclosure-invariant.zh.md new file mode 100644 index 0000000000..0921c2574d --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-06-15-turn-enclosure-invariant.zh.md @@ -0,0 +1,42 @@ +# Agent Note: 每个会话事件都封闭在一个轮次内 + +Status: implemented + +[English](2026-06-15-turn-enclosure-invariant.md) | 中文 + +## 问题 + +持久化的会话持久化后端(在配套变更中引入)以**轮次**作为崩溃恢复边界:崩溃可能留下一个未关闭的最终轮次,`load` 会用一个合成的 `turn/end {kind:'interrupted'}` 将其关闭,同时保留该轮次的真实事件(见[会话持久化](2026-06-14-session-persistence.md))。这种恢复只有在没有任何*合法的*持久事件位于轮次之外(即上一个 `turn/end` 与下一个 `turn/start` 之间的间隙)时才是良定义的,否则这类事件会被卷入下一个轮次的中断关闭中。 + +这一假设并不成立。有两条路径在任何轮次之外记录了事件: + +1. **排队的用户消息。** agent loop(智能体循环)排空排队消息并在 `turn/start` *之前*追加 `user/message`——于是一个轮次自身的提示词落在了前一个 `turn/end` 与下一个 `turn/start` 之间的间隙中。 +2. **空闲时的上下文注入。** `agent.inject()` 直接追加一条 `context/message`。它在生产环境中的真实调用方是 `dsh-tool-bash`,后者从 `ctx.bash.onTaskDone` 注入后台任务完成通知——该回调在后台 bash 任务完成时触发,而这经常发生在 agent **空闲**(轮次之间)时。 + +在情况 2 中,如果注入的 `context/message` 是 flush/dispose 之前的最后一个事件(之后没有轮次追加 `turn/end`),`scanLog` 会将其视为崩溃残留并在**恢复时丢弃**——注入的上下文已持久写入磁盘,但重新加载后被静默丢失。情况 1 本身无害(`user/message` 之后总会跟着它触发的轮次),但使「什么可以出现在轮次之外」这条规则变得模糊。 + +## 决策 + +**每个会话事件都位于一个轮次内部**:在 `turn/start` 与其匹配的 `turn/end` 之间。具体而言: + +- agent loop 在 `turn/start` **之后**(轮次内部)追加排队的 `user/message` 事件,而非之前。因此,一旦这些消息被记录,就欠下一个 `turn/end`,既有的 finalizer 保证它被写入。 +- agent **运行中**调用 `agent.inject()` 时,它会加入已打开的轮次。当前步骤执行 assistant 工具调用期间,已接受的上下文按到达顺序等待该批次结算,随后在每个已记录结果之后追加;即使执行中断,也会在轮次关闭前写入。 +- agent **空闲时**调用 `agent.inject()`,则将 `context/message` 包裹在一个一次性轮次中:`turn/start{trigger:{kind:'injection'}}` → `context/message` → `turn/end{completed}`。一个新的 `injection` 变体加入可合并扩展的 `TurnTriggerMap`。 +- agent loop 每次迭代从日志推导下一个轮次编号(`lastTurnNumber(session) + 1`),而不是维护一个私有计数器,这样空闲注入的一次性轮次不会与下一个真实轮次的编号冲突。 +- `dsh-session/invariant` companion 将该检查注册到 `ctx.invariants`:选中后,在没有打开轮次的情况下追加 `user/message` / `context/message` / `steering/message` 会抛出归因于 `@deepseek-ai/dsh-session` 的 `InvariantError`。 + +可序列化性不变式在同一源码边界处强制执行(`Session.append` 对不可 JSON 序列化的数据抛出异常),因此「什么可以进入日志」现在由一个位置统一管控,而非由下游碰巧在监听的某个后端各自发现。 + +## 曾考虑的替代方案 + +**放宽读取端而非约束生产端**——让 `scanLog` 提交位于已打开轮次之外的事件。否决:一条单一、可检查的生产端规则优于一个更宽松的边界扫描(后者需要同时推理部分轮次*和*轮次间的散落事件)。 + +## 后果 + +轮次现在是*唯一的*持久性/回放边界,因此[会话持久化](2026-06-14-session-persistence.md)的崩溃恢复规则是完备的,而不仅仅是充分的:被中断的最终轮次被关闭(用合成的 `turn/end {interrupted}`),其真实事件得以保留,且零风险将轮次间上下文混入其中,因为不存在轮次间上下文。`scanLog` 保持简洁(最多一个可能未关闭的最终轮次,绝无散落的轮次间事件),空闲时的后台任务通知在持久化 + 恢复后依然存活。 + +代价:空闲时调用 `agent.inject()` 现在写入三行日志而非一行;派生的历史中多出一个仅包含注入上下文(无 assistant 输出)的轮次——`deriveMessages()` 已经纯粹按事件类型派生,因此渲染结果完全相同。`injection` 触发器是一个新的磁盘词汇值;与每次 `SessionEventMap`/`TurnTriggerMap` 的新增一样,它属于冻结格式的一部分。轮次内的事件顺序发生了变化(`turn/start` 现在先于 `user/message`),这对任何断言旧顺序的代码可观测——agent loop 自身的测试是唯一的此类消费方。 + +该规则有意采用生产端强制、开发环境检查的方式,而非读取端容忍的方式:未来的后端(SQLite/WAL)无需额外工作即可继承同样干净的边界,而在轮次外记录事件的插件会在开发环境中大声失败,而非在下次重新加载时静默丢失数据。 + +轮次内检测到的失败在 `turn/end` 之前记录。后续的 flush 失败没有有效的轮次内位置,因此通过 `agent/error` 和日志报告,而非作为会话事件追加。这保持了回放日志的平衡;持久化的运维诊断需要一个独立的遥测通道。 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 new file mode 100644 index 0000000000..6f85d08fe8 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-06-17-filesystem-capability-seam.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-17-filesystem-capability-seam.md: 08e8d52b314eb10e2c7ec444dd61a96d8621e032 +2026-06-17-filesystem-capability-seam.zh.md: 6f4889234516ee134c9873781a874b5f1a3644ac 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 7fa2bde08c..08e8d52b31 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 @@ -2,6 +2,8 @@ Status: implemented +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. 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 new file mode 100644 index 0000000000..6f48892345 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-06-17-filesystem-capability-seam.zh.md @@ -0,0 +1,160 @@ +# Agent Note: 文件系统能力 seam——ctx.fs、本地后端与面向模型的文件系统工具 + +Status: implemented + +[English](2026-06-17-filesystem-capability-seam.md) | 中文 + +## 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。 + +这把三个独立变化的关注点耦合在了一起: + +1. 文件系统契约:插件可以请求哪些操作。 +2. 后端:当前是本地磁盘,未来可能是沙箱/远程/项目作用域的文件系统。 +3. 消费方接口:面向模型的 `read` / `write` / `edit` schema 与结果格式化。 + +如果没有 `ctx.fs` 接口,将本地文件系统访问替换为沙箱或远程后端时,即使面向模型的契约应当保持稳定,工具 schema、演示和提示词引导也会被迫变动。这还使权限/沙箱边界更难推理:一个 `cwd` 选项看起来像沙箱,但除非有显式的后端或 `tools/execute` 策略强制隔离,否则它只是一个基础路径。 + +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。 + +## 决策 + +文件系统访问是一个一等的能力 seam,遵循[能力 seam Agent Note](2026-06-13-capability-seams.md): + +1. `@deepseek-ai/dsh-fs`(`packages/fs/fs`)拥有抽象的 `ctx.fs` 服务、文件系统词汇类型,以及 `fs/*` 策略事件词汇。 +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。 + +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。 + +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。 + +第一个消费方有意仅限文本文件:`dsh-tool-fs` 暴露面向模型的 `read`、`write` 和 `edit` 工具,处理 UTF-8 文本文件。未来的消费方可以添加目录列表、搜索/glob、二进制安全操作、文件监视或更高层的项目操作,只要 `ctx.fs` 上存在所需能力,就无需改动本地后端包。直接目录列表后来由[为文件系统 seam 添加直接目录列举能力](2026-07-03-filesystem-directory-listing-seam.md)添加。 + +文件系统权限和沙箱并非此拆分所隐含。本地后端从其配置的基目录解析相对路径,但隔离策略是独立的决策:要么由更严格的 `ctx.fs` 实现强制执行,要么由权限/沙箱插件包装 `tools/execute` 并在调用到达消费方之前否决。 + +读后写/编辑与观测状态属于 `dsh-fs-policy`,而非 `ctx.fs`。通过 `fs/*` 事件门控,策略按不透明 actor 记录版本,并提供可选的变更期望;提供方原子性地强制新鲜度。`dsh-tool-fs` 发出事件但不依赖策略。见[拆分文件系统 seam](../simplification/2026-06-26-fsspec-style-fs-seam.md)和[事件门控插件](2026-06-26-file-context-as-event-gate.md) Agent Note。 + +## 包拓扑 + +文件系统 seam 使用与 bash 三件套相同的依赖方向: + +```text +@deepseek-ai/dsh-tool-fs --depends on--> @deepseek-ai/dsh-fs <--depends on-- @deepseek-ai/dsh-fs-local + consumer interface implementation +``` + +`@deepseek-ai/dsh-fs` 仅依赖 `cordis` 加上来自 `@deepseek-ai/dsh-llm` 的仓库级 `HarnessError` 基类。它声明 `ctx.fs` 键、抽象 `FileSystem` 服务、后端和消费方共享的词汇类型、文件系统错误词汇,以及 `fs/*` 策略事件词汇。它不持有观测状态存储,也不持有 owner 推导形态;事件传递一个不透明的 `object` actor,提供方从不读取它,`dsh-fs-policy` 插件在这些事件之上拥有 owner 推导形态和观测状态存储。 + +`@deepseek-ai/dsh-fs-local` 依赖 `@deepseek-ai/dsh-fs` 和 `cordis`。它继承 `FileSystem`,将自身注册为 `ctx.fs`,拥有本地后端配置(如基目录),并包含所有直接的 `node:fs` / `node:path` 访问。它不持有观测状态存储——新鲜度是后端铸造、策略插件记录的版本令牌。 + +`@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。 + +## `ctx.fs` 契约 + +`@deepseek-ai/dsh-fs` 拥有一个语义文件系统服务。它比 `readFile` / `writeFile` 更高层,这样 `tool-fs` 就不必重新实现路径解析、版本管理、文本解码、二进制拒绝、分页、原子替换、符号链接行为或字面编辑语义。 + +该接口涵盖以下语义操作: + +- 将模型/插件提供的路径解析为后端定义的目标。 +- 获取目标元数据而不读取文件内容。 +- 从目标读取有界的 UTF-8 文本页。 +- 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: + +- 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<owner, Map<targetKey, version>>`;`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。) + +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。 + +解析后的目标必须至少暴露三个概念: + +- 原始输入路径,用于诊断。 +- 不透明的 `targetKey`,用于陈旧守护和文件状态查找。本地后端可能使用类似 realpath 的键;远程后端可能使用工作区 URI 或文件 id。消费方禁止解析或假设它是本地绝对路径。 +- `displayPath`,用于面向模型/UI 的输出。根据后端不同,它可能是本地绝对路径、工作区相对路径或远程 URI。 + +读取和变更结果必须包含不透明的文件 `version`。本地后端从 bigint stat 元数据(`dev`、`ino`、`size`、`mtimeNs` 和 `ctimeNs`)派生令牌,因此同大小重写和 inode 替换都会可靠地使消费方失效;远程后端可以使用 revision id 或类似 hash 的令牌。`dsh-fs-policy` 插件记录版本用于陈旧检查;消费方可以展示相关元数据但禁止解释版本令牌。 + +提供方返回已解码的文本:`readText` 返回整个常规文本文件,`streamText` 为大文件流式传输相同的文本语义。两者负责常规文件检查;有界的行/输出处理不是它们的职责——行窗口化、带行号渲染和总行数统计位于执行器(`dsh-tool-fs`)中,执行器通过 `ctx.fs` 读取并渲染面向模型的窗口。提供方负责 UTF-8 解码和二进制/NUL 拒绝;它不知道行窗口或视图。 + +观测状态记录不在 `ctx.fs` 上:成功读取后,执行器发出 `fs/observed`,`dsh-fs-policy` 插件为推导出的 owner 记录 `{ version }`。没有 `full`/`partial` 视图——任何窗口的读取都记录版本,新鲜度(而非视图完整性)授权后续的写入/编辑。 + +全文件写入创建或替换 UTF-8 文本文件。后端在支持且有文档说明时可以创建父目录。已有的非常规目标被拒绝。`writeText` 接受一个可选期望:`createIfAbsent` 创建缺失的目标并拒绝已存在的(报 `FS_NOT_OBSERVED`,这是策略为未观测 owner 使用的路径);`replaceIfVersion` 仅在目标处于观测版本时替换,否则报 `FS_STALE_VERSION`;省略期望则为无条件的裸提供方创建或覆盖。策略插件根据 owner 的观测状态选择提供哪个期望。 + +字面编辑是提供方原语(`editText`),而非在 `tool-fs` 中由读取加写入组合而成。字面匹配、重复匹配拒绝、CRLF 保留、二进制拒绝、可选的陈旧版本检查和原子读-改-写必须一起留在后端的变更临界区内。`editText` 接受相同的可选版本期望;陈旧检查在字面匹配之前运行,因此基于旧读取的编辑会报 `FS_STALE_VERSION`。远程后端可以将编辑实现为原生的 compare-and-edit 操作;消费方不强制本地风格的组合。 + +策略插件(而非 `ctx.fs`)对先前观测进行门控:`edit` 要求 owner 有先前观测(否则报 `FS_NOT_OBSERVED`),记录的版本作为 CAS 基础传给 `editText`。在策略插件缺席时,`ctx.fs` 本身是一个完整的无约束 seam(无条件写入/编辑);工具从不与策略方法耦合。 + +文件系统契约失败以 `FsError extends HarnessError` 抛出,工具注册表将其转换为带结构化 `{ name, code }` 元数据的 `isError` 工具结果。`dsh-fs` 拥有此词汇,而非由每个工具各自发明消息。错误码包括 `FS_NOT_FOUND`、`FS_NOT_TEXT`、`FS_STALE_VERSION`、`FS_NOT_OBSERVED`、`FS_NOT_REGULAR_FILE`、`FS_AMBIGUOUS_EDIT`、`FS_EDIT_NOT_FOUND` 和 `FS_ABORTED`。(早期草案包含 `FS_PARTIAL_OBSERVATION`;基于新鲜度的授权没有 partial/full 区分,因此已删除。目录列表相关的错误码后来由[为文件系统 seam 添加直接目录列举能力](2026-07-03-filesystem-directory-listing-seam.md)添加。) + +## 工具消费方行为 + +`@deepseek-ai/dsh-tool-fs` 是面向模型的消费方。它拥有工具名称、JSON Schema、模型边界的参数校验、提示词段落和结果格式化。它不拥有文件系统执行。 + +第一个工具套件包含: + +- `read`:检查一个 UTF-8 文本文件并返回带行号的内容与分页引导。 +- `write`:创建或完全替换一个 UTF-8 文本文件。 +- `edit`:通过替换字面文本更新一个已有的 UTF-8 文本文件,默认要求唯一匹配,并允许显式的全部替换模式。 + +每个工具遵循相同的执行形态: + +1. 校验并规范化模型参数。 +2. 调用相应的 `ctx.fs` 操作。 +3. 将结果格式化为面向模型的 `ContentBlock[]`。 +4. 让抛出的后端/工具错误流经 `ToolRegistry.execute()`,由其转换为 `isError` 工具结果。 + +该包通过 `ctx.systemPrompt.section(...)` 注册提示词引导,通过 `ctx.tools.register(...)` 注册 schema。工具 schema 仍通过 `SystemPrompt.assemble()` 和 `ToolRegistry.schemas()` 流入正常的提示词组装路径;无需改动 agent loop(智能体循环)。 + +工具包在后端变化时保持面向模型的契约稳定:本地后端和远程后端内部可能以不同方式解析路径,但 `read` / `write` / `edit` schema 不会仅因后端变化而改变。 + +默认部署要求在用 `write` 或 `edit` 更新已有文件之前先 `read`。`tool-fs` 不通过检查是否运行过名为 `read` 的工具来实现这一点:它分发 `fs/write-intent`/`fs/edit-intent` 事件(将执行上下文作为不透明 actor 传递),`dsh-fs-policy` 插件推导 owner、对先前观测进行门控并提供版本期望。任何窗口化读取都能授权后续的写入/编辑,只要文件未变。用 `write` 创建新文件不要求先前观测。 + +根插件通过组合各工具的注册辅助函数来注册完整套件。它注入 `fs`、`tools` 和 `systemPrompt`。 + +## 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。 + +本仓库曾踩过的防御性模式类别被直接固定: + +- **原子写入临时文件安全。** 写入/编辑通过目标旁边一个私有随机 `0700` 目录中的独占 owner-only(`'wx'`、`0o600`)临时文件暂存,失败时清理,最后原子 rename——与 bash 溢出文件规则一致,因为可预测的 world-readable 临时路径招致符号链接竞争和信息泄露。测试断言权限,并断言已存在的临时路径不会被覆盖;此原语是 seam 的常设要求。 +- **通过符号链接的 `targetKey` 同一性。** 两个输入路径解析到同一 realpath 时共享一个观测状态条目:通过路径 A 的 `read` 满足通过符号链接路径 B 的 `edit` 的读后编辑守护,通过一个路径的陈旧写入可通过另一个路径检测到。 +- **并发/陈旧竞争。** 对同一目标的两个并发写入/编辑操作确定性地收敛——一个成功,另一个被 `FS_STALE_VERSION` 拒绝——成功的编辑刷新记录状态,使同一 owner 的下一次编辑可以继续。 +- **HMR(热模块替换)安全与 dispose(资源释放)。** dispose 后端的 fiber 会撤回 `ctx.fs` 提供方;后续的提供方以无继承状态启动。 + +## 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。 +- **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 + +**`cwd` 可能被误认为沙箱。** 本地后端的基目录是解析默认值,而非自动的隔离边界。如果需要隔离,必须由后端契约或 `tools/execute` 上的权限/沙箱插件强制执行。 + +**接口可能变得过于本地化。** 如果 `ctx.fs` 返回 `absolutePath` 之类的字段,远程、沙箱或虚拟后端会变得尴尬。契约应暴露显示元数据,而不要求消费方理解宿主路径。 + +**接口可能变得过于薄。** 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。 + +**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。 + +**`resolve` 然后操作的形态每次调用多一次往返。** 每个工具可能先将路径解析为 `FsTarget`,再以单独的 `ctx.fs` 调用发起读取/写入/编辑。对本地后端来说这可以忽略(解析是内存中的路径规范化),但远程/沙箱后端可能将每步变成独立请求,使单次 `read` 变为两次网络往返。往返开销重要的后端可以在内部缓存或折叠解析,同时保持可观测契约不变。 + +**观测状态持久化被推迟。** 观测状态存在于内存中(`dsh-fs-policy` 内部的 `WeakMap`),因此恢复的会话保守地要求文件在写入/编辑前重新读取,直到未来的会话事件或持久化机制使观测可回放。 + +**错误码成为 seam 的一部分。** `FsError` 错误码使陈旧版本和观测失败可通过既有的结构化错误分类体系进行机器路由。代价是 `dsh-fs` 从 `dsh-llm` 导入共享的 `HarnessError` 基类;该依赖是有意为之且限于错误词汇。 + +**包拆分的成本前置。** 三包拆分在只有一个后端时就增加了样板代码。这是有意为之:文件系统访问是可能的沙箱/远程边界,在面向模型的工具发布后再改包接口代价更高。 diff --git a/.agents/notes/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.i18n.yaml new file mode 100644 index 0000000000..8c6edb72a9 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-18-agent-lifecycle-and-ownership-seams.md: 70ebf1c6de97cb14e27377ec1f9bac18fc0766a6 +2026-06-18-agent-lifecycle-and-ownership-seams.zh.md: 54d174aa325384f7c7492f072f10954f0b1d08c9 diff --git a/.agents/notes/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.md b/.agents/notes/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.md index 3d84c8074b..70ebf1c6de 100644 --- a/.agents/notes/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.md +++ b/.agents/notes/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-06-18-agent-lifecycle-and-ownership-seams.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. diff --git a/.agents/notes/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.zh.md b/.agents/notes/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.zh.md new file mode 100644 index 0000000000..54d174aa32 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.zh.md @@ -0,0 +1,50 @@ +# Agent Note: Agent 生命周期与所有权 seam + +Status: implemented + +[English](2026-06-18-agent-lifecycle-and-ownership-seams.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。 + +## 决策 + +三个 seam: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?)` + +`Agent` 接口新增 `cancel()` 动词——唯一的公开停止原语。(它最初与范围更窄、仅作用于步骤的 `abort()` 一同交付;后者后来因无人使用而移除,使 `cancel()` 成为唯一公开的停止工作方式。)它清空 inbox 的 queued + steering FIFO,在存在活跃轮次时中止它,并保留一个不带 cause 的 pre-run 标记,使在取得所有权前被取消的提示词永不运行,而后来的提示词仍保持独立。有效调用会在清空或中止前发出 `agent/cancel-requested`,携带类型化的 `user | parent` cause;空闲取消不发出任何事件,也不会使下一条提示词搁浅。`whenIdle()` 会在取消后达到完全停稳,ACP 的 `session/cancel` 映射到 `user`。[显式轮次取消决策](2026-07-16-explicit-turn-cancellation.md)拥有当前的 cause、signal 生命周期与协作式结算契约。 + +### 2. `AgentHandle` 异步释放器 + +`ctx.agents.create`/`resume`(以及 `AgentFactory` 接口)返回 `AgentHandle = { agent: Agent; dispose(): Promise<void> }`。释放器是一种**消费方能力**——仅持有裸 `Agent` 的注册表观察者无法将其拆除。调用方 fiber 和已注册的 factory 提供方是结构上的共同所有者:调用方卸载强制结构化所有权,而提供方卸载必须停止旧实例,因为其实例作用域的依赖 surface 通过该提供方解析。三条路径都会进入同一个 memoize 的拆除过程:停止循环、等待其退出与空闲刷写完成(完全停稳,而非仅把状态翻转为 `disposed`)、分离 agent、分离其会话,然后解除其 scope。每个公开 ID 在其精确注册表条目分离时变得可复用;不存在独立的保留释放阶段。由配置创建的 agent 已归 `AgentLoop` fiber 所有(handle 被丢弃)。ACP 在其 `SessionRecord` 中保存每个会话的释放器,并在断连/拆除时运行它,因此单纯的客户端断连不会留下已注册 agent 或会话存储条目——即使 `session/load` 与拆除竞争(刚恢复的 handle 会在 closed-guard 抛出前释放)。 + +**拆除顺序对持久性至关重要**,实现将会话生命周期折叠进 agent 的单个复合 Cordis effect(`SessionStore.prepare`/`enter`/`announce`,取代兄弟 effect 拆分)。fiber 卸载会并发释放兄弟 effect(`Promise.all`),这会让会话存储的 append 发布钩子移除与循环关闭时的 `session/flush` 竞争,从而丢失关闭的 `turn/end`;在一个 effect 内,释放器作为有序的 LIFO 链运行(停止循环 + `await agent.done` 在会话分离之前),因此无论 handle 的 `dispose()` 还是 fiber 卸载,都会捕获循环的最终刷写。被隔离的 `agent/disposed` 和 `session/disposed` 通知无法拒绝该链或跳过后续拆除。 + +### 3. Bash seam 中的所有者令牌 + +后台任务所有权从 `tool-bash` 插件本地的 `Map<string, Agent>` 移入执行器。`BashExecRequest` 新增可选的 `owner?: string`;解析后的 `BashExecSpec` 将其作为必需但可空的 `owner: string | undefined` 携带(被遗忘的 owner 是可见的 `undefined`,而非静默缺失的属性)。执行器把 token 存在任务上,并通过新的 `BashExecutor.ownerOf(id): string | undefined` seam 暴露它(不放在公开的 `BashTask` 上——只有一条读取路径,没有冗余 API)。`tool-bash` 完全删除其 `Map`:它在 `start` 时将 `exec.agent?.id`(共享的注册表/会话 id)盖章为 owner,`bash_output`/`bash_kill` 则以 `!== undefined` 语义把 `ctx.bash.ownerOf(id)` 与调用方 token 比较(空字符串 token 仍是真实 owner)。完成通知通过扫描 `ctx.get('agents')?.list()` 查找 `agent.id === ownerToken` 的存活 agent(经 `ctx.get` 读取——`onTaskDone` 运行在 bash fiber 这一外部 fiber 上,直接使用 `ctx.agents` proxy 会抛异常)。由于所有权现在存活在执行器的任务上(随 `dsh-bash` fiber dispose),它能跨越 `tool-bash` HMR 重载,关闭旧的 `XXX(tool-bash-owner-hmr)` 缺口。(`onTaskDone` 监听器仍受 `tool-bash` 的 `apply` effect 约束,因此落在重载间隙的完成仍会丢失一条通知——既有的重载间隙丢失——但所有权隔离本身已经不受 HMR 影响。) + +## 验证 + +以下不变式已经成立,并由测试固定: + +- ACP 断连/会话关闭后,不留下该会话的任何已注册 agent 或会话存储条目,即使 `session/load` 与拆除竞争。 +- 已入队的提示词启动前执行 `session/cancel`,能阻止该提示词运行;后来接受的提示词仍是独立的已入队轮次。 +- `tool-bash` HMR 重载不会使另一个会话能够读取或终止已有的后台任务(所有权保留在执行器上)。 +- 既有的非 ACP 演示无需显式管理 handle 仍能工作;由配置创建的 agent 仍归 `AgentLoop` 插件 fiber 所有。 + +## 会话所有者令牌在存活 agent 中唯一 + +bash 所有者 token 比较依赖共享的 `Agent.id`/`SessionId` 在存活 agent 中唯一。并发的同 ID 操作可以都私下准备,但发布会依次进入会话和 agent;`SessionStore.enter()` 拒绝重复的存活会话 id,每个失败事务都回滚自己的私有状态。因此程序化调用方无法发布两个共享同一会话 token 的存活 agent。访问*策略*(token 比较)留在消费方 `tool-bash`;bash seam 只存储不透明的 `owner` 字符串且从不解释它——这是正确的接口/实现/消费方拆分。 + +## 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。 +- **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))。 + +## 后果 + +本变更有意触及公开接口(`Agent`、`AgentFactory`、bash seam),而非作为 ACP 的局部补丁。同步 `Agent.send()` 的简洁易用性得以保留;异步生命周期路径是增量添加的,供需要它的所有者使用。 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 new file mode 100644 index 0000000000..4946fc219a --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-06-18-session-surface.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-18-session-surface.md: 80034881d0112076759a68737b5931c8ff659d15 +2026-06-18-session-surface.zh.md: 26a3119faf0b6988049a7599ea9551a8ae65d63d 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 f1297b1f05..80034881d0 100644 --- a/.agents/notes/implemented/architecture/2026-06-18-session-surface.md +++ b/.agents/notes/implemented/architecture/2026-06-18-session-surface.md @@ -2,6 +2,8 @@ Status: implemented +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()`. 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 new file mode 100644 index 0000000000..26a3119faf --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-06-18-session-surface.zh.md @@ -0,0 +1,73 @@ +# Agent Note: 会话 surface:事件日志上的有序投影 + +Status: implemented + +[English](2026-06-18-session-surface.md) | 中文 + +## 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()`。 + +## 决策 + +新增一个 **surface**:事件 seq 的派生、缓存有序投影(即产出 LLM(大语言模型)消息的事件子集),通过事件日志中的 `surfaceOp` 标记维护。 + +### `SessionEvent` 新增两个顶层字段 + +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。 +- **`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 + +```ts +export type SurfaceOp = + | 'append' // normal tail append + | { op: 'replace'; start: number; end: number } // shadow [start, end] inclusive +``` + +1. **Append**:在尾部追加新事件的 seq。`user/message`、`assistant/message`、`tool/result`、`context/message`、`steering/message` 使用此操作。agent loop(智能体循环)在所有此类追加上传入 `surfaceOp: 'append'`,并在适用时记录 `sourceEventSeqs`:每个成功的 `assistant/message` 都记录完整的 `assistant/chunk` 来源集合(包括 `[]`),而 `tool/result` 记录其 `tool/call` 来源。 + +2. **Replace**:移除从 `start` 到 `end`(两端包含)的条目,并在其位置插入新事件的 seq。`start` 和 `end` 都必须存在于当前 surface;`start === end` 表示替换单个条目。该事件的 `sourceEventSeqs` 必须包含所有被遮蔽的 surface seq。被遮蔽的事件仍留在日志中,但不再出现在 surface 上。 + +### SurfaceManager:基于增量,而非全量重建 + +一个 `Session` 拥有一个 `SurfaceManager`,后者维护事件 seq 的有序 `number[]`。管理器会在提交前校验每个种子或追加候选项而不应用它,然后只处理上次同步之后已经提交的事件,而不重新扫描整个日志。`Session.surface` 通过只读的 `SessionSurface` 契约暴露同一个管理器,因此接纳、派生历史、压缩与工作区上下文共享同一份增量状态。Replace 按数组位置找到两端都包含的端点,并把替换 seq splice 到该范围;不会用第二个管理器、链接对象或 seq 到节点的 map 来重复表达顺序。 + +无新事件时增量处理为 O(1),有新事件到达时为 O(新事件数)。 + +`deriveMessages()` 在存在 surface 标记时使用 surface,对没有标记的会话回退到既有的线性扫描(向后兼容)。 + +### 持久化 + +新字段作为顶层 JSON 属性序列化。JSONL 后端无需任何改动:`JSON.stringify`/`JSON.parse` 透明地保留一切。SQLite 后端的 `events` 表新增两个可空 TEXT 列(`source_event_seqs`、`surface_op`)。磁盘上的 `SCHEMA_VERSION` 递增以反映列集变化,并且按照预发布的 bump-and-reject 策略,由其他构建写入的数据库在打开时被拒绝而非迁移(没有需要升级的持久化用户数据)。会话格式 `version` 固定为 `SESSION_FORMAT_VERSION = 0`(「不稳定/预发布」立场):可选的 surface 字段被吸收而不递增版本号。 + +### 崩溃恢复 + +`repair.ts` 模块在崩溃后为孤立的工具调用合成 `tool/result` 闭合事件。这些闭合事件携带 `surfaceOp: 'append'` 和指向孤立 `tool/call` 事件的 `sourceEventSeqs`,确保重建的 surface 有效。 + +### 不变式 + +`Session` 在始终启用的 seed/append 边界校验 `sourceEventSeqs` 与 `surfaceOp`:只有 `assistant/message` 可以使用空的溯源列表;引用必须唯一、更早且已知;替换端点必须存在于 surface 顺序中;溯源必须覆盖每个被遮蔽的节点。这些是单记录接纳与存储投影规则,不是可选的不变式服务贡献。 + +每个 surface 可达事件都必须携带 `surfaceOp`,否则它将从派生历史中消失。类型化的 `append` 重载对字面事件类型强制执行此规则;`append` 和种子构造函数中的运行时检查覆盖宽化联合类型和加载的日志。按照预发布格式策略,无效的种子被拒绝而非升级。 + +## 曾考虑的替代方案 + +- **逐插件的 `agent/request` 包装**(surface 之前的历史操纵模式):监听器排序脆弱、无法持久记录改动内容,且每种新操纵都迫使核心 `deriveMessages()` 再次修改。 +- **半开区间 `[start, endExclusive)` 的 replace 范围**:否决。端点由 surface 事件 seq 命名,单条目替换(`start === end`)在闭区间语义下读起来更自然。 +- **链接节点对象加 seq map**:否决。生产代码不读取前驱链接,唯一的后继用途就是数组中的下一个位置,而替换本来就需要线性 `indexOf` 查找。单个 seq 数组在保留相同渐进复杂度的同时,只留下一个需要校验的表示。 +- **脏标记后全量重建**替代增量处理:在会话生命周期内为 O(N²),每次单事件追加都要重新扫描所有先前事件。 + +## 后果 + +- **`packages/core/session`**:`surface.ts`(`SurfaceManager`)维护一个用于候选接纳和实时投影的有序 seq 数组;`SessionSurface` 是其只读公共视图。`SurfaceOp`/`SurfaceIntent` 与顶层会话事件字段记录条目如何加入它。`append()` 要求 surface 事件携带 `SurfaceIntent`,`deriveMessages()` 以遍历 surface 作为唯一派生路径,`repair.ts` 则发出 surface 感知的闭合事件。种子构造函数拒绝缺少 `surfaceOp` 标记的 surface 可达种子事件(见「不变式」一节)。 +- **`packages/core/agent-loop`**:所有 surface 可达的追加操作传入 surface 选项。收集分片 seq 用于 `assistant/message` 溯源;捕获 `tool/call` seq 用于 `tool/result` 溯源。 +- **`packages/session-persistence/session-persistence-sqlite`**:`events` 表新增两个可空 TEXT 列(`source_event_seqs`、`surface_op`);`SCHEMA_VERSION` 递增(bump-and-reject,无迁移)。 +- **`packages/session-persistence/session-persistence-jsonl`**:无需改动。 +- **`packages/session-persistence/session-persistence`**:抽象接口不变。 + +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。 + +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。 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 new file mode 100644 index 0000000000..b289d47edd --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-18-shared-persistence-write-coordinator.md: ea9c4fb74f7c1bd68fb62efedd3e1657da96ea65 +2026-06-18-shared-persistence-write-coordinator.zh.md: 3b4dd7b762c2f39a908eabe23e5d734981b5767b 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 48b1bfa45f..ea9c4fb74f 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 @@ -2,6 +2,8 @@ Status: implemented +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. 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 new file mode 100644 index 0000000000..3b4dd7b762 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.zh.md @@ -0,0 +1,47 @@ +# Agent Note: 共享持久化写入协调器 + +Status: implemented + +[English](2026-06-18-shared-persistence-write-coordinator.md) | 中文 + +## 问题 + +`dsh-session-persistence-jsonl` 与 `dsh-session-persistence-sqlite` 有意在不同存储介质上证明同一份 `SessionPersistence` 契约,但它们重复实现了写入路径编排:每会话状态、`session/created` 接管、后端特定的前缀读取、write-behind 控制、按 id 串行执行操作、HMR(热模块替换)种子注入与 dispose(资源释放)排空。纯粹的种子前缀碰撞检查与可序列化守卫已迁入 seam 包;剩余的编排仍然对正确性要求很高,且同样的修复被应用了两次。唯一的差异在于存储原语(写字节 vs. INSERT 行)。 + +## 决策 + +将一个后端无关的 `PersistenceCoordinator` 提取到 `dsh-session-persistence` 中。协调器统一拥有编排逻辑;每个第一方后端组合一个协调器实例(`new PersistenceCoordinator(ctx, this)`),实现一个小型 `PersistenceBackend` 钩子接口,并将其有状态的公开方法(`create`/`append`/`load`/`inspect`)委托给协调器。由后端拥有的元数据与修订版本列举会绕过协调器。 + +组合,而非继承。协调器是后端持有的具体类,不是后端继承的基类。本 Agent Note 的风险——「协调器不得让非常规后端与继承层级作斗争」——由此规避:后端只暴露钩子,无法触及协调器的私有编排状态。第三方后端仍然可以完全不使用协调器、直接实现抽象服务,包括供读模型使用、不修改状态的 `inspect` 契约。 + +协调器为每个确切的存活 `Session` 持有一个控制器;该控制器统合初始化、待处理事件与共享 flush promise。每个 `session/event` 都会立即启动排空,而 `session/flush` 只观察完全停稳,不会发起常规写入路径。[flush 控制器简化](../simplification/2026-07-23-collapse-persistence-flush-state.md)定义该生命周期。 + +协调器通过 `session/disposed` 退役会话:它等待控制器完成初始化和当前 flush,串行执行最后一次排空,且仅在成功后才移除控制器与其拥有的每 id 状态。失败时保持控制器可被找到,以供后端 teardown(拆除)重试。每个 id 的已结算链尾仅在其仍是当前链尾时才移除自身,因此旧操作完成后不会抹除同一 id 的新操作。后端 teardown 会注销写入路径监听器、flush 每个剩余的控制器、等待所有按 id 串行化的操作,最后关闭后端。 + +### 钩子接口(`PersistenceBackend<TornMarker>`) + +五个必需成员加一个可选的生命周期钩子,构成协调器与存储之间唯一的边界: + +- `name`——后端标签,用于 dispose 失败时的 `AggregateError`。 +- `loadStored(id)`——按 id 跨所有存储范围读取一个已存储前缀(JSONL 的所有 cwd bucket;SQLite 的 id 全局唯一)。恢复/加载、不修改状态的检查、存活会话接管与创建碰撞探测共用此查找。协调器会断言返回的 id,并在修复或发布状态之前拒绝已存储记录与存活会话的 cwd 不匹配。 +- `appendBatch(meta, events, isMaterialized)`——持久追加一个连续批次,在尚未物化时原子地惰性物化会话(物化写入与首批事件必须一起提交——崩溃不得留下一个已物化但为空的会话;这就是为什么没有单独的 `materialize` 钩子)。 +- `commitRepair(meta, tornMarker, closers)`——使崩溃修复持久化:截断损坏的尾部(当且仅当 `tornMarker !== undefined`)并追加 `closers`。**不要求原子性**——JSONL 合理地分两步 fsync(先截断再追加),SQLite 在一个事务中完成 DELETE+INSERT。用于 `load`(截断 + 合成 closers)和 live-adoption(仅截断,`closers = []`)。 +- `list()`——列出所有已存储的元数据。 +- `close?()`——可选的生命周期清理(SQLite 关闭 db 句柄;JSONL 省略),在 dispose effect 中于排空至完全停稳之后被 await,因此 close 失败不会掩盖排空错误。 + +### 不透明的 torn marker + +保持 seam 整洁的唯一设计选择:崩溃修复中「损坏尾部在哪里」的 token 对协调器是不透明的。协调器计算合成 closers(它拥有来自 `dsh-session` 的 `interruptedTurnClosers`),但它只测试 `tornMarker !== undefined` 并将值原样传回 `commitRepair`——从不检视其内容。每个后端选择自己的 marker 类型:JSONL 携带要截断到的字节偏移,以及从不完整最终帧中解码出的任何完整事件;SQLite 则携带要从其开始删除的 seq。协调器因此既不了解字节长度,也不了解帧恢复状态。 + +## 测试 + +共享的 `runPersistenceContract`(公开 API 契约)为每个后端运行,并证明在 `load` 执行恢复之前,`inspect` 会保持被中断的日志与修订版本不变。`runCoordinatorContract`(`tests/coordinator-contract.ts`)通过内存参考实现、JSONL 与 SQLite 覆盖接管、HMR、碰撞、会话与后端 dispose 排空,以及崩溃尾部修复。协调器专属测试覆盖立即执行的后续批次、存活控制器清理、同 id 链尾竞态、排空失败重试与关闭顺序。各后端自身的测试规格只保留存储机制。每个真实后端都有一个经由协调器的崩溃尾部修复测试,以覆盖不透明 marker 分支,因为契约中的崩溃用例会产生合成 closers,却不会产生 torn marker。 + +## 曾考虑的替代方案 + +- **后端继承的基类**——否决,改用组合:后端只暴露钩子,无法触及协调器的私有编排状态,且第三方后端仍可完全不使用协调器、直接实现抽象服务。 +- **更宽的钩子面**——每个候选钩子都被折叠掉:没有限定存储范围的实时查找,因为 `loadStored` 加上协调器的 cwd 检查即可维持碰撞边界;没有存储定位器泛型,因为经验证的 JSONL 元数据可还原其路径,而 SQLite 已按 id 绑定;没有单独的 `materialize` 钩子,因为首批事件必须与物化原子提交;没有单独的创建碰撞探测,因为它就是 `loadStored(id) !== undefined`;`list()` 也不经由协调器透传,因为列举不需要任何编排。 + +## 后果 + +协调器增加了一层间接、一个不透明的 torn marker 和脱离会话生命周期的退役任务,但将此前每个后端重复的、对正确性要求很高的编排逻辑集中到一处。会话 dispose 仍是仅观察事件,因此会话所有者不会等待持久化退役;协调器会收容失败、在存活控制器中保留待处理事件,并以后端 teardown 为完全停稳边界。其钩子面保持窄小:标识校验、接管、碰撞检查与不修改状态的检查共用 `loadStored`;物化保持在 `appendBatch` 内原子完成;列举绕过协调器。读模型使用 `inspect` 而非 `load`,因此观察已持久化但仍开放的轮次时,不会因提交中断 closers 而与新的存活所有者产生竞态。新后端只需实现存储原语,而无需复制立即写入生命周期。 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 new file mode 100644 index 0000000000..35c9875149 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-06-20-branded-ids.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-20-branded-ids.md: 93bab1d47c793cc4dd1f1d19fa3af22d1721be29 +2026-06-20-branded-ids.zh.md: 6cc8a45717b547614a873d3f13c54c3950484a22 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 e7a3110fce..93bab1d47c 100644 --- a/.agents/notes/implemented/architecture/2026-06-20-branded-ids.md +++ b/.agents/notes/implemented/architecture/2026-06-20-branded-ids.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-06-20-branded-ids.zh.md) + ## Problem 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<B> = 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. 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 new file mode 100644 index 0000000000..6cc8a45717 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-06-20-branded-ids.zh.md @@ -0,0 +1,69 @@ +# Agent Note: 在所有应有之处使用 branded ID + +Status: implemented + +[English](2026-06-20-branded-ids.md) | 中文 + +## 问题 + +harness 使用 `Branded<B> = string & { readonly [BRAND]: B }` 机制,为 `CallId`(`packages/llm/llm/src/brand.ts`)和 agent/会话共享的 `SessionId`(`packages/core/session/src/types.ts`)做 brand 处理;该机制由纯类型包(package) `@deepseek-ai/dsh-brand` 拥有,位于 `packages/util/brand/`,见其 [README](../../../../packages/util/brand/README.md),并为每个类型提供零开销的 cast 工厂。`dsh-brand` 还声明了治理策略:*「Branding 用于跨包边界且可能被混淆的 id;不是每个 string 都需要 brand。」* 这条策略是正确的;问题在于它只落实了一半。两处缺口使得结构相同但语义错误的 string 今天仍能通过类型检查器。 + +**缺口 1:bash seam 中未 brand 的跨边界 ID。** 后台 task id 是普通 `string`:`BashTask.id: string`(`packages/bash/bash/src/types.ts`),作为 `string` 贯穿整个执行器 seam(`packages/bash/bash/src/index.ts` 中的 `BashExecutor.get`/`ownerOf`/`readOutput`/`kill(id: string)`),再由面向模型的工具以 `string` 校验并传递(`validateTaskId`、`assertTaskAccess`、`packages/bash/tool-bash/src/index.ts` 中 `task_id` 的 schema 参数)。它由每执行器计数器生成——`packages/bash/bash-local/src/index.ts` 中的 `` `bash-${this.nextTaskId++}` ``——其形状与 `SessionId` 的默认值**完全相同,都是 `name-N`**(`packages/core/session/src/index.ts` 中的 `` `session-${++counter}` ``)。bash task id 和会话 id 在调用点轻易就能互换,而编译器毫无反应。这是用户询问的核心案例,并且它是面向模型的 id(模型会把 `task_id` 传回 `bash_output`/`bash_kill`),所以该混淆可由不受信任的输入触达。 + +bash **owner token** 是相关的子情形:`BashExecRequest.owner?: string` 和 `BashExecSpec.owner: string | undefined`(`packages/bash/bash/src/types.ts`)被文档描述为刻意*不透明*的隔离键,但在所有实际调用方中,该值就是所属 agent(智能体)共享的 `Agent.id`/`SessionId`(`callerToken = (exec) => exec.agent?.id`,位于 `packages/bash/tool-bash/src/index.ts`),只是披着另一个 seam 本地名称。它被用于访问控制比较(`owner !== callerToken(exec)`),因此一个不匹配但类型正确的 string 在此处就是跨会话隔离 bug,而当前类型系统无法捕获。这正是[统一 agent/session 标识决策](../simplification/2026-06-20-unify-agent-and-session-id.md)覆盖的共享 id 别名。 + +**缺口 2:*已经 brand* 的 ID 在 seam 处被侵蚀。** 就连 `CallId` 和 `SessionId` 也恰好在最容易混淆的地方退化为裸 `string`:注册表/store 键类型和公开方法参数。代表性位置包括会话存储、agent 注册表(二者都以共享的 `SessionId` 为键)、`ToolPresenter` 的 call-id map、ACP 的会话 id 记录和 loading set,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。 + +- **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)。 + +- **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。) + +- **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<SessionId, Session>`、`Map<SessionId, Agent>`、`get(id: SessionId)`、`Map<CallId, …>`、ACP 的 `SessionId` surface、协调器的 `Map<SessionId, …>`。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。 + +示意形状(工厂模式与已有的三个 brand 完全一致): + +```ts ignore-check +import type { Branded } from '@deepseek-ai/dsh-brand' + +/** A background bash task handle (generated `bash-N` by the local executor). */ +export type BashTaskId = Branded<'BashTaskId'> +export function BashTaskId(id: string): BashTaskId { + return id as BashTaskId +} + +/** A bash task's opaque isolation key — the consumer's owner identity, NOT the bash seam's. */ +export type OwnerToken = Branded<'OwnerToken'> +export function OwnerToken(id: string): OwnerToken { + return id as OwnerToken +} +``` + +## 曾考虑的替代方案 + +### 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。 + +## 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。 +- **`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<string>` 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。 + +## 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。 + +## 后果 + +- **两个接口面的机械性改动。** 传播 brand 涉及 bash seam(接口 + 实现 + 消费方)以及 ACP 会话 id 接口和持久化协调器。改动面广但严重度低:遗漏的位置是编译错误而非静默 bug。变更可观察地为纯类型变更——无快照或 e2e 行为差异。它与[统一 agent/会话标识决策](../simplification/2026-06-20-unify-agent-and-session-id.md)相邻,因为二者都触及会话 id / owner-token 边界;`OwnerToken` 出于上述解耦理由仍与统一后的 id 保持独立。 +- **Brand 不做校验。** Brand 是混淆防护,不是正确性证明:一个*错误的* 会话 id 只要仍是合法的 string,就和以前一样能通过类型检查器。本 Agent Note 不关闭这个缺口(见「不在范围内」)——它只阻止这类*类别*错误:传入错误*种类*的 id。 +- **「在哪里停下」仍是判断题。** 为 `BashTaskId` 加 brand 但不为 `ToolName` 加,为 `OwnerToken` 加但不为 `ModelId` 加,是对哪些 string「可能被混淆」的品味判断。合理的评审者可能想要更多或更少;`brand.ts` 中的策略是裁决依据,本 Agent Note 倾向于面向模型或用于访问控制的 id。 diff --git a/.agents/notes/implemented/architecture/2026-06-20-extract-example-app-packages.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-20-extract-example-app-packages.i18n.yaml new file mode 100644 index 0000000000..35bc3836ff --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-06-20-extract-example-app-packages.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-20-extract-example-app-packages.md: 8e87a7164d9cc4789705b3d8fe83dc4978b4def0 +2026-06-20-extract-example-app-packages.zh.md: bb5bf6a78d749bf2fc0637a48bff4496399a787d diff --git a/.agents/notes/implemented/architecture/2026-06-20-extract-example-app-packages.md b/.agents/notes/implemented/architecture/2026-06-20-extract-example-app-packages.md index 953a977c19..8e87a7164d 100644 --- a/.agents/notes/implemented/architecture/2026-06-20-extract-example-app-packages.md +++ b/.agents/notes/implemented/architecture/2026-06-20-extract-example-app-packages.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-06-20-extract-example-app-packages.zh.md) + ## Problem An example folder is supposed to be *thin* — the variable wiring of a demo, not the demo's machinery. Before this change it was thick. Each example carried a hand-rolled `start.ts` boot bootstrap, an infra preamble (`timer`, and — for the stdio demos — `logger` + `hmr`), nested includes of three shared YAML fragments (`base.yml` / `base-core.yml` / `acp-agent/acp-tail.yml`), and per-example `agent-loop`/persistence/system-prompt config. The actual app — the spine of services every agent needs — was spread across the leaf and those includes. diff --git a/.agents/notes/implemented/architecture/2026-06-20-extract-example-app-packages.zh.md b/.agents/notes/implemented/architecture/2026-06-20-extract-example-app-packages.zh.md new file mode 100644 index 0000000000..bb5bf6a78d --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-06-20-extract-example-app-packages.zh.md @@ -0,0 +1,57 @@ +# Agent Note: 将示例应用提取为独立包 + +Status: implemented + +[English](2026-06-20-extract-example-app-packages.md) | 中文 + +## 问题 + +示例目录本应是*精简的*——只包含演示的可变接线,而非演示的基础设施。在此次变更之前,它是臃肿的。每个示例都携带一份手写的 `start.ts` 启动引导、一段基础设施前导(`timer`,以及 stdio 演示所需的 `logger` + `hmr`(热模块替换))、三个共享 YAML 片段的嵌套引用(`base.yml` / `base-core.yml` / `acp-agent/acp-tail.yml`),还有各示例自身的 `agent-loop`/持久化/系统提示词配置。真正的应用——每个 agent(智能体)都需要的服务主干——散落在叶子配置和那些 include 中。 + +叶子配置还拥有耦合的前门。ACP(Agent Client Protocol)要求 stdout 纯净,并通过 `session/new` 创建 agent;终端应用和 Headless 应用则预创建 `main`,但进程 I/O 契约不同。防止错误组合的唯一屏障是文档中的文字警告,而三个 `start.ts` 文件重复着 Loader 引导和生命周期代码。 + +## 决策 + +每个示例现在**主要是对一个应用包(package)的调用**,沿着既有的[接口 / 实现 / 消费方 seam](2026-06-13-capability-seams.md) 拆分接线:**应用包拥有组合**,叶子 `cordis.yml` 只拥有**可替换的选择**(哪个 LLM(大语言模型)适配器、哪个 bash 执行器、模型、提示词、持久化根目录)。 + +- **`@deepseek-ai/dsh-agent-spine-demo`**([packages/examples/agent-spine-demo](../../../../packages/examples/agent-spine-demo))组合了不含提供方、不含执行器、不含 UI 的主干,并转发 agent loop(智能体循环)的 agent 列表配置。它对具体 loop 的依赖是有意为之,因为该包组合的是主干而非扩展主干;替换 loop 意味着提供另一个 bundle。 +- **`@deepseek-ai/dsh-tui-demo`**、**`@deepseek-ai/dsh-cli-demo`** 和 **`@deepseek-ai/dsh-acp-demo`** 各自内置其进程角色。TUI 包含全屏 UI 和预创建的 `main`;Headless 包含 one-shot driver 和预创建的 `main`;ACP 包含 bridge 且不预创建 agent。三者都包含 JSONL 持久化,并省略 stdout logger。 +- **`start.ts` 已移除。** 每个应用包都暴露一个 bin;`demo:*` 脚本调用它。Loader 引导、`.env` 加载和快速失败守卫位于共享的 [`@deepseek-ai/dsh-app-boot`](../../../../packages/ui/app-boot) 包(在逐文件覆盖率门禁下有单元测试——见[共享应用 bin 的启动胶水](../simplification/2026-07-04-share-app-bin-boot-glue.md));精简的自执行入口由 keyless 的 Loader 路径测试驱动。 +- **每个叶子 `cordis.yml` 精简为**后端、可选产品工具,以及一个承载应用配置的 app 条目。TUI 和 Headless 把模型/会话选择路由到预创建的 agent;ACP 把初始提供方/模型路由到 bridge。 +- **`base.yml`、`base-core.yml` 和 `acp-agent/acp-tail.yml` 已退役**——它们共享的主干现在位于 `dsh-agent-spine-demo` 中。 + +`bash-local` 和 LLM 适配器仍然是**叶子选择**:bundle 提供 `tool-bash`(消费方 schema),叶子选择执行器实现,因此沙箱执行器或回放适配器无需触碰应用即可替换。 + +### 实现修正:`hmr` 保留为叶子条目 + +提案最初将 `hmr` 列入交互式应用内置的前门集群。对照代码验证后发现,将 `hmr` 内置到应用包中会在两个方面与 Cordis 冲突,因此改为作为**叶子 `cordis.yml` 条目**交付: + +1. `@cordisjs/plugin-hmr` 是一个仅限 Loader、仅限子进程的开发插件——它需要活跃的 `loader` 服务及其内部模块访问权限,因此只能在真实的 `demo:*`/bin 子进程中运行,不能在进程内的单元/覆盖率测试层运行。 +2. 进程内测试层(vitest)甚至无法*导入* vendor 的 `hmr` 模块(其 class-decorator `@Inject` 形式在 Vite 的 transform 下会失败),因此一个 `apply` 静态导入了它的包永远无法满足其主函数的逐文件 100% 覆盖率门禁。 + +关键在于,`hmr` 不是 stdout 纯净隐患:ACP 配置中误加该条目不会破坏 JSON-RPC 帧。所有已交付应用都省略 stdout 控制台 logger;stdout 只归应用或协议 driver 所有。 + +## 曾考虑的替代方案 + +### 为什么不继续用共享 YAML include 来管理接线? + +旧的 `base*.yml`/`acp-tail.yml` include 已经去重了*配置*,但 YAML include 无法**封装**前门耦合——它只能在注释中描述,并信任每个叶子遵守。它也无法拥有 `bin`,因此启动胶水一直在三个 `start.ts` 文件中重复。包将「ACP 应用绝不向 stdout 输出日志」从文字警告变成了产物的属性:叶子中不存在可以写错的 logger 条目。 + +## 验证 + +- 示例目录只包含配置、README 和测试:`start.ts`、基础设施前导和共享 YAML include 已移除。 +- `demo:tui`、`demo:headless` 和 `demo:acp` 调用应用包的 bin。 +- 每个新包都有 README 和逐文件 100% 覆盖率;每个应用包还有一个 keyless 的真实 Loader 路径 bin 冒烟测试,用于捕获[事后分析 0001](../../../../docs/postmortem/0001-acp-default-export-drops-inject.md) 中描述的导出形状故障。 +- ACP 回放 transcript(文本记录)保持不变,因为插件集合和加载顺序未改变。 + +## 后果 + +- **裸插件树的教学性。** 主干现在隐藏在 bundle 之后,查看完整树意味着打开 `dsh-agent-spine-demo`。应用包的 README 承担了这份教学职责。 +- **多了一层间接。**「这个演示加载了什么?」从扫描单个 YAML 变成了阅读一个包。 + +## 相关 + +- 取代[使共享示例基础配置与提供方无关](../../rejected/architecture/2026-06-20-providerless-example-base.md):一旦主干移入 `dsh-agent-spine-demo` 且 `base*.yml` 文件被删除,将 `base.yml` 重命名为无提供方核心便不再有意义。 +- 基于[能力 seam](2026-06-13-capability-seams.md)的接口/实现/消费方拆分——后端和展示层保持为叶子选择;主干是共享 bundle。 +- 与[将包重组为模块化层级结构](2026-06-20-package-hierarchy.md)互补:新的 app/core 包按该层级结构归入既有分组(`core` 放可复用的主干 bundle,`ui` 放应用特有的前门)。 +- 后续的[冗余 agent 移除](../simplification/2026-07-20-remove-stdio-and-echo-agents.md)拥有最终的 TUI/Headless 拆分,并移除行式与仅 mock 的叶子。 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 new file mode 100644 index 0000000000..ec8a2059a2 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-06-20-generic-long-running-tool-runtime.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-20-generic-long-running-tool-runtime.md: 25668a6a699576e435670b9580385073f2f036fe +2026-06-20-generic-long-running-tool-runtime.zh.md: 3c214bb4309ea331ae2d4ba73c01df1ded8f40ef 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 f3fe6373ea..25668a6a69 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 @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-06-20-generic-long-running-tool-runtime.zh.md) + ## Problem Background bash originally combined two responsibilities: the bash executor ran processes and also managed task ids, ownership, incremental reads, cancellation, completion listeners, and model-facing control tools. Adding background subagents required the same lifecycle and interaction contract. Implementing that contract independently for every long-running capability would duplicate isolation, cleanup, notification, and prompt behavior while teaching the model a different collect-and-stop protocol for each producer. 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 new file mode 100644 index 0000000000..3c214bb430 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-06-20-generic-long-running-tool-runtime.zh.md @@ -0,0 +1,134 @@ +# Agent Note: 后台任务运行时(`ctx.tasks`)与通用任务控制工具 + +Status: implemented + +[English](2026-06-20-generic-long-running-tool-runtime.md) | 中文 + +## 问题 + +后台 bash 原本兼有两项职责:bash 执行器既运行进程,又管理 task id、所有权、增量读取、取消、完成监听器和面向模型的控制工具。新增后台 subagent 需要相同的生命周期与交互契约。如果每种长时间运行能力都独立实现该契约,就会重复隔离、清理、通知和提示词行为,还会让模型为每种生产方学习不同的收集与停止协议。 + +任务注册表、控制工具与完成通知共同构成一项 harness 功能。bash 和 subagent 只提供执行专属的钩子,不拥有通用任务行为。 + +## 决策 + +`tasks/` 包组拥有后台任务语义: + +- `@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。 + +`TaskService` 是一个具体的进程内服务。TODO(task-service-backend):当第二个后端明确所需生命周期后,将其公共契约与实现分离;systemd 驱动的运行时是一种可能方案,但本 PR(Pull Request)不臆测其持久性、重连、所有权或观察语义。 + +## 运行时契约 + +字面类型见[任务数据结构目录](../../../../docs/core-data-structures/tasks.md)。生产方调用 `ctx.tasks.start()`,传入 kind、label、可选的所属 `Agent`、可选的正数 `outputLimitBytes` 与一个 `run()` 函数。运行时会在调用 `run()` 前完成所有可能失败的预检工作,并且只调用一次。`run()` 返回钩子后,注册过程不会再执行可能失败的步骤而直接提交;生产方无法启动没有可收集 task id 的工作。 + +`outputLimitBytes` 是生产方拥有的呈现策略,而非注册表缓冲区。注册表校验该值,并将其原样投影到 `TaskSnapshot`;通用控制接口添加自身的状态或通知元数据后,再将该上限应用于完整的面向模型输出。省略该值时保持现有接口行为,因此运行时不会向无关的生产方类别施加隐式默认值。 + +面向模型的生产方会在规范成功值中暴露已提交的 id,通常为 `{ kind: 'background', taskId }`;Native 渲染仍可保留便于人类阅读的行文。预先被中止的后台调用会失败,而不是返回空操作,因为不存在可履行所承诺句柄的任务。一旦注册过程发布 id,取消就归任务自身的控制器与任务运行时所有:随后取消生产工具调用不得终止已发布的任务。`task_kill`、所有者资源释放和服务拆除会请求取消;前台执行仍与调用的 `exec.signal` 耦合。 + +生产方钩子定义三项职责: + +- `cancel(reason?)` 同步请求终止,具备幂等性,并且必须使 `done` 完成。 +- `done` 从不拒绝,并且仅在生产方释放任务资源后完成。 +- 可选的 `readOutput()` 返回下一个消费式输出增量。省略该钩子即声明这是最终输出任务,其终止结果来自 `TaskOutcome.output`。 + +状态包括 `running`、`stopping`、`completed`、`killed` 和 `failed`。退出码或停止原因等生产方专属信息放在 `detail` 中,注册表不解释这些信息。任务 kind 构成可合并扩展的字符串联合;task id 带品牌,并按 `<kind>-N` 生成,每个 kind 各有一个计数器。 + +运行时为 `done` 附加一个 continuation,记录第一个终止结果、解决等待方,并逐个调用完成监听器,同时隔离每个监听器的错误。首次结果优先的结算在资源销毁期间至关重要:如果 `cancel` 抛出,运行时会强制将记录标为失败,并警告工作可能遗留,而不是永远等待一个可能永不完成的 promise。后续生产方结果不能覆盖该诊断,也不能重复通知。`cancel` 返回后如果最终未使 `done` 完成,仍会阻塞资源销毁,因为运行时无法区分这种情况与缓慢但有效的停止。 + +任务注册不是生产方工具 fiber 的 effect。因此,重新加载工具或控制接口插件不会终止由 agent(智能体)和后端拥有的工作。任务服务自身释放时会取消所有实时任务,并等待遵守契约的生产方。 + +## 授权与所有者生命周期 + +task id 在运行时全局可见且可预测,因此注册表会授权每次访问。`get`、`read`、`wait` 和 `kill` 接受调用方 `Agent`;`list` 仅返回该调用方可见的任务。有所有者的任务仅允许对应的确切会话访问。无所有者任务向非 agent 调用方开放,并随任务服务一起终止。 + +快照存储所有者的品牌化 `SessionId` 以供授权,生命周期操作则保留确切的实时 `Agent` 实例。这两种身份用途不同:会话相等性授予访问权,精确对象身份决定清理和完成通知的接收方。复用 agent 或会话 id,不能将旧作用域的清理或通知重定向到替代实例。 + +某个所有者的第一个任务会向 `owner.ctx` 附加一个异步 effect。agent 作用域释放时会取消该所有者的实时任务、等待其终止记录,并移除其快照。该 effect 可跨生产方重载存续,并加入 agent 现有的完全停稳边界。任务服务保留 effect disposer,使服务重载可以在全局资源销毁后,从仍然存活的 agent 作用域中分离回调。 + +对于遵守契约的生产方,`AgentHandle.dispose()` 只在所属后台工作停止后解决。需要比 agent 存活更久的工作必须以无所有者方式启动;要跨运行时重启存续,则需另行设计持久任务。 + +## 服务接口 + +`TaskService` 提供: + +- `start(spec)`:经过预检的原子注册。 +- `get(id, caller?)` 和 `list(caller?)`:非消费式快照。 +- `read(id, caller?)`:消费式流增量或幂等的最终结果。 +- `kill(id, caller?, reason?)`:取消。 +- `wait(id, timeoutMs, caller?, signal?)`:有界的终止等待。 +- `onTaskDone(listener)`:effect 作用域内的观察,具有精确所有者投递和监听器隔离。 +- `attachSurface(name)`:控制接口可用性防线。 + +`wait` 在任务完成时返回终止快照,在等待超时时返回实时快照。中止一次等待只取消该次等待。如果结算已经将终止投递分配给该等待方,终止快照仍然优先。等待方在中止时同步注销,因此同一 tick 内的结算无法代表一个什么也未收到的读取方压制完成通知。 + +如果生产方加载时没有任何控制接口,调用方就能启动无法收集或停止的工作。因此,`dsh-tool-tasks` 在其整个生命周期内调用 `attachSurface()`;没有附加接口时,`start()` 会在生产方开始执行前失败。该检查发生在启动时而非插件加载时,因为兄弟插件可能并发激活。自定义的非模型接口可以自行附加,无需让注册表了解工具名称。 + +## 面向模型的控制接口 + +`dsh-tool-tasks` 注册三个与 kind 无关的工具,并使用通用 ACP(Agent Client Protocol)卡片: + +- `task_output(task_id, wait?, timeout_ms?)` 读取输出,并始终追加 `[status: ...]`。流式任务只返回上次读取以来的输出;最终输出任务在结算后返回结果。除非指定 `wait: true`,否则读取不会阻塞;等待超时由插件配置提供默认值并限定上限。等待超时会报告仍在运行的状态,不会停止任务。 +- `task_list()` 将调用方可见的任务返回为 `<id> [<kind>] <status> — <label>`,没有任务时返回 `(no background tasks)`。 +- `task_kill(task_id, reason?)` 立即请求取消。可选的已记录原因会转发给生产方。终止任务报告现有状态;生产方的取消操作若抛出,调用便会失败,任务保持运行。 + +流式读取共享一个任务作用域内的消费游标,因为所属模型是预期读取方。UI 或多个独立读取方需要单独的非消费式观察 API;共享该游标会让读取方彼此消费对方的输出。 + +系统提示词要求模型保留 task id、在后台工作运行时继续处理独立工作而非忙轮询或重复启动同一任务、在给出最终答案前收集相关任务,并终止不再重要的工作。完成时,系统会向确切所有者的会话注入一条已记录的 `context/message`;它会成为下一个请求的持久上下文,但不会唤醒空闲的 agent。 + +当读取或等待交付终止任务、实时等待方在结算时认领了投递,或模型显式终止任务时,运行时将终止任务标为 `reported`。已报告的任务不会注入冗余的完成通知。监听器失败会独立记录,不会阻止后续监听器,也不会被等待方或资源销毁过程等待。当快照携带 `outputLimitBytes` 时,`dsh-tool-tasks` 会保持 UTF-8 边界,并复用生产方已有的截断标记,而不会重复添加。读取会为状态后缀预留空间并保留输出尾部;完成通知会先为稳定的 `background task <id>` 前缀与 `task_output` 指令预留空间,再截断可变的 kind、label、status、detail,乃至截断标记本身,因此 PTY 的最小上限仍能标识需要收集的任务。任务接口在策略有机会拒绝或短路分发之前,于最先执行的 pre-execute 监听器中解析调用方可见的生产方上限;随后通过任务定义最后一道的 `finalizeContent` 回调应用该上限,使规范化的工具错误、外层流水线失败与单文本策略结果都无法绕过该边界;经特意结构化的多块策略结果仍由策略拥有其形状与大小。 + +## 生产方显式启用 + +每个生产方通过带默认值的配置,自行决定其 schema 是否暴露 `run_in_background`。`dsh-tool-bash`、`dsh-tool-pty` 和每个 `dsh-tool-subagent` 实例都使用 `enableRunInBackground`,默认值为 true。禁用的实例会省略该参数;由于通用参数校验器允许未声明的键,它还会在执行时拒绝强制传入的后台参数。省略 schema 用于声明能力不可用;执行检查负责强制该约束。 + +`ctx.tasks` 不改写生产方 schema。bundle 只转发其所拥有生产方的配置。如果后台调用在没有附加接口的情况下到达 `start()`,运行时防线会在执行前使其失败。 + +## 生产方集成 + +bash seam 暴露 `resolve`、`run` 和 `start`。`start(spec)` 返回一个 `BashProcess`,提供增量读取、取消、退出事实以及不拒绝的完全停稳 promise。本地执行器只为自身释放时能终止并等待进程而保留实时句柄。前台调用方继续直接使用 `resolve` 和 `run`。 + +对于后台 bash,`dsh-tool-bash` 将调用方 agent 注册为所有者。其钩子将 `kill()` 映射为取消,将 `done` 映射为 completed 或 killed 的 `TaskOutcome`,并将 `readOutput()` 映射为进程的有界增量输出,以及溢出文件与沙箱通知。通用任务工具拥有 id、状态行、列表、等待和完成通知。 + +对于后台 subagent,`dsh-tool-subagent` 创建由任务拥有的 `AbortController`,并在任务 starter 内启动提供方。无论提供方就绪前后,取消都会中止同一个 signal。`done` 同时等待子运行结果和子运行释放,将已完成输出映射为最终结果,将中止映射为 `killed`,并将其他停止原因或基础设施失败映射为 `failed`。中间子历史保留在子会话中,不通过 `readOutput()` 暴露。 + +## 备选方案 + +### 按功能划分控制工具 + +为 bash 与 subagent 分别提供输出/停止工具,会重复 id、隔离、清理、通知和指导,并增加模型的 schema 与协议负担。统一运行时将执行专属行为保留在生产方中,而无需复制任务生命周期。 + +### 立即抽象任务运行时后端 + +当前 `TaskStart.run()` 契约传入进程内回调与确切的 `Agent` 对象。持久化后端会改变身份、重启、所有权与观察语义,因此在第二种实现出现前抽取接口,会固化错误的边界。 + +### 由消费方负责授权或清理事件 + +由消费方负责检查,会使每个新接口的隔离实现不一致或遗漏。广播清理事件会迫使每个监听器过滤所有 agent,且不提供注册 disposer。集中授权加一个所有者作用域内的 effect,为每个消费方提供相同防线,以及可等待、可移除的生命周期钩子。 + +### 阻塞输出或单独的等待工具 + +默认阻塞会在后台工作运行时串行化父任务。只等待而不读取会增加一次不返回有用信息的模型调用和 schema。`task_output(wait: true)` 显式表达阻塞,并将其与结果交付合并。 + +等待使用共享的 deadline 原语,而不使用通用工具超时策略。等待超时是一次成功的观察,会返回 `[status: running]`;通用策略会将它替换为超时错误。任务返回 task id 后,没有任何工具调用超时会控制任务生命周期。 + +### 由运行时拥有输出接收端 + +推送式接收端可以集中缓冲,但 bash 已经在执行器 seam 后拥有有界缓冲、截断与溢出文件。拉取格式化增量能够保留这一所有权。拥有存储的持久化后端可能足以支持重新审视生产方接口。 + +### 随机 id、提升或生命周期会话事件 + +授权而非不可猜测性才是访问边界,并且 id 不用于派生文件系统路径;顺序生成的品牌化 id 可保持 transcript(文本记录)易读。将前台任务提升为后台任务需要 SDK 并未规定的用户交互契约。启动、读取和通知已作为工具与上下文事件记录,因此专用任务会话事件会重复面向模型的事实。 + +## 测试 + +单元覆盖固定预检原子性、按 kind 分配的 id、输出上限的校验与投影、完整结果的 UTF-8 字节上限、流式与最终读取、等待超时与中止竞态、取消、首次结果优先的结算、监听器隔离、通知压制、所有者隔离、陈旧的所有者实例、所有者清理、服务资源销毁和无接口防线。生产方测试覆盖 bash 进程映射、subagent 启动取消、终止映射与释放。快照覆盖固定控制工具 schema 与提示词指导。 + +## 后果 + +bash 命令与 subagent 共享一套 id 词汇、列表、通知格式、提示词习惯和控制工具。新的长时间运行生产方只需实现执行钩子,而不必再实现一套注册表与工具族。[工具实操手册](../../../../docs/cookbook/adding-a-tool.md)将生产方指向本契约。 + +有所属后台 bash 会随其 agent 一起停止,不再比 agent 存活更久。后台进程没有执行器超时;调用方必须终止无关工作,或依赖所有者/服务释放。流式读取只支持一个消费方,完成通知不会唤醒空闲 agent;生产方的 `cancel` 返回后如果未使 `done` 完成,仍可能阻塞资源销毁。持久任务、独立观察游标和前台提升仍属于单独设计。 diff --git a/.agents/notes/implemented/architecture/2026-06-20-package-hierarchy.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-20-package-hierarchy.i18n.yaml new file mode 100644 index 0000000000..63ef106781 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-06-20-package-hierarchy.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-20-package-hierarchy.md: ab0732172934414f2361b9e4976b54e5daee298c +2026-06-20-package-hierarchy.zh.md: 57058860de5b4cba3e8a45ecad9d611d068fb82c diff --git a/.agents/notes/implemented/architecture/2026-06-20-package-hierarchy.md b/.agents/notes/implemented/architecture/2026-06-20-package-hierarchy.md index 1ba3b94e8b..ab07321729 100644 --- a/.agents/notes/implemented/architecture/2026-06-20-package-hierarchy.md +++ b/.agents/notes/implemented/architecture/2026-06-20-package-hierarchy.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-06-20-package-hierarchy.zh.md) + The later [fold-stdio-helper](../simplification/2026-07-04-fold-stdio-ui-helper.md) decision superseded the original `support/ui-stdio` placement, and the [redundant-agent removal](../simplification/2026-07-20-remove-stdio-and-echo-agents.md) subsequently removed that surface entirely. The uniform depth-two hierarchy remains the decision owned here. ## Problem diff --git a/.agents/notes/implemented/architecture/2026-06-20-package-hierarchy.zh.md b/.agents/notes/implemented/architecture/2026-06-20-package-hierarchy.zh.md new file mode 100644 index 0000000000..57058860de --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-06-20-package-hierarchy.zh.md @@ -0,0 +1,77 @@ +# Agent Note: 将包重组为模块化层级结构 + +Status: implemented + +[English](2026-06-20-package-hierarchy.md) | 中文 + +后续的[折叠 stdio helper](../simplification/2026-07-04-fold-stdio-ui-helper.md)决策取代了最初的 `support/ui-stdio` 放置方式,[冗余 agent 移除](../simplification/2026-07-20-remove-stdio-and-echo-agents.md)随后又彻底移除了该接口。这里拥有的决策仍是统一的二层目录深度。 + +## 问题 + +`packages/` 原先是扁平的:18 个包(package)全部位于 `packages/<name>/`,从路径上完全看不出一个包属于核心产品 API、可替换的能力 seam、提供方适配器、产品集成,还是示例/测试支撑。包的 README 带着 `FIXME(package-hierarchy)`,`scripts/publint-all.ts` 带着 `TODO(package-inventory)`,标记的正是这个问题。核心包、提供方集成、能力 seam、示例 UI 支撑和仅用于快照的回放支撑看起来同样基础。 + +这不仅仅是外观问题。由于每个顶层包看起来都属于同一个公开接口,未来移除更加困难,而 publish/lint/doc 脚本不得不通过注释或手工维护的静态列表来编码意图,而不是从布局中直接读取。 + +## 决策 + +按模块角色将包分组,统一放在 `packages/<group>/<pkg>/` 深度。分组目录是纯容器(没有 `package.json`);每个包保留其 `@deepseek-ai/dsh-<pkg>` 名称——这是仓库结构与维护策略的调整,不是包的重命名。 + +```text +packages/ + core/ (product API spine) + session/ + system-prompt/ + tools/ + agent/ + agent-loop/ + llm/ (product — capability family) + llm/ + llm-deepseek/ + llm-pi-ai/ + bash/ (product — capability family) + bash/ + bash-local/ + tool-bash/ + session-persistence/ (product — capability family) + session-persistence/ + session-persistence-jsonl/ + session-persistence-sqlite/ + ui/ (product integration) + acp/ + support/ (dev/test/example infrastructure) + invariants/ + ui-stdio/ + llm-replay/ +``` + +### 放置决策 + +- **能力族使用同名嵌套。** 一个族的接口包位于 `packages/<group>/<group>/`(`llm/llm`、`bash/bash`、`session-persistence/session-persistence`),实现和消费方作为扁平兄弟并列。不设额外的 `adapters/`/`impls/` 子层——每个包恰好在深度 2,这使 workspace glob 保持简洁的 `packages/*/*`,并让一条 `@deepseek-ai/dsh-*` tsconfig 通配符即可解析所有包(唯一的目录名使 first-on-disk-wins 无歧义)。 +- **`session` 留在 `core/`;持久化独立成族。** 会话日志是核心产品 API。其存储后端构成一个平行的能力族(`session-persistence/`),与 `llm/` 和 `bash/` 对称,而非嵌套在 `core/session/` 下。 +- **`agent-loop` 在 `core/` 中。** 它是 `agent` seam 唯一的具体实现,但作为 harness 的默认产品循环交付,因此与核心主干同处。插件仍然依赖 `agent` 的词汇,从不依赖 `agent-loop`,所以循环仍可替换。 +- **`invariants` 和 `ui-stdio` 属于 `support/`,不是产品。** `invariants` 是开发模式的契约检查。`ui-stdio` 从示例中提取出来以便复用和满足覆盖率门禁——它与示例耦合,因此与 `llm-replay`(快照测试的回放适配器)一起放在 `support/` 中。`acp` 是 `ui/` 的唯一成员,因为它是真正的产品接口(编辑器驱动的 ACP 桥接),与 readline 演示辅助工具在结构上截然不同。 + +### 去重包列表 + +包列表此前在五个地方重复枚举。统一的深度 2 布局使大部分可以被推导: + +- `tsconfig.base.json` 通过一条 `@deepseek-ai/dsh-*` `paths` 通配符(每个分组列一个候选)映射所有包,取代了逐包条目。聚合配置(`tsconfig.host.json`、`tsconfig.client.json`)复用该源映射,并携带显式 project references 以保持包/vendor 类型检查边界完整。(这里引入了一个细节:路径候选中包含 `/*/`,朴素的正则注释剥离器会将其误认为块注释——`scripts/doc-typecheck.ts` 正是因此通过 TypeScript 解析器读取 JSONC 配置,而非手动剥离注释。) +- `scripts/publint-all.ts` 通过读取层级结构(`packages/<group>/<pkg>`)推导列表,解决了 `TODO(package-inventory)`。 +- 聚合配置的 project `references` 仍为显式列表——TypeScript project references 没有通配符形式。从 manifest(元数据清单)生成这些引用留作后续工作(见[通过发现机制获取包清单](../../proposed/process/2026-06-20-discover-package-inventory.md))。 + +### 新增的护栏 + +两道 doc-sync/hygiene 门禁确保结构及其引用保持正确,使本次重组所需的手动检查无需日后重复: + +- `scripts/verify-package-paths.ts` 标记 Markdown 或 `.ts` 注释/字符串中的 `packages/<path>` 引用,如果该引用无法解析**且**某个路径段命名了一个真实存在的包,即指向已移动包的陈旧路径。如果路径命名的包在任何地方都不存在(前瞻性提案),则不予标记,因此该门禁在 proposed/implemented/rejected 中统一适用。 +- `scripts/check-workspace-constraints.ts` 断言 `packages/<group>/<pkg>` 形状:分组目录不带 `package.json`,且没有包扁平地位于根层或嵌套更深。分组名称保持开放——添加新分组无需修改门禁;只有深度 2 的形状是固定的。 + +## 曾考虑的替代方案 + +- **第三层(每个族下设 `adapters/`/`impls/`)**:否决。统一深度 2 使 workspace glob 保持简洁的 `packages/*/*`,并让一条 `@deepseek-ai/dsh-*` tsconfig 通配符即可解析所有包。 +- **将持久化嵌套在 `core/session/` 下**:否决。存储后端构成一个平行的能力族,与 `llm/` 和 `bash/` 对称,而会话日志本身属于核心产品 API。 +- **`ui-stdio` 放在 `ui/` 下**:否决。它是与示例耦合的开发支撑,不是产品接口;`acp` 是 `ui/` 的唯一成员,因为编辑器实际驱动它。 + +## 后果 + +本次重组在一次协调的变更中搅动了 import、workspace glob、文档链接、构建引用和包路径。这种变动在发布前是可接受的(依据 AGENTS.md 中「基础优先于爆炸半径」的立场),因为它阻止了扁平布局将支撑包固化为产品契约,且这是一次性成本:通配符 `paths`、glob 推导的 publint 列表和形状门禁意味着新增一个包无需额外的结构性编辑。 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 new file mode 100644 index 0000000000..e72b100327 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-21-mandatory-app-attribution-headers.md: a8ffe91c431cdc7907626bbc3eaf8096035777de +2026-06-21-mandatory-app-attribution-headers.zh.md: 5529a42dddf4615ee1054b4d1dee36b077800d7d 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 fdd98b89cb..a8ffe91c43 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 @@ -2,6 +2,8 @@ Status: implemented +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. 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 new file mode 100644 index 0000000000..5529a42ddd --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.zh.md @@ -0,0 +1,84 @@ +# Agent Note: 对提供方请求强制携带 `User-Agent` 归属标识 + +Status: implemented + +[English](2026-06-21-mandatory-app-attribution-headers.md) | 中文 + +## 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。 + +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。 + +## 调研 + +- **OpenRouter 的机制是提供方特有的。** 其当前文档说明应用归属通过 `HTTP-Referer`(必需)、`X-OpenRouter-Title` 和 `X-OpenRouter-Categories` 来追踪;`X-Title` 仅为向后兼容而接受。其 API 参考称这些头部为可选,并说它们使应用在 OpenRouter 上可被发现。这是一份具体的 OpenRouter 契约,而非 IETF 或 OpenAI 兼容 API 标准。 +- **在 agent 工具生态中,`HTTP-Referer` 是一种 OpenRouter 感知的约定,而非通用 agent 约定。** 它足够常见,以至于 OpenRouter SDK 和示例直接暴露它,面向 OpenRouter 的框架通常需要一种方式来透传它。但 ACP(Agent Client Protocol)等 agent 协议在自己的 initialize 消息中协商名称、版本和能力,而模型提供方请求仍需 HTTP 层面的身份标识。因此「在 agent 世界中被接受」意味着「被 OpenRouter 集成所识别」,而非「可跨 agent 运行时或提供方移植」。 +- **编程 agent 在 `User-Agent` 中标识产品和版本。** 公开实现在环境细节和提供方特有的附加头部上各有不同,但产品身份是共同契约;不存在通用的精确格式。 +- **标准化的通用客户端身份头部是 `User-Agent`。** RFC 9110 第 10.1.5 节将 `User-Agent` 定义为用户代理软件身份,说明它用于互操作性报告和分析,并说用户代理应当在每个请求中发送它(除非被配置为不发送)。这是唯一直接对应「哪个产品在发出此 HTTP 请求」的标准头部。 +- **`Referer` 是标准的,但 OpenRouter 的 `HTTP-Referer` 不是标准字段。** RFC 9110 第 10.1.3 节将 `Referer` 定义为获取目标 URI 的来源 URI,并用大量篇幅讨论隐私限制。OpenRouter 则要求 `HTTP-Referer`,将其用作应用 URL 标识符。该名称和含义是 OpenRouter 特有的,尽管它形似标准 `Referer` 头部的 CGI 环境变量形式。 +- **`From` 是标准的,但不适合作为强制默认值。** RFC 9110 第 10.1.2 节将 `From` 定义为负责用户代理的人的电子邮件地址。机器人代理应当发送它以便服务器联系运营者,但非机器人代理出于隐私和安全策略考虑不应在未经用户显式配置的情况下发送。harness 可以后续支持运营者联系方式,但不得凭空捏造或全局强制要求。 +- **请求体中的 `user` 或 `metadata` 字段不是应用归属。** 部分模型 API 暴露稳定的终端用户标识符、请求元数据、标签或项目/账户头部。这些对滥用监控、内部计费、仪表盘或链路追踪有用,但它们要么标识的是终端用户而非产品,要么是提供方特有的 body schema,要么不保证能通过 OpenAI 兼容网关透传。它们不能替代静态的应用身份头部。 +- **SDK 遥测头部标识的是 SDK,而非应用。** 官方和第三方 SDK 常发送库/版本头部。这些帮助 SDK 维护者调试其客户端,但除非应用显式提供产品归属层,否则它们不能标识 harness 作为应用。 +- **pi-ai 有一流的头部钩子。** `@earendil-works/pi-ai` 的 `StreamOptions.headers` 将调用方头部最后合并(覆盖提供方默认值),因此基于库的适配器无需包装或上游改动即可满足与手写适配器相同的协议格式契约。mock 服务器测试套件对两个适配器都断言头部到达了线路。 + +## 决策 + +在 LLM 适配器边界,提供方请求归属是强制的,且仅使用标准 `User-Agent` 头部。规则:每个生产 LLM 适配器在每个提供方 HTTP 请求上发送一个静态、非机密的应用身份,且每个适配器都有测试证明 `User-Agent` 到达了线路(mock 服务器断言收到的头部;对于基于库的适配器,通过库的头部钩子馈入同一个 mock 服务器断言)。 + +本 Agent Note **不**实现 OpenRouter 应用归属。`HTTP-Referer`、`X-OpenRouter-Title`、`X-Title` 和 `X-OpenRouter-Categories` 是 OpenRouter 特有的产品展示头部,不是提供方无关的模型请求归属。它们可以后续由 OpenRouter 适配器或显式 OpenRouter 模式提出,附带自己的隐私/产品决策、测试和文档。在此之前,即使请求指向 OpenRouter,也只发送本 Agent Note 定义的共享 `User-Agent` 归属。 + +提供方无关的身份由 `dsh-llm`(`packages/llm/llm/src/attribution.ts`)拥有,而非各适配器。`AppIdentity` 仅包含构建 `User-Agent` 所需的公开产品事实,默认的 `APP_IDENTITY` 确定了提案中留待决定的值: + +- `User-Agent` 的产品 token:`deepseek-harness`(与 Agent Note 之前的线路值及仓库/组织身份保持连续性) +- 版本:通过 `createRequire` 从所属包的 manifest 读取,绝不手动复制常量 +- 应用 URL:`https://github.com/deepseek-ai/deepseek-harness-sdk`——计划中的公开主页;`attribution.ts` 中的 `FIXME` 标记在该仓库实际存在之前阻塞发布 + +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。 + +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): + +| 目标 | 映射 | +|---|---| +| 所有基于 HTTP 的适配器 | `User-Agent: {product}/{version} (+{url})`——括号中的 `+url` 注释符合 RFC 9110 保守的 product/comment 语法。 | +| 直连 DeepSeek 端点 | `User-Agent`;除非 DeepSeek 文档化了等效契约,否则不发送 OpenRouter 特有头部。 | +| OpenRouter 端点 | 目前仅 `User-Agent`。本 Agent Note 下不发送 `HTTP-Referer`、`X-OpenRouter-Title`、`X-Title` 或 `X-OpenRouter-Categories`。 | +| 未来提供方 | 仅 `User-Agent`,除非后续提供方特有的 Agent Note 接受额外头部。不要类比复用 `HTTP-Referer`。 | + +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。 + +## 验证 + +已落地的契约: + +- `dsh-llm` 为 `LlmAdapter` 作者文档化了强制的 `User-Agent` 归属契约(`LlmAdapter` JSDoc、包 README,以及 `docs/core-data-structures/llm-streaming.md` 的适配器契约章节)。 +- 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`)。 +- 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。 + +**向所有提供方发送 OpenRouter 头部。** 否决。这会把一份自定义的 OpenRouter 契约当作通用标准,并向未要求这些字段的提供方发送语义误导的头部。还有风险将 `HTTP-Referer` 当作通用应用 URL 字段使用,尽管标准 HTTP 已有 `User-Agent` 用于产品身份、`Referer` 用于不同的浏览上下文概念。 + +**仅使用提供方账户/项目身份。** 否决。组织/项目头部、API key、云账户和计费项目标识的是谁付费或谁拥有请求,而非哪个应用在发送流量。它们也不暴露公开的应用标题/类别,无法帮助 OpenRouter 等网关构建应用排名。 + +**终端用户 `user`/`metadata` 字段。** 本 Agent Note 否决。这些对滥用监控和客户支持有价值,但描述的是请求背后的人或租户。应用归属必须是静态的产品身份,且可安全地在每个请求上发送。 + +**仅配置启用的归属。** 否决。默认关闭的设置正是适配器不断漂移的原因。策略是强制默认归属加可覆盖的公开值,而非可选归属。 + +**以产品命名的 token(`deepseek-harness-sdk`)。** 曾考虑用于 `User-Agent` token,因为产品名是 DeepSeek Harness SDK。`deepseek-harness` 因连续性胜出:它是提供方从本代码库已经看到的身份,与组织/仓库身份和包 scope 一致,且在展示文案承载产品名的同时保持线路归属稳定。 + +## 后果 + +**提供方看到流量来自 harness。** 这正是目的,但意味着此前混在通用 SDK 流量中的部署变得可识别。缓解措施:仅发送静态公开产品数据,并允许 fork/白标部署传入自己的 `AppIdentity`。 + +**应用 URL 指向一个尚不存在的仓库。** `deepseek-ai/deepseek-harness-sdk` 是计划中的公开主页;在它创建之前,该 URL 是一个悬空承诺。常量上的 `FIXME` 标记阻塞发布,不允许带着未解决的问题出门(见 `docs/development.md` 标记语义)。 + +**不同客户端库的头部支持有差异。** 手写适配器直接设置头部;基于 pi-ai 的适配器依赖 pi-ai 继续尊重 `StreamOptions.headers`(最后合并覆盖提供方默认值)。线路级 mock 服务器测试是守卫:如果 pi-ai 升级后不再投递该头部,套件会变红。这对抽象施加了有益的压力:一个无法设置强制头部的提供方适配器不能完整实现 harness 的 LLM 契约。 + +**OpenRouter 排名尚未受益。** `User-Agent` 是提供方无关的 HTTP 身份的正确基线,但它不会创建 OpenRouter 应用页面或排名,因为 OpenRouter 要求 `HTTP-Referer` 来实现该产品功能。这是有意为之:公开应用市场参与是一个独立的产品决策,不是强制请求归属的前提。 diff --git a/.agents/notes/implemented/architecture/2026-06-24-web-capability-seam.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-24-web-capability-seam.i18n.yaml new file mode 100644 index 0000000000..70ec051143 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-06-24-web-capability-seam.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-24-web-capability-seam.md: 4f4e821fec9494fe9ea96894267707d9dd202e4d +2026-06-24-web-capability-seam.zh.md: d7c07a8ae0365c321120102a0af401d85d7e2eae 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 b3dad98f18..4f4e821fec 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 @@ -2,6 +2,8 @@ Status: implemented +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. @@ -75,6 +77,8 @@ Provider packages depend only on `dsh-web` and Cordis. They own credentials, end `ctx.web` is a provider registry plus a provider-selecting execution surface. The registry half stays close to `LlmService`: a `Map<id, provider>` per capability kind, `registerSearchProvider` / `registerFetchProvider` methods that return disposers, duplicate ids that throw `WebError`, and execution-time resolution that throws when the selected provider is absent or unusable. The authoritative signatures live in `packages/web/web/src/types.ts`; the seam's shape: ```ts +import type { WebFetchRequest, WebFetchResult, WebSearchRequest, WebSearchResult } from '@deepseek-ai/dsh-web' + interface WebSearchProvider { readonly id: string available(): boolean @@ -206,18 +210,18 @@ The seam request deliberately does not include a per-call timeout, `format`, `pr HTTP status is part of the fetched resource state, not automatically a tool failure. A successful network fetch of a `404` or `500` response returns `WebFetchResult` with the status code and a bounded decoded body when the content type is supported. `WebError` is for failures to safely retrieve or represent the resource: invalid or blocked URL, redirect policy violation, timeout, abort, response too large, unsupported content type, provider failure, or network failure. ```ts -interface WebFetchRequest { +export interface WebFetchRequest { readonly url: string } -interface WebFetchResult { +export interface WebFetchResult { readonly url: string readonly statusCode: number readonly body: WebFetchBody readonly truncated: boolean } -type WebFetchBody = +export type WebFetchBody = | { readonly kind: 'html'; readonly content: string } | { readonly kind: 'text'; readonly content: string } ``` 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 new file mode 100644 index 0000000000..d7c07a8ae0 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-06-24-web-capability-seam.zh.md @@ -0,0 +1,336 @@ +# Agent Note: Web 能力 seam——稳定的工具覆盖多个提供方 + +Status: implemented + +[English](2026-06-24-web-capability-seam.md) | 中文 + +## 问题 + +harness 需要面向模型的 web 工具,但不能将模型契约绑定到某一家厂商的 API 形状上。搜索是当前的压力点:从一开始就同时支持 Exa 搜索和 Perplexity 搜索——两种刻意不同的提供方形状(Exa 返回扁平的 `results[]`,每项包含 `{title, url, highlights, publishedDate}`;Perplexity 返回一段生成式回答加引用列表)——正是用来证明归一化的 seam 并非只是镜像某一家厂商。Fetch 是另一项独立能力:匿名公开 HTTP(S) fetch 后端涉及传输、安全、重定向、解码和大小限制等关注点,与提供方支撑的搜索并不相同。 + +面向模型的接口必须保持稳定,而后端可以更换。更换搜索提供方不应改变模型发起查询的方式;更换 fetch 实现不应改变模型请求 URL 的方式。反过来,提供方包也不应仅仅因为自己有额外的提供方特有旋钮就暴露自己的面向模型工具 schema。 + +如果把搜索和 fetch 直接放进 `dsh-tool-web`,面向模型的工具就要同时承担提供方选择、后端请求映射、传输策略、结果归一化、提示词引导、展示和 schema 注册。让每个提供方注册自己的工具则有相反的问题:工具的可用性、名称、描述和参数将取决于恰好加载了哪些提供方包,提供方特有字段会泄漏到模型契约中。 + +还有一个提供方选择的问题。现有的 `tool-bash` 和 `tool-fs` 可以依赖 Cordis 的 `inject`,因为只有一个后端服务键。Web 有两项独立能力(`search` 和 `fetch`),每项能力可能有多个提供方。`inject: ['web']` 能证明 seam 存在,但不能证明存在可用的搜索或 fetch 提供方,也无法定义多个提供方注册时谁胜出。 + +## 决策 + +Web 访问是一个一等能力 seam,遵循[能力 seam Agent Note](2026-06-13-capability-seams.md): + +1. `@deepseek-ai/dsh-web`(`packages/web/web`)拥有 `ctx.web`、提供方注册、提供方选择、共享的请求/结果词汇,以及 web 特有的错误。 +2. 提供方包实现具体后端并向 `ctx.web` 注册能力,例如 `@deepseek-ai/dsh-web-search-exa`、`@deepseek-ai/dsh-web-search-perplexity`、`@deepseek-ai/dsh-web-search-deepseek` 和 `@deepseek-ai/dsh-web-fetch-local`。 +3. `@deepseek-ai/dsh-tool-web`(`packages/web/tool-web`)拥有面向模型的 `web_search` 和 `web_fetch` 工具 schema、提示词段落、参数校验、结果格式化,以及通过 `ctx.web` 实现的工具展示。 + +提供方不注册工具。提供方注册能力。`dsh-tool-web` 是面向模型的名称、描述、提示词引导、JSON Schema、展示的唯一所有者。 + +搜索和 fetch 是两个独立工具,但属于同一个 web 访问 seam。`ctx.web` 为两个并行注册表统一拥有提供方选择、abort/错误词汇和部署配置。它们的请求 schema 和提供方逻辑保持独立;共享的服务是触达 web 的产品边界。 + +`dsh-tool-web` 在产品启用了相应工具且 `ctx.web` seam 存在时注册面向模型的 web 工具。后端可用性是执行时关注点,而非 schema 注册时关注点: + +- `web_search` 在产品/应用启用了 web 搜索时注册,`web_fetch` 在启用了 web fetch 时注册。 +- 工具绝不会仅仅因为其选定的提供方缺失、配置错误、缺少凭证、存在歧义或暂时不可用就被注销。 +- 提供方在执行时解析,当选定的能力无法运行时返回结构化的 `WebError`。 + +这使模型 schema 保持稳定,而不将插件加载顺序、凭证状态或 HMR(热模块替换)时序纳入面向模型的契约。如果 web 搜索已启用但不存在可用的搜索提供方,`web_search` 仍然可见,执行时以结构化的 `WebError`(如 `WEB_PROVIDER_UNAVAILABLE` 或 `WEB_PROVIDER_CONFIGURED_UNAVAILABLE`)失败。如果某个提供方在 `dsh-tool-web` 之后出现,下一次执行即可使用它而无需更改 schema。如果某个提供方在调用过程中消失,执行以结构化的 `WebError` 失败,而不是静默选择另一个提供方或回退到 `UNKNOWN_TOOL`。 + +该 seam 刻意不暴露任何观察面——没有注册表变更事件,也没有聚合的能力状态查询。不可用性是调用方通过执行观察到的事实:`search()`/`fetch()` 在调用时解析提供方,并抛出命名了失败原因的结构化 `WebError`。[观察面 Agent Note](../simplification/2026-07-04-drop-unconsumed-web-observation-surface.md) 记录了这一判断:基于调用的派生选择与基于启用的注册使得没有消费方需要变更信号或独立于执行和错误路由的可用性探测;未来的提供方状态面板会重新引入它实际消费的最小信号或查询。 + +## 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。 + +依赖方向与 bash 和 filesystem 一致: + +```text +@deepseek-ai/dsh-tool-web --depends on--> @deepseek-ai/dsh-web <--depends on-- @deepseek-ai/dsh-web-search-exa + consumer interface implementation + <--depends on-- @deepseek-ai/dsh-web-search-perplexity + implementation + <--depends on-- @deepseek-ai/dsh-web-search-deepseek + implementation + <--depends on-- @deepseek-ai/dsh-web-fetch-local + implementation +``` + +运行时,提供方包向 `ctx.web` 注册能力;`tool-web` 向 `ctx.tools` 注册稳定的工具并通过 seam 执行: + +```mermaid +flowchart LR + exa["@deepseek-ai/dsh-web-search-exa"] -->|registerSearchProvider| web["@deepseek-ai/dsh-web / ctx.web"] + perplexity["@deepseek-ai/dsh-web-search-perplexity"] -->|registerSearchProvider| web + deepseek["@deepseek-ai/dsh-web-search-deepseek"] -->|registerSearchProvider| web + fetchLocal["@deepseek-ai/dsh-web-fetch-local"] -->|registerFetchProvider| web + toolWeb["@deepseek-ai/dsh-tool-web"] -->|search/fetch| web + toolWeb -->|ctx.tools.register| webSearch["tool: web_search"] + toolWeb -->|ctx.tools.register| webFetch["tool: web_fetch"] +``` + +`@deepseek-ai/dsh-web` 仅依赖 Cordis 和底层 harness 支持。它声明 `ctx.web`、提供方接口、请求/结果类型、提供方可用性契约和错误码。它不导入工具、agent、会话、LLM 或提供方包。 + +提供方包仅依赖 `dsh-web` 和 Cordis。它们拥有凭证、端点、协议格式映射、解析和 `WebError` 转换,使用平台 `fetch`。每个提供方注入共享服务并注册后端;只有 `dsh-web` 拥有 `ctx.web` 键。提供方私有的协议形状不会产生对 `ctx.llm` 或 Cordis HTTP 服务的依赖。 + +`@deepseek-ai/dsh-tool-web` 依赖 `@deepseek-ai/dsh-web`、`@deepseek-ai/dsh-tools`、`@deepseek-ai/dsh-system-prompt` 和 Cordis。它从不导入具体的提供方包。 + +## `ctx.web` 契约 + +`ctx.web` 是一个提供方注册表加上一个带提供方选择的执行面。注册表部分与 `LlmService` 保持接近:每种能力类别一个 `Map<id, provider>`,`registerSearchProvider`/`registerFetchProvider` 方法返回 disposer,重复 id 抛出 `WebError`,执行时解析在选定提供方缺失或不可用时抛出异常。权威签名见 `packages/web/web/src/types.ts`;seam 的形状: + +```ts +import type { WebFetchRequest, WebFetchResult, WebSearchRequest, WebSearchResult } from '@deepseek-ai/dsh-web' + +interface WebSearchProvider { + readonly id: string + available(): boolean + search(request: WebSearchRequest, signal?: AbortSignal): Promise<WebSearchResult> +} + +interface WebFetchProvider { + readonly id: string + available(): boolean + fetch(request: WebFetchRequest, signal?: AbortSignal): Promise<WebFetchResult> +} + +interface WebService { + registerSearchProvider(provider: WebSearchProvider): () => void + registerFetchProvider(provider: WebFetchProvider): () => void + + search(request: WebSearchRequest, signal?: AbortSignal): Promise<WebSearchResult> + fetch(request: WebFetchRequest, signal?: AbortSignal): Promise<WebFetchResult> +} +``` + +可选的 signal 是执行控制,而非业务输入:`tool-web` 直接传递 `exec.signal`,使轮次取消、工具超时和 agent dispose(资源释放)能到达提供方的网络请求、流读取器和高开销解码。seam 不传递 `ToolExecution`——否则 `dsh-web` 就要依赖 `dsh-tools`。 + +提供方 id 是稳定字符串,在各自的能力类别内唯一。注册重复的搜索提供方 id 或重复的 fetch 提供方 id 会失败,而非静默替换旧提供方。提供方注册返回 disposer,沿用现有的 `ctx.tools.register()`/`ctx.systemPrompt.section()` 模式:变更包裹在 `ctx.effect()` 中,注册随贡献它的 fiber 一起拆除。 + +## 提供方可用性与选择 + +提供方可用性与能力选择是两个独立概念,但都保持最小化。提供方仅报告该具体实现是否可用,通过廉价的本地检查(如凭证是否存在、端点配置是否可解析)。提供方的 `available()` 禁止发起网络调用。 + +`LlmService` 完全没有状态类型:可用性通过注册表成员资格加解析时抛出来表达。`ctx.web` 遵循同样的纪律。seam 不暴露聚合的能力状态查询——`search()`/`fetch()` 在每次调用时根据配置的提供方 id、已注册的提供方和每个提供方廉价的本地 `available()` 布尔值派生选择结果,选择失败就是执行时抛出的结构化 `WebError`。需要知道某项能力能否运行的调用方通过执行并路由该错误来获知;没有任何东西作为可变服务状态存储。 + +该布尔值是选择的输入,而非健康系统。`tool-web` 从不直接调用提供方的 `available()`——它进入 seam 的唯一路径是 `search()`/`fetch()`——因此选择策略只有一个所有者。 + +选择不得依赖注册顺序。Cordis 加载顺序、配置排列和 HMR 时序不是产品语义。 + +| 情况 | 执行行为 | +|---|---| +| 配置的提供方 id 已注册且 `available() === true` | 运行该提供方 | +| 配置的提供方 id 未注册 | 以 `WEB_PROVIDER_CONFIGURED_MISSING` 失败 | +| 配置的提供方 id 已注册但不可用 | 以 `WEB_PROVIDER_CONFIGURED_UNAVAILABLE` 失败 | +| 未配置提供方 id,且该类别恰好有一个已注册且可用的提供方 | 运行该唯一提供方 | +| 未配置提供方 id,且该类别无已注册提供方 | 以 `WEB_PROVIDER_UNAVAILABLE` 失败 | +| 未配置提供方 id,且该类别有多个可用提供方已注册 | 以 `WEB_PROVIDER_AMBIGUOUS` 失败,而非按注册顺序选择 | +| 未配置提供方 id,且有提供方存在但均不可用 | 以 `WEB_PROVIDER_UNAVAILABLE` 失败 | + +「唯一提供方自动选择」规则面向测试、演示和简单部署。产品配置设置显式提供方 id: + +```yaml +- id: web + name: '@deepseek-ai/dsh-web' + config: + searchProvider: exa + fetchProvider: local-http + +- id: web-search-exa + name: '@deepseek-ai/dsh-web-search-exa' + +- id: web-search-perplexity + name: '@deepseek-ai/dsh-web-search-perplexity' + +- id: web-search-deepseek + name: '@deepseek-ai/dsh-web-search-deepseek' + +- id: web-fetch-local + name: '@deepseek-ai/dsh-web-fetch-local' + +- id: tool-web + name: '@deepseek-ai/dsh-tool-web' +``` + +运维覆盖走同一条显式选择路径:`DSH_WEB_SEARCH_PROVIDER=perplexity` 等同于配置 `searchProvider: perplexity`,而非 `dsh-tool-web` 内部的隐式优先级链。 + +`ctx.web.search()` 和 `ctx.web.fetch()` 在执行时按上述选择规则解析提供方。如果选定的能力不可用,它们抛出带有结构化代码的 `WebError`,如 `WEB_PROVIDER_UNAVAILABLE`、`WEB_PROVIDER_CONFIGURED_MISSING`、`WEB_PROVIDER_CONFIGURED_UNAVAILABLE` 或 `WEB_PROVIDER_AMBIGUOUS`。如果未显式配置提供方且不存在可用提供方,执行错误是通用的 `WEB_PROVIDER_UNAVAILABLE` 情况;刻意不提供对每个不可用提供方的诊断汇总。 + +## 搜索请求与结果 schema + +面向模型的 `web_search` 工具很小。唯一的面向模型参数是: + +- `query`:必填字符串。 + +`max_results` 不暴露给模型。它是 `dsh-tool-web` 层的决策:工具设定结果上限——`searchMaxResults` 插件配置,默认 `8`(与 OpenCode 的 Exa 默认值对齐),类似 `dsh-tool-fs` 的 `readLimit`——并作为 `WebSearchRequest` 上的 `maxResults` 传给 seam。将其排除在模型 schema 之外意味着模型只需提问,产品控制返回多少上下文;该字段日后可以提升为面向模型的参数而不破坏 seam。 + +`maxResults` 沿工具 → seam → 提供方流动,上限在返回路径上强制执行: + +- `dsh-tool-web` 拥有该值并将其放在 `WebSearchRequest.maxResults` 上。 +- `ctx.web` 将请求原样传递给选定的提供方。 +- 当提供方的 API 支持结果数量控制时(Exa 的 `numResults`),提供方在请求层应用 `maxResults`,作为成本/延迟优化。 +- `ctx.web` 在结果上强制执行上限:如果提供方返回的 source 数量超过 `maxResults`——因为其 API 没有结果数量控制(Perplexity)或忽略了提示——seam 将 `sources[]` 截断到 `maxResults` 并在返回前将 `WebSearchResult.truncated` 设为 `true`。这使上限成为面向模型层可以依赖的单一跨提供方保证,而非每个提供方都必须记得遵守的东西。 + +seam 请求不携带提供方特有的控制——没有 Perplexity 模型选择、搜索时效性、域名过滤器、Exa `livecrawl`、Exa `type`、区域提示、生成式回答预算或搜索深度。只有当某个字段具有提供方无关的语义,且工具 schema 和选定的提供方都能诚实地遵守时,才会添加。 + +```ts +interface WebSearchRequest { + readonly query: string + /** Upper bound on returned sources; the seam truncates to it. Omitted = no bound. `dsh-tool-web` always sets it. */ + readonly maxResults?: number +} + +interface WebSearchResult { + readonly content?: string + readonly sources: readonly WebSearchSource[] + readonly truncated: boolean +} + +interface WebSearchSource { + readonly url: string + readonly title?: string + readonly snippet?: string + readonly publishedAt?: string +} +``` + +`content` 是可选的提供方生成的回答文本、搜索上下文或摘要。`sources[]` 是可移植的引用面。source 必有 URL;title、snippet 和 `publishedAt` 可选,因为并非每个提供方都返回它们。`title` 不是必填:Perplexity 风格的引用可能只提供 URL,强制适配器编造标题会让 seam 说谎。`dsh-tool-web` 渲染 `title ?? hostname(url)` 风格的回退标签用于展示。`publishedAt` 是可选的发布/抓取时间戳,为 ISO-8601 字符串——Exa 在每条结果上以 `publishedDate` 返回它,Perplexity 在搜索结果上返回 `date`,因此它是真实的提供方数据而非派生值;seam 以字符串形式传递,日期解析留给消费方。 + +Exa 搜索将提供方扁平 `results[]` 的每一项映射为 `WebSearchSource`:`url` ← `url`、`title` ← `title`、`snippet` ← 第一个 `highlights[]` 条目(没有 highlight 的条目没有可移植的 snippet,被丢弃)、`publishedAt` ← `publishedDate`。Exa 不返回提供方生成的回答,因此 `content` 省略。Perplexity 搜索将 `choices[0].message.content` 映射为 `content`,并优先使用结构化的顶层 `search_results[]` 作为 `sources[]`——`url` ← `url`、`title` ← `title`、`snippet` ← `snippet`(常为空)、`publishedAt` ← `date`——仅在 `search_results` 缺失时回退到纯 URL 的 `citations[]` 数组(这些 source 只有 `url`)。如果提供方返回的结构化字段少于 seam 支持的,适配器省略那些可选字段。 + +完整页面获取仍是 `web_fetch(url)` 的职责。搜索 snippet 是发现上下文,不是获取到的页面正文。 + +## Fetch 请求与结果 schema + +`web_fetch` 的实现是一个匿名公开 HTTP(S) fetch 提供方 `local-http`。它从具体 URL 获取字节,应用下述基本传输卫生措施(仅 http/https、拒绝 URL 中的凭证、字节/时间上限、跨源重定向阻断),解码文本内容,并仅返回最小的模型可用结果:最终 URL、状态码、正文和截断标志。它不携带浏览器 cookie、编辑器凭证、git 凭证、内部认证令牌,也不隐式访问私有服务。(完整的 SSRF/私有网络阻断推迟——见[推迟工作](#deferred-work)。) + +seam 请求比 OpenCode 的面向模型工具更小: + +- `url`:必填 HTTP(S) URL。 + +seam 请求刻意不包含逐调用超时、`format`、`prompt` 或提供方特有的提取控制。取消通过直接的可选执行信号实现,fetch 提供方拥有一个部署配置的超时兜底。`format` 是对已获取资源的展示决策;`prompt` 是更高层的 LLM 摘要指令;Firecrawl、Exa、Tavily 或 Parallel 等提取 API 可能不暴露具体的 HTTP 响应。如果产品日后需要提供方支撑的页面提取,那是一个独立的 `web_extract` 能力或对本 seam 的刻意扩展——提取语义绝不通过将每个 HTTP 字段设为可选来偷渡进 `web_fetch`。 + +HTTP 状态码是已获取资源状态的一部分,不自动构成工具失败。成功的网络获取一个 `404` 或 `500` 响应会返回带有状态码和有界解码正文(当内容类型受支持时)的 `WebFetchResult`。`WebError` 用于无法安全获取或表示资源的失败:无效或被阻断的 URL、重定向策略违规、超时、abort、响应过大、不支持的内容类型、提供方失败或网络失败。 + +```ts +export interface WebFetchRequest { + readonly url: string +} + +export interface WebFetchResult { + readonly url: string + readonly statusCode: number + readonly body: WebFetchBody + readonly truncated: boolean +} + +export type WebFetchBody = + | { readonly kind: 'html'; readonly content: string } + | { readonly kind: 'text'; readonly content: string } +``` + +`WebFetchResult.url` 是允许的重定向之后的最终 URL。请求 URL 已在 `WebFetchRequest` 中,因此没有单独的 `requestedUrl`/`finalUrl` 对。 + +`WebFetchBody` 是封闭的可辨识联合类型,因为正文类别需要 seam、提供方和工具三方协调变更,而非独立的插件扩展。穷举 switch 使新类别在每个渲染器处编译失败,直到被处理。独立的对象分支为类别特有字段留出空间。 + +提供方负责安全的资源获取:URL 校验、HTTP 传输、重定向策略、超时、abort 传播、字节上限、字符集解码、内容类型分类和二进制拒绝。`dsh-tool-web` 负责展示:HTML 转 Markdown、HTML 转纯文本、面向模型的截断格式化,以及未来的摘要。 + +fetch 提供方的资源控制: + +- 仅接受 `http:` 和 `https:` URL;拒绝 URL 中的凭证。 +- 强制执行最大 URL 长度、响应字节上限、解码正文字符上限、超时和重定向跳数上限。 +- Abort 信号传播到网络获取和高开销解码。 +- 仅自动跟随同源重定向;跨源重定向以 `WEB_REDIRECT_BLOCKED` 失败,要求一次新的工具调用,从而触发新的提供方/权限决策。(Claude Code 的 WebFetch 使用同样的模型——它不自动跟随跨主机重定向,而是将重定向目标返回给模型以发起新调用。) +- 请求携带显式的产品 User-Agent,而非静默伪装浏览器。 + +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,通过先 DNS 解析再验证 IP 来防御 rebinding,并在重定向的每一跳重新验证)**推迟**——见[推迟工作](#deferred-work)。在其落地之前,`web_fetch` 是一个 SSRF 原语,不得在能触达敏感内部网络目标的部署中启用。 + +## 工具消费方行为 + +`dsh-tool-web` 拥有两个 `ToolDefinition`:`web_search` 和 `web_fetch`。它拥有面向模型的 JSON Schema、snake_case 参数名、提示词段落、结果渲染为 `ContentBlock[]`、`presentCall` 和 `presentResult`。 + +`dsh-tool-web` 禁止枚举提供方或直接调用提供方的 `available()`。它进入 seam 的唯一路径是 `ctx.web.search()`/`ctx.web.fetch()`。这将提供方选择保持在单一层;否则工具包可能判定某个提供方可用,而执行时解析出不同的状态。 + +工具注册是最小化的稳定同步:插件启动时,`dsh-tool-web` 的 `Config`(`search?: boolean`、`fetch?: boolean`,均默认 `true`)启用或禁用每个 web 工具;已启用的工具通过基于 effect 的注册表以 fiber 作用域的 disposer 注册;任何工具都不会仅因其选定的提供方缺失、不可用或存在歧义而被 dispose;dispose `tool-web` fiber 时自动拆除其注册。 + +提供方可用性变化影响执行结果和诊断信息,而非面向模型的 schema 是否存在。如果产品完全不需要 web 工具,在配置中禁用 `dsh-tool-web` 或单个 web 工具即可;如果需要 web 工具但后端配置有误,模型在执行时看到结构化的工具错误。 + +提示词引导解释了语义分工——`web_search` 用于发现和获取当前信息,`web_fetch` 用于模型需要特定 URL 内容的场景——提示词和工具结果告诉模型用 Markdown 链接引用相关 URL。 + +面向模型的输出以文本为先,因为工具结果是 `ContentBlock[]`,但 seam 的产出保持结构化,以便 UI 展示和未来的适配器无需解析渲染后的文本。 + +## 错误 + +`dsh-web` 定义 `WebError extends HarnessError`,带有稳定的错误码,仅覆盖调用方可能合理分支的状态: + +- `WEB_PROVIDER_UNAVAILABLE` +- `WEB_PROVIDER_CONFIGURED_MISSING` +- `WEB_PROVIDER_CONFIGURED_UNAVAILABLE` +- `WEB_PROVIDER_AMBIGUOUS` +- `WEB_DUPLICATE_PROVIDER` +- `WEB_INVALID_URL` +- `WEB_BLOCKED_URL` +- `WEB_REDIRECT_BLOCKED` +- `WEB_FETCH_TOO_LARGE` +- `WEB_FETCH_TIMEOUT` +- `WEB_ABORTED` +- `WEB_UNSUPPORTED_CONTENT_TYPE` +- `WEB_PROVIDER_ERROR` + +`WEB_DUPLICATE_PROVIDER` 在 `registerSearchProvider`/`registerFetchProvider` 发现该能力类别中已有相同 id 时同步抛出(类似 `LlmService` 的 `DUPLICATE_ADAPTER`);它是注册时的编程错误而非执行结果,但共享 `WebError` 码空间,使调用方看到统一的分类体系。`WEB_PROVIDER_ERROR` 是提供方自身失败通过 seam 浮出的兜底码,包括 `web-fetch-local` 中的网络/传输失败(DNS、连接拒绝、TLS);刻意不设单独的 `WEB_NETWORK` 码——提供方设置描述性消息,使模型和日志能区分网络失败与提供方 API 失败。 + +工具执行让这些错误流经 `ToolRegistry.execute()`,后者已将 `HarnessError` 转换为带结构化元数据的错误工具结果。模型得到可读的错误消息;钩子、测试和 UI 代码可以根据稳定的错误码路由。 + +## 测试 + +每一层在自己的 seam 处固定:`dsh-web` 中的注册/选择/截断/abort 契约与 `WebError` 码;每个提供方基于录制的 fixture(测试前置数据)的请求/响应映射(Perplexity fixture 包含纯 URL 引用,以保持可选 source 字段的诚实性),加上每个真实提供方的自跳过带密钥冒烟测试;`web-fetch-local` 中的真实本地 HTTP 行为;`dsh-tool-web` 中通过真实工具注册表的启用驱动注册、结构化执行错误和结果格式化。一个真实 Loader 冒烟测试守护两种导出形状([事后分析 0001](../../../../docs/postmortem/0001-acp-default-export-drops-inject.md)):`dsh-web` 是默认导出的服务,而提供方和 `tool-web` 是命名空间插件,误加 `export default` 会丢失 `inject`。 + +## 曾考虑的替代方案 + +### 让每个提供方注册自己的面向模型工具 + +这与最灵活的提供方插件系统一致:每个提供方可以暴露其完整的原生 schema。在 harness 中被否决,因为它将面向模型的名称、描述、提示词引导和结果格式化的所有权交给了提供方包。多个搜索提供方会产生重复的工具名或提供方特有的工具名,模型将学到后端细节而非稳定的产品能力。 + +### 将提供方调度直接放在 `dsh-tool-web` 中 + +这类似 OpenCode 的本地 web 搜索:一个稳定的 `websearch` 工具在内部调度到 Exa 或 Parallel。对于小型产品路径可以接受,但作为 harness 基础是错误的。工具包将拥有提供方选择、凭证、请求映射、传输、响应解析和展示,使得在不将 Exa 和 Perplexity 的差异烘焙进工具 schema 的情况下难以添加它们。 + +### 将搜索和 fetch 拆为两个 seam(`dsh-search`、`dsh-fetch`) + +很有吸引力,因为两半不共享请求 schema 和业务逻辑,各自能干净地映射到 bash/fs 的三包模板上,且 `WebService` 上的 `Search`/`Fetch` 方法对重复也会消失。否决,因为共享的机制——提供方 id 注册表、不依赖注册顺序的选择策略、abort 传播、`WebError` 分类体系,以及面向产品的「这个 harness 如何触达 web」配置面——是真实存在的,否则会在两个几乎相同的 seam 之间重复。一个 `ctx.web` 中间层给产品一个统一的注入和配置对象,给提供方选择一个唯一的所有者。代价是并行的 `searchX`/`fetchX` 方法对,这是有意接受的。 + +### 选择第一个注册的提供方 + +否决。注册顺序不是产品策略。它可能随配置顺序、插件加载、HMR 或重构而变化。提供方选择必须是显式的,或仅在恰好只有一个可用提供方时自动选择。 + +### 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。 + +### 镜像 Claude Code 的 `url + prompt` WebFetch 形状 + +在 seam 层面否决。`prompt` 将 fetch 变成 LLM 摘要,并将公开 web 获取耦合到模型提供方。harness seam 应当确定性地获取和解码;`dsh-tool-web` 日后可以将摘要作为展示模式提供,而无需让 `ctx.web` 依赖 `ctx.llm`。 + +## 后果 + +**搜索 schema 刻意精简。** Exa 和 Perplexity 都暴露了有用的提供方特有控制;只有当某个控制能以提供方无关的方式定义、且工具注册和提供方执行都能诚实遵守时,才会添加。 + +**Perplexity 引用可能稀疏。** 一条引用可能只有 URL。将 `title` 和 `snippet` 设为可选使 seam 保持诚实,但意味着 `tool-web` 需要渲染回退标签。 + +**稳定的工具注册将配置错误推迟到执行时。** 当产品启用了 web 访问时,保持工具可见是正确的;但期望 web 搜索可用的产品应用应当醒目地浮出结构化的 `WEB_PROVIDER_CONFIGURED_MISSING`/`WEB_PROVIDER_CONFIGURED_UNAVAILABLE`/`WEB_PROVIDER_AMBIGUOUS` 失败,使用户不会在模型调用工具后才发现配置问题。 + +**提供方状态可能在启动后变化。** 一个工具可能在步骤开始时组装的请求中可见,但在执行前失去其提供方。执行路径重新解析并以结构化错误失败。 + +**Fetch 是网络边界,不仅仅是只读工具。** `web_fetch` 能触达敏感网络目标或通过 URL 外泄数据。仅交付基本传输卫生措施(仅 http/https、拒绝凭证、字节/时间上限、跨源重定向阻断);SSRF/私有网络阻断推迟(见[推迟工作](#deferred-work)),因此在其落地之前,`web_fetch` 不得在能触达内部目标的环境中启用。 + +**大量 web 内容可能损害上下文质量。** 提供方强制执行字节/字符上限并报告 `truncated`;`tool-web` 格式化有界的模型输出,附带清晰的继续或后续引导。 + +## 推迟工作 + +- `web_fetch` 的 SSRF/私有网络防护:阻断私有、回环、链路本地、多播及其他非公开目的地,使 `web_fetch` 不再是 SSRF 原语。正确实现不仅仅是 URL 字符串检查——需要先 DNS 解析再连接到已验证的 IP(防御 DNS rebinding/TOCTOU)、跨重定向的每跳重新验证,以及 IPv6 边缘处理(私有范围、IPv4 映射地址)。所调研的参考实现均未做 IP 级阻断(OpenCode 做前缀检查后直接 fetch;Claude Code 依赖集中式主机名黑名单加「私有 URL 会失败」的提示词),因此没有可复制的实现,且这是 harness 唯一的 SSRF 防线——值得一次专门的设计/spike。在其落地之前,`web_fetch` 只能在无法触达敏感内部目标的部署中启用。 +- `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。 +- `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? 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 new file mode 100644 index 0000000000..614868ada0 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-06-26-file-context-as-event-gate.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-26-file-context-as-event-gate.md: 4700222aa2e0f91d9f355495c228e2eb92825f55 +2026-06-26-file-context-as-event-gate.zh.md: 21c8706bcc14790a5092fa59e03bce329049760a 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 3f34cf3559..4700222aa2 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 @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-06-26-file-context-as-event-gate.zh.md) + ## Problem [The split-fs-seam Agent Note](../simplification/2026-06-26-fsspec-style-fs-seam.md) put `ctx.fileContext` between the model-facing tools and the `ctx.fs` provider: `dsh-tool-fs` injects `fileContext` and routes every `read`/`write`/`edit` through its methods. That makes `fileContext` **in-path and mandatory**. The tool cannot reach `ctx.fs` without it, the policy layer owns the fs I/O and the read windowing, and a deployment that does not want observed-state policy cannot simply drop the package — `dsh-tool-fs` would fail to resolve `ctx.fileContext`. 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 new file mode 100644 index 0000000000..21c8706bcc --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-06-26-file-context-as-event-gate.zh.md @@ -0,0 +1,171 @@ +# Agent Note: 将 `dsh-fs-policy` 改为事件门控插件,而非方法接口 + +Status: implemented + +[English](2026-06-26-file-context-as-event-gate.md) | 中文 + +## 问题 + +[拆分文件系统 seam Agent Note(agent 决策记录)](../simplification/2026-06-26-fsspec-style-fs-seam.md) 在面向模型的工具与 `ctx.fs` 提供方之间放置了 `ctx.fileContext`:`dsh-tool-fs` 注入 `fileContext`,并将每次 `read`/`write`/`edit` 路由到它的方法。这使得 `fileContext` **位于关键路径上且不可省略**。工具不经过它就无法访问 `ctx.fs`,策略层掌控着 fs I/O 和读取窗口,而一个不需要观测状态策略的部署也无法简单地移除该包——`dsh-tool-fs` 会因无法解析 `ctx.fileContext` 而失败。 + +这把三件本应可分离的事情耦合在了一起: + +1. **工具做什么**——解析路径、读取窗口、写入/编辑文件。这是工具的职责,只需要 `ctx.fs`。 +2. **新鲜度/观测策略**——「编辑前必须先读」、「写入/编辑必须基于你读到的版本」。这是 `dsh-fs-policy` 插件的职责。 +3. **观测状态的记录**——一个副作用,永远不应阻止工具正常运行。 + +由于工具调用的是 `fileContext` 方法,移除策略层就是一个破坏性变更,而非优雅地失去一个*附加*能力。策略层对工具的运行是承重性的,而非可选的收紧。 + +## 决策 + +反转控制流。**`dsh-tool-fs` 成为执行器,直接调用 `ctx.fs`**;**`dsh-fs-policy` 成为门控 + 记录插件**,通过事件参与,从不通过工具调用的方法,也不注册 `ctx.fileContext` 服务。 + +```text +tool dsh-tool-fs executor: resolves, reads windows, writes/edits via ctx.fs; + emits fs policy events; renders results +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 + 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。 + +`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`。 + +这是有意为之的。如果 `dsh-fs-policy` 在其 waterfall(瀑布式事件)处理器中 stat 并比较版本,该检查与工具实际写入之间会存在 TOCTOU 间隙——文件可能在此期间变化,因此该检查只是一个虚假保证,提供方的锁无论如何都要兜底。将版本检查放在提供方的临界区中既无竞态又无额外 `stat`。所以 `dsh-fs-policy` **不做**任何文件系统 I/O;「必须基于最近一次读取」的保证由 CAS *实现*,`dsh-fs-policy` 只负责选择基准(`vObserved`)并对先前观测进行门控。 + +## 提供方契约变更:版本守卫变为可选 + +为使裸提供方不受约束,其两个 mutation 上的版本守卫变为**可选**——传入则守卫,省略则无条件执行: + +```ts ignore-check +// writeText: expected is now optional. The FsWriteIntent union is UNCHANGED. +writeText(target: FsTarget, content: string, expected?: FsWriteIntent, signal?: AbortSignal): Promise<FsWriteOutcome> +// undefined → unconditionally create-or-overwrite (bare default) +// createIfAbsent → create only, reject an existing file (dsh-fs-policy, unobserved) [unchanged] +// replaceIfVersion → overwrite only at the observed version, else FS_STALE_VERSION [unchanged] + +// editText: expected becomes optional (was the required { version: FsVersion }). +editText(target: FsTarget, edit: FsEditRequest, expected?: { version: FsVersion }, signal?: AbortSignal): Promise<FsEditOutcome> +// undefined → unconditionally replace literal text in the current content (bare default); +// a missing target still reports FS_STALE_VERSION +// { version } → edit only at that version, else FS_STALE_VERSION (the current behavior) +``` + +`FsWriteIntent` 联合类型本身不变——第三种「无条件」状态通过*省略* `expected` 来表达,因此两个 mutation 共享同一种对称形状(`expected?`:省略 = 无守卫,传入 = 有守卫)。这对 `dsh-fs-policy` 使用的有守卫路径保持完全向后兼容;只有之前不可能出现的「无守卫」情况是新增的,且它是裸提供方的默认行为。无论哪种情况,mutation 仍在后端的 per-target 锁内运行,因此无条件写入/编辑仍是原子的(不会产生撕裂文件);「无条件」去掉的是*版本*前置条件,而非原子性。`editText` 在有守卫和无守卫路径上都将缺失目标报告为 `FS_STALE_VERSION`,保持一个统一的编辑失败码表示「此刻无法编辑该目标」。 + +## 事件词汇(由 `dsh-fs` 拥有) + +事件定义在 `@deepseek-ai/dsh-fs` 中,而非 `dsh-fs-policy` 中。这是解耦契约所迫:`dsh-tool-fs` 是发射方,因此它必须引用事件类型,且即使 `dsh-fs-policy` 不再提供方法服务,它也必须能编译通过。`dsh-fs` 是 `dsh-tool-fs` 和 `dsh-fs-policy` 都已依赖的包,因此它是唯一能让发射方和策略监听方共享词汇而不让发射方依赖策略插件的归属地。 + +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)。 + +**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。 + +```ts +import type { FsTarget, FsVersion, FsWriteIntent } from '@deepseek-ai/dsh-fs' + +interface Events { + /** + * Single-slot decision: produce the write expectation for the next + * ctx.fs.writeText. The default returns undefined (unconditional create-or- + * overwrite — the bare provider). The policy listener returns createIfAbsent + * (unobserved) or { kind: 'replaceIfVersion', version: vObserved } (observed). + * The listener does NOT call next(): one decision, not a composable chain. @mode waterfall + */ + 'fs/write-intent'(target: FsTarget, actor: object | undefined, next: () => FsWriteIntent | undefined | Promise<FsWriteIntent | undefined>): Promise<FsWriteIntent | undefined> + /** + * Single-slot decision: produce the optional version guard for the next + * ctx.fs.editText. The default returns undefined (unconditional edit of the + * current content — the bare provider; no stat). The policy listener returns + * { version: vObserved }, or throws FS_NOT_OBSERVED if the actor is unset or + * has not observed the target. Does NOT call next(): one decision. @mode waterfall + */ + '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 + * 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/*` 决策事件是**由工具分发的无绑定 waterfall**(类似 `agent/request`,由循环分发且无 `this`),而非服务绑定的 waterfall(如 `llm/stream`)。分发者是 `dsh-tool-fs` 插件,它不是一个服务。 + +## 工具契约(`dsh-tool-fs`) + +工具保留其面向模型的 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。 + +`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。 + +`dsh-tool-fs` 是一个注册全部三个工具(`read`/`write`/`edit`)的单一根插件,与 `dsh-tool-bash` 相同。它注入 `fs`(加 `tools`/`systemPrompt`),从不注入 `fileContext`。(最初的提案还将每个工具作为 `/read`/`/write`/`/edit` 子路径插件暴露,供聚焦部署使用;实现时被放弃——没有消费方需要单工具部署,且子路径发布迫使引入兄弟工具包都不需要的定制 `tsdown`/`tsconfig`/`files`/workspace-constraint 处理。每工具的注册辅助函数(`applyReadTool`/`applyWriteTool`/`applyEditTool`)仍作为根插件组合的内部模块保留。) + +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`。 + +工具在每次分发时将 `exec`(工具执行上下文)作为 `actor` 参数传入,以便 `dsh-fs-policy` 推导其观测状态的 owner。工具不知道策略插件是否存在:它始终在 `next` thunk 中提供裸默认行为,而 `dsh-fs-policy` 在默认部署中会在 thunk 运行前短路它。 + +**`fs/observed` 在操作成功后触发。** 其监听器必须是同步、不抛异常的记录器;工具不对 plain emit 做保护,因此抛异常的监听器会在 mutation 已成功后报告失败。异步或可失败的观测需要另一份事件契约。 + +## 策略插件契约(`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<owner, Map<targetKey, { version }>>`,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)`。 + +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)。 + +`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。 + +## 裸提供方行为(无 `dsh-fs-policy`) + +这不是预期的部署姿态——加载 fs 工具的配置预期也会加载 `dsh-fs-policy`。它是工具不再耦合于策略方法服务后所存在的无约束提供方下限。当 `dsh-fs-policy` 不存在时,每个 `fs/*` waterfall 落入其 `undefined` 默认值,`fs/observed` 无监听器: + +- **read** 行为不变(它从不需要策略;只是 emit 了一个现在无人监听的 `fs/observed`)。 +- **write** 无条件 create-or-overwrite:`expected` 为 `undefined`,因此 `writeText` 无论文件是否存在、无论当前版本如何都直接写入。无先读要求,无版本检查。 +- **edit** 无条件替换文件当前内容中的字面文本:`expected` 为 `undefined`,因此 `editText` 无版本守卫、无先读要求地匹配并重写(`FS_EDIT_NOT_FOUND`/`FS_AMBIGUOUS_EDIT` 仍适用——它们关乎字面匹配,而非新鲜度)。缺失目标仍报告 `FS_STALE_VERSION`,与有守卫编辑路径的「此刻无法编辑该目标」错误码一致。 + +两个 mutation 仍是原子的(后端的 per-target 锁是无条件的)。仅仅是*不存在*(而非丢失)的是 `dsh-fs-policy` 本会叠加的策略:观测状态、先读后编辑和版本守卫的写入/编辑。加载 `dsh-fs-policy` 后,其监听器返回有守卫的 `expected` 值而非 `undefined`,从而叠加这些约束;裸提供方本身无需任何变更。 + +## 取代关系 + +本 Agent Note 修正——而非推翻——[拆分文件系统 seam Agent Note](../simplification/2026-06-26-fsspec-style-fs-seam.md)。四层拆分、提供方契约和新鲜度*策略*均保留。变更的是**工具与策略层之间的耦合方式**:强制性方法服务变为插件拥有的事件门控,fs I/O + 读取窗口从 `fileContext` 上移至 `dsh-tool-fs`。拆分文件系统 seam Agent Note 中关于 `dsh-tool-fs` 注入 `fileContext` 以及 `fileContext` 拥有 `read`/`write`/`edit` 的描述已在同一变更中更新。 + +## 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。 + +## 曾考虑的替代方案 + +- **保留 `ctx.fileContext` 作为关键路径上的方法服务**——[拆分文件系统 seam Agent Note](../simplification/2026-06-26-fsspec-style-fs-seam.md) 最初落地的形态;否决,因为工具无法在没有策略层的情况下运行,使策略对基本操作是承重性的,而非可选的收紧。 +- **策略侧版本检查**(`dsh-fs-policy` 在其 waterfall 处理器中 stat 并比较版本)——否决,因为该检查与工具实际写入之间存在 TOCTOU 间隙;提供方的 mutation 临界区是唯一无竞态的位置,因此策略只选择 CAS 基准并对先前观测进行门控。 +- **每工具 `/read`/`/write`/`/edit` 子路径插件**——实现时放弃:没有消费方需要单工具部署,且子路径发布迫使引入兄弟工具包都不需要的定制 `tsdown`/`tsconfig`/`files`/workspace-constraint 处理;每工具的注册辅助函数仍作为根插件组合的内部模块保留。 + +## 后果 + +- **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`。 +- **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 new file mode 100644 index 0000000000..51d0eb9a78 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-30-bash-stdin-env-trusted-plugin-surface.md: 284cd45a66294dbc9e8207a1e00e9642d32d4e58 +2026-06-30-bash-stdin-env-trusted-plugin-surface.zh.md: 9486f8c35c5060150b072fb673acca5d4167ec1a 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 cc1de3c53e..284cd45a66 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 @@ -2,6 +2,8 @@ Status: implemented +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. 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 new file mode 100644 index 0000000000..9486f8c35c --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.zh.md @@ -0,0 +1,33 @@ +# Agent Note: 在 bash seam 上支持 stdin 与额外 env + +Status: implemented + +[English](2026-06-30-bash-stdin-env-trusted-plugin-surface.md) | 中文 + +## 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。 + +`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)。 + +## 决策 + +在 `BashExecRequest`(模型/插件侧请求)和 `BashExecSpec`(`run`/`start` 所作用的已解析 spec)上**同时**添加 `stdin?: string` 与 `env?: Record<string, string>`,并在 `dsh-bash-local` 中贯穿它们:`resolve()` 原样传递,`run()`/`start()` 将其传给 `runBash`,后者把字节写入子进程的 stdin 并合并额外 env。 + +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。 + +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保留 `DSH_*`:环境条目会被移除,普通 `env` 无法设置它们,受信的 `dshEnv` 最后合并。完整顺序为 `scrub(process.env, including DSH_*)` → `ENV_OVERRIDES` → 普通 `env` → `dshEnv`。 + +3. **`stdin`/`env` 在已解析 spec 上是 required-absent-OK(普通 optional),而非像 `owner` 那样 required-but-nullable。** `owner` 之所以是 required-but-nullable,是因为*静默*缺失的 owner 会产生一个无主、跨会话可读的任务——一个安全隐患,显式的 `undefined` 可以防范。`stdin`/`env` 没有这种风险:缺失意味着「无 stdin / 无额外 env」,这是安全的常规情况(所有模型驱动的调用都如此)。因此它们保持普通 optional,与 `signal` 一致。 + +`dsh-bash-local` 仅在有字节需要写入时才创建 stdin 管道;否则 fd 0 仍为 `/dev/null`,保持先前行为。它写入字节后关闭管道。子进程未读取即退出时产生的 `EPIPE` 被忽略,因为命令退出码和输出决定结果。 + +## 曾考虑的替代方案 + +**可配置的环境秘密擦除。** 否决,属于推测性需求。受信调用方可以在擦除之后显式提供所需值,无需削弱默认的环境保护。 + +## 后果 + +钩子桥接层通过既有的 bash seam 传递 JSON 载荷和钩子特定变量,保留其进程组终止、截断和溢出行为。模型接口面不变,bash 工具仍是模型调用请求构建的唯一所有者。相关词汇定义见 [bash 数据结构参考](../../../../docs/core-data-structures/bash.md)。 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 new file mode 100644 index 0000000000..2da1519019 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-06-30-event-domain-semantics.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-30-event-domain-semantics.md: 7310840088d4ff77ddf83c5c16753b4d46256692 +2026-06-30-event-domain-semantics.zh.md: 61d99878ab5e04b74d55d02789c434e0919bd785 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 56c3fdf231..7310840088 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 @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-06-30-event-domain-semantics.zh.md) + ## Problem The harness extends the agent loop through a Cordis event taxonomy (see [the microkernel event-taxonomy Agent Note](2026-06-11-microkernel-event-taxonomy.md)). As that taxonomy grew, the line between the three event domains blurred: 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 new file mode 100644 index 0000000000..61d99878ab --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-06-30-event-domain-semantics.zh.md @@ -0,0 +1,39 @@ +# Agent Note: 事件域语义——会话是事实日志,agent 是运行时表面 + +Status: implemented + +[English](2026-06-30-event-domain-semantics.md) | 中文 + +## 问题 + +harness 通过 Cordis 事件分类体系扩展 agent loop(智能体循环)(见[微内核事件分类体系 Agent Note](2026-06-11-microkernel-event-taxonomy.md))。随着该分类体系的增长,三个事件域之间的界限变得模糊: + +- `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。 + +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。 + +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。 + +## 决策 + +**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 `session/load` 回放共享同一路径。 +- **`agent/*`——运行时实时表面。** 始终携带活的 `Agent`。两种形态:拦截 waterfall(瀑布式事件)(`agent/request`、`agent/step-result`、`agent/turn-continuation`)可变更或否决;瞬态 emit(`agent/status`、`agent/error`、`agent/created`/`agent/disposed`、`agent/queued`)在持有 `Agent` 的情况下通知。轮次和步骤边界不在此处——它们是持久的会话事件,从 `session/event` 读取;token 流(`assistant/chunk`)和中途 steering(中途引导)(`steering/message`)同理。 +- **`tools/*`——工具注册表与执行 seam。** + +**边界规则:** 持久的、可回放的事实是 `SessionEvent`;实时拦截或瞬态/活对象信号是 `agent`/`tools` Cordis 事件。轮次或步骤边界是持久事实,因此存在于会话日志中并从 `session/event` 源读取——不会被镜像为 `agent/*` emit。 + +**将规则应用于边界镜像:** 全部四个边界镜像——`agent/turn-start`、`agent/turn-end`、`agent/step-start`、`agent/step-end`——被**移除**。没有生产消费方需要在边界处获取活的 `Agent`:ACP 桥接从 `session/event` 的 `turn/end` 加 `agent/status` 结算;唯一的轮次镜像消费方(`dsh-ui-stdio`,一个一次性测试 REPL)从 `session/event` 渲染边界,同时保留其实时目标对象用于固定的 `main` 标签。步骤镜像先被移除(它们完全没有消费方);轮次镜像在 ui-stdio 迁移后随之移除,见[移除边界镜像事件 Agent Note](../simplification/2026-06-20-remove-agent-boundary-mirror-events.md),该决策由它负责。移除 emit 也简化了循环的 `closeStep`/`closeTurn`(各只需一次 append,无需配对 emit)。 + +## 后果 + +- 循环不再 emit 任何边界镜像;`closeStep` 仅追加 `step/end`,`closeTurn` 仅追加 `turn/end`。`Session.append` 负责 post-commit observer 隔离,因此抛出异常的边界 observer 无法改变轮次结果或饿死后续消费方;接受或内部校验失败仍会在边界进入日志之前逃逸。 +- 之前通过已移除 emit 观察边界的测试,现在观察持久的 `turn/start`/`turn/end`/`step/start`/`step/end` 会话事件——它们固定的行为(边界顺序、步骤计数)不变;只是读取的源移到了规范源。那些测试*抛出异常的轮次边界 emit 监听器*的用例被删除,因为该代码路径不再存在(没有 emit 可供抛出)。按照 [AGENTS.md「测试记录行为,而非黄金真相」](../../../../AGENTS.md),行为与其测试一同迁移(或一同消亡)。 +- 循环仅在 `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](../simplification/2026-07-04-remove-agent-steering-mirror.md) 单独移除——它镜像的是持久的 `steering/message`。 +- Cordis 事件目录(`docs/cordis-catalog/events.md`)重新生成以移除镜像事件。 + +<!-- agent-note-format: alternatives-not-recorded (pre-format Agent Note) --> 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 new file mode 100644 index 0000000000..74c94e5b4f --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-07-02-fs-per-session-cwd.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-02-fs-per-session-cwd.md: aeb17e0a235720bee277f6533468dbdb6cae82dc +2026-07-02-fs-per-session-cwd.zh.md: b9ad4b868c472c8feb9e6f65e42b1658ffdcd2e0 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 0a6d9b85b1..aeb17e0a23 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 @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-07-02-fs-per-session-cwd.zh.md) + ## Problem The ACP bridge gives every session its own workspace: `session/new` records the editor's project directory as `SessionHeader.cwd`, and `dsh-tool-bash` defaults each bash call's `workdir` to the calling agent's `session.header.cwd` (see [the per-session cwd Agent Note work in `packages/ui/acp`](../../../../packages/ui/acp) and `resolveWorkdir` in `dsh-tool-bash`). So a bash command in session A runs in A's project, and in session B runs in B's — one server process, N workspaces. 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 new file mode 100644 index 0000000000..b9ad4b868c --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-07-02-fs-per-session-cwd.zh.md @@ -0,0 +1,39 @@ +# Agent Note: 相对文件系统路径按调用方的会话 cwd 解析 + +Status: implemented + +[English](2026-07-02-fs-per-session-cwd.md) | 中文 + +## 问题 + +ACP(Agent Client Protocol)桥接层为每个会话提供独立的工作区:`session/new` 将编辑器的项目目录记录为 `SessionHeader.cwd`,`dsh-tool-bash` 将每次 bash 调用的 `workdir` 默认设为调用方 agent(智能体)的 `session.header.cwd`(见 [`packages/ui/acp`](../../../../packages/ui/acp) 中的每会话 cwd Agent Note 工作与 `dsh-tool-bash` 中的 `resolveWorkdir`)。因此会话 A 中的 bash 命令在 A 的项目目录执行,会话 B 中的在 B 的项目目录执行——一个服务器进程,N 个工作区。 + +文件系统解析使用的是插件加载时的 cwd,而 bash 使用的是会话的项目目录。因此,当编辑器项目目录与服务器启动目录不同时,相对路径的解析结果就会不一致;快照测试因为让这两个路径相同而掩盖了这个 bug。 + +一个有效的绝对 cwd 本身可能看起来有两个父目录:当它包含 `symlink/..` 时,文件系统查找会先跟随符号链接再应用 `..`,而 `path.resolve()` 会从词法上抹掉这两个组件。如果用词法解析沙箱策略却从原始 cwd 启动 bash,就会把权限授予无关的词法父目录、拒绝真实工作区内的写入,并让文件系统工具把相对路径解析进错误目录。 + +普通的符号链接 cwd 在请求的相对路径包含 `..` 时也暴露同一区别:进程从符号链接的物理目标开始遍历,`path.resolve(cwd, path)` 却从其词法拼写开始遍历。因此,对于同一个模型提供的路径,read 会选择与 bash 或沙箱化 mutation 不同的文件。 + +## 决策 + +将调用方的会话 cwd 传入路径解析,与 `dsh-tool-bash` 对 `workdir` 的处理方式完全一致。当 cwd 或请求路径任一包含父目录段时,在任何词法 join 之前把 cwd 解析为原生文件系统标识;没有遍历会使标识可观察时,则保留普通 cwd 拼写以供展示。mutation 和沙箱化 bash 调用复用解析后的沙箱策略根目录,使一次调用只有一个工作区标识。**调用方**(即工具)提供 cwd;提供方不读取会话或 agent。 + +- `FileSystem.resolve` 接受 `resolve(path: string, opts?: { cwd?: string; signal?: AbortSignal }): Promise<FsTarget>`。`opts.cwd` 是相对 `path` 解析时的基准目录;绝对 `path` 忽略它;省略 `opts.cwd` 则使用后端自身的默认值。后端执行 I/O 时,`opts.signal` 可以取消解析。options 对象把调用方拥有的两个解析控制项放在一起,避免位置参数继续增长。 +- `dsh-fs-local.resolve` 使用 `resolveLocalTarget(opts?.cwd ?? this.config.cwd, path)`。`config.cwd` 仍作为调用方未提供 cwd 时的默认值(非 ACP/无会话场景,以及 `process.cwd()` 本身就是工作区的单会话 stdio 演示)。 +- `dsh-tool-fs` 的 `read`/`write`/`edit` 通过共享的 `sessionCwd(exec, requestedPath)` 辅助函数(`exec.agent?.session.header.cwd`,与 bash 的 `resolveWorkdir` 对应)获取会话 cwd,并传给 `resolve`。只要任一值中的父目录段可能跨越符号链接,该辅助函数就使用原生 realpath 语义,否则保留普通拼写;沙箱化 mutation 复用完整策略的 `workspaceRoot`;非 agent/无 header 的调用方得到 `undefined`,后端因此应用其默认值。 + +## 曾考虑的替代方案 + +### 为何由调用方(而非提供方)提供 cwd + +提供方 seam 不得依赖 `dsh-agent`/`dsh-session`——它是一个文本存储后端,沙箱或远程实现同样满足该接口,而这些实现没有「agent 会话」的概念。工具已经接收了 `ToolExecution`(`exec`),其中携带 agent,因此工具是将 `exec → cwd` 投影并向提供方传递一个纯字符串的正确位置。这遵循「包(package)边界处显式优于隐式」的约定:基准目录作为显式参数传入,提供方据此行动,而非让提供方越界去读取它不应知晓的会话。这也与 `dsh-tool-bash` 一一对应,使两个面向模型的文件操作接口以相同方式解析路径。 + +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。 + +## 后果 + +- 在 ACP 演示中,fs 工具与 bash 现在对每个会话的工作区达成一致;编辑器可以打开任意项目目录,两类工具都在该目录下操作。 +- 对于包含 `symlink/..` 的会话 cwd,或普通符号链接 cwd 搭配含父目录遍历的相对路径,bash、文件系统工具和沙箱授权都会从同一个物理工作区解析;词法父目录不会获得授权。 +- `FsTarget` 的标识不变:`targetKey` 仍为解析后绝对路径的 realpath,因此 observed-state 键控与符号链接标识不受影响——正确的每会话 cwd 产生与 bash 目标相同的 key。 +- 向后兼容:所有现有的 `resolve(path)` 调用(均在测试中)继续正常工作;新参数是可选的。 +- 单会话 stdio 演示不受影响:它不提供会话 cwd(其 agent 的会话没有 `cwd`),因此解析回退到 `config.cwd = process.cwd()`,即工作区本身。 diff --git a/.agents/notes/implemented/architecture/2026-07-02-result-time-applied-hunk-diffs.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-02-result-time-applied-hunk-diffs.i18n.yaml new file mode 100644 index 0000000000..632ba388a2 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-07-02-result-time-applied-hunk-diffs.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-02-result-time-applied-hunk-diffs.md: fe163484ad56858fabd55dacace1d56814bd93e4 +2026-07-02-result-time-applied-hunk-diffs.zh.md: e8283a40d96c031a84e2627117801b3043eb8904 diff --git a/.agents/notes/implemented/architecture/2026-07-02-result-time-applied-hunk-diffs.md b/.agents/notes/implemented/architecture/2026-07-02-result-time-applied-hunk-diffs.md index ce0f146b39..fe163484ad 100644 --- a/.agents/notes/implemented/architecture/2026-07-02-result-time-applied-hunk-diffs.md +++ b/.agents/notes/implemented/architecture/2026-07-02-result-time-applied-hunk-diffs.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-07-02-result-time-applied-hunk-diffs.zh.md) + ## Problem The [tagged render-intent union](2026-07-02-tool-render-intent-union.md) gave `dsh-tool-fs` write/edit a `card:'diff'` at CALL time, derived purely from the tool's args: write ⇒ `{oldText:null, newText:content}` (the whole new file), edit ⇒ `{oldText:old_string, newText:new_string}` (the bare replaced snippet). An editor renders that as an inline diff, but it is a **context-free** diff — the bare `old_string`→`new_string` with no surrounding lines, and a `replace_all` that touched five scattered sites still renders as one snippet pair. diff --git a/.agents/notes/implemented/architecture/2026-07-02-result-time-applied-hunk-diffs.zh.md b/.agents/notes/implemented/architecture/2026-07-02-result-time-applied-hunk-diffs.zh.md new file mode 100644 index 0000000000..e8283a40d9 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-07-02-result-time-applied-hunk-diffs.zh.md @@ -0,0 +1,57 @@ +# Agent Note: 结果时刻的 applied-hunk diff 用于文件变更 + +Status: implemented + +[English](2026-07-02-result-time-applied-hunk-diffs.md) | 中文 + +## 问题 + +[带标签的 render-intent 联合类型](2026-07-02-tool-render-intent-union.md)为 `dsh-tool-fs` 的 write/edit 在调用时刻提供了 `card:'diff'`,纯粹从工具参数推导:write ⇒ `{oldText:null, newText:content}`(整个新文件),edit ⇒ `{oldText:old_string, newText:new_string}`(裸替换片段)。编辑器将其渲染为行内 diff,但这是一个**无上下文**的 diff:裸的 `old_string`→`new_string` 没有周围行,而一次触及五个分散位置的 `replace_all` 仍然渲染为一对片段。 + +在对接 `claude-agent-acp` 自身的 ACP(Agent Client Protocol) bridge 时可以看到完整编辑器 diff 的样子:变更应用后,它发出第二个 `tool_call_update`,其 diff 是**带 ±3 行上下文的 applied hunk**(`replace_all` 的每个变更位置各一个 hunk),由工具的 `structuredPatch` 重建。这个结果时刻的 hunk 正是让 Zed 在文件中*原位*显示变更(而非浮动片段)的关键。我们的工具止步于调用时刻的片段;完成后的结果只携带纯文本「updated successfully」,没有 diff。 + +障碍在于一个 seam 边界:`presentResult(args, result)` 是 **`args` + 面向模型的 `result`(`{content, isError}`)的纯函数**——它在实时流式输出和会话日志回放中都会运行,因此必须具备回放确定性且不能做 I/O。它看不到文件的前后内容,而 `FsEditOutcome`/`FsWriteOutcome` 只携带替换计数和版本号,没有文本。因此无法计算——甚至无法携带——applied hunk 给 presenter。 + +## 决策 + +添加一个**持久化的、工具私有的展示通道**,使工具的 `execute` 能附加一个结果时刻的渲染载荷并在回放中存活,并用它来携带 applied-hunk diff。 + +### 1. 规范工具输出上的可回放展示投影(core) + +原始实现允许 `execute` 返回 `{ content, meta }`。[规范工具输出契约](2026-07-20-canonical-tool-output-contract.md)取代了这种编写形态:每个工具如今返回一个由 schema 声明的 JSON 值,`output.render(args, value)` 从中派生面向模型的内容块,可选的 `output.presentationMeta(args, value)` 则派生可回放的 UI 数据。 + +`presentationMeta` 是工具自有的 `JsonValue`,core 会持久化它,但不解释其中的字段。`Session.append` 将它与事件的其余部分一并校验,回放再把存储的载荷传回 `presentResult`;因此展示无需 I/O 或重新计算即可复现。规范值本身只存在于执行期间,不会加入会话格式。 + +这仍是通用形态(「工具投影持久化的结果展示」),而非 fs 特有;任何工具都可以使用。 + +### 2. 工具计算 hunk;后端返回 before/after(fs) + +按照 [capability-seam 拆分](2026-06-13-capability-seams.md),存储后端只返回**存储事实**,面向模型的工具拥有**展示**: + +- `dsh-fs` 将 `FsEditOutcome` 扩展为包含 `{ before: string; after: string }`,将 `FsWriteOutcome` 扩展为包含 `{ before: string | null; after: string }`(`before: null` 表示创建,或已存在但不可 diff 的二进制/非 UTF-8 文件)。本地后端在写入时已持有两份文本;它以原始 LF 规范化文本返回,**不让任何 diff/UI 概念进入 seam**。 +- `dsh-tool-fs` 返回规范的变更前/后事实,并将上下文 hunk 投影为 `meta: { diffs: FileDiff[] }`。成功的变更始终以 diff 卡片完成,因为 ACP 结果内容会替换待定卡片:创建或无变化的覆写回退到由参数推导的整文件 diff,而编辑使用 applied hunk。失败的变更不携带 diff 元数据,正常渲染其错误信息。 + +### 3. Bridge 渲染 `diff` 结果卡片 + +`ToolResultView` 新增 `DiffResultView { card:'diff'; title?; diffs: FileDiff[] }`;bridge 结果侧的 `switch (view.card)` 增加 `diff` 分支,发出 `{type:'diff'}` 的 `ToolCallContent` 块(与调用侧分支对称)。ACP 的 `tool_call_update.content` 在编辑器中替换调用时的内容,因此结果 diff **取代**调用时刻的片段(并防止面向模型的结果文本覆盖它)——两次更新序列(先调用片段,再结果 diff)与 `claude-agent-acp` 完全一致。 + +## 曾考虑的替代方案 + +**手写或 vendor diff 算法。** 上下文 hunk 有已知的边界情况,因此 `dsh-tool-fs` 使用带类型的 [`diff`](https://www.npmjs.com/package/diff) 包,并在一个模块中规范化 `structuredPatch` 输出。仓库的 vendor 策略适用于框架源码,而非每个叶子工具库。 + +## 后果 + +`tool/result` 事件携带工具私有的 `meta` 载荷;它属于磁盘格式词汇的一部分,由 `Session.append` 在运行时限制为 JSON。任何工具都可以投影持久化的结果展示,无需再改 core。diff 卡片在会话重载和快照回放时免费复现:它从日志中读回,从不重新计算。代价:覆写操作在内存中同时持有旧文本和新文本以计算仅用于 UI 的 hunk(`TODO(overwrite-diff-bound)`),且 `dsh-tool-fs` 引入了一个小型、知名的运行时依赖。 + +## 非目标 + +- **实时增量 diff 流式输出。** hunk 在变更完成后一次性计算;没有逐键 diff。 +- **对二进制/非 UTF-8 覆写做 diff。** 此类文件的 `before` 为 `null`(没有文本 diff 基础);写入仍然成功,结果渲染整文件 diff(`oldText: null`)而非上下文 hunk。 +- **重命名/移动 diff。** 仅限单个已解析路径的内容 diff。 +- **限制覆写 diff 基础的大小。** 覆写操作将整个旧文件读入内存以计算上下文 hunk(加上已持有的新内容),因此非常大的文本覆写会为仅 UI 用途的 diff 分配两份文本。未来的改进可以设定预读上限,超过阈值时回退到整文件/无上下文 diff;在读取位置以 `TODO(overwrite-diff-bound)` 跟踪。 + +## 相关 + +- 补全了[带标签的 render-intent 联合类型](2026-07-02-tool-render-intent-union.md)中作为非目标列出的最后一项表示差异——该 Agent Note 的「非目标」一节已更新,记录 applied-hunk diff 在此处交付。 +- 基于[文件系统 capability seam](2026-06-17-filesystem-capability-seam.md)(before/after 是后端返回的存储事实)和[事件溯源会话](2026-06-11-event-sourced-sessions.md)(`meta` 载荷持久化在 `tool/result` 事件上,因此回放可复现卡片)。 +- `meta` 通道有意设计为通用的:未来的工具(结构化搜索、数据表结果)可以附加自己的持久化结果展示而无需再改 core。 diff --git a/.agents/notes/implemented/architecture/2026-07-02-tool-render-intent-union.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-02-tool-render-intent-union.i18n.yaml new file mode 100644 index 0000000000..c4e769f684 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-07-02-tool-render-intent-union.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-02-tool-render-intent-union.md: c7adf8f405000ec7940f82e1e1e2406d86253461 +2026-07-02-tool-render-intent-union.zh.md: 01dff0daaacc45f5c85eb2c4380dc78800ce9a81 diff --git a/.agents/notes/implemented/architecture/2026-07-02-tool-render-intent-union.md b/.agents/notes/implemented/architecture/2026-07-02-tool-render-intent-union.md index 9d7fac0471..c7adf8f405 100644 --- a/.agents/notes/implemented/architecture/2026-07-02-tool-render-intent-union.md +++ b/.agents/notes/implemented/architecture/2026-07-02-tool-render-intent-union.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-07-02-tool-render-intent-union.zh.md) + ## Problem A tool declares how its calls render in a UI (an editor's tool-call card) through two callbacks, `presentCall`/`presentResult` on `ToolDefinition`, returning `ToolCallPresentation` / `ToolResultPresentation` with an optional `ToolTerminal` sub-shape. These grew incrementally into a **bag of optional fields**: `title`, `kind`, `rawInput`, `content`, `locations`, `terminal` on the call; `title`, `content`, `terminal` on the result; `cwd`/`output`/`exitCode`/`signal` on `ToolTerminal`. The split of responsibility is muddy: diff --git a/.agents/notes/implemented/architecture/2026-07-02-tool-render-intent-union.zh.md b/.agents/notes/implemented/architecture/2026-07-02-tool-render-intent-union.zh.md new file mode 100644 index 0000000000..01dff0daaa --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-07-02-tool-render-intent-union.zh.md @@ -0,0 +1,82 @@ +# Agent Note: 用于工具调用展示的带标签 render-intent 联合类型 + +Status: implemented + +[English](2026-07-02-tool-render-intent-union.md) | 中文 + +## 问题 + +工具通过 `ToolDefinition` 上的两个回调 `presentCall`/`presentResult` 声明其调用在 UI(编辑器的工具调用卡片)中如何渲染,返回 `ToolCallPresentation` / `ToolResultPresentation`,并带有一个可选的 `ToolTerminal` 子结构。这些类型在增量演进中变成了一个**可选字段的集合**:调用侧有 `title`、`kind`、`rawInput`、`content`、`locations`、`terminal`;结果侧有 `title`、`content`、`terminal`;`ToolTerminal` 上有 `cwd`/`output`/`exitCode`/`signal`。职责划分模糊不清: + +- 调用侧和结果侧的 `terminal` 字段重叠,bridge 需要将每次调用的 `content` 块、`terminal` 块和 `rawInput` 用临时条件逻辑拼接在一起。 +- 哪些组合是*合法的*没有文档说明:一个设置了 `content` 的 `terminal` 调用意味着「卡片上方的描述」;一个设置了 `terminal` 的 generic 调用毫无意义但类型上可表达。类型允许无意义的状态存在。 +- 无法表达编辑器最需要的文件工具能力:**diff 卡片**(`{path, oldText, newText}`,Zed 将其渲染为内联 diff / 新文件预览)。`ToolCallPresentation.content` 使用的是 *LLM(大语言模型)* 的 `ContentBlock[]` 词汇(text/image),工具根本无法请求 diff 展示。 + +`packages/core/tools/src/index.ts` 中已有的 `FIXME(tool-presentation)` 指出了修复方向:「重新设计类型,让工具一次性声明其渲染意图(例如按卡片种类的带标签联合类型),而非一堆由 bridge 拼接的可选字段。」被否决的 Agent Note [折叠工具拥有的 UI 呈现](../../rejected/simplification/2026-06-20-generic-tool-rendering.md)明确推迟了此事:富渲染「应当在至少有两个真实工具和两个真实消费方验证词汇之后,以带标签 render-intent 联合类型的形式回归。」该条件现已满足:两个生产者族(`dsh-tool-bash`、`dsh-tool-fs`)和两个消费方(ACP bridge 实时路径 + 快照回放路径)。 + +## 决策 + +用一个**以 `card` 为标签的可辨识联合类型**替代可选字段集合。工具为每次调用/结果声明一个渲染意图;bridge 根据标签分发。 + +```ts ignore-check +type FileLocation = { path: string; line?: number } +type FileDiff = { path: string; oldText: string | null; newText: string } // oldText null ⇒ new file + +// presentCall → ToolCallView +type ToolCallView = GenericCallView | TerminalCallView | DiffCallView +interface GenericCallView { card: 'generic'; title: string; kind?: ToolCallKind; rawInput?: unknown; content?: ContentBlock[]; locations?: FileLocation[] } +interface TerminalCallView { card: 'terminal'; title: string; description?: string; cwd?: string } +interface DiffCallView { card: 'diff'; title: string; diffs: FileDiff[]; locations?: FileLocation[] } + +// presentResult → ToolResultView +type ToolResultView = GenericResultView | TerminalResultView +interface GenericResultView { card: 'generic'; title?: string; content?: ContentBlock[] } +interface TerminalResultView { card: 'terminal'; title?: string; output?: string; exitCode?: number; signal?: string } +``` + +`card` 在每个变体上都是**必填**的——真正的判别式,而非可选默认值。bridge 执行 `switch (view.card) { case 'generic': … case 'terminal': … case 'diff': … default: assertNever(view) }`。该联合类型是**封闭的**(遵循 [switch 穷举约定](../../../../AGENTS.md)):第四种渲染意图(表格、图表)无论如何需要新的 bridge 代码来渲染,因此一个由插件添加但被 bridge 静默丢弃的变体,比编译错误更糟糕。新增变体会在 bridge 的 switch 处中断编译——这正是我们想要的信号。 + +### 为什么带标签联合类型优于字段集合 + +- **无效状态变得不可表达。** generic 卡片不能携带终端输出;terminal 卡片不能携带 diff。旧的字段集合允许所有这些组合。 +- **bridge 分发而非拼接。** 每种卡片一个分支,各自精确产出该卡片所需的协议格式(wire format),而非调和五个交互关系未文档化的可选字段。 +- **`diff` 成为一等意图。** `dsh-tool-fs` 的 write/edit 声明 `card:'diff'`;bridge 输出 ACP `{type:'diff', path, oldText, newText}` 的 `ToolCallContent`(已存在于 SDK 的 `ToolCallContent` 联合类型中,此前 bridge 未使用)。这正是本次重设计解锁的能力。 + +### 生产者映射 + +- `dsh-tool-fs` read → `generic`(`kind:'read'`,附带一个 follow-along `location`);write → `diff`(`oldText:null`);edit → `diff`(`oldText:old_string || null`,`newText:new_string ?? ''`)。这与 `claude-agent-acp` 的 `toolInfoFromToolUse` 中 Read/Write/Edit 各分支逐字段对应。 +- `dsh-tool-bash` foreground → `terminal` 调用 + `terminal` 结果;`run_in_background` → `generic`。通用 `task_*` 控制工具拥有各自的 generic 卡片。 +- `dsh-tool-todo` → `generic`。 + +### 终端回退的归属 + +`TerminalResultView` 只携带 `output`/`exitCode`/`signal`。不具备终端能力的 UI 需要一个围栏 ` ```console ` 文本回退;该推导移至 **bridge**(在无能力路径上将 `output` 包裹在围栏代码块中),而非由工具双重编码。这使 bash 工具的结果保持单一结构化形状,并逐字节保留既有的能力门控行为。 + +### 纯函数性保持不变 + +`presentCall`/`presentResult` 仍然是 `args`(`presentResult` 还有 result)的纯函数——它们在实时流式输出和会话日志回放中都会运行,因此必须具备回放确定性。每个 view 仅从 args 推导:write 的 diff 是新文件风格(`oldText:null`),因为工具在调用时没有旧内容;edit 的 diff 是 `old_string`→`new_string`。 + +## 相对路径显示标题 + +`claude-agent-acp` 将文件卡片标题中的路径相对于会话 cwd 做缩短处理(`toDisplayPath`)——显示 `Read src/foo.ts` 而非 `/abs/proj/src/foo.ts`——同时保持 `locations[]`/`diff.path` 为**原始路径**(编辑器打开真实路径)。我们的 `presentCall` 是纯函数/仅依赖 args,无法访问会话 cwd,因此这一相对化处理发生在 **bridge**,bridge 已经将会话 cwd 传入工具调用渲染逻辑(与它用于解析 terminal 卡片标题的 cwd 相同)。bridge 仅对标题做相对化,方式是对已知的 `locations[0].path`/`diffs[0].path` 子串做精确的结构化替换——对所有文件卡片类型通用,从不针对工具名做特殊处理。 + +## 曾考虑的替代方案 + +- **完全删除工具自有的展示**:即[被否决的 collapse 提案](../../rejected/simplification/2026-06-20-generic-tool-rendering.md);其自身的结论正是推迟到两个真实工具和两个真实消费方存在后再做此联合类型,该条件现已满足。 +- **可合并扩展的联合类型**(`ContentBlockMap` 模式):否决。新的渲染意图无论如何需要新的 bridge 代码来渲染,因此一个被 bridge 静默丢弃的插件添加变体,比封闭联合类型在 bridge 的 `assertNever` switch 处引发的编译错误更糟糕。 +- **保留可选字段集合**:即「问题」一节所剖析的现状:无效状态可表达、字段交互无文档、且完全无法请求 diff 卡片。 + +## 后果 + +新的渲染意图会在 bridge 的 switch 处引发编译中断——这是有意为之:渲染代码必须先于卡片种类存在。无效的卡片/字段组合现已不可表达,bash 回退推导归 bridge 所有,工具只返回一个结构化形状。第四种卡片(表格、图表)的门槛是在同一个变更中编写其 bridge 分支。 + +## 非目标 + +- **实时增量 `terminal_output_delta` 流式输出**与**命令分类**:终端渲染 Agent Note 自身推迟的后续工作,本 Agent Note 不涉及。 + +## 相关 + +- 取代[折叠工具拥有的 UI 呈现](../../rejected/simplification/2026-06-20-generic-tool-rendering.md)(已否决——「等两个真实工具和两个真实消费方,然后做带标签 render-intent 联合类型」)中的推迟决定。该条件现已满足;本 Agent Note 即为那个联合类型。 +- 被[结果时已应用 hunk 差异](2026-07-02-result-time-applied-hunk-diffs.md)扩展:后者添加了一个持久化的 `meta` 通道,使 write/edit 在结果时输出 `DiffResultView`(应用后的变更:带上下文行的 contextual hunk / 每个 `replace_all` 位点一个,或创建时的整文件 diff),叠加在本联合类型的调用时 diff 卡片之上。 +- 将 `ToolTerminal` 折入 [ACP terminal 与工具调用渲染](../feature/2026-06-18-acp-terminal-and-tool-rendering.md)所描述的 `terminal` view(`_meta` terminal 卡片约定和能力门控不变;仅 harness 侧的展示类型改变)。 +- ACP SDK 的 `Diff` / `ToolCallContent` 类型支撑新的 `diff` 卡片。 diff --git a/.agents/notes/implemented/architecture/2026-07-03-filesystem-directory-listing-seam.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-03-filesystem-directory-listing-seam.i18n.yaml new file mode 100644 index 0000000000..0a8c0d62fa --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-07-03-filesystem-directory-listing-seam.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-03-filesystem-directory-listing-seam.md: c7db576ff3c7a56622f90a4400bd9297c9591bef +2026-07-03-filesystem-directory-listing-seam.zh.md: 75ee6851127ca6d8c3fc60a66115d521d4627cdc diff --git a/.agents/notes/implemented/architecture/2026-07-03-filesystem-directory-listing-seam.md b/.agents/notes/implemented/architecture/2026-07-03-filesystem-directory-listing-seam.md index d40c50695d..c7db576ff3 100644 --- a/.agents/notes/implemented/architecture/2026-07-03-filesystem-directory-listing-seam.md +++ b/.agents/notes/implemented/architecture/2026-07-03-filesystem-directory-listing-seam.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-07-03-filesystem-directory-listing-seam.zh.md) + ## Problem `@deepseek-ai/dsh-fs` is the provider seam for filesystem access, with local and future non-local backends behind the same `ctx.fs` contract. Before this change it could resolve paths, stat targets, read text, stream text, write text, and edit text. That was enough for model-facing file tools, but not for non-model-facing consumers that need to enumerate directories without importing `node:fs`. diff --git a/.agents/notes/implemented/architecture/2026-07-03-filesystem-directory-listing-seam.zh.md b/.agents/notes/implemented/architecture/2026-07-03-filesystem-directory-listing-seam.zh.md new file mode 100644 index 0000000000..75ee685112 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-07-03-filesystem-directory-listing-seam.zh.md @@ -0,0 +1,53 @@ +# Agent Note: 为文件系统 seam 添加直接目录列举能力 + +Status: implemented + +[English](2026-07-03-filesystem-directory-listing-seam.md) | 中文 + +## 问题 + +`@deepseek-ai/dsh-fs` 是文件系统访问的提供方 seam,本地后端与未来的非本地后端共享同一个 `ctx.fs` 契约。在本次变更之前,它能解析路径、stat 目标、读取文本、流式读取文本、写入文本和编辑文本。这对面向模型的文件工具已经足够,但对于需要枚举目录而又不想直接导入 `node:fs` 的非模型侧消费方来说还不够。 + +直接的压力来自 skill(技能)加载:读取单个 `SKILL.md` 已经可以走 `ctx.get('fs')`,但发现哪些 skill 根目录包含 `<name>/SKILL.md` 或 `<name>.md` 仍需要目录枚举。如果仅在 `dsh-skill` 中添加目录列举,要么保留对 Node 的直接依赖,要么在文件系统提供方栈之外发明一个一次性的本地辅助函数。 + +本决策只添加提供方能力,不涉及面向模型的 `ls`/`list` 工具或 skill 发现机制的变更。那些消费方需要独立的 UX、提示词与策略决策。 + +## 决策 + +在 `@deepseek-ai/dsh-fs` 中添加 `FileSystem.listDir(target, signal?)`。 + +`listDir` 仅列举一层目录。它以稳定的名称顺序返回直接子项,包含以下字段: + +- `name`:子项的 basename; +- `type`:`file`、`directory` 或 `other`; +- `target`:已解析的子项 `FsTarget`; +- `version`:可用时返回的轻量元数据; +- `size`:可用时返回的常规文件大小。 + +它从不读取文件内容。递归遍历、glob 匹配、分页、搜索、文件监听和面向模型的渲染均有意不在范围内。 + +本地后端通过 `readdir({ withFileTypes: true })`、`resolveLocalTarget` 以及元数据 `stat`/`realpath` 探测来实现。结果顺序是确定性的(`name.localeCompare`),以保持未来消费方的提示词/列表输出稳定,并提高前缀缓存复用率。 + +损坏或已消失的子项可以表示为 `type: 'other'`(不带 `version`/`size`);它们不会中止整个列举。在列举目录或解析/探测子项元数据时遇到权限或后端 I/O 故障,则以结构化的 `FsError` 错误码使整个列举失败: + +- `FS_NOT_FOUND`:目标不存在; +- `FS_NOT_DIRECTORY`:目标存在但不是目录; +- `FS_PERMISSION_DENIED`:权限不足; +- `FS_IO_ERROR`:其他后端 I/O 故障; +- `FS_ABORTED`:调用被中止。 + +## 曾考虑的替代方案 + +**在添加 seam 的同时添加面向模型的 list 工具。** 否决。其提示词、schema 和渲染契约与提供方原语相互独立。 + +**让每个消费方自行枚举目录。** 否决。这会将 `dsh-skill` 等产品包绑定到 Node/本地文件系统行为上,绕过策略/远程/沙箱后端。 + +**让 `listDir` 支持递归或 glob 形式。** 暂时否决。skill 根发现只需要直接子项,而简单的单层列举是未来消费方可以安全组合的最小后端契约。 + +**跳过元数据解析失败的子项。** 否决。API 承诺返回已解析的子项 target,因此解析子项时的权限/IO 故障属于契约失败。损坏或已消失的子项是例外,因为它们仍可在不声称拥有一个活跃已解析文件的前提下被表示。 + +## 后果 + +每个文件系统后端现在必须多实现一个提供方原语。这是 harness 尚未发布时有意为之的基础工作,但也意味着未来的沙箱/远程后端需要定义等价的直接子项列举行为。 + +该能力仍停留在提供方层面。在消费方落地之前,ACP(Agent Client Protocol)/模型会话仍需使用 `bash` 等既有工具来列举目录。缺少面向模型的 `listdir` 工具是预期行为,而非接线错误。 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 new file mode 100644 index 0000000000..1f232965a5 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-05-prompt-variables-and-tool-guidance-ownership.md: 94f5fa409e7b539b48750d12576c7a342a30c9ba +2026-07-05-prompt-variables-and-tool-guidance-ownership.zh.md: f1379e143a94a3ae3a07b3120c6f0b9fc8561fe9 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 cdd37091a2..94f5fa409e 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 @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-07-05-prompt-variables-and-tool-guidance-ownership.zh.md) + ## Problem The assembled system prompt had four defects, all of one family: facts the harness already knows were restated by hand somewhere else, and drifted. 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 new file mode 100644 index 0000000000..f1379e143a --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.zh.md @@ -0,0 +1,72 @@ +# Agent Note: 提示词变量与工具指导归属 + +Status: implemented + +[English](2026-07-05-prompt-variables-and-tool-guidance-ownership.md) | 中文 + +## 问题 + +组装后的系统提示词存在四个缺陷,同属一类:harness 已知的事实在别处被手工重述,然后漂移。 + +**模型无法知道自己的名字。** `AgentOptions.model` 驱动每个请求,但没有任何提示词文本携带它——也不可能携带:`dsh-system-prompt` 中的 section 是上下文全局的,而模型名称是 per-agent 的,`assemble()` 根本不接受任何 per-agent 输入。 + +**工具指导是 leaf YAML 中的手写行文。** bash/subagent/todo_write 的使用指导存放在 coding-agent 和 ACP persona 字符串里——两份漂移的副本(ACP 那份已经被删减)——而 `dsh-tool-fs` 和 `dsh-tool-web` 则通过 `ctx.systemPrompt.section()` 贡献各自的指导。加载或卸载一个工具插件意味着手动编辑每个部署的 persona;两份 YAML 都带着一条 `FIXME(config-comments)` 为这种分裂的症状道歉,旧终端欢迎横幅也手动枚举了工具集。 + +**Persona 渲染在工具指导之后。** agent loop(智能体循环)将 `agent.options.systemPrompt` 字符串拼接在已组装的 section 之后,于是模型先读到「Use the read tool…」再读到「You are a coding agent」——与 identity-first 约定(Claude Code、Codex)相反,且是 section 流水线之外的第二条组合路径。 + +**Fork 工具的描述是假的。** `dsh-tool-subagent` 硬编码了一段为 spawn 语义编写的描述——「a separate agent that works in its own context … it does not see this conversation」——而 `subagent_fork` 实例(其子 agent 继承父级已完成的轮次)拿到了同样的措辞;YAML 行文在带外纠正了这个谎言。小问题:`PromptSection.name` 文档标注为「(diagnostics / dedup)」,但重复项被静默接受。 + +## 决策 + +**一条原则:提示词中的每个事实恰好有一个归属方。** 模型名称和工作区是配置/会话事实 → harness 将它们暴露为变量,persona 引用它们。每个工具的语义和何时使用 → 工具的 `description`。description 无法承载的跨调用习惯 → 工具包(package)的提示词 section。harness 来源标识 → 静态的 `harness:identity` section。部署角色与行为 → 部署的 persona。 + +### 组装上下文 + +`SystemPrompt.assemble(context)` 接受一个可合并扩展的 `AssembleContext`。`dsh-system-prompt` 声明可选的 `scope` 选择器用于 scoped 路由,而 `dsh-agent` 通过声明合并将可选的类型化 `agent` 字段附加到其上(类型层面的 `agent → system-prompt` 边,无运行时依赖循环)。循环在每个步骤调用 `assembleContextFor(agent)`,使两个字段标识同一个 agent;section 文本提供方可以读取该上下文,`system-prompt/assemble` waterfall(瀑布式事件)也接收它,监听器可据此按 agent 过滤或扩展。 + +### 提示词变量 + +插件通过 `ctx.systemPrompt.variable(name, provider)` 注册 `{{name}}` 值。组装过程将它们解析到 waterfall 可见的变量映射中。渲染阶段拒绝以下情况:引用了未知的 own-property、已注册的提供方返回 `undefined`、格式错误的完整引用、以及仍包含闭合 `}}` 的不平衡引用;孤立的未匹配 `{{` 保留为行文,替换后的值不会被重新扫描。注册阶段拒绝无效或重复的变量名,section 名称也必须唯一。 + +`dsh-agent-loop` 注册两个内置变量,均为上下文 agent 的纯投影:`model`(= `options.model`)和 `cwd`(= `session.header.cwd`)。示例 persona 写 `powered by the {{model}} model`——模型名称只在 `model:` 配置键中声明一次。`{{cwd}}` 仅在 ACP 示例中演示:每个 ACP 会话携带客户端的 cwd,而配置预创建的 stdio agent 没有 cwd(在那里声称 `{{cwd}}` 的 persona 会导致该轮次失败——这是有意为之)。变量留在 loop 插件上(不同于下面的 section):它们是本循环驱动的 agent 的运行时事实,替换循环自行提供自己的变量。 + +### Persona 作为 order-0 section + +`dsh-system-prompt` 拥有 order 为 `-100` 的 `harness:identity` 和 order 为 0 的配置 `deployment:persona`,因此两者在循环被替换时仍然存活。提示词渲染只有一条路径 `renderPrompt(assembly)`,已路由请求 header 因此会记录准确的提示词,稍后由 `ctx.tokenMeter` 为压缩压力回放。agent 作用域的 `deployment:persona` 遮蔽全局默认值,允许 subagent 提供方在发布前安装 persona。约定的 order 区间为:identity `-100`、persona `0`、工具指导 `100–199`。 + +### 工具指导归属 + +每个工具的语义和选择指导放在工具 description 中。提示词 section 只承载跨调用习惯,例如检查 bash 退出标记或优先使用文件系统工具而非 shell 命令。`todo_write` 和 subagent 工具不需要 section,因为它们的 description 包含完整契约。部署 persona 只包含角色和行为。 + +### Subagent 对话历史描述符 + +`SubagentProvider.inheritsParentContext` 描述的是对话种子,而非作用域、服务、工具或权限。spawn 和 ACP 将其设为 `false`;fork 设为 `true`。`dsh-tool-subagent` 根据该标志派生工具和提示词参数的描述,包括 fork 继承已完成轮次但不继承进行中轮次这一点。提供方生命周期事件使该措辞与响应式提供方注册保持同步;其设计动机见[提供方生命周期事件 Agent Note](2026-07-05-subagent-provider-lifecycle-events.md)。 + +## 曾考虑的替代方案 + +- **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。 +- **宽松插值(未知引用保留原样或替换为空)**:一个拼写错误 `{{modle}}`(或一个空洞)会被发送给模型,直到 transcript(文本记录)审查时才会被发现。 +- **在配置中为每个 subagent 实例编写措辞**:面向模型的行文回到每个部署 × 实例中,重蹈 P2 病症。**根据提供方名称选择措辞**:`providerName` 本身是配置,重命名提供方后会静默获得错误的措辞。 +- **在 `apply` 时解析提供方(加载顺序要求)** 与 **仅用 section 承载 subagent 措辞(在 assemble 时惰性解析)**:提供方生命周期事件的替代方案;两者均在[提供方生命周期事件 Agent Note](2026-07-05-subagent-provider-lifecycle-events.md)中被否决。 + +## 不在范围内 + +- 更多变量(`date`、platform、git 状态):注册表使每个变量成为拥有该事实的插件的一行贡献;本 Agent Note 不认领任何一个。 +- 为预创建的 stdio agent 提供配置 `cwd`(可让 stdio persona 使用 `{{cwd}}` 并按真实路径分区持久化):推迟到会话 cwd 方案重新讨论时。 + +## 交付的不变式 + +- tui-agent 的提示词通过一条组装路径依次渲染 identity、带插值模型名的 persona,然后是 fs/bash/web 指导。 +- fork 和 fresh subagent 的描述反映提供方是否继承已完成的对话轮次;工具随提供方生命周期变化而出现、消失和重新措辞。 +- 未知、无值、格式错误或不平衡的变量引用会指明 section 名称并抛出异常;重复的 section、变量和工具注册同样抛出异常。 +- 快照回放与提示词无关:它按轮次和步骤索引已记录的分片流,不比较发出的请求。 + +## 后果 + +- 组装后的提示词中每个事实现在恰好有一个归属方,leaf YAML 中手工维护的工具行文已消除:加载或卸载一个工具插件不再需要编辑任何部署的 persona。 +- `{{model}}` 在组装时反映 `AgentOptions.model`。如果一个插件在 `agent/request` waterfall 中切换模型,提示词对该步骤的声明就会过时;如果一个插件在那里提供模型(options.model 未设置——循环文档中记载的回退路径),变量在渲染时无值,包含 `{{model}}` 的 persona 会在 waterfall 运行前失败。两者的补救方式相同,就是归属规则本身:拥有延迟绑定模型事实的插件在 `system-prompt/assemble` waterfall 上提前声明它(`assembly.variables['model'] = …`)——一个归属方,两处声明;一个循环测试端到端固定了 supply 路径。已接受。 +- 当一个已绑定的提供方不存在时(尚未激活、已卸载、HMR(热模块替换)重载中),subagent 工具不存在,该窗口内的模型请求中不会包含它。这是诚实的状态——替代方案是注册一个 description 或执行都不可信的工具。 +- 严格性意味着 persona 可能在渲染时导致轮次失败(例如在无 cwd 的会话上使用 `{{cwd}}`)。失败是受控的——该轮次以 `error` 结束,循环存活——且这是一个我们希望大声暴露的撰写错误。 +- 目前没有在提示词行文中转义字面 `{{name}}` 的语法;如果真实提示词确实需要,再行添加。 diff --git a/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.i18n.yaml new file mode 100644 index 0000000000..f9c309c39f --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-05-reconstructable-requests.md: 153d37a2faf2265134d5ff9e88f0bbfa275328e0 +2026-07-05-reconstructable-requests.zh.md: caf51c3065e416fd11aebc1c1d4dc2ee248e2e5c 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 99a7633c5b..153d37a2fa 100644 --- a/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.md +++ b/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-07-05-reconstructable-requests.zh.md) + ## Problem The request pipeline did not guarantee prefix stability for provider caching, and the session log could not reconstruct what the model saw. It omitted model, system prompt, and tool schemas while allowing per-call request rewrites. Cache behavior and replay equivalence therefore depended on whichever plugins happened to be loaded. 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 new file mode 100644 index 0000000000..caf51c3065 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.zh.md @@ -0,0 +1,56 @@ +# Agent Note: 每个 LLM(大语言模型)请求都可从会话日志重建 + +Status: implemented + +[English](2026-07-05-reconstructable-requests.md) | 中文 + +## 问题 + +请求流水线未能保证前缀稳定性以利用提供方缓存,会话日志也无法重建模型实际看到的内容。日志遗漏了 model、系统提示词和工具 schema,同时允许逐次调用的请求改写。因此缓存行为和回放等价性取决于碰巧加载了哪些插件。 + +快乐路径的参考形态是 MiniCode 的 `LLMClient`:一个有状态的对话客户端,随对话推进只做追加而不重建,仅在系统提示词、工具集或压缩(compaction)真正改变了模型需要看到的内容时才重置。本 Agent Note 回答的设计问题是:如何在不放弃事件溯源的前提下获得这种纪律。 + +## 决策 + +### 原则 + +**模型可见 ⟺ 已记录。** 凡到达模型请求的内容都必须记录在会话日志中。可检查的推论:**循环发出的每个对话请求都是会话日志的纯函数**——任何人持有日志即可逐字节重建请求。精确的范围声明:该保证覆盖循环构建的 `GenerateOptions`;提供方协议格式(wire format)字节由此推导而来,因为两个适配器的序列化在固定代码版本下都是逐消息的纯函数;直接的一次性调用(压缩的 summarize 调用)记录其信封标量(`compact/summary.{provider, model, maxTokens}`),其输入是对日志区域的确定性代码运算——可从日志加代码重建,因为只有循环会标记请求归属,所以它们不在不变式内。 + +前缀缓存稳定性是推论 #1,而非标题:一个仅追加的日志经逐节点纯函数投影,在 header 不变时自然产出前一请求的追加扩展——稳定性是涌现的,不是管理出来的。字节精确的审计/回放是推论 #2;带*可归因*漂移的恢复与 fork 是推论 #3。 + +### 机制 + +**消息。** `Session.deriveMessages()` 带缓存:每个 surface 条目在首次出现时通过公开的逐事件函数 `deriveEventMessage(event)` 精确投影一次;surface 重写(压缩的 `replace`,即 `SurfaceManager.replaceGeneration`)触发重建。调用方每次获得一个新数组,底层是共享的深度冻结消息:通过投影变异已记录的历史是不可表达的(会抛异常),取代了旧的逐次调用克隆隔离。外部重建器对日志前缀折叠同一个公开函数,因此不可能有两条路径产生分歧。 + +`EpochHeader` 记录请求的非历史状态:调用配置、渲染后的系统提示词、工具 schema 和会话前缀,空值规范化为缺失。`request/header` 始终写入完整快照:首个循环实例使用 reason `initial`,后续实例使用 `resume`,实例内变更使用 `change`。`foldRequestHeader` 选择最新快照。旧的 `request/header-delta` 事件和已移除的 `fallback` reason 在追加或加载时都会被拒绝。 + +每个步骤重建提示词组装。在实例的首个步骤中,`agent/session-prefix` 以一个冻结的空种子为基础,用仅限请求的开场消息进行扩展;结果在通用 `agent/pre-step` 检查点与边界快照之前被冻结并缓存于该循环实例。首次调用配置从显式的 `AgentOptions` 出发,保留 fork 覆盖和恢复重配置;后续调用从折叠后的 header 出发。`agent/request` 只能替换那个冻结的配置种子,模型可见内容通过已记录的通道进入。循环记录欠下的 header 事件(前缀唯一的持久归宿),从前缀、快照和 header 构建 `GenerateOptions`,对其深度冻结但保持 `AbortSignal` 活跃。每实例状态仅有缓存的前缀和锚定快照是否已写入。 + +**`step/start` 是重建边界。** 一个步骤从该序列之前的事件推导消息。快照之后的注入加入下一次请求,事件发布期间的重入追加被拒绝。`agent/pre-step(agent, turn, step, signal)` 仍是当前请求所需内容的通用 seam。header 重建选择该步骤的 `request/header`,或在无新 header 写入时沿用前一个快照。 + +**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 + +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。 + +## 曾考虑的替代方案 + +- **客户端作为真源**(照搬 MiniCode):在日志之外多出一个运行时真相——两者漂移而无人察觉;见上节。 +- **镜像日志的有状态传输客户端**:重复对话状态,需要围绕监听器做回滚,留下未记录的编辑面,且仍无法重建请求 header。Session 拥有的缓存加已记录的 header 避免了这些分裂的真相。 +- **逐次调用的请求标量**(一个可自由变异的配置传给每次 `agent/request` 分发):监听器可以零记账地逐次切换 model,悄然放弃本设计旨在保护的提供方缓存。配置是逐对话的已记录状态;waterfall(瀑布式事件)提议,日志记录。 +- **检测并报告**(比较连续请求,发散时告警):事后捕获违规;违规请求仍可构造并发出。因接口层面的不可表达性而否决。 +- **事件驱动组装**(仅在变更信号时重新渲染):存在漏信号的 bug 类别——会话中途注册的工具发出 `tools/change` 而非 `system-prompt/change`,第三方提供方可能什么都不发。逐步骤渲染加值比较在零信号纪律下即可稳健工作。 +- **自定义 header-delta 编解码器**(系统行编辑、按名称键控的工具编辑、完整配置/前缀替换):减少了重复字节,却复制了表示及其 diff/apply/fallback 机制。完整快照只保留一种回放表示。 +- **Header 快照上的叙事性变更字段列表**:可以通过比较连续快照推导。`reason` 仍保留,因为实例边界无法从快照值推导。 + +## 后果 + +- 一个日志无法解释的请求不可能被意外构造——无论是循环还是监听器;变异已构建的请求会抛异常;每个 header 变更都是持久的、可 diff 的日志事件。 +- 在建议性通道之间做选择是变更频率的决策,而本设计使稳定的那个在结构上成为默认:`agent/session-prefix` 的贡献在每个循环实例中只组合一次并逐字复用,因此以零边际成本扩展可缓存前缀,且不可能在会话中途击穿提供方缓存;会话中途变化的内容通过仅追加的历史通道流入——`agent.inject()` 以及工具/prompt-submit 的 `additionalContexts`——每条都是持久的 `context/message`,付出一次代价后即被前缀缓存,代价是在历史和日志中累积。将会话冻结的开场内容路由到前缀,将变更通知路由到历史通道;逐步骤的仅限请求尾部槽位被有意放弃(无消费方,且持久追加覆盖了当前所有更新模式)。 +- 在提供方处仍需全价计算的内容是固有的且已记录的:压缩(其 `compact/*` 事件和替换条目)、真正的提示词、工具或配置变更(reason 为 `change` 的 `request/header`),或带漂移的进程边界(不同的 `resume` 快照)。提供方自身的 reasoning-content 排除由服务端管理。 +- `step/start` 监听器行为变更(见上文)是对插件唯一可观察的语义变更;`agent/pre-step` 是当前请求的 seam。 +- 工具结果裁剪(计划中)无需新机制:一个已记录的单条目 surface replace(`start === end`),携带同一 `callId` 下裁剪后的 `tool/result`——属压缩家族,回放正确,缓存击穿由相同的压力逻辑批量处理。 +- 会话日志每个循环实例增长一个 `request/header` 快照,并在真正变更时增加快照。它比 delta 编解码器更大,但相对分片密集型日志仍然很小,并只保留一种回放表示。`SESSION_FORMAT_VERSION` 保持 `0`;旧的 delta 事件被拒绝而非迁移。 +- 快照预期输出变更一次(每个 transcript(文本记录)增加其 header 事件);写入文件系统的 fixture(测试前置数据)以规范化的撰写形式存储,工具参数使用 cwd 相对路径,因为回放只对 cwd 无关的参数路径做往返。 +- FIXME(call-config-shape):重新审视 `LlmCallConfig` 的确切字段集——哪些字段对缓存而言真正属于 epoch 级别(`model` 毫无疑问;采样标量出于谨慎放在那里),以及当适配器需要时,提供方特定的额外项(reasoning 选项、额外 body 参数)应归属何处。 diff --git a/.agents/notes/implemented/architecture/2026-07-05-subagent-provider-lifecycle-events.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-05-subagent-provider-lifecycle-events.i18n.yaml new file mode 100644 index 0000000000..516dd4edcb --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-07-05-subagent-provider-lifecycle-events.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-05-subagent-provider-lifecycle-events.md: afd45027e8b56cbf1d17e6dec749d8602c81124d +2026-07-05-subagent-provider-lifecycle-events.zh.md: 58d439936a3f2cc51d8190cbebe8e68cdb14c855 diff --git a/.agents/notes/implemented/architecture/2026-07-05-subagent-provider-lifecycle-events.md b/.agents/notes/implemented/architecture/2026-07-05-subagent-provider-lifecycle-events.md index 44733bb8c9..afd45027e8 100644 --- a/.agents/notes/implemented/architecture/2026-07-05-subagent-provider-lifecycle-events.md +++ b/.agents/notes/implemented/architecture/2026-07-05-subagent-provider-lifecycle-events.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-07-05-subagent-provider-lifecycle-events.zh.md) + ## Problem [The prompt-variables Agent Note](2026-07-05-prompt-variables-and-tool-guidance-ownership.md) makes `dsh-tool-subagent` DERIVE its model-facing wording from its provider: `SubagentProvider.inheritsParentContext` (spawn/ACP `false`, fork `true`) drives both the tool description and the `prompt` parameter description, so the fork tool stops lying about context inheritance. That fix created a cross-fiber data dependency: a tool's description is fixed at TOOL REGISTRATION (deliberately — the description is where tool-choice guidance lives), but the provider arrives on its own plugin fiber, on no particular schedule. diff --git a/.agents/notes/implemented/architecture/2026-07-05-subagent-provider-lifecycle-events.zh.md b/.agents/notes/implemented/architecture/2026-07-05-subagent-provider-lifecycle-events.zh.md new file mode 100644 index 0000000000..58d439936a --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-07-05-subagent-provider-lifecycle-events.zh.md @@ -0,0 +1,36 @@ +# Agent Note: Subagent 提供方生命周期事件——`subagent/provider-added` / `subagent/provider-removed` + +Status: implemented + +[English](2026-07-05-subagent-provider-lifecycle-events.md) | 中文 + +## 问题 + +[提示词变量 Agent Note](2026-07-05-prompt-variables-and-tool-guidance-ownership.md) 让 `dsh-tool-subagent` 从其提供方派生面向模型的措辞:`SubagentProvider.inheritsParentContext`(spawn/ACP 为 `false`,fork 为 `true`)同时驱动工具描述和 `prompt` 参数描述,使 fork 工具不再在上下文继承问题上对模型撒谎。这一修复引入了跨 fiber 的数据依赖:工具描述在工具注册时固定(这是有意为之——描述是 tool-choice 引导所在之处),但提供方在自己的插件 fiber 上到达,时机不确定。 + +如果在工具插件的 `apply` 时刻解析提供方,就会产生一个隐式的加载顺序要求(「在 cordis.yml 中把后端列在工具前面」)。这个要求不成立,因为 Cordis Loader 并发启动同级条目,且 `Entry.init()` 不会等待激活完成:延迟到达的后端即使列在前面,也可能让工具 fiber 失败。Loader 不提供同级顺序保证——「异步状态不是同步状态」(见[防御性模式](../../../../docs/defensive-patterns.md))。 + +## 决策 + +注册表将提供方的成员变化作为类型化事件广播,消费方镜像这些事件而非假设顺序: + +- **`subagent/provider-added(provider)`**:一个提供方在 `ctx.subagents` 注册表中变为可解析。在注册时发出。 +- **`subagent/provider-removed(name)`**:一个提供方离开注册表(其插件 fiber 被 dispose(资源释放)——卸载或 HMR(热模块替换)重载)。从注册的 disposer 中发出。 + +`dsh-tool-subagent` 镜像其命名提供方的生命周期:当提供方可用(或变为可用)时注册工具——在那一刻从该提供方派生措辞——当提供方离开时注销工具,并在重新注册时(HMR 重载)重新派生。提供方不在时工具不存在,因此不会对模型撒谎。这里有意不留下任何需要文档化的加载顺序要求:事件让顺序问题消失,而非将其钉死。 + +这些事件还完善了 seam 的词汇:`ctx.subagents` 是一个命名注册表,多个委派后端(`spawn`、`fork`、`acp`)在其上共存;一个其他插件从中派生状态的注册表,应当以类型化事件广播成员变化,而非要求轮询或依赖加载顺序。 + +## 曾考虑的替代方案 + +- **在 `apply` 时解析提供方,不存在则抛异常**:否决。「先列后端」这一要求声称了 Loader 并不存在的顺序保证。 +- **重试查找(轮询直到提供方出现)**:最终能收敛,但在框架已有的机制(effect 注册 + disposal)之外发明了一套私有就绪协议;它也无法感知提供方离开,因此 HMR 会遗留一个措辞描述已 dispose 后端的工具。 +- **仅在 section 中放置 subagent 措辞,在组装时惰性解析**:同样能容忍任意加载顺序,但将 tool-choice 引导移出了描述,与提示词变量 Agent Note 建立的所有权规则相矛盾(每个工具的语义和何时使用属于描述)。响应式注册既保持描述的权威性,又不依赖顺序。 +- **根据提供方名称而非提供方对象确定措辞**:`providerName` 本身是配置,重命名后的提供方会静默获得错误的措辞;从已解析提供方自身的 `inheritsParentContext` 派生则不会漂移。 + +## 后果 + +- 从命名提供方派生状态的消费方响应 `subagent/provider-added`/`-removed` 事件,而非在 `apply` 时读取注册表;`dsh-tool-subagent` 是参考实现。 +- **添加时大声失败;移除时按监听器隔离。** 添加监听器可以回滚注册。移除在 disposal 期间运行,因此单个监听器抛异常只会被记录日志,不会饿死后续镜像或干扰拆解流程。`start()` 仍在每次运行时按名称解析提供方,防止陈旧工具调用已移除的后端。见[事件目录](../../../../docs/cordis-catalog/events.md)与[生产者/消费方映射](../../../../docs/event-producer-consumer.md)。 +- **工具不存在的窗口期。** 在后端 disposal 与重新注册之间(HMR 重载期间),模型看不到 subagent 工具。这是诚实的状态——替代方案是一个向空处分发的工具——工具注册表的 `tools/change` 事件发出会保持提示词组装的时效性。 +- **两个等待中的 fiber 共享同一 `toolName` 是无效配置,被延迟捕获。** 如果两个 `dsh-tool-subagent` 加载实例命名了不同的提供方但相同的 `toolName`,两者都会等待,先到达的提供方先注册;第二次注册仅在其提供方到达时才抛异常。插件中的 `TODO(subagent-dup-toolname)` 记录了这一影响范围;工具注册表的重名拒绝机制仍是最终防线。 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 new file mode 100644 index 0000000000..6d14977e92 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-06-timeout-deadline-library.md: 11d4b8cd48dd345d2324b63e01bd726f12d846b4 +2026-07-06-timeout-deadline-library.zh.md: 334914c689adf54a654c5907395c29ceeeb50891 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 1c407d777d..11d4b8cd48 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 @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-07-06-timeout-deadline-library.zh.md) + ## Problem Timeout handling was drifting apart across the tool-bearing capabilities, and the divergence was not superficial — it was the same logic re-implemented three ways, each with its own subtle correctness burden. 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 new file mode 100644 index 0000000000..334914c689 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.zh.md @@ -0,0 +1,115 @@ +# Agent Note: 共享的超时/截止时间原语,硬终止留给各能力自行实现 + +Status: implemented + +[English](2026-07-06-timeout-deadline-library.md) | 中文 + +## 问题 + +超时处理在各个承载工具的能力之间逐渐分化,而且这种分化并非表面的:同一套逻辑被以三种方式重新实现,各自带有微妙的正确性负担。 + +- **bash**([packages/bash/bash-local/src/run.ts](../../../../packages/bash/bash-local/src/run.ts))在进程管道内部有一套完整、正确的超时实现:一个经配置钳位的 `timeoutMs`,两个独立触发器(用于超时的 `killTimer` 和用于上游取消的 `onAbort` 监听器),各自调用同一个 `kill()` 闭包对进程组执行 SIGTERM→宽限期→SIGKILL 升级,以及两个正交的结果布尔值(`timedOut`、`aborted`)独立锁存。 +- **web_fetch**([packages/web/web-fetch-local/src/provider.ts](../../../../packages/web/web-fetch-local/src/provider.ts))有一套正确但*手写*的超时:构造一个 `AbortController`,连接 `setTimeout(() => controller.abort(new WebError(…, 'WEB_FETCH_TIMEOUT')))`,手动添加和移除上游信号监听器,在 `finally` 中清除定时器,并在 `translateAbortOrNetwork` 辅助函数中从 `signal.reason` 恢复超时原因(因为 reader 只抛出裸 `AbortError`)。 +- **web_search**([packages/web/tool-web/src/search.ts](../../../../packages/web/tool-web/src/search.ts))**完全没有超时**:`WebSearchRequest`([packages/web/web/src/types.ts](../../../../packages/web/web/src/types.ts))不携带 `timeoutMs` 字段,各提供方的 `search()` 只转发 `exec.signal`。(web_search 在本次设计中保持无超时——见「后果」。) + +每个新的外部进程或网络工具都要重新推导同样四件事:钳位请求值、启动定时器、将超时与上游取消融合、在出口处区分「超时」与「已取消」。而融合与原因恢复恰恰是最容易出微妙错误的部分(web_fetch 的 `signal.reason` 处理就是证据)。与此同时,各能力执行的*终止*操作不可归约地不同:bash 杀死一个 OS 进程组(工作运行在子进程中,在本运行时之外,只能通过信号触达),而 web 中止一个进程内的 `fetch`(undici 拆除 socket)。不存在一个能停止所有能力工作的单一机制。 + +## 决策 + +`@deepseek-ai/dsh-timeout` 位于 `packages/util/`(与 `dsh-brand` 同级),负责超时的*计时与分类*这一半;*终止*那一半——硬终止——留在各能力的实现中。它是一个纯函数库,**不是** Cordis 服务或插件:不接收 `ctx`、不注册任何东西、不持有跨调用状态、不发射事件。这里刻意不设中央「超时服务」,因为那样的服务必须知道如何停止每个能力的工作——而这正是微内核要排除在共享层之外的知识,也是 Codex 将 `ExecExpiration` 限定于 exec 族所示范的原则。 + +### 库的对外接口 + +四个函数、一个 watchdog 接口加一个 reason 类型: + +```ts ignore-check +/** The internal reason attached to a timeout abort, so consumers can classify it after the fact. */ +export class TimeoutReason extends Error { + override name = 'TimeoutReason' + + constructor(readonly code: string, readonly timeoutMs: number) { + super(`${code} after ${timeoutMs}ms`) + } +} + +/** Validate/fill a caller's optional positive hint from the backend's default, then cap at its max. */ +export function clampTimeout( + requested: number | undefined, + def: number, + max: number, + name = 'timeoutMs', +): number + +/** + * Build a deadline signal that aborts on upstream cancellation OR on timeout, + * with the timeout carrying a `TimeoutReason`. `timeoutMs <= 0` means "no + * timeout" (background tasks): forward only the upstream signal, arm no timer. + * The returned object's `[Symbol.dispose]` clears the timer — `using` for a + * scope-lifetime consumer, a manual call for an event-lifetime one. + */ +export function deadline( + upstream: AbortSignal | undefined, + timeoutMs: number, + code: string, +): { signal: AbortSignal; [Symbol.dispose](): void } + +/** A stable signal plus one-at-a-time, timer-guarded async-iterator demand. */ +export interface IdleWatchdog { + readonly signal: AbortSignal + next<T>(iterator: AsyncIterator<T>): Promise<IteratorResult<T>> + [Symbol.dispose](): void +} + +/** Arm only while one iterator `next()` is outstanding, then rearm on later demand. */ +export function idleWatchdog( + upstream: AbortSignal | undefined, + timeoutMs: number, + code: string, +): IdleWatchdog + +/** Recover the TimeoutReason from an aborted signal (or error); `code` scopes the match to this deadline's timer. */ +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。 + +### 职责划分 + +| 关注点 | 负责方 | +|---|---| +| 校验请求提示并钳位默认值/最大值 | `dsh-timeout`(`clampTimeout`):纯算术加共享的正有限请求契约 | +| 启动一次性定时器、到期中止、携带 reason、与上游取消融合 | `dsh-timeout`(`deadline`) | +| 仅围绕未结算的迭代器 demand 启动和重启 | `dsh-timeout`(`idleWatchdog`) | +| 清除定时器 | `dsh-timeout`(任一原语的 `[Symbol.dispose]`) | +| 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 | +| 默认值/最大值*数值* | 各能力的配置 | +| 超时 `code` 字符串 | 各能力(`WEB_FETCH_TIMEOUT` ≠ `BASH_TIMEOUT`) | + +信号只*通知*;终止始终是监听方的职责,而监听方因能力而异。bash 自行编写 `addEventListener('abort', kill)`,因为 OS 进程存在于本运行时之外,没有别的东西会杀死它;web 将 `d.signal` 交给 `fetch`,由 undici 拆除 socket。这也是文件读/写/编辑**不接受** `timeoutMs` 的原因:本地系统调用最多只能尽力中止,超时无法强制 `fsync`/`rename` 停止,添加超时将是一个违反「显式优于隐式」的隐式默认值。两个参考 agent 出于同样的原因对文件 I/O 不设超时。 + +### 各能力如何消费该库 + +- **web_fetch**:工具层保持校验并转发;提供方手写的 controller + `setTimeout` + 手动监听器 + `finally` + `signal.reason` 恢复被替换为提供方自有的 `deadline`/`timeoutOf`。已预先中止的上游信号仍然立即抛出 `WEB_ABORTED`;否则 `fetch` 使用融合后的 `d.signal` 运行,`translateAbortOrNetwork` 根据信号分类抛出的错误(`timeoutOf` → `WEB_FETCH_TIMEOUT`,否则已中止 → `WEB_ABORTED`,否则网络错误 → `WEB_PROVIDER_ERROR`)。公开的错误码契约不变,`TimeoutReason` 永远不会作为公开错误跨越 web seam。 +- **bash**:`resolve()` 将请求钳位为显式规格。前台 `run()` 创建 deadline 并将其信号传给进程执行,后者既有的 abort 监听器执行进程组 kill。执行器将首个 abort 分类为超时或取消。后台启动保持无超时,仅转发上游取消。 +- **LLM 适配器**:`dsh-llm-deepseek` 和 `dsh-llm-pi-ai` 用 `idleWatchdog` 包装实际的传输迭代。配置的五分钟间隔只覆盖尚未结算的提供方 demand,不包括下游消费方在分片之间花费的时间。稳定信号在整个调用期间传给 `fetch` 或 SDK,因此超时会关闭底层请求并映射为 `TIMEOUT`,而更早的调用方中止映射为 `ABORTED`。 + +## 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。 +- web_fetch 去除了其定制的 controller/timer/listener/reason-recovery;分类器现在基于 deadline 信号(`timeoutOf` + `aborted`)而非抛出错误的形状来判断,这在请求阶段的 reject-with-reason 和读取阶段的裸 `AbortError` 两种情况下都是健壮的。 +- `AbortSignal.any` 和 `using`/`Symbol.dispose` 在此首次进入本仓库(Node ≥ 24 基线,已满足)。 +- 模型流现在共享一个可重启的定时器契约,不会把滑动的空闲间隔变成总调用截止时间,也不会计入消费方思考时间。该原语仍然只做通知;适配器测试证明其传输观察到稳定信号并终止。 + +以下内容不在本次范围内,列出以标明边界:`web_search` 可以在其工具 schema/快照覆盖率规划就绪后获得可选的面向模型的 `timeout_ms`;未来基于 ripgrep 的文件系统发现工具可以在存在后消费同样的提供方自有 deadline 形状;`tools/execute` waterfall(瀑布式事件)中间件可以通过驱动 `exec.signal` 为每次工具调用设置默认 deadline——那将是一个*消费*本库的插件,仍然只做通知,硬终止仍是各能力自己的事。 + +## 曾考虑的替代方案 + +**统一的超时*插件* / `ctx.timeout` 服务。** 基于微内核原则否决。一个能停止任何工具工作的服务必须理解每个能力的终止机制(进程组 SIGKILL、socket 拆除、系统调用边界检查),这正是架构所禁止的「内核知道太多」。Codex 的 `ExecExpiration` 被限定于 exec 族,正是因为它驱动的 kill(`killpg`)是进程族特有的;MCP 和模型流各自保有自己的。不存在一个连贯的中间层能为所有东西拥有终止权,因此共享部分只能是纯计时/分类那一半——一个库,而非服务。 + +**每个工具各自实现超时,不共享代码(先前的现状,也是 Claude Code 的选择)。** 否决,因为它已经在产生分化和重复的正确性负担:web_fetch 手写了与未来网络/进程类工具各自需要重新推导的完全相同的 controller/reason 逻辑,而融合 + `signal.reason` 恢复正是容易出错的部分。Claude Code 容忍完全重复;本仓库有一个统一的共享 abort 通道(每次 `execute` 上的 `exec.signal`),使得一个小型共享原语严格更优,因此成本/收益不同。 + +**用 `withTimeout(promise, ms)` 包装器代替信号工厂。** 否决,因为让 promise 与定时器竞争只是在截止时间到达时 resolve *工具调用*的 promise,而不会停止底层工作——子进程或 fetch socket 会泄漏。分发信号并要求能力监听,才能强制一条真实的终止路径存在。这与「dispose 必须达到完全停稳,而非仅仅请求它」的防御性规则一致。 + +**保留 bash 独立的超时和取消触发器。** 否决,因为一个 deadline 信号移除了定制定时器并标准化了分类。竞争的原因报告先到达的那个 abort,而既有的 SIGTERM→SIGKILL 终止路径保持不变。 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 new file mode 100644 index 0000000000..bd2426f377 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-07-07-tool-call-timeout-policy.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-07-tool-call-timeout-policy.md: 69fd1ee721de69621d3b57c10d960da0651b94dd +2026-07-07-tool-call-timeout-policy.zh.md: c0dc56127cb983bd515db424d0ca37da9d0e978a 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 b7713fa8e0..69fd1ee721 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 @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-07-07-tool-call-timeout-policy.zh.md) + ## Problem The [timeout/deadline Agent Note](2026-07-06-timeout-deadline-library.md) extracted the timing-and-classification primitive into `@deepseek-ai/dsh-timeout`, but timeout policy was still attached to individual capabilities and model-facing schemas. `bash` exposed `timeoutMs`; `web_fetch` exposed `timeout_ms`; `web_search` had no model-facing timeout even though providers already honor `exec.signal`; a future grep/glob tool would either import the timeout library directly or invent its own timeout policy. That is the wrong authoring shape for a plugin SDK: a tool author should normally forward `exec.signal` to the implementation it calls, and deployment policy should decide the budget. 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 new file mode 100644 index 0000000000..c0dc56127c --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-07-07-tool-call-timeout-policy.zh.md @@ -0,0 +1,114 @@ +# Agent Note: 工具调用超时策略作为插件 + +Status: implemented + +[English](2026-07-07-tool-call-timeout-policy.md) | 中文 + +## 问题 + +[超时/截止时间 Agent Note](2026-07-06-timeout-deadline-library.md) 将计时与分类原语提取到了 `@deepseek-ai/dsh-timeout`,但超时策略仍然附着在各个能力和面向模型的 schema 上。`bash` 暴露了 `timeoutMs`;`web_fetch` 暴露了 `timeout_ms`;`web_search` 没有面向模型的超时参数,尽管提供方已经遵循 `exec.signal`;未来的 grep/glob 工具要么直接导入超时库,要么自行发明超时策略。对于一个插件 SDK 来说,这是错误的编写范式:工具作者通常只需将 `exec.signal` 转发给其调用的实现,而部署策略来决定预算。 + +与此同时,仓库中并非所有超时都是面向模型的工具调用预算。钩子通过直接调用 `ctx.bash` 执行命令钩子,而非通过 `ctx.tools.execute()`;`bash` 模型工具通过同一个后端复用前台执行、后台启动、后台轮询和钩子调用。一步到位地将所有超时移入工具插件会混淆这些路径,并有破坏钩子超时语义的风险。 + +## 决策 + +工具调用超时是仅适用于面向模型的工具执行的策略,由三部分组成: + +- `@deepseek-ai/dsh-timeout` 仍是拥有 `deadline()` 和 `timeoutOf()` 的共享库。 +- `@deepseek-ai/dsh-tools` 在 `tools/pre-execute` 和 `tools/post-execute` 之间有一个环绕分发的 waterfall(瀑布式事件)`tools/execute`。 +- `@deepseek-ai/dsh-timeout-policy` 从注册表读取每个工具声明的 `timeoutMs`,并通过派生新的 `exec.signal` 来包装有此声明的调用。 + +执行流水线如下: + +```text +ctx.tools.execute(exec) + -> tools/pre-execute + -> tools/execute + -> registry dispatch (the base next()) + -> tool.execute(args, exec) + -> thrown tool errors normalize to ToolExecutionResult + -> tools/post-execute +``` + +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 + +`@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。 + +catch 是基础 `next`(而非 waterfall 之外的东西)这一点至关重要:当提供方看到超时信号并抛出自己的上游中止错误时,注册表分发首先将其转换为普通错误结果,然后 `timeout-policy` 才能将最终结果替换为 `TOOL_TIMEOUT`。 + +### `timeout-policy` 插件 + +该插件是 `@deepseek-ai/dsh-timeout-policy`,一个零配置的函数/命名空间插件(`name` / `inject` / `apply`),位于 `packages/timeout/` 组。每个工具的预算声明在工具自身,而非本插件:`ToolDefinition` 携带一个可选的 `timeoutMs`,由拥有该工具的插件从自身配置中设置。例如 `dsh-tool-web` 将 `fetchTimeoutMs` / `searchTimeoutMs`(默认 30000)解析到 `web_fetch` / `web_search` 的定义上: + +```yaml +- id: timeout-policy + name: '@deepseek-ai/dsh-timeout-policy' +- id: tool-web + name: '@deepseek-ai/dsh-tool-web' + config: + fetchTimeoutMs: 30000 + searchTimeoutMs: 30000 +``` + +超时放在工具定义上而非自由文本名称映射中,消除了拼错名称导致策略不生效的问题。`defineTool` 校验预算为正有限数。分发期间,执行器派生截止信号并将其赋给 `exec.signal`;注册表依据[工具取消契约](2026-07-19-cooperative-tool-cancellation.md),在执行工具体之前将该截止信号与调用方的原始信号融合。执行器随后恢复调用方信号,并将自身的超时转换为 `TOOL_TIMEOUT`;没有预算的工具原样通过。 + +信号替换采用**就地修改 `exec.signal`** 的方式,而非向 `next()` 传递新对象。Cordis 的 waterfall `next()` 忽略传入的任何参数,并以共享的 payload 数组重新调用下游监听器(`vendor/cordis/src/events.ts`),因此修改共享对象是包装器向注册表提供截止信号的方式。注册表会在进入工具体前再次融合已捕获的调用方信号;插件则在 `finally` 中将 `exec.signal` 恢复为调用方的原始值,使 `tools/post-execute` 永远不会看到本插件的截止信号。 + +`timeout-policy` 拥有 `TOOL_TIMEOUT` 代码的两种用途:传递给 `deadline()`/`timeoutOf()` 的内部截止代码(有作用域,使嵌套的外层截止读为普通取消)和结构化工具结果错误代码。其替换结果为: + +```ts ignore-check +function toolTimeoutResult(timeoutMs: number): ToolExecutionResult { + return { + content: [{ type: 'text', text: `Error: tool call timed out after ${timeoutMs}ms` }], + isError: true, + error: { + message: `tool call timed out after ${timeoutMs}ms`, + info: { name: 'ToolTimeoutError', code: 'TOOL_TIMEOUT' }, + }, + } +} +``` + +这是一个协作式截止。它不会通过竞争工具 promise 来杀死任意工作;工具或其调用的能力必须遵循 `exec.signal` 并达到完全停稳。因此声明 `timeoutMs` 意味着「此工具与 `exec.signal` 协作」,插件 README 将此作为其契约。 + +无需新的会话事件来保证可重建性:`TOOL_TIMEOUT` 是该调用的最终面向模型的 `tool/result`,因此现有会话日志已经记录了下一次模型请求所见的内容和结构化 `{ name, code }` 错误。 + +### 现有工具适配 + +`web_fetch` 和 `web_search` 已迁移。`dsh-tool-web` 保留对其面向模型 schema 的所有权,这些 schema 不暴露超时旋钮:`web_fetch` 移除了 `timeout_ms` 参数以匹配参考 agent 的形状,`web_search` 保持仅查询。工具体不导入 `@deepseek-ai/dsh-timeout`;它们将 `exec.signal` 转发给 `ctx.web`。 + +`dsh-web-fetch-local` 保留一个配置级别的 `timeoutMs` 作为大型资源兜底,服务于直接调用 `ctx.web.fetch()` 的调用方和配置错误的部署;它不拥有面向模型的超时。当 `TOOL_TIMEOUT` 信号先到达 fetch 提供方时,提供方作用域的分类将其视为上游 `WEB_ABORTED`,而外层 `tools/execute` 包装器将最终工具结果替换为 `TOOL_TIMEOUT`。一个已发布的 web 工具部署将提供方兜底配置为高于 `timeout-policy` 预算,使工具调用策略在模型调用中通常胜出。 + +`bash` 保持当前的后端超时路径。`dsh-tool-bash` 继续暴露 `timeoutMs` 和 `run_in_background`;`dsh-bash-local` 继续使用 `@deepseek-ai/dsh-timeout` 处理 `BASH_TIMEOUT`;钩子桥接继续调用 `runHook()` 并通过 `ctx.bash` 传递 `timeoutMs`。这保持了前台/后台/钩子行为的稳定。 + +`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。 + +## 曾考虑的替代方案 + +**将插件命名为 `tool-timeout`。** 字面的 Agent Note 名称匹配了 `gen-tool-catalog` 完整性守卫的 `packages/*/tool-*` glob,该 glob 要求每个匹配项注册一个面向模型的工具。本插件不注册任何工具——它是一个 `tools/execute` 包装器——因此 `tool-*` 名称要么导致 `verify-tool-catalog` 失败,要么强制产生一个误导性的启动条目。包(package)为 `@deepseek-ai/dsh-timeout-policy`,位于新的 `packages/timeout/` 组;cordis.yml 的 `id` 仍可为 `timeout-policy`。 + +**仅保留逐工具的超时处理。** 这是 `bash` 和 `web_fetch` 的既有形态,也与 Claude Code 和 Codex 对 shell 命令的做法一致。它对 web 类工具不利,因为每个新的支持超时的工具都必须自行选择校验方式、上限语义、文档、快照和分类。插件集中了策略和分类,让每个工具的 schema 专注于业务输入。 + +**立即将所有超时策略移出 bash-local。** 长期来看更干净——bash-local 将成为纯子进程执行器,所有调用方自行管理截止时间。但作为第一步不合适,因为钩子直接调用 `ctx.bash`,且 bash 模型工具的前台/后台语义与工具调用生命周期不同。保留 `BASH_TIMEOUT` 维持了这些路径的稳定,同时让工具调用超时在更简单的工具上先行验证。 + +**为所有工具使用全局默认预算。** 方便,但会让工具作者意外:任何偶然运行超过全局预算的工具在插件加载后就会开始失败。逐工具声明预算使采纳成为有意的行为。 + +**暴露面向模型的 `timeout_ms` 覆盖参数。** Claude Code 的 `WebFetch`/`WebSearch` 和 Codex 的 web 工具将超时排除在模型调用形状之外。模型覆盖会使超时成为提示词语义的一部分,并迫使 `timeout-policy` 引入 schema/参数剥离规则。Web 超时仅作为部署策略。 + +**让 `timeout-policy` 自行匹配工具参数。** 诸如「当 `bash.run_in_background` 为 true 时禁用超时」之类的规则引擎会让策略插件了解工具特定的参数语义。通过不将 bash 迁移到工具调用超时来规避此问题。 + +**使用 `tools/pre-execute` 加 `tools/post-execute` 代替新的环绕 seam。** pre 监听器可以启动截止时间并修改 `exec.signal`;post 监听器可以分类并替换。这样做的问题是截止时间的生命周期会跨越两个独立的 waterfall:需要 call-id 映射、在每条 pre-deny/tool-throw/post-throw/dispose 路径上清理,以及与其他监听器的排序规则。`tools/pre-execute` 也是允许/拒绝门禁,而非执行包装器。`tools/execute` 给超时一个词法作用域:启动、委托、分类、释放。 + +**使用 `Promise.race` 对非协作工具强制超时。** 与超时库 Agent Note 相同的理由否决:它在底层进程、fetch 或提供方操作可能仍在运行时就将控制权返回给调用方。插件只发送信号;终止仍是实现方的责任。 + +## 后果 + +- `@deepseek-ai/dsh-tools` 在有意拆分 pre/post 工具钩子的拦截 seam 之后,获得了一个环绕分发的表面。其契约是狭窄的——包装注册表分发,而非替代 pre 门禁或 post 结果策略——且基础 `next()` 是带规范化的分发,因此包装器永远不会看到原始的工具抛出。 +- 多个 `tools/execute` 监听器按普通 Cordis waterfall 顺序组合:调用 `next()` 的监听器包装下游监听器加分发;不调用 `next()` 直接返回的监听器短路它们。一个同时组合超时与未来重试/沙箱/指标包装器的部署通过注册顺序选择语义(「超时覆盖整个重试」vs「超时覆盖每次尝试」)。 +- 按声明加入是一个有意的误配置风险:工具可以声明 `timeoutMs` 但不遵循 `exec.signal`,这样的工具在超时时不会停止。注册表会等待这一未达完全停稳的工具体,而不是竞速它;同时插件契约声明:声明预算意味着协作;web 工具在已转发信号的工具上验证了这一模式。 +- 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 new file mode 100644 index 0000000000..67955d377d --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-07-08-agent-scope-contexts.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-08-agent-scope-contexts.md: e4c076189a8e8a438b561232d3779ad1f6ab0d08 +2026-07-08-agent-scope-contexts.zh.md: 35e725e43d402b048daf12c3b4be384b3fd2d2ce diff --git a/.agents/notes/implemented/architecture/2026-07-08-agent-scope-contexts.md b/.agents/notes/implemented/architecture/2026-07-08-agent-scope-contexts.md index 68c9bd3b3e..e4c076189a 100644 --- a/.agents/notes/implemented/architecture/2026-07-08-agent-scope-contexts.md +++ b/.agents/notes/implemented/architecture/2026-07-08-agent-scope-contexts.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-07-08-agent-scope-contexts.zh.md) + ## Problem One application needs to share infrastructure across many agents while letting each agent have its own tools, prompt contributions, policies, and listeners. Shared adapters, persistence, and user interfaces belong to the deployment; a persona, tool variant, or listener often belongs to one agent. 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 new file mode 100644 index 0000000000..35e725e43d --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-07-08-agent-scope-contexts.zh.md @@ -0,0 +1,171 @@ +# Agent Note: agent 即注册作用域 + +Status: implemented + +[English](2026-07-08-agent-scope-contexts.md) | 中文 + +## 问题 + +一个应用需要在多个 agent(智能体)之间共享基础设施,同时让每个 agent 拥有自己的工具、提示词贡献、策略和监听器。共享的适配器、持久化和用户界面属于部署层面;而 persona、工具变体或监听器往往只属于某一个 agent。 + +为每个 agent 建立独立的服务图会重复共享基础设施。使用一个全局注册图则有相反的问题:某个 agent 特有的贡献可能泄漏到无关的 agent 中。贡献者需要一种普通的注册机制,既能决定谁可以看到某项贡献,又能决定何时清理它。 + +该机制还需要一个发布边界。agent 在其本地世界构建完成之前不得变为可见,拆除时也必须保留该本地世界直到最终工作停止。 + +## 决策 + +每个存活的 agent 拥有一个扁平的注册层,通过 `agent.ctx` 暴露。代码通过拥有某项贡献的上下文进行注册;具备作用域感知的服务将部署全局注册与恰好一个匹配的 agent 层合并;操作从其真实 agent 选择该层;该层在 agent 的完整发布生命周期内存在。 + +Cordis 是 SDK 底层的插件框架。Cordis **上下文**是插件用来访问服务和注册效果的对象,效果的清理跟随该上下文。[Cordis 入门](../../../../docs/cordis-primer.md)对该框架有更详细的说明。 + +对大多数贡献者而言,完整契约是四条规则: + +| 问题 | 规则 | +|---|---| +| 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 | + +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。 + +```mermaid +flowchart LR + plain["Plain plugin context<br/>cleanup follows the plugin"] -->|"registers into"| globalLayer["Deployment-global layer"] + agentAContext["agentA.ctx<br/>cleanup follows Agent A"] -->|"registers into"| agentALayer["Agent A layer"] + agentBContext["agentB.ctx<br/>cleanup follows Agent B"] -->|"registers into"| agentBLayer["Agent B layer"] + + operationA["Operation for Agent A"] -->|"selects"| agentAView["Agent A view<br/>globals plus A local"] + globalLayer --> agentAView + agentALayer --> agentAView + operationB["Operation for Agent B"] -->|"selects"| agentBView["Agent B view<br/>globals plus B local"] + globalLayer --> agentBView + agentBLayer --> agentBView +``` + +缺失的交叉边即隔离规则:Agent A 的本地注册不会进入 Agent B 的视图,父级的注册也不会仅因父级拥有子级的生命周期就进入子级。 + +配套的[运行时设计 Agent Note](2026-07-12-agent-scope-runtime-design.md) 阐述了实现与正确性推理。[subagent 组合控制 Agent Note](../feature/2026-07-12-subagent-persona-tool-filter-and-depth.md) 负责独立的 `persona`、`toolFilter` 和 `maxDepth` 功能。 + +### 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。 + +| 注册来源 | 默认可见性 | 随谁 dispose | +|---|---|---| +| 普通插件上下文 | 每个符合条件的 agent 视图 | 注册插件 | +| `agent.ctx` | 仅该 agent 的视图 | agent 作用域 | + +工具、提示词段落与变量、工具限制、守卫以及作用域事件监听器都遵循此契约。命名的本地值通常对该 agent 遮蔽同名全局值;各所属服务文档会说明例外与合并行为。 + +普通贡献者的模式是在 agent setup 期间注册完整的本地世界: + +```js +const handle = await ctx.agents.create({ + sessionId: SessionId('reviewer'), + agentOptions: { model: 'model-name' }, + setup(agentCtx) { + agentCtx.systemPrompt.section({ + name: 'deployment:persona', + order: 0, + text: 'Review code, but do not modify files.', + }) + agentCtx.tools.register({ + name: 'review_summary', + description: 'Return the review summary.', + parameters: { type: 'object', properties: {} }, + async execute() { + return [{ type: 'text', text: 'review complete' }] + }, + }) + }, +}) + +ctx.tools.get('review_summary') // undefined: not global +ctx.tools.get('review_summary', handle.agent) // the reviewer-local tool + +await handle.dispose() +ctx.tools.get('review_summary', handle.agent) // undefined: scope is gone +``` + +setup 接收一个完整的受信 Cordis 上下文,因此可以组合普通插件和服务。其契约仅限组合:不支持通过 cast 或内部注册表调用来驱动或发布正在构建中的 agent。 + +### 操作选择视图 + +注册来源与操作主体是两个独立的事实。通过 `agent.ctx` 调用服务决定的是新注册归属何处,并不将后续读取绑定到该 agent。 + +工具查找与执行接收其所服务的 agent。提示词组装接收正在构建请求的 agent 的组装上下文。事件分发接收其领域主体。这使共享服务实例可在多个 agent 间复用,同时让每个操作的视图保持显式。 + +只有采纳了作用域契约的服务才会解析 agent 层。`agent.ctx` 不会自动改变任意 Cordis 服务调用的行为。 + +### 作用域事件将路由与事件数据分离 + +关于 Agent A 的事件通常到达无作用域监听器和 A 作用域监听器,而不到达 B 作用域监听器。没有 agent 主体的事件仅到达无作用域监听器。 + +在 Cordis 层面,`Scoped<T>` 是一个不透明的路由接收器。它携带用于选择监听器的过滤器,但本身不是领域对象。因此事件签名将真实的 `Agent`、工具执行、审批请求或其他主体作为显式参数保留,供监听器检查。 + +以 `{ global: true }` 注册的监听器有意绕过上下文受众过滤,但其清理仍跟随注册上下文。注册表成员变更通知保持不过滤,因为它们描述的是共享注册表状态而非某个 agent 的操作。生成的[事件目录](../../../../docs/cordis-catalog/events.md)是详尽的事件参考。 + +### 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`,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。 + +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、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。 + +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。 + +```mermaid +flowchart TB + request["Create or resume"] --> privateWorld["Build private session, scope, agent, and driver"] + privateWorld --> setup["Await composition through agent.ctx"] + setup --> admission["Admit final session and agent entries"] + admission --> publish["Announce lifecycle and start the driver"] + publish --> live["Return AgentHandle"] + + privateWorld -->|"failure, cancellation, or owner loss"| rollback["Rollback private work"] + setup -->|"failure, cancellation, or owner loss"| rollback + admission -->|"duplicate or owner loss"| rollback + publish -->|"listener failure or owner loss"| rollback + live -->|"handle or owner disposal"| quiesce["Stop and drain work"] + rollback --> quiesce + quiesce --> detach["Detach agent, then session"] + detach --> revoke["Dispose the agent scope"] +``` + +## 安全与权限是非目标 + +agent 作用域组合的是受信的同进程注册。它不沙箱化插件、不定义父到子的权限格、不在创建时冻结授权、也不保证子级不能做超出父级的事。 + +父级可以拥有一个可见工具比自身更广的子级,因为生命周期所有权不赠予也不限制注册。持有 Cordis 上下文的插件同样运行在同一进程中,可以直接调用可用服务。 + +需要非升权保证的部署需要独立的权限表示、传播规则和执行检查。父级子集授权、创建时授权快照、显式未来授权 API,以及通用的能力/输出/终止标签均不在本决策范围内。 + +## 曾考虑的替代方案 + +被否决的设计要么将可见性与清理分离,要么只覆盖一类注册,要么重复共享基础设施,要么将生命周期所有权与继承混为一谈。 + +### 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。 + +### 过滤事件但保持注册表全局 + +监听器过滤可以阻止错误的钩子运行,但无法限定工具 schema、可执行查找、提示词段落、变量或其他已注册数据的作用域。agent 本地组合仍需临时的全局变更。 + +### 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。 + +### 继承父级注册作用域 + +父子关系描述的是生命周期和对话谱系,而非通用合并策略。层级查找会让无关服务意外继承,且在没有独立权限模型的情况下无法定义安全性。 + +## 后果 + +贡献者使用一种熟悉的模式:通过插件上下文注册共享行为,通过 `agent.ctx` 注册本地行为,在操作中选择真实 agent,dispose 返回的 handle。从观察者角度看 setup 是原子的,拆除则保留本地行为直到工作停止。 + +代价是显式的主体选择、异步的编程式创建,以及服务需要逐个采纳作用域。扁平注册作用域有意不等同于权限,subagent 组合控制作为独立功能存在,而非隐藏的作用域语义。 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 new file mode 100644 index 0000000000..b003d4de31 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-07-12-agent-scope-runtime-design.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-12-agent-scope-runtime-design.md: cf42bbacbfb9d2fcbd72aafba5ea02ddf83e1ce5 +2026-07-12-agent-scope-runtime-design.zh.md: d0d599664290dc7dc4debe1ccf8f419a40912ba1 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 bc27d37268..cf42bbacbf 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 @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-07-12-agent-scope-runtime-design.zh.md) + ## Problem The [agent-scope contract](2026-07-08-agent-scope-contexts.md) is simple for contributors: register through `agent.ctx`, resolve one global-plus-agent view, publish only after setup, and retain the scope until work stops. The runtime must preserve that contract across a cooperative plugin framework, asynchronous creation, reentrant listeners, durable session commits, and worker or process failure. 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 new file mode 100644 index 0000000000..d0d5996642 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-07-12-agent-scope-runtime-design.zh.md @@ -0,0 +1,392 @@ +# Agent Note: Agent 作用域运行时设计与正确性 + +Status: implemented + +[English](2026-07-12-agent-scope-runtime-design.md) | 中文 + +## 问题 + +[agent 作用域契约](2026-07-08-agent-scope-contexts.md)对贡献者而言很简单:通过 `agent.ctx` 注册,解析出一个全局加单 agent 的视图,仅在 setup 完成后发布,并保持作用域直到工作停止。运行时必须在协作式插件框架、异步创建、可重入监听器、持久化会话提交以及 worker 或进程故障等场景下维护这份契约。 + +主要的设计风险是为每个竞态条件引入第二套机制。独立的预留、就绪哨兵、取消中继、快照层和保护注册表可能镜像同一个事实,直到没有读者能分辨哪个才是权威的。这些机制还会诱使运行时把可信的类型化调用当作敌对的序列化边界来处理。 + +实现需要足够的状态来维护真实的所有权和结算边界,但不能更多。正确性审查者必须能够从接受、发布到拆除,沿着一条事实链跟踪下去,而无需在并行的表示之间做调和。 + +## 决策 + +运行时对每个独立事实使用一种机制。作用域路由有一个不透明载体与共享 layer store;每个活跃的注册表对象有一条注册表条目;每个创建或恢复操作有一个事务;类型化的同进程调用借用 readonly 值;真实数据边界只物化一次;协作式提示词组装的结果即为权威;worker/进程代码仅在不同所有者确实可能竞争时才保留独立的终止态和完全停稳态。 + +该设计可概括为七项选择: + +| 问题 | 权威机制 | +|---|---| +| 选择全局加某个 agent 的注册 | 不透明作用域键、路由载体与共享 layer store | +| 拥有一个活跃的 agent 或会话 | 由其 disposer 捕获的单条注册表条目 | +| 协调创建/恢复 | 单个 `AgentCreationTransaction` | +| 保护持久化、队列、模型或协议格式数据 | 在该边界处一次性物化 | +| 在同一进程内传递类型化值 | Readonly 借用契约 | +| 组合模型可见的提示词与工具表面 | 单个共享工具视图加权威的 assembly-waterfall 结果 | +| 协调 subagent、worker 和进程关闭 | 单个取消信号加该边界独立的终止态/完全停稳态事实 | + +本 Agent Note 余下部分按依赖顺序展开这些选择:Cordis 机制、作用域路由、创建与会话提交、工具与提示词、subagent 与工作流,最后是可执行检查。 + +[7 月 8 日 Agent Note](2026-07-08-agent-scope-contexts.md)仍然是贡献者契约。独立的 [subagent 组合控制 Agent Note](../feature/2026-07-12-subagent-persona-tool-filter-and-depth.md)拥有 `persona`、`toolFilter` 和 `maxDepth`;本文仅讨论它们的 setup 如何融入生命周期。 + +## Cordis 模型:上下文、fiber、effect、receiver 与 waterfall + +理解实现需要五个 Cordis 概念。上下文选择服务和注册所有权;fiber 是一个活跃的插件或子生命周期;effect 将清理逻辑附加到 fiber;事件接收器选择监听器;waterfall(瀑布式事件)让监听器按顺序变换或否决一个操作。 + +### 上下文是贯穿单个服务图的所有权路径 + +所有 agent 共享一个 Cordis 服务图。派生的上下文不会克隆 `ToolRegistry`、`SystemPrompt`、持久化或模型适配器;它改变的是:通过该上下文进行的注册如何被标记,以及哪些 effect 拥有其清理逻辑。 + +`agent.ctx` 就是这样一个派生上下文。服务调用仍然到达共享实例,而注册操作可以检查其调用上下文并将贡献存储在最近的作用域键下。普通的插件上下文不携带作用域键,因此注册到全局。 + +### Fiber 与 effect 使清理成为结构性的 + +Cordis fiber 是插件或子上下文被激活时创建的活跃实例。其状态记录该生命周期是 active、unloading、failed 还是 disposed。`ctx.effect()` 和 `ctx.on()` 返回 disposer,同时将这些 disposer 附加到注册所在的 fiber,因此卸载一个插件或 agent 作用域会移除通过该上下文注册的一切,无需单独的清单。 + +vendor 中的 Cordis fiber 实现在任意 setup 或 `internal/plugin` 观察者运行之前就建立了所有权。可重入的卸载可以看到已启动的子 fiber 或 effect,拒绝卸载开始后添加的 effect,并通过一个公开的一次性 disposer 加入已启动的清理。拆除观察者被逐个隔离,因此一个回调无法阻止结构性清理。 + +这些是框架生命周期保证,而非 agent 特有的策略。Agent 创建依赖它们,因为 setup 可以激活任意插件并同步重入所有者的 dispose。 + +### Receiver 路由监听器;waterfall 组合决策 + +Cordis 使用 dispatch receiver(`this`)过滤监听器,而 harness 的监听器需要一个显式的 agent、execution、request 或其他主体。`Scoped<T>` 标记作用域事件声明所期望的 receiver,但运行时载体刻意不暴露主体 API。 + +因此,产品辅助函数构造载体并单独传递领域主体。这防止监听器路由变成另一套对象模型,并使事件签名在不了解载体内部的情况下也可理解。 + +Cordis waterfall 是中间件风格的 dispatch。每个监听器接收 `next()`:调用它则委托给剩余监听器和基础操作,不调用则否决或替换下游结果。Waterfall 驱动提示词组装和工具策略;普通 emit 事件同步通知,parallel 事件等待所有监听器但没有否决结果。 + +## 作用域路由:一个不透明键选择一层 + +scope 包实现了 Cordis 路由所需的最小对象。其载体仅持有一个组合的服务过滤器和作用域谓词,而包私有地记录不透明键,并单独暴露会等待作用域 fiber 完全停稳的 disposer。 + +### 作用域标识使用对象标识 + +`ScopeKey` 是一个按标识比较的不透明对象。Harness 使用活跃的 `Agent` 作为自身的键,但该原语与领域无关,支持其他作用域所有者。 + +`createScope(parent, key)` 返回一个作用域,其 `ctx` 共享父级的服务,其 effect 被标记为该键。`scopeOf(ctx)` 读取最近的注册键。`scopeTarget(base, key)` 创建事件接收器,其过滤器保留 base receiver 的 Cordis 服务过滤器,然后接纳无作用域的监听器和具有该确切键的监听器。 + +Receiver 是一个小型载体而非领域对象的透明代理。需要 agent 的代码接收显式的事件参数;需要注册所有权的代码接收 `agent.ctx`。 + +### 注册表读取叠加一个精确 layer + +作用域感知的注册表使用 `ScopedLayers`,拥有一个即时创建的全局 aggregate 和按标识键惰性创建的 aggregate。读取解析全局 layer 和至多一个精确局部 layer;它不创建状态,也从不遍历父级链。注册可见性与 Cordis effect 所有权都从同一个上下文派生,而回收会等待具体 layer 的完整 aggregate 变空(见[决策](2026-07-12-scoped-layers-store.md))。 + +每个服务保留其领域规则。命名 command 和提示词视图使用共享的、保持插入顺序的 shadow 合并;工具保留更丰富的 resolver,因为限制会在加入局部工具前过滤全局工具,保留的 Code Mode transport 则单独插入。提示词变量和工具 guard 保持实时迭代,而工具提供方成员关系按每次 assembly 物化。Scope 提供存储生命周期和命名遮蔽,而非通用的注册表视图。 + +### 融合 dispatch 辅助函数防止主体漂移 + +`agentEvents(context, agent)` 构造 agent 的载体并注入同一个 agent 作为事件主体。会话、工具、approval、提示词和 subagent 服务同样从它们已拥有的对象派生路由,而非接受一个无关的键。 + +类型标记拒绝普通的裸 receiver 误用,开发环境不变式覆盖直接 JavaScript 或强制转换的 dispatch。主体保持显式,因为路由正确性和有用的事件数据是不同的关注点。 + +## Agent 创建:一个事务拥有完整操作 + +创建和恢复是一个具有多个阶段的异步生命周期,而非多个生命周期。`AgentCreationTransaction` 拥有调用方和工厂的活跃性、可选取消、私有资源、发布、回滚,以及每个所有者观察到的记忆化拆除。 + +### 注册表条目是唯一的活跃标识记录 + +AgentRegistry 和 SessionStore 各为每个活跃对象保留一条注册表条目。注册表条目持有稳定 ID、对象、作用域载体,以及属于该对象的少量发布或追加状态。 + +detach 闭包捕获其确切注册表条目。它仅在映射仍指向该注册表条目时才删除,因此旧的 disposer 无法删除一个复用相同 ID 的后续对象。注册表不会重读可变的调用方对象来决定标识。 + +没有预留 API。调用方提供的 ID 在最终写入注册表时被接纳。并发的同 ID 操作可能都完成私有 setup;恰好一个最终 `enter()` 成功,每个失败者回滚其私有资源。前一个 disposer 达到完全停稳态后,顺序复用即为有效。 + +### 事务在等待之前就拥有准备工作 + +事务在持久化加载或 setup 可能挂起之前,就被安装到调用方的 Cordis 上下文和具体的 AgentLoop 工厂下。它还在公开操作结算之前观察可选的创建/恢复信号。 + +创建准备一个新 Session。恢复加载并验证持久化的 Session,然后准备相同的活跃会话标识。两条路径随后构建作用域、agent 和 driver,并调用相同的 setup/发布算法。 + +工厂存储具体的 trace 目标,但通过调用方绑定的 Cordis trace 调用它们。这保留了依赖来源和调用方所有权,而不堆叠 trace 代理。 + +### Setup 是私有世界内的可信组合 + +Setup 接收完整的子上下文,可以等待插件激活。它可以注册工具、提示词段、限制、监听器和其他 effect,但公开契约不支持通过强制转换或内部注册表调用来驱动或发布正在创建中的 agent。 + +事务将异步加载和 setup 与停用进行竞争,而非无限等待外部代码拥有的 promise。如果取消或所有者卸载获胜,即使外部 promise 永不结算,公开创建也会在事务拥有的清理之后拒绝。 + +### 发布有一条有序的提交路径 + +发布按观察者所需的顺序接纳和宣告资源: + +1. 将会话写入注册表。 +2. 将 agent 写入注册表。 +3. 宣告 `session/created`。 +4. 宣告 `agent/created`。 +5. 启用公开驱动。 +6. 发射 `agent/session-start`。 +7. 启动 driver。 + +Agent 在两个注册表和创建通知都达成一致之前绝不驱动。同步监听器可以否决或 dispose 一个所有者;事务记录发布进行中,并等待该回调栈展开后再继续拆除。每个已开始的创建宣告在回滚期间都有匹配的销毁宣告。 + +以下序列图隔离了非显而易见的竞态:同步创建监听器可以在发布调用栈仍拥有两个注册表条目时请求 dispose。拆除必须立即停用,但要等待该栈展开后才停止和分离任何东西。 + +```mermaid +sequenceDiagram + participant Tx as AgentCreationTransaction + participant Registries + participant Listener as Synchronous listener + participant Driver + + Tx->>Tx: mark publication in progress + Tx->>Registries: announce agent/created + Registries->>Listener: invoke inside the same call stack + Listener->>Tx: dispose reentrantly + Tx->>Tx: deactivate, teardown waits for publication + Tx-->>Listener: disposal request accepted + Listener-->>Registries: return + Registries-->>Tx: announcement unwound + Tx->>Tx: resolve publication settlement + Tx->>Driver: stop and drain + Tx->>Registries: detach agent, then session + Tx->>Tx: dispose scope and resolve teardown +``` + +### 拆除在撤销注册之前保留工作 + +每个拆除请求加入一条记忆化路径。顺序为: + +1. 停用创建或驱动,让同步发布完成。 +2. 停止并排空 driver,包括空闲注入刷新。 +3. 分离 agent。 +4. 分离会话。 +5. Dispose agent 作用域。 +6. 退役事务所有权追踪。 + +此顺序让最终的 agent 和会话事件能使用匹配的作用域监听器,并使持久化观察者在最终刷新完成前保持附加。作用域 dispose 放在最后,因为注册撤销是外部可见的生命期边界。 + +## 会话追加:物化、验证、提交、通知 + +会话事件跨越持久化边界,因此追加操作拥有其数据。算法的其余部分使用一条已附加的注册表条目和一个提交点。 + +### 持久化数据一次性物化 + +Session 头部、种子和追加的事件是无损 JSON 数据。Session 构造函数或追加路径在存储前物化并验证它们,并暴露冻结的快照,因此后续调用方的修改无法改变持久化、回放或模型重建。 + +这是一个真实的所有权边界:值离开调用方,可能被持久化,且必须在之后重建相同的请求。这比类型化的同进程回调或注册表定义有意更严格。 + +### 提交前监听器可以否决;提交后观察者不能 + +追加遵循一个序列: + +1. 物化持久化事件和表面意图。 +2. 取得 SessionEntry 的独占所有权,并拒绝该注册表条目上的重入追加。 +3. 解析作用域回调并运行内部不变式验证。 +4. 恰好推送一次;这是提交点。 +5. 逐个通知每个观察者,隔离同步和异步失败。 +6. 释放追加状态并兑现发布期间请求的 detach。 + +没有观察者错误能让已提交的事件看起来未提交,一个坏的监听器也无法饿死后续监听器。Session 不变式在提交前暂存其转换,仅当同一事件到达被隔离的提交后观察者时才应用。 + +`flush()` 启动每个持久化监听器并等待所有结果后再报告失败。这种有意的 all-settled 行为防止同步失败饿死另一个后端或最终刷新。 + +## 信任边界:仅在所有权真正变更时复制 + +运行时区分类型化的进程内契约与序列化及持久化边界。这是值和回调的主要简化规则。 + +| 边界 | 所有权规则 | +|---|---| +| 同进程内的类型化服务/插件调用 | 借用 readonly 值和回调 | +| 解析的插件配置或外部文件 | 验证语义和结构输入 | +| 队列中的收件箱消息 | 在异步消费前物化 | +| 模型/工具 JSON 输入或输出 | 在模型/工具边界处物化 | +| 持久化会话或持久化数据 | 在提交前物化并验证 | +| Worker、进程或协议格式消息 | 序列化、验证并拥有解码后的值 | + +测试中构造恶意 getter、在交接后替换类型化回调、或强制转换伪造服务对象的做法本身不定义生产契约。运行时在数据跨越解析器、队列、模型、持久化、文件、worker、进程或协议格式(wire format)边界时保留检查,并在可信进程内依赖 readonly 类型加插件纪律。 + +回调隔离与数据所有权是分开的。监听器是任意扩展代码,即使其参数是可信的也可能抛出异常;发布和提交后路径仍按其事件契约隔离失败。 + +## 工具与提示词:单一视图、权威组装、已提交的结果 + +工具展示和执行共享一个私有解析器。提示词组装仍然是可信的协作式组合:注册表提供有序输入,assembly waterfall 的返回值就是 agent loop(智能体循环)记录和发送的内容。执行仅在策略或结果结算必须单调时才使用独立的单向边界。 + +### 一个解析器定义工具视图 + +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。 + +`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。 + +### 工具执行拥有标识和边界物化 + +注册表为每次执行分配一个新的带品牌的 `Symbol` token。嵌套的 Code Mode 调用将外层 token 作为 `parent` 携带,因此结构化输出可以通过标识将内层捕获与其外层 `run_code` 结果关联。 + +注册表分配的新 Symbol 提供无碰撞的执行标识,无需 WeakSet 成员注册表。调用方无法通过 `ToolExecutionInput` 提供执行自身的 token;它们仅在注册表创建后接收流水线拥有的 `ToolExecution`。这是一个可信的类型化契约,而非针对任意强制转换或 JavaScript 调用方的运行时防御。 + +参数在模型/工具 JSON 进入流水线时一次性物化。Pre-、around- 和 post-execute 监听器操作类型化的 execution 和决策。Call ID 关联、审批、单调守卫和 Code Mode 嵌套仍然是显式的关系检查。 + +在 post-execute 或外层流水线完成规范化后,注册表先为候选结果创建无损快照,并将快照失败转为普通错误;随后调用在本次调用创建时已快照的可选 `ToolDefinition.finalizeContent` 回调,最后一次性物化并冻结被接受的最终结果。该回调只能替换内容,因此即使工具强制最后一道结果上限,结构化错误标识、上下文与元数据仍由注册表拥有。每个同步的 `tools/result` 观察者接收该确切的已提交对象,观察者失败被逐个隔离。外层流水线失败或候选快照失败会在最终内容处理之前被规范化,因此观察者可以丢弃针对同一权威边界的暂存工作。 + +### Assembly waterfall 拥有最终的模型可见组合 + +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。 + +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。 + +### 结构化输出仅提交权威结果 + +结构化输出将子作用域组合与两阶段执行提交相结合。子级在发布前注册其 `structured_output` 工具和指令;可信的 assembly 监听器可以变换这些普通贡献,并有责任在期望子级完成时保持协议。工具体验证候选值并按当前 `ToolExecution` 暂存,但成功捕获仅由不可变的 `tools/result` 观察决定。 + +对于原生调用,观察者仅在该确切执行的最终结果成功时才删除暂存并提交其值。因此 post-execute 阻止或外层流水线失败不会留下已捕获的值。 + +对于 Code Mode SDK 调用,内层成功结果记录 `{ parentToken, value }` 而非提交。观察者等待 token 匹配 `parentToken` 的 `run_code` 执行,仅在该外层最终结果也成功时才提交。程序失败、运行时中止或外层 post-policy 拒绝会丢弃待定值。 + +一旦值处于待定或已提交状态,作用域单调守卫拒绝后续工具调用。提交后,普通串行的 `agent/turn-stop` 监听器在 continuation 和 steering(中途引导)已折叠之后返回停止决策。Schema 验证失败仍然是普通的 `INVALID_ARGS` 工具错误,子级可以在同一轮次内重试。 + +纯 Code Mode 的注册表贡献从原生 wire schema 中省略 `structured_output`,并通过生成的 SDK 暴露它。Assembly waterfall 可以有意改变该展示;执行仍然针对子作用域定义进行验证,监听器拥有其创建的任何替代模型可见路由的一致性。 + +### 三个执行边界有意设为单向 + +提示词组装有意是协作式的,但三个执行事实在其可扩展阶段之后需要单向结算: + +| 边界 | 最终权力 | 为何普通监听器顺序不够 | +|---|---|---| +| 工具 pre-policy | 单调拒绝 | 后续监听器不得重新允许已被拒绝的调用 | +| 工具结果 | 观察不可变的已提交结果 | 结构化输出必须仅提交实际逃出流水线的结果 | +| 轮次 continuation | 在普通 continuation 折叠之后停止 | 已提交的终端输出必须结束轮次 | + +`ToolGuard` 是单调策略注册表。已提交的工具观察是上述被隔离的 `tools/result` 点。终端结构化输出监听普通串行的 `agent/turn-stop` 折叠,在正常 continuation 和 steering 决策之后;类型化的监听器契约不需要公开的 `strictSerial()` dispatcher。 + +### Skill 和 approval 服务信任类型化调用方 + +Skill 注册表定义和 approval 策略是 readonly 的同进程契约。它们的服务不克隆回调对象,也不防御交接后的回调替换。 + +Skill 仍然验证外部 skill 文件和解析的提供方输出,通过调用 agent 的工具视图路由目录,并精确 dispose 注册。Approval 仍然解析策略、观察取消、按 `request.agent` 路由 `approval/request`、记录持久化审计对,并隔离应答者和提交后观察者的失败。 + +## Subagent:就绪即 start promise + +Subagent 启动有一次所有权转移。提供方拥有部分资源直到其 start promise 以一个就绪的已发布 run 兑现;调用方拥有返回的 run 并必须 dispose 它。 + +### 服务契约有一个取消通道 + +`SubagentProvider.start()` 和 `SubagentService.start()` 返回 `Promise<SubagentRun>`。Promise 仅在后端建立了它所承诺的子级之后才兑现,因此调用方和 `subagent/start` 观察者从不需要第二个 `run.started` 就绪 promise。 + +`SubagentStartRequest.signal` 是必需的。中止它会在启动期间和就绪之后请求取消。`SubagentRun.dispose()` 也请求取消并等待完全停稳。没有单独的公开 `run.cancel()` 通道。 + +可选的 `sendMessage()` 支持能接受 steering 的活跃后端。可选的 `resume()` 返回 `Promise<SubagentRun>`,因为恢复的子级有相同的异步就绪边界。 + +服务在调用提供方之前验证提供方能力和请求语义。提供方拒绝在拒绝逃出之前清理所有部分资源,且不发射 `subagent/start`/`subagent/end` 对。兑现之后,服务附加结果观察、发射作用域 start 并返回 run。提供方移除阻止后续 start,但不撤销提供方已接受的 run。 + +### 进程内提供方复用核心事务 + +Spawn 和 fork 共享一个进程内 driver。它通过 `parent.ctx` 创建子级,将必需的 signal 传入核心创建事务,并在未发布的 setup 期间安装 persona、工具限制和结构化输出贡献。 + +提供方等待创建并仅返回已发布的 run。在交接时,核心创建分离其仅用于创建的 abort 监听器;提供方在安装活跃 run 监听器之前立即重新检查 signal,因此在那个窄窗口中的 abort 会 dispose 新句柄而非逃脱取消。父级拆除跟随子级,因为操作属于 `parent.ctx`;提供方卸载阻止新 start 但不成为已接受 run 的第二个撤销所有者。Run disposer 取消子级并等待 AgentHandle 的有序拆除。 + +Spawn 使用空会话种子。Fork 使用经验证的已完成轮次前缀。对话种子仅改变历史,不导入作用域、工具、服务或权限。 + +### ACP 提供方拥有进程直到就绪或清理 + +ACP 提供方跨越真实的进程和协议格式边界,因此它保留验证、环境清洗、消息序列化、abort/进程竞争,以及从 kill 到进程退出并完全停稳的过程。 + +Start 仅在 `initialize` 和 `newSession` 成功后才 resolve。Abort、spawn 失败、RPC 失败或无效启动响应在拒绝前回收进程。就绪后,result 映射 ACP 提示词结果和流式输出;dispose 请求取消、关闭连接并通过一条记忆化路径等待进程退出。 + +## 工作流与 ACP UI:仅保留独立的异步事实 + +Worker 和编辑器桥接比同进程注册表需要更多状态,因为消息、进程死亡和渲染可以独立结算。它们的状态围绕这些真实事实组织,而非重复的取消协议。 + +### 工作流子级是待定 start 或已发布记录 + +工作流宿主保持待定的提供方 start promise 和已发布的子级记录。子级仅在异步 `SubagentService.start()` 兑现时才从待定变为已发布;被拒绝的 start 清理其部分提供方工作且不产生子级生命周期对。 + +一个宿主拥有的 AbortController 向待定和活跃子级提供必需的 signal。关闭工作流准入中止该 signal,因此没有重复的 `ChildCancel` worker RPC 或显式的宿主侧 `run.cancel()` 扇出。完全停稳需要等待待定 start 和已发布子级 dispose 两者。 + +Worker 边界仍然序列化请求和结果。宿主保留首个终端结果仲裁、精确的子级计数、worker 死亡处理、优雅终止、迟到/重复消息拒绝和有界清理,因为结果接收、worker 退出和子级完全停稳是真正独立的事实。 + +### 终端结果与物理清理保持分离 + +工作流结果按公开优先级规则记录首个被接受的终端结果。该结果选定后清理可以继续:活跃子级仍需 dispose,worker 仍需终止,慢速外部后端可能超出配置的优雅期限。 + +公开 dispose 在调用回调之前取得其记忆化 promise 的所有权。Worker 死亡在处理任何排队的迟到子级请求之前关闭准入,合成缺失的生命周期结束,并启动子级/进程清理而不重写已声明的结果。 + +### ACP 提示词结算不依赖渲染成功 + +ACP UI 直接将提示词与其观察到的轮次关联。它不从 `logWatermark` 扫描,也不使用会话状态作为第二个调和预言机。 + +提示词处理在 transcript(文本记录)渲染的 `finally` 中结算关联。渲染失败可以导致展示失败,但不能跳过提示词结算或让会话永久处于进行中状态。对同一持久化的调用方提供的会话 ID 的并发加载仍被排除,因为那是真实的持久化标识竞争,而非 UUID 碰撞问题。 + +## 正确性强制 + +该设计通过类型、运行时逃逸点、生成的契约和行为测试来强制执行。没有哪一层被要求证明它无法观察到的东西。 + +### 类型使常规路径难以误用 + +Readonly 契约描述借用的同进程值。`Scoped<T>` 标记事件接收器,`agentEvents()` 融合载体和主体,工具输入省略注册表拥有的 token,subagent 异步返回类型直接暴露就绪性。 + +TypeScript 无法管控 JavaScript 强制转换、直接 Cordis dispatch、进程消息或持久化文件,因此运行时强制保留在这些逃逸点。 + +### 运行时不变式覆盖跨服务事实 + +`dsh-scope/invariant` 配套插件在被选用时验证每个声明的作用域事件使用带标记的载体,以及暴露主体的事件族使用匹配的键。独立的 `dsh-session/invariant` 贡献在追加提交前暂存 trace 验证,并在同一事件提交后推进;二者都通过 `ctx.invariants` 注册。 + +该插件不通过扫描注册表来管控可信 setup,也不拒绝通过强制转换构造的提示词 assembly 对象。这些检查会将组合契约变成推测性的运行时机制,却不保护真实的外部边界。 + +### 生成的产物使公开契约保持对齐 + +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。 + +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契约的替代方案。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 + +模拟主体的代理必须保持属性、可调用、可构造、私有字段、描述符和代理不变式行为,而监听器路由从不需要这些。一个小型不透明载体保持过滤器和键,而显式事件参数携带主体。 + +### 在 setup 前预留 agent 和会话 ID + +预留防止重复的私有 setup 工作,但需要跨服务能力、释放排序、废弃预留清理和已准备对象绑定。ID 由调用方提供,并发复用是调用方错误;最终写入注册表时可以选择赢家,而失败的事务干净地回滚。 + +### 对每个类型化的同进程参数做快照 + +通用复制防御有状态 getter 和违反 readonly 契约的调用方,但增加分配、重复验证器和可能遗忘复制的路径。物化属于解析器、队列、模型、持久化、worker、进程和协议格式边界——即所有权真正变更的地方。 + +### 为就绪、取消和 dispose 提供独立控制器 + +并行哨兵可能都镜像一个操作是否活跃。一个事务或 start promise 拥有操作;独立 promise 仅在发布展开、外部工作、终端结果和物理层面的完全停稳可以独立结算时才保留。 + +### 保留同步 subagent start 加 `run.started` + +这将提供方接受与就绪分离,迫使每个消费方注册部分 run、附加结果观察、等待就绪并清理就绪失败。异步 start promise 使提供方到调用方的所有权转移本身成为就绪边界。 + +### 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。 + +### 用同进程加固替代 worker/进程生命周期守卫 + +Worker 消息、进程死亡和持久化输入确实跨越所有权和序列化边界。首个结果仲裁、验证、环境清洗和使进程完全停稳的清理即使在敌对的同进程回调机制不存在时仍然必要。 + +## 后果 + +实现更小,其证明与所有权图具有相同的形状。一个键选择一层,一条注册表条目拥有一个活跃注册表对象,一个事务拥有创建,一个解析器拥有工具视图,一个异步 promise 转移 subagent 所有权。 + +### 设计保证的内容 + +- 作用域贡献仅在其精确的 agent 视图中可见,并随该作用域一起 dispose。 +- 创建和恢复不暴露部分配置的句柄;最终写入注册表时的失败者和发布失败清理每个已准备的资源。 +- Dispose 在 driver 排空和最终会话工作期间保留作用域监听器和持久化,然后撤销作用域。 +- 持久化、队列、模型、worker、进程和协议格式的值在其真实边界处被拥有;类型化的同进程值遵循 readonly 契约。 +- ToolRegistry 的展示、查找和执行在专家 assembly 变换之前解析相同的活跃视图,已提交的结果有一个不可变的观察点。 +- 注册表贡献是确定性输入,而可信的 assembly waterfall 拥有最终的模型可见组合。 +- Subagent start 仅返回就绪的 run,必需的 signal 取消待定或活跃的工作,dispose 到达后端的完全停稳契约。 +- Worker/进程结果优先级和清理在死亡、迟到消息和有界拆除下保持正确。 + +### 代价与局限 + +作用域感知服务仍然维护全局和按标识键索引的映射,操作必须显式携带其真实 agent。异步创建/恢复和 subagent start 要求调用方等待所有权转移并 dispose 返回的句柄。 + +可信的 `system-prompt/assemble` 监听器可以移除或替换 Code Mode 和结构化输出协议片段。这是有意为之:监听器拥有最终组合,必须保持部署期望仍可用的任何协议。 + +该设计信任同进程中的类型化插件。它不防御任意强制转换、有状态 getter、违反 readonly 契约的修改,或插件有意在支持的组合 API 之外使用环境服务访问。 + +[安全与权限非目标](2026-07-08-agent-scope-contexts.md#security-and-authority-are-non-goals)仍然是根本性的。这些机制证明注册组合、发布和生命期所有权;它们不证明隔离或父到子的非升权。 diff --git a/.agents/notes/implemented/architecture/2026-07-22-unified-send-and-coalesced-user-messages.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-22-unified-send-and-coalesced-user-messages.i18n.yaml new file mode 100644 index 0000000000..b0afe427ce --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-07-22-unified-send-and-coalesced-user-messages.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-22-unified-send-and-coalesced-user-messages.md: bf0ae468c4783b73e2dbd0e1bc50b9bd2f50cb3f +2026-07-22-unified-send-and-coalesced-user-messages.zh.md: 17913d2636e3ee5e5ae69f9c554935ba861d14d9 diff --git a/.agents/notes/implemented/architecture/2026-07-22-unified-send-and-coalesced-user-messages.md b/.agents/notes/implemented/architecture/2026-07-22-unified-send-and-coalesced-user-messages.md new file mode 100644 index 0000000000..bf0ae468c4 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-07-22-unified-send-and-coalesced-user-messages.md @@ -0,0 +1,46 @@ +# Agent Note: Unify agent delivery and coalesce injected context into user/message + +Status: implemented + +English | [中文](2026-07-22-unified-send-and-coalesced-user-messages.zh.md) + +## Problem + +The agent's public driving surface had grown three near-parallel verbs — `send`, `steer`, `inject` — each with its own options type, its own live event story, and its own durable event. `send` and `steer` both queued a frozen inbox record and emitted `agent/queued`; `inject` bypassed the inbox and wrote a separate `context/message` durable event. The three verbs actually vary along only two independent axes: which queue an item joins (a whole new turn versus the active turn) and whether the item makes the model run. Encoding that 2×2 as three hand-written methods hid the symmetry, made "queue a turn without waking the driver" unreachable, and left `cancel()` with no way to abort a turn while preserving queued work. + +Separately, `context/message` and `user/message` had converged: the surface projected both as verbatim user-role content, and the only real difference was that injected context carried `source`/`meta` and was "not a prompt." Two event types for one projection meant every consumer branched on event type to answer "is this a human prompt?", and the goal system used the type split as a side channel (round-zero state changes were `context/message`, admitted rounds were `user/message`). + +## Decision + +**One acceptance mechanism, four intent helpers.** The concrete loop resolves `followup`, `queue`, `steer`, and `inject` into one (`target` × `wakeup`) acceptance mechanism. `followup` is `next-turn`/wakeup, `queue` is `next-turn`/no-wakeup, `steer` is `next-step`/wakeup, and `inject` is `next-step`/no-wakeup. The public structural interface exposes that mechanism as `send(ResolvedAgentInput)` for callers that already have fully resolved routing; every field is mandatory, and the discriminated input type excludes attached contexts from injection. The [intent-named delivery decision](2026-07-24-intent-named-agent-delivery.md) owns that superseding interface choice. Internally, `wakeup` means “make the model run”: wake a parked driver for an ordinary item or force a continuation for running steering. + +**inject keeps its mechanism.** `inject` appends durable model-facing context at the current log position (deferred behind an executing tool batch), or opens a one-shot `injection` turn when idle. It bypasses the FIFOs entirely, accepts no attached contexts, and defaults its source to `{ kind: 'plugin', plugin: '' }`, never `{ kind: 'user' }`. + +**context/message is gone.** Injected context is now a `user/message` whose `source` is a non-`user` kind (plugin or goal). `PromptMessageData` gained the optional `meta` that `context/message` carried. The surface, derivation, and `SurfaceEventType` drop `context/message`; consumers that need "is this a human prompt?" read `source.kind === 'user'` instead of the event type. This keeps goal-authority's human-authority check exactly as strict as before — an injected message defaults to a plugin source and can never satisfy `source.kind === 'user'`. + +**Goal replay disambiguates by round, not type.** A goal state change is a round-zero goal-sourced `user/message` carrying `goal/change` metadata; a positive round is an admitted continuation prompt. `decodeGoalEvent` now takes a `user/message` and still fails loud on goal metadata under a non-goal source or a goal source lacking metadata. + +**Delivery returns an id.** Each delivery method returns an opaque branded `AgentMessageId` for the accepted input. FIFO methods carry it through their inbox lifecycle events; injection bypasses those events. + +**Three inbox events replace agent/queued.** `agent/inbox/enqueue` (an item entered a FIFO), `agent/inbox/dequeue` (the driver claimed one), and `agent/inbox/discard` (`cancel()` dropped pending items) each carry an `AgentMessage` — the accepted message including its returned `id`, steering/wakeup facts, source, and contexts — so a caller can correlate a queued item with its lifecycle. Injection never touches a FIFO and emits none of these. Every FIFO entry publishes an enqueue, including the loop-authored continuation-reason steer (`agent/turn-continuation` returning `{ action: 'continue', reason }`), so the ledger stays balanced with its later dequeue or discard. The `dsh-agent` invariant companion asserts FIFO conservation: a per-agent outstanding count that dequeue and discard can never drive negative. + +**cancel gains keepInbox.** `cancel(cause?, { keepInbox? })`; when true it aborts the active turn but preserves queued and steering items (no discard event, and un-started work is not dropped). + +## Alternatives considered + +- **A dedicated `MessageSource` kind `context`** for injected content. Rejected because `plugin` already means "not a human," so a fourth kind would add a parallel axis the authority checks would have to learn. Injected context defaults to a plugin source instead. +- **A typed discriminant field on `PromptMessageData`** (e.g. `origin: 'prompt' | 'context'`) to replace the event-type split. Rejected in favor of `source`, which every consumer already carries and which the goal system already keyed on; a second discriminant would duplicate that fact. +- **Keeping `agent/queued` alongside the inbox events.** Rejected as a mirror: `agent/inbox/enqueue` is the same enqueue-time signal with the accepted routing facts, and the dequeue/discard events complete the FIFO lifecycle the single event could not describe. + +## Consequences + +The concrete driver has one delivery mechanism. Four common helpers hide its (`target` × `wakeup`) matrix behind caller intent, while `send` exposes the fully resolved matrix for advanced callers. One durable message type serves prompts, injected context, and goal rounds, so the surface projection and every “human prompt?” check simplify to a `source` test. The goal fold's channel split moves from event type to `source.round`, and every consumer that filtered `context/message` filters `user/message` by source. The turn-enclosure and reconstruction invariants are unchanged: an idle injection still wraps a one-shot turn, now emitting `user/message` instead of `context/message`. + +Internally, `wakeup` is the “should the model run” signal, so the inbox distinguishes `hasWakingQueued` (drives the loop and idle/quiescence decisions) from `hasQueued` (anything to dequeue): a lone `queue()` item stays parked at idle and rides along the next waking follow-up, and `whenIdle`/`cancel` settle quiescence off the waking signal (a lone quiet item takes `whenIdle`'s fast path, so no waiter is left hanging). `SendOptions.meta` on a queued or steering message is carried onto the durable `user/message`/`steering/message`, matching injection; it is intentionally absent from the live `AgentMessage`, which carries only routing facts. Every enqueued id gets exactly one terminal lifecycle event: a terminal stop that drops pending steering emits `agent/inbox/discard` both at the in-turn stop point and on the post-turn drain of late steering, and disposal discards any still-pending items before the loop exits. The `agent/inbox/*` payload is frozen so a listener cannot mutate the shared correlation object mid-dispatch, and a loop-authored continuation reason is snapshotted and frozen like public steering. Injection validates its payload before opening an idle one-shot turn; `InjectOptions` omits attached contexts, while the non-waking next-step variant of `ResolvedAgentInput` requires an empty context tuple. + +## Related + +- [one-send-one-turn](../simplification/2026-07-17-one-send-one-turn.md) — the one-claimed-message-per-turn rule this builds on. +- [remove-agent-steering-mirror](../simplification/2026-07-04-remove-agent-steering-mirror.md) — the precedent for collapsing a mirrored live event. +- [explicit-turn-cancellation](2026-07-16-explicit-turn-cancellation.md) — the cancel-cause signal `keepInbox` extends. +- [intent-named-agent-delivery](2026-07-24-intent-named-agent-delivery.md) — the public helpers and fully resolved acceptance interface. diff --git a/.agents/notes/implemented/architecture/2026-07-22-unified-send-and-coalesced-user-messages.zh.md b/.agents/notes/implemented/architecture/2026-07-22-unified-send-and-coalesced-user-messages.zh.md new file mode 100644 index 0000000000..17913d2636 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-07-22-unified-send-and-coalesced-user-messages.zh.md @@ -0,0 +1,46 @@ +# Agent Note: 统一 agent 投递并把注入的上下文合并进 user/message + +Status: implemented + +[English](2026-07-22-unified-send-and-coalesced-user-messages.md) | 中文 + +## 问题 + +agent 的对外驱动接口逐渐长出三个近乎平行的动词——`send`、`steer`、`inject`——各自带有独立的选项类型、独立的实时事件叙事,以及独立的持久事件。`send` 和 `steer` 都会把一条冻结的 inbox 记录入队并发出 `agent/queued`;`inject` 则绕过 inbox,写入一条独立的 `context/message` 持久事件。这三个动词实际上只沿两条独立的轴变化:一个队列项加入哪个队列(一个全新的轮次,还是当前活跃的轮次),以及这个队列项是否让模型运行。把这个 2×2 编码成三个手写方法,掩盖了其中的对称性,让“排入一个轮次但不唤醒驱动器”无法表达,也让 `cancel()` 无从在保留排队工作的前提下中止一个轮次。 + +另外,`context/message` 与 `user/message` 已经趋同:对外接口把二者都投影为逐字的 user 角色内容,唯一真正的区别是注入的上下文携带 `source`/`meta` 且“不是提示词”。一个投影对应两种事件类型,意味着每个消费方都要根据事件类型分支来回答“这是不是一条人类提示词?”,而 goal 系统把这种类型区分当作侧信道使用(第 0 轮的状态变更是 `context/message`,已准入的轮次是 `user/message`)。 + +## 决策 + +**一种接受机制,四种意图辅助方法。** 具体循环把 `followup`、`queue`、`steer` 和 `inject` 解析到同一个(`target` × `wakeup`)接受机制中。`followup` 是 `next-turn`/wakeup,`queue` 是 `next-turn`/no-wakeup,`steer` 是 `next-step`/wakeup,`inject` 是 `next-step`/no-wakeup。公开的结构化接口将该机制暴露为 `send(ResolvedAgentInput)`;调用方若已持有完全解析的路由信息,即可使用该方法。使用时必须提供所有字段,可辨识输入类型也不允许注入携带附加上下文。取代旧接口的选择由[按意图命名的投递决策](2026-07-24-intent-named-agent-delivery.md)负责说明。内部的 `wakeup` 表示「让模型运行」:为一条普通消息唤醒处于停泊状态的驱动器,或强制运行中的 steering 继续执行。 + +**inject 保留其机制。** `inject` 在当前日志位置追加持久、面向模型的上下文(在执行中的工具批处理之后延迟处理),或在空闲时开启一个一次性的 `injection` 轮次。它完全绕过 FIFO,不接受附加上下文,并把来源默认设为 `{ kind: 'plugin', plugin: '' }`,绝不是 `{ kind: 'user' }`。 + +**context/message 已移除。** 注入的上下文现在是一条 `user/message`,其 `source` 为非 `user` 类别(plugin 或 goal)。`PromptMessageData` 新增了 `context/message` 原本携带的可选 `meta`。对外接口、派生逻辑和 `SurfaceEventType` 都不再包含 `context/message`;需要判断“这是不是一条人类提示词?”的消费方改为读取 `source.kind === 'user'`,而不是事件类型。这让 goal-authority 的人类授权检查与此前一样严格——注入的消息默认使用 plugin 来源,永远无法满足 `source.kind === 'user'`。 + +**goal 回放靠轮次而非类型来区分。** 一次 goal 状态变更是一条第 0 轮、来源为 goal 的 `user/message`,携带 `goal/change` 元数据;正数轮次则是一条已准入的继续执行提示词。`decodeGoalEvent` 现在接收一条 `user/message`,并仍会在非 goal 来源携带 goal 元数据、或 goal 来源缺少元数据时立即报错。 + +**投递返回一个 id。** 每种投递方法都为被接受的输入返回一个不透明的 branded `AgentMessageId`。FIFO 方法通过其 inbox 生命周期事件携带这个 id;注入绕过这些事件。 + +**三个 inbox 事件取代 agent/queued。** `agent/inbox/enqueue`(一个队列项进入某个 FIFO)、`agent/inbox/dequeue`(驱动器认领了一个)和 `agent/inbox/discard`(`cancel()` 丢弃了待处理项)都携带一条 `AgentMessage`——即被接受的消息,包含其返回的 `id`、steering/wakeup 事实、来源和上下文——因此调用方可以把一个排队项与其生命周期关联起来。注入从不触及 FIFO,也不发出这些事件中的任何一个。每一次 FIFO 入队都会发布一个 enqueue 事件,包括由 loop 生成的携带继续原因的 steer(`agent/turn-continuation` 返回 `{ action: 'continue', reason }`),因此账目会与其后的 dequeue 或 discard 保持平衡。`dsh-agent` 的不变量配套断言 FIFO 守恒:一个按 agent 计的未结算计数,dequeue 和 discard 永远无法把它压到负数。 + +**cancel 新增 keepInbox。** `cancel(cause?, { keepInbox? })`;当其为 true 时,它中止活跃轮次,但保留排队项和 steering 项(不发出 discard 事件,尚未启动的工作也不会被丢弃)。 + +## 考虑过的替代方案 + +- **为注入内容设立专门的 `MessageSource` 类别 `context`。** 不予采纳,因为 `plugin` 已经表示“不是人类”,因此第四种类别会增加一条平行的轴,让授权检查不得不去学习它。注入的上下文改为默认使用 plugin 来源。 +- **在 `PromptMessageData` 上设一个类型化的判别字段**(例如 `origin: 'prompt' | 'context'`)来取代事件类型的区分。不予采纳,转而采用 `source`——每个消费方都已经携带它,goal 系统也已经以它为键;第二个判别字段会重复这一事实。 +- **在 inbox 事件之外保留 `agent/queued`。** 作为镜像而被否决:`agent/inbox/enqueue` 是同一个入队时刻的信号,只是多带了已接受的路由事实,而 dequeue/discard 事件补全了单个事件无法描述的 FIFO 生命周期。 + +## 后果 + +具体驱动器只有一个投递机制。四种常用辅助方法以调用方意图封装其(`target` × `wakeup`)矩阵,而 `send` 则向高级调用方暴露完全解析后的矩阵。一种持久消息类型同时服务提示词、注入的上下文和 goal 轮次,因此对外接口的投影和每一处「是否人类提示词?」检查都简化为一次 `source` 判断。goal 折叠的通道区分从事件类型改到 `source.round`,此前过滤 `context/message` 的每个消费方都改为按来源过滤 `user/message`。轮次封闭与重建的不变量保持不变:空闲状态下的一次注入仍然封装成一个一次性轮次,只是现在发出 `user/message` 而非 `context/message`。 + +在内部,`wakeup` 是“模型是否应当运行”的信号,因此 inbox 区分 `hasWakingQueued`(驱动 loop 以及空闲/静默判定)与 `hasQueued`(是否有任何可 dequeue 的项):一个孤立的 `queue()` 项会停泊在空闲状态,并随下一条会唤醒驱动器的后续消息一同带出,而 `whenIdle`/`cancel` 依据唤醒信号来结算静默(一个孤立的静默项走 `whenIdle` 的快速路径,因此不会让任何等待者悬而未决)。排队消息或 steering 消息上的 `SendOptions.meta` 会被带到持久的 `user/message`/`steering/message` 上,与注入保持一致;它有意不放在实时的 `AgentMessage` 上,后者只携带路由事实。每个已入队的 id 都恰好得到一个终止性生命周期事件:一次会丢弃待处理 steering 项的终止性停止会为它发出 `agent/inbox/discard`,既在轮次内的停止点,也在轮次结束后对迟到 steering 的清空时;dispose(资源释放)会在 loop 退出前丢弃所有仍在等待的项。`agent/inbox/*` 的事件载荷已被冻结,因此监听器无法在分发中途修改共享的关联对象,而由 loop 生成的继续原因会像公开 steering 一样被快照并冻结。注入会在打开空闲状态的一次性轮次之前校验其载荷;`InjectOptions` 不包含附加上下文,而 `ResolvedAgentInput` 中不唤醒的下一步变体要求使用空上下文元组。 + +## 相关 + +- [one-send-one-turn](../simplification/2026-07-17-one-send-one-turn.md)——本决策所依托的“每轮次只认领一条消息”规则。 +- [remove-agent-steering-mirror](../simplification/2026-07-04-remove-agent-steering-mirror.md)——折叠镜像实时事件的先例。 +- [explicit-turn-cancellation](2026-07-16-explicit-turn-cancellation.md)——`keepInbox` 所扩展的取消原因信号。 +- [intent-named-agent-delivery](2026-07-24-intent-named-agent-delivery.md)——公开辅助方法以及接受完全解析输入的接口。 diff --git a/.agents/notes/implemented/architecture/2026-07-24-intent-named-agent-delivery.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-24-intent-named-agent-delivery.i18n.yaml new file mode 100644 index 0000000000..ec8c9d105f --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-07-24-intent-named-agent-delivery.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-24-intent-named-agent-delivery.md: 32b0502350063610efff746cbef779e8225055eb +2026-07-24-intent-named-agent-delivery.zh.md: ce8860b397497f4de587a9373d1cd300cf7dab29 diff --git a/.agents/notes/implemented/architecture/2026-07-24-intent-named-agent-delivery.md b/.agents/notes/implemented/architecture/2026-07-24-intent-named-agent-delivery.md new file mode 100644 index 0000000000..32b0502350 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-07-24-intent-named-agent-delivery.md @@ -0,0 +1,52 @@ +# Agent Note: Name public agent delivery by intent + +Status: implemented + +English | [中文](2026-07-24-intent-named-agent-delivery.zh.md) + +## Problem + +A configurable `send(content, { target?, wakeup?, ... })` makes every caller learn the loop's routing matrix, its defaults, and the interaction between active-turn targeting and model activation. Optional routing fields also let advanced-looking calls silently become ordinary sends. Most callers have one semantic intent, while some adapters already possess exact routing facts and should not have to reverse-map them into a helper name. + +Sharing helper implementations through an abstract `Agent` class also makes the public seam nominal in practice. Object-literal adapters and tests must inherit prototype methods even though the package promises a swappable structural handle. The shared base exists only to forward fixed arguments, while the concrete loop remains the sole production adapter. + +## Decision + +`Agent` is a structural interface with four intent-named delivery helpers: + +- `followup()` queues an ordinary turn and wakes the driver. +- `queue()` queues an ordinary turn without waking an idle driver. +- `steer()` targets the running turn and requests another step; while idle it becomes a waking ordinary turn. +- `inject()` appends model-facing context without running the model. + +`followup`, `queue`, and `steer` accept `SendOptions`; `inject` accepts `InjectOptions`, which omits attached contexts because injection has no inbox item to own them. `followup` names the waking next-turn operation used for both initial prompts and later independent prompts. + +`Agent` also exposes `send(ResolvedAgentInput)` for callers that already hold the complete route. Every field is mandatory: content, source, contexts, metadata (possibly `undefined`), target, and wakeup. The discriminated union requires the empty context tuple for non-waking next-step injection. `ReactLoopAgent` implements this method once, and all four helpers resolve their defaults before delegating to it. The method accepts the delivery facts as one resolved input; acceptance can still lead to later dequeue, discard, or durable injection rather than eventual delivery. + +The target/wakeup matrix is an explicit advanced part of the structural `Agent` interface, not the ordinary helper options and not a base-class implementation seam. With one concrete adapter, a protected subclass seam would be hypothetical; callers and tests use the same public interface. + +## Alternatives considered + +**Keep the resolved primitive private.** This minimizes the public method count, but forces adapters that already hold exact target/wakeup facts to reverse-map them into helper calls and removes the reusable type for that resolved state. + +**Use configurable `send(content, options)` as the primitive.** Optional routing fields would let advanced-looking calls silently become ordinary sends. One mandatory discriminated input keeps the resolved route explicit and rejects attached contexts on injection. + +**Name the primitive `acceptInput`, `sendInternal`, or `addMessageAdvanced`.** `acceptInput` describes the synchronous acceptance boundary but not the caller's delivery action. A public method must not describe itself as internal, and `addMessageAdvanced` is inaccurate because the input may later be discarded. + +**Use `send(content, options)` as the waking-turn helper.** This reserves the shortest delivery name for one preset and forces callers with complete target/wakeup facts through a less direct primitive name. `followup` distinguishes the next-turn/wakeup intent while leaving `send` for the resolved operation. + +**Bind source first through a public sender object.** A source-bound adapter can make attribution explicit for repeated producers, but it adds another public object and does not simplify one-off human input. The existing source default remains, with the standing requirement that non-human producers label their content. + +## Verification + +Focused agent-loop coverage exercises direct fully resolved acceptance, waking sends, quiet queues, active and idle steering, injection, source/context snapshots, cancellation, and inbox lifecycle correlation through the public methods. Type-level coverage uses structural `Agent` fakes, requires every `ResolvedAgentInput` field, requires empty contexts on its injection variant, and keeps routing fields out of `SendOptions`. The keyless Cordis inspection snapshot pins the structural interface without an abstract-class implementation. + +## Consequences + +Ordinary callers choose one verb instead of encoding two routing axes; advanced callers may submit the exact discriminated route. The concrete loop retains one acceptance path and one ownership boundary, while the structural interface preserves simple adapters and fakes. Adding a common delivery intent still requires an explicit public helper and mapping rather than another optional matrix combination. + +The advanced method adds interface surface and requires structural fakes to implement it. In return, resolved routing has one typed representation, while helper defaults and mappings stay beside the only implementation that owns them. + +## Related + +- [unified delivery and coalesced user messages](2026-07-22-unified-send-and-coalesced-user-messages.md) owns the shared acceptance mechanism, inbox lifecycle, and durable event convergence this decision narrows at the public seam. diff --git a/.agents/notes/implemented/architecture/2026-07-24-intent-named-agent-delivery.zh.md b/.agents/notes/implemented/architecture/2026-07-24-intent-named-agent-delivery.zh.md new file mode 100644 index 0000000000..ce8860b397 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-07-24-intent-named-agent-delivery.zh.md @@ -0,0 +1,52 @@ +# Agent Note: 按意图命名公开的 agent 投递 + +Status: implemented + +[English](2026-07-24-intent-named-agent-delivery.md) | 中文 + +## 问题 + +可配置的 `send(content, { target?, wakeup?, ... })` 会迫使每个调用方理解循环的路由矩阵、默认值,以及活跃轮次目标与模型激活之间的相互作用。可选路由字段还会让看似高级的调用悄然变成普通投递。大多数调用方只有一种语义意图,而有些适配器已经持有确切的路由信息,不应再被迫将这些信息反向映射为某个辅助方法名称。 + +通过抽象 `Agent` 类共享辅助方法的实现,实际上也会让公开 seam 具有名义类型约束。对象字面量适配器和测试必须继承原型方法,尽管该包承诺提供一个可替换的结构化句柄。共享基类只负责转发固定参数,而具体循环仍是唯一的生产适配器。 + +## 决策 + +`Agent` 是一个结构化接口,提供四种按意图命名的投递辅助方法: + +- `followup()` 将一个普通轮次入队并唤醒驱动器。 +- `queue()` 将一个普通轮次入队,但不唤醒空闲驱动器。 +- `steer()` 以运行中的轮次为目标并请求另一个步骤;空闲时,它会变成一个唤醒式普通轮次。 +- `inject()` 追加面向模型的上下文,但不运行模型。 + +`followup`、`queue` 和 `steer` 接收 `SendOptions`;`inject` 接收 `InjectOptions`,后者不包含附加上下文,因为注入没有 inbox 项来拥有它们。`followup` 为唤醒式下一轮操作命名,这项操作既用于初始提示词,也用于后续的独立提示词。 + +`Agent` 还公开 `send(ResolvedAgentInput)`,供已经持有完整路由的调用方使用。每个字段都必须提供:内容、来源、上下文、元数据(可以是 `undefined`)、目标和唤醒标志。对于目标为下一步且不触发唤醒的注入,可辨识联合类型要求上下文为空元组。`ReactLoopAgent` 统一实现这个方法;四个辅助方法都会先解析各自的默认值,再委托给它。调用方以一个解析后的输入向该方法提交各项投递事实;接受之后,工作仍可能在稍后出队、被丢弃或持久注入,而不是最终必然送达。 + +结构化 `Agent` 接口显式包含面向高级用法的 target/wakeup 矩阵;该矩阵不属于普通辅助方法的选项,也不是基类实现 seam。只有一个具体适配器时,protected 子类 seam 只是假想的;调用方和测试使用同一个公开接口。 + +## 考虑过的替代方案 + +**让解析后的原语保持私有。** 这会把公开方法数量降到最低,但会迫使已经持有精确 target/wakeup 路由信息的适配器将其反向映射为辅助方法调用,也会移除表示该解析后状态的可复用类型。 + +**使用可配置的 `send(content, options)` 作为原语。** 可选路由字段会让看似高级的调用悄然变成普通投递。一个各字段均为必填项的可辨识输入既能让解析后的路由保持显式,也会拒绝为注入附加上下文。 + +**把原语命名为 `acceptInput`、`sendInternal` 或 `addMessageAdvanced`。** `acceptInput` 描述了同步接受边界,却没有描述调用方的投递操作。公开方法不应在名称中把自己称为内部方法,`addMessageAdvanced` 也不准确,因为输入可能在之后被丢弃。 + +**使用 `send(content, options)` 作为唤醒轮次的辅助方法。** 这会让最简短的投递名称只表示一种预设操作,并迫使持有完整 target/wakeup 信息的调用方改用一个不够直接的原语名称。`followup` 明确区分下一轮/唤醒意图,并把 `send` 留给解析后的操作。 + +**先通过公开的发送方对象绑定来源。** 对于重复产生消息的来源,来源绑定适配器可以明确标注归属,但它会增加一个公开对象,也不会简化一次性的人类输入。现有的来源默认值予以保留,同时继续要求非人类生产方标注其内容。 + +## 验证 + +聚焦的 agent-loop 覆盖率测试通过公开方法覆盖直接接受完全解析的输入、唤醒式投递、静默排队、活跃与空闲状态下的 steering(中途引导)、注入、来源与上下文快照、取消,以及 inbox 生命周期关联。类型级覆盖使用结构化 `Agent` 测试替身,要求提供 `ResolvedAgentInput` 的每个字段,要求其注入变体的上下文为空,并确保 `SendOptions` 不包含路由字段。无密钥的 Cordis 检查快照固定了不采用抽象类实现的结构化接口。 + +## 后果 + +普通调用方选择一个动词即可,无需编码两条路由轴;高级调用方则可提交经过判别的精确路由。具体循环保留一条接受路径和一个归属边界,而结构化接口保留了对简单适配器和测试替身的支持。新增一种常见投递意图时,仍需要显式提供公开辅助方法及其映射,而不是再增加一种可选的矩阵组合。 + +这个高级方法会扩大接口范围,并要求结构化测试替身实现它。作为回报,解析后的路由只有一种类型化表示,而辅助方法的默认值和映射仍留在拥有它们的唯一实现旁边。 + +## 相关 + +- [统一投递并合并 user 消息](2026-07-22-unified-send-and-coalesced-user-messages.md)负责定义共享的接受机制、inbox 生命周期和持久事件趋同;本决策只收窄它们的公开 seam。 diff --git a/.agents/notes/implemented/bug-fix/2026-07-24-recursive-python-sdk-session-notifications.i18n.yaml b/.agents/notes/implemented/bug-fix/2026-07-24-recursive-python-sdk-session-notifications.i18n.yaml new file mode 100644 index 0000000000..cae5b75cb4 --- /dev/null +++ b/.agents/notes/implemented/bug-fix/2026-07-24-recursive-python-sdk-session-notifications.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-24-recursive-python-sdk-session-notifications.md: c90213659391b565acd043a1be64e225f8babd31 +2026-07-24-recursive-python-sdk-session-notifications.zh.md: 214a5ef924dcc9da3a97aab6385837acd2b364d9 diff --git a/.agents/notes/implemented/bug-fix/2026-07-24-recursive-python-sdk-session-notifications.md b/.agents/notes/implemented/bug-fix/2026-07-24-recursive-python-sdk-session-notifications.md new file mode 100644 index 0000000000..c902136593 --- /dev/null +++ b/.agents/notes/implemented/bug-fix/2026-07-24-recursive-python-sdk-session-notifications.md @@ -0,0 +1,29 @@ +# Agent Note: Recursive Python SDK session notifications + +Status: implemented + +English | [中文](2026-07-24-recursive-python-sdk-session-notifications.zh.md) + +## Problem + +The Python SDK filtered turn notifications by comparing each payload directly with the root session id. This admitted a direct child's lifecycle because its parent id named the root, but rejected a grandchild's lifecycle and every descendant `session.event`. The JSON-RPC server still emitted those notifications, so they accumulated on the low-level global queue while high-level consumers lost nested trajectory relationships and completion states. + +## Decision + +`HarnessClient` records every valid `subagent.started` child-to-parent edge before dispatching the notification. A later `subagent.finished` routes by its immutable parent id but never rewrites current ancestry, so an older run that settles after its child id has been reused cannot displace the replacement session. Other session notifications resolve their session id by walking that client-lifetime ancestry graph to the requested root. The graph survives successive subscriptions so a descendant that outlives one `Session.run()` remains attributable when it emits during a later turn, and it resets when the client starts a new runtime process. + +`Session.run()` delivers the complete discovered session-tree notification stream through `TurnResult.notifications` and `on_notification`. Only `session.event` notifications whose `sessionId` equals the requested root enter `TurnResult.events` or final-response reconstruction. Descendant events are therefore observable without allowing a child response to replace the root response. + +## Alternatives considered + +**Add a root session id to every JSON-RPC notification.** The server already provides exact immediate-parent edges, and duplicating transitive ancestry on the wire would make every producer responsible for client subscription state. + +**Limit subagents to one level.** A deployment can set `maxDepth: 1`, but changing the SDK to depend on that policy would silently misreport valid recursive compositions. + +**Subscribe only to descendant lifecycle notifications.** This would repair relation and completion reporting, but descendant session events would continue accumulating on the global queue and callbacks would expose an incomplete tree. + +**Expose and index every subagent run id on the JSON-RPC wire.** Exact run identity is useful when a client must correlate two concurrent outcomes for the same child, but session-tree routing already has the authoritative start edge and each terminal notification's immutable parent. Expanding the protocol is unnecessary for this ownership decision. + +## Consequences + +High-level consumers receive nested lifecycle and session notifications in wire order while root turn results preserve their prior response semantics. The client retains one current parent entry per observed child until the runtime restarts; ancestry lookup is cycle-safe, and unrelated session notifications remain available through the global queue. Keyless Python tests cover two-level delegation, root-response isolation, absence of tree-notification queue buildup, ancestry reuse across subscriptions, and reused child ids whose older runs settle out of order. diff --git a/.agents/notes/implemented/bug-fix/2026-07-24-recursive-python-sdk-session-notifications.zh.md b/.agents/notes/implemented/bug-fix/2026-07-24-recursive-python-sdk-session-notifications.zh.md new file mode 100644 index 0000000000..214a5ef924 --- /dev/null +++ b/.agents/notes/implemented/bug-fix/2026-07-24-recursive-python-sdk-session-notifications.zh.md @@ -0,0 +1,29 @@ +# Agent Note: Python SDK 递归会话通知 + +Status: implemented + +[English](2026-07-24-recursive-python-sdk-session-notifications.md) | 中文 + +## 问题 + +Python SDK 过去通过将每条通知的 payload 与根会话 ID 直接比较来过滤轮次通知。直接子 agent 的生命周期通知因 parent ID 指向根会话而能够通过,但孙级生命周期通知与所有后代 `session.event` 都会被拒绝。JSON-RPC 服务器仍会发出这些通知,因此它们会堆积在底层全局队列中,而高层消费者会丢失嵌套轨迹的关系与结束状态。 + +## 决策 + +`HarnessClient` 会在分发通知前,记录每条有效 `subagent.started` 所包含的 child-to-parent(子到父)关系。后续的 `subagent.finished` 会依据自身不可变的 parent ID 路由,但不会改写当前祖先关系,因此旧 run 即使在其 child ID 已被复用后才结束,也无法覆盖替代它的新会话。其他会话通知会沿客户端生命周期内保存的祖先关系图回溯自身 session ID,判断它们是否属于请求的根会话。该关系图会跨连续订阅保留,因此某个后代即使跨过一次 `Session.run()`,在后续轮次中发出通知时仍能正确归属;客户端启动新的运行时进程时会重置关系图。 + +`Session.run()` 通过 `TurnResult.notifications` 与 `on_notification` 提供已发现会话树的完整通知流。只有 `sessionId` 等于请求根会话的 `session.event` 才会进入 `TurnResult.events` 或参与最终回复重建。因此调用方能够观察后代事件,同时子会话回复不会覆盖根会话回复。 + +## 考虑过的替代方案 + +**在每条 JSON-RPC 通知中加入根会话 ID。** 服务器已经提供精确的直接父子关系;在线路协议中重复传递祖先关系,会迫使每个生产者承担客户端订阅状态的职责。 + +**把 subagent 限制为一层。** 部署可以设置 `maxDepth: 1`,但让 SDK 依赖该策略,会对合法的递归组合产生静默误报。 + +**只订阅后代生命周期通知。** 这可以修复关系与结束状态的上报,但后代会话事件仍会堆积在全局队列中,回调看到的会话树也不完整。 + +**在 JSON-RPC 线路上公开并索引每个 subagent run ID。** 当客户端必须关联同一 child 的两个并发结果时,精确 run 身份很有价值;但会话树路由已经拥有权威 start 关系和每条终止通知中不可变的 parent。没有必要为这一归属决策扩展协议。 + +## 后果 + +高层消费者会按线上的原始顺序收到嵌套生命周期与会话通知,同时根轮次结果保持原有回复语义。客户端会为每个已观察到的子会话保留一条当前父关系,直到运行时重启;祖先回溯能够安全处理环,无关会话通知仍可从全局队列获取。无密钥 Python 测试覆盖两层派生、根回复隔离、会话树通知不堆积、跨订阅复用祖先关系,以及旧 run 乱序结束的复用 child ID。 diff --git a/.agents/notes/implemented/feature/2026-06-14-acp-agent-client-protocol.i18n.yaml b/.agents/notes/implemented/feature/2026-06-14-acp-agent-client-protocol.i18n.yaml new file mode 100644 index 0000000000..a3a3e3b72f --- /dev/null +++ b/.agents/notes/implemented/feature/2026-06-14-acp-agent-client-protocol.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-14-acp-agent-client-protocol.md: c6976ed28a254684fca62e2d309cdde7ea90340d +2026-06-14-acp-agent-client-protocol.zh.md: 6bd234f2aa3f43f4fc6cbd921161253c46aab73e diff --git a/.agents/notes/implemented/feature/2026-06-14-acp-agent-client-protocol.md b/.agents/notes/implemented/feature/2026-06-14-acp-agent-client-protocol.md index 7c47fc78e9..c6976ed28a 100644 --- a/.agents/notes/implemented/feature/2026-06-14-acp-agent-client-protocol.md +++ b/.agents/notes/implemented/feature/2026-06-14-acp-agent-client-protocol.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-06-14-acp-agent-client-protocol.zh.md) + ## Problem The harness originally exposed agents only through a readline loop. That surface could carry text, but it gave an editor no structured way to create or resume sessions, correlate prompt completion, stream reasoning and tool activity, render tool-specific UI, ask for permission, or cancel one conversation without disturbing another. ACP defines those interactions as JSON-RPC over stdio, and Zed is the target client used to make concrete compatibility decisions. diff --git a/.agents/notes/implemented/feature/2026-06-14-acp-agent-client-protocol.zh.md b/.agents/notes/implemented/feature/2026-06-14-acp-agent-client-protocol.zh.md new file mode 100644 index 0000000000..6bd234f2aa --- /dev/null +++ b/.agents/notes/implemented/feature/2026-06-14-acp-agent-client-protocol.zh.md @@ -0,0 +1,59 @@ +# Agent Note: Agent Client Protocol(ACP)支持——从外部编辑器驱动编码 agent + +Status: implemented + +[English](2026-06-14-acp-agent-client-protocol.md) | 中文 + +## 问题 + +harness 最初仅通过 readline 循环暴露 agent。该接口能传输文本,但编辑器无法以结构化方式创建或恢复会话、关联提示词完成、流式输出推理(reasoning)与工具活动、渲染工具专属 UI、请求权限,或在不干扰其他对话的前提下取消某个对话。ACP(Agent Client Protocol)将这些交互定义为基于 stdio 的 JSON-RPC,Zed 是用于做出具体兼容性决策的目标客户端。 + +桥接层必须保持 harness 既有的所有权边界。它不能依赖具体的 agent loop(智能体循环),不能绕过工具注册表,不能在编辑器中执行 shell 命令,也不能发明第二个会话真源。stdout 同时也是协议传输通道,因此任何意外的日志输出都会破坏连接。 + +## 决策 + +`@deepseek-ai/dsh-acp` 是位于 `packages/ui/acp` 的 UI/客户端驱动插件。它使用 `@agentclientprotocol/sdk` 的 `AgentSideConnection`(基于 stdin/stdout),仅编排接口服务:agent 创建/恢复工厂、会话持久化、工具注册表、用户交互,以及可选的审批/bash 能力。它不修改 agent loop,也不是能力 seam 的实现。 + +桥接层实现以下稳定的会话路径: + +- `initialize` 协商协议版本,声明支持 text 与 `resource_link` 类型的提示词,并声明 `loadSession` 能力。 +- `session/new` 校验绝对路径 `cwd`,将其存入 `SessionHeader`,通过 `ctx.agents` 创建 agent,并返回由组合层支持的配置选项。 +- `session/load` 在构造 agent 之前校验请求的 cwd 与持久化元数据是否一致,在异步恢复期间保留 id,将用户/助手/工具事件作为 ACP update 回放,并报告恢复后的 config-option 折叠结果。 +- `session/prompt` 接受文本和 resource link,拒绝不支持的或空的内容,每个会话同时只允许一个 in-flight 提示词,并在该提示词所属的 `turn/end` 时结算。错误轮次拒绝 RPC;其他关闭轮次的原因通过一个全覆盖的 ACP stop-reason 编解码器映射。 +- `session/cancel` 调用队列感知的 agent 取消路径,仅结算被寻址会话的提示词。 + +工具调用的展示仍由工具自身负责。工具的 `presentCall` 和 `presentResult` 返回 `generic`、`terminal` 或 `diff` 渲染意图变体;桥接层对该联合类型做 switch 并映射到 ACP。没有 presenter 的工具获得通用回退。Bash 终端卡片使用 Zed 的能力门控约定 `_meta.terminal_info`、`_meta.terminal_output` 和 `_meta.terminal_exit`;harness 仍通过 `ctx.bash` 执行命令,保留沙箱、环境清洗、所有权和 cwd。不支持该扩展的客户端收到普通文本内容。文件系统工具提供 diff 卡片和文件位置,桥接层中无需硬编码工具名分支。 + +权限处理是[用户审批 seam](2026-07-06-approval-seam.md)上的一个 answerer,而非 ACP 中的「每次工具调用都询问」策略。对桥接层所属 agent 且带有 call id 的 `approval/request`,会变为该 agent 编辑器会话上的 `session/request_permission`,提供一次性允许/拒绝选项。外部请求或无 call id 的请求委托给下游;缺失或失败的 answerer 会在故障时保持拒绝。发起询问的插件(如预执行策略或 bash 升级)拥有「是否询问」的决策权。 + +当 `ctx.permission` 被组合时,桥接层从部署的预设表中暴露一个 `permission` select。已发布的 `workspace-write` 和 `danger-full-access` 预设各自捆绑一个沙箱模式与一条审批策略;无法匹配的有效旋钮组合产生只能切走的 `custom` 状态。`session/set_config_option` 通过 `PermissionService.set()` 校验并写入两个所属旋钮事件。在开放轮次中的切换立即追加;空闲时的切换叠加在响应中,并在下一次 `agent/prompt-submit` 时锚定到开放轮次之前的请求组装阶段。在此之前它仅存于内存,因此崩溃后恢复的是持久化的折叠结果。ACP session mode 不被建模,因为 config option 是面向未来的协议表面;`AcpConfig.model` 保持连接级别。 + +桥接层还提供基于 ACP 的 `UserInteractionProvider`:`ask_user_question` 请求变为所属会话上的表单引导。select、multi-select、选项描述与自定义回答覆盖语义均被保留。 + +生命周期所有权是显式的。桥接层为每个活跃会话持有一个 `AgentHandle`。断连和 Cordis dispose(资源释放)会取消待处理的提示词,并行 dispose 所有 handle,等待循环完全停稳与持久化刷写,然后移除记录。流通知失败被隔离,因此消失的客户端不会破坏 agent 轮次。ACP 应用组合不加载 stdout logger;一个测试守卫 stdout 仅包含帧化的 JSON-RPC。 + +精确的已支持与已推迟的协议行列表见 [`packages/ui/acp/acp-feature-support.md`](../../../../packages/ui/acp/acp-feature-support.md);包 README 是操作契约。 + +## 曾考虑的替代方案 + +**在 `tools/execute` 监听器前置一层,对每个 ACP 所属调用都询问权限**:否决。这会将权限策略硬编码到 UI 桥接层,即使没有策略要求也会询问,且无法服务于执行开始后才产生的审批请求。共享的 user-approval seam 将机制、询问策略和 UI answerer 分离。 + +**注入具体的 `agentLoop`**:否决。agent 的创建、恢复、空闲观察与释放是 `dsh-agent` 上的接口级所有权操作;UI 插件不需要依赖规则例外。 + +**通过 ACP `terminal/*` 执行 bash**:否决。这会将执行移到 harness 之外,绕过其沙箱、凭证清洗、任务所有权、cwd 解析与会话日志。终端元数据仅用于展示。 + +**将权限预设表示为 ACP session mode**:否决。部署定义的预设已经是一个 config-option select,而 session mode 是 ACP v2 计划移除的遗留接口。 + +**防御性劫持 stdout**:否决。进程级 monkey-patching 超出 Cordis 副作用所有权范围,且与协议传输存在竞争。应用组合拥有 stdout 纯净性。 + +## 后果 + +编辑器可以通过一条 ACP 连接创建、加载、提交提示词、取消、渲染、询问和重新配置多个 harness 会话,无需依赖特定的循环实现。会话事件日志仍是回放、提示词结算、cwd 与每会话配置的持久真源。工具展示与人工回答通道仍是可扩展的插件契约,而非 ACP 专属行为。 + +桥接层有意不实现会话列表/删除/恢复/关闭能力、MCP 透传、附加目录、图片/音频/嵌入资源提示词、plan、斜杠命令、用量更新、编辑器文件系统委托或 ACP 终端执行子协议。后续已通过标准会话配置选项加入运行时模型选择,见 [LLM 目录与 ACP 选择 Agent Note](../architecture/2026-07-15-llm-model-catalog-and-acp-selection.md)。 + +空闲时的配置选择在实时响应中是真实的,但在下一次 `agent/prompt-submit` 将其锚定到开放轮次之前不具持久性。在该边界之前崩溃会丢失待定选择;这是保持会话事件封闭于轮次内且回放安全的代价。 + +## 验证 + +ACP 测试套件覆盖内存协议编解码器、创建/加载回放、精确的提示词结算、取消竞争、不支持的内容、工具展示、终端能力回退、权限结果映射、config-option 校验与持久化、多会话隔离、断连/释放后的完全停稳,以及 HMR(热模块替换)清理。快照测试与 built-bin 测试验证应用组合,真实 API 的 e2e 测试在无 key 时自动跳过。 diff --git a/.agents/notes/implemented/feature/2026-06-14-acp-multi-session.i18n.yaml b/.agents/notes/implemented/feature/2026-06-14-acp-multi-session.i18n.yaml new file mode 100644 index 0000000000..4969861f15 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-06-14-acp-multi-session.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-14-acp-multi-session.md: 43aa32a43fef7aa69f5efd45d4c8176da9f459cd +2026-06-14-acp-multi-session.zh.md: 6835f9623b89dc20d6c7b3054365cd9c39402aeb diff --git a/.agents/notes/implemented/feature/2026-06-14-acp-multi-session.md b/.agents/notes/implemented/feature/2026-06-14-acp-multi-session.md index 91d85aeded..43aa32a43f 100644 --- a/.agents/notes/implemented/feature/2026-06-14-acp-multi-session.md +++ b/.agents/notes/implemented/feature/2026-06-14-acp-multi-session.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-06-14-acp-multi-session.zh.md) + ## Problem An ACP editor can keep several conversations alive over one agent subprocess. A single-active-session bridge would force extra processes and would not match Zed's client model, which tracks multiple session ids and concurrent loads. Multiplexing introduces isolation risks: events, prompt completion, cancellation, permission prompts, config selections, and predictable background-task ids must never cross session boundaries. diff --git a/.agents/notes/implemented/feature/2026-06-14-acp-multi-session.zh.md b/.agents/notes/implemented/feature/2026-06-14-acp-multi-session.zh.md new file mode 100644 index 0000000000..6835f9623b --- /dev/null +++ b/.agents/notes/implemented/feature/2026-06-14-acp-multi-session.zh.md @@ -0,0 +1,47 @@ +# Agent Note: 在单个连接上多路复用并发 ACP 会话 + +Status: implemented + +[English](2026-06-14-acp-multi-session.md) | 中文 + +## 问题 + +一个 ACP(Agent Client Protocol)编辑器可以在同一个 agent(智能体)子进程上保持多个对话。如果桥接层只支持单活跃会话,就不得不启动额外进程,也无法匹配 Zed 的客户端模型——该模型跟踪多个会话 id 和并发加载。多路复用引入了隔离风险:事件、提示词完成、取消、权限提示、配置选择以及可预测的后台 task id 绝不能跨越会话边界。 + +## 决策 + +ACP 桥接层将活跃会话存储在 `Map<SessionId, SessionRecord>` 中。agent 作用域的回调使用 `ownedRecord`:在正向 map 中查找 `agent.session.id`,且仅当该记录拥有精确的 agent 对象时才接纳它,使外部的同 id 对象无法冒领会话。一条记录拥有其 agent 句柄、进行中的提示词、活跃的工具调用展示状态、待处理的空闲配置切换、会话 cwd 以及客户端能力快照。一个独立的 loading-id 集合在异步恢复之前预留每个 id,使两个流水线化的加载请求无法构造出重复的 agent;不同 id 可以并发加载。 + +每个 `session/event` 和 `agent/status` 回调在发送或结算任何内容之前,先解析出所属记录。每个会话独立允许一个进行中的提示词。提示词记录一个日志水位线,捕获自己的 `turn/start`,并仅在匹配的 `turn/end` 到达时结算;来自已取消的前一轮次的迟到 end 不能 resolve 更新的提示词。`session/cancel` 定位到一条记录,只调用该 agent 的队列感知取消路径。 + +权限归属使用对正向 map 的同一精确 agent 检查。ACP `approval/request` 应答器只向拥有发起请求的 agent 的编辑器会话发起提示,并将外部请求委托出去。用户交互引出同样按 agent 归属路由。每会话的沙箱和审批配置值只折叠该会话自身的事件,待处理的空闲切换存储在该记录上,直到下一轮次将其锚定。 + +后台 bash 任务携带一个不透明的 owner token,其值等于所属会话 id。`bash_output` 和 `bash_kill` 在读取或终止之前,将调用方的 token 与执行器的任务归属进行比较;仅凭可预测的 task id 不能获得访问权。归属信息与执行器任务一起存储,因此工具插件重载不会擦除它。 + +连接拆除时清空活跃 map,将每个待处理的提示词以取消状态结算,并并行 dispose(资源释放)所有 `AgentHandle`。每个句柄停止并等待其循环完成、在仍然附着时刷新会话、注销 agent 并移除会话。拆除操作被 memoize 化,由客户端断连和插件 dispose 共享。 + +## 协议与工作区作用域 + +[ACP v1 明确允许一个连接上存在多个并发会话](https://github.com/agentclientprotocol/agent-client-protocol/blob/01beb5fb5eec60e9f516a80d85eb03594bac61e3/docs/get-started/architecture.mdx#L16-L24),每个新会话都携带自己的主 `cwd`。本桥实现该会话级多路复用,其中包括[按会话 cwd 决策](../architecture/2026-07-02-fs-per-session-cwd.md)所记录的不同主工作区;它不会为每个会话创建一个 agent 子进程。 + +一个会话内部的多根项目是另一项可选能力:ACP 把[有效根目录定义为主 `cwd` 加 `additionalDirectories`](https://github.com/agentclientprotocol/agent-client-protocol/blob/01beb5fb5eec60e9f516a80d85eb03594bac61e3/docs/protocol/v1/session-setup.mdx#L313-L367)。[Zed 仅在 agent 公布该能力时发送其余项目工作目录](https://github.com/zed-industries/zed/blob/ea77ca2818f3e059a2b61ecc7e63b67e01e1cec5/crates/agent_servers/src/acp.rs#L1139-L1145),否则会[从会话请求中丢弃这些目录](https://github.com/zed-industries/zed/blob/ea77ca2818f3e059a2b61ecc7e63b67e01e1cec5/crates/agent_servers/src/acp.rs#L1454-L1472)。如其[已知限制](../../../../packages/ui/acp/README.md#known-limitations-and-deferred-work)所记录,桥不公布该能力,并拒绝非空值,因此当前 Zed 多根项目到达桥时只携带第一个工作目录。 + +[标准传输是每个 stdio 连接一个由编辑器启动的 agent 子进程](https://github.com/agentclientprotocol/agent-client-protocol/blob/01beb5fb5eec60e9f516a80d85eb03594bac61e3/docs/protocol/v1/transports.mdx#L17-L42);多个编辑器连接因此需要多个子进程或自定义传输,而本决策保证的是一个连接内部存在多个会话。在该连接内,`ctx.sandboxPolicy` 把每个会话的 `cwd` 解析为其自己的 `workspace-write` 根目录,因此共享的 bash 和文件系统服务可以服务并发项目而不授予跨项目写入。这不会添加 ACP `additionalDirectories`;它只是从已经支持的「每会话一个主根目录」路径中移除了进程级根目录限制。 + +## 曾考虑的替代方案 + +**每连接单活跃会话**:否决。增加进程开销,与目标客户端的多会话形态相矛盾,且并未消除编辑器端的多路复用需求。 + +**每会话 `ctx.extend()`**:否决。子上下文本身不会创建子插件 fiber,因此监听器仍属于桥接层 fiber。实际实现的桥接层使用全局监听器加显式 O(1) 解复用,以及每会话拥有的记录;agent 生命周期由 `AgentHandle` 管理。 + +**以 Agent 对象标识作为 bash 任务归属**:否决。恢复或替换后的 agent 对象可能合法地代表同一个持久会话。不透明的会话 token 才是跨边界的标识,应当在插件重载后仍然存活。 + +## 后果 + +N 个会话可以并发地进行流式输出、提示词、权限请求、配置切换和后台任务运行,而不会交错或跨会话结算。一个会话中的取消或 dispose 不影响相邻会话。桥接层为此付出了显式 map 和隔离测试的代价,但它不会为每个会话添加一组监听器,从而避免了长连接期间的监听器扇出。 + +桥接层目前仍未暴露独立关闭单个活跃会话的协议方法。当前所有记录在连接拆除时一起离开;会话关闭/恢复的生命周期能力在 ACP 功能清单中仍处于延期状态。 + +## 验证 + +多会话测试套件通过交错更新、独立的进行中提示词、定向取消、相同 id 与不同 id 的加载竞争、权限路由、配置隔离以及拆除来驱动并发会话。工具 bash 测试证明一个会话无法读取或终止另一个会话的后台任务。 diff --git a/.agents/notes/implemented/feature/2026-06-15-code-mode.i18n.yaml b/.agents/notes/implemented/feature/2026-06-15-code-mode.i18n.yaml new file mode 100644 index 0000000000..9375a02315 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-06-15-code-mode.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-15-code-mode.md: 94a95ba2c5760c0fed6ebfe09330546f401c42c4 +2026-06-15-code-mode.zh.md: 0ba5d69258bce23a24db9a0b470ddb074840cba7 diff --git a/.agents/notes/implemented/feature/2026-06-15-code-mode.md b/.agents/notes/implemented/feature/2026-06-15-code-mode.md index 0f5e8cc94b..94a95ba2c5 100644 --- a/.agents/notes/implemented/feature/2026-06-15-code-mode.md +++ b/.agents/notes/implemented/feature/2026-06-15-code-mode.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-06-15-code-mode.zh.md) + ## Problem In the registry's native presentation, the agent loop advertises every visible capability as a JSON-schema function definition. `ToolRegistry` contributes its schemas to the system-prompt assembly, the assembly's `tools` land on the wire (and in the logged request header), the model invokes one `tool-call` block per step, and the loop dispatches each call through `ctx.tools.execute()` **sequentially** (parallel tool execution is an explicit open TODO in `dsh-tools` and [docs/architecture.md](../../../../docs/architecture.md)), with **every** intermediate `tool-result` re-entering the model's context on the next request. diff --git a/.agents/notes/implemented/feature/2026-06-15-code-mode.zh.md b/.agents/notes/implemented/feature/2026-06-15-code-mode.zh.md new file mode 100644 index 0000000000..0ba5d69258 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-06-15-code-mode.zh.md @@ -0,0 +1,133 @@ +# Agent Note: Code Mode——模型针对工具注册表编写 TypeScript + +Status: implemented + +[English](2026-06-15-code-mode.md) | 中文 + +## 问题 + +在注册表的原生呈现方式下,agent loop(智能体循环)将每个可见能力以 JSON Schema 函数定义的形式通告给模型。`ToolRegistry` 将其 schema 贡献给系统提示词组装,组装结果中的 `tools` 落到协议格式(wire format)上(也记录在请求头日志中),模型每步调用一个 `tool-call` 块,循环通过 `ctx.tools.execute()` **逐个**分发每次调用(并行工具执行是 `dsh-tools` 和 [docs/architecture.md](../../../../docs/architecture.md) 中明确标注的 open TODO),且**每一个**中间 `tool-result` 都会在下一次请求时重新进入模型上下文。 + +对于多步工具操作,这种方式 token 开销大且串行。模型无法组合工具——遍历结果集、根据中间值分支、扇出、后处理——每次调用都需要一次完整的模型往返,而每次往返都会把完整的中间结果拖回上下文,不管模型是否需要。 + +Cloudflare 的 [Code Mode](https://blog.cloudflare.com/code-mode/) 提出了一种替代方案,基于一个简单的观察:LLM(大语言模型)编写代码的能力优于发出工具调用,因为它们见过数百万行真实代码,而人为构造的工具调用 trace 相对很少。模型不再每步发出一次工具调用,而是针对工具生成的 API 编写一段 TypeScript 程序,程序在沙箱运行时中执行,模型只策展返回的内容——仅限它 print 或 return 的部分——而非所有中间结果。 + +工具呈现属于掌管工具可见性的注册表:如果把第二种呈现方式实现为事后的 waterfall(瀑布式事件)变换,正确性将依赖监听器顺序,并与[可重建请求](../architecture/2026-07-05-reconstructable-requests.md)冲突。执行基底同样属于基础设施而非占位实现:Node `worker_threads` 提供独立 isolate、空环境、堆上限以及对热同步循环的终止能力,同时契合 harness 既有的信任模型(§信任姿态)。 + +## 决策 + +三项决策,各自在下方独立小节中展开: + +1. **Code Mode 是 `ToolRegistry`(`dsh-tools`)的一等呈现模式**,通过经校验的 `mode` 配置选择:`'native'`(默认,贡献可见能力 schema)、`'code'`(注册表仅贡献其保留的 `run_code` 传输通道加一份生成的 SDK `.d.ts` 到系统提示词中)或 `'both'`(原生 schema 加传输通道 + SDK)。注册表在源头塑造其权威贡献;协作式提示词组装的结果仍具权威性,记录在日志中的请求头精确反映该返回的呈现。 +2. **代码执行是一个能力 seam**——`packages/code-runtime/` 包含接口包 `@deepseek-ai/dsh-code-runtime`,拥有 `ctx.codeRuntime`([能力 seam](../architecture/2026-06-13-capability-seams.md);消费方 = `dsh-tools`,core 消费 seam 的先例见 `agent-loop` → `dsh-llm`)。运行时对工具一无所知:它接收一段程序和命名的异步绑定,执行程序,报告 `{ value, logs, error? }`。语言和基底是后端属性,因此未来的 Python 或容器后端只是另一个实现包,而非重新设计。 +3. **交付的实现是 `@deepseek-ai/dsh-code-runtime-worker`**:每次运行 spawn 一个全新的 Node worker 线程,对模型的 TypeScript 进行 type-strip 后执行,绑定通过消息端口桥接,环境为空,堆/输出/时间上限可配置,并支持硬终止。其信任姿态在设计上等同于 bash——无需 unsafe-acknowledgement flag——因为 harness 已经交付了 `dsh-bash-local`,后者以严格*更高*的环境权限执行模型编写的任意 shell 命令。 + +本说明负责定义 Code Mode 的呈现、组合、隔离与结算基础。后续的[类型化工具返回值 Agent Note](2026-07-20-code-mode-typed-tool-returns.md)负责定义生成的输出映射、规范绑定值、`ToolCallError` 和无损外层输出边界。 + +### 注册表拥有模式 + +`ToolRegistry` 获得一个经 schemastery 校验的配置(`static Config`),这是它的第一个配置:`mode: 'native' | 'code' | 'both'`,默认 `'native'`。部署通过 `cordis.yml` 翻转模式(`tools: { mode: code }`),无需改代码,遵循 no-hardcoded-tunables 约定。 + +**协议工具列表。** 注册表在 `'native'` 下贡献可见能力,在 `'code'` 下仅贡献 `run_code`,在 `'both'` 下两者都贡献。最终的 `PromptAssembly.tools` 列表记录在请求头中。`run_code` 是一个保留的呈现传输通道,位于注册和限制层之外;直接提示词提供方和组装 waterfall 仍各自负责自己的贡献。 + +**与 `toolOrder` 的交互,预先说明:** 如果配置的 `systemPrompt.toolOrder` 引用了原生能力名称,在 `mode: 'code'` 下会拒绝所有组装,因为那些名称不在该模式的协议校验范围内。这是正确行为而非 bug:使用 Code Mode 的部署需要更新其 order 配置或移除它。 + +**SDK 提示词段。** 在 `'code'` 和 `'both'` 下,tool-guidance order band 中的惰性 `tools:sdk` 段为当前 scope 的可见能力渲染 TypeScript 声明加固定的使用说明。它共享查找和执行可见性,排除 `run_code`,并按字典序排列工具以获得字节稳定的输出。 + +**组装所有权。** `run_code` 和 `tools:sdk` 作为正常的组装输入进入受信任的 `system-prompt/assemble` waterfall。一个 scoped 的 `tools:sdk` 段可以在分发前遮蔽全局默认值,监听器也可以移除或替换任一贡献。waterfall 返回的组装结果是最终的,因此修改这些输入的人有责任在部署期望 Code Mode 可用时保持协议面的完整性;没有恢复 pass 会覆盖有意的组合。 + +**代码生成。** `jsonSchemaToTs()` 将 `defineTool` 的 JSON Schema 子集映射为 TypeScript,将 schema 描述带入 JSDoc,不支持的构造降级为 `unknown`。SDK 将工具暴露为带引号的对象键,支持任意名称而无需别名或冲突处理。类型是建议性的,因为运行时在执行前会剥离类型。 + +### run_code 工具与分发桥 + +在 `'code'` 和 `'both'` 下,注册表拥有 `run_code` 作为保留的呈现传输通道,带一个必需参数 `{ code: string }`。它由一个正常的 `ToolDefinition` 表示以供分发,但位于可过滤的能力层之外,因此限制规则不会意外移除 Code Mode 的唯一入口。调用遍历完整的工具流水线——`tools/pre-execute` → 单调守卫 → `tools/execute` 包裹分发 → `tools/post-execute` → 由定义拥有的可选 `finalizeContent` → 不可变的 `tools/result` 通知——与原生调用完全一致;权限插件可以在程序运行前检查程序文本,最终结果观察者看到的是规范化的外层结果。其 `execute(args, exec)`: + +1. **构建绑定。** 一个 run 级别的 signal 跟随外层取消,并在 run 结算时被 abort。每个可见工具绑定都会对无损 JSON 参数创建快照,等待序列化队列,以确定性的 call id 和外层 token 作为 `parent` 执行,通过外层 execution 延后返回的上下文,并记录 `tool/code-dispatch`。成功时返回工具最终的规范 JSON 值;失败则变为程序可见的 `ToolCallError`。每个子调用保留自己不可变的执行标识,并遍历完整的工具流水线。 +2. **运行程序**:`ctx.codeRuntime.run({ program: args.code, bindings: [{ global: 'tools', functions }], signal: runController.signal })`。运行时接收的是 run 级别的 signal 而非仅调用方的外层 signal,因此外层 run 以任何方式结算都会同时 abort 运行时内部的工作。 +3. **完全停稳后结算。** 运行时结算后,桥 abort 未完成的工作并排空分发队列后再返回。成功时返回捕获的日志和完成值,将其作为规范输出;注册表再把该值渲染为持久化的 `tool/result.content`,供结果卡片直接读取。运行时失败变为 `CodeRunFailedError`;后端拒绝使用注册表的正常错误边界。两者都产生结构化的错误结果,且 `run_code` 结算后不允许子调用追加。 + +**子调用上下文通过父调用延后。** 在 `run_code` 内部注入会破坏父调用/结果的相邻性,因此 `ToolRunContext.deferContext()` 按分发顺序收集每个子结果的 `additionalContexts` 条目。即使程序后来抛出异常,注册表仍携带该数组;循环只在外层结果与步骤中所有兄弟结果之后追加每个条目。外层 post-execute 阻止会丢弃工具延后的条目,只暴露阻止 decision 显式附加的上下文。 + +**并发被序列化。** 每次 run 拥有一个分发队列,因此即使 `Promise.all` 也按提交顺序执行工具调用。结算时放弃尚未开始的排队调用。并行化需要每个工具的并发安全元数据。 + +**呈现。** `run_code` 的 render intent 按[呈现意图 Agent Note](../architecture/2026-07-02-tool-render-intent-union.md)在此决定:`presentCall` 创建一个 `generic` 卡片,`kind: 'execute'`,以程序文本作为标题,并将同一程序文本作为 `rawInput`;`run_code` 有意不声明 `presentResult`,因此 ACP 和 TUI 会通过通用原始内容回退机制,使用最终持久化的 `tool/result.content` 补全该卡片,其中包括捕获的日志,以及返回值、失败信息或 post-policy 输出落盘预览。程序作为标题是因为 ACP execute 卡片可靠地渲染该字段,而某些客户端会省略 body 和 raw-input 内容。这不是 `terminal` 卡片:该卡片的语义是「工作目录中的 shell 命令」,程序不是。参见[结果卡片完整性说明](../bug-fix/2026-07-20-code-mode-result-card-completeness.md)。 + +### 可观测性:`tool/code-dispatch` + +每次子分发追加一个仅日志的 `tool/code-dispatch` 事件,包含父子 call id、工具标识、规范化参数和结果摘要。它不进入模型历史,但可供持久化和 UI 使用。追加发生在开放的 `run_code` 轮次内。没有 agent 的直接执行仍然运行,但无法记录该事件。 + +### code-runtime seam + +`packages/code-runtime/code-runtime/`——`@deepseek-ai/dsh-code-runtime`,仅依赖 `cordis`。一个抽象的 `CodeRuntime extends Service`(`super(ctx, 'codeRuntime')`)加上词汇: + +- `CodeRunRequest = { program: string; bindings: CodeBindingNamespace[]; signal?: AbortSignal }` +- `CodeBindingNamespace = { global: string; functions: Record<string, (args: unknown) => Promise<CodeJsonValue>>; errorClass?: { name: string; memberNameProperty: string } }`——运行时将每个命名空间作为程序内部的全局异步函数对象暴露;可选描述符要求运行时注入真正的、程序可见的 reject 类,而无需让 seam 获知消费方专用名称。`CodeJsonValue` 是这个低依赖 seam 的结构化无损 JSON 类型,因此绑定参数与解析值可以完整跨越实现的序列化边界。 +- `CodeRunResult = { value?: CodeJsonValue; logs: string[]; error?: CodeRunFailure }`——程序执行失败时,执行 promise 仍会 fulfill,并通过 `error` 字段返回失败结果。只有调用方/seam 误用(例如重复的绑定命名空间)时,`run()` 才会 reject;消费方仍在自己的错误边界处理不合规后端的拒绝。 +- `CodeRunFailure = { kind: 'exception' | 'timeout' | 'abort' | 'worker-exit' | 'invalid-output' | 'output-limit'; message: string }`——按[防御性模式](../../../../docs/defensive-patterns.md)独立报告的正交结果;超时的 run 不是异常,abort 不是超时,有损完成值不是溢出,基底退出也与上述情况相互独立。 +- 两个只读的后端描述符,仅供信息参考而非门禁判定:`language`(程序必须使用的语言——交付的后端为 `'typescript'`;Python 后端会声明自己,并在呈现侧配对自己的 SDK 生成器)和 `isolation`(交付的后端为 `'worker-thread'`;未来可为 `'process'`、`'container'` 等)。`dsh-tools` 在 MVP 中要求 `language === 'typescript'`——其代码生成输出 TS——否则组装会大声失败,与 `toolOrder` 违规时的配置错误惯用法相同(如 `mode` 为非 native 但根本没有加载 `ctx.codeRuntime`)。 + +请求包含所有运行时输入;实现方拥有经校验的超时和上限默认值。注册表仅在组装 Code Mode 时查找可选的运行时,因此 native 模式不依赖它。缺失或语言不兼容的运行时会大声失败。替代基底或语言可以在同一 seam 背后替换实现,配对相应的 SDK 生成器。 + +### worker-thread 运行时 + +`@deepseek-ai/dsh-code-runtime-worker`,`packages/code-runtime/` 组的第二个包(package)。每次 `run()`: + +1. **宿主侧 type-strip**,使用 Node 内置的 `stripTypeScriptTypes`(`node:module`;在本仓库的整个引擎范围 `^22.19.0 || >=24.0.0` 内可用,且保持位置不变,因此运行时错误行号与模型源码一致)。仅剥离模式拒绝不可擦除的语法(`enum`、namespaces)——该拒绝以 `error.kind: 'exception'` 加 Node 的消息返回,SDK 说明写明「仅限可擦除 TypeScript」,模型像处理其他程序错误一样自我修正。语法级失败不会 spawn worker。 +2. **每次 run spawn 一个全新 `Worker`**,来自包自身的 bootstrap 模块:`env: {}`(真正为空——比 spawn 命令的 scrubbed-env 规则更严格),`resourceLimits` 来自配置,`stdout`/`stderr` 捕获到 `logs` 而非继承。不做池化,不跨 run 保留状态:程序的世界随 worker 消亡,这使得 run 仅从日志即可重建,状态泄漏不可表达。 +3. **在 bootstrap 中执行**:剥离后的程序成为一个 `AsyncFunction` 的函数体,其参数是绑定全局变量、消费方声明的 reject 类和一个捕获式 `console` shim,因此顶层 `await` 和 `return` 可用。Code Mode 声明 `ToolCallError`,成员属性为 `toolName`;运行时无需硬编码工具即可实体化真正的构造函数。无损 JSON 完成值会精确跨越边界;`undefined` 仍表示缺席,有损值产生 `invalid-output`,过大的外层结果产生 `output-limit`,而不会退化为检查格式化后的字符串替代品。 +4. **通过消息端口桥接绑定**:worker 中的每个绑定函数发送 `{ id, global, name, args }` 并等待回复;宿主根据请求的绑定校验名称、调用、并回复 `{ id, ok, value }` 或 `{ id, ok: false, message }`(宿主侧绑定拒绝变为程序侧 rejection)。worker 侧的命名空间对象通过 `defineProperty` 构建为 null-prototype,因此名为 `__proto__`、`constructor` 或 `toString` 的绑定是普通自有属性,而非原型链碰撞。未知名称、重复 id 和结算后消息被拒绝或忽略——端口协议假设对端是恶意的,因为对端运行的是模型代码。 +5. **强制独立预算。** `computeMs` 计量 worker 忙碌时间,允许慢速的 awaited 工具而不放过热循环。`maxWallMs` 约束总经过时间,包括未解析的等待。`maxOutputBytes` 只约束序列化后的外层日志、完成值或诊断的组合;中间绑定值没有字节数上限。到期、取消和完成都终止 worker,堆退出或外层溢出会作为显式失败报告。 +6. **dispose 至完全停稳**:服务自身的 dispose(资源释放)终止进行中的 worker 并*等待*其退出后再 resolve,遵循[防御性模式](../../../../docs/defensive-patterns.md)。 + +### 信任姿态 + +worker 运行时提供的是隔离,而非安全边界:模型代码可以访问 Node API,权限与 bash 工具相当。`worker.terminate()` 停止线程但不停止它 spawn 的 OS 进程。Code Mode 使用与 bash 相同的 `tools/pre-execute` 策略门禁,并额外提供空环境、堆限制、独立 isolate 和对程序本身的硬终止。需要硬多租户边界的部署需要为代码和 bash 都使用容器级后端;运行时的 isolation 描述符让它们能区分该后端。 + +### 模型看到的内容 + +SDK 指示模型编写一个异步的可擦除 TypeScript 函数体,通过 `await tools.name(args)` 调用工具,在需要时捕获被拒绝的工具调用,并仅 return 或 log 应重新进入上下文的输出。即使在 `Promise.all` 下调用仍保持顺序。声明前缀可能与原生 schema 一样大,尤其在 `'both'` 下,但对提供方缓存保持稳定。 + +## 后果 + +切换到 `'code'` 的部署必须更新任何仅限 native 的 `toolOrder`。组装监听器有责任维护任何被重写的协议面的完整性。子分发保持序列化,而每次调用的上下文会通过外层结果保留其 source、信封与元数据。 + +## 测试 + +- **Worker 运行时:** 真实 worker 测试覆盖类型化的绑定值与失败、每一种无损 JSON 根类型的完成值、无效和超限输出、精确的组合账本边界、compute 和 wall 预算、恶意绑定流量、空环境以及 dispose 至完全停稳。一个构建后包测试在纯 Node 下运行 worker 入口。 +- **注册表集成:** 测试覆盖代码生成、所有呈现模式、保留名称和限制规则、scoped 可见性、权威组装重写、`toolOrder`、运行时兼容性失败、完整流水线子分发、parent-token 关联、序列化、取消和队列排空、JSON 规范化、错误传播、日志事件、成功与失败程序中的有序上下文延后、外层阻止抑制以及 HMR(热模块替换)清理。 +- **带密钥 e2e:** 真实模型在一个程序中组合两次 bash 调用;另一个模型通过 Code Mode fs 分发发现嵌套的工作区指令。测试验证折叠的请求头、关联的分发事件、结果文件、延后上下文和模型行为。 +- **快照:** `code-mode-turn`、`both-mode-turn` 和 `code-mode-workspace-context` fixture(测试前置数据)固定 SDK 文本、请求头工具列表、分发事件、延后上下文和结果卡片。 + +## 曾考虑的替代方案 + +**一个零核心改动的附加消费方插件。** 否决,因为 `agent/request` 在[可重建请求](../architecture/2026-07-05-reconstructable-requests.md)下仅限 call-config,而变换已组装的工具列表需要在不拥有其配置的情况下撤销 `toolOrder` 规范化,并依赖监听器顺序。向模型提供哪些工具、以何种表示形式提供,是注册表的单一关注点:原生 schema 和 SDK 是同一个可见存储的两种投影。 + +**`node:vm` 作为参考运行时,加固推迟。** 否决:`node:vm` 不是隔离(原型链逃逸可达宿主 realm)且无法中断热循环。worker 线程提供独立 isolate、空环境、`resourceLimits` 和可靠的 `terminate()`,信任等级等同于 bash,因此参考实现和生产实现是同一个包,无需 unsafe-acknowledgement 仪式。 + +**在原生工具调用上做结果省略/摘要。** 仅解决问题的上下文膨胀一半:裁剪旧 `tool-result` 作为可重建请求下的日志化表面替换成本低,但仍需每次调用一次模型往返,且无法表达循环、分支或汇合。互补而非竞争;它可以在 Code Mode 下为残余的原生调用分层。 + +**循环中的并行原生分发。** 往返成本的另一个答案;仍是有效的未来工作(open TODO),仍被并发安全元数据阻塞,且仍无组合能力——它并行化的是模型在一步中已经决定的调用。Code Mode 的序列化队列决策保持两者兼容:当元数据就绪时,原生并行分发和每工具绑定并行化一起解锁。 + +**始终排他(忠于 Cloudflare,无模式)。** 否决,因为本 SDK 的主要消费方是编码 agent:其日常的单次调用(`bash`、`read`、`edit`)作为原生调用已经是最优的,强制每次编辑都通过程序会给常见场景增加负担。mode 配置让忠实形式(`'code'`)只需一行配置即可启用,而不强加于人。 + +**每工具可见性分层(此工具 native,彼工具 code-only)。** 推迟:它需要每工具元数据和 `'native' | 'code' | 'both'` 不提供的呈现拆分,且其设计取决于模型在 `'both'` 下如何分配使用的证据。 + +**SDK 中的清洁化标识符别名**(`my-tool` → `my_tool`,Cloudflare 的做法)。否决:`declare const` 上的带引号键使每个名称可达,零别名碰撞逻辑;模型能正常处理 `tools["my-tool"](…)`。 + +**REPL 风格的持久内核**(状态跨 `run_code` 调用存活)。在 MVP 中否决:跨调用状态对会话日志不可见,破坏了「每个请求是日志的纯函数」这一可重建性保证;每次 run 全新保持了这一点。内核风格的后端在未来仍可通过同一 seam 表达,配合自己的日志方案。 + +## 风险 + +**Worker 不是硬安全边界。** 有意为之且已文档化(§信任姿态):姿态等同于既有的 bash 工具,隔离程度超过它,门禁使用相同的 seam。需要更强隔离的部署需要未来的 `isolation: 'container'` 后端——作为 seam 设计的扩展点跟踪,而非本设计的 TODO。 + +**`stripTypeScriptTypes` 标记为 experimental。** 它与 Node 自身原生 `.ts` 执行背后的引擎(amaro/swc)相同,在本仓库的整个引擎范围内作为 API 暴露。缓解措施:运行时的单元测试套件固定了所依赖的行为(位置保持、可擦除限制的拒绝消息形状宽松匹配),调用位于一个私有函数之后,且 `amaro`/`sucrase` 是 API 变化时的直接替代品。仅可擦除子集是面向模型的契约线,错误路径是一个可工作的反馈循环,而非死胡同。 + +**SDK 的提示词成本,尤其在 `'both'` 下。** `.d.ts` 可能与它补充的原生 schema 体量相当;`'both'` 携带两种表示。前缀稳定性 + 提供方缓存摊销了每会话成本;mode 是每部署的;本 Agent Note 不做无条件节省的声明。何时优先使用哪种模式的量化指导明确属于上线后学习。 + +**注册表 scope 增长。** `dsh-tools` 吸收了代码生成、一个工具、一个桥和一个事件。通过包内的模块边界(`ts-types.ts`、`code-mode.ts` 与 `schema.ts`/`json-schema.ts`/`presentation.ts` 并列)和 seam 约束:所有基底相关的内容都在 `ctx.codeRuntime` 之后。 + +**大型无损 JSON 值可能耗尽内存。** 工具绑定会在分发前对无损 JSON 创建快照,并完整返回规范 JSON 解析值。运行时会校验 worker 端口两侧,但不对单次绑定设置字节数上限;结构化克隆成本以及进程或 worker 内存构成实际边界。只有包含日志、完成值和失败诊断的组合外层输出账本受字节数上限约束。 + +**仅序列化的子分发。** `Promise.all` 尚未获得挂钟并行性,仅减少往返次数;模型可能过度期望。说明中已声明;解除此限制与原生并行分发 TODO 所需的并发安全元数据绑定。 + +**预算计量读取事件循环,而非 flag。** 忙碌时间轮询(`eventLoopUtilization()`)比精确 CPU 计量更粗糙——预算到期最多延迟一个轮询间隔——且其正确性声明(「pending 的分发不能暂停它」)对恶意程序是承重的。两侧都有单元测试(带 pending 诱饵分发的热循环在 `computeMs` 处死亡;在慢绑定上空闲的程序存活到 `maxWallMs`),轮询间隔是内部常量而非配置——部署无法将其误调为绕过手段。 diff --git a/.agents/notes/implemented/feature/2026-06-17-filesystem-tool-schemas.i18n.yaml b/.agents/notes/implemented/feature/2026-06-17-filesystem-tool-schemas.i18n.yaml new file mode 100644 index 0000000000..60a0b50006 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-06-17-filesystem-tool-schemas.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-17-filesystem-tool-schemas.md: 9941b3916b361a916c8148eb099eb8cfd46371c8 +2026-06-17-filesystem-tool-schemas.zh.md: 47e43c47db83b1fcc292b17cf0113d9abd9293d1 diff --git a/.agents/notes/implemented/feature/2026-06-17-filesystem-tool-schemas.md b/.agents/notes/implemented/feature/2026-06-17-filesystem-tool-schemas.md index 59bf9be768..9941b3916b 100644 --- a/.agents/notes/implemented/feature/2026-06-17-filesystem-tool-schemas.md +++ b/.agents/notes/implemented/feature/2026-06-17-filesystem-tool-schemas.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-06-17-filesystem-tool-schemas.zh.md) + ## Problem [The filesystem capability-seam Agent Note](../architecture/2026-06-17-filesystem-capability-seam.md) defines the filesystem capability seam (`ctx.fs`), the package split (`dsh-fs`, `dsh-fs-local`, `dsh-tool-fs`, plus the `dsh-fs-policy` policy plugin), and the observed-file/stale-version policy for read-before-write/edit checks — which the [split-fs-seam](../simplification/2026-06-26-fsspec-style-fs-seam.md) and [event-gate](../architecture/2026-06-26-file-context-as-event-gate.md) Agent Notes moved off `ctx.fs` into the `dsh-fs-policy` plugin on the `fs/*` event gate. The remaining decision for the first filesystem tool delivery is the model-facing schema surface: what arguments the model sees for `read`, `write`, and `edit`. diff --git a/.agents/notes/implemented/feature/2026-06-17-filesystem-tool-schemas.zh.md b/.agents/notes/implemented/feature/2026-06-17-filesystem-tool-schemas.zh.md new file mode 100644 index 0000000000..47e43c47db --- /dev/null +++ b/.agents/notes/implemented/feature/2026-06-17-filesystem-tool-schemas.zh.md @@ -0,0 +1,112 @@ +# Agent Note: 文件系统工具 schema——面向模型的读/写/编辑接口形状 + +Status: implemented + +[English](2026-06-17-filesystem-tool-schemas.md) | 中文 + +## 问题 + +[文件系统能力 seam Agent Note](../architecture/2026-06-17-filesystem-capability-seam.md) 定义了文件系统能力 seam(`ctx.fs`)、包(package)拆分(`dsh-fs`、`dsh-fs-local`、`dsh-tool-fs`,加上 `dsh-fs-policy` 策略插件),以及针对 read-before-write/edit 检查的 observed-file/stale-version 策略——[拆分文件系统 seam](../simplification/2026-06-26-fsspec-style-fs-seam.md)和[事件门控插件](../architecture/2026-06-26-file-context-as-event-gate.md) Agent Note 后来将其从 `ctx.fs` 移至 `dsh-fs-policy` 插件的 `fs/*` 事件门上。首次文件系统工具交付剩余的决策是面向模型的 schema 接口:模型在 `read`、`write` 和 `edit` 中看到哪些参数。 + +该 schema 应足够小,以便在 `dsh-tool-fs` 的首次实现中完成,但又足够稳定,使未来的本地/远程/沙箱文件系统后端不需要改动面向模型的接口。同时应避免从参考系统中照搬所有选项。Claude Code 和 OpenCode 暴露了类似的核心文件工具,但在命名风格和额外 flag 上有所不同;本 Agent Note 为原型选择最小的共有接口。 + +## 决策 + +`@deepseek-ai/dsh-tool-fs` 在首个文件系统工具套件中暴露以下三个面向模型的工具: + +| 工具 | 我们的 schema | Claude Code | OpenCode | 说明 | 原型包含 | +|---|---|---|---|---|---| +| `read` | `read(file_path, offset?, limit?)` | `Read(file_path, offset?, limit?, pages?)` | `read(filePath, offset?, limit?)` | 仅文件;`offset` 从 1 开始;首版不支持图片、PDF 或多模态内容。 | 是 | +| `write` | `write(file_path, content)` | `Write(file_path, content)` | `write(content, filePath)` | 创建或覆盖 UTF-8 文本。在默认 fs-policy 下,更新现有文件前必须先观测;创建新文件则不需要。 | 是 | +| `edit` | `edit(file_path, old_string, new_string, replace_all?)` | `Edit(file_path, old_string, new_string, replace_all?)` | `edit(filePath, oldString, newString, replaceAll?)` | 字面字符串替换;默认要求唯一匹配;在默认 fs-policy 下必须先观测(任意窗口读取均算作观测)。 | 是 | + +schema 使用 snake_case 字段名(`file_path`、`old_string`、`new_string`、`replace_all`),与 Claude Code 及现有 DeepSeek Harness 工具 schema 示例保持一致。消费方包将这些面向模型的名称转换为 `ctx.fs` 调用和 `fs/*` 事件分发。 + +## 工具 schema + +### `read` + +`read` 检视一个 UTF-8 文本文件并返回带行号的内容。 + +参数: + +- `file_path: string`——必填。要读取的路径,由 `ctx.fs` 解析。 +- `offset?: number`——可选。返回的第一行,从 1 开始。默认为第一行。 +- `limit?: number`——可选。返回的最大行数。默认值与上限是 `dsh-tool-fs` / `ctx.fs` 的实现细节。 + +首次实现不涉及的内容: + +- 无 PDF `pages` 参数。 +- 无图片或多模态文件读取。 +- 不通过 `read` 列出目录;如有需要,目录列表将作为单独的后续工具。 + +### `write` + +`write` 创建或完整替换一个 UTF-8 文本文件。 + +参数: + +- `file_path: string`——必填。要写入的路径,由 `ctx.fs` 解析。 +- `content: string`——必填。要写入的完整 UTF-8 文本内容。 + +在默认 fs-policy 下,使用 `write` 更新已有文件需要同一执行上下文先前对该文件有过一次观测(read/write/edit);`dsh-fs-policy` 插件将观测到的版本作为 `fs/write-intent` 上的 stale guard 提供。创建新文件不需要先前观测。如果策略插件不存在,`write` 是无条件的裸提供方 create-or-overwrite。 + +schema 不将 `expected_hash`、`expected_version` 或 `create_only` 作为面向模型的参数暴露。陈旧版本检查由后端产生的版本和策略插件的观测状态驱动,而非要求模型通过 schema 复制版本令牌。 + +### `edit` + +`edit` 通过替换字面文本来更新已有的 UTF-8 文本文件。 + +参数: + +- `file_path: string`——必填。要编辑的路径,由 `ctx.fs` 解析。 +- `old_string: string`——必填。要替换的字面文本。首次实现中空字符串无效。 +- `new_string: string`——必填。字面替换文本;空字符串表示删除匹配内容。 +- `replace_all?: boolean`——可选。默认为 false。为 false 时,`old_string` 必须恰好匹配一处。 + +`edit` 要求同一执行上下文先前对该文件有过一次观测(任何窗口化的 read 都算——授权基于版本新鲜度,而非全文查看要求),或该上下文先前对该文件做过 write/edit。`dsh-fs-policy` 策略插件推导所有者并将记录的版本作为 stale guard 提供;提供方的 mutation lock 负责执行。 + +首次实现拒绝 Codex 风格的 patch 语法和多模式 edit API。它使用一种严格的字面替换模式,使面向模型的契约保持简单,并让后端掌控精确匹配、重复匹配、行尾和陈旧版本的语义。 + +## 结果形状 + +首次实现曾将 `ContentBlock[]` 格式化逻辑放在 `execute` 中。[规范工具输出契约](../architecture/2026-07-20-canonical-tool-output-contract.md)如今将 `ctx.fs` 的结果事实保留为工具经校验的值,并通过 `output.render` 派生相同的模型文本;文件状态的记录/刷新仍归 `ctx.fs` 所有。 + +默认原生投影: + +| 工具 | `tool-fs` 使用的结构化 `ctx.fs` 结果 | 默认模型投影 | +|---|---|---| +| `read` | 返回的行、返回行数、总行数、目标显示路径、文件版本、部分视图标记 | 带行号的文本及分页页脚 | +| `write` | 创建/更新操作、目标显示路径、新文件版本 | 简洁的创建/更新成功文本 | +| `edit` | 替换次数、全量替换标记、目标显示路径、新文件版本 | 简洁的编辑成功文本 | + +结构化结果不会重复模型参数(如 `file_path`、`old_string` 或 `content`),除非后端已将其解析为新信息(如 `displayPath`、`targetKey` 或新版本)。面向 token 的截断属于模型投影的职责,而非后端规范结果的一部分。 + +## 延后事项 + +以下内容被明确排除在首次文件系统 schema 实现之外: + +- 面向模型的 `expected_hash`、`expected_version` 或 `create_only` 参数。 +- 目录列表、glob、grep 和搜索工具。 +- 二进制安全的读/写操作。 +- PDF/图片/多模态 `read`。 +- 文件系统工具的 Code Mode 投影值。 +- 规范的 edit diff 格式。 + +## 测试 + +schema 测试固定每个工具的必填/可选参数集、空 `old_string` 拒绝、`replace_all` 默认值、snake_case 字段名、描述文字中对观测策略的说明,以及根插件套件注册;集成测试通过 `ctx.tools.execute()` 对真实的 `dsh-fs-local` 提供方执行全部三个工具,并验证模型参数被正确转换为预期的 `ctx.fs` 调用和 `fs/*` 分发。 + +## 曾考虑的替代方案 + +- **Codex 风格的 patch 语法或多模式 edit API**:否决。一种严格的字面替换模式使面向模型的契约保持简单,并让后端掌控精确匹配、重复匹配、行尾和陈旧版本的语义。 +- **camelCase 参数名(OpenCode 风格)**:snake_case 与 Claude Code 及现有 harness 工具 schema 示例一致,且命名一旦发布即成为公开接口。 +- **面向模型的 `expected_hash` / `expected_version` / `create_only` 参数**:否决。陈旧检查由后端产生的版本和策略插件的观测状态驱动,从不依赖模型复制的脆弱令牌。 + +## 后果 + +**首版 schema 有意小于 Claude Code 的。** 去掉 PDF pages、多模态 read、丰富的 grep/list flag 和 expected hash 字段使实现保持聚焦,但用户可能很快就会提出这些需求。它们将以独立 Agent Note 或聚焦的后续工作形式到来,而非对初始 schema 的重载。 + +**v1 中没有显式的面向模型的 stale guard。** schema 不要求模型提供 expected hash/version。这是有意为之:陈旧检查来自后端产生的版本和 `dsh-fs-policy` 插件的观测状态,而非模型复制的脆弱令牌。文件系统安全失败通过 `dsh-fs` 拥有的结构化 `FsError` 代码浮现,而非模型提供的版本字段。 + +**命名成为公开接口。** 一旦发布,将 `file_path` 改为 `filePath` 或 `old_string` 改为 `oldString` 会搅动提示词、示例和下游客户端。本 Agent Note 预先选择 snake_case,并将其视为稳定的面向模型的契约。 diff --git a/.agents/notes/implemented/feature/2026-06-18-acp-terminal-and-tool-rendering.i18n.yaml b/.agents/notes/implemented/feature/2026-06-18-acp-terminal-and-tool-rendering.i18n.yaml new file mode 100644 index 0000000000..0852385897 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-06-18-acp-terminal-and-tool-rendering.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-18-acp-terminal-and-tool-rendering.md: 166e52f8e659a78b1347279c61956ca1001e4939 +2026-06-18-acp-terminal-and-tool-rendering.zh.md: 1623c8f51f9a1e0aacf374d182ab1c74dfa407cc diff --git a/.agents/notes/implemented/feature/2026-06-18-acp-terminal-and-tool-rendering.md b/.agents/notes/implemented/feature/2026-06-18-acp-terminal-and-tool-rendering.md index 8d9c0197eb..166e52f8e6 100644 --- a/.agents/notes/implemented/feature/2026-06-18-acp-terminal-and-tool-rendering.md +++ b/.agents/notes/implemented/feature/2026-06-18-acp-terminal-and-tool-rendering.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-06-18-acp-terminal-and-tool-rendering.zh.md) + ## Problem The ACP bridge lets each tool own its call rendering via `presentCall`/`presentResult` (see [tool-call UI presentation](2026-06-14-acp-agent-client-protocol.md) and `packages/core/tools`). For `bash` we surface the exact command as the `tool_call` title, the model's `description` as a content text block, `kind: 'execute'`, and the completed output wrapped in a fenced ` ```console ` text block. diff --git a/.agents/notes/implemented/feature/2026-06-18-acp-terminal-and-tool-rendering.zh.md b/.agents/notes/implemented/feature/2026-06-18-acp-terminal-and-tool-rendering.zh.md new file mode 100644 index 0000000000..1623c8f51f --- /dev/null +++ b/.agents/notes/implemented/feature/2026-06-18-acp-terminal-and-tool-rendering.zh.md @@ -0,0 +1,48 @@ +# Agent Note: 富 ACP bash 渲染——通过 `_meta` 约定实现终端卡片 + +Status: implemented + +[English](2026-06-18-acp-terminal-and-tool-rendering.md) | 中文 + +## 问题 + +ACP(Agent Client Protocol)桥接层允许每个工具通过 `presentCall`/`presentResult` 自行控制调用渲染(见[工具调用 UI 呈现](2026-06-14-acp-agent-client-protocol.md)与 `packages/core/tools`)。对于 `bash`,我们将确切命令作为 `tool_call` 标题呈现,模型的 `description` 作为一个内容文本块,`kind: 'execute'`,完成后的输出包裹在 ` ```console ` 围栏文本块中。 + +参考编辑器将终端元数据渲染为一张专用卡片,包含 cwd、命令、实时风格的输出和退出状态;纯文本则丢失了这些结构。命令之所以作为标题,是因为执行卡片隐藏原始输入,而人类可读的描述保留为卡片上方的独立块。 + +## 关键发现:agent 执行的终端使用 `_meta` 约定,而非 `terminal/create` + +ACP 规范有一个*客户端侧*终端子协议:agent(智能体)调用客户端的 `terminal/create`(传入 `{ command, args, cwd, env }`),由**编辑器**执行进程,然后 agent 读取 `terminal/output` / `wait_for_exit`。这个模型不适合我们:我们的 harness 通过 `dsh-bash` 自行执行 bash(沙箱化的环境清理、后台任务所有权、按会话的 cwd)。将执行路由到编辑器会绕过所有这些机制,并将执行分叉到两个后端。 + +研究两个参考 agent(2026-06-18)发现,二者都没有为自己的 shell 工具使用 `terminal/create`——**两者都保持 agent 侧执行,并发出一套 `_meta` 约定**,由 Zed 特殊处理: + +- **`claude-agent-acp`**(`tools.ts`、`acp-agent.ts`):以 `clientCapabilities._meta.terminal_output` 为门控。`tool_call` 携带 `content: [{ type: 'terminal', terminalId }]` 与 `_meta.terminal_info.{ terminal_id, cwd }`;输出和退出通过 `tool_call_update` 的 `_meta.terminal_output.{ terminal_id, data }` 与 `_meta.terminal_exit.{ terminal_id, exit_code, signal }` 到达。 +- **`codex-acp`**(`CodexToolCallMapper.ts`、`TerminalOutputMode.ts`):调用上同样携带 `terminal_info`;输出通过 `_meta.terminal_output`(完整)或 `_meta.terminal_output_delta`(增量),由同一个 `_meta.terminal_output` 能力选择。 + +Zed 侧(`crates/agent_servers/src/acp.rs`,已验证):收到 `ToolCall` 且其 `_meta.terminal_info.terminal_id` 已设置时,注册一个**仅展示**的终端(header = `terminal_info.cwd`,label = `tool_call.title`);收到 `ToolCallUpdate` 时,`_meta.terminal_output.data` 写入该终端,`_meta.terminal_exit.{exit_code,signal}` 设置状态。客户端通过 `clientCapabilities._meta.terminal_output = true` 声明此能力。`_meta` 本身是 ACP 规范认可的扩展点(在 `ToolCall`/`ToolCallUpdate` 上类型为 `{[k]: unknown} | null`);这里的*具体键*(`terminal_info`/`terminal_output`/`terminal_exit`)是 Zed 约定,不属于 ACP 规范,但它们是 Zed 集成的事实契约,也是在保持 agent 侧执行的前提下获得终端卡片的唯一方式。 + +## 决策 + +保持 `dsh-bash` 的 agent 侧执行;通过 `_meta` 约定渲染终端卡片,以能力声明为门控,以 ` ```console ` 文本块作为保底回退。 + +1. **能力声明。** `initialize` 读取 `clientCapabilities._meta.terminal_output`,桥接层按连接记住它。 +2. **提供方无关的展示词汇。** `dsh-tools` 新增一种终端形态的展示结构,工具可返回它——提供方无关(`cwd`、输出 `data`、`exitCode`/`signal`),不含 ACP 类型。`dsh-tool-bash` 为 `bash` 返回该结构(cwd 来自解析后的工作目录;输出与退出从运行结果解析)。 +3. **桥接映射。** 当客户端声明了该能力时,桥接层将展示结构映射为:在 `tool_call` 上,`content:[…, {type:'terminal', terminalId}]`(工具的任何 `content`,如描述,渲染在终端块之前)+ `_meta.terminal_info.{terminal_id,cwd}`;在 `tool_call_update` 上,`_meta.terminal_output.{terminal_id,data}`(捕获的输出)+ `_meta.terminal_exit.{terminal_id, exit_code|signal}`(解析后的退出),且 update 的文本 `content` 被省略(ACP 的 `tool_call_update.content` 会替换调用的 content 集合,因此重新发送围栏块会覆盖终端内容块)。`terminalId` 由 harness 的 `callId` 派生(稳定、每次调用唯一)。当能力未声明时,桥接层在调用上发送描述内容块,在 update 上发送既有的 ` ```console ` 文本内容——行为不变。 +4. **退出信息从渲染输出中解析;无新执行路径,无实时流式传输。** 输出在完成时附加(来自 agent 自身的 `tool/result`),不逐 token 流式传输。退出状态(`_meta.terminal_exit.{exit_code,signal}`)确实会发出:纯 `presentResult(args, result)` seam 只能看到内容块,因此 `dsh-tool-bash` 通过解析 `renderResult` 追加的状态标记(`[exit code: N]` / `[killed by signal: …]`)来恢复结构化退出信息——解析是标记发出的精确逆操作,二者在同一文件中共同演进,一个往返测试守护这对关系。资源释放不受影响:无需新增拆除逻辑,因为桥接层从未创建客户端侧终端。 + +## 曾考虑的替代方案 + +- **ACP 客户端侧终端子协议(`terminal/create`)**:明确否决。编辑器将执行进程,绕过 `dsh-bash` 的环境清理、后台任务所有权和按会话的 cwd,并将执行分叉到两个后端。两个参考 agent 以同样的方式否决了它(见上述关键发现);agent 侧执行加 `_meta` 约定是在保持 harness 执行策略的同时获得终端卡片的唯一形态。 +- **通过事件 schema 传递结构化退出信息**:否决,改用标记往返方案。纯 `presentResult(args, result)` seam 只能看到内容块,而解析是标记发出的精确逆操作,二者在同一文件中共同演进,由往返测试守护。 + +## 后果 + +- **Zed 约定的 `_meta` 键。** 终端卡片依赖 Zed 特有的键(`terminal_info`/`terminal_output`/`terminal_exit`),位于 ACP 规范认可的 `_meta` 扩展点内,而非 ACP 终端子协议。不识别这些键的客户端仍然获得文本回退(能力门控确保我们仅在客户端通过 `_meta.terminal_output` 声明支持时才发出这些键),因此非 Zed 客户端不会变差。如果 ACP 日后标准化了 agent 执行的终端,则迁移到该标准并移除约定键。 +- **能力诚实。** 仅在客户端声明了 `_meta.terminal_output` 时才发出终端元数据;文本回退是对其他所有客户端的契约,绝不可退化。由一个无能力测试覆盖,断言 ` ```console ` 路径。 +- **terminalId 冲突。** 从每次调用的 `callId` 派生,保证在会话内唯一且在 call/result 对之间稳定;绝不跨调用复用。 +- **退出信息从渲染文本解析。** 退出信息通过解析 `renderResult` 的状态标记恢复 `exit_code`/`signal`,而非通过事件 schema 传递结构化退出(纯 `presentResult` seam 看不到后者)。解析是标记发出的精确逆操作,且位于同一文件中;往返测试固定了这对关系,标记格式变更若破坏解析则测试套件失败。如果标记格式日后需要与退出信息分道扬镳,则改为在 result 事件上暴露结构化退出。 +- **提供方无关词汇的蔓延。** 终端展示结构扩大了 `dsh-tools` 的接口面;保持其中立性(不让 ACP 类型泄漏到 `dsh-tools`),且只提供第二个 UI 消费方同样需要的丰富度。 + +## 超出范围 / 非目标 + +文本块基线仍为无能力声明时的默认行为。以下两项后续工作有意不在此处构建,各自需要单独的 Agent Note:**实时增量流式传输**(在分片到达时发出 `_meta.terminal_output_delta`,需要在 `dsh-bash` 上新增增量输出 seam);**命令分类**(将 `cat`/`sed` 解析为带文件位置的 `read` 卡片,将 `grep` 解析为 `search`,回退到终端卡片——仅展示,绝不改变实际执行内容)。 diff --git a/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.i18n.yaml b/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.i18n.yaml new file mode 100644 index 0000000000..7998dc3257 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-18-compaction-capability-seam.md: a263b5e7d0245bd1279024a50e05b2f33edad521 +2026-06-18-compaction-capability-seam.zh.md: df0cf9d9131978e608d47124ba0f0db0343ee12a diff --git a/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.md b/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.md index f5beab3eb4..a263b5e7d0 100644 --- a/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.md +++ b/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-06-18-compaction-capability-seam.zh.md) + ## Problem A long-running agent conversation grows without bound. As the event log accumulates turns, the derived message history eventually approaches the model's context window — the model then truncates mid-response (`max-tokens`) or degrades. **Compaction** is the mitigation: replace a run of older history with a concise summary, keeping recent context intact. diff --git a/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.zh.md b/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.zh.md new file mode 100644 index 0000000000..df0cf9d913 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.zh.md @@ -0,0 +1,132 @@ +# Agent Note: 压缩作为能力 seam(抽象契约 + 基础后端) + +Status: implemented + +[English](2026-06-18-compaction-capability-seam.md) | 中文 + +## 问题 + +长时间运行的 agent(智能体)对话会无限增长。随着事件日志不断累积轮次,派生出的消息历史最终逼近模型的上下文窗口,模型随即截断响应(`max-tokens`)或性能退化。**上下文压缩(context compaction)** 是对此的缓解手段:用一段简洁的摘要替换一批较早的历史,保持近期上下文完整。 + +[会话接口面](../architecture/2026-06-18-session-surface.md)正是为此而构建的基础设施:一份建立在事件日志之上的有序投影,带有专门设计的 `surfaceOp: { op: 'replace', start, end }` 操作,用于遮蔽一段条目并插入替换内容,`sourceEventSeqs` 记录溯源信息以便决策可确定性地回放。剩下的是那个*决定压缩什么、并产出摘要*的插件。 + +两股力量塑造了设计。第一,压缩策略与可复用的 token 测量独立变化:测量归 LLM 系列的 [`ctx.tokenMeter` 服务](../architecture/2026-07-15-replay-token-meter-service.md)所有,摘要生成则可以使用模型调用、模板或远程服务。第二,`SurfaceEventType` 封闭为五种事件类型(`user/message`、`assistant/message`、`tool/result`、`context/message`、`steering/message`);只有这些类型可以携带 `surfaceOp`。因此一个专用的 `compaction/*` 事件**不能**出现在 surface 上,编译器与 Session 始终启用的 append/seed 边界都会拒绝在其上附加 `surfaceOp`。 + +## 决策 + +### 压缩是一个能力 seam,接口与实现分离 + +遵循[能力 seam Agent Note(agent 决策记录)](../architecture/2026-06-13-capability-seams.md),压缩以独立包(package)发布,使契约、算法和(后续的)消费方 surface 各自独立演进: + +1. **接口** — `@deepseek-ai/dsh-compact`:抽象 `CompactService`,拥有 `ctx.compact` 键、`CompactionResult` 词汇、`compact/*` 会话事件以及规范的检查点消息来源。它将 `compactIfNeeded()` 和 `compactRegion()` 声明为**抽象方法**——契约说明压缩*做什么*,而非*怎么做*。 +2. **实现** — `@deepseek-ai/dsh-compact-basic`:具体的 `BasicCompactService`,消费 `ctx.tokenMeter`,并拥有尾→头保留遍历、通过 `ctx.llm.stream()` 生成摘要、surface 替换、锁、步骤后压力处理和规范的上下文溢出恢复。`summarize()` 是其唯一的子类钩子;计价与回放仍归 meter 所有。 +3. **无模型配套服务** — `@deepseek-ai/dsh-compact-tool-result-prune`:一个具体的可选服务,在后端选择摘要范围之前,重写当前过大的 `tool/result` 节点。它不是第二种压缩实现,也不实现 `CompactService`。 +4. **消费方** — 推迟。一个 `/compact` 工具和斜杠命令将 `inject: ['compact']` 并调用契约;它们被有意排除在本 Agent Note 范围之外,以便 seam 先稳定下来。 + +### 契约依赖 `dsh-session` 和 `dsh-llm`——有意为之的偏离 + +能力 seam Agent Note 规定接口包「仅依赖 cordis」(对 `dsh-bash` 成立,因为其词汇是自包含的)。压缩**无法**遵守这一点:它的动词作用于 agent 所有的 `Session`(`compactRegion(start, end, agent)`),其输出使用内容词汇(`CompactionResult.summary: ContentBlock[]`)。不引用 `Session`/`SessionEvent`(来自 `dsh-session`)和 `ContentBlock`(来自 `dsh-llm`),契约就无法表达。 + +这不是耦合异味,而是契约的领域所在。「仅 cordis」的指导原则一直是「接口仅依赖契约真正需要命名的东西,绝不依赖实现」的简写。`dsh-session` 和 `dsh-llm` 本身是接口/词汇包,不是实现;`dsh-compact` 仍然不导入任何后端。seam 的真正不变式——*消费方和实现在抽象服务背后独立演进*——完好无损。 + +### 抽象 `compactIfNeeded` / `compactRegion`,算法在后端 + +早期草案将完整算法(保留遍历、token 求和、文本提取)作为接口上的具体方法。这会将契约重新耦合到一种策略:想要不同保留策略或事件排序的后端必须与继承来的具体代码对抗。将两个核心方法都设为抽象,把所有*怎么做*的决策放在后端,并让接口保持为*做什么*的声明。token 测量根本不是压缩钩子;单例服务使多个消费方能够共享逐会话的回放折叠。 + +`compactIfNeeded(agent, trigger, signal)` 接受显式的 `'pressure' | 'context-overflow'` 触发原因与取消信号。它只读取最新的持久化已路由请求;没有 header 就不执行工作,任何已路由的提供方/模型目标都使用单例估算器。`compactRegion(start, end, agent, signal?)` 将 `agent.session` 作为唯一会话身份,并为手动调用方保留可选 signal。默认摘要器依次从显式配置、最新记录的已路由目标和 agent 选项解析目标,并在任何 `llm/stream` 路由后记录提供方/模型对。它回放已路由请求的前缀,并将压缩指令追加为尾部 user 消息,从而复用提供方的热 KV cache;见[摘要前缀缓存 Agent Note](../bug-fix/2026-07-21-compaction-summary-prefix-cache-reuse.md)。该调用将提供方无关的 `GenerateOptions.purpose` 设为 `compaction`;适配器可以将此用途映射为对模型隐藏的传输元数据,DeepSeek 适配器会发送 `x-deepseek-harness-compact: 1`。 + +### 成功的持久步骤工作完成后运行自动压力检查 + +成功调用的压力检查不能在步骤前运行,因为最终的 `agent/request` 路由、提供方输出、工具结果、缓冲上下文与 steering 当时尚不存在。串行的 `agent/post-step(agent, turn, step, signal)` 会在这些事实持久化后、`step/end` 之前触发。`dsh-compact-basic` 通过 `ctx.tokenMeter` 测量规范的已记录请求,因此下一个请求无需推测性覆盖信封即可看到任何替换。压力达到条件后,可选的 `ctx.toolResultPrune` 重写在摘要范围选择前运行;compact-basic 重新测量持久 surface,如果修剪恢复到安全压力便跳过摘要生成。 + +规范的提供方上下文溢出走另一条路径。失败步骤先关闭,`agent/request-error` 接收原始请求错误与连续重试次数,compact-basic 在强制执行一次有效且平衡的缩减前先修剪。仅当 `session.surface.replaceGeneration` 增加时,它才返回 retry;这包括没有摘要范围时仅修剪取得的进展。随后循环开启新的编号步骤,并从持久日志重建请求。没有替换、任何替换前的恢复失败、取消、耗尽的上限或无关错误都会保留原始提供方失败。如果修剪已经推进 generation,而后续摘要工作失败,恢复会从该持久的已修剪 surface 重试,除非取消或资源释放胜出。完整生命周期决策见[调用后恢复 Agent Note](../architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md)。 + +``` +assistant/message → tool/result/context/steering +await serial agent/post-step ⟵ pressure compaction inside the successful step +step/end + +provider overflow → step/end +await waterfall agent/request-error ⟵ forced compaction between attempts +retry → next numbered step/start ⟵ derives from the replacement surface +``` + +### 保留是轮次无关的;工具配对平衡是唯一的结构守卫 + +自动压缩在**每个成功的**步骤之后检查,而非每轮一次。这对失控轮次存活至关重要:工具密集型的 ReAct 轮次每步追加一个 `assistant/message` + 一个 `tool/result`,因此 surface 会在一轮之内增长。步骤后检查可以在后续步骤开启前压缩早期已关闭的工具对;如果请求率先越过限制,由提供方确认的溢出仍是兜底机制。 + +`compactIfNeeded` 保留估算大小达到解析后保留 token 预算的最小完整 surface 单元尾部,压缩更早的节点。一个单元是一个完整的已关闭步骤或一条无步骤消息。如果 token 截断点落在步骤内部,保留范围会扩展直到切割点满足工具配对平衡。平衡按 surface 顺序检查,而非日志序号,因为替换摘要在旧的 surface 位置拥有新的序号。`dsh-compact` 导出前后边缘辅助函数;只要 `replaceGeneration` 不变,其逐会话缓存就只折叠新增的 surface 尾部节点,面对仅日志增长时不读取事件,并在替换后重建当前成员关系与平衡。`compactRegion` 拒绝将工具调用与其结果拆分的边界。进行中的轮次不享受特殊保留。 + +因此失控轮次的压缩方式与其他历史完全相同:其早期*已关闭*步骤被摘要,近期步骤保持原样。当唯一可压缩的内容只剩一个不可拆分的开放尾部步骤(其工具调用尚无结果)时,压缩拒绝执行(返回 `null`)并在该步骤关闭后重试。 + +**部分单单元溢出仍不在范围内。** 摘要范围选择无法拆分不可分割的单元。当可移除的文本型工具结果内容占据大部分空间,且修剪后的余量能够容纳时,可选修剪器可以修复一个已关闭的工具对。仅信封压力、粘贴的 `user/message` 等不可分割的超大非工具节点,以及不可修剪余量仍然过大的工具单元,依旧不属于压缩范围;限制这些单元是另一个关注点。 + +### 头部锚定:一个自动检查点,始终在头部 + +自动压缩始终从 surface 头部开始,将先前的检查点与新压缩的历史合并,因此只保留一个自动检查点。`shadowedRange` 因此是位置性的而非数值序号区间:一个较新的摘要序号可能占据较旧的 surface 位置。`shadowedSeqs` 记录权威的 surface 顺序。手动的中间范围压缩可能留下多个检查点。 + +### 近似收敛不变式 + +`resolveConfig` 提供可用默认值:阈值比例 `0.8`、保留尾部比例 `0.16`、空的摘要提供方/模型覆盖、`maxTokens: 8192`、`compactionRetries: 1`、`maxOverflowRetries: 1` 以及 `auto: true`。可选的精确提供方/模型策略会部分覆盖顶层默认值;压力根据拥有该路由的 LLM 适配器所报告容量缩放比例,而 `retainTokens` 可以替代按比例保留。保留量必须低于最终阈值。收敛仍然是动态的,因为提供方输出上限可能被隐藏或显式的推理 token 消耗,摘要大小也不可预测。如果压力仍高于阈值,`compactIfNeeded()` 会按配置的重试次数再次压缩头部检查点,但每次提交的摘要必须小于其遮蔽的内容。溢出不需要容量元数据,并会绕过阈值和保留尾部策略,执行一次最大且平衡的头部缩减,留下最新的不可分割单元。所有权划分由[已路由模型上下文与压缩策略 Agent Note](../architecture/2026-07-20-routed-model-context-and-compaction-policy.md)规定。 + +### Surface 替换:`compact/*` 事件仅存在于日志;一条 `user/message` 承载摘要 + +由于 `SurfaceEventType` 是封闭的,摘要不能搭载在 `compact/*` 事件上。后端改为追加一条**单独的 `user/message`**,带有 `source: COMPACT_CHECKPOINT_SOURCE` 和 `surfaceOp: { op: 'replace', start, end }`;其 `content` 是(带框架的)摘要,`sourceEventSeqs` 覆盖被遮蔽的条目*和*簿记事件。接口导出该来源和 `isCompactCheckpointSource()`,使消费方无需依赖后端包身份,即可识别持久化或克隆得到的检查点。`compact/*` 事件是纯日志记录(锁 + 溯源信息)。surface 变更位于锁**内部**,`compact/end` 是最后追加的事件: + +``` +compact/start → log-only. Acquires the lock. +[summarize older range via the backend] +compact/summary → log-only. Provenance: raw summary, range, shadowed seqs, token count. +user/message → canonical checkpoint source + surfaceOp { op:'replace', start, end }. + THE surface mutation (framed summary). + deriveMessages() renders it as a user-role message. +compact/end → log-only. Releases the lock (carries `error` on a recoverable failure). +``` + +`deriveMessages()` 随后产出 `[summary_as_user_message, ...retained_entries]`。复用 `user/message` 是诚实的而非变通:摘要确实*是* user 角色的上下文。 + +### 检查点框架 + 增量合并(后端私有) + +基础后端将摘要包装为已建立的检查点上下文,并标记以便下一轮增量合并。原始摘要保留在 `compact/summary` 上。框架是后端策略;seam 承诺由一条替换 user 消息承载可能带框架的摘要,并使用规范的检查点来源。 + +### 通过日志记录的锁实现阻塞,加上崩溃/可恢复失败的分类 + +`compact/start … compact/end` 括号的存在理由,按当前实际承担的职责排序: + +1. **可检测的崩溃孤儿 + 来源追溯**(首要)。摘要生成是一次慢速模型调用,持久化在 `compact/start` *之后*。摘要生成中途崩溃会留下一个没有匹配 `compact/end` 的 `compact/start`——一个可检测的孤儿。最后释放锁(而非最先)将崩溃窗口从*静默损坏*转变为可检测的孤儿。 +2. **防止并发压缩。** 如果当前轮次持有未匹配的 `compact/start`,`compactRegion` 拒绝启动。(循环在任一 awaited 自动 seam 上都是单线程的,因此这也是重入绊线——抛出「already in progress」表示真正的 bug。) + +该锁只排除另一项压缩,不排除无关的仅日志事实。基础后端会在 `compact/start` 之后对 token meter 的 surface 节点取快照,并在异步摘要后再次比较;任何 surface 变更都会使替换前的检查失败,而标题或其他仅日志追加不会使已选范围失效。 + +两种失败路径,均有文档记录: + +- **崩溃**(循环在摘要生成中途死亡):悬空的 `compact/start`,无关闭事件。由于 `compact/*` 是**仅日志**事件,孤儿是**惰性的**,不会落地摘要替换。派生 surface 保持为 `compact/start` 时已经持久化的 surface:如果修剪未产生替换,就是完整历史;如果已经修剪,就是已修剪历史。通用轮次修复(`interruptedTurnClosers`)用合成的 `turn/end` 关闭轮次;孤儿位于该 `turn/end` *之前*,因此轮次范围内的进行中检查永远看不到它,崩溃不会卡住未来的压缩。 +- **可恢复**(摘要生成抛出异常但循环存活):后端追加设置了 **`error`** 字段的 `compact/end`,但不落地摘要替换。步骤后压力处理发出警告,并从最新的持久 surface 继续:如果尝试前没有替换,就是完整历史;如果修剪已经落地,就是已修剪 surface。溢出恢复只会在没有任何替换前委托;先前修剪带来的 generation 进展允许从该持久 surface 重试,除非取消或资源释放胜出。 + +`compact/end` 保留其 `error?` 字段(与 `tool/result` 的自包含错误一致——一个事件即可区分成功与失败,无需关联兄弟事件)。没有单独的 `compact/error` 事件。 + +**核心会话修复保持对压缩无感知——这是有意为之。** `interruptedTurnClosers` 从不被教导 `compact/*`。如果教导它,每个未来的 `xxx/start … xxx/end` 插件对都必须修补核心模块——这恰好是能力 seam 架构存在的意义所要避免的耦合。由于仅日志的孤儿是惰性的,不需要特殊修复:通用轮次修复加上未落地 surface 变更的惰性就足够了。 + +## 曾考虑的替代方案 + +- **完整算法作为接口的具体方法**——否决,因为它将契约重新耦合到一种保留策略。两个核心方法都是抽象的;可复用测量属于单独的 LLM 系列服务,`summarize()` 是 basic 唯一的钩子。 +- **在 `agent/request` 或临时 `agent/pre-step` 输入上执行压缩**——否决,因为两者都无法证明最终的持久请求,而且都会将通用生命周期耦合到压缩专属的信封数据。步骤后回放与规范溢出恢复同时覆盖成功和被拒绝的调用。 +- **`compact` 布尔值或无类型的请求元数据 map**——否决,因为多个辅助调用种类会变成互斥标志,而开放 map 会丢弃由编译器检查的词汇。一个类型化的 `purpose` 判别字段可以扩展其他调用种类,而无需再为 `GenerateOptions` 添加字段。 +- **单独的 `compact/error` 事件**——否决:`compact/end` 保留 `error?` 字段,与 `tool/result` 的自包含错误一致——一个事件即可区分成功与失败,无需关联兄弟事件。 +- **教导核心轮次修复识别 `compact/*`**——否决:仅日志的孤儿是惰性的,为每个未来的 `xxx/start … xxx/end` 插件对修补核心模块恰好是能力 seam 架构存在的意义所要避免的耦合。 + +## 后果 + +- **包**:`packages/compact/compact` 提供接口,`compact-basic` 提供后端,`compact-tool-result-prune` 提供可选的确定性重写。`packages/llm/token-meter` 独立拥有回放感知的测量。消费方层推迟。 +- **自动 seam**:`agent/post-step`(`@mode serial`)处理成功调用的压力,`agent/request-error`(`@mode waterfall`)处理失败步骤关闭后的最终请求失败。通用 `agent/pre-step` 保持为四参数检查点,不携带压缩专属的提示词/前缀 payload。 +- **`SessionEventMap`** 通过可合并扩展的声明合并获得 `compact/start` / `compact/summary` / `compact/end`;`SurfaceEventType` **未被**触及。这些是会话事件,不是 cordis `Events`,因此事件分类门禁无需新增条目。 +- **`dsh-compact`** 拥有 `COMPACT_CHECKPOINT_SOURCE`、`isCompactCheckpointSource(source)`、`toolPairingBalancedBefore(session, seq)` 与 `toolPairingBalancedAfter(session, seq)`。该标记用于跨后端实现识别替换摘要。带缓存的 surface 边缘检查会防止 `compactRegion` 和 `compactIfNeeded` 拆分工具调用/结果对,按 seq 校验当前成员关系,从每个切割点的一条平衡序列回答两侧边缘,并拒绝陈旧或缺失的 seq 与孤立结果。 +- **`dsh-session`** 通过唯一的 surface 管理器校验位置替换、完整溯源信息和仅内容的单节点 `tool/result` 重写。其不变式配套插件将新追加的工具结果视为执行,要求存在已打开的步骤与待处理调用;已校验的替换仍是位于轮次内的重写。 +- **接线**:`examples/tui-agent/cordis.yml` 依次加载零配置的 `dsh-token-meter`、`dsh-compact-tool-result-prune` 和 `dsh-compact-basic`;服务级默认值使组合无需重复数值策略即可使用。 + +## 测试 + +- **单元测试:** 使用真实 Loader 和 invariant 插件覆盖完整单元保留、修剪配置与回放、富块顺序、元数据保留、收敛、`compact/end` 的两种结果、开放尾部拒绝、仅修剪与带摘要的溢出恢复、generation 证明、上限和原始错误保留。 +- **循环测试:** 测试固定步骤后处理发生在持久工具结果之后、`step/end` 之前,使用实际 `agent/request` 路由,关闭失败步骤,分配新的重试编号,并覆盖完整的抛出/带内溢出 → 压缩 → 重建重试组合。 +- **带密钥 e2e:** 真实模型和 bash 会话在降低的限制下触发压缩,记录完整的 `compact/start…end` 对,缩小 surface,并完成任务。 +- **快照缺口:** 失控轮次压缩尚无法回放,因为摘要调用未记录 `assistant/chunk` 事件或 `sessionId`;交错摘要调用的回放仍是后续工作。 diff --git a/.agents/notes/implemented/feature/2026-06-21-subagent-capability-seam.i18n.yaml b/.agents/notes/implemented/feature/2026-06-21-subagent-capability-seam.i18n.yaml new file mode 100644 index 0000000000..3d1140f5cf --- /dev/null +++ b/.agents/notes/implemented/feature/2026-06-21-subagent-capability-seam.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-21-subagent-capability-seam.md: 9c17a93751de209e5e4e5a0ca7d7b1d8e5656a47 +2026-06-21-subagent-capability-seam.zh.md: 6294c84a8fa11e492316f4b69048aa5f477aa04f diff --git a/.agents/notes/implemented/feature/2026-06-21-subagent-capability-seam.md b/.agents/notes/implemented/feature/2026-06-21-subagent-capability-seam.md index 3ed2090b22..9c17a93751 100644 --- a/.agents/notes/implemented/feature/2026-06-21-subagent-capability-seam.md +++ b/.agents/notes/implemented/feature/2026-06-21-subagent-capability-seam.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-06-21-subagent-capability-seam.zh.md) + > The full seam is shipped: the `dsh-subagent` interface and `dsh-tool-subagent` consumer; the two in-process backends (`dsh-subagent-spawn`, `dsh-subagent-fork`); the nested-agent snapshot infrastructure ([per-session snapshot replay](../testing/2026-06-22-subagent-snapshot-replay.md)); and the out-of-process `dsh-subagent-acp` backend ([its Agent Note](2026-06-22-acp-subagent-backend.md)). ## Problem diff --git a/.agents/notes/implemented/feature/2026-06-21-subagent-capability-seam.zh.md b/.agents/notes/implemented/feature/2026-06-21-subagent-capability-seam.zh.md new file mode 100644 index 0000000000..6294c84a8f --- /dev/null +++ b/.agents/notes/implemented/feature/2026-06-21-subagent-capability-seam.zh.md @@ -0,0 +1,73 @@ +# Agent Note: Subagent 能力 seam + +Status: implemented + +[English](2026-06-21-subagent-capability-seam.md) | 中文 + +> 完整 seam 已交付:`dsh-subagent` 接口与 `dsh-tool-subagent` 消费方;两个进程内后端(`dsh-subagent-spawn`、`dsh-subagent-fork`);嵌套 agent 快照基础设施([逐会话快照回放](../testing/2026-06-22-subagent-snapshot-replay.md));以及进程外后端 `dsh-subagent-acp`([其 Agent Note](2026-06-22-acp-subagent-backend.md))。 + +## 问题 + +harness 有一个长期搁置的 seam 用于 **subagent**:一个 agent(智能体)将工作委派给另一个 agent。这一意图在 `Agent`/`AgentLoop` 接口中已有草案([packages/core/agent/src/types.ts](../../../../packages/core/agent/src/types.ts)、[packages/core/agent-loop/src/index.ts](../../../../packages/core/agent-loop/src/index.ts)):一个创建选项引用父 agent(fork = 用父会话的事件日志初始化子会话;spawn = 全新会话),子 agent 以 `Agent` 句柄返回,使 steering(中途引导)和事件订阅可以统一工作。本 Agent Note 实现了这个 seam;上方横幅列出了已交付的内容。 + +决定整体设计走向的核心需求是:**多种 subagent 实现必须在运行时共存**。一个父 agent 可能在同一个会话中既需要一个廉价的进程内子 agent 处理有限范围的子任务,又需要一个隔离的进程外子 agent(通过 ACP(Agent Client Protocol))。我们预见的传输方式: + +- **进程内**:在同一个 `Context` 上创建一个具体的子 `Agent`(最廉价,且鉴于现有 agent 工厂几乎零成本); +- **ACP**:作为 ACP *客户端*驱动另一个 agent 进程(可以是自身的另一个实例); +- 后续:**A2A**、**Codex app-server** 与 **Claude Code Agent SDK**——每种都与 ACP 后端相同的进程外形状:「启动子 agent、发送提示词、流式接收更新、取消」。 + +## 曾考虑的替代方案 + +### 为何不采用 bash seam 的形状 + +bash seam([能力 seam](../architecture/2026-06-13-capability-seams.md))在每个上下文中只注册恰好一个 `BashExecutor`;加载第二个会抛异常。这对 bash 是正确的(一台机器、一种执行命令的方式),但对这里是错误的:共存才是需求。因此 subagent 服务是一个**命名提供方注册表**——每个实现以唯一名称注册,调用方按名称选择——镜像 **LLM(大语言模型)适配器注册表**(`LlmService.registerAdapter`),而非单服务的 bash 执行器。seam 仍然是由三个包构成的结构(接口 / 实现 / 消费方);只是「一个 vs. 多个实现」这个维度不同。 + +## 决策 + +### 由三个包构成的 seam + +新建包(package)组 `packages/subagent/`: + +| 包 | 角色 | +|---|---| +| `@deepseek-ai/dsh-subagent` | 接口:`SubagentService`(`ctx.subagents`)、`SubagentProvider`、`SubagentRun`、请求/结果/能力词汇、`subagent/*` 事件 | +| `@deepseek-ai/dsh-subagent-spawn` | 实现:通过 `ctx.agents.create` 创建全新的进程内子 agent | +| `@deepseek-ai/dsh-subagent-fork` | 实现:用父 agent 日志快照初始化的进程内子 agent | +| `@deepseek-ai/dsh-subagent-acp` | 实现:作为 ACP 客户端驱动已配置的子进程 | +| `@deepseek-ai/dsh-tool-subagent` | 消费方:基于 `ctx.subagents` 的面向模型的 `subagent` 工具 | + +### 原语:异步 `start → SubagentRun` + +提供方暴露 `start(request) → Promise<SubagentRun>`。完成时发布一个就绪的子 agent 并将其运行句柄转交给调用方。一个信号覆盖就绪前后的取消;`dispose()`(资源释放)取消剩余工作并等待完全停稳。启动失败时清理部分资源,不发出生命周期事件。`start` 与传输方式无关;`spawn` 仅指代全新的进程内后端。 + +### 两类可选能力,两种发现方式 + +- **启动时功能**(`outputSchema`、`depthLimit`、`toolFilter`、`persona`)挂在静态的 `provider.capabilities` 描述符上。服务在委派之前检查每个被请求的功能,如果提供方不支持则**大声拒绝**(`SubagentError('UNSUPPORTED_CAPABILITY')`),绝不接受后静默忽略。这些功能必须在 run 存在之前检查,因此不能是运行时方法。 +- **运行时功能**(通过 `sendMessage` 进行 steering、通过 `resume` 进行后续对话)是 `SubagentRun` 上的**可选方法**。方法的存在本身即为能力,TypeScript 类型收窄即为发现机制:消费方不经收窄就无法调用不存在的方法,因此不存在静默降级路径,也不需要额外的 flags 对象来保持同步。 + +### Fork 与 fresh 是独立后端,而非一个 flag + +全新子 agent 与 fork 子 agent 是独立的提供方,而非请求中的一个 flag。`dsh-subagent-spawn` 启动隔离的子 agent;`dsh-subagent-fork` 用一个平衡前缀初始化子 agent,该前缀仅包含已完成的父轮次。进行中的轮次被排除,因为其 subagent 调用尚无结果,无法构成有效的回放历史。 + +### 子 agent 隔离与父日志 + +每个 subagent 运行在**自己的 `Session`** 中(独立 id、`parentSession` 谱系),独立持久化。父日志仅记录 spawn `tool/call` 及其 `tool/result`(子 agent 的最终输出)——子 agent 的内部步骤和工具调用留在子 agent 自己的会话中,绝不注入父日志。这是唯一在所有传输方式下行为一致的设计:ACP 子 agent 的内部事件在物理上无法注入我们的父日志,因此让进程内行为保持一致,使 seam 真正与传输方式无关。 + +### 同步收集(首版) + +`dsh-tool-subagent` 将其执行信号传给 `start()`,等待子 agent 结果,并在 `finally` 中 dispose 该 run。非完成态的结果变为错误结果,而非成功的部分输出。这个前台消费方不使用 run 的可选 steering 方法。 + +### 提供方选择是配置,不面向模型 + +`dsh-tool-subagent` 绑定到恰好一个提供方名称(`Config.provider`);模型只看到 `{ description, prompt }`。若要暴露多种传输方式,请多次加载该工具插件,每次绑定不同的提供方和不同的 `toolName`(工具注册表拒绝重名)。*服务*持有多提供方注册表;*工具*选择其中一个——本版 schema 中没有提供方/type 参数。 + +## 测试 + +注册表与工具测试仅用包内脚本化提供方替换非确定性的子进程边界,同时运行真实的 `SubagentService`、生命周期、任务集成和面向模型的工具。提供方与消费方的 export 形状仍保留 Loader 回归覆盖,以防止[事后分析 0001](../../../../docs/postmortem/0001-acp-default-export-drops-inject.md) 中描述的失败。注册表测试覆盖重载安全性、重名和启动时能力拒绝;嵌套 agent 场景通过[逐会话快照回放](../testing/2026-06-22-subagent-snapshot-replay.md)进行无密钥回放;进程内后端还有真实循环的单元测试和带密钥的 e2e 测试。 + +## 后果 + +- **递归。** 如果不设限制,进程内子 agent 能看到委派工具并递归调用。进程内后端实现了可选的绝对深度限制和有作用域的实时全局 `toolFilter`;ACP 声明这两项能力为关闭状态,并拒绝此类请求。[subagent 组合控制 Agent Note](2026-07-12-subagent-persona-tool-filter-and-depth.md) 负责定义它们的确切语义和安全边界。 +- **阻塞父轮次。** 前台收集在子 agent 的整个持续时间内保持父 agent 的步骤打开。后台委派使用共享的 `ctx.tasks` 运行时与通用 `task_*` 工具,与后台 bash 共用同一套收集机制;subagent seam 本身仍不感知任务。 +- **实时进度。** 本版仅暴露生命周期事件与最终结果;逐分片的子→父更新流推迟到后台重新设计时一并处理。 +- **ACP 客户端接口。** 将 ACP 子 agent 的 `fs`/`terminal` 代理回父 agent(共享工作区模式)是后续工作;首版不声明这两项能力,子 agent 在自己的进程中自行服务。 diff --git a/.agents/notes/implemented/feature/2026-06-22-acp-subagent-backend.i18n.yaml b/.agents/notes/implemented/feature/2026-06-22-acp-subagent-backend.i18n.yaml new file mode 100644 index 0000000000..64d1f57f51 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-06-22-acp-subagent-backend.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-22-acp-subagent-backend.md: a45ce5e34873249969bbe4dabb87a89d10246b3d +2026-06-22-acp-subagent-backend.zh.md: 3b6a11efc1ae0427eb5ce3b30029b77b00d6801a diff --git a/.agents/notes/implemented/feature/2026-06-22-acp-subagent-backend.md b/.agents/notes/implemented/feature/2026-06-22-acp-subagent-backend.md index d1b61b0af8..a45ce5e348 100644 --- a/.agents/notes/implemented/feature/2026-06-22-acp-subagent-backend.md +++ b/.agents/notes/implemented/feature/2026-06-22-acp-subagent-backend.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-06-22-acp-subagent-backend.zh.md) + ## Problem The subagent seam ([the seam Agent Note](2026-06-21-subagent-capability-seam.md)) was built so multiple backends coexist by name on `ctx.subagents`. The in-process backends (`-spawn`/`-fork`) run a child as a second `Agent` on the SAME cordis context — cheap, but the child shares the parent's process, model client, and tools. The seam's whole point was to also support an OUT-OF-PROCESS child reached over a protocol, proving the abstraction generalizes across a process boundary. This Agent Note adds the first such backend: an Agent Client Protocol (ACP) client. diff --git a/.agents/notes/implemented/feature/2026-06-22-acp-subagent-backend.zh.md b/.agents/notes/implemented/feature/2026-06-22-acp-subagent-backend.zh.md new file mode 100644 index 0000000000..3b6a11efc1 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-06-22-acp-subagent-backend.zh.md @@ -0,0 +1,62 @@ +# Agent Note: ACP subagent 后端(进程外委派) + +Status: implemented + +[English](2026-06-22-acp-subagent-backend.md) | 中文 + +## 问题 + +subagent seam([seam Agent Note](2026-06-21-subagent-capability-seam.md))的设计使多个后端可以按名称共存于 `ctx.subagents`。进程内后端(`-spawn`/`-fork`)将子 agent(智能体)作为第二个 `Agent` 运行在同一个 Cordis 上下文上:开销低,但子 agent 与父 agent 共享进程、模型客户端和工具。seam 的核心意义在于同时支持通过协议到达的进程外子 agent,以证明该抽象能跨越进程边界泛化。本 Agent Note 添加第一个此类后端:一个 ACP(Agent Client Protocol)客户端。 + +## 决策 + +`@deepseek-ai/dsh-subagent-acp` 注册一个 `SubagentProvider`,将每个子 agent 运行在一个派生的子进程中,并以 ACP *客户端*身份驱动它。它是现有服务端桥接 `@deepseek-ai/dsh-acp`(ACP *agent*)的方向反转孪生体:桥接应答 `initialize`/`newSession`/`prompt`;本后端调用它们并实现 `Client` 回调(`sessionUpdate`、`requestPermission`)。将配置的 spawn 命令指向 `acp-agent` 示例,即可让 harness 与自身进程通信。 + +### 每次运行启动全新进程 + +每次 `start` 都 spawn 一个新的子进程,运行恰好一个 ACP 会话(`initialize` → `newSession` → `prompt`),`dispose` 杀死子进程并等待其退出。这是最简单的生命周期,与进程内「每次运行一个子 agent」的形态一致。 + +### 最小化客户端桩 + +客户端不声明任何可选能力(无 `fs`、无 `terminal`):子 agent 在自己的进程中自行处理文件/终端访问。`session/update` 通知被消费:后端将 `agent_message_chunk` 文本累积为结果输出,在本阶段忽略其余内容(思考、工具调用卡片),仅暴露子 agent 的最终回答。`session/request_permission` 由配置的策略自动应答(`reject` 拒绝所有提示,`allow` 通过第一个允许形态的选项批准)——本阶段不向人类暴露任何权限提示。将 `fs`/`terminal` 代理回父进程(共享工作区模式)仍为后续工作,如 seam Agent Note 所述。 + +### 无启动时能力 + +提供方的 `capabilities` 全部为 `false`。进程外子 agent 无法遵守父 agent 的 `maxDepth`(它无权访问 `parent.options.subagentDepth`)或 `toolFilter`(它拥有自己的工具注册表),本阶段也未实现 `outputSchema`。如果请求需要其中任何一项,服务在 `start` 运行前即拒绝。后端仅注入 `subagents`(而非 `ctx.agents`);它从 `request.parent` 读取的唯一内容是会话 header 的 cwd(见下方工作区解析)——对话上下文、深度和工具状态都不会跨越进程边界。 + +### 工作区 cwd 解析 + +子进程工作目录来自显式解析,绝不使用 harness 进程的 cwd:若已配置部署 `cwd` 覆盖,则相对于启动目录将其转为绝对路径并在加载时验证;否则使用父会话 header 的 cwd 并在启动时验证;如果两者都不存在,则在生成任何进程前大声拒绝。一个 ACP 服务端进程会服务来自多个工作区的会话,因此 `process.cwd()` 不能代替会话工作区——旧的隐式回退会让子进程在服务端启动目录中运行。候选路径必须是 harness 可以进入的绝对目录(要求 `X_OK`;仅 `statSync().isDirectory()` 会接受 mode-600 的目录,而 spawn 会因 EACCES 失败);解析出的同一路径同时用作子进程 cwd 与 ACP `session/new` 工作区。 + +### StopReason 映射 + +ACP `StopReason` → harness `SubagentStopReason`:`end_turn`→`completed`、`max_tokens`→`max-tokens`、`refusal`→`refusal`、`cancelled`→`aborted`、`max_turn_requests`→`error`(无对等语义,任务未完成)、未知→`error`。spawn/传输/RPC 失败解析为 `error`(如果已请求取消则为 `aborted`);按 seam 契约,`result` 在子 agent 级别失败时从不 reject。 + +### 安全:清洗子进程环境 + +子 agent 是独立进程,因此会继承环境变量。形如凭证的环境变量(`/KEY|SECRET|TOKEN/i`)默认不转发——父 harness 自身的密钥不得隐式泄露到派生进程中(与 bash 执行器采用的策略相同)。子 agent 自己的凭证(它需要模型密钥)通过 `config.env` 显式提供,在清洗之后叠加,因此有意传入的 `DEEPSEEK_API_KEY` 得以保留,而偶然存在的 `AWS_SECRET_ACCESS_KEY` 则不会。子进程的 stderr 继承到父进程的 stderr(诊断信息自然浮现);spawn 级别的 `error` 事件(如命令不存在时的 ENOENT)被捕获并与 ACP 驱动竞速,因此错误命令解析为 `error` 而非以未处理错误崩溃父进程。 + +## 测试 + +- **无需密钥的单元/集成测试:** 一个脚本化的 ACP 子进程通过真实 stdio 测试提示词/输出流、所有 stop-reason 映射、信号与 dispose 取消(包括 pre-abort、会话前竞态和管道断裂场景)、两种权限策略、被忽略的非消息更新、命令缺失时的清理、提供方重载以及命名空间导出。 +- **无需密钥的 Loader 组合测试:** 仅用于测试的 cordis.yml 通过真实 Loader 启动 stdio 应用,并省略后端的 `cwd`;脚本化模型委派一次,脚本化子进程则证明它在父会话工作区中运行,且 ACP 也对外公布了该工作区,从而端到端覆盖 cwd 继承分支。 +- **需要密钥的 e2e 测试:** 后端 spawn 真实的 ACP 示例;其模型回答 `PONG`,写入 `proof.txt`,父进程验证该文件。 +- **快照缺口:** 每个 ACP 子 agent 是独立进程,拥有自己的回放会话,不同于进程内的按会话回放。确定性 mock 服务器覆盖率已具备;`TODO(acp-subagent-replay)` 跟踪父进程对回放中子 agent 的回放支持。 + +## 曾考虑的替代方案 + +### 为何继续使用 SDK 0.25.1? + +后端只需要 `ClientSideConnection`、`ndJsonStream`、`PROTOCOL_VERSION` 和客户端协议类型,0.25.1 全部支持。0.28 的 fluent API 需要在 ACP 层同时迁移客户端和服务端连接类,却不会改善本后端,因此升级作为独立变更保留。 + +### 为何不使用持久子进程? + +持久进程池(跨运行复用热子进程)是一项性能优化,推迟到后续工作。它增加了会话生命周期和崩溃恢复的复杂度,本阶段不需要;每次 `start` spawn 全新子进程与进程内「每次运行一个子 agent」的形态一致。 + +## 后果 + +每次运行都要付出一个全新子进程的代价(spawn + `initialize` + `newSession`)。父进程仅暴露子 agent 的最终回答:`session/update` 中的思考和工具调用卡片被消费后丢弃,权限提示从不到达人类——由配置的策略应答。子进程环境默认经过凭证清洗,因此其自身的模型密钥需通过 `config.env` 显式提供。 + +## 后续提供方 + +同样的进程外启动/提示词/流式输出/取消形态可泛化到 seam Agent Note 中列出的其他传输方式——A2A、Codex app-server 和 Claude Code Agent SDK——每个都是按名称注册的兄弟提供方。ACP 后端证明了 seam 支持跨进程边界;其余在机制上类似。 diff --git a/.agents/notes/implemented/feature/2026-06-25-ask-user-question.i18n.yaml b/.agents/notes/implemented/feature/2026-06-25-ask-user-question.i18n.yaml new file mode 100644 index 0000000000..cd85b98708 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-06-25-ask-user-question.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-25-ask-user-question.md: 9eab7aeb17774961dfc40224accdcfcbd5eb9d5f +2026-06-25-ask-user-question.zh.md: eb166acfef7ed8f7ab4eb3018bf161a9ecc3549e diff --git a/.agents/notes/implemented/feature/2026-06-25-ask-user-question.md b/.agents/notes/implemented/feature/2026-06-25-ask-user-question.md index cd1a423499..9eab7aeb17 100644 --- a/.agents/notes/implemented/feature/2026-06-25-ask-user-question.md +++ b/.agents/notes/implemented/feature/2026-06-25-ask-user-question.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-06-25-ask-user-question.zh.md) + ## Problem The agent sometimes cannot proceed safely from model inference alone: it needs the human to choose a path, confirm a risky/default action, or provide missing information. Before this change, the only way to get that answer was for the model to ask in assistant text and then stop, which broke the normal tool-call loop: the agent had no structured way to pause, no option metadata for UIs, no abort/error taxonomy, and no way for non-stdio front doors to present the question consistently. diff --git a/.agents/notes/implemented/feature/2026-06-25-ask-user-question.zh.md b/.agents/notes/implemented/feature/2026-06-25-ask-user-question.zh.md new file mode 100644 index 0000000000..eb166acfef --- /dev/null +++ b/.agents/notes/implemented/feature/2026-06-25-ask-user-question.zh.md @@ -0,0 +1,55 @@ +# Agent Note: ask-user 提问能力 + +Status: implemented + +[English](2026-06-25-ask-user-question.md) | 中文 + +## 问题 + +agent(智能体)有时仅凭模型推理(inference)无法安全地继续执行:它需要人类选择路径、确认有风险的或默认的操作,或者提供缺失的信息。在此变更之前,获取答案的唯一方式是模型在 assistant 文本中提问然后停止,这打断了正常的工具调用循环:agent 没有结构化的暂停方式,没有供 UI 使用的选项元数据,没有中止/错误分类体系,也没有让非 stdio 前端一致地呈现问题的途径。 + +这是一个面向用户的能力,但它也跨越了包(package)边界。面向模型的工具需要一套提供方无关的请求词汇;每个 UI 界面需要决定如何展示和收集答案;agent loop(智能体循环)应保持不变,因为工具调用本身已具备正确的异步形状。 + +## 决策 + +引入 `dsh-user-interaction` 作为 `ctx.userInteraction` 的提供方无关接口包,与面向模型的消费方 `dsh-tool-ask-user` 一同放在 `packages/ui` 下。这一分组是有意为之的:向人类提问是一种由 UI 支撑的产品功能,不属于无提供方的核心主干。seam 仍然拥有稳定的请求/应答/错误词汇,而 UI 产品界面提供收集答案的具体提供方。该工具注册 `ask_user_question`,转发 `{ questions, agent, signal }`,并将提供方计算出的结构化答案作为工具结果返回。 + +面向模型的请求词汇有意与产品调研 schema 对齐:`ask_user_question({ questions: [{ id, question, header?, options?: [{ label, description? }], multi_select? }] })`。`id` 按问题提供并在结果中回传,使批量请求无需依赖问题文本即可路由。`label` 既是面向用户的显示文本,也是返回给模型的选中值;没有单独的 `value`,没有 `recommended`,没有 `allow_custom`,也没有 `desc` 别名。 + +提供方返回 `{ answers: [{ id, selected, custom? }] }`。`selected` 始终是选中选项 label 的数组,因此单选和 `multi_select` 的答案共享同一种结果形状。`custom` 承载自由文本的「其他」答案;无选项的问题直接收集 `custom`。当 `custom` 存在时,它覆盖任何已选择的选项,`selected` 为空。支持部分完成的提供方使用现有的 `{ id, selected: [] }` 形状表示某项被有意跳过,在不扩展工具结果词汇的前提下保留其他答案。 + +`UserInteractionError` 继承 `HarnessError`,因此 `NO_PROVIDER`、`ASK_ABORTED`、ACP(Agent Client Protocol)取消或会话路由缺失等失败会以机器可路由的 `{ name, code }` 工具错误形式通过 `ctx.tools.execute()` 传出。这与结构化错误分类体系一致,使模型或包装插件能够区分「用户取消」与一般的抛出异常。 + +## UI 映射 + +`dsh web` 挂载 `dsh-client-ui-question`:其 host 侧使 Web 产品选择性加载面向模型的工具,浏览器侧则在 conversation 拥有的具名输入区 slot 中注册 `question` 项。`createApiProxy` 使用以 host 生成的 rpcId 为键的进程内 pending 表实现 Web 提供方。它先注册等待项,再广播 `question/requested`;每次 mux 重开时以相同 id 重放;在受理前校验会话和完整答案批次;并在回答、取消、中止或资源释放后广播 `question/resolved`。受理会同步删除该条目,因此首个有效响应胜出,重复或迟到的响应返回 `not-pending`。 + +Web 输入区一次显示一个问题,同时在会话对象层保留每个请求。它支持单选、多选、无选项问题或显式自定义答案、描述文本与可视化推荐标记,但不会自动选中推荐项。选择单选项后会立即进入下一项;当所有项都已回答或显式跳过时,按 Enter 提交;IME 组字期间按 Enter 只会确认输入候选项。页脚只跳过当前项并保留先前的草稿;关闭控件以 `ASK_CANCELLED` 拒绝整个工具调用。常规输入区只有在 host 的 resolved 帧移除待处理项后才会恢复。 + +`dsh-tui` 将每个问题渲染为键盘叠层,展示选项描述,支持单选、多选和自由格式自定义答案,并在中止、提供方 dispose(资源释放)或终端关闭时拒绝待处理的问题。批量请求和并发请求都会排队,确保同一时刻只有一个叠层占用键盘焦点。 + +`dsh-acp` 为 ACP 会话提供同一 seam。它通过 `ownedRecord` 解析调用方 `Agent`,要求位于 `agent.session.id` 的正向会话 map 记录拥有该精确 agent 对象,并为每个问题调用 ACP `unstable_createElicitation`(附带会话范围的表单)。单选选项变为 `choice` 字符串枚举;`multi_select` 选项变为 `choice` 数组枚举;无选项的问题使用必填的 `custom` 文本字段。如果客户端同时返回 `choice` 和非空 `custom`,以 custom 答案为准。ACP `decline`/`cancel`、缺失答案、缺失会话以及客户端不支持 elicitation,都会转为结构化的 `UserInteractionError`。 + +ACP 映射有意使用 elicitation 而非 `session/request_permission`。`request_permission` 仍保留给独立的权限门禁:它是围绕工具执行的 yes/no 或策略式授权协议。`ask_user_question` 是一个通用的信息收集工具,支持可选的自由格式答案,因此 ACP 表单 elicitation 是更贴合的协议。bridge 的会话路由与未来的权限门禁共享,但用户意图不同。 + +## 曾考虑的替代方案 + +**Assistant 文本后跟一个停止的轮次。** 模型可以在纯 assistant 文本中向用户提问然后停止。这会丢失结构化选项元数据,UI 没有提供方无关的方式来渲染选择,且下一条人类回答只能作为新的 user 提示词到达,而非作为需要答案的那次操作的结果。 + +**核心拥有的 ask-user 包。** 最初实现将 seam 和面向模型的工具分别放在 `packages/core` 和 `packages/ui`,但两者描述的是同一个由 UI 支撑的人机交互功能。seam 仍然是提供方无关的,但它不是像会话、工具或 agent 注册表那样的无提供方核心基础设施。将 `dsh-user-interaction` 和 `dsh-tool-ask-user` 一起放在 `packages/ui` 下,使包的划分与产品边界一致:应用和 bridge 提供人类答案的提供方,stdio 应用选择性加载面向模型的工具。 + +**ACP `session/request_permission`。** 权限请求是围绕工具执行的授权;`ask_user_question` 是带可选自由格式答案的信息收集。将权限用于通用提问会混淆两个不同的产品概念,并使未来的权限门禁更难推理。 + +**循环级别的暂停原语。** agent loop 已经知道如何等待工具调用并从工具结果恢复。添加新的循环特殊分支会重复这一异步形状,并迫使每个循环实现都了解一个 UI 关注点。 + +## 后果 + +ACP elicitation 目前在 SDK 中标记为 unstable。回退仍然是结构化的:如果客户端未实现它,工具返回 `ASK_FAILED` 而非挂起。后续 ACP 稳定化可能重命名或重塑该方法;该迁移应限制在 `dsh-acp` 内部,因为核心 `ctx.userInteraction` 词汇是提供方无关的。 + +该功能赋予模型一个强大的暂停原语,因此提示词引导很重要。工具描述告诉模型:提问要简洁,尽可能使用选项。产品策略后续可以包装 `tools/execute` 来限制工具何时可用,但循环不应对其做特殊处理。 + +`dsh-user-interaction` 和 `dsh-tool-ask-user` 都位于 `packages/ui`,因为它们共同构成一个面向产品的人机交互能力。`agent-core` 不加载工具或提供方。`dsh-tui-demo` 选择性加载 seam、TUI 提供方和面向模型的工具。`dsh web` 在 host 运行时启动 seam/提供方,并通过选定的 Web question 插件暴露该工具。`acp-agent` 默认只保留 `userInteraction` seam/提供方:ACP elicitation 支持仍取决于客户端,因此 ACP 叶节点必须在其客户端能完成 elicitation 请求后才有意加载面向模型的工具。 + +## 测试 + +单元覆盖率固定了以下场景:提供方注册/释放、重复提供方拒绝、提供方就绪前中止、空问题拒绝、通过 `ctx.tools.execute()` 传出的结构化工具错误、批量答案、多选答案、自定义答案、显式按项跳过,以及模型 schema(包括移除 `value`、`recommended`、`allow_custom` 和 `desc`)。TUI 测试覆盖选项描述、排队请求、关闭/中止清理、无选项自由格式输入、无效选择、重复多选和批量问题流。ACP bridge 测试驱动一个真实的内存 ACP 连接(使用真实的 `ask_user_question` 工具),验证选中选项、custom 覆盖 choice、多选和无选项自由格式 elicitation 路径能继续 agent loop。Web 测试固定稳定 id 重放、响应校验、首个响应胜出的结算、重复和迟到响应、整个请求的取消与拥有方中止的区别、单选后前进、IME 安全的 Enter 提交、按项跳过保留、输入区接管、结构化批量提交,以及常规输入区的恢复。 diff --git a/.agents/notes/implemented/feature/2026-06-29-todo-write-tool.i18n.yaml b/.agents/notes/implemented/feature/2026-06-29-todo-write-tool.i18n.yaml new file mode 100644 index 0000000000..e6fc4aba97 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-06-29-todo-write-tool.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-29-todo-write-tool.md: bf5fceaafd475224914212beb460fdbc42e3dd68 +2026-06-29-todo-write-tool.zh.md: 3afc03a393284e2a9c2d6e234bc95f0faebbfb48 diff --git a/.agents/notes/implemented/feature/2026-06-29-todo-write-tool.md b/.agents/notes/implemented/feature/2026-06-29-todo-write-tool.md index ab9421c2ed..bf5fceaafd 100644 --- a/.agents/notes/implemented/feature/2026-06-29-todo-write-tool.md +++ b/.agents/notes/implemented/feature/2026-06-29-todo-write-tool.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-06-29-todo-write-tool.zh.md) + ## Problem The harness gives the model bash and subagent tools but no way to record a structured task list. A todo list serves two co-equal purposes: it steers the model to plan multi-step work and keep the active task unambiguous (at most one active, exactly one while work remains), and it gives the human a live progress checklist. The ACP protocol has a native `plan` sessionUpdate that editors (Zed) already render, but the bridge never emitted one. Every reference coding agent surveyed (claude-code, opencode, codex, oh-my-pi, pi) ships some form of this; the harness had nothing. diff --git a/.agents/notes/implemented/feature/2026-06-29-todo-write-tool.zh.md b/.agents/notes/implemented/feature/2026-06-29-todo-write-tool.zh.md new file mode 100644 index 0000000000..3afc03a393 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-06-29-todo-write-tool.zh.md @@ -0,0 +1,64 @@ +# Agent Note: `todo_write` 工具——将模型任务列表作为事件溯源的会话状态 + +Status: implemented + +[English](2026-06-29-todo-write-tool.md) | 中文 + +## 问题 + +harness 为模型提供了 bash 和 subagent 工具,却没有办法记录结构化的任务列表。todo 列表有两个同等重要的用途:引导模型规划多步骤工作并保持当前活跃任务明确(最多一个活跃,有剩余工作时恰好一个);同时为人类提供实时进度清单。ACP(Agent Client Protocol)协议原生支持 `plan` sessionUpdate,编辑器(Zed)已能渲染它,但 bridge 从未发出过。调研的所有参考编码 agent(智能体)(claude-code、opencode、codex、oh-my-pi、pi)都提供了某种形式的此功能;本 harness 此前没有。 + +## 决策 + +新增一个面向模型的 `todo_write(todos: [{ content, status }])` 工具,其整列表状态作为新的 `todo/write` `SessionEventMap` 变体存储在事件溯源的会话日志上。stdio UI 和 ACP bridge 均从现有的 `session/event` 渲染;ACP bridge 将列表映射为 `plan` sessionUpdate。 + +### 整列表替换,三态 status + +模型每次调用发送完整列表;新列表替换旧列表(回放时 last-write-wins)。这是 claude-code V1、opencode 和 codex `update_plan` 共同采用的形状,也是模型训练最多的形状——没有逐项 id,没有 delta 协议。`status` 恰好是 `pending | in_progress | completed`:与 codex `update_plan` 相同的三元组,且关键的是**与 ACP `PlanEntryStatus` 完全一致**,bridge 因此可以 1:1 映射,无需有损转换。 + +### 状态在会话日志上,而非服务 + +列表作为 `todo/write` 事件追加到日志,携带完整的 `{ todos }` 快照。harness 是事件溯源的——LLM(大语言模型)历史、工具调用和轮次结构都在日志上——所以 todo 列表也在那里。这免费获得了持久性、回放和 `session/load` 重建:重新打开的会话从最后一条 `todo/write` 重新推导当前列表,ACP bridge 在加载时重新发出 `plan`,无需独立的持久化后端、无需重新注水的内存服务、无需额外接线。一个内存中的 `ctx.todos` 服务需要重新发明以上所有。 + +### 不是 surface 事件 + +`todo/write` 被有意排除在 `SurfaceEventType` 之外。surface 是产出 LLM 消息历史(`deriveMessages()`)的投影;todo write 不产生对话消息。因此它不携带 `surfaceOp`,不加入有序 surface,不进入 `deriveMessages()`——它是持久、可回放的 *UI* 状态,与对话并行传输但不属于对话的一部分。(dev-mode 不变式仍要求它位于一个打开的轮次内,而它始终如此:它在工具调用的步骤中途追加。) + +### Priority 仅在 ACP 边界合成 + +ACP 的 `PlanEntry` 要求 `content` + `priority` + `status`,但 `TodoItem` 没有 priority——模型从不推理它。与其在 schema 中增加一个模型每次都必须提供的字段,bridge 在构建 `plan` 时为每条条目合成常量 `priority: 'medium'`。Priority 是 ACP 协议格式(wire format)的要求,不是 harness 概念,因此它恰好存在于需要它的边界上。 + +### 相比 claude-code V1 舍弃的字段:`activeForm`、id、priority + +claude-code V1 的条目是 `{ content, status, activeForm }`;后来(V2)增加了 id、依赖和所有权——但仅为支持 agent *集群*(磁盘持久、锁保护、逐项变更)。本工具将条目保持在最小集:`{ content, status }`。不要 `activeForm`(现在进行时标签)——UI 直接展示 `content`;不要 id——整列表替换不需要稳定标识;不要 priority——见上文。每舍弃一个字段,模型每次调用就少产出一项。 + +### 单一所有者——无集群机制(YAGNI) + +每个列表属于调用它的 agent 会话,非 agent 调用被拒绝。没有共享作用域、resolver 或 delta 协议。跨 agent 列表需要逐项日志 delta 和显式作用域选择,因此留作未来独立设计。 + +### 校验:低成本的中间路线 + +schema 强制 type/required/enum。在此之上,`execute` 拒绝为空或重复的 `content`,以及超过一个 `in_progress` 任务。claude-code 将单一 in_progress 交给提示词约束;oh-my-pi 在代码中强制。我们取中间路线:强制执行使计划*连贯*的低成本不变式(无空任务、无重复、最多一个活跃),但将排序和保持列表最新的纪律通过工具描述交给模型。被拒绝的写入返回 `isError` 结果,使模型自行修正。 + +## 为何没有 cordis-catalog 条目 / 没有 `@mode` + +`todo/write` 是 `SessionEventMap` 的成员,不是一等的 cordis `interface Events` 事件。catalog 生成器(`scripts/gen-cordis-catalog.ts`)扫描 `interface Events` 声明;`SessionEventMap` 变体搭载现有的 `session/event` emit,不产生新的 catalog 行。因此它不携带 `@mode` 标签(生成器仅对 `interface Events` 成员要求该标签)——添加一个毫无意义。 + +## 测试 + +四个层级,预先设计: +- **单元测试**——会话事件(append/snapshot-clone/last-write-wins/not-on-surface);工具(schema 形状、通过真实 `ctx.tools.execute` 的参数校验、值校验、事件追加与替换、非 agent 拒绝、`presentCall`、HMR(热模块替换)安全性);ACP `todosToPlan` 映射;stdio 渲染分支。 +- **真实 Loader 路径**——插件通过 `Loader.unwrapExports` 运行,断言命名空间导出形状存活(它有 `inject`,因此一个意外的 default 导出会在加载时崩溃——postmortem/0001)。 +- **全循环集成**——一个脚本化的 mock 模型通过真实 agent loop(智能体循环)调用 `todo_write`;`todo/write` 事件落地,第二次调用替换它。 +- **`session/load` 回放**——持久化的 `todo/write` 在新的 ACP bridge 加载会话时重新发出 `plan` 更新。 +- **带密钥 e2e + 快照**——真实提示词诱导一次 `todo_write`;快照预期输出获得 `plan` 通知和日志事件。 + +## 曾考虑的替代方案 + +- **内存中的 `ctx.todos` 服务**——需要重新发明日志免费提供的持久性、回放和 `session/load` 重建。 +- **逐项 delta 协议**——仅在共享多所有者列表时需要,超出当前范围;整列表替换更简单,且与参考实现一致。 +- **工具放在 `core/` 中**——`todo_write` 是注册在 `ctx.tools` 上的扩展工具,不属于主干;它像其他工具族一样位于自己的 `packages/todo/` 分组中。 + +## 后果 + +todo 列表是持久、可回放的会话状态:持久化的 `todo/write` 在 `session/load` 时重新发出编辑器的 `plan` 更新,日志(而非插件内存)是唯一真源。整列表替换意味着每次更新一次工具调用,last-write-wins;没有需要协调的 delta 协议。事件不进入 surface,因此 todo 更新永远不会扰动推导出的模型历史——模型只看到自己的工具调用和结果。 diff --git a/.agents/notes/implemented/feature/2026-06-30-hook-bridges.i18n.yaml b/.agents/notes/implemented/feature/2026-06-30-hook-bridges.i18n.yaml new file mode 100644 index 0000000000..cfcf477426 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-06-30-hook-bridges.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-30-hook-bridges.md: b6b0894e5551563187b1631e8c641e326fa166b0 +2026-06-30-hook-bridges.zh.md: 5f3adef958738d9d23c159c388be35b89f321828 diff --git a/.agents/notes/implemented/feature/2026-06-30-hook-bridges.md b/.agents/notes/implemented/feature/2026-06-30-hook-bridges.md index 0c3c1e13ef..b6b0894e55 100644 --- a/.agents/notes/implemented/feature/2026-06-30-hook-bridges.md +++ b/.agents/notes/implemented/feature/2026-06-30-hook-bridges.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-06-30-hook-bridges.zh.md) + ## Problem The harness's extension surface is its typed interception seams ([the interception-seams Agent Note](2026-06-30-interception-seams.md)): a "native hook" is just an ordinary cordis plugin subscribing to `agent/session-start`, `agent/prompt-submit`, `tools/pre-execute`, `tools/post-execute`, `agent/turn-continuation`, `subagent/start`, `subagent/end`. But users arrive with **existing** Claude Code (CC) and Codex hook configs — a `hooks.json` (or a settings file's `hooks` key) full of shell-command hooks — and want those to run unmodified. This Agent Note introduces the two **bridge plugins** that translate that external shell-hook protocol onto the typed seams, built on the shared wire-protocol library ([the hook-protocol-lib Agent Note](2026-06-30-hook-protocol-lib.md)). diff --git a/.agents/notes/implemented/feature/2026-06-30-hook-bridges.zh.md b/.agents/notes/implemented/feature/2026-06-30-hook-bridges.zh.md new file mode 100644 index 0000000000..5f3adef958 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-06-30-hook-bridges.zh.md @@ -0,0 +1,70 @@ +# Agent Note: dsh-hooks-claude + dsh-hooks-codex —— Claude Code / Codex 钩子桥接插件 + +Status: implemented + +[English](2026-06-30-hook-bridges.md) | 中文 + +## 问题 + +harness 的扩展面是其类型化的拦截 seam(见[拦截 seam Agent Note](2026-06-30-interception-seams.md)):所谓「原生钩子」不过是一个普通的 Cordis 插件,订阅 `agent/session-start`、`agent/prompt-submit`、`tools/pre-execute`、`tools/post-execute`、`agent/turn-continuation`、`subagent/start`、`subagent/end`。但用户带着**既有的** Claude Code(CC)和 Codex 钩子配置到来,一个 `hooks.json`(或 settings 文件中的 `hooks` 键)里满是 shell 命令钩子,并希望它们原样运行。本 Agent Note 引入两个**桥接插件**,将外部 shell 钩子协议翻译到类型化 seam 上,构建于共享的协议格式(wire format)库之上(见 [hook-protocol-lib Agent Note](2026-06-30-hook-protocol-lib.md))。 + +贯穿整个设计的定位:**桥接是兼容性适配器,不是高级工具。** 桥接能做的事(阻止工具、注入上下文、强制继续、观察 subagent),原生 Cordis 插件都能做得更强——类型化返回值、完整 `ctx`、无序列化边界。桥接存在的理由是运行外部 CC/Codex 命令钩子中被明确支持的子集。这使每个桥接保持精简:解析配置、选择匹配模式、构建每事件的 payload、调用共享库的 `runHook` + `mergeHookOutputs`,再将中性结果映射为 seam Decision。各包的 README 维护着当前不支持的事件和部分字段的完整清单,以官方协议为参照。 + +## 决策 + +`packages/hooks/` 组下两个独立插件,各为 function/namespace 插件(`name`/`inject`/`Config`/`apply`,无 default export——见[事后复盘 0001](../../../../docs/postmortem/0001-acp-default-export-drops-inject.md)),仅注入 `bash`: + +- **`dsh-hooks-claude`**——CC 方言。Claude Code 当前七个钩子点中的七个:`SessionStart`、`UserPromptSubmit`、`PreToolUse`、`PostToolUse`、`Stop`、`SubagentStart` 和 `SubagentStop`。拥有 CC 形态的每事件 stdin payload(基础字段 `session_id`/`transcript_path`/`cwd`/`hook_event_name` 加每事件字段)、`CLAUDE_PROJECT_DIR` 环境变量加 `${CLAUDE_PLUGIN_ROOT}`/`${CLAUDE_PROJECT_DIR}` 替换,以及字面量或正则的匹配模式。`transcript_path` 是持久化定位器结果或 `''`;stdin 带有**尾部换行**。 +- **`dsh-hooks-codex`**——Codex 当前五个钩子点中的五个:`PreToolUse`、`PostToolUse`、`SessionStart`、`UserPromptSubmit` 和 `Stop`。使用始终为正则的匹配模式、Codex 形态的 snake_case payload(含 `turn_id`/`model`/`permission_mode` 额外字段),写入时不带尾部换行,不注入 Codex 插件环境变量,不做配置时占位符替换,也没有 pre-tool 审批或重写路径。`transcript_path` 是同一定位器结果或 `null`;工具 payload 在精简后的 `tool_input: { command }` 形态中携带真实的 `tool_name`。 + +### Outcome → Decision 映射 + +每个桥接将共享库返回的中性 `MergedHookOutcome` 映射到 seam 的类型化 Decision: + +| Seam | CC | Codex | +|---|---|---| +| `agent/session-start`(emit) | additionalContext → `agent.inject()` | 纯 stdout 输出 → additionalContext → `agent.inject()` | +| `agent/prompt-submit` | `deny`→`block`;仅上下文→delegate+fold | `block`→`block`;仅上下文→delegate+fold | +| `tools/pre-execute` | `deny`→`deny`;`ask`→`ask` | `block`→`deny`(无 allow/ask) | +| `tools/post-execute` | `deny`→`block`+feedback;仅上下文→delegate+fold | 同上 | +| `agent/turn-continuation` | 阻塞的 Stop → `continue`(reason = 下一步 steering(中途引导)) | 同上 | +| `subagent/start`(emit) | additionalContext → 注入到存活的进程内 subagent;远程 subagent 无本地注入目标 | 本桥接不支持 | +| `subagent/end`(emit) | 仅观察 | 本桥接不支持 | + +CC 桥接的 `ask` 结果是一条真正的权限路径,而非终态桥接决策:`dsh-tools` 通过可选的[审批 seam](2026-07-06-approval-seam.md) 来解析它。组合式 ACP 应答器向拥有该会话的编辑器会话发起提示,`allowed-once` 后继续执行;如果没有 ApprovalService 或应答器,调用以 `deny` 安全关闭。 + +### 上下文来源始终是插件(误标签防护) + +`agent.inject()` 在缺少 `MessageSource` 时默认为 `{ kind: 'user' }`,因此每个桥接的 `inject()` 和 `HookContext` 都传入 `{ kind: 'plugin', plugin: 'hooks-claude' | 'hooks-codex' }`。单元测试覆盖率固定验证结果中的 `context/message.source` 为插件而非用户。 + +### 添加上下文不是否决——先 delegate,再 prepend + +仅附加 `additionalContext`(没有 block/deny)的钩子并不是桥接可以独自返回的决策:在 waterfall 监听器中不调用 `next()` 就返回 `allow`/`accept`,会短路其后的每个 `agent/prompt-submit` / `tools/post-execute` 监听器,使注册在桥接之后的策略/沙箱插件看不到该提示词。因此,每个桥接都会先通过 `next()` 委托,再将自身上下文加入下游决策。两个 seam 都携带有序的 `additionalContexts` 数组,因此桥接会在保留所有下游来源、信封和元数据字段的同时,前置加入其独立来源的条目;下游提示词阻止仍会丢弃所有上下文,因为提示词从未到达模型,而工具后阻止语义可以显式保留上下文。Code Mode 会通过外层 `run_code` 结果转送同一数组。只有钩子本身真正返回 `deny`/`block` 才会短路。测试断言:上下文钩子允许后,较晚的监听器仍能阻止提示词,且保留的提示词和工具后上下文仍彼此分离。 + +### CLAUDE_PROJECT_DIR 默认为会话工作区 + +Claude Code 始终导出 `CLAUDE_PROJECT_DIR`,常见的未修改钩子引用 `$CLAUDE_PROJECT_DIR` 来构造项目相对路径。显式的 `config.projectDir` 优先;当它被省略时(默认 ACP 接线只配置 `configPath`),桥接将该环境变量按每次运行默认为 agent(智能体)的会话工作区——即钩子已经在其中运行的 `session.header.cwd`——而非留空。这样,一个标准的项目相对路径钩子在默认配置下即可正常工作。 + +### 隔离 + +配置在加载时一次性解析;读取/解析失败时记录日志并不注册任何内容,而非崩溃启动(一个拼错的路径不应拖垮 agent)。CC 桥接只运行 shell 形式的 `type: 'command'` 钩子;`http`、`mcp_tool`、`prompt` 和 `agent` 处理器被解析后跳过。Codex 桥接只运行同步命令处理器,跳过 `async: true` 或非命令条目。emit 监听路径(`session-start`、`subagent/start`)以 detached 方式运行,其 `inject` 包裹在 `.catch` 中记录日志(抛异常的 inject 不得中断会话启动或循环)。 + +### 钩子在哪里运行,配置从哪里来 + +钩子在 agent 的会话工作区中运行,因此相对路径指向用户的项目。`configPath` 相对于进程启动时的 cwd 解析一次,适用于所有会话。按会话的项目本地发现仍推迟在 `TODO(per-session-hook-config)` 下。 + +## 推迟的兼容性缺口 + +- **工具输入重写。** CC/Codex 的 `updatedInput` 被记录日志并发出警告,但不予执行——输入重写是一个推迟的一致性设计问题(见 [pre-tool-input-rewrite Agent Note](../../proposed/feature/2026-06-30-pre-tool-input-rewrite.md)),因为 pre-execution 参数被 `tool/call` 审计、`assistant/message` 历史和 ACP/tool-bash 展示共同读取,诚实的重写是一个设计单元,而非一个字段。 +- **Stop 循环防护**(`TODO(stop-loop-guard)`)。Claude Code 提供 `stop_hook_active` 并在连续八次阻塞后覆盖钩子;Codex 提供 `stop_hook_active` 但未记录等效上限。两个桥接始终报告 `false`,因此一个无条件阻塞的 Stop 钩子会在每一步强制继续——在状态追踪落地之前,钩子作者必须自行限制。 +- **钩子 `continue:false`(硬停止)。** 钩子可以请求终止整个运行(CC/Codex `continue:false`);共享合并将其折叠为 `MergedHookOutcome.stop`/`stopReason`,但没有桥接对其采取行动(`TODO(hook-continue-false)`)——拦截 seam 尚无「硬停止 agent」原语(Decision 阻塞/引导的是单个点,而非整个运行)。与循环防护工作一同推迟;停止请求记录在 `hook/result` 日志中,钩子在此期间保留其逐点效果(决策/上下文)。 +- **配置发现。** 路径在 `cordis.yml` 中显式指定且为进程级(见上文);完整的多层 CC/Codex 优先级遍历、按会话的项目本地发现以及信任/hash 模型未被重新实现(`TODO(per-session-hook-config)`)。 +- **Session-start / subagent-start 上下文为尽力而为(`TODO(session-start-gating)`)。** 两个钩子以 detached 方式运行于启动过程之外,因此其上下文在就绪时注入,但可能错过首个请求或短命的 subagent。要保证首请求送达,需要一个 awaited 的启动 seam。 + +## 曾考虑的替代方案 + +**每点钩子并发执行。** 参考引擎对一个点匹配到的钩子并发运行并折叠结果。本桥接**串行**运行(匹配循环内每个钩子 `await`),并以相同的最严格合并策略折叠。串行是刻意的:它使每个钩子的 `hook/invoked`/`hook/result` 对在会话日志中相邻且顺序确定,而折叠对决策是顺序无关的(`deny > ask > allow`),因此结果一致。代价是延迟(钩子 *N* 等待钩子 *N−1*)以及每钩子超时不重叠——对真实配置中的钩子数量可以接受;如果某配置的扇出大到影响总耗时,再重新评估。 + +## 后果 + +匹配语义、退出码处理和合并优先级位于 `dsh-hook-protocol`;每个桥接只负责解析配置、构建方言 payload 和映射结果。逐文件覆盖率包含配置分支以及通过真实循环、`dsh-bash-local` 和 shell 脚本的端到端映射,同时一个真实 Loader 冒烟测试守护包的导出形态。原生插件绕过协议格式,直接返回类型化决策。 diff --git a/.agents/notes/implemented/feature/2026-06-30-hook-protocol-lib.i18n.yaml b/.agents/notes/implemented/feature/2026-06-30-hook-protocol-lib.i18n.yaml new file mode 100644 index 0000000000..de9949114b --- /dev/null +++ b/.agents/notes/implemented/feature/2026-06-30-hook-protocol-lib.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-30-hook-protocol-lib.md: 19a69119befde99417b736edf38923ec6ac5fa7c +2026-06-30-hook-protocol-lib.zh.md: f4950eea2b02e86ed7109f8ebdaab29dd77428d8 diff --git a/.agents/notes/implemented/feature/2026-06-30-hook-protocol-lib.md b/.agents/notes/implemented/feature/2026-06-30-hook-protocol-lib.md index bb1822504a..19a69119be 100644 --- a/.agents/notes/implemented/feature/2026-06-30-hook-protocol-lib.md +++ b/.agents/notes/implemented/feature/2026-06-30-hook-protocol-lib.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-06-30-hook-protocol-lib.zh.md) + ## Problem The hooks subsystem ships two bridge plugins: one that runs a user's existing Claude Code (CC) hooks, one for Codex hooks. Studying the reference implementations (`~/repos/refs/claude-code`, `~/repos/refs/codex`) surfaced a decisive fact: **Codex deliberately reimplements a SUBSET of the CC hook protocol.** Its engine reads the same `hooks.json`, uses the same matcher-group shape, the same exit-code/structured-stdout output contract, and the same command-hook execution model — Codex's source even names the engine after Claude's and comments where it "intentionally diverges." So the two bridges would otherwise duplicate the bulk of the protocol. diff --git a/.agents/notes/implemented/feature/2026-06-30-hook-protocol-lib.zh.md b/.agents/notes/implemented/feature/2026-06-30-hook-protocol-lib.zh.md new file mode 100644 index 0000000000..f4950eea2b --- /dev/null +++ b/.agents/notes/implemented/feature/2026-06-30-hook-protocol-lib.zh.md @@ -0,0 +1,32 @@ +# Agent Note: dsh-hook-protocol——Claude Code / Codex 钩子协议格式共享核心库 + +Status: implemented + +[English](2026-06-30-hook-protocol-lib.md) | 中文 + +## 问题 + +钩子子系统提供两个桥接插件:一个运行用户既有的 Claude Code(CC)钩子,另一个运行 Codex 钩子。研究参考实现(`~/repos/refs/claude-code`、`~/repos/refs/codex`)后发现一个决定性事实:**Codex 有意重新实现了 CC 钩子协议的一个子集。** 它的引擎读取相同的 `hooks.json`,使用相同的 matcher-group 形状、相同的 exit-code/structured-stdout 输出契约,以及相同的命令钩子执行模型。Codex 的源码甚至以 Claude 的引擎命名,并在注释中标注了「有意偏离」之处。因此,如果不做抽取,两个桥接插件将大量重复协议逻辑。 + +本 Agent Note 引入 `@deepseek-ai/dsh-hook-protocol`,一个**库**(不是插件——它不注册也不注入任何东西),持有两个桥接插件共同依赖的真正相同的原语。共享与方言专属之间的分界是本设计的重心。 + +## 决策 + +在 `packages/hooks/` 分组下新建 `hook-protocol` 作为纯库。它拥有四个原语族和 `hook/*` 会话事件;每个桥接插件(`dsh-hooks-claude`、`dsh-hooks-codex`)拥有真正不同的部分。 + +**共享(本库):** +- **Matcher** — `matchesMatcher(pattern, query, mode)`。两种方言唯一不同的轴被收敛为 `mode` 参数:`claude` 将纯 `[A-Za-z0-9_|]+` 模式视为字面量(管道符 = 精确匹配的多选),其余视为正则;`codex` 始终是无锚定正则。缺省/`''`/`'*'` 匹配一切;无效正则匹配空集(绝不向 agent loop(智能体循环)抛异常)。 +- **执行** — `runHook(bash, hook, options)`。通过 `ctx.bash` seam 而非自建 `spawn` 运行命令钩子:执行器已提供清洗但可覆盖的 env、进程组 kill 和超时,正是协议所需的能力;`dsh-bash` 的 `stdin`/`env` 字段(正是为此添加的)是进程内桥接插件被允许使用的受信插件接口。它将桥接插件构建的 payload 序列化到 stdin(CC 时追加尾部换行),遵守钩子的 `timeoutSec`(否则使用 `DEFAULT_HOOK_TIMEOUT_MS`,即两种方言共享的 10 分钟参考默认值),且从不抛异常(执行器拒绝变为 non-blocking-error 的 `HookOutput`)。 +- **解码** — `parseHookOutput(exit, stdout, stderr)`,exit-code + structured-stdout 编解码器,产出方言无关的 `HookOutput`。Exit `0` → 宽松 JSON 解析 stdout;exit `2` → blocking error,`stderr` 为原因(以 `decision: 'block'` 呈现,调用方无需单独处理 exit-code 分支);其他 → non-blocking error。解析 CC structured-stdout 中在某条路径上有消费方的字段(`continue`/`stopReason`/`decision`/`hookSpecificOutput.{permissionDecision,additionalContext,updatedInput}`/`systemMessage`);桥接插件只采纳对其方言有意义的子集。在任何路径上都没有消费方的字段不予解析(CC 的 `suppressOutput`——钩子 stdout 在此处从不进入 transcript(文本记录),因此无需抑制;见 [收紧钩子协议契约 Agent Note](../simplification/2026-07-04-tighten-hook-protocol-contract.md))。 +- **合并** — `mergeHookOutputs(outputs)`,将多个匹配钩子的输出折叠为一个最严格的 `MergedHookOutcome`:权限优先级 **deny > ask > allow**,halt 在首个 `continue:false` 时粘滞,阻止原因以 `\n\n` 拼接,context/system-messages 按序累积。 +- **`hook/*` 会话事件** — `hook/invoked` / `hook/result`,通过声明合并进入 `SessionEventMap`(仅日志,如 `compact/*`——不是 `SurfaceEventType`),配有 `appendHookInvoked`/`appendHookResult` 辅助函数,确保 invoked/result 配对与轮次包含关系在各桥接插件间保持一致。`appendHookResult` 还拥有持久化记录的语义:decision 字符串(钩子解析出的 decision,否则 `continue:false` 时为 `'stop'`,否则为 `'pass'`)和 500 字符的 `stderrSummary` 截断均从本库的 `HookOutput` 派生,而非各桥接插件各自实现。 + +**方言专属(桥接插件):** 构建每个事件的 stdin payload(CC 的 base+per-event 字段集 vs Codex 的 snake_case 加 `turn_id`/`model` 额外字段)、方言的 env 与 `${CLAUDE_PLUGIN_ROOT}` 替换(CC)vs 无替换(Codex),以及将方言无关的 `HookOutput`/`MergedHookOutcome` 映射为 harness seam 专属的类型化 Decision(`PreToolDecision`、`PromptDecision`、`ContinuationDecision`、`PostToolDecision`)。 + +## 曾考虑的替代方案 + +**单一参数化引擎。** 否决,因为 payload 构建与 decision 映射在方言间确实不同。Matcher、编解码器、执行、合并规则和事件保持共享;每个桥接插件保留自己的 payload 和映射,使其协议格式行为在代码中可就地阅读。 + +## 后果 + +每个桥接插件解析配置、构建方言 payload、调用共享的 runner 与合并逻辑、映射 decision、追加 `hook/*`。协议测试覆盖每种 matcher 模式、exit-code 与编解码器字段、runner 管道、合并优先级和审计辅助函数,逐文件 100% 覆盖率;桥接插件测试验证库的真实加载路径。`updatedInput` 已解析但仅记录日志并发出警告,直到 [input-rewrite 提案](../../proposed/feature/2026-06-30-pre-tool-input-rewrite.md)落地。 diff --git a/.agents/notes/implemented/feature/2026-06-30-interception-seams.i18n.yaml b/.agents/notes/implemented/feature/2026-06-30-interception-seams.i18n.yaml new file mode 100644 index 0000000000..639a586e7c --- /dev/null +++ b/.agents/notes/implemented/feature/2026-06-30-interception-seams.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-30-interception-seams.md: 8af489d3f575dd457e1981e433330f08cefa2043 +2026-06-30-interception-seams.zh.md: 3886ed21504abfe14a2ccb344d7aa0d3f8d25064 diff --git a/.agents/notes/implemented/feature/2026-06-30-interception-seams.md b/.agents/notes/implemented/feature/2026-06-30-interception-seams.md index a0504893d9..8af489d3f5 100644 --- a/.agents/notes/implemented/feature/2026-06-30-interception-seams.md +++ b/.agents/notes/implemented/feature/2026-06-30-interception-seams.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-06-30-interception-seams.zh.md) + ## Problem The harness needs a hooks subsystem: users extend or gate the agent at lifecycle points the way Claude Code (CC) and Codex do. The key reframe driving this design is that **"native hooks" are not a package** — a native hook is just an ordinary Cordis plugin subscribing to the canonical lifecycle events. So the real product is a *powerful, well-typed canonical event surface*; the CC/Codex bridges (the `dsh-hooks-claude` / `dsh-hooks-codex` packages) are merely translators that map an external shell-hook protocol onto that same surface. Anything a bridge can do, a plain plugin can do directly — more powerfully (no serialization boundary, full `ctx`, typed returns). diff --git a/.agents/notes/implemented/feature/2026-06-30-interception-seams.zh.md b/.agents/notes/implemented/feature/2026-06-30-interception-seams.zh.md new file mode 100644 index 0000000000..3886ed2150 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-06-30-interception-seams.zh.md @@ -0,0 +1,61 @@ +# Agent Note: 拦截 seam——钩子编程所面对的类型化 Decision 表面 + +Status: implemented + +[English](2026-06-30-interception-seams.md) | 中文 + +## 问题 + +harness 需要一套钩子子系统:用户像 Claude Code(CC)和 Codex 那样在生命周期节点扩展或管控 agent(智能体)。驱动本设计的关键视角转换是:**「原生钩子」不是一个包**——原生钩子只是一个普通的 Cordis 插件,订阅规范的生命周期事件。因此真正的产品是一个*强大、类型完备的规范事件表面*;CC/Codex 桥接(`dsh-hooks-claude` / `dsh-hooks-codex` 包)只是将外部 shell 钩子协议映射到同一表面的翻译层。桥接能做的事,普通插件可以直接做——而且更强大(无序列化边界、完整 `ctx`、类型化返回值)。 + +该表面需要为以下场景提供各自独立的契约:逐提示词策略(CC 的 `UserPromptSubmit`)、会话启动观测(CC 的 `SessionStart`)、工具执行前策略、环绕调度控制、工具执行后变换、最终结果观测,以及携带面向模型的原因的继续执行。如果把这些阶段混为一谈,插件就会获得不需要的 mutation 通道,而终结性将依赖监听器的注册顺序。[事件域语义 Agent Note](../architecture/2026-06-30-event-domain-semantics.md)提供了三域规则与类型化 Decision 惯用法;本 Agent Note 将其应用于生命周期 seam。 + +## 决策 + +规范表面将可变换策略、环绕调度控制与仅观测通知分离。策略 waterfall(瀑布式事件)返回小型的、seam 专属的**类型化 Decision 联合类型**;包装层返回规范化结果;通知接收不可变快照,无法影响结果。覆盖的钩子点包括 `session-start`、`prompt-submit`、`pre-tool`、`post-tool`、通过 continuation 实现的 `stop`,同时将非钩子的执行策略留作独立可组合。 + +**Agent 事件**(`dsh-agent`): +- `agent/session-start(agent, source)` ——emit,在第 1 轮次之前触发一次,携带 `SessionStartSource`(`startup` 表示全新/fork 创建,`resume` 表示重新加载的持久化会话;`clear`/`compact` 保留)。纯通知,不能阻塞启动(这是有意的空白:桥接可以记录/注入,但不管控启动)。监听器通过 `agent.inject()` 注入上下文。 +- `agent/prompt-submit(agent, content, source, signal, next) → PromptDecision` ——waterfall,在轮次唯一取得所有权的排队消息追加为 `user/message` 之前触发。显式轮次 signal 位于最后的 `next` 之前;`allow` 可以重写提示词 `content` 或附加来源各自独立的 `additionalContexts[]`,而 `block` 会追加一条持久的 `prompt/blocked`,并拒绝这个零步骤轮次。 + +**`agent/turn-continuation`** 接收并返回一个 `ContinuationDecision`。`{action:'continue', reason?}` 可携带面向模型的内容和来源,记录为同一轮次内的下一步 steering(中途引导)——与 `/goal` step-end-steer 模式互为类型化孪生。它不是 `context/message`,因此其类型不提供持久上下文元数据。 + +### 工具流水线为每个阶段赋予一种权限 + +每次调用遵循 `tools/pre-execute` → guards → `tools/execute` → dispatch → `tools/post-execute` → 由定义拥有的 `finalizeContent` → `tools/result`。注册表对调用方输入创建快照、实体化并冻结参数、分配一个不透明 token,并在策略开始前对可见定义的最终内容回调创建快照。嵌套调用仅携带父 token。身份始终不可变;只有 `signal` 可在环绕调度时改变。日志、UI 和工具体因此对「执行了什么」达成一致。 + +- **`tools/pre-execute`** 是可扩展的 waterfall 门禁。其 `PreToolDecision` 允许、拒绝或询问。拒绝跳过 `tools/execute` 与核心调度。询问通过可选的审批 seam 解析:只有 `allowed-once` 继续通过 guards 和调度;拒绝、取消、通道不可用、审批服务缺失或无 agent 调用均规范化为拒绝。每个已解析的 decision 仍会到达后策略;抛出异常的监听器会成为最终的规范化失败。 +- **`ctx.tools.guard()`** 在整个 pre-execute waterfall 之后安装同步的、作用域感知的策略。guard 可以拒绝或弃权,永远不能强制允许,因此监听器顺序无法复活一个被最终不变式禁止的操作。 +- **`tools/execute`** 是用于超时、重试和指标插件的环绕调度 waterfall。包装层通过 `next()` 委托给核心调度,在此之前可以替换并恢复必需的 `exec.signal`,但不能移除它;包装层接收抛出异常或未知工具产生的、已完成规范化的规范成功/失败结果。包装层自行产生的成功结果会短路调度,并通过已解析的输出声明重新规范化。 +- **`tools/post-execute`** 是检查/变换 waterfall。其 `PostToolDecision` 接受、以反馈阻止、替换呈现内容或规范值,或附加 `additionalContexts`。替换值会重新校验并重新计算呈现;替换内容会保留程序化值,且不构成保密边界。返回的 decision 是受支持的变换通道。 +- **`ToolDefinition.finalizeContent`** 是一个可选、同步、完备且仅能处理内容的边界,在调用创建时随可见定义一起被快照。注册表将候选结果规范化并创建无损快照后,它恰好运行一次;候选结果包括绕过后续 waterfall 的 pre、around 或 post 监听器失败,以及为另一个结果字段创建快照时发现的错误。它可以替换 `content`,也可返回 `undefined` 保留原内容,但不能重写 `isError`、结构化错误身份、上下文或呈现元数据。工具在此执行自身最后一道内容不变式,而无需将策略失败转换为更弱的阻止 decision。 +- **`tools/result`** 是在所有变换、无损 JSON 实体化和外层错误边界之后的同步封闭通知。它接收相同的冻结执行身份和权威结果的不可变快照;观测者的失败按监听器隔离,无法改变或拒绝 `ToolRegistry.execute()` 返回的结果。 + +核心调度与工具体位于规范化边界内部,因此工具、监听器、无效规范值、渲染器/投影器、非 JSON 呈现和身份形状错误均解析为 JSON 安全的 `isError` 结果,而非逃逸出轮次。post-execute 监听器因此可以检查一个抛出异常的工具;由定义拥有的最终内容不变式也会覆盖外层流水线与候选结果实体化失败;最终观测者会同时看到执行期间的规范值,以及会话日志能够持久化的确切呈现字段。[规范工具输出契约](../architecture/2026-07-20-canonical-tool-output-contract.md)定义值/投影与持久性规则。 + +**`TurnEndReason.rejected`**(`dsh-session`):取得所有权的提示词被 `prompt-submit` 阻止的零步骤轮次。 + +### 三个承重的循环决策 + +1. **在提示词策略之前开启轮次。** 被阻止的提示词成为零步骤的 `rejected` 轮次,保持封闭性并为 ACP(Agent Client Protocol)提供持久的终结事件。否决记录 `prompt/blocked`(含原始提示词和原因),而每个允许的 `additionalContexts` 条目都注入到已开启的轮次中。依照[一次 send 对应一个轮次的简化](../simplification/2026-07-17-one-send-one-turn.md),每个取得所有权的 ordinary-send 条目都是其轮次中的唯一消息;启动前丢弃不会创建轮次。 + +2. **工具执行后的 `additionalContexts` 与异步注入进入活跃批次 FIFO,并在该批次结算时追加。** `content`/`feedback` 塑造 `execute()` 返回的结果,但每项上下文都是独立的 `context/message`,而单个步骤或组合工具可以产生许多上下文。立即追加上下文会产生 `result(c1) → context → result(c2)` 的交错,或把嵌套上下文放在外层结果之前,破坏工具调用/结果邻接性。因此 `ToolRunContext.deferContext()` 会在失败路径上也收集嵌套调度上下文,`execute()` 在 `ToolExecutionResult` 上暴露有序数组,循环再把它接纳到与执行期间 `agent.inject()` 调用相同的 FIFO 中。FIFO 在批次结算时,于每个已记录结果之后追加,其中也包括被中断轮次关闭之前。被接受的外层调用将 deferred contexts 保留在 decision contexts 之前;被外层阻止时则丢弃 deferred contexts,只暴露阻止 decision 显式提供的上下文。 + +3. **强制 `continue` 的 `reason` 通过 steering 通道入队**,使得下一步骤在循环顶部排空时将其记录为当前轮次的 steering——同一轮次内的下一*步骤* steering,而非下一*轮次*的提示词(与现有的 `hasSteering` 强制继续覆盖一致)。 + +### 工具执行前输入重写是一个独立的一致性决策 + +`PreToolDecision` 不能重写参数。历史和审计调用在执行前记录,ACP 展示读取相同的输入,因此注册表在策略之前封存参数。有效的重写必须在身份创建之前同时更新历史、审计、展示和执行;该契约属于[输入重写提案](../../proposed/feature/2026-06-30-pre-tool-input-rewrite.md)。 + +### 边界 + +seam 包**不**声明 `hook/*` 会话事件(持久的钩子调用日志);那些属于 `dsh-hook-protocol`,因为原生插件使用类型化 decision 而无需外部钩子日志。原生插件集成测试(`packages/core/agent-loop/tests/interception.spec.ts`)通过真实循环组合这些 seam,不涉及 `hook/*` 协议。压缩(compaction)(`PreCompact`/`PostCompact`)、Notification 和 Codex `PermissionRequest` 不在本决策范围内。[审批 seam](2026-07-06-approval-seam.md) 通过 `ctx.approval` 解析 `ask` decision,而终结性的单调停止由 `agent/turn-stop` 独立负责。 + +## 曾考虑的替代方案 + +- **将工具执行前输入重写作为本 seam 集的一部分发布**:推迟,视为越界信号;上文已阐述一致性问题(审计、历史和展示都读取执行前记录的 `tool/call.arguments`),[工具执行前输入重写提案](../../proposed/feature/2026-06-30-pre-tool-input-rewrite.md)负责该设计。 +- **将持久的 `hook/*` SessionEvents 与 seam 一起声明**:否决。原生插件使用类型化 Decision 而完全不需要钩子日志(实际示例已证明),因此持久日志属于[钩子协议库](2026-06-30-hook-protocol-lib.md),而非 seam 表面。 + +## 后果 + +规范拦截表面具有统一的类型化,同时不给每个扩展相同的权力:钩子返回 decision,执行包装层做包装,终结 guard 只能拒绝,最终观测者只能观测。循环负责 session-start、prompt-submit、工具执行后上下文缓冲和 continuation;`dsh-tools` 负责身份封存与五阶段执行流水线。它们的契约记录在 [architecture.md](../../../../docs/architecture.md)、各包 README、[核心拦截 decision](../../../../docs/core-data-structures/core.md#interception-decisions) 与[工具结构](../../../../docs/core-data-structures/tools.md)中。ACP 桥接将 `rejected` 轮次映射为其 `cancelled` 编解码值,而钩子驱动的快照端到端验证可观测的桥接行为。 diff --git a/.agents/notes/implemented/feature/2026-06-30-session-store-fork-api.i18n.yaml b/.agents/notes/implemented/feature/2026-06-30-session-store-fork-api.i18n.yaml new file mode 100644 index 0000000000..b1ad660010 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-06-30-session-store-fork-api.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-30-session-store-fork-api.md: 4e4ea7f1d3aa3290bdb21999a292dbdfd016302e +2026-06-30-session-store-fork-api.zh.md: d17daa464ad59c6b5ac4d5041b4af30c44321fa7 diff --git a/.agents/notes/implemented/feature/2026-06-30-session-store-fork-api.md b/.agents/notes/implemented/feature/2026-06-30-session-store-fork-api.md index ee67af7d96..4e4ea7f1d3 100644 --- a/.agents/notes/implemented/feature/2026-06-30-session-store-fork-api.md +++ b/.agents/notes/implemented/feature/2026-06-30-session-store-fork-api.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-06-30-session-store-fork-api.zh.md) + ## Problem The event-sourced session log already has the primitive a fork needs: create a new session with a seed event prefix, then derive model history from that seeded log exactly as replay does. That primitive is intentionally low-level: `ctx.sessions.create(id, { seed, meta })` accepts any valid seed, but ordinary live-session branching needs policy around which prefix can be copied, which metadata is stamped on the child, and how errors are classified. diff --git a/.agents/notes/implemented/feature/2026-06-30-session-store-fork-api.zh.md b/.agents/notes/implemented/feature/2026-06-30-session-store-fork-api.zh.md new file mode 100644 index 0000000000..d17daa464a --- /dev/null +++ b/.agents/notes/implemented/feature/2026-06-30-session-store-fork-api.zh.md @@ -0,0 +1,43 @@ +# Agent Note: SessionStore fork API + +Status: implemented + +[English](2026-06-30-session-store-fork-api.md) | 中文 + +## 问题 + +事件溯源的会话日志已经具备 fork 所需的原语:创建一个带有种子事件前缀的新会话,然后像回放一样从该种子日志推导模型历史。这个原语有意保持底层:`ctx.sessions.create(id, { seed, meta })` 接受任何合法种子,但常规的活跃会话分支需要围绕以下问题制定策略:哪些前缀可以被复制、子会话应打上哪些元数据、以及错误如何分类。 + +语义上的风险在于 fork 边界。一个合法的用户可见 fork 种子必须是连续的且封闭在轮次内。如果在一个活跃轮次内部 fork,会复制一个未关闭的 `turn/start`、可能还有一个未关闭的 `step/start`,以及可能悬空的工具调用。这违反了轮次封闭性与提供方 transcript 不变式,并且会创建一段误导性的子历史——看起来子会话参与了父会话中一个尚未完成的轮次。现有的 [subagent seam](2026-06-21-subagent-capability-seam.md) 有意解决的是另一个问题:工具触发的 subagent fork 通常发生在父轮次仍然打开时,因此 `dsh-subagent-fork` 会将种子裁剪到父会话最后一个已完成轮次的前缀。通用的会话 fork 不应静默裁剪;它应当要么在请求的边界处 fork,要么拒绝请求。 + +## 决策 + +`dsh-session` 直接在 `ctx.sessions` 上拥有常规活跃会话 fork 的能力。不设独立的 `dsh-session-fork` 包(package),也不设 `ctx.sessionFork` 服务:该 API 没有独立的后端、事件词汇、生命周期或持久化行为,所有持久化工作都委托给现有的会话存储和持久化后端。 + +store 暴露一个操作: + +```ts ignore-check +type SessionForkSource = Session | SessionId + +class SessionStore extends Service { + fork(source: SessionForkSource, boundary?: number, childSessionId?: SessionId): Session +} +``` + +`boundary` 是要复制到的源事件 `seq`(含该序号)。省略时默认为源会话当前的最后一个事件;对空源会话省略 `boundary` 则创建一个空的子会话。fork 特有的校验仅检查请求的边界是否存在且为 `turn/end`。选定的前缀随后被深拷贝到子会话的种子中。子会话继承源会话的 `cwd`,将 `parentSession` 设为源会话 id,并将 `seedLength` 设为已复制前缀的长度。省略 `childSessionId` 时,`SessionStore` 使用其现有的 id 策略生成一个。 + +空前缀可以被 fork;任何非空边界都必须是一个安全的、已存在的、位于 `turn/end` 的序号,无论结束原因为何。类型化的错误区分源缺失、对象陈旧、子 id 重复和边界无效等情况。更广泛的日志校验与崩溃恢复仍由其现有的负责方处理。 + +## 曾考虑的替代方案 + +**独立的 `ctx.sessionFork` 服务。** 这是最初的实现,但评审表明它过度套用了 capability-seam 模式。代码没有可替换的后端、没有额外的事件面、没有独立的所有权生命周期,也没有超出 `ctx.sessions.create({ seed, meta })` 的持久化行为。保留独立包会迫使调用方为了在会话存储原语之上执行一层策略而去发现并安装第二个服务。 + +**两个函数:`snapshot()` 加 `fork()`。** 这保留了一个可复用的种子/元数据计算,但唯一支持的消费方会立即创建会话。它还使接口看起来比用户实际需要的具体操作更抽象。单一的 `fork()` 加显式 `boundary` 使 API 保持直接,同时仍支持对先前时间点的 fork。 + +**静默裁剪未关闭轮次到最后一个已完成边界。** 这对 `dsh-subagent-fork` 是正确的——委托通常在父轮次仍然打开时开始,子会话应只继承已完成的前缀。但对常规的用户/会话分支而言是错误的,因为它隐藏了请求的 fork 点实际上不是合法边界这一事实,并且静默丢弃了父轮次的尾部。 + +## 后果 + +公开接口保持精简且易于发现:活跃会话分支是 `ctx.sessions` 的一部分,紧邻 `create({ seed })`,而非一个独立服务或一对两步辅助函数。持久化继续通过现有的 `session/created` 和 `session/flush` 行为运作:fork 出的子会话以种子事件开始生命,因此现有后端只需持久化该种子一次,并在 header 中保存 `parentSession`/`seedLength`。 + +v1 范围仍然排除 ACP(Agent Client Protocol) `session/fork`、对未加载的已持久化会话的 fork、面向模型的工具,以及 subagent 重构。如果未来添加 ACP 方法,应在具备 transcript(文本记录)/快照覆盖后才广播该能力;本 Agent Note 不添加面向编辑器的更新,因此当前不需要 ACP 快照。fork 子会话的回放仍由现有的[种子边界测试 Agent Note](../testing/2026-06-22-fork-child-replay-seed-boundary.md) 覆盖,而本 API 则获得专门的 `dsh-session` 单元测试加 JSONL 持久化覆盖。 diff --git a/.agents/notes/implemented/feature/2026-06-30-subagent-observe-enrich.i18n.yaml b/.agents/notes/implemented/feature/2026-06-30-subagent-observe-enrich.i18n.yaml new file mode 100644 index 0000000000..c7281e3189 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-06-30-subagent-observe-enrich.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-30-subagent-observe-enrich.md: a07cef95630689d1ca8cacd3eb7c50e691cb304a +2026-06-30-subagent-observe-enrich.zh.md: 578aae0a7273defcc1f88fb2a50c83ef454e3c16 diff --git a/.agents/notes/implemented/feature/2026-06-30-subagent-observe-enrich.md b/.agents/notes/implemented/feature/2026-06-30-subagent-observe-enrich.md index 861779fc50..a07cef9563 100644 --- a/.agents/notes/implemented/feature/2026-06-30-subagent-observe-enrich.md +++ b/.agents/notes/implemented/feature/2026-06-30-subagent-observe-enrich.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-06-30-subagent-observe-enrich.zh.md) + ## Problem The hooks subsystem ([interception seams Agent Note](2026-06-30-interception-seams.md)) lets a plugin observe and gate the agent at lifecycle points. Claude Code and Codex both expose **SubagentStart / SubagentStop** hooks, and CC's carry the subagent's final message. The harness already emits `subagent/start` and `subagent/end` lifecycle events ([the subagent capability-seam](2026-06-21-subagent-capability-seam.md)), but their payloads were minimal (`provider`, `id`, and on end `stopReason`) — not enough for a hooks bridge to report WHAT a subagent produced without separately reaching for the live run. diff --git a/.agents/notes/implemented/feature/2026-06-30-subagent-observe-enrich.zh.md b/.agents/notes/implemented/feature/2026-06-30-subagent-observe-enrich.zh.md new file mode 100644 index 0000000000..578aae0a72 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-06-30-subagent-observe-enrich.zh.md @@ -0,0 +1,31 @@ +# Agent Note: Subagent 生命周期丰富化——lastAssistantMessage(仅观察) + +Status: implemented + +[English](2026-06-30-subagent-observe-enrich.md) | 中文 + +## 问题 + +钩子子系统([拦截 seam Agent Note](2026-06-30-interception-seams.md))允许插件在生命周期节点观察和拦截 agent(智能体)。Claude Code 和 Codex 都暴露了 **SubagentStart / SubagentStop** 钩子,且 CC 的钩子携带 subagent 的最终消息。harness 已经发出 `subagent/start` 和 `subagent/end` 生命周期事件([subagent 能力 seam](2026-06-21-subagent-capability-seam.md)),但其载荷极为精简(`provider`、`id`,以及 end 时的 `stopReason`),不足以让钩子桥接层在不单独访问活跃 run 的情况下报告 subagent 产出了什么。 + +本 Agent Note 丰富 end 载荷。它刻意限定为**仅观察**:不改变控制流,不引入 waterfall(瀑布式事件)。影响 run 的 subagent-stop 决策(续行、改变 run 的注入)属于另一个更大的重设计,不在本 Agent Note 范围内。 + +## 决策 + +**在 `SubagentRunEndInfo` 中添加 `lastAssistantMessage`——子 agent 的最终输出。** 在正常结束路径上,它是只读的类型化 `SubagentResult.output`,观察者无需持有 run 即可看到子 agent 产出了什么。在基础设施拒绝(不存在 `SubagentResult`)的情况下,该字段缺失,事件报告 `stopReason: 'error'`。提供方与监听方是受信任的同进程协作者,遵守借用不可变载荷的契约。 + +两个事件仍为普通 **`emit`**。异步的 `SubagentService.start()` 将结果观察附加到就绪的提供方 run 上,发出 `subagent/start`,然后返回该 run;进程内监听方因此可以通过 `ctx.agents.get(info.id)` 访问已发布的子 agent,而远程提供方无需在本地注册表中有对应条目。提供方启动被拒绝时不发出任何事件。回调保持仅观察,且逐监听方隔离确保一个异常订阅者不会阻塞活跃 run 或饿死后续监听方。 + +## 曾考虑的替代方案 + +**`agentType` subagent 类别标签**(CC 的 `subagent_type` 在 harness 中的对应物),放在请求与两个生命周期载荷上。早期草案曾包含它;评审中移除,因为它是 Claude Code 的概念,不适合我们自己的 seam(此处没有任何逻辑解释它,唯一消费方是 CC 方言桥接层)。CC 桥接层改为直接为其 SubagentStart/Stop 的 `agent_type` matcher 填入 Claude Code 自身的默认值 `"general-purpose"`,因此本 Agent Note 只交付**一项**丰富化:`lastAssistantMessage`。 + +**控制流式 `subagent/end`**:推迟;见下文。 + +## 为何仅观察,以及推迟了什么 + +控制流式 `subagent/end`(一个被 await 的 waterfall,返回停止/继续决策,与其他拦截 seam 一致)需要:将 `subagent/end` 从 emit 改为 waterfall、重构 `SubagentService.start` 使其在结算前 await 监听方、在进程内提供方中实现 `resume` 能力以便「继续」能真正重新运行子 agent。这属于[能力 seam Agent Note](2026-06-21-subagent-capability-seam.md) 已推迟的后台/steering(中途引导)subagent 重设计(同一个重设计还将统一 subagent 与 bash 之间的长时间运行工具处理)。本 Agent Note 交付钩子桥接层当前所需的仅观察丰富化;`FIXME(subagent-continuation)` / `TODO` 锚点标记了控制流版本在重设计发生时的落点。 + +## 后果 + +钩子桥接层(或原生插件)现在可以通过订阅既有 emit 将子 agent 的 `lastAssistantMessage` 转发给 SubagentStop 处理器,无需新的控制流接口。词汇新增记录在 [docs/core-data-structures/subagent.md](../../../../docs/core-data-structures/subagent.md)(事件行文部分)与两个 subagent README 中;catalog 已重新生成。生产行为无变化——事件触发方式与之前完全一致,end 载荷上多了一个可选字段——因此无需更新快照或 e2e 测试。 diff --git a/.agents/notes/implemented/feature/2026-07-05-dynamic-workflows.i18n.yaml b/.agents/notes/implemented/feature/2026-07-05-dynamic-workflows.i18n.yaml new file mode 100644 index 0000000000..2b02053f05 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-05-dynamic-workflows.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-05-dynamic-workflows.md: 4c8606fb617b3fb6b2e8ad9c35d77c585b1fe8b1 +2026-07-05-dynamic-workflows.zh.md: 757eafb5d21f42b2ca529ebeb6b16eb8205e823d diff --git a/.agents/notes/implemented/feature/2026-07-05-dynamic-workflows.md b/.agents/notes/implemented/feature/2026-07-05-dynamic-workflows.md index fcd0b66062..4c8606fb61 100644 --- a/.agents/notes/implemented/feature/2026-07-05-dynamic-workflows.md +++ b/.agents/notes/implemented/feature/2026-07-05-dynamic-workflows.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-07-05-dynamic-workflows.zh.md) + ## Problem The harness can delegate ONE task to ONE child (`dsh-tool-subagent`), but work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — forces the model to orchestrate turn by turn: every intermediate result lands in the parent context, the plan lives nowhere durable, and coordination costs a model round-trip per step. Claude Code ships this capability as [dynamic workflows](https://code.claude.com/docs/en/workflows): the model writes a JavaScript orchestration script, a runtime executes it, and the script — not the conversation — holds the loop, the branching, and the intermediate results. diff --git a/.agents/notes/implemented/feature/2026-07-05-dynamic-workflows.zh.md b/.agents/notes/implemented/feature/2026-07-05-dynamic-workflows.zh.md new file mode 100644 index 0000000000..757eafb5d2 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-05-dynamic-workflows.zh.md @@ -0,0 +1,80 @@ +# Agent Note: 动态工作流——脚本驱动的多 agent 编排 seam + +Status: implemented + +[English](2026-07-05-dynamic-workflows.md) | 中文 + +## 问题 + +harness 可以将一个任务委派给一个子 agent(`dsh-tool-subagent`),但需要扇出到多个独立部分的工作——跨多文件审计、迁移、多角度调研、对抗式验证——迫使模型逐轮次编排:每个中间结果都落入父上下文,计划无处持久存储,每一步的协调都要消耗一次模型往返。Claude Code 以[动态工作流](https://code.claude.com/docs/en/workflows)的形式提供了这一能力:模型编写一段 JavaScript 编排脚本,运行时执行它,由脚本(而非对话)持有循环、分支和中间结果。 + +## 决策 + +在 `packages/workflow/` 下以 bash seam 的形态(接口/实现/消费方)提供一组工作流能力,以及它在 subagent seam 上所需的结构化输出基础。 + +### 脚本契约(兼容 Claude Code) + +一次工作流调用包含 JSON `meta`(`name`、`description`,以及可选的 `whenToUse`/`phases`)和一段支持顶层 `await` 并返回 JSON 值的 JavaScript `script` 正文。元数据作为数据校验,从不被执行。正文接收 `agent(prompt, options)`、`parallel(thunks)`、`pipeline(items, ...stages)`、`phase(title)`、`log(message)` 和 `args`。流水线各阶段接收 `(prev, item, index)`,阶段之间无屏障;失败的子 agent 和普通阶段错误将受影响的 item 解析为 `null` 并跳过其剩余阶段。Claude Code 的确定性限制通过日志化延迟处理,因此兼容的脚本正文在将 meta 头移入参数后可以使用时钟和随机数。 + +与 CC 有一处刻意的严格性差异:钩子误用——未知或延迟的选项(`effort`/`isolation`/`agentType`)、格式错误的参数、超出支持子集的 schema、触发上限、seam 启动失败——会抛出带 `fatal: true` 的 `WorkflowError`,组合器会重新抛出 fatal 错误而非将 item 置为 null。如果不这样做,一个拼错的选项会悄然变成一个与子 agent 失败无法区分的 `null`——这正是本仓库禁止的「被接受后被忽略」的失败模式。另有一处新增:工具的 `args` 参数是一个 JSON 对象(裸列表被包装为一个字段),使协议格式(wire format)保持诚实。 + +### seam(dsh-workflow) + +`ctx.workflows` 是 bash 形态的抽象 `WorkflowService`——每个上下文一个引擎,无命名提供方注册表(引擎是部署级替换,不是共存者)。`start(request)` 对无法启动的脚本同步抛出;返回的 `WorkflowRun` 的 `result` 永不 reject(失败解析为 `stopReason: 'error' | 'cancelled'`)。`workflow/*` 事件是仅观察的 emit,携带数据快照(id + meta;`workflow/end` 省略 result 值),按监听器隔离,与 `subagent/start`/`subagent/end` 对称——控制权留在 run 的持有者手中。词汇详情见 [core-data-structures/workflow.md](../../../../docs/core-data-structures/workflow.md)。 + +### 引擎(dsh-workflow-workerthread):每次运行一个 worker 线程 + +**信任前提**:工作流脚本与模型的 bash 访问具有相同的信任级别。引擎容纳有缺陷的脚本,并保证结果已 settled、值为 JSON 安全、取消后完全停稳;它不防御恶意代码。vm 上下文和 worker 线程不是安全边界:脚本可以逃逸到具有进程级权限的 Node API。沙箱化需要在此 seam 背后使用独立进程或 isolated-vm 引擎。 + +**为何选择 `node:worker_threads`**:每次运行获得一个非池化的 worker。vm 上下文限制了文档化的脚本表面,而消息端口 RPC 将 `agent()` 桥接到宿主侧的子循环。worker 防止脚本的同步工作阻塞宿主,提供序列化边界,并允许取消后强制终止。`isolated-vm` 因其维护状态和部署要求被否决。 + +宿主在发布前校验元数据并解析正文。私有枚举键 payload 映射定义协议格式;待启动记录、已发布子记录、单一取消信号、worker 死亡回收、结果优先级与 dispose 完全停稳,在此协议上保持 subagent run 契约。这些竞态算法归[agent 作用域运行时设计 Agent Note](../architecture/2026-07-12-agent-scope-runtime-design.md#workflow-children-are-pending-starts-or-published-records)所有。 + +引擎暴露一条进程内 `MessageChannel` 测试路径,因为主进程 V8 覆盖率无法观测 worker 执行。 + +**Meta 是数据**:经 schema 校验的 `meta` 字段以 JSON 形式到达 seam,仅做形状校验。宿主从不执行元数据字面量,否则脚本控制的访问器可以在 worker 隔离之外运行。 + +**值边界**:`materializeFromRealm` 复制出站值,并拒绝函数、symbol、嵌套 `undefined`、异域原型、循环引用、稀疏数组和非有限数字。数据属性复制使 `"__proto__"` 安全;getter 正常读取,抛出异常的 getter 会大声失败。`args` 通过 `workerData` 传入,暴露前再次克隆。realm 函数被调用而非复制,抛出的值使用全量渲染器,因此 `result` 不会 reject。钩子错误是宿主 realm 的 `WorkflowError`,脚本应基于 `name` 或 `code` 分支而非 `instanceof Error`,如引擎 README 所述。并发、total-agent、item、超时和宽限限制均为经校验的配置。 + +### 消费方(dsh-tool-workflow) + +一个 `workflow` 工具,镜像 `dsh-tool-subagent` 的同步形态:启动、await、`try/finally` dispose、abort 桥接 `exec.signal`、非 `completed` → `isError`。渲染意图:一张以调用的 `meta.name` 参数为标题的 `generic` 卡片(展示是参数的纯函数)。工具描述即面向模型的编写规范。使用策略以工具自身的 `tool:<toolName>` 提示词段落随工具发布(显式请求才使用的引导——工具引导存在于工具插件中,从不在部署 persona 中);harness 没有 ultracode 风格的 effort 门控。 + +### 基础:subagent seam 上的结构化输出 + +`SubagentStartRequest.outputSchema` 由 `dsh-subagent-inprocess` 为两个进程内后端实现。每个结构化子 agent 在 `child.ctx` 上获得自己的作用域捕获工具、指令和强制注册;并发子 agent 可以使用不同的 schema 而不共享可变策略,dispose 子 agent 时移除整个附件。 + +输出 schema 使一次 schema 有效的已提交捕获成为子 agent 成功完成的必要条件。作用域运行时呈现捕获工具和指令,仅提交成功的最终结果(包括 SDK 调用时外层 `run_code` 的结果),在捕获变为 pending 后拒绝后续副作用,并在提交后不再进行模型步骤即停止子 agent。校验失败仍是可重试的工具错误;没有已提交捕获的正常完成以错误结算。 + +`ObjectJsonSchema` 是 `dsh-tools` 统一且可强制执行的原始 JSON Schema 子集所提供的对象根消费方视图;不支持的关键字会大声失败,因为该协议数据会逐字成为捕获工具的 parameters。[统一 JSON 值 schema Agent Note](../architecture/2026-07-20-unified-json-value-schema-dsl.md)定义词汇与校验语义,[agent 作用域运行时设计 Agent Note](../architecture/2026-07-12-agent-scope-runtime-design.md#structured-output-commits-only-authoritative-outcomes)则定义组装、提交、守卫和终止停止算法。 + +## 测试 + +worker 侧逻辑通过进程内 `MessageChannel` 运行,使 V8 覆盖率能够度量它。单元测试覆盖脚本辅助函数、fatal 与 nullable 失败、JSON 边界、上限、取消、子 agent 所有权和通过真实循环的结构化输出。built-bin 冒烟测试在纯 Node 下运行单独打包的 `lib/worker.cjs`,带密钥的 e2e 驱动真实子 agent,面向模型的工作流行为通过其所属示例进行快照覆盖。 + +## 延迟(本轮明确的非目标) + +- **后台收集**(启动工具 → run id → 完成通知 → 收集),与 bash/subagent 后台统一一起设计。 +- **日志化 + 恢复**(`resumeFromRunId`、缓存的 agent() 前缀):实现它会以脚本契约收紧的形式重新引入 CC 的确定性禁令(脚本目前可以读取时钟)。 +- **保存/打包的工作流**(`.deepseek/workflows/` 注册表、斜杠命令界面)和**脚本持久化到运行目录**(工具调用事件已经持久记录了脚本)。 +- **嵌套 `workflow()`**、**token `budget`**,以及 `effort`/`isolation`/`agentType` agent 选项(每个都以命名延迟的消息大声拒绝)。 +- **整体运行的挂钟超时**:取消总能释放调用方(result 在宽限期内 settle),因此总运行时间上限是后台重设计的策略旋钮,不是此处的正确性需求。 +- **超越 worker 线程的引擎加固**:在同一 seam 背后使用 isolated-vm 或独立进程引擎(真正的沙箱化;内存限制)。 +- **ACP 进度 UI**(基于 `workflow/*` 事件的 `/workflows` 风格视图);事件已为此而存在。 +- **ACP 后端结构化输出**和 **`toolFilter`**(两者仍以能力标志 `false` 门控)。 + +## 曾考虑的替代方案 + +- **宿主侧的恶意值防护**(无 trap 代理拒绝、从不调用访问器的描述符遍历、realm 侧预渲染抛出值、realm 构建的 promise/array/error 克隆加结构化 fatal 识别):否决。每项防御针对的都是信任前提所接受的作者,而线程的序列化边界已经从构造上使跨 realm 值全量化。 +- **进程内 `node:vm` 执行**:机械上最简——无 RPC、无线程——但 `start()` 会在脚本的初始同步切片期间阻塞调用方,第一个 await 之后的同步自旋无法在进程内终止(vm `timeout` 仅覆盖第一个切片),且 `dispose()` 只能在宿主循环上放弃一个未 settle 的脚本。worker 线程引擎保持相同的 vm 上下文脚本表面,同时解除宿主阻塞并使终止成为现实。 +- **后台执行作为默认**(CC 的形态):延迟。前台同步与 `dsh-tool-subagent` 的当前形态一致,后台语义应在 bash、subagent 和工作流之间统一设计一次,而非逐工具设计。 +- **工作流层为 `agent({schema})` 做 JSON 解析**:在一个消费方重复 seam 关注点,而 seam 的能力标志仍不诚实地为 `false`。 +- **Meta 嵌入脚本中作为 `export const meta = {...}`**(CC 的确切格式):保持脚本自包含且 CC 脚本可直接使用,但获取 meta 需要在宿主上执行模型编写的文本。即使一个空的限时 vm 上下文也无法约束脚本控制的 getter(当宿主读取结果对象时)。JSON 参数消除了扫描器、执行和宿主自旋漏洞;代价是 CC 脚本的 meta 头必须移入参数(正文保持可直接使用)。 +- **`ValueSchemaSpec` 作为 `outputSchema` 协议类型**:面向作者的形式如今具有等价词汇,但工作流提供的是来自其他 realm 的原始 JSON Schema 数据;将这类运行时数据假装成可信的作者声明,会跳过原始 schema 断言边界。 +- **schema 对象库(zod 或本仓库的 schemastery)用于结构化输出子集**:schema 是协议数据——纯 JSON,跨越 `agent({schema})` 中的 vm realm 边界并逐字落入强制工具的 parameters——正是活 schema 对象无法存在的位置;在运行时消费原始 JSON Schema 需要在其上加一个第三方转换器(zod core 只输出 JSON Schema,不能反向),且会在 schemastery 的配置角色旁边放置第二种 schema 语言。 +- **ajv 用于值校验**:它校验完整 JSON Schema,因此子集门控——模块的真正要点,因为每个被接受的关键字都必须是 harness 强制执行的——无论如何仍需手写;它通过 `new Function` 编译校验器;且它将成为 dsh-tools 的第一个运行时依赖,仅为替换约 70 行的值遍历器,而路径限定的、报告每一处违规的错误报告无论如何都是自定义的。 +- **提供方 JSON 模式代替捕获工具**:它保证有效 JSON,不保证 schema 一致性,且它与工具调用的交互不明确。捕获工具保留了轮次内的校验重试。提供方侧的严格工具 schema 后续可以在不改变本设计的情况下收窄接受的子集。 + +## 后果 + +扇出计划现在存在于可重运行的脚本中,`outputSchema` 提供权威的结构化子 agent 结果。每次运行付出 worker 启动和消息端口 RPC 成本,但宿主启动保持非阻塞,取消可以终止 worker,序列化强制执行值边界。worker 线程不是安全边界。无效选项快速失败而非退化为 Claude Code 的 `null`;消费方通过 run handle 保持控制权,观察者仅接收快照。 diff --git a/.agents/notes/implemented/feature/2026-07-05-skill-system.i18n.yaml b/.agents/notes/implemented/feature/2026-07-05-skill-system.i18n.yaml new file mode 100644 index 0000000000..b5882ad5ea --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-05-skill-system.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-05-skill-system.md: 3c328adf09ab0f6ad3388a01bac3661d45c9247e +2026-07-05-skill-system.zh.md: ba30a3735b73b00afb46baa24f969fd687a759b5 diff --git a/.agents/notes/implemented/feature/2026-07-05-skill-system.md b/.agents/notes/implemented/feature/2026-07-05-skill-system.md index eccc58f7c2..3c328adf09 100644 --- a/.agents/notes/implemented/feature/2026-07-05-skill-system.md +++ b/.agents/notes/implemented/feature/2026-07-05-skill-system.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-07-05-skill-system.zh.md) + ## Problem Agent products have converged on a skill pattern: keep the request prompt small by listing only available instruction bundles, then load the full body when the model decides a task matches. Codex, Claude Code, OpenCode, and Kimi Code differ in details, but all separate discovery metadata from complete instructions so a workspace can carry reusable behavior without paying the full prompt cost on every turn. diff --git a/.agents/notes/implemented/feature/2026-07-05-skill-system.zh.md b/.agents/notes/implemented/feature/2026-07-05-skill-system.zh.md new file mode 100644 index 0000000000..ba30a3735b --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-05-skill-system.zh.md @@ -0,0 +1,55 @@ +# Agent Note: Skill 系统——面向 agent 的渐进式指令披露 + +Status: implemented + +[English](2026-07-05-skill-system.md) | 中文 + +## 问题 + +Agent(智能体)产品已趋同于一种 skill(技能)模式:保持请求提示词精简,仅列出可用的指令包,当模型判定某任务匹配时再加载完整正文。Codex、Claude Code、OpenCode 与 Kimi Code 在细节上各有不同,但都将发现元数据与完整指令分离,使工作区能承载可复用的行为而无需在每个轮次支付全量提示词开销。 + +DeepSeek Harness 使用同一原语,使项目特定的评审、插件编写和工具使用指南存放在工作区或用户的 agent 配置旁,而非硬编码到 agent loop(智能体循环)中。 + +## 决策 + +`@deepseek-ai/dsh-skill` 是纯提供方注册表(`ctx.skills`),`@deepseek-ai/dsh-skill-local` 是随附的本地文件系统提供方,`@deepseek-ai/dsh-tool-skill` 负责会话前缀目录与面向模型的 loader 工具。`dsh-agent-spine-demo` 默认加载注册表、本地提供方和消费方,使 stdio 与 ACP(Agent Client Protocol)应用获得相同行为,同时嵌入式或远程提供方可在不修改注册表或消费方的前提下贡献 skill。其 `skills` 配置将 `registry`、`local` 和 `tool` 分支分别转发给对应的所有者。 + +提供方插件在 `apply()` 期间同步注册。提供方成员资格是由直接 effect 持有的状态:注册与 dispose(资源释放)同步地使已完成的目录失效,发现操作按需读取当前提供方映射而非监听注册表变更事件。提供方目录从等待的 `list()` 调用返回排序后的候选项,远程提供方在此过程中执行初始化、认证和发现,同时遵守查找的 abort 信号。注册表校验每个候选项,按排名、提供方注册顺序和提供方内部顺序以先到先得方式解决同名 skill 冲突,然后按 skill 名称排序摘要以保证消费方获得确定性结果。它仅缓存已完成的目录快照,并在发现过程中提供方/运行时修订版本发生变化时重试,因此卸载操作不会将一个陈旧且不可解析的 skill 冻结到会话前缀中。运行时 `ctx.skills.register(...)` 仍作为嵌入式进程内 skill 的便捷方式保留,使用 project 优先于 user 的优先级;`runtime` 保留为注册表拥有的提供方名称。 + +本地提供方按先到先得的排名顺序扫描 cwd 敏感的项目根目录、自定义根目录和用户根目录:项目 `.dsh`、项目 `.agents`、`customSkillDirs`、用户 `.dsh`,然后是用户 `.agents`。用户 `.dsh/skills` 扫描跳过 `.system`,以免系统拥有的目录被当作普通用户内容处理。DeepSeek Harness 不随附内置系统 skill;嵌入式或远程提供方在配置后提供额外 skill。 + +每个 skill 是 `<name>/SKILL.md` 或带 YAML frontmatter 的 `<name>.md`。`name` 和 `description` 为必填;`whenToUse`、`disableModelInvocation` 和 `metadata` 为可选。名称采用 kebab-case。YAML frontmatter 使用 `yaml` 包(package)解析,而非 `js-yaml` 或手写解析器:`yaml` 是本包有限 frontmatter 需求已声明的现代解析器,窄解析器要么拒绝用户预期可用的合法 YAML,要么膨胀为一个未经评审的 YAML 子集。 + +本地 skill 的文件系统 I/O 在加载了文件系统服务时通过 `ctx.fs` 进行:项目根目录查找使用 `resolve` 和 `stat` 探测 `.git`,根目录发现使用 `listDir`,skill 读取使用 `readText`。Node 文件系统作为后备,供在不挂载 fs seam 的最小上下文中加载 `dsh-skill-local` 时使用。缺失的根目录、不可读或格式错误的 skill 文件、以及提供方 `list()` 的瞬态失败均降级为警告并跳过,使一个坏源不会导致所有 agent 请求失败;格式错误的候选项仍然快速失败,因为它们违反了提供方契约。 + +`dsh-tool-skill` 通过 [`agent/session-prefix`](2026-07-07-session-prefix.md) 贡献一个 user-role `<system-reminder>` 目录。该目录仅包含排序后的 skill 名称与描述;不包含正文、路径、来源、提供方和路由提示。描述经过空白规范化、XML 转义,并受 `catalogDescriptionMaxLength` 上限约束,其默认值为 `500`,最小值为 `3`。session-prefix seam 将仅用于请求的目录按 loop 实例冻结,并记录在请求头中,在不将其加入持久化历史的前提下保持可重建性。完整的 skill 正文从不包含在目录中。 + +`skill({ name })` 工具为当前 agent cwd 加载一个完整 skill,返回包含 `<skill_content name="...">`、`<skill_resources>` 和 `<skill_instructions>` 的工具结果。`resourceBase` 提供一个目录、URL 或不透明的提供方管理的基路径,用于显式引用的脚本、参考资料和资产;资源仅按需加载,不进行目录枚举。无法解析的名称报告该 skill 未知或不再可用;无效名称和标记了 `disableModelInvocation` 的 skill 保留不同的工具错误。工具结果是面向模型的可见披露路径。 + +数据结构与目录/工具契约记录在 [skills.md](../../../../docs/core-data-structures/skills.md) 中,服务签名见生成的[服务目录](../../../../docs/cordis-catalog/services.md)。 + +## 曾考虑的替代方案 + +**将完整 skill 正文注入每条系统提示词。** 否决,因为这破坏了渐进式披露,使每个请求都为可能不适用的指令付出代价。 + +**仅以斜杠命令暴露 skill。** 否决,因为模型主动加载是核心能力;斜杠/ACP 命令广播不改变发现机制。 + +**将本地文件系统扫描直接放入 `ctx.skills`。** 否决,因为编码 agent、Web agent 和未来的插件生态需要不同的 skill 来源。提供方注册表与 subagent seam 镜像:注册表拥有冲突解决和消费方,实现拥有加载。 + +**使用系统提示词段落。** 否决,因为渲染后的系统提示词是单一字符串,而目录是一条具有仅请求生命周期要求的 user-role `<system-reminder>` 消息。[`agent/session-prefix`](2026-07-07-session-prefix.md) 是选定的机制:它将目录置于派生历史之前,并将组合后的消息记录在请求头中。 + +**在 `~/.dsh/skills/.system` 下物化内置 DSH 编写 skill。** 否决,因为打包的 skill 不应在启动时写入用户主目录,嵌入式或远程提供方在配置后提供 skill。 + +**递归发现嵌套的 `**/SKILL.md`。** 否决。扁平文件和一级目录包覆盖了配置的根目录,同时使重复处理和目录顺序易于推理。 + +**手写 frontmatter 解析器。** 否决,因为已接受的 schema 包含一个开放的 `metadata` 对象。窄解析器要么拒绝用户预期可用的合法 YAML,要么膨胀为一个未经评审的 YAML 子集。 + +## 后果 + +agent-core 主干包含一个 session-prefix 贡献者、一个本地提供方和一个面向模型的工具。Skill 发现是 cwd 敏感的,因此以不同会话 cwd 值创建 agent 的调用方可以按设计观察到不同的项目 skill 覆盖。 + +目录对于固定的根目录集合和运行时注册修订版本是确定性的,但不监视磁盘变化;发现结果被缓存,直到运行时注册使缓存失效或进程重启。 + +## 延后 + +Fork 的 skill 上下文(`context: fork`)、参数声明与提示(`arguments` 和 `argument-hint`)、以及逐 skill 的工具约束(`allowed-tools` 和 `disallowed-tools`)不在已交付的契约范围内。注册表、本地提供方和面向模型的工具不解析、不广播、也不执行这些字段,`user-invocable` frontmatter 字段同样不会被解析。直接用户调用本身则作为消费方层面的能力交付:TUI 前门基于注册表现有的 `list()` 与 `get()` 方法提供手动 `/skill:<name>` 命令,无需变更注册表、提供方或工具契约——见 [TUI skill 斜杠命令](2026-07-21-tui-skill-slash-command.md)。 diff --git a/.agents/notes/implemented/feature/2026-07-06-approval-seam.i18n.yaml b/.agents/notes/implemented/feature/2026-07-06-approval-seam.i18n.yaml new file mode 100644 index 0000000000..ec785c65c4 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-06-approval-seam.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-06-approval-seam.md: e28587e0185530164f300562f7dd5e57255ac515 +2026-07-06-approval-seam.zh.md: 94ffb330cd36ae88975e8ae9d579b3b4606a5c25 diff --git a/.agents/notes/implemented/feature/2026-07-06-approval-seam.md b/.agents/notes/implemented/feature/2026-07-06-approval-seam.md index af063895e2..e28587e018 100644 --- a/.agents/notes/implemented/feature/2026-07-06-approval-seam.md +++ b/.agents/notes/implemented/feature/2026-07-06-approval-seam.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-07-06-approval-seam.zh.md) + ## Problem Two callers need to put one question — "may this specific action proceed?" — to a human: `tools/pre-execute`'s `ask` decision (including the Claude-Code hook bridge's `permissionDecision: ask`) and the [sandbox Agent Note](2026-07-06-sandbox.md)'s post-denial one-shot escalation retry. A shared seam keeps them from inventing separate outcome vocabularies, UI routing, cancellation, and audit trails, while guaranteeing that a deployment with no UI can never grant an unanswerable request. diff --git a/.agents/notes/implemented/feature/2026-07-06-approval-seam.zh.md b/.agents/notes/implemented/feature/2026-07-06-approval-seam.zh.md new file mode 100644 index 0000000000..94ffb330cd --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-06-approval-seam.zh.md @@ -0,0 +1,139 @@ +# Agent Note: 审批 seam——基于 waterfall(瀑布式事件)应答者的一次性权限决策 + +Status: implemented + +[English](2026-07-06-approval-seam.md) | 中文 + +## 问题 + +两个调用方需要向人类提出同一个问题——「这个具体操作可以继续吗?」:`tools/pre-execute` 的 `ask` 决策(包括 Claude-Code 钩子桥的 `permissionDecision: ask`)以及[沙箱 Agent Note](2026-07-06-sandbox.md) 中拒绝后的一次性升级重试。一个共享的 seam 使它们无需各自发明独立的结果词汇、UI 路由、取消机制和审计轨迹,同时保证没有 UI 的部署永远不会批准一个无法应答的请求。 + +路由问题的核心是归属:审批提示必须到达拥有发起请求的 agent(智能体)的编辑器会话(ACP(Agent Client Protocol)桥在一条连接上多路复用 N 个会话),对无人拥有的 agent(进程内 subagent、测试)失败关闭,并且不侵入没有组合 UI 的部署(headless、CI)。 + +## 决策 + +一个包 `dsh-user-approval`(`packages/ui/user-approval`),拥有词汇表和 `ctx.approval` 服务——即机制。策略——谁来应答、某个会话是否需要被询问——不在其中:应答者是 `approval/request` waterfall 监听器,由拥有通道的插件注册(ACP 桥、未来的终端 UI、测试脚本),而每会话的策略层可以在任何人类介入之前做出决定。消费方(`dsh-tools` 的 ask 路由、沙箱升级门禁)将问题解析为一个封闭结果,并从中派生各自的工具结果。刻意设计为一个包,而非能力 seam 的三包拆分(见「替代方案」)。 + +### 部署如何使用它 + +一条 `cordis.yml` 条目挂载该 seam。不加载它就是失败关闭的退出方式:消费方在没有注册任何审批代码的情况下拒绝无法应答的请求。 + +```yaml +- id: approval + name: '@deepseek-ai/dsh-user-approval' + # config: + # policy: never # deployment default for sessions without an override; 'ask' when omitted +``` + +仅有这条条目只提供机制,不提供通道:没有组合应答者时,每次 ask 都解析为 `unavailable`,发起请求的工具调用被拒绝——失败关闭无需配置。组合 ACP 应用(`@deepseek-ai/dsh-acp-demo`,如 [acp-agent 示例的默认树](../../../../examples/acp-agent/README.md))即可闭环:其桥注册一个应答者,通过 `session/request_permission` 向拥有该会话的编辑器发出提示,于是钩子的 `ask` 或升级请求会以一次性 Allow/Reject 提示的形式呈现,附着在已流式输出的工具调用上。`policy: never` 是无人值守姿态:每次 ask 确定性地自动拒绝,在系统提示词中声明,无人类参与。`policy` 在插件加载时对照封闭列表校验;非法值直接抛异常。 + +组合部署的可观测行为:`allowed-once` 仅允许该次调用继续;拒绝、关闭和通道缺失以三种不同原因拒绝,模型可以区分;轮次内成功的请求会在发起请求的 agent 的会话日志上落一对持久的 `approval/asked`/`approval/decided` 事件;授权不会在发起请求的调用结束后继续存在。空闲时的请求或审计追加失败会拒绝,而不会返回未经审计的决策。 + +以下是该组合下的一次 ask,逐字取自沙箱示例录制的 `escalation-approved` 场景——模型请求沙箱升级,门禁发起 ask,桥向拥有该会话的编辑器发出提示,用户点击 Allow once: + +``` +tool/call bash {"command": "printf 'escalated\n' > escalated.txt && cat escalated.txt", + "sandbox_permissions": "workspace-write", + "justification": "the user asked to write escalated.txt in the workspace"} +approval/asked {"toolName": "bash", "callId": "call_00_…", + "reason": "escalate sandbox to workspace-write: the user asked to write escalated.txt in the workspace"} + → session/request_permission {"toolCall": {"toolCallId": "call_00_…"}, + "options": [{"optionId": "allow-once", "name": "Allow once", "kind": "allow_once"}, + {"optionId": "reject-once", "name": "Reject", "kind": "reject_once"}]} + ← the user picks "Allow once" on the prompt the editor attaches to the streamed bash call +approval/decided {"outcome": "allowed-once"} +tool/result "escalated" — this one call ran under the wider mode; the grant died with it +``` + +`escalation-rejected` 孪生场景以 `{"outcome": "rejected"}` 结束:不执行任何操作,模型的结果携带发起方的逐字失败关闭文本(`the user rejected escalating this command to "workspace-write"`)。钩子的 `permissionDecision: ask` 走完全相同的协议;只有发起方和拒绝文本不同(§ dsh-tools 中的 Ask 路由)。在 headless 环境下,同一请求完全跳过提示,直接结算为 `unavailable`。 + +### 设计细节 + +#### seam:机制与策略分离 + +经过校验并成功追加 `approval/asked` 后,服务将 `approval/request` waterfall 解析为 `allowed-once`、`rejected`、`cancelled` 或 `unavailable`。服务借用只读的请求标识和 signal,将中止视为 `cancelled`,把应答者失败和无效返回容纳为 `unavailable`,丢弃迟到的应答,并追加配对的 `approval/decided` 事件。提交前的审计失败会拒绝;追加后的观察者失败无法撤销权威事件。`allowed-once` 仅授权所询问的操作,而 `request()` 会拒绝打开轮次之外的调用,以保证审计对留在持久提交边界内。 + +应答者是 `approval/request` waterfall 监听器。零监听器会一路委派至 `unavailable`;识别该 agent 的监听器占用先到先得的决策槽,而不识别的监听器必须调用 `next()` 委派。监听器随其 fiber dispose,因此卸载通道会失败关闭。由于兄弟插件的注册顺序不确定,部署应组合一个终端应答者,并保留 `prepend` 给「决策或委派」门禁。 + +`ApprovalRequest` 携带发起请求的 `agent`、`toolName`、可选的精确 `callId`、人类可读的 `reason` 和可选的 `signal`。它使用 `CallId` brand 而不导入依赖本 seam 的 `dsh-tools`。工具参数仍留在 UI 通过 `callId` 引用的、已流式输出的调用上。 + +#### dsh-tools 中的 Ask 路由 + +`ToolRegistry.execute()` 在派发前解析 `ask`:`allowed-once` 继续执行,而拒绝、取消和通道不可用产生三种不同的拒绝原因。机会性消费 `ctx.get('approval')`,让缺失或未挂载的服务失败关闭而不阻塞注册表 fiber。无 agent 的执行同样失败关闭,因为它既没有审计会话,也没有 UI 所有者。 + +#### 每会话策略层 + +seam 还拥有[沙箱 Agent Note](2026-07-06-sandbox.md) 所描述的会话级 `'ask' | 'never'` 策略。生效策略由日志中记录的切换在部署默认值之上折叠而成。`'never'` 会在任何应答者运行之前,于 `request()` 内部解析为 `rejected`;`'ask'` 则派发请求,否则一路委派至 `unavailable`。提示词仅声明确定性的 `'never'`,切换叙述会被合并,每个请求仍记录审计对。 + +#### ACP 应答者 + +ACP 桥只应答其正向会话映射所拥有的精确 agent 对象。它把 `session/request_permission` 附着到既有 `callId`,声明一次性的 allow/reject 选项,单独映射取消,并且绝不批准未知选项。外部或无调用标识的请求会委派;客户端 RPC 失败变为 `unavailable`。钩子和 `tools/pre-execute` 决定一次调用是否需要询问。 + +应答者通过 [ACP 支持 Agent Note](2026-06-14-acp-agent-client-protocol.md) 描述的桥精确 agent 归属检查进行路由,实现了[多会话 Agent Note](2026-06-14-acp-multi-session.md) 要求的每会话权限归属。 + +#### 审计,以及模型看到什么 + +`approval/asked` 和 `approval/decided` 是持久的仅日志事件;模型只看到从结果派生出的普通工具结果。成功完成时,每个 `asked` 都提交一个 `decided`,包括取消和被容纳的应答者失败。空闲时的请求不追加任何事件;提交前失败会拒绝,而第二次追加失败可能留下一个已经提交但未匹配的 `asked`。 + +#### 实体与依赖 + +`dsh-user-approval` 依赖 Cordis,以及会话、agent 和带 brand 的调用契约;`dsh-tools` 与 `dsh-acp` 消费它。沙箱执行器保持独立,因为升级请求归 `dsh-tool-bash` 所有。固定的派发与审计服务仍是一个包;可替换的应答者留在各自的通道所有者中。静态能力授权和 `subagent-acp` 子侧权限应答仍是独立关注点。 + +### 测试 + +单元测试固定结果、先到先得的委派、错误容纳、取消、作用域路由、审计配对、不可绕过的 `'never'` 策略、工具拒绝原因,以及通过真实脚本化桥实现的 ACP 归属/结果映射。 + +快照记录通过 `session/request_permission` 批准和拒绝沙箱升级,以及 `'never'` 提示词与策略切换通知。没有脚本化应答的权限提示会取消并失败关闭。 + +## 延后 + +- **`allow_always` 授权存储**:兑现持久授权意味着设计存储、作用域标识(调用?路径?前缀?会话?时间窗口?)和撤销;在设计完成之前,只展示一次性选项([沙箱 Agent Note](2026-07-06-sandbox.md) § Escalation 记录了开放的作用域问题)。 +- **通过组合应答者录制由钩子驱动的 `ask`**:人类提示协议格式已通过沙箱示例的升级分支录制。钩子矩阵中的 `hook-cc-pretool-ask` 固定无 ApprovalService 时的后备拒绝,而钩子生产者与应答者的组合仍留在单元测试层。 +- **将子 agent 的审批路由到父会话**:`subagent-acp` 的子侧自动应答自己的 `permission` 请求;将其呈现给父会话的编辑器是独立的设计。 + +## 曾考虑的替代方案 + +- **单一注册提供方而非 waterfall 监听器**:否决。`registerProvider()` 接口迫使所有组合问题——允许列表预过滤、外部钩子决策者、脚本化测试应答、人类前面的策略门禁——都塞进一个提供方实现。waterfall 从运行时已有的机制中获得组合能力、缺失时失败关闭和 HMR(热模块替换) dispose(资源释放);seam 的 JSDoc 以约定固定单决策槽语义,而非发明一个提供方注册表。 +- **在 ACP 桥中内联 `tools/pre-execute` 权限门禁**:否决。对桥拥有的每次调用都弹出提示,会将请求策略硬编码进 UI 插件,无法服务第二个发起方(沙箱升级发生在执行开始之后,没有 pre-execute 时刻),且钩子产生的 `ask` 决策没有共享机制。 +- **通用用户交互 seam(`ctx.userInteraction`)**:否决作为审批机制。二者骨架相似(按 agent 路由、阻塞等待人类、处理缺失),但审批的契约在每个关键维度上都更窄:封闭的结果词汇而非自由文本、附着在工具调用上的协议原生提示而非通用表单、强制的缺失时失败关闭、以及审计事件。因此审批不走已交付的 `packages/ui/user-interaction` / `ask_user_question` 引出路径——引出表单不是权限提示,自由文本应答不是封闭结果;如果二者将来趋同,共享提供方管道仍然开放。 +- **`dsh-tools` 中的静态可选注入**:否决。vendor 的 Cordis `Inject` 类型没有 optional 标志——对象形式将服务名映射到拦截配置,声明的 inject 会阻塞 fiber。`ctx.get('approval')` 是文档化的机会性消费模式(`tool-bash` 的 owner-token 查找、loop 的持久化探测),按调用读取存在性,跨 HMR 正确降级,无需额外机制。 +- **能力 seam 的三包拆分**:否决。接口/实现/消费方适合实现可替换的 seam(bash-local vs bash-sandbox)。此处服务体是固定机制,可变部分是留在各自通道拥有者插件中的监听器——拆分只会制造一个空的实现包(「不要预防性拆分」)。 +- **现在就提供 `allow_always`**:否决。协议能表达它,但兑现它意味着设计授权存储、作用域标识和撤销(§ 延后)。展示 harness 无法兑现的选项只会制造注定失败的授权。 + +## 后果 + +实现后的契约由「测试」一节所列套件固定: + +- `allowed-once` 派发一次操作;其他所有结果都以不同原因拒绝,而 `'never'` 会在提示前拒绝。 +- 缺失、外部、无 agent、抛异常、无效或断开连接的应答路径都会失败关闭。 +- 成功的请求按精确 agent 归属路由,并追加一对可回放、对模型不可见的审计事件;空闲时和提交前失败的请求会拒绝。 +- ACP 归属把提示限制在其会话内,而没有该服务的部署不产生提示或审计事件。 + +代价与已接受的局限: + +- **两个急于决策的应答者竞争同一槽位。** 兄弟插件的监听器顺序不确定,seam 无法仲裁竞争的终端应答者。通过约定缓解(每个部署一个终端应答者;仅对「先决策或委派」门禁使用 `prepend`),而非事件总线不具备的优先级机制。 +- **生产环境验证依赖单一组合。** `ask` 有两个生产者家族——钩子桥通过 `tools/pre-execute`,沙箱升级通过自己的门禁——协议格式录制在沙箱示例的快照套件中;因此在更多部署组合它之前,seam 的真实覆盖面就是这一种组合。 +- **归属以 `Agent` 对象标识为键。** 应答者先在 `agent.session.id` 处解析正向会话映射记录,再要求该记录拥有精确的 agent 对象;当前所有路径在 loop 和各 seam 之间传递同一对象,但未来如果某个边界克隆或代理了 agent,桥会委派并失败关闭——安全,但静默无 UI——届时需要另一种归属契约。 + +## FAQ + +- **在完全没有应答者的部署中(headless、CI)会发生什么?** 每次 ask 穿过空的 waterfall 降级为 `unavailable`,工具调用以「no approval channel is available」原因被拒绝。失败关闭是零监听器的默认行为,不是配置。 +- **授权能持久化吗——「始终允许」?** 不能。`allowed-once` 仅授权单次被询问的操作,服务在请求之间不存储任何内容;`allow_always` 在授权存储设计完成之前刻意不展示(§ 延后)。 +- **模型看到审批的什么?** 只看到发起方从结果派生的工具结果——审计对永远不进入 transcript(文本记录)。三种非授权原因各不相同,模型可以区分人类说「不」、提示被关闭、通道缺失。 +- **谁决定一次调用是否需要 ask?** 策略生产者:返回 `permissionDecision: ask` 的钩子、任何 `tools/pre-execute` 监听器、或沙箱升级门禁。seam 和桥只负责路由和应答;二者都不注入自己对「什么值得弹出提示」的判断。 +- **用户关闭提示或轮次在 ask 进行中中止时会发生什么?** 关闭映射为 `cancelled` 并携带自己的拒绝文本。已中止的 signal 直接结算为 `cancelled` 而不派发;ask 进行中的中止丢弃迟到的应答。当两个审计追加都提交时,任一路径都记录恰好一对事件,绝不会两对。 +- **如果客户端以 harness 从未提供的选项应答呢?** 除已提供的 `allow_once` 之外的任何选项都映射为 `rejected`——来自不合规客户端的未知 optionId 永远不能授权。 +- **subagent 的审批如何路由?** 没有应答者拥有的 agent 穿过整个 waterfall 委派并失败关闭——进程内 subagent 被刻意设计为不可应答。`subagent-acp` 的子侧自动应答是独立的;将子 agent 的 ask 路由到父会话的编辑器已延后(§ 延后)。 +- **`policy: 'never'` 在运行时实际改变了什么?** 服务在派发任何应答者之前,将该会话的每次 ask 解析为 `rejected`(在服务内部,因此没有注册顺序能绕过它);系统提示词声明该策略;切换在边界处被叙述;每次成功的自动拒绝都会记录审计对。 +- **热重载或 UI 插件在会话中途卸载时会发生什么?** 应答者随其拥有的 fiber 一起 dispose,因此下一次 ask 降级为 `unavailable` 而非挂在死通道上;重新挂载会重新注册应答者,无需追赶状态。 +- **用户在哪里看到自己在批准什么?** 在工具调用本身:提示通过 `callId` 附着在已流式输出的调用上(包含参数),并添加发起方的人类可读 `reason`;请求本身不携带参数副本。 + +## 先例 + +本设计复用或对照的仓库内先例: + +- `fs/write-intent` 门禁(`packages/fs/fs/`)——文档化的单占用决策槽 waterfall 语义(先到先得,通过 `next()` 委派),应答者契约复用了它。 +- `hook/invoked`/`hook/result`——仅日志审计对先例,`approval/asked`/`approval/decided` 沿用了它;[钩子桥 Agent Note](2026-06-30-hook-bridges.md) 交付了 `permissionDecision: ask`,即第一个生产者。 +- [拦截 seam Agent Note](2026-06-30-interception-seams.md)——`tools/pre-execute` 的 `allow`/`deny`/`ask` 词汇,本 seam 服务其中的 `ask`。 +- [ACP 支持 Agent Note](2026-06-14-acp-agent-client-protocol.md)——应答者路由时对正向会话映射执行的精确 agent 归属检查;[多会话 Agent Note](2026-06-14-acp-multi-session.md)——本设计实现的每会话权限归属阻塞项。 +- 机会性 `ctx.get()` 消费模式(`tool-bash` 的 owner-token 查找、loop 的持久化探测)——`dsh-tools` 消费该 seam 而不阻塞其 fiber 的方式。 diff --git a/.agents/notes/implemented/feature/2026-07-06-explicit-tool-order.i18n.yaml b/.agents/notes/implemented/feature/2026-07-06-explicit-tool-order.i18n.yaml new file mode 100644 index 0000000000..1c1ae2daf2 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-06-explicit-tool-order.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-06-explicit-tool-order.md: bd6d0a04aa470ca33e618957ae1f08c1ef15fcfe +2026-07-06-explicit-tool-order.zh.md: 5cdecc0e59ff00b6dce7134819f8230072d084cb diff --git a/.agents/notes/implemented/feature/2026-07-06-explicit-tool-order.md b/.agents/notes/implemented/feature/2026-07-06-explicit-tool-order.md index c78126e92a..bd6d0a04aa 100644 --- a/.agents/notes/implemented/feature/2026-07-06-explicit-tool-order.md +++ b/.agents/notes/implemented/feature/2026-07-06-explicit-tool-order.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-07-06-explicit-tool-order.zh.md) + ## Problem Model-facing tool order followed plugin registration order, which depends on concurrent module loading for otherwise independent plugins. That race produced different request headers in CI and snapshot recordings. Because order affects request bytes, caching, and the durable header, it needs an explicit deterministic policy. diff --git a/.agents/notes/implemented/feature/2026-07-06-explicit-tool-order.zh.md b/.agents/notes/implemented/feature/2026-07-06-explicit-tool-order.zh.md new file mode 100644 index 0000000000..5cdecc0e59 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-06-explicit-tool-order.zh.md @@ -0,0 +1,51 @@ +# Agent Note: 显式的模型侧工具顺序 + +Status: implemented + +[English](2026-07-06-explicit-tool-order.md) | 中文 + +## 问题 + +模型侧的工具顺序此前跟随插件注册顺序,而注册顺序取决于相互独立的插件的并发模块加载。这种竞态在 CI 和快照录制中产生了不同的请求头。由于顺序影响请求字节、缓存和持久化的 header,因此需要一个显式的确定性策略。 + +## 决策 + +系统提示词的组装逻辑拥有模型侧工具顺序的权威定义,正如它已经拥有 section 顺序的权威定义一样。`dsh-system-prompt` 上的 `toolOrder?: string[]` 是可选的显式策略: + +- 列表中已注册的工具按列表位置排列。 +- 列表中的名称没有对应的已注册工具,属于配置错误。形状错误(缺少 rest 条目或名称重复)在服务构造器中快速失败;未注册的名称则在每次 `assemble()` 时拒绝——这是已注册工具集存在并可供检查的最早时刻(工具插件在服务构造之后才注册),也是唯一的通用时刻(注册随时可能变化;Cordis 没有「所有插件已加载」事件)。在已交付的 agent loop(智能体循环)下,第一个轮次在发出任何模型请求之前就会失败——确切的影响范围见下文「后果」。 +- 已注册但不在列表中的工具,插入到 `'<unlisted-tools>'` rest 条目(`TOOL_ORDER_REST`)的位置,与其他未列出的工具按名称字典序排列。 +- 任何已收集的工具不得使用 `TOOL_ORDER_REST` 作为其 `ToolSchema.name`;组装逻辑在排序之前就会拒绝这个保留名称。 +- 列表必须恰好包含一个 rest 条目,且不得有重复名称。 +- 当 `toolOrder` 未设置时,权威顺序为纯字典序(code-unit 比较,与 locale 无关),因此无需配置即可保证确定性。 + +`assemble()` 在 `system-prompt/assemble` waterfall(瀑布式事件)之前对提供方工具进行规范化排序,从源头消除注册顺序的差异。waterfall 从这个确定性列表开始;不变的顺序随后流入请求头、冻结的请求和重建检查,无需 loop 特有的排序逻辑。 + +范围刻意收窄:本 Agent Note 修复的是注册顺序竞态,而非插件行为。`system-prompt/assemble` 的监听器仍然可以添加、移除或重排工具——正如它可以在 section 排序之后编辑 section——并对自身输出的确定性负责;waterfall 契约已经要求监听器是确定性的(可重建性不变式会捕获在构建与回放之间行为不一致的监听器)。 + +配置传递沿用 `persona` 的先例,`toolOrder` 与之并列:TUI、Headless 和 ACP 应用配置接受该键,并通过 `dsh-agent-spine-demo`(其 schema 是各所有者 schema 的交集)转发给 `SystemPrompt` 子服务。有一个 schemastery 细节至关重要:schemastery 数组默认为 `[]`,但省略的 `toolOrder` 必须保持 ABSENT(= 字典序),而不是变成一个显式配置的空列表(无效——缺少 rest 条目),因此链路上每个 schema 都将默认值强制为 `undefined`。 + +## 曾考虑的替代方案 + +- **注册顺序(现状)**:并发导入竞态,依赖宿主环境(上述 CI 抖动),评审中不可见。 +- **插件依赖图的线性化**:该关系是偏序的,独立的工具插件不可比较;抖动发生时偏序已完全满足。 +- **每个插件在其工具贡献上标注 `weight`**:将顺序分散到各插件中,仍需一个无人拥有的全局编号约定(section 的 `order` 分段已经展示了这种协调成本需要手工承担)。 +- **在 `ToolRegistry.schemas()` 中排序(注册表层)**:同样确定,但注册表是一个成员存储,被组装之外的多方消费;排序是提示词组合的关注点,而组装逻辑已经拥有 section 的组合策略。 +- **在 `LlmService` 上加配置 + `orderTools()` 方法,由 loop 在记录 header 前调用**:可行,但仅为在远处应用一个策略就增加了一个公开服务方法和一处 loop 改动;每个未来的请求组合者都必须记得调用。在列表诞生处进行规范化使得无序列表不可表示,且零新增接口。 +- **在 `llm.stream()` 内部规范化**:在 header 事件已记录之后才运行(抖动仍然存在),且需要重建深度冻结的信封,静默地解除了重建不变式。 +- **穷举列表(无 rest 条目)**:每个新加载的工具插件都会导致启动失败;强制的 rest 条目使未列出的工具保持确定性,且其位置是显式的。 +- **启动时校验(由 `dsh-app-boot` 在 `loader.await()` 之后调用 `SystemPrompt.assertToolOrderSatisfied()`)**:能将错误配置变为启动时死亡而非首轮次失败,但代价是一个公开服务方法加上通用启动胶水对单个服务的结构耦合,且无法替代组装时检查(嵌入式调用者从不运行 app boot;注册在 boot 之后仍会变化)。也没有现成事件可以承载该检查:Cordis v4 没有 ready 类事件,`loader/entry-init`/`internal/status` 在加载中途触发(与工具注册存在竞态——正是本 Agent Note 要消除的熵源),而 agent 生命周期事件不会早于组装。在 `assemble()` 设置单一执行点被判定值得接受较晚的失败时刻。 + +## 后果 + +- 每个由注册表构建的组装在任何宿主上都以确定性工具顺序开始;在没有专家监听器刻意改变的情况下,每个 `request/header` 事件和模型请求都继承该顺序。CI 与本地之间的注册顺序翻转从结构上被消除,默认为字典序。 +- 初始 `PromptAssembly.tools` 是权威的,因此 waterfall 监听器从模型侧顺序开始;提供方注册顺序在该协作 seam 之前无处可观测。 +- 快照套件中唯一固定请求头的 fixture(`text-turn`)携带新的权威工具顺序;按照固定请求头设计,其他 ACP 快照仍将大块 header 清洗为 `{{system}}`/`{{tools}}`。 +- 步骤之间的纯工具重排与其他 header 变更一样记录:一份原因是 `'change'` 的完整 `request/header` 快照。稳定的权威顺序会防止注册时序在普通路径上制造这类变化。 +- `toolOrder` 键沿 app → `agent-core` → `SystemPrompt` 的转发链传递,因此部署时将其放在 app 配置中 `persona` 旁边即可;`dsh-llm` 和 agent loop 无需改动。 +- `toolOrder` 中拼错或未加载的工具名称在提示词组装时使轮次失败,而非启动时:loop 在轮次内部组装(`turn/start` 之后、`step/start` 之前),因此拒绝到达轮次的外层 catch——轮次以 `error` 原因平衡关闭并携带错误消息,`agent/error` 镜像该消息,不打开步骤,不记录 `request/header`,不向适配器发出请求,agent 回到空闲状态。每个轮次都以相同方式失败,直到配置被修正;进程本身保持运行(符合仓库规则:显式配置引用不得被静默忽略——执行点是组装,因为不存在更早的通用时刻)。 +- 工具提供方返回保留的 rest 条目名称时,其提示词组装失败形态与未知的已列名称相同。这防止哨兵值变成一个歧义的真实工具,并保持「从不丢弃工具」的排序契约。 + +## 测试 + +系统提示词测试覆盖:字典序默认顺序、列表/rest 位置、提供方顺序无关性、共享名称、无效列表、未知或保留名称、waterfall 前的权威列表,以及监听器添加的工具不被重新排序的规则。Loop 测试固定:跨注册排列的已记录与已分发顺序一致、通过 agent-core 和两个 app 的转发、深度冻结的请求,以及在配置了未知名称时的平衡轮次失败(无步骤、无 header、无适配器调用)。快照回放仅在固定的 `text-turn` header 中保留完整的权威列表;其他 fixture(测试前置数据)继续使用 `{{tools}}`。 diff --git a/.agents/notes/implemented/feature/2026-07-06-sandbox.i18n.yaml b/.agents/notes/implemented/feature/2026-07-06-sandbox.i18n.yaml new file mode 100644 index 0000000000..287deaff20 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-06-sandbox.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-06-sandbox.md: c1307a7201ed1bc331a86d4ffee002d69fd1d5e5 +2026-07-06-sandbox.zh.md: 4e3d4951f71a602bc78551c90dda04317d0f8284 diff --git a/.agents/notes/implemented/feature/2026-07-06-sandbox.md b/.agents/notes/implemented/feature/2026-07-06-sandbox.md index 507142fac9..c1307a7201 100644 --- a/.agents/notes/implemented/feature/2026-07-06-sandbox.md +++ b/.agents/notes/implemented/feature/2026-07-06-sandbox.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-07-06-sandbox.zh.md) + ## Problem A coding agent needs this product path: bash subprocesses — and the hook commands that ride them — execute under a restricted file sandbox by default; if and only if the sandbox actually denies an operation, the model may request one user approval for that same operation and, once granted, retry it once with wider permissions. An every-tool boundary is deliberately NOT the claim: fs/web/todo execute in-process where an `execve` wrapper is meaningless (§ In-process tools), and the cross-family boundary is staged follow-up work (§ Deferred phases). Without a shared vocabulary, every tool reinvents approval fields, denial parsing, retry matching, and permission-state hints. diff --git a/.agents/notes/implemented/feature/2026-07-06-sandbox.zh.md b/.agents/notes/implemented/feature/2026-07-06-sandbox.zh.md new file mode 100644 index 0000000000..4e3d4951f7 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-06-sandbox.zh.md @@ -0,0 +1,207 @@ +# Agent Note: 子进程沙箱——约束 seam、原生 runner、升级机制与按会话模式 + +Status: implemented + +[English](2026-07-06-sandbox.md) | 中文 + +## 问题 + +一个编码 agent 需要如下产品路径:bash 子进程(以及依附其上的钩子命令)默认在受限的文件沙箱下执行;当且仅当沙箱实际拒绝了某个操作时,模型可以为同一操作请求一次用户批准,获批后以更宽的权限重试一次。本设计刻意不声称覆盖所有工具:fs/web/todo 在进程内执行,`execve` 包装对它们毫无意义(§ 进程内工具);跨工具族的统一边界属于分阶段后续工作(§ 延迟阶段)。如果没有共享词汇,每个工具都会各自重新发明批准字段、拒绝解析、重试匹配和权限状态提示。 + +harness 是一个 SDK,因此约束必须是开发者可组合的能力:是否启用沙箱、每个平台使用哪个后端,都应作为一等条目写在叶子 `cordis.yml` 中,而非藏在某个执行器的私有机制里。而首选 runner `bwrap` 恰恰在沙箱最重要的主机上不可用(精简容器、禁用了非特权 userns、LSM 拒绝 `mount`),因此备选 runner 必须随 SDK 一起交付,而不能假设主机已有。 + +仅有约束还留下两个缺口。拒绝后没有升级路径就是死路:模型只能放弃,这会迫使运维人员全局配置 `workspace-write` 或 `danger-full-access`,从而使沙箱形同虚设。而模型可见的旋钮(沙箱模式、批准策略)在 agent 生命周期内会变化——ACP 用户切换按会话设置、运维人员在进程停止期间编辑 `cordis.yml`——模型绝不能基于过时的信念行动:每次请求时的实际状态是什么、agent 存活期间发生了什么变化、无人看管时又发生了什么变化,都需要有明确答案。 + +## 决策 + +一个 seam、一条按平台的本地后端链、一个消费方,加上两个上层杠杆:按调用的升级路径与按会话的运行时模式。以下所有内容均从叶子 `cordis.yml` 组合而来;不触及 `agent-loop`。跨工具族 fs 强制与按会话工作区根目录已经作为后续设计落到同一策略载体上;剩余阶段——`subagent-acp` 消费方、更多环境与 Windows 链——仍列在 § 延迟阶段。 + +### 部署方式 + +四条 `cordis.yml` 条目即可将一个无约束的编码 agent 转变为沙箱产品路径;[`examples/acp-agent`](../../../../examples/acp-agent/README.md) 默认使用此组合: + +```yaml +- id: sandbox + name: '@deepseek-ai/dsh-sandbox-local' # the per-platform runner provider (ctx.sandbox) +- id: bash + name: '@deepseek-ai/dsh-bash-sandbox' # the confined executor, replacing dsh-bash-local behind ctx.bash + config: + mode: workspace-write # the deployment default every session starts from + workspaceRoot: !!js process.cwd() # the boundary workspace-write may write under +- id: approval + name: '@deepseek-ai/dsh-user-approval' # the escalation gate's channel (the approval Agent Note) + config: + policy: ask +- id: permission + name: '@deepseek-ai/dsh-permission' # one product-facing select over both mechanism knobs +``` + +这一替换对 `ctx.bash` 的所有消费方透明:bash 工具、钩子命令和后台任务照常运行,通过提供方返回的包装 argv spawn。删除 `sandbox` 和 `permission` 条目、将 `bash` 替换为 `@deepseek-ai/dsh-bash-local` 即为退出——执行恢复为无约束,升级字段从工具 schema 中消失,因为它们是基于已挂载执行器的能力门控,而非基于配置。仅省略 `approval` 则保留约束但以自身错误文本关闭每次升级;`permission` 还要求 approval seam 和约束执行器同时存在,因此部分组合的 preset 层在加载时即大声失败。 + +配置错误大声失败:`mode` 不在封闭词汇中时在插件加载时被拒绝;主机上没有可用后端时在 `confine()` 阶段(命令 spawn 之前)抛出结构化的 `SANDBOX_UNAVAILABLE`,而非降级为无约束执行。`dsh-sandbox-local` 上的 `runnerCommand` 是运维人员对一个 bwrap 兼容 runner 的显式断言(跳过链和探测);它同时充当 keyless 测试的确定性 fake-runner seam。 + +被拒绝的文件操作返回 `[sandbox: file access denied under <mode> mode]` 标记,并附带不要绕过拒绝的指令。约束执行器添加配对的 `sandbox_permissions` 和 `justification` 字段,用于一次经批准的重试,该重试必须严格宽于会话的有效模式。授权仅放宽该次重试;拒绝则不执行任何内容,返回 `the user rejected escalating this command to "<mode>"`,且不允许再次请求。提示词不声明沙箱模式,以避免基于常驻标签的预防性拒绝。当 `dsh-permission` 被组合时,ACP 暴露一个 `Permissions` 选择器,其 preset 同时写入两个旋钮事件;不匹配的旋钮组合显示为仅可切换离开的 `custom`。只有切换到确定性的 `'never'` 批准策略才会在提示词中声明并叙述。 + +### 设计细节 + +#### 范围界定 + +OS 子进程约束适用于 bash 执行器(包括钩子命令),后续还将适用于 ACP subagent 子进程。文件系统、web 和其他工具在进程内执行,需要在各自的 seam 层面实施策略;argv 包装无法约束一个闭包了 `ctx` 的函数。既有的 bash request/spec 拆分承载按调用的覆盖,而 `tools/pre-execute` 和 approval seam 负责人的决策。 + +#### seam:`ctx.sandbox` + +`dsh-sandbox` 拥有词汇和 `SandboxProvider` 契约:`confine(argv, policy)` 返回调用方应当 spawn 的替代 argv(经过包装,使进程及其所有子进程在约束下运行),加上所选后端达到的 `enforcement` 完整度、其拒绝方言(`denialSignatures`,该后端内核在拒绝文件操作时打印到 stderr 的子串)、以及其 runner 失败方言(`runnerFailureSignatures`,runner 本身失败——因而命令从未运行——时的自我标识方式);没有可用后端时抛出失败关闭的 `SANDBOX_UNAVAILABLE` 错误,绝不静默放行。词汇:`SandboxMode`(`read-only` / `workspace-write` / `danger-full-access`,仅限文件操作——不声称覆盖网络和进程可见性)、`SandboxEnforcement`(`full` / `partial`)、`SandboxExecutionPolicy`(每次能力调用的完整 mode + workspace root)以及 `SandboxPolicy`(提供给约束后端的子集)。 + +策略随每次调用而非提供方携带:两个消费方可以在同一时刻以不同策略约束(bash 在 `read-only` 下运行,而一个受约束的子 agent 保持其状态目录可写),且经批准的升级重试是一次带有更宽策略的新调用——在配置固定的提供方模式下无法表达。 + +该 seam 仅约束与宿主机共享文件系统和内核的子进程。容器、microVM 和远程执行器不是此 seam 的后端——它们以环境一致的组替换整个能力实现(`ctx.bash`、`ctx.fs`),因为一个 bash 在容器中运行而 fs 工具写主机的 agent 生活在两个割裂的世界中。 + +留待需要时再决定:网络限制是作为独立的 `network_mode` 到来,还是在某个 runner 同时强制两者后合并进 `sandbox_mode`;以及 `SandboxPolicy` 是现在就增加额外的可写根授权(launcher 已支持 `--rw <path>`),还是等到升级机制需要时再加。 + +#### 本地后端与随附 launcher + +`dsh-sandbox-local` 在提供方生命周期内选择一个平台 runner 并缓存结论。Linux 功能性探测 `bwrap` 然后 Landlock;macOS 使用 Seatbelt。不支持的平台和不可用的 runner 失败关闭。每次包装携带后端特定的拒绝签名和 runner 失败签名,以便 `dsh-bash-sandbox` 区分被拒绝的文件操作与损坏的沙箱。`runnerCommand` 作为运维人员对 bwrap 形状 runner 的断言跳过选择,但缺失或不可执行的命令仍被归类为沙箱失败,绝不无约束地运行负载。 + +launcher 是一个约 300 行的 C 程序(纯 C11,直接使用 Landlock UAPI——除静态链接的 musl 外无其他库,因此审计面仅为该文件加内核的稳定 syscall 契约):`--ro <path>` / `--rw <path>` 授权,`--`,被包装的 argv;它在自身上安装规则集并 `exec`(规则集跨 `execve` 继承,且它在限制前设置 `no_new_privs`);`--probe` 在一个短生命周期子进程中强制最大规则集,仅当内核确实强制时才以 0 退出;launcher 失败以 125 退出且不 exec。 + +Landlock launcher 源码和包工作区位于 `native/landlock-run`,与 harness 消费方同仓。独立的 [`node-addon-landlock-run`](https://github.com/deepseek-harness/node-addon-landlock-run) 仓库是用于打包并发布 npm 包族的发布镜像;导出流程归 `native/README.md` 所有。平台二进制由 npm 选择,入口包拥有路径解析、探测和 CLI flag,而 harness 将沙箱模式映射为授权。将入口点与其二进制一起版本化,使探测解析和启动语法保持对齐。 + +后端 profile 共享模式契约但在必要的主机授权上有所不同。Landlock 和 Seatbelt 在 read-only 模式下仅允许 `/dev/null`;workspace-write 还允许各自所需的主机临时目录根。每次包装携带后端特定的拒绝签名。Landlock 在较旧的 ABI 无法管控所有操作时报告 partial enforcement,而成功的 bwrap 和 Seatbelt profile 报告 full enforcement。 + +#### bash 消费方 + +`dsh-bash-sandbox` 扩展 `LocalBashExecutor`,并把即将 spawn 的确切 `['bash', '-c', command]` argv 交给 `ctx.sandbox`。拒绝是与其他结果正交的事实,依据当前 runner 的 stderr 方言保守分类。Runner 失败优先于拒绝:前台执行抛出 `SANDBOX_UNAVAILABLE`;结算后的 `BashProcess` 会盖章 `sandbox.runnerFailed`,bash 生产者再通过通用 `task_output` 渲染它。 + +模型看到的仅是结果事实:静态工具描述解释拒绝标记(`[sandbox: file access denied under <mode> mode]`),鼓励尝试可能被拒绝的命令,并禁止绕过拒绝重试;当升级字段被公布时,被拒绝的结果还额外携带升级提示本身,使被认可的同轮次重试在决策点被提示,而非依赖模型回忆描述(§ 升级机制)。没有提示词段落声明沙箱模式(§ 按会话模式)。 + +#### 升级机制:拒绝后一次经批准的更宽重试 + +`BashExecRequest.sandboxPolicy` 是可选的完整按调用输入;解析后的 spec 使该字段显式。`BashExecutor.sandboxMode` 仍是公布已挂载执行器能否兑现该策略的能力事实,因此只有约束组合才暴露升级。seam 接受任何显式策略;工具拥有会话解析和「仅更宽」的升级规则。非沙箱执行器诚实地保持无约束。 + +`ctx.sandboxPolicy.resolve()` 在执行器运行前盖章完整执行策略——显式升级模式 > 会话覆盖 > 配置默认值,且 `SessionHeader.cwd` > 配置的后备根目录。`SandboxBashExecutor.resolve()` 在 spec 上保留该策略,或为直接的无 agent 调用方提供部署后备值,使 `run()`/`start()` 永不读取可变会话状态。每进程包装事实以返回的 `BashProcess` 为键;`onProcessDone()` 在 `done` 结算前分类 stderr 并给该句柄盖章,因此重叠进程各自保留自己的模式和 runner 方言。 + +当约束执行器被挂载时,`bash` 公布配对的 `sandbox_permissions` 和 `justification` 字段。schema 暴露完整的封闭升级词汇,因为有效模式是按会话的;执行拒绝任何不严格宽于该调用有效模式的目标。批准在执行之前解析。`allowed-once` 仅将授权模式盖章到该请求上,而 `rejected`、`cancelled`、`unavailable`、缺失的 approval 服务或缺失的 agent 都以各自不同的结果文本失败关闭。授权不持久化。 + +升级是对被拒绝命令的同轮次重试,使用最窄的足够 `sandbox_permissions` 和一个 `justification`;批准提示是同意步骤。它必须基于实际的拒绝,除非会话已观察到相同的被拒绝访问;禁用或被拒绝的批准终结该命令。重试、批准决策和结果使用既有的工具和批准事件。`dsh-tool-bash` 拥有请求动作,因为执行器 seam 既没有 agent 也没有用户交互所需的 call id。 + +仍未决定:持久授权超出沙箱模式之外的作用域标识是什么——确切调用、路径、命令前缀、会话或时间窗口——这是公布 `allow_always` 选项之前必须回答的问题。 + +#### 按会话模式:会话日志即存储 + +``` +effective(session) = findLast(the session's own knob events)?.value ?? the composition-config default +``` + +默认值是组合配置(`cordis.yml`)——运维人员拥有,进程范围。运行时切换是会话范围的覆盖,记录为该会话自身日志中的一条仅日志事件。重启免疫(恢复会话时回放其日志,覆盖自然恢复,无需追赶机制)和多会话隔离(一个编辑器标签页的 `workspace-write` 不会干扰另一个的 `read-only`)都是构造性的自然结果,且不存在任何外部配置存储。 + +**每个旋钮一种事件,由其领域拥有**——这是每个既有事件族已遵循的可合并扩展 `SessionEventMap` 惯用法(`dsh-user-approval` 中的 `approval/*`、hooks 包中的 `hook/*`): + +```ts +interface SessionEventMap { + 'sandbox/mode': { mode: 'read-only' | 'workspace-write' | 'danger-full-access' } + 'approval/policy': { policy: 'ask' | 'never' } +} +``` + +每个拥有者导出相同的三件套:事件声明、纯 fold(`effectiveSandboxMode(events)` / `effectiveApprovalPolicy(events)`——一个 `findLast`,类型化到领域的封闭联合),以及唯一的写入路径(`setSandboxMode(session, mode)` / `setApprovalPolicy(session, policy)`——切换即其事件;没有任何东西在带外修改状态)。无共享拥有者服务、无通用 facts map、无注册表:第三个旋钮只需将约 40 行模式复制到自己的包中。执行在两侧都遵循 fold——bash 工具的按调用盖章将其作为 § 升级机制优先级链的中间层读取,approval seam 的 `'never'` 门控是[批准 Agent Note](2026-07-06-approval-seam.md) 同一模式的另一侧。 + +沙箱模式不在提示词中叙述;拒绝结果在需要时报告模式,避免基于常驻标签的预防性拒绝。批准策略不同:只有 `'never'` 被声明,因为自动拒绝在行为上与用户的「不」无法区分。策略变更通知被合并,由下一个步骤前检查点递送,重启后有基于日志的回退。通知来源从事件位置推断:最后一个 request header 之后的旋钮事件是用户驱动的;未记录的漂移是运维人员或配置驱动的。 + +**编辑器界面**是协议原生的[会话配置选项](https://agentclientprotocol.com/protocol/session-config-options)——该规范对 session modes 的替代(计划在 ACP v2 中移除),已有 SDK 类型。当 `ctx.permission` 被组合时,bridge 在 `session/new` 和 `session/load` 中公布一个 `permission` 选择器(category `mode`);其选项是部署的 preset 表,其 `currentValue` 是 `PermissionService.current()` 对会话日志加组合默认值的结果。随附的 `workspace-write` 和 `danger-full-access` preset 各自捆绑一个沙箱模式与一个批准策略,并写入两个领域 setter;preset 表之外的旋钮组合报告为仅可切换离开的 `custom`。`session/set_config_option` 通过权限服务验证并切换,然后返回完整的刷新状态(规范契约)。 + +**轮次封闭是提交边界。** 开放轮次中的切换立即追加。空闲切换保持在 bridge 记录上待定,在下一次提示词提交时、assembly 或执行之前追加到开放轮次中;每个旋钮以最后写入为准。开放性来自日志边界而非 `agent.status`,setter 不从 `session/event` 监听器内追加,因为那会重排后续观察者。锚定之前,响应叠加待定值。崩溃丢弃它,重新加载返回持久 fold。 + +#### 进程内工具 + +fs/web/todo 在进程内执行,因此它们的沙箱语义是各自 seam 层面的策略。fs seam 现在通过沙箱提供方强制共享模式词汇(`dsh-fs-sandbox` 按模式限制 write/edit;见[跨工具族 fs 沙箱 Agent Note](2026-07-14-cross-family-fs-sandbox.md)),因此 `read-only`/`workspace-write` 对文件系统工具也是真实边界,而非仅限 bash 的近似。web/todo 仍不受限制(web 的唯一效果是网络,不在文件效果模式词汇内)。没有通用的按工具沙箱运行时:主机中介的工具仅通过返回主机验证的声明式效果来离开进程,那是一次重写而非包装——后续设计选择了一个共享策略归属 `ctx.sandboxPolicy`,由各 seam 强制,而不是统一包装器。 + +### 测试 + +- **单元测试:** 固定平台选择和 profile、失败关闭的 runner 分类、按调用的模式/根目录解析、按进程事实、升级验证和结果、权限 preset fold 和写入透传、叙述器合并、ACP 公布和验证、轮次封闭的配置写入。 +- **Keyless 真实 runner:** 在提供方和 bash 消费方层面对 bwrap、Landlock 和 Seatbelt 执行真实文件系统效果测试;一个真实 Cordis 上下文通过已交付的 bash 和 fs 工具并发驱动两个项目会话,证明在自身根目录写入成功、在兄弟根目录写入被拒绝。Packed-install 覆盖率证明注册表 launcher 保持可执行。真实 ACP 组合固定权限切换并拒绝未知 preset。CI 拒绝静默全跳过。 +- **With-key:** 以只读模式启动真实 ACP 组合,让模型驱动的 bash 写入命中 runner 的拒绝标记,再通过已授权与被拒绝的 workspace-write 重试驱动 bridge 应答器和磁盘效果;不可用的凭证或 runner 自动跳过。 +- **快照:** 固定权限 config-option 协议格式(wire format)、preset 和旋钮事件、提示词 delta 和通知、以及两个脚本化的 approval 分支。一个真实 ACP 示例场景把会话放在用户主目录下,同时让部署后备根目录指向 `/tmp`,然后固定一次成功的 workspace-write 变更;这能区分会话根目录解析与进程后备值,而不依赖 runner 特定的拒绝文本。其他快照以无约束启动,使无关 fixture(测试前置数据)保持平台无关;策略场景显式切换。 + +## 延迟阶段 + +每个阶段在被拾起时获得完整设计,对照当时的代码验证,并在其涉及的层级带上单元测试、真实 API e2e 和快照覆盖率落地。 + +- **第二个消费方**——`subagent-acp` 可选地约束子 agent(按调用策略;默认无约束——子 agent 必须写入自己的持久化)。 +- **更多环境**——环境一致的能力组示例(如 bash+fs 对一个容器)。 +- **Windows 链**——`PLATFORM_CHAINS.win32` 保留为空(失败关闭);填充它意味着来自 AppContainer/restricted-token 家族的约束 runner,从其自己的仓库按 `node-addon-landlock-run` 模板交付,加上其 profile 方言和拒绝/runner 失败签名。 + +## 曾考虑的替代方案 + +- **命令字符串启发式预检**:否决。无法理解展开/子进程/符号链接;严格尝试(运行它,让内核决定)是唯一可信的拒绝信号。 +- **即使平台仅有一个后端也功能性探测**:否决。探测用于在候选者之间仲裁;只有一个时无需决策,且探测开销对每个会话的首次约束命令征税(对未来重量级后端而言代价过高)。runner 自身执行时的失败关闭拒绝加 `runnerFailureSignatures` 分类承载了安全属性。 +- **提交构建好的 launcher 二进制**:否决。diff 中的二进制不可审查且膨胀历史;经审查的源码 + 原生 CI 构建 + launcher 仓库的字节固定发布演练使二进制远离所有代码树。 +- **安装时编译 launcher**:否决。将 C 工具链强加给每个消费方;仅在碰巧有编译器时才存在的备选不是备选。 +- **从一个构建器交叉编译两种架构**:否决。仅为重建两个约 70 KB 的二进制就需要携带一个固定的交叉工具链(rustup targets、zig 或容器镜像);每架构的原生 runner 已存在,各自构建自己的平台包(`node-addon-require-builtin` 模式,launcher 仓库自己的流水线)。 +- **无备选(bwrap 或失败关闭)**:否决。将失败集中在沙箱最重要的主机上,最终因放弃而降级到 `danger-full-access`。 +- **将机制保留在 `dsh-bash-sandbox` 内部**:否决。阻塞既有的第二个消费方,使未来阶段从一个 bash 插件的配置中读取模式,且无法表达升级。 +- **提供方上的配置固定模式**:否决。每进程一个模式;无法服务具有不同策略的并发消费方,也无法表达一次性放宽重试。 +- **一个接口同时覆盖容器/VM**:否决。`confine(argv)` 预设共享文件系统;环境隔离是作为一致组部署的能力兄弟后端。 +- **通用 ToolRuntime 包装任何工具**:否决。对进程内工具(闭包了 `ctx`)机械上不成立;声明式效果重写对 fs/web/todo 而言不合理。 +- **在执行器内部(`dsh-bash-sandbox`)请求批准**:否决。没有可路由的 `agent`,没有可附加提示词的 `callId`;添加它们会让传输 seam 了解会话和 UI——工具层持有两者并拥有面向模型的词汇。 +- **同一工具调用内自动重试**:否决。日志无法重建的隐藏重入:一个 `tool/call` 会产生两次具有不同策略的执行——重试是一次新的带有自身参数和结果事实的已记录调用。 +- **无条件公布升级字段**:否决。在 `dsh-bash-local` 下它们是死杠杆——公布 harness 无法兑现的选项会制造注定失败的授权;能力门控仅需注册时一次读取。 +- **默认值相对的升级阶梯(仅公布比执行器注册时默认值更宽的模式)**:否决。按会话覆盖使默认值成为错误的基线——切换到比默认值更窄的会话恰恰失去它需要的杠杆,而在 `danger-full-access` 默认值下字段完全消失,同时一个被覆盖为 `read-only` 的会话仍处于约束中却没有升级路径。枚举固定封闭的目标词汇;严格放宽是针对会话有效模式的按调用执行检查。 +- **按会话动态工具 schema**:否决。schema 设计上是注册表全局的(一套 assembly 词汇、固定 header 快照契约),按会话重新注册只能买到执行时严格放宽检查已保证的东西,代价是按会话的 schema 表面和每次切换的 header 变动。 +- **将重试硬匹配到先前的拒绝**:否决。命令字符串同一性脆弱(引号、`workdir`、env 前缀、作为失败阶段重试的管道)——要么误拒诚实的重试,要么被轻易满足;真正的边界是人看到命令 + 理由。仅在 `allow_always` 授权存储需要机器可检查的范围时才重新考虑。 +- **通用 `env/state` facts map 加拥有者服务**:否决。approval 和沙箱独立组合,因此任何一方的状态都不应拖入第三个包;单键 fold 各自是一个 `findLast`,拥有者服务自然消解;没有跨旋钮的不变式,因此原子多键补丁无收益。 +- **通过 `agent/user-message` + 总线事件叙述**:否决。它预设了一个不存在的轮次入口 seam(真正的 seam 是 `agent/prompt-submit`),而步骤前检查点的位置使一个监听器能够同时服务合并的轮次入口通知和轮中即时性约束。 +- **提示词中常驻声明沙箱模式(+ 切换叙述器)**:先交付后移除,基于实际证据:当每个请求中都有 `Bash commands run under the "read-only" file sandbox.` 时,模型拒绝尝试被拒绝后可升级的工作(首次手动会话中十二个轮次有五个以零工具调用结束),将沙箱变成了软锁定。拒绝标记在需要时命名模式,升级字段承载恢复路径;批准旋钮保留其声明,因为自动拒绝在行为上与人的「不」无法区分。 +- **用专门的簿记事件追踪「上次告知」**:否决。`request/header` fold 已记录模型看到的确切提示词;将封闭的候选句子解析回来替代了第二条簿记流——事件仅在它们本身即为存储时才需要。 +- **ACP session modes 而非 config options**:否决。preset 已经是一个部署定义的 config-option 选择器,且 modes 计划在 ACP v2 中移除。 + +## 后果 + +已交付并固定的内容——测试中的各层级分别保障: + +- 被拒绝的命令以 `sandbox_permissions` + `justification` 重试时,通过组合的应答器链提示用户;授权使该次调用在更宽模式下运行(结果事实如此报告),而其他所有调用保持各自的有效模式;每种非授权结果产生各自不同的错误文本且不执行任何内容。 +- 升级字段恰好在已挂载的执行器约束时存在;不严格宽于调用有效模式的请求以自身文本失败关闭且不提示任何人;没有 ApprovalService 的部署对升级调用失败关闭,对普通调用不影响。 +- 系统提示词从不声明沙箱模式(批准 `'never'` 策略是唯一被声明的旋钮),且整个交互——header、旋钮事件、通知、批准、结果——仅从会话日志即可重建,除两个旋钮事件外无额外事件类型。 +- N 次空闲切换每个旋钮最多产生一个锚定事件(净零序列不锚定任何事件——客户端回显当前选择的无操作推送不记录任何内容);批准策略切换最多以一条合并通知叙述;轮中沙箱切换由下一次调用的盖章兑现。 +- 恢复的会话的覆盖生效并报告给编辑器,无需特殊处理;进程停止期间变更的默认值在会话的首个新请求前被叙述,归因于运维人员。 +- 两个并发会话永远看不到彼此的状态、通知或配置选项。 +- 同一个 Cordis 上下文中的两个并发项目会话解析各自独立的工作区根目录;bash 和 fs 写入在调用方会话的 cwd 内成功,对其相邻会话的 cwd 则失败。 +- `agent-loop` 未被触及——一切搭载 `systemPrompt.section`、`SessionEventMap` 合并、`agent.inject()`、`agent/pre-step`、`agent/prompt-submit` 和 ACP handler 表面。 + +代价与已接受的限制: + +- **单一包装的幻觉被有意放弃。**`tools/pre-execute` 包装加提示词约定无法解决沙箱批准——正确的设计需要结构化拒绝、原生 runner 探测、按调用策略承载和一致的跨工具族强制,本设计为此付出了代价。 +- **`read-only` 通过后续设计成为跨工具族边界。** 本 Agent Note 最初只交付 bash 强制;[跨工具族 fs 沙箱 Agent Note](2026-07-14-cross-family-fs-sandbox.md) 通过沙箱化的 `ctx.fs` 提供方把同一模式词汇扩展到文件系统工具,并将 mode/root 配置和 `sandbox/mode` 覆盖迁移到 `ctx.sandboxPolicy`(§ 进程内工具)。 +- **Windows 没有后端。** 其链槽保留为空——失败关闭,绝不穿透;填充它是延迟阶段。 +- **Seatbelt 层级依赖 Apple 已弃用但仍交付的 `sandbox-exec` CLI。** 作为 darwin 的唯一候选,它无需探测即被选中,因此未来移除会在执行时作为 runner 失败分类浮现——重新抛出 `SANDBOX_UNAVAILABLE`,命令从未运行;失败关闭,绝不开放。 +- **Landlock 约束的完整度取决于运行内核的 ABI。** 报告为 `enforcement: 'partial'` 而非拒绝——这是有意的权衡,使备选在旧内核主机上仍可用。 +- **launcher 作为注册表依赖到达。** 通过其自身仓库的发布流水线(经审查的 C 源码、原生 CI 构建器、字节固定的发布演练)加上本仓库的版本固定获得信任——真实内核 e2e 测试腿是通过安装字节为行为背书的。 +- **模型可能过度请求。** 在没有拒绝依据的情况下升级,或在 `workspace-write` 足够时选择 `danger-full-access`:描述引导且枚举强制阶梯,但人的提示词是实际门控;`approval/asked` 原因使过度请求可审计,且 `prepend` 策略应答器可以自动拒绝部署永远不想要的模式。 +- **公布的目标集是静态的,而有效模式是按会话的**(schema 是注册表全局的)——已处于最宽模式的会话仍被提供这些字段。构造上无害:执行时的严格放宽检查(而非枚举)是安全边界——非放宽请求以自身文本失败且不提示任何人。 +- **授权的升级不等于可工作的沙箱。** 不可用的后端即使对授权升级到约束模式也仍然失败关闭——在平台没有链或所有探测失败时于 `confine()` 阶段,在未探测的唯一 runner 拒绝时于执行阶段(归类为沙箱失败而非命令失败)——而授权的 `danger-full-access` 运行根本不触及提供方:此时授权(而非探测)是权威。 +- **空闲切换存在于 bridge 内存中,直到下一次提示词提交锚定它。** 该窗口内的崩溃将其回退(在 `session/load` 时报告),且永不再提交提示词的会话永不持久化它——已接受,loop 拥有的空闲提交轮次留作未来工作(如果持久性成为需求)。 +- **批准叙述器的重启基线解析提示词文本。** 封闭的候选句子由写入模块本身拥有,因此措辞变更是同一文件中写入器+解析器的协调编辑;header 早于该段落的会话静默采用当前策略而不发通知。 +- **批准段落仍是动态提示词表面**(`'never'` 切换会破坏该会话的提供方提示词前缀缓存)。已接受:策略切换罕见,且模型基于过时的 `'never'` 行动更糟。沙箱旋钮不再触及提示词。 +- **模型可能持有关于沙箱模式的过时信念**(没有任何东西宣布切换)。有意接受:下一次尝试的标记或成功会纠正它,而宣布的观察到的失败模式——预防性拒绝——比一次浪费的重试更糟。 + +## FAQ + +- **一个命令返回了 `[sandbox: file access denied under read-only mode]`——它失败了吗?** 它运行了,内核拒绝了一个文件操作:拒绝是与退出码正交的结果事实。教学禁止绕过它重试;唯一被认可的动作是以升级请求重试同一命令一次。 +- **如何区分损坏的沙箱与失败的命令?** Runner 失败在分类中优先于拒绝:匹配包装的 `runnerFailureSignatures` 的失败运行意味着命令从未运行——前台重新抛出结构化的 `SANDBOX_UNAVAILABLE` 并附带 runner 的 stderr 行,后台任务盖章 `sandbox.runnerFailed` 并渲染自己的标记。损坏的沙箱永远不会被读作失败的命令,且命令永远不会无约束运行。 +- **在没有后端的平台上会发生什么——今天的 Windows?** `confine()` 抛出失败关闭的 `SANDBOX_UNAVAILABLE`,命令永不 spawn;`win32` 是保留的空链,由测试固定为同样失败关闭,直到 Windows runner 填充它(§ 延迟阶段)。 +- **`bwrap` 已安装在我的主机上但不可用(禁用了非特权 userns、LSM 拒绝 `mount`)——会发生什么?** 链探测是功能性的——它构建并强制一个真实 profile 而非检查 `--version`——因此存在但不可用的 `bwrap` 探测失败,选择落到注册表安装的 Landlock launcher,结论在提供方生命周期内缓存。 +- **沙箱限制网络或进程可见性吗?** 不——`SandboxMode` 仅声称文件操作;bwrap profile 刻意不 unshare pid,没有后端声称网络。网络限制是否成为自己的旋钮留在 § seam 中开放。 +- **哪些工具实际在约束下运行?** 通过 `ctx.bash` 的 OS 子进程——bash 工具及传递性的钩子命令——再加上通过沙箱化 `ctx.fs` 提供方运行的文件系统工具(`read`/`write`/`edit`,见[跨工具族 fs 沙箱 Agent Note](2026-07-14-cross-family-fs-sandbox.md)):bash 通过 OS runner 约束,fs 通过进程内路径围栏约束,二者都以同一个 `ctx.sandboxPolicy` 模式为键。web/todo 仍在进程内且不受限制(web 的唯一效果是网络,不在文件效果模式词汇内)。 +- **授权的升级会持久化吗?** 不会。授权由发起请求的确切前台或后台调用消费;每个相邻调用保留自己的有效模式。后续的后台拒绝通过 `task_output` 呈现,并且可以作为一次新的精确命令重试的依据。 +- **编辑器的模式切换何时生效?** 轮中:立即追加,由下一次调用的盖章兑现。空闲:保持在 bridge 的会话记录上,在下一次 `agent/prompt-submit` 时锚定到其开放轮次中,N 次切换合并为最多一个事件(净零则无);锚定前崩溃回退它,`session/load` 报告真实状态。模型不被告知——其下一个命令直接在新模式下运行。 +- **重启后什么存活——如果运维人员在进程停止期间改了配置默认值呢?** 覆盖从会话日志回放(`effective = fold ?? config`),因此恢复的会话以零追赶机制保持其模式;离线漂移的默认值以与切换相同的方式改变行为(批准策略因被声明,还额外以运维人员/配置归因叙述)。 +- **结果上的 `enforcement: 'partial'` 是什么意思?** 所选后端强制其内核 ABI 管控的子集——例如 ABI v3 之前的 Landlock 不管控路径 truncate——并以结构化方式如此声明而非拒绝主机;探测的报告行区分各种情况。bwrap 和 Seatbelt profile 构造上管控所有承诺的文件操作,因此始终报告 `full`。 + +## 先例 + +本设计复制或对比的仓库内先例: + +- [能力 seam Agent Note](../architecture/2026-06-13-capability-seams.md)——接口/实现/消费方拆分与「不要过早拆分」的时机规则(第二个消费方满足了该规则)。 +- `dsh-bash` 的 request/spec 拆分([bash 词汇目录](../../../../docs/core-data-structures/bash.md))——完整的 `sandboxPolicy` 搭载其按调用载体,以及显式 `resolve()` 默认约定。 +- [批准 seam Agent Note](2026-07-06-approval-seam.md)——升级请求通过的通道;其应答器 waterfall(瀑布式事件)、审计对和单包理由记录在那里。 +- [事件溯源会话](../architecture/2026-06-11-event-sourced-sessions.md)与[轮次封闭不变式](../architecture/2026-06-15-turn-enclosure-invariant.md)——按会话模式 fold 所依赖的日志即存储基础,以及锚定设计遵守的提交边界。 +- [拦截 seam Agent Note](2026-06-30-interception-seams.md)——`tools/pre-execute` 词汇,升级门控刻意不复用它(升级调用没有自己的 pre-execute 时刻)。 diff --git a/.agents/notes/implemented/feature/2026-07-07-mcp-client-plugin.i18n.yaml b/.agents/notes/implemented/feature/2026-07-07-mcp-client-plugin.i18n.yaml new file mode 100644 index 0000000000..f199fdb731 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-07-mcp-client-plugin.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-07-mcp-client-plugin.md: 90c43383882034954f33b79459fac273e60b9e0e +2026-07-07-mcp-client-plugin.zh.md: a60aa537a03dec5add7e91fd78b91fece4e4a259 diff --git a/.agents/notes/implemented/feature/2026-07-07-mcp-client-plugin.md b/.agents/notes/implemented/feature/2026-07-07-mcp-client-plugin.md index 95cad58b46..90c4338388 100644 --- a/.agents/notes/implemented/feature/2026-07-07-mcp-client-plugin.md +++ b/.agents/notes/implemented/feature/2026-07-07-mcp-client-plugin.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-07-07-mcp-client-plugin.zh.md) + ## Problem The harness had no way to consume tools from the MCP (Model Context Protocol) ecosystem. MCP is the emerging standard for tool servers — GitHub, filesystem, databases, code search, and hundreds of community servers expose tools via MCP. Users want to point the harness at one or more MCP servers and have their tools appear as native model-facing tools, without writing per-server glue code. diff --git a/.agents/notes/implemented/feature/2026-07-07-mcp-client-plugin.zh.md b/.agents/notes/implemented/feature/2026-07-07-mcp-client-plugin.zh.md new file mode 100644 index 0000000000..a60aa537a0 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-07-mcp-client-plugin.zh.md @@ -0,0 +1,214 @@ +# Agent Note: MCP 客户端插件——连接外部 MCP 服务器并桥接其工具 + +Status: implemented + +[English](2026-07-07-mcp-client-plugin.md) | 中文 + +## 问题 + +harness 此前无法消费 MCP(Model Context Protocol)生态中的工具。MCP 是工具服务器的新兴标准——GitHub、文件系统、数据库、代码搜索以及数百个社区服务器都通过 MCP 暴露工具。用户希望将 harness 指向一个或多个 MCP 服务器,让其工具以原生的模型可见工具形式出现,而无需为每个服务器编写胶水代码。 + +`ToolRegistry` 已经接受原始 JSON Schema 工具定义(`dsh-tools` README 中有记录:「Raw JSON-Schema tool definitions (from MCP servers) are still accepted by `ToolRegistry.register()` directly」),扩展实操手册(cookbook)也勾勒了预期模式(「MCP | one plugin per server: discover tools → `ctx.tools.register()`」)。基础设施已就绪,缺的是桥接插件。 + +## 决策 + +### 包 + +单个包(package) `@deepseek-ai/dsh-mcp-client`,位于 `packages/mcp/mcp-client/`。不做能力 seam 的三包拆分——可预见范围内不会有第二种 MCP 客户端实现,且约定是「不要预防性拆分」([能力 seam Agent Note](../architecture/2026-06-13-capability-seams.md))。 + +### SDK + +使用官方 [`@modelcontextprotocol/sdk`](https://github.com/modelcontextprotocol/typescript-sdk)(`Client`、`StdioClientTransport`、`StreamableHTTPClientTransport`)。harness 不自行实现 JSON-RPC,与 ACP 委托给 `@agentclientprotocol/sdk` 的做法一致。 + +### 范围 + +仅 MCP Client(不含 server 端——ACP 已承担「将 harness 暴露为 agent」的角色)。仅桥接 **Tools**——Resources 和 Prompts 延后处理(它们需要 harness 侧尚不存在的消费机制,且设计空间较大)。 + +### 插件形态 + +命名空间插件(具名导出 `name`/`inject`/`Config`/`apply`,无 `export default`)。`inject: ['tools']`。每个 MCP 服务器对应 `cordis.yml` 中的一个插件实例——同一个包以不同配置加载 N 次,与 `dsh-tool-subagent` 相同。 + +### 配置 + +以 `transport` 字段为判别的扁平联合类型: + +```typescript +interface StdioConfig { + transport: 'stdio' + serverName: string // required namespace, ^[A-Za-z0-9_-]{1,32}$ + command: string + args?: string[] + env?: Record<string, string> + cwd?: string + toolCallTimeoutMs?: number // default 60_000 +} + +interface StreamableHttpConfig { + transport: 'streamable-http' + serverName: string // required namespace, ^[A-Za-z0-9_-]{1,32}$ + url: string + headers?: Record<string, string> + toolCallTimeoutMs?: number // default 60_000 +} + +type Config = StdioConfig | StreamableHttpConfig +``` + +`serverName` 是稳定的本地标识,用于在模型可见名称(见下文)中为该服务器的工具提供命名空间。它有意设计为用户配置,而非远端的 `serverInfo.name`:远端名称是不可信输入、跨部署不唯一(同一服务器的生产和预发布实例报告相同名称)、且可能在服务器升级时变化——这些都不得静默重命名模型可见工具。多个活跃实例使用重复的 `serverName` 属于配置错误:后加载的实例在启动时以可操作的错误消息失败,绝不静默覆盖或跳过。短 `serverName`(如 `gh`)也是缩短公开名称的调节手段。 + +`cordis.yml` 用法示例: + +```yaml +- id: mcp-github + name: '@deepseek-ai/dsh-mcp-client' + config: + serverName: github + transport: stdio + command: npx + args: ['-y', '@modelcontextprotocol/server-github'] + env: + GITHUB_TOKEN: !!js process.env.GITHUB_TOKEN + +- id: mcp-web + name: '@deepseek-ai/dsh-mcp-client' + config: + serverName: web + transport: streamable-http + url: http://localhost:3000/mcp + headers: + Authorization: !!js `Bearer ${process.env.MCP_TOKEN}` +``` + +模型看到的是 `mcp__github__create_issue`、`mcp__github__search_code`、`mcp__web__search`。 + +### 生命周期 + +启动时从 `cordis.yml` 加载。HMR(热模块替换)(`@cordisjs/plugin-hmr`)提供热替换:编辑 yml 条目触发旧实例的 dispose(资源释放)(断开连接、注销工具),并创建新实例(连接、发现、注册)。目前不提供运行时动态 API。公开名称是 `(serverName, rawName)` 的纯函数,因此保持 `serverName` 不变的 HMR 替换会重建完全相同的模型可见名称——会话历史和权限规则保持有效——而添加或移除不相关的服务器永远不会重命名已有工具。 + +### 工具发现与注册 + +每个 MCP 工具有两个名称: + +- `rawName`——MCP `Tool.name` 的原始值,仅用于协议通信(`tools/call`)。 +- `publicName`——在 `ToolRegistry` 中注册的全局唯一模型可见名称: + + mcp__<serverName>__<rawName> + +这种按服务器限定的形式是多服务器 agent 客户端的事实标准——所有被调研的终端用户产品都按服务器限定 MCP 工具名([Claude Code](https://code.claude.com/docs/en/agent-sdk/mcp#tool-naming-convention) `mcp__github__list_issues`、[Codex](https://openai.com/index/unrolling-the-codex-agent-loop/) `mcp__weather__get-forecast`、[Gemini CLI](https://geminicli.com/docs/tools/mcp-server/#3-tool-naming-and-namespaces)、[VS Code](https://github.com/microsoft/vscode/blob/ab9ec62c6a61e429a9abd612ff220c3f4834c9ea/src/vs/workbench/contrib/mcp/common/mcpServer.ts#L217-L260)、[Cline](https://github.com/cline/cline/blob/52fdbb1d72f7324a28142a7ba7678d4b53c902f4/sdk/packages/core/src/extensions/mcp/name-transform.ts#L20-L35)、[Roo Code](https://github.com/RooCodeInc/Roo-Code/blob/b867ec9145750d0ae1ff7f02d35406e9bf2a0b16/src/utils/mcp-name.ts#L117-L140)、[Goose](https://github.com/block/goose/blob/b3a012cbdde854b0fe14f95b1c48543bf6517c0a/crates/goose/src/agents/extension_manager.rs#L1391-L1441)、[OpenCode](https://github.com/anomalyco/opencode/blob/d199b1bff90282a4f9cd6251b5fc7b16875a52f6/packages/opencode/src/mcp/catalog.ts#L117-L120));`mcp__<server>__<tool>` 的拼写方式与 Claude Code 和 Codex 一致。`mcp__` 前缀将 MCP 注册与原生工具的命名空间隔离,并为权限/遥测规则提供稳定的匹配模式(`mcp__*`、`mcp__github__*`)。 + +1. 连接时:遍历 `client.listTools()` 的分页结果,推导每个工具的 `publicName`,然后通过 `ctx.tools.register()` 将其注册为原始 `ToolDefinition`。MCP 的 JSON Schema 和描述原样透传(不做 `defineTool` DSL 转换);仅替换模型可见的 `name`。 +2. 监听 `notifications/tools/list_changed` → 重新执行同步(dispose 上一代、注册新一代)。确定性命名意味着未变化的工具在重新同步后保持原名。 +3. 执行器闭包持有 `rawName`;公开名称永远不发送给服务器,也永远不被解析以还原原始名称。 +4. 无 `presentCall`/`presentResult`——ACP 桥接的通用卡片兜底负责渲染。 +5. 工具在系统提示词中是透明的——除名称本身外不附加「[via MCP]」标注。 + +### 公开名称规范化 + +MCP 允许工具名最长 128 字符且可包含 `.`;DeepSeek 的函数名契约允许 `[A-Za-z0-9_-]` 且最多 64 字符。公开名称按确定性规则规范化:非法字符替换为 `_`,当替换或截断改变了名称时,追加 `(serverName, rawName)` 标识的 12 位十六进制 SHA-256 hash,确保不同的 MCP 标识永远不会坍缩为同一个公开名称: + +```typescript +function publicToolName(serverName: string, rawName: string): string { + const joined = `mcp__${serverName}__${rawName}` + const normalized = joined.replace(/[^A-Za-z0-9_-]/g, '_') + if (normalized === joined && normalized.length <= 64) return normalized + const hash = sha256(`${serverName}\0${rawName}`).slice(0, 12) + return `${normalized.slice(0, 64 - 13)}_${hash}` +} +``` + +### 名称冲突处理 + +MCP 仅保证工具名在[单个服务器内](https://modelcontextprotocol.io/specification/2025-11-25/server/tools#tool-names)唯一;跨服务器冲突是常态而非例外(一项[微软研究院调查](https://www.microsoft.com/en-us/research/blog/tool-space-interference-in-the-mcp-era-designing-for-agent-compatibility-at-scale/#namespacing-issues-and-naming-ambiguity)覆盖 1,470 个服务器,发现 775 个冲突的工具名;仅 `search` 就出现在 32 个服务器中,官方 GitHub 服务器发布的是裸名 `create_issue`)。始终启用的命名空间从结构上杜绝冲突,而非在冲突发生时再处理: + +- 两个服务器都发布 `search` → 共存为 `mcp__github__search` 和 `mcp__web__search`。 +- 名为 `search` 的原生 harness 工具不受影响。 +- 重复的 `serverName` 配置使后加载的实例在启动时失败(见配置一节)。 +- 服务器列出重复的工具名属于无效工具列表:同步抛出异常,上一代注册保持不变。 +- 替换期间的注册表冲突只可能意味着外部工具占据了该服务器的 `mcp__<serverName>__` 命名空间:部分代注册被回滚(该服务器零工具),并以醒目日志记录错误。 + +工具永远不会被静默跳过;哪些工具可用永远不取决于插件加载顺序。 + +### 命名不变式 + +1. 每个 MCP 工具拥有稳定标识 `(serverName, rawName)`;每个活跃标识恰好对应一个公开名称。 +2. 公开名称是确定性的、全局唯一的,且满足 DeepSeek 64 字符 `[A-Za-z0-9_-]` 契约。 +3. MCP `tools/call` 始终接收原始的 raw name。 +4. 连接、断开或重新同步不相关的服务器永远不会重命名已有工具。 +5. 注册顺序永远不决定哪个工具可用。 + +### 工具执行 + +为来自同一个 MCP 服务器的所有工具提供统一的 `execute` 处理器: + +1. 解析 `rawName`(执行器闭包持有它),以配置的超时时间调用 `client.callTool({ name: rawName, arguments }, { signal: exec.signal })`——公开名称永远不发送给服务器。 +2. 映射结果: + - 多个 `text` 内容块 → 以 `'\n'` 连接为单个 `TextBlock`(必要原因:`flattenText` 使用 `join('')` 无分隔符,多块会丢失块间边界)。 + - `image` 内容块 → 丢弃并 `ctx.logger.warn`(harness 没有图片内容块类型;[删除图片 Agent Note](../simplification/2026-07-04-drop-image-content-block.md))。 + - `isError: true` → 映射到 harness 的 `isError` 结果路径(`{ content: [...], isError: true }`)。 +3. 取消:`exec.signal`(来自 agent loop(智能体循环)的取消)透传给 MCP SDK 的 `callTool`,后者向服务器发送 `$/cancelRequest`。 + +### 子进程环境(stdio 传输) + +复用 `dsh-subagent-acp` 的 `buildChildEnv` + `SENSITIVE_ENV_PATTERN` 清洗逻辑:过滤环境变量(剥离匹配 `/KEY|SECRET|TOKEN/i` 的凭证形变量),然后将 `config.env` 覆盖合并到顶层。显式配置的 env 不受清洗影响。 + +### 断连 / 崩溃 + +不自动重连。如果 MCP 服务器进程退出或传输层关闭: + +1. effect dispose → 所有已注册工具被注销(fiber 作用域的 disposer)。 +2. 后续模型对这些工具的调用 → `ToolNotFoundError` → `isError: true`。 +3. 恢复:用户编辑 `cordis.yml`(触发 HMR 重载)或重启 harness。 + +这与 ACP subagent 模式一致:「崩溃即终态,报告错误,清理资源,不重试。」 + +## 曾考虑的替代方案 + +### MCP Server 端(将 harness 工具暴露给外部 MCP 客户端) + +延后。ACP 桥接已将 harness 暴露为 agent 服务器。再加一层 MCP server 会以不同协议重复这一功能,而用户的首要需求是消费外部工具,而非暴露自身工具。 + +### 能力 seam 三包拆分(接口 / 实现 / 消费方) + +否决。可预见范围内不会有替代的 MCP 客户端实现——MCP 只有一个协议、一个 SDK。约定是「不要预防性拆分」,直到出现第二种实现。 + +### 指数退避自动重连 + +v1 否决。引入复杂性(工具已注册但暂时不可用的部分可用状态),且 stdio 进程崩溃通常表明配置问题,重试无法修复。HMR 已提供手动恢复路径。如有需要,可在未来作为 `reconnect: boolean` 配置项添加。 + +### 桥接 Resources 和 Prompts + +延后。Resources 需要 harness 侧的机制来决定何时注入内容(系统提示词?按需?模型触发?)。Prompts 需要 harness 尚不具备的「提示词模板」概念。两者都需要独立设计;Tools 是高价值、低风险的起点。 + +### 原始模型可见工具名加可选 `toolPrefix` + +否决。这是最初的提案,基于「大多数 MCP 服务器已在工具名中使用语义前缀(如 `github_create_issue`)」这一前提。该前提不成立:官方 GitHub 服务器发布的是 `create_issue`,参考文件系统服务器发布 `read_file`,Sentry 发布 `search_issues`——且上述微软调查表明冲突在生态规模下很常见。冲突时再加前缀(或 warn-and-skip)还会使可用工具集取决于插件加载顺序,且添加不相关服务器时工具可能被静默重命名——在对话中途使会话历史和权限规则失效。所有被调研的多服务器 agent 产品都不使用裸名。 + +### 仅服务器命名空间(`github__create_issue`,无 `mcp__` 前缀) + +v1 否决。它能防止跨服务器冲突,但无法将 MCP 注册与原生 harness 工具分离,也丧失了 MCP 全局策略匹配模式(`mcp__*`)。前缀仅多花 5 个字符;`mcp__<server>__<tool>` 拼写与 Claude Code 和 Codex 一致,最大化模型的熟悉度。如果 ToolRegistry 未来引入源感知命名空间,届时可作为命名策略变更重新考虑去掉字面前缀。 + +### 从服务器公告的 `serverInfo.name` 派生命名空间 + +否决。远端名称不可信、跨部署不唯一、升级时可变;工具标识和权限规则不得静默跟随它。命名空间是本地配置。 + +### 在工具结果中保留多个 TextBlock + +否决。DeepSeek 序列化器中的 `flattenText()` 在将 `ContentBlock[]` 扁平化为协议格式(wire format)时使用 `join('')`(无分隔符)。多个 text 块会静默丢失块间边界——这是正确性缺陷。所有现有工具返回单个 TextBlock;MCP 桥接遵循同一做法。 + +## 测试 + +覆盖率按层级命名;每个行为放在能表达它的最低成本层级。 + +- **单元测试**(`tests/mcp-client.spec.ts`、`tests/apply.spec.ts`,mock MCP SDK):`publicToolName` 算法(干净名称、规范化、截断加 hash、确定性、不同标识的分离)、raw 与 public 的协议纪律、跨服务器与原生工具共存、重复 `serverName` 加载失败与预留释放、无效工具列表拒绝、代切换/回滚、重新同步失败时的保留、结果映射、取消、配置 schema 校验。100% 逐文件覆盖率门禁约束该包。 +- **E2E**(`tests/mcp-client.e2e.ts`,无需密钥):使用真实 MCP 协议对接仓库内的 fixture(测试前置数据)服务器、`@modelcontextprotocol/server-everything` 和 `@modelcontextprotocol/server-filesystem`(stdio 传输),以及进程内 `StreamableHTTPServerTransport` 服务器(Streamable HTTP 传输)——命名空间下的发现、带点号名称的端到端规范化、执行往返、重复 `serverName` 拒绝、dispose。 +- **快照**:刻意不做。MCP 工具不引入新的 transcript(文本记录)呈现面——它们以原始 `ToolDefinition` 注册,通过 ACP 桥接的通用卡片兜底渲染,该兜底已由桥接的单元测试套件固定(`packages/ui/acp/tests/stream-update.spec.ts`)。将 MCP 服务器添加到快照示例的 `cordis.yml` 会改变已固定的 `text-turn` 系统提示词 fixture(迫使每条录制的预期输出都需要带密钥重新录制),且使每次回放依赖于 spawn 外部 MCP 服务器进程——而新增渲染行为为零。如果后续变更为 MCP 工具引入专属渲染意图,该变更届时自行声明快照覆盖。 + +## 后果 + +- 每个 MCP 服务器只需 `cordis.yml` 中的一条配置即完成集成:`serverName: filesystem` 加一条 stdio 命令(或一个 Streamable HTTP URL),就能将 `mcp__filesystem__read_file` 放入模型的工具列表,可调用,协议上使用原始的 `read_file`。 +- 公开名称是会话历史和权限/配置表面的一部分;命名算法是由测试固定的 v1 契约,发布后变更即为破坏性变更。 +- `mcp__<serverName>__` 限定符在每个名称上消耗 token。已接受:描述和 JSON Schema 在工具定义 token 中占主导,而限定符换来了稳定标识、冲突隔离和 MCP 全局策略匹配模式(`mcp__*`、`mcp__github__*`)。 +- **MCP SDK 稳定性**:`@modelcontextprotocol/sdk` 仍在演进中;破坏性变更需要更新桥接。版本已固定,且该 SDK 被广泛采用(Claude Desktop、Cursor、VS Code),因此破坏性变更不太可能悄然发生。 +- **工具 schema 质量**:MCP 服务器可能暴露描述不佳的工具(模糊的描述、不完整的 JSON Schema)。harness 原样透传——垃圾进垃圾出;这是服务器作者的责任,不是桥接的。 +- **Stdio 进程管理**:行为异常的 MCP 服务器如果忽略信号,可能卡住 dispose。Cordis fiber 的 dispose 有有界的完全停稳过程;卡住的传输层最终在框架层面超时。 +- 崩溃恢复是手动的(HMR 编辑或重启)——v1 已接受;`reconnect` 配置作为未来工作保持开放。 diff --git a/.agents/notes/implemented/feature/2026-07-07-session-prefix.i18n.yaml b/.agents/notes/implemented/feature/2026-07-07-session-prefix.i18n.yaml new file mode 100644 index 0000000000..63ac02b35e --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-07-session-prefix.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-07-session-prefix.md: 322413f541706244a8a9a9113c0b79693fe54ccd +2026-07-07-session-prefix.zh.md: 710cfbd2656d132640d39b1d62374ef2d16be612 diff --git a/.agents/notes/implemented/feature/2026-07-07-session-prefix.md b/.agents/notes/implemented/feature/2026-07-07-session-prefix.md index 7faf80cf80..322413f541 100644 --- a/.agents/notes/implemented/feature/2026-07-07-session-prefix.md +++ b/.agents/notes/implemented/feature/2026-07-07-session-prefix.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-07-07-session-prefix.zh.md) + ## Problem A plugin often owns a session-stable opener the model must always see — a skills catalog, an AGENTS.md digest, a workspace baseline. Before this seam the harness offered two homes, and both are wrong for that content. The system prompt is one rendered string: message-shaped content (a user-role `<system-reminder>` envelope, a multi-message primer) does not fit it, and providers weight conversation messages differently from system text. Durable history (`agent.inject()`, a `context/message` at session start) makes the opener permanent: every `deriveMessages()` consumer replays it, the compaction retention walk owns it, forks bake it in stale, and a resume cannot refresh it — a catalog captured at session birth outlives the world it described. diff --git a/.agents/notes/implemented/feature/2026-07-07-session-prefix.zh.md b/.agents/notes/implemented/feature/2026-07-07-session-prefix.zh.md new file mode 100644 index 0000000000..710cfbd265 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-07-session-prefix.zh.md @@ -0,0 +1,43 @@ +# Agent Note: 会话前缀——派生历史之前的仅请求消息 + +Status: implemented + +[English](2026-07-07-session-prefix.md) | 中文 + +## 问题 + +插件经常拥有一段会话级别稳定的开场内容,模型必须始终看到它:技能目录、AGENTS.md 摘要、工作区基线。在引入本 seam 之前,harness 为这类内容提供了两个归属位置,但两者都不合适。系统提示词是一个渲染后的单一字符串:消息形态的内容(user 角色的 `<system-reminder>` 信封、多消息引导序列)放不进去,而且提供方对会话消息和系统文本的权重处理不同。持久化历史(`agent.inject()`、会话启动时的 `context/message`)使开场内容变为永久:每个 `deriveMessages()` 消费方都会回放它,压缩(compaction)的保留遍历拥有它,fork 会将其以陈旧状态固化,恢复也无法刷新它——会话诞生时捕获的目录会比它所描述的世界活得更久。 + +显而易见的第三种选项——让插件在请求发出途中编辑 `messages`——被[可重建请求 Agent Note](../architecture/2026-07-05-reconstructable-requests.md)禁止:每个由循环构建的请求都是会话日志的纯函数,因此无论哪个通道承载开场内容,都必须精确记录它所发送的内容。缺失的是一个带有持久记录的仅请求消息通道。 + +## 决策 + +`agent/session-prefix` 是 agent 事件映射上的一个 waterfall(瀑布式事件)([`packages/core/agent/src/types.ts`](../../../../packages/core/agent/src/types.ts)):监听器接收一个冻结的空种子并返回扩展(规范的贡献方式是前置插入 `[mine, ...await next()]`,在协议格式上产生注册顺序)。agent loop(智能体循环)([`packages/core/agent-loop/src/loop.ts`](../../../../packages/core/agent-loop/src/loop.ts))在每个循环实例中触发一次,惰性地在实例首次 `agent/pre-step` 之前执行;组合后的列表被深拷贝、深冻结、缓存在实例上,并在该实例发出的每个请求中置于整个派生历史之前——紧接在提供方的 system 槽位之后([协议格式顺序](../../../../docs/core-data-structures/core.md#the-request-envelope-llmcallconfig-and-the-logged-header))。 + +三个属性承载了这一设计: + +- **仅请求,记录在 header 中。** `deriveMessages()` 从不返回前缀;它唯一的持久记录是实例锚定的 `request/header` 快照上的 `EpochHeader.messagePrefix`——可重建请求 Agent Note 已为请求的非历史部分拥有的通道,因此不引入新的会话事件。配套的 [`dsh-agent-loop/invariant`](../../../../packages/core/agent-loop/src/invariant.ts)对每个循环构建的请求重新计算 `messagePrefix + boundary derivation`;启用该贡献时,未记录的前缀无法到达协议格式。 +- **按实例冻结。** 复用是结构性的,而非靠纪律保证:缓存的产物在会话中途不可变,因此提供方的提示词缓存从构造上成立,前缀以每步零边际成本扩展了可缓存区域。进程重启或 `ctx.agents.resume()` 产生新实例:它重新组合,任何漂移都可追溯地落在 `'resume'` header 快照上。这就是本 seam 创建的路由规则:会话冻结的开场内容走前缀;会话中途变化的内容走仅追加历史通道(`agent.inject()` 或工具/prompt-submit 的 `additionalContexts`——[拦截 seam Agent Note](2026-06-30-interception-seams.md)),每条都是一次性支付的持久 `context/message`,之后被前缀缓存覆盖。 +- **在持久请求信封中保持精确。** 组合先于实例的首次 `agent/pre-step` 和请求边界。第一个已路由请求会把当前前缀记录在其 header 上,因此步骤后的 token 压力会将精确前缀与实际提示词、工具和已路由模型一起读取;通用的步骤前检查点 seam 不携带压缩专属参数。被取消/dispose 中断的组合会被丢弃,永不缓存:感知中止的监听器的降级回退不会泄漏到后续请求中,下一轮次在活信号下重新组合。 + +由于组合在边界快照之前运行,组合监听器的会话追加会加入当前请求的派生历史。压缩在结构上不可能触及前缀(或系统提示词):它重写的是表面节点,而 header 状态从不进入表面。 + +## 测试 + +[拦截测试](../../../../packages/core/agent-loop/tests/interception.spec.ts)固定了以下行为:没有变更 header 时的组合一次复用、前置插入顺序、空前缀省略、不可变性、组合在步骤前检查点之前完成,以及已路由 header 上的前缀;[取消测试](../../../../packages/core/agent-loop/tests/cancel.spec.ts)固定了丢弃与重新组合。Session、不变式、token-meter 和压缩测试覆盖 header 往返、请求重建与持久前缀感知的压力核算。快照归一化保留前缀计数,[固定 header 场景](../testing/2026-07-06-pin-request-header-content-in-one-scenario.md)拥有内容,默认示例保持无前缀。与提供方无关的 seam 无需专门 e2e;带密钥的 [request-cache e2e](../../../../packages/core/agent-loop/tests/request-cache.e2e.ts) 覆盖了其缓存经济性。 + +## 曾考虑的替代方案 + +- **每请求 `before`/`after` 槽位,每步重新计算**(最初提出的形态:一个每请求触发的 waterfall,贡献冻结的 `before` 消息置于历史之前、新鲜的 `after` 消息置于历史之后):否决。每步重新组合 `before` 会引入漂移,必须记录为完整的变更 header;`after` 槽位位于不断增长的历史之后,其 token 在每个请求中重复支付,且其后的所有内容不可缓存。对照各替代方案衡量,当前所有更新模式都能通过持久追加更廉价地满足(支付一次,此后缓存读取),而唯一没有归属的内容是会话稳定的开场——它需要的是冻结,而非重新计算。 +- **系统提示词分段**(`system-prompt/assemble`):对此类内容否决。assembly 渲染为单一 `system` 字符串,消息形态的开场放不进去;且系统提示词被设计为每步重新组装(变化时带完整的变更 header),而开场内容需要按实例冻结的语义。 +- **持久化历史开场**(会话启动时 `inject()`):否决。永久历史正是问题陈述中的失败模式——到处被回放、可被压缩、在恢复后仍保持陈旧状态。 +- **按轮次组合而非按实例组合**:否决。轮次边界的重新组合要么与日志静默失同步,要么强制产生变更 header;且它每次触发都会破坏提供方缓存。合理的刷新点是实例边界,`'resume'` 快照已在那里可追溯地记录漂移。 +- **通过 `agent/pre-step` 携带提示词/前缀,用于临时压力估算**:否决,因为它把通用生命周期 seam 耦合到一个消费方,而且仍会遗漏更晚的请求路由和工具;步骤后的回放会从持久的已路由 header 读取请求信封的每个字段。 +- **专用会话事件承载前缀**:否决。header 事件按设计就是请求的非历史记录;第二个事件会为同一事实提供第二个归属,并多出一个需要保持完整的编解码器。 + +## 后果 + +- `agent/pre-step` 保持通用的 `(agent, turn, step, signal)` 检查点。压缩不接收 prefix 参数;`ctx.tokenMeter` 在步骤后从规范的已路由 header 折叠前缀。 +- 贡献者的内容在会话中途变化时,直到下一个实例才会被重新读取——这是设计意图。需要会话中途目录更新的部署,应将变更通知路由到仅追加历史通道,支付一条持久 `context/message`。 +- 被放弃的 `after` 槽位意味着请求尾部附近没有仅请求通道;仓库中没有任何功能需要它,且恢复它会重新引入本设计旨在避免的每步重复支付成本。 +- 空组合即为规范缺失:无贡献者的部署不记录额外的 header 字节,其请求就是裸派生。 diff --git a/.agents/notes/implemented/feature/2026-07-08-repeat-tool-guard.i18n.yaml b/.agents/notes/implemented/feature/2026-07-08-repeat-tool-guard.i18n.yaml new file mode 100644 index 0000000000..95661f953c --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-08-repeat-tool-guard.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-08-repeat-tool-guard.md: 67ec29c6c9fa38bf1d5935c469f3f71b1119dc3a +2026-07-08-repeat-tool-guard.zh.md: 01037f29810c781c33beee414e50412a0c9b0f89 diff --git a/.agents/notes/implemented/feature/2026-07-08-repeat-tool-guard.md b/.agents/notes/implemented/feature/2026-07-08-repeat-tool-guard.md index 08f5bb01cf..67ec29c6c9 100644 --- a/.agents/notes/implemented/feature/2026-07-08-repeat-tool-guard.md +++ b/.agents/notes/implemented/feature/2026-07-08-repeat-tool-guard.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-07-08-repeat-tool-guard.zh.md) + ## Problem A model stuck in a loop re-issues the same tool call with byte-identical arguments — re-running a failing grep, re-reading an unchanged file, polling a command that already gave its answer — and each round trip burns tokens, wall-clock, and (for paid APIs) money without adding information. The harness has nothing that notices: the loop has no step budget, no plugin tracks call repetition, and the model only escapes when it happens to vary its own behavior. The failure mode is real and cheap to detect — [pi-repeat-tool-guard](https://github.com/Kingwl/pi-repeat-tool-guard) ships exactly this as a pi coding-agent extension: count consecutive identical calls and, past a threshold, append a `<system-reminder>` telling the model to stop repeating itself and change course. diff --git a/.agents/notes/implemented/feature/2026-07-08-repeat-tool-guard.zh.md b/.agents/notes/implemented/feature/2026-07-08-repeat-tool-guard.zh.md new file mode 100644 index 0000000000..01037f2981 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-08-repeat-tool-guard.zh.md @@ -0,0 +1,76 @@ +# Agent Note: 重复工具调用守卫插件 + +Status: implemented + +[English](2026-07-08-repeat-tool-guard.md) | 中文 + +## 问题 + +模型陷入循环时,会以字节级相同的参数反复发起同一个工具调用——重新运行一条失败的 grep、重新读取一个未变化的文件、轮询一条已经给出答案的命令——每一轮往返都消耗 token、挂钟时间以及(对付费 API 而言)金钱,却不带来新信息。harness 目前没有任何机制能察觉这一点:循环没有步骤预算,没有插件追踪调用重复,模型只有在碰巧改变自身行为时才能跳出。这种失败模式真实存在且检测成本极低——[pi-repeat-tool-guard](https://github.com/Kingwl/pi-repeat-tool-guard) 正是以 pi coding-agent 扩展的形式提供了这一功能:统计连续相同调用次数,超过阈值后追加一条 `<system-reminder>` 告诉模型停止重复并换个方向。 + +harness 已经具备 pi 扩展所使用的全部 seam,而且更好:[拦截 seam Agent Note](2026-06-30-interception-seams.md)赋予 `tools/post-execute` 一种经过认可的方式,将面向模型的上下文附加到已完成的调用上;循环缓冲并注入该上下文,同时保持调用/结果的邻接关系;注入的上下文是一条已记录的 `context/message`——因此原生守卫无需新增会话事件即可满足「模型可见 ⟺ 已记录」规则。缺少的只是插件本身。 + +## 决策 + +该守卫是一个循环卫生插件,而非面向模型的工具。它统计对同一工具以相同规范化参数发起的连续调用次数,并在配置的阈值处注入建议性提醒。它从不延迟、阻止或改写调用;模型自行决定是换种方式重试还是结束。 + +插件为 `@deepseek-ai/dsh-repeat-tool-guard`,位于 `packages/guard/repeat-tool-guard/`,开辟 `guard/` 分组用于循环卫生插件(单包(package)分组有先例:[todo-write Agent Note](2026-06-29-todo-write-tool.md)发布了 `todo/tool-todo`)。它注册两个监听器,将状态保存在以存活 `Agent` 对象为键的 `WeakMap` 中——工具注册表是上下文级别的单例,其 waterfall(瀑布式事件)交错所有 agent(智能体)的调用(subagent 运行在同一个上下文上),因此按 agent 分键是正确性要求,而非锦上添花;弱对象键还使得纯清理用途的 disposal 监听器不再必要。 + +- **`tools/post-execute`(waterfall)**——唯一的检测点。监听器同时接收 `(exec, result)`,因此计数和提醒投递无需跨事件的 pending map(pi 扩展需要它,仅因为其 `tool_call`/`tool_result` 钩子是分开的事件)。它始终通过 `next()` 委托,当命中阈值时,将提醒前置到下游决策的 `additionalContexts`——这正是[钩子桥接](2026-06-30-hook-bridges.md)已采用的「观察并丰富」姿态,遵守 waterfall 契约。计数放在此处而非 `tools/pre-execute`,因为 post-execute 也会为被拒绝的调用触发(`ToolRegistry.execute` 将 deny 路由到同一条流水线),而模型反复敲击一个被拒绝的调用恰恰是值得打破的循环。 +- **`agent/prompt-submit`(waterfall)**——纯重置钩子:通过 `next()` 委托,清除提交 agent 的链。用户介入改变了上下文;跨越介入的重复不是循环。 + +### 检测语义 + +链的键是 `(tool name, canonical arguments)`;与前一个被追踪调用相同的调用递增该 agent 的连续计数器,不同的被追踪调用将其重置为 1。规范化方式为深度键排序加 `JSON.stringify`:`ToolExecution.arguments` 按构造就是循环中 `JSON.parse` 的输出(或格式错误的参数 JSON 的原始字符串回退,其本身也是可比较的值),因此 pi 原版对 bigint/循环引用/`undefined` 的处理在此没有输入,被有意去除。 + +两条刻意的规则,均记录在[包 README](../../../../packages/guard/repeat-tool-guard/README.md) 中,因为它们是读者否则只能猜测的行为: + +- **未追踪的调用对链透明。** 被 `include`/`exclude` 排除的调用既不递增也不重置计数器,因此 `grep X → todo_write → grep X` 在 `todo_write` 被排除时仍计为两次连续的 `grep X`。这正是排除功能有用的原因——穿插在循环中的簿记工具不得为循环洗白——也是 pi 扩展的(未文档化的)语义,有意保留并明确写下。 +- **没有 agent 的调用被忽略。** 直接调用 `ctx.tools.execute()` 的调用方(测试、非循环消费方)没有可提醒的模型,也没有可作键的存活 agent 对象。 + +### 提醒投递 + +提醒作为独立条目搭载在 `additionalContexts` 上(source 为 `{kind: 'plugin', plugin: 'repeat-tool-guard'}`——依照 `HookContext`,该标签承载语义),绝不替换 `content`:`tool/result` 事件仍是工具自身的审计输出,循环则在步骤结果之后把缓冲的上下文追加为 `context/message`,会话将其渲染为带标签的合成 user 信封,并由派生历史回放。阈值逐级升级:第一个配置阈值获得简短的「你正在重复自己,请分析先前结果」提示;后续各阈值获得详细形式,包含工具、重复计数和规范参数(在头部截断到 `argumentsPreviewChars`,默认 500——循环中的 `write` 级 payload 不得无界地进入下一次请求;链键始终比较完整规范字符串),并说明这些调用没有取得进展。pi 原版把温和文本硬编码为字面计数 3;本守卫以 `thresholds[0]` 为键,修复了移植中的这一 bug。下游钩子桥贡献仍是独立数组条目,因此两个插件都保留各自的 source、信封与元数据。 + +### 配置 + +```yaml +- id: repeat-tool-guard + name: '@deepseek-ai/dsh-repeat-tool-guard' + config: + thresholds: [3, 5, 8] # default; consecutive counts that trigger a reminder + include: [] # tool-name patterns to track; empty ⇒ all tools + exclude: [todo_write] # tool-name patterns transparent to the chain + argumentsPreviewChars: 500 # default; cap on arguments quoted in the detailed reminder +``` + +`thresholds` 在加载时校验,遇到空列表、非整数、小于 2 的值或重复项时抛出异常——配置错误快速失败,取代 pi 原版的静默回退到默认值。`include`/`exclude` 条目支持 `*` 通配符。模式是对调用时实际存在的工具的谓词,而非对注册表条目的引用,因此匹配不到当前已注册工具的条目不是错误——与 `toolOrder` 的引用检查不同,`exclude: [mcp_*]` 在未加载 MCP 工具的部署中也必须保持有效。 + +## 测试 + +- **单元测试:** 使用脚本化适配器的真实循环,覆盖计数与重置规则、未追踪透明性、dispose(资源释放)清理、按 agent 隔离、规范化参数键序、升级、被拒绝的调用、无 agent 执行、通配符转义、无效配置,以及下游阻止或 replacement 决策,达到逐文件 100% 覆盖率。 +- **快照测试:** keyless 的 `repeat-tool-guard` 场景发起五次相同的 `todo_write` 调用,在 ACP 输出和会话日志中固定第三次调用的温和提醒与第五次调用的详细提醒。该插件在实时示例中加载,但在其他场景中保持静默。 +- **E2e 测试:** 无。该插件是确定性的且与提供方无关,其 seam 契约由各自的所有者覆盖。 + +## 曾考虑的替代方案 + +- **将提醒追加到工具结果中**(以替换 `content` 的方式 `accept`——pi 扩展的机制,它修补结果内容是因为那是其 API 提供的唯一通道):否决。这会让已记录的 `tool/result` 对工具实际返回的内容撒谎,而 `additionalContexts` 是 post-execute 评注的独立认可通道,循环级缓冲保持了调用/结果的邻接关系。 +- **在 `tools/pre-execute` 中计数并使用 pending-reminder map**(pi 的两阶段形态):否决。post-execute 单独就能同时看到 `(exec, result)` 且也为被拒绝的调用触发,因此一个监听器、无跨事件状态即可以更少的机制覆盖严格更多的尝试。 +- **在最高阈值升级为 `block`**:在初始范围内否决。阻止调用会惩罚合法的相同重复(轮询长时间运行的终端、重新检查 agent 预期会变化的文件),而建议性提醒让模型保持控制权。待有证据后重新审视;决策形状(`PostToolDecision`)已支持此选项。 +- **通过 CC/Codex 桥接的逐部署外部钩子**(一个 `PostToolUse` 脚本):否决作为最终答案。它对单个部署有效,但一个已发布、有单元测试、可通过 `cordis.yml` 配置的插件才是 harness 原生的形式,且没有逐调用的子进程开销。 +- **在 `agent-loop` 中设置循环级步骤或重复预算**:否决。「用插件,不改循环」;硬性步骤预算是一种更粗粒度的正交控制,需要自己的提案。 +- **模糊/近似相同检测**(路径归一化、相似但不完全相同的参数):否决。规范化后的精确匹配成本低、确定性强、且可向模型解释;相似度阈值引入误报风险,需要证据才能换取复杂度。 +- **将包放在 `core/`**:否决。core 是产品主干;行为守卫是可选的叶子插件,`todo/` 的先例是每个插件族一个小型专属分组。 + +## 后果 + +- 提醒在设计上是建议性的:有意重复相同调用的幂等轮询模式仍会在超过阈值后收到提示,减压阀是配置(`thresholds`、`exclude`)加上明确允许「在已收集足够证据时结束」的提醒文本。每次触发在下一次请求中增加提醒 token 的开销;阈值限制了触发频率。 +- 链状态仅存于内存:从持久化恢复的会话以全新的链开始,因此跨越恢复的循环比实时循环更晚收到提醒——可以接受,守卫是启发式提示而非已记录的不变式,持久化计数器状态带来的收益不值得其复杂度。 +- 当多个 post-execute 生产者在同一次调用上附加上下文时,每项贡献保持为独立的 `HookContext`;顺序遵循 waterfall 嵌套关系,每个条目保留自己的溯源信息。 +- 实现快照层时暴露了 suite kit 的一项隐藏假设:fixture guard 把「撰写的模型场景」等同于「由 override 驱动」。`Scenario` 表现在携带显式的 `overridden` 标志,并且 sidecar 是否存在会以双向方式与其核对(未注册的游离 sidecar 会静默替换派生脚本)——suite kit 比本插件出现前更严格。 + +## 延后事项 + +- 压缩(compaction)不重置链:压缩后的历史改变了模型所见的内容,但重复风险通常在压缩后仍然存在。 +- 在高阈值升级为 `block` 未实现;`PostToolDecision` 已支持此选项,待证据到来时启用。 +- subagent 的链按 agent 隔离;在出现具体用例之前不提供共享机制。 diff --git a/.agents/notes/implemented/feature/2026-07-08-self-referential-cordis-toolset.i18n.yaml b/.agents/notes/implemented/feature/2026-07-08-self-referential-cordis-toolset.i18n.yaml new file mode 100644 index 0000000000..f91e3b5d42 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-08-self-referential-cordis-toolset.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-08-self-referential-cordis-toolset.md: 80bffa3a2a959939f18fd1d3422607cf61895fc7 +2026-07-08-self-referential-cordis-toolset.zh.md: 2ec79037045fdb040cccf31699789abdd3a12db2 diff --git a/.agents/notes/implemented/feature/2026-07-08-self-referential-cordis-toolset.md b/.agents/notes/implemented/feature/2026-07-08-self-referential-cordis-toolset.md index 429102aeee..80bffa3a2a 100644 --- a/.agents/notes/implemented/feature/2026-07-08-self-referential-cordis-toolset.md +++ b/.agents/notes/implemented/feature/2026-07-08-self-referential-cordis-toolset.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-07-08-self-referential-cordis-toolset.zh.md) + ## Problem Everything in this harness is a cordis plugin, but the agent running inside that plugin runtime cannot see or touch it: it cannot enumerate the services and events around it, cannot extend itself with a new tool mid-session, and cannot compose capabilities it invents. Handing the model that power is worth exploring — a self-referential agent that inspects and modifies its own runtime — but it raises three correctness problems at once, and the design is about answering them rather than the raw "let the model run code" mechanic. diff --git a/.agents/notes/implemented/feature/2026-07-08-self-referential-cordis-toolset.zh.md b/.agents/notes/implemented/feature/2026-07-08-self-referential-cordis-toolset.zh.md new file mode 100644 index 0000000000..2ec7903704 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-08-self-referential-cordis-toolset.zh.md @@ -0,0 +1,82 @@ +# Agent Note: 自引用 cordis 工具集 + +Status: implemented + +[English](2026-07-08-self-referential-cordis-toolset.md) | 中文 + +## 问题 + +本 harness 中的一切都是 cordis 插件,但运行在该插件运行时内部的 agent(智能体)既看不到也碰不到它:它无法枚举周围的服务和事件,无法在会话中途为自己添加新工具,也无法组合自己发明的能力。赋予模型这种能力值得探索——一个能审视并修改自身运行时的自引用 agent——但这同时引发三个正确性问题,本设计的核心正是回答这些问题,而非单纯的「让模型执行代码」机制。 + +第一,模型编写的注册必须在注册发生时就完成校验:格式错误的工具 schema 必须在注册时失败,而不是等到后续请求尝试将其组装进提示词时才报错。第二,模型编写的代码需要调用它从未见过源码的服务 API——靠猜测方法签名、更糟糕的是猜测返回值结构,会消耗大量盲目试探的步骤。第三,模型挂载的一切都必须完全可释放:模型可以按需释放,普通的插件生命周期在宿主插件重载时也会释放,否则长会话会积累遗留的监听器和工具。 + +## 决策 + +该工具集以 [`@deepseek-ai/dsh-tool-cordis`](../../../../packages/cordis/tool-cordis/README.md) 发布——一个新的顶层 `packages/cordis/` 分组——并由 [`examples/cordis-agent`](../../../../examples/cordis-agent/README.md) 演示。它为模型提供三个工具,操作模型自身运行其中的活跃 cordis 运行时:审视它、将模型编写的插件挂载进去、再将其释放。 + +vm 隔离了意外的全局污染,上下文门面隐藏了框架内部细节。但二者都不限制已暴露服务的权限:一个挂载可以调用 `ctx.bash` 以宿主执行器的权限运行命令,也能访问真实的文件系统和网络服务。这是一个需要显式启用的开发工具,信任等级与 bash 相当,不是安全边界,也不是产品默认配置。 + +### 三个工具 + +| 工具 | 契约 | +|---|---| +| `cordis_inspect` | 对活跃运行时的只读报告,每个 `what` 值对应一个 Markdown 段落(省略 `what` 则输出全部段落)。精确的 `name` 搭配 `what: "api"` 或 `what: "events"` 可收窄到一个带源码文档的目标。从不产生变更。 | +| `cordis_mount` | 在 `node:vm` 沙箱中执行 `code`(一个异步 JavaScript 函数的函数体);代码必须 `return` 一个 cordis 插件,该插件作为 `cordis-dynamic` 分组 fiber 的子节点挂载,并以一个新 id(`dyn-1`、`dyn-2`……)跟踪。 | +| `cordis_unmount` | 按 id 释放一个动态挂载,并等到释放达到完全停稳后才返回——该插件所做的每一项注册都被撤销,而不仅仅是请求停止。 | + +`cordis_inspect` 的段落:`services`(每个已提供的 ctx 服务及其所属 fiber,非活跃的所有者会被标记)、`plugins`(来自 `ctx.registry` 的所有已加载插件的扁平列表及其生命周期状态——展示加载了哪些能力,刻意不展示树形结构)、`tools`(模型可调用的工具)、`dynamic`(挂载表:id、名称、状态、提供的服务、等待的服务)、`api`(来自生成目录的活跃服务签名及其引用的类型形状)和 `events`(harness 事件及其分发模式和签名)。宽泛的 `api` 和 `events` 报告省略完整 JSDoc 以保持紧凑;精确 `name` 会返回一个服务或事件,以及其原始方法/声明 JSDoc。其他段落不能搭配 name,未知目标会失败,而 API 目标必须处于活跃状态。面向模型的工具描述携带了模型在调用时所需的操作规则;[生成的工具目录](../../../../docs/tool-catalog.md)是其完整呈现。 + +### 沙箱语义 + +挂载代码以异步函数体的形式在一个新的 vm realm 中运行。其文档化的接口面将文件、网络、进程和定时器访问引导至 Cordis 服务,使挂载保持可审视和可释放。宿主 realm 的辅助手段仍然使 Node 逃逸成为可能,这与信任姿态一致。`vmTimeoutMs` 仅约束同步执行部分。 + +沙箱全局变量刻意精简:一个带标签的直写 `console`(在宿主 stdout/stderr 上输出 `[cordis:<id>] …`,这样在挂载调用之后很久才触发的监听器输出仍能落到用户可见的地方)、`harness.defineTool` / `harness.registerTool` 注册对、新 vm 上下文缺少的编码原语(`btoa`/`atob` 作为基于 `Buffer` 的宿主闭包——这是一个经过审批的例外,`Buffer` 本身从不暴露——加上 `TextEncoder`/`TextDecoder`),以及对被扣留的 Node API 的可调用陷阱(`require`、`setTimeout`/`setInterval`/`setImmediate`/`clearTimeout`/`clearInterval`、`fetch`),这些陷阱会抛出一条重定向消息指明 cordis 替代方案。只有函数形态的全局变量才设陷阱;`process` 和 `Buffer` 保持 `undefined`,这样 `typeof` 特性探测保持惰性而不会引爆一个抛异常的访问器。 + +挂载代码通过三道控制跨越 vm 边界。双 realm `instanceof` 同时识别宿主和 vm 对象。`harness.defineTool` 在宿主 realm 中重建输出 schema/投影器,将工具体返回值快照为宿主自有的 JSON,并让注册表在观测前强制执行[规范工具输出契约](../architecture/2026-07-20-canonical-tool-output-contract.md)。挂载的插件接收的是一个白名单上下文门面,而非原始或透传的 `Context`;框架管道和以 context 为值的返回会被拒绝。服务读取需要声明 `inject`,保留 Cordis 的激活与卸载语义。`ctx.tools.get` 仅暴露 schema 视图,因此挂载代码无法绕过 `ToolRegistry.execute` 直接调用定义。 + +边界将无歧义的 JSON-Schema 形式规范化为 `ParameterSchemaSpec`,同时保留 `integer`、原始对象开放性和 required 数组。直接使用 DSL 的对象节点必须声明 `additionalProperties`;无效词汇会报错并给出可接受的替代方案。解析错误、TypeScript 错误、缺少 return、Node API 误用和重复工具名等错误信息包含相关源码行或纠正性契约,不叙述实现内部细节。 + +### 动态分组与挂载生命周期 + +所有动态挂载都是工具插件下方 `cordis-dynamic` 分组的子节点,因此普通的 fiber 释放即可处理重载和卸载。挂载会等待 settlement;启动失败时在返回错误前释放 fiber。已 settle 但处于 pending 状态的挂载仍然可见,并列出其缺失的注入。`cordis_unmount` 等待挂载 fiber 的释放完成。 + +### 通过 provide/inject 实现跨挂载组合 + +挂载之间通过普通的 cordis 服务语义相互关联,以各自的 id 作为生命周期句柄:挂载 A 调用 `ctx.provide('foo', value)`,挂载 B 声明 `inject: ['foo']` 并在 `foo` 存在的瞬间激活;如果 B 先挂载,它保持 pending 状态并列出缺失的服务;卸载 A 使 B 回到 pending(其注册被撤销),之后重新 provide 会通过一个新的沙箱门面重新运行 B 的 `apply`;重复 provide 会明确报错并指出拥有该服务的 fiber。一个 realm 注意事项:由挂载 provide 的服务值是 vm realm 对象——从任何地方调用其方法都能工作,但消费方不得假设它具有宿主原型。 + +### 生成的 API 目录 + +`cordis_inspect` 从生成的目录提供 API 和事件数据,而非维护一份重复的表格。生成器复用 Cordis 目录的 AST 扫描,输出服务摘要、签名、原始服务方法与事件 JSDoc、事件模式、引用的类型声明以及继承的上下文接口面。有歧义的类型名被省略,过大的声明被标记为截断。 + +新鲜度像所有生成产物一样受门禁约束:`pnpm run verify-cordis-api`(在 `doc-sync` 中)在内存中重新生成并在有任何 diff 时失败,因此 JSDoc 或公开签名变更如果不重新生成模型读取的目录就无法合入。运行时 inspect 工具将目录与活跃运行时取交集而非直接转储:宽泛报告把有目录条目的活跃服务渲染为摘要 + 签名,把没有目录条目的活跃服务(挂载提供的)渲染为名称 + 所属 fiber,简要列出有目录条目但无活跃提供方的服务,再附上引用的类型形状。精确名称报告渲染一个活跃服务或事件,并把原始 JSDoc 紧靠在每个签名之前;让该细节按需出现,避免探索性列表承担其 token 成本。 + +### 配置、渲染与可观测性 + +该插件暴露一个配置字段,由 schemastery 校验并记录在[配置目录](../../../../docs/config-catalog.md)中:`vmTimeoutMs`(默认 5000),挂载代码同步执行部分的毫秒上限。工具名、`cordis-dynamic` 分组名和 `dyn-` id 前缀是结构性词汇,保持固定。三个工具均按[工具实操手册](../../../../docs/cookbook/adding-a-tool.md)渲染为 `generic` 卡片(`cordis_inspect` 为 `read`,`cordis_mount` 为 `execute` 并将代码作为 `rawInput` 携带,`cordis_unmount` 为 `delete`),不覆盖 `presentResult`。 + +「模型可见 ⟺ 已记录」成立,且无需新的会话事件类型:挂载或卸载仅通过其自身的 `tool/call` / `tool/result` 对可见(循环会记录它们),而挂载引起的工具集变化由循环在 schema 在步骤间发生变化时发出的完整变更 request header 记录。刻意不设 `cordis/mount` 溯源事件——它只会重复工具调用对已记录的内容。动态挂载是进程生命周期的,不是会话状态:恢复一个持久化的会话会重建对话,但不会重新挂载插件。 + +## 曾考虑的替代方案 + +**用结构化的逐能力注册工具替代 `cordis_mount`。** 最具吸引力的替代方案是一个带有显式 `name` / `description` / `parameters` / `code` 字段的 `cordis_register_tool`(以及兄弟工具 `cordis_register_listener`、`cordis_register_service`……),而非单一的「挂载一个插件」原语。否决原因:它唯一的真正优势——对最常见的单一场景免去插件样板代码——不足以抵偿其代价,而单一的 mount 原语能一次性覆盖所有能力。 + +| 维度 | 结构化逐能力工具 | 单一 `cordis_mount` | +|---|---|---| +| Schema 正确性 | `parameters` 仍然是模型编写的 JSON,需要统一 schema 校验,只是提前了一步 | 同样的校验在沙箱边界运行,同样的指导性错误信息 | +| 代码字段 | `execute` 函数体仍然是 vm 中模型编写的 JS;realm 和服务调用的正确性问题不变 | 一个沙箱、一条规范化路径、一处受保护的注册 | +| 能力覆盖面 | 仅限工具;监听器、服务、`inject` 关系各需另一个结构化工具——接口面无限增长 | 一套词汇(cordis 插件)覆盖当前和未来的所有效果 | +| 跨挂载组合 | 在工具注册载荷中无法表达 | 原生 `provide`/`inject`,普通的 cordis 语义 | +| 可审视性 | 注册的东西无法在插件列表中显示为插件 | 模型挂载的正是 `cordis_inspect` 渲染的 | +| 模型易用性 | 对最常见的单一场景有优势(无插件样板) | 通过 mount 描述中的规范示例加边界错误信息教会正确调用来缓解 | + +因此正确性投入放在能一次性为所有能力带来回报的地方:通过 `cordis_inspect` 呈现的生成 API 目录,以及沙箱边界校验(其错误信息教会正确的调用方式)。结构化注册工具日后仍可作为语法糖添加,由它合成 mount 代码;本设计不排斥这一可能。 + +**在工具中手工维护服务/事件参考。** inspect 工具的第一版携带了一份手写的服务方法签名表。它被生成的 `api-catalog.ts` 取代,因为手写表在签名变化的瞬间就会与 JSDoc 脱节且没有门禁约束这种漂移,而生成产物的新鲜度由文档使用的同一套 AST 检查。 + +**新增 `cordis/mount` 会话事件。** 一个持久的溯源事件记录每次挂载(源码、名称)有明确先例(`hook/invoked`、`compact/start`)。v1 中予以否决:挂载和卸载已经作为 `tool/call` / `tool/result` 对可见,工具集变化已经作为完整的变更 request header 被记录,因此专用事件只会重复记录。如果审计用例需要将挂载溯源从工具调用中分离出来,日后仍可添加。 + +**加固的/能力受限的沙箱。** 对 Node 内置模块设陷阱并向挂载代码提供白名单门面而非原始上下文,可能暗示意图是为安全而沙箱化。这里明确不是:陷阱和门面收窄的是挂载代码所见的*接口面*——将其引导至 cordis 服务、远离易泄漏的 Node 内置模块和框架内部——目的是正确性和封堵未受保护的上下文逃逸,但门面暴露的能力(`ctx.bash`、`ctx.fs`、`ctx.web`)触及真实运行时,因此它不是安全边界。真正的安全边界(独立进程、权限提示)超出了一个开发/显式启用工具集的范围,且会与其核心目的——将活跃运行时交给模型——相冲突。 + +## 后果 + +该工具集是刻意的显式启用设计,具有完全特权的 `ctx`,因此部署方采用它的意识程度应与 bash 工具相当。以下几个事实由工具描述直接告知模型:一个 waterfall(瀑布式事件)监听器(如 `tools/pre-execute`)如果不调用 `next()` 就返回,会否决整条链,因此一个挂载的监听器可以瘫痪 agent 自身的工具分发([waterfall 语义](../../../../docs/cordis-primer.md#cordis-waterfall-semantics));挂载代码在当前轮次的工具调用内运行,因此 await 任何只在该轮次结束后才 resolve 的东西会导致死锁;`vmTimeoutMs` 仅约束同步执行;挂载不会在会话恢复后存活。 diff --git a/.agents/notes/implemented/feature/2026-07-10-session-query-service.i18n.yaml b/.agents/notes/implemented/feature/2026-07-10-session-query-service.i18n.yaml new file mode 100644 index 0000000000..f19f20eb9e --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-10-session-query-service.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-10-session-query-service.md: 722f6bf6163278719c3bbb598ed2a2a9d042fb8e +2026-07-10-session-query-service.zh.md: ae6fcb78e18afe83784560c493ea93b7ee0bd68c diff --git a/.agents/notes/implemented/feature/2026-07-10-session-query-service.md b/.agents/notes/implemented/feature/2026-07-10-session-query-service.md index 8cc529377b..722f6bf616 100644 --- a/.agents/notes/implemented/feature/2026-07-10-session-query-service.md +++ b/.agents/notes/implemented/feature/2026-07-10-session-query-service.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-07-10-session-query-service.zh.md) + ## Problem Session history exists in two places: current `SessionStore` objects and an optional persistence backend. Consumers that need exact inspection would otherwise duplicate live-versus-persisted precedence, persistence lifecycle handling, raw-event surface classification, relationship tracing, and defensive cloning. Durable state can lag the live log between checkpoints, so persistence alone is not a truthful current source. diff --git a/.agents/notes/implemented/feature/2026-07-10-session-query-service.zh.md b/.agents/notes/implemented/feature/2026-07-10-session-query-service.zh.md new file mode 100644 index 0000000000..ae6fcb78e1 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-10-session-query-service.zh.md @@ -0,0 +1,42 @@ +# Agent Note: 精确会话查询服务 + +Status: implemented + +[English](2026-07-10-session-query-service.md) | 中文 + +## 问题 + +会话历史存在于两处:当前的 `SessionStore` 对象与可选的持久化后端。需要精确检查的消费方若无统一服务,就不得不各自重复实现活跃/持久化优先级判定、持久化生命周期处理、原始事件的 surface 分类、关系追踪以及防御性克隆。在检查点之间,持久化状态可能落后于活跃日志,因此仅靠持久化并非当前状态的可靠来源。 + +全文搜索与此相关,但规模大得多。将提供方协调、同步、失效、排序和游标状态放入精确读取服务,会在具体数据库拥有方旁边再创建一个状态机。 + +## 决策 + +`@deepseek-ai/dsh-session-query` 拥有面向单一逻辑语料库的唯一抽象 `ctx.sessionQuery` 服务。它具体实现 `listSessions()`、提供方无关的 `filterSessions(filters)`、`listEvents(sessionId)`、`filterEvents(sessionId, filters)`、有界的 `readEvent(request)`、`traceSession(sessionId)` 和 `traceEvent(request)`,而具体后端实现其两个全文搜索方法。[统一服务决策](../architecture/2026-07-23-unified-session-query-service.md)拥有这一拓扑,[SQLite 搜索决策](2026-07-10-sqlite-session-query-provider.md)拥有搜索行为,[追踪决策](2026-07-13-session-query-tracing.md)拥有血缘与事件关系语义。 + +该服务动态观察可选的 `ctx.sessionPersistence` 绑定,但不保留持久化缓存或失效监听器。每次跨语料库列表操作向活跃后端请求权威元数据,然后叠加一份新鲜的活跃 store 列表。id 匹配的条目合并为一条 `SessionRecord`:活跃 header 优先,`live`/`persisted` 各自独立报告来源可用性。不可变 header 不一致时产生 `SESSION_QUERY_SOURCE_CONFLICT`。 + +精确目标读取首先检查活跃 store,快照活跃 header 与事件日志。此路径从不查询持久化,因此持久化后端故障不会导致已知的活跃历史不可读。若活跃 store 中无目标,服务列出当前持久化元数据、证明该 id 存在、加载它,并在列表/加载 header 不一致时拒绝。所有返回的 header 与事件都经过一次 structured-clone 边界。 + +## Surface 语义 + +`dsh-session` 导出 `foldSurface(events)`,`SurfaceManager` 使用相同的转换函数维护其增量缓存。fold 返回分离的当前事件 seq 以及每次替换实际移除的 seq。`listEvents()` 和 `traceEvent()` 利用该结果为每个原始事件分类,使检查结果不会在位置替换语义上与 model-history 推导产生分歧。 + +`readEvent()` 返回完整的目标加上按连续 seq 排列的原始相邻事件。`before` 和 `after` 默认为零,各自受 `readWindowMax`(默认 50)约束。结果携带克隆的 `SessionHeader` 而非来源可用性记录,因为判断活跃目标的 persisted 标志会违反「活跃精确读取不依赖持久化健康状态」这一保证。 + +## 安全边界 + +该服务是上下文级别的受信任基础设施,而非授权层。未来面向模型的历史工具或人类 UI 将施加显式的调用方/会话范围。该服务不添加面向模型的工具,也不改变 transcript(文本记录)或快照的 surface。 + +## 曾考虑的替代方案 + +- **将逻辑语料库解析直接放在每个消费方中**:否决。来源优先级、冲突处理、可选服务生命周期、克隆与 surface 分类是共享的正确性规则。 +- **仅查询持久化**:否决。检查点可能落后于当前活跃日志。 +- **缓存持久化元数据并监听写入/删除**:否决。精确读取可以直接询问权威来源,而缓存失效在规模尚未要求时就引入了生命周期与并发状态。 +- **将提供方注册放入精确读取服务**:否决。SQLite 包拥有一套对账/事务生命周期;若没有第二个提供方证明其必要性,注册表只会拆分该状态。 + +## 后果 + +继承的精确读取实现只有一个来源解析状态变量:当前挂载的持久化服务。它没有提供方队列、指纹、提取器注册表、观察代次或派生索引更新;具体后端单独拥有其全文搜索状态。精确读取、语义扫描和事件追踪在纯活跃部署中仍然可用,在持久化存在时具有确定性。 + +跨语料库列表、血缘追踪和持久化事件操作在每次调用时执行后端 I/O。这是有意为之:正确性来自当前权威状态,而面向规模的全文搜索方法使用具体后端的 SQLite 派生索引。 diff --git a/.agents/notes/implemented/feature/2026-07-10-sqlite-session-query-provider.i18n.yaml b/.agents/notes/implemented/feature/2026-07-10-sqlite-session-query-provider.i18n.yaml new file mode 100644 index 0000000000..da1ff70e09 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-10-sqlite-session-query-provider.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-10-sqlite-session-query-provider.md: be8795b609b52eeb03268c4986b52004eef0dba9 +2026-07-10-sqlite-session-query-provider.zh.md: bb3650da907cf86a853f748fa0ee40d5c2168709 diff --git a/.agents/notes/implemented/feature/2026-07-10-sqlite-session-query-provider.md b/.agents/notes/implemented/feature/2026-07-10-sqlite-session-query-provider.md index ff57904358..be8795b609 100644 --- a/.agents/notes/implemented/feature/2026-07-10-sqlite-session-query-provider.md +++ b/.agents/notes/implemented/feature/2026-07-10-sqlite-session-query-provider.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-07-10-sqlite-session-query-provider.zh.md) + ## Problem The exact-read `ctx.sessionQuery` service deliberately has no derived index. Large persisted histories need full-text search without scanning every event on every query, while current live sessions need an overlay newer than the last durability checkpoint. Search also needs concrete ranking, snippets, filters, pagination, cancellation, and rebuild behavior. @@ -36,7 +38,7 @@ One serialized operation reads the provider-neutral `SessionPersistence` snapsho Persisted documents survive restarts. Live sessions use connection-local TEMP tables, shadow the persisted base for the same id, and reveal that base on detach. Closing the database drops live rows. Unmounting persistence hides durable rows without treating absence as authoritative deletion; remounting observes and reconciles the backend again. Conflicting immutable live and durable headers fail rather than combining sources. -The derived schema has its own application id and monotonic schema version. A recognized incompatible version resets only this derived database. A database with a foreign application id or unrecognized user tables is refused before journal-mode mutation, which prevents an accidentally configured canonical session database from being changed. On POSIX filesystems, missing directories and database files are created owner-only so new SQLite sidecars inherit that mode; existing modes are preserved. One service in one process exclusively owns a derived-index path; cross-process writers are unsupported because generations and live TEMP shadow state are connection-owned. +The derived schema has its own application id and monotonic schema version. Persistent and TEMP session metadata store the integer `SessionHeader.createdAt` contract in strict `INTEGER` columns. A recognized incompatible version resets only this derived database. A database with a foreign application id or unrecognized user tables is refused before journal-mode mutation, which prevents an accidentally configured canonical session database from being changed. On POSIX filesystems, missing directories and database files are created owner-only so new SQLite sidecars inherit that mode; existing modes are preserved. One service in one process exclusively owns a derived-index path; cross-process writers are unsupported because generations and live TEMP shadow state are connection-owned. Cancellation rejects queued operations and caller waits around asynchronous source observation without committing an aborted observation. Node's synchronous `DatabaseSync` MATCH call cannot be interrupted once it is executing on the JavaScript thread, so the service checks the signal at serialized boundaries but does not promise mid-statement preemption. diff --git a/.agents/notes/implemented/feature/2026-07-10-sqlite-session-query-provider.zh.md b/.agents/notes/implemented/feature/2026-07-10-sqlite-session-query-provider.zh.md new file mode 100644 index 0000000000..bb3650da90 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-10-sqlite-session-query-provider.zh.md @@ -0,0 +1,59 @@ +# Agent Note: SQLite FTS5 会话搜索 + +Status: implemented + +[English](2026-07-10-sqlite-session-query-provider.md) | 中文 + +## 问题 + +精确读取的 `ctx.sessionQuery` 服务有意不维护派生索引。大规模持久化的历史记录需要全文搜索,而不是每次查询都扫描全部事件;当前的活跃会话则需要一个比上一次持久性检查点更新的覆盖层。搜索还需要具体的排序、摘要片段、过滤器、分页、取消以及重建行为。 + +如果把这些关注点拆分到提供方协调器和数据库实现之间,就会产生两个耦合的对齐状态机。第一个实现既要暴露精简的提供方无关调用契约,也要在同一个生命周期内管理源观察、提取、SQLite 事务、代际与查询执行。 + +## 决策 + +`@deepseek-ai/dsh-session-query` 声明一个抽象的 `ctx.sessionQuery` 服务,其精确读取、过滤与追踪均有具体实现,仅有两项全文方法为抽象方法。`searchSessions(request, exec?)` 返回按游标分页的 `SessionSearchHit`,并按每个会话中匹配度最强的事件分组;`searchEvents(request, exec?)` 返回一个逻辑会话内的 `SessionEventSearchHit`。两种请求都必须提供 `query`,可以接受 `limit` 和由服务拥有的品牌化 `SessionSearchCursor`,并支持可选的中止信号。会话搜索接受 `sessionFilters` 与事件元数据过滤器,事件搜索接受事件元数据过滤器。结果会公开有界的纯文本摘要片段,但不公开提供方标识符或数值相关性分数。单一键拓扑由[统一服务决策](../architecture/2026-07-23-unified-session-query-service.md)定义。 + +`@deepseek-ai/dsh-session-query-sqlite` 扩展接口服务,并且是 `ctx.sessionQuery` 唯一的具体所有者。它依赖实时的 `ctx.sessions`,动态观察可选的 `ctx.sessionPersistence`,并拥有一个专用的派生 SQLite 数据库。系统没有搜索提供方注册表、协调器、持久化事件或 agent loop(智能体循环)集成。 + +接口包还拥有共享的第一方语义提取与提供方无关的过滤。`SessionResultFilter` 涵盖 id、可空的 cwd、创建时间范围、可空的父会话与可用性;`ctx.sessionQuery.filterSessions()` 无需 FTS 提供方即可应用这些过滤器。`SessionEventResultFilter` 涵盖 seq/时间范围、事件类型、surface 与字面语义文本。过滤器数组内各项按逻辑与(AND)组合,列表值按逻辑或(OR)组合。文本子句会将调用方输入转义为不区分大小写的 Unicode 正则表达式,其中每段连续空白都匹配一个或多个空白字符;该子句通过 `ctx.sessionQuery.filterEvents()` 提供,不会委托给 FTS 提供方。 + +## 搜索语义 + +每个语义事件对应一份 FTS 文档,其中携带会话元数据、事件元数据、surface 分类与提取文本。除非 surface 过滤器缩小范围,否则所有 `current`、`shadowed` 与 `log-only` 文档都会参与搜索。元数据过滤器在排序前编译为参数化 SQL。会话结果按会话划分匹配文档,并保留匹配度最强的文档。 + +排序在持久化 FTS 表与 TEMP FTS 表之间具有确定性和可比性:先按实际 FTS5 高亮匹配区段数量降序,再按已索引文档的码点长度升序、事件时间降序、跨会话范围内的会话 id 升序,最后按 seq 降序排列。摘要片段使用这些实际高亮位置,移除保留标记、规范化空白,并按 Unicode 码点限制长度。不透明游标会绑定到服务实例、范围、规范化后的标准请求、偏移量与相关代际。语料库发生任何变更都会使跨会话游标失效;会话内游标仅在其目标源或代际发生变化时失效,因此不相关的会话不会使其失效。重新打开服务会创建新的服务实例,并使旧游标失效。 + +查询会先去除首尾空白并规范化内部空白,再作为一个字面 FTS5 短语整体加引号。嵌入的引号在绑定前写成两个,因此 `OR`、`NEAR`、引号、括号与 `*` 等 MATCH 运算符会作为数据,而不是可执行的查询语法。系统会在 SQLite 执行前拒绝 NUL。文档中的保留高亮非字符与 NUL 会在索引前规范化,因此插入的呈现标记不会与源文本冲突。短语匹配遵循分词器 token,而不是任意子串。 + +## 分词器选择 + +持久化 FTS5 表与实时 FTS5 表都使用 `unicode61`。实现实验表明,该分词器支持由两个字符组成的 token `AI`,生成的索引体积约为 trigram 方案的 1/2.1。系统接受的限制是 token/短语召回:`AI` 不会匹配较长的 token `BRAID`,任意子串搜索改用提供方无关的文本扫描。 + +## 提取与对齐 + +共享提取器会提取消息文本、推理(reasoning)、嵌套的工具调用/结果内容、工具名称与参数、被阻止提示词的原因、待办事项状态与内容,以及错误或结束状态详情。结构性边界、流式分片、请求头、成功完成标记,以及通过声明合并扩展的未知事件/内容变体都不会产生文档。surface 分类复用 `foldSurface()`,使搜索与模型历史派生保持一致。 + +一个串行化操作会读取提供方无关的 `SessionPersistence` 快照清单,将每个包含源身份的不透明修订号与同已索引会话一并存储的修订号比较,只加载新增或变更的日志,在一个事务中对齐各行,然后执行查询。它绝不会调用后端会修改状态的 `load()` 来处理当前由 `ctx.sessions` 拥有的 id;TEMP 覆盖层会记录持久化可用性,实时所有者分离后,持久化基础层随之刷新。修订号同时标识其底层持久化存储与后端本地日志修订版本,因此针对同一存储重新打开服务可以复用已索引行,而切换到独立存储时不会因会话 id 与本地计数器相同而发生冲突。如果加载期间清单发生变化,系统会重复观察;因此,会修改状态的加载修复所产生的新修订号会在提交前纳入结果。重复查询与针对未变更存储的重新打开都不会加载完整的持久化日志。新增、变更与删除的会话会在下一次稳定搜索中更新。源或提取失败不能将某一行标记为当前状态,事务失败则会回滚,使后续搜索能够重试。 + +持久化文档在重启后仍然存在。实时会话使用连接本地的 TEMP 表,遮蔽相同 id 的持久化基础行,并在实时所有者分离时重新显露该基础行。关闭数据库会删除实时行。卸载持久化服务会隐藏持久化行,但不会把缺失视为权威删除;重新挂载后,系统会再次观察并对齐后端。实时会话头与持久化会话头的不可变字段发生冲突时,系统会失败,而不会合并两个来源。 + +派生 schema 拥有独立的 application id 与单调递增的 schema 版本。持久化与 TEMP 会话元数据均遵循 `SessionHeader.createdAt` 的整数契约,将其存入严格的 `INTEGER` 列。系统识别到不兼容版本时,只会重置该派生数据库。如果数据库具有不属于本应用的 application id 或无法识别的用户表,系统会在修改日志模式前拒绝该数据库,防止意外配置的规范会话数据库遭到修改。在 POSIX 文件系统上,缺失的目录与数据库文件会以仅所有者可访问的权限创建,使新的 SQLite 伴随文件沿用该模式;现有权限模式保持不变。一个进程中的一个服务独占一条派生索引路径;代际与实时 TEMP 遮蔽状态都归连接所有,因此不支持跨进程写入方。 + +取消会拒绝排队中的操作,并终止调用方对异步源观察的等待;已经中止的观察结果不会提交。Node 的同步 `DatabaseSync` MATCH 调用一旦开始在 JavaScript 线程上执行就无法中断,因此服务会在串行化边界检查信号,但不承诺在语句执行期间抢占。 + +## 曾考虑的替代方案 + +- **将 FTS 表添加到规范持久化数据库**:不予采纳,因为可重建索引不应与权威日志共享 schema、重置或故障边界。 +- **添加第一阶段的提供方注册表与协调器**:不予采纳,因为单一实现无法证明注册语义,并且会将一个对齐生命周期拆给两个所有者。 +- **立即持久化实时覆盖层**:不予采纳,因为在现有检查点提交前,实时事件并非规范数据。 +- **使用 FTS5 trigram 分词器**:不予采纳,因为它会遗漏短于三个字符的有用查询,并且测得的索引体积约为 `unicode61` 的 2.1 倍;扫描路径仍可提供字面子串过滤。 +- **在每个表中独立使用 FTS5 BM25**:不予采纳,因为填充内容不同的持久化语料库与 TEMP 语料库所产生的分数不可比较;实际匹配区段与文档长度采用同一套尺度。 + +## 后果 + +搜索只公开精简的提供方无关 API,而唯一后端负责派生索引的全部状态转换。独立数据库增加了配置与查询前的轻量快照读取,但索引损坏、重置与分词器变更都不会危及规范日志。持久化修订号使未变更会话无需读取或重写完整日志;TEMP 实时覆盖层保留当前会话事实,同时不会让尚未经过检查点的事件具有持久性。 + +选定的分词器以较小的索引体积支持短 token,但不承诺子串召回。字面短语使查询语法安全且可预测,代价是不支持布尔表达式或完整 MATCH 表达式。取消在操作排队或等待数据源期间有效,但同步 SQLite 执行仍是不可抢占区段。 + +单元测试将以下行为固化为契约:提取、过滤器、两种搜索范围、所有默认 surface、先过滤元数据再排序、摘要片段、字面量转义、确定性平局处理、完整分页、按范围的游标失效、动态挂载/卸载持久化服务、重启对齐、实时遮蔽、显露与重新打开、schema 安全、回滚重试,以及排队中或进行中的数据源等待取消。一个无需密钥的真实 Loader 路径测试会将该包与真实的 SQLite 持久化后端组合使用。 diff --git a/.agents/notes/implemented/feature/2026-07-12-subagent-persona-tool-filter-and-depth.i18n.yaml b/.agents/notes/implemented/feature/2026-07-12-subagent-persona-tool-filter-and-depth.i18n.yaml new file mode 100644 index 0000000000..d7dfbedded --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-12-subagent-persona-tool-filter-and-depth.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-12-subagent-persona-tool-filter-and-depth.md: c690f4701a54272205eedf719fbfe0863bac566c +2026-07-12-subagent-persona-tool-filter-and-depth.zh.md: 6e9e9ad44fff4dee6ddb286227485420d100f4ee diff --git a/.agents/notes/implemented/feature/2026-07-12-subagent-persona-tool-filter-and-depth.md b/.agents/notes/implemented/feature/2026-07-12-subagent-persona-tool-filter-and-depth.md index 0f42a547cf..c690f4701a 100644 --- a/.agents/notes/implemented/feature/2026-07-12-subagent-persona-tool-filter-and-depth.md +++ b/.agents/notes/implemented/feature/2026-07-12-subagent-persona-tool-filter-and-depth.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-07-12-subagent-persona-tool-filter-and-depth.zh.md) + ## Problem A reusable subagent provider answers how to run a child, but different delegation tools need different child behavior. One deployment may want a reviewer persona, a research-only tool set, or a hard recursion bound without creating a new provider for every combination. diff --git a/.agents/notes/implemented/feature/2026-07-12-subagent-persona-tool-filter-and-depth.zh.md b/.agents/notes/implemented/feature/2026-07-12-subagent-persona-tool-filter-and-depth.zh.md new file mode 100644 index 0000000000..6e9e9ad44f --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-12-subagent-persona-tool-filter-and-depth.zh.md @@ -0,0 +1,96 @@ +# Agent Note: 配置 subagent 的人设、工具可见性与深度 + +Status: implemented + +[English](2026-07-12-subagent-persona-tool-filter-and-depth.md) | 中文 + +## 问题 + +一个可复用的 subagent 提供方解决的是「如何运行子 agent(智能体)」的问题,但不同的委派工具需要不同的子 agent 行为。某个部署可能需要评审者人设、仅限研究的工具集,或硬性递归上限,而不必为每种组合创建新的提供方。 + +这些控制影响子 agent 的第一次模型请求,因此不能在子 agent 可见之后再安装。它们还需要提供方的诚实支持:ACP(Agent Client Protocol)后端不能默默接受一个仅限进程内的工具过滤器,而过滤器在所有插件运行于同一可信进程的情况下也不应被描述为安全边界。 + +## 决策 + +subagent 启动有三个独立的组合控制:`persona`、`toolFilter` 和 `maxDepth`。提供方声明对每个控制的支持情况,服务在启动运行之前拒绝不受支持的请求,进程内提供方在子 agent 尚未发布时安装所请求的组合。 + +这些控制回答不同的问题: + +| 控制 | 问题 | 结果 | +|---|---|---| +| `persona` | 什么角色指令替换该子 agent 的部署人设? | 一个子 agent 局部的提示词段落遮蔽 `deployment:persona` | +| `toolFilter` | 部署全局工具中哪些进入该子 agent 的可见工具视图? | 一个有作用域的限制在添加子 agent 局部工具之前过滤全局工具 | +| `maxDepth` | 这棵委派树最深可以长到多少层? | 子 agent 深度超过绝对上限时,启动请求被拒绝 | + +`dsh-tool-subagent` 将这些控制作为插件配置暴露,并复制到它创建的每个请求中。直接调用 `SubagentService` 的调用方可以按请求选择这些控制。提供方的能力描述符仍然是后端能否兑现各字段的真源。 + +### 人设是有作用域的遮蔽 + +人设控制改变一个子 agent 的行为,而不改变部署级的提示词组装。在未发布的设置阶段,进程内提供方在子 agent 作用域中注册一个名为 `deployment:persona` 的段落;普通的最具体者优先解析规则仅在该子 agent 的组装中替换全局段落。 + +其值与部署人设具有相同的严格模板语义。省略时通过全局层继承部署段落;显式空字符串则以空段落遮蔽全局人设。父级和兄弟级的人设永远不会进入子 agent 的扁平作用域。 + +这使用的是常规的系统提示词注册机制,而非第二条人设通道。因此第一次提示词看到的命名贡献与后续提示词和提示词检查工具看到的一致。 + +### 工具过滤是一条作用于全局视图的活规则 + +工具过滤同时控制能力可见性和可执行查找。进程内提供方在发布前于子 agent 作用域中安装 `ToolRegistry.restrict()`,注册表的单一解析器对协议格式(wire format)的工具 schema、查找、执行和 Code Mode SDK 生成施加相同的结果。独立注册的系统提示词段落不在 `ToolRegistry` 内,因此过滤一个工具不会移除该插件的独立指导文本。 + +解析遵循以下规则: + +1. 每条限制对活跃的部署全局工具注册表先应用 `allow` 再应用 `deny`。 +2. 多条限制取交集,因此每条已安装的限制都必须放行一个全局工具。 +3. 子 agent 作用域的工具在全局过滤之后添加,可以遮蔽一个已放行的全局工具。 +4. 保留的 `run_code` 呈现和其他作用域局部的协议贡献不受全局过滤器影响。 + +当过滤器既未提供 `allow` 也未提供 `deny`,或命名了当前全局可限制集合之外的内容(包括仅作用域局部或保留名称)时,配置会显式失败。`allow: []` 合法,且有意隐藏所有全局工具。这些检查能捕获拼写错误,并防止配置在无法影响所命名条目时看起来仍然有效。 + +全局注册表保持活跃。仅 deny 的过滤器会放行后来注册的全局名称(除非显式 deny 该名称);allow 列表会排除后来注册的全局名称(除非显式 allow 该名称)。移除一个全局工具会将其从所有已解析视图中移除。这些语义在保持热注册的同时,使 allow 与 deny 的区别显式化。 + +### 深度是绝对的树上限 + +深度限制独立于工具可见性来约束递归委派。顶层 agent 深度为零;进程内子 agent 的深度为其父级已验证深度加一。`maxDepth` 是一个绝对的非负安全整数,当推导出的子 agent 深度大于上限时,启动在子 agent 所有权开始之前即被拒绝。 + +有效父级深度取持久 `SessionHeader.delegationDepth` 与运行时 `AgentOptions.subagentDepth` 中的较大值。进程内子 agent 把推导出的深度记录在会话 header 中,恢复时会重新载入该 header,因此重启无法降低递归计数。 + +每个公开入口都自行验证值域,而非依赖单一的面向模型配置路径。负值、小数、负零、非有限值、不安全整数、格式错误的存储父级深度以及推导溢出均被拒绝。直接的 `SubagentStartRequest` 可以省略上限,让此机制不约束深度;经 Loader 解析的 `dsh-tool-subagent` 配置则默认值为 `3`、接受数值覆盖,并使用显式的 `'provider-managed'` 来省略由进程外提供方部署拥有递归预算时的上限。三是一个较小的有限默认值,仍允许 root 加三代后代:[SDK 辅助函数生成的 subagent 条目](../../../../packages/sdk/helper/src/features/builtin/index.ts)和 [JSON-RPC 示例](../../../../examples/jsonrpc-agent/cordis.yml)采用这项通用策略,而已交付的交互式 ACP、headless 和 REPL 示例固定为一。提供方缺少 `depthLimit` 时,数值工具上限会在提供方挂载阶段失败。 + +部署可以组合深度与过滤,但数值上限不会合成过滤器。委派工具在上限处仍然可见,因为授权可能依赖运行时状态;每次尝试启动都会检查调用方 agent 当前的持久与运行时深度,被拒绝的启动返回错误工具结果,且不发布子 agent。可见性策略固定的部署可以另外在子 agent 中 deny 委派工具。两种选择都不改变提供方的对话历史行为。 + +### 能力门控保持提供方诚实 + +能力将请求的功能与提供方实现分离。`SubagentCapabilities` 声明 `persona`、`toolFilter` 和 `depthLimit`;`SubagentService.start()` 在调用提供方之前,对照这些标志检查请求中每个存在的字段。 + +这使 spawn 和 fork 提供方可以共享进程内实现,而外部提供方只声明自己能强制执行的部分。请求永远不会静默降级:选择不受支持的控制会产生 `UNSUPPORTED_CAPABILITY`,不会有运行或生命周期事件存在。 + +### 未发布设置使第一次请求正确 + +所有子 agent 局部的组合在子 agent 变得可观察之前完成。进程内提供方向 agent 创建提供一个设置回调;该回调在子 agent 作用域中安装人设、工具限制和结构化输出贡献。只有设置成功后,创建才发布会话和 agent 并允许驱动器启动。 + +设置失败会回滚私有子 agent。没有观察者能获取到一个「第一次提示词使用了部署人设或未过滤工具集、后续提示词才使用所请求配置」的子 agent。 + +## 可见性不是授权 + +这些控制组合的是同一可信进程内的行为,而非授权行为。`toolFilter` 改变工具注册表解析出的子 agent 视图,但它不创建父到子的授权格,不要求子 agent 仅持有父级子集授权,不沙箱化插件,也不阻止持有另一个 Cordis 上下文的代码直接调用服务。 + +具体而言,子 agent 局部工具在全局过滤之后添加,可能不在父级视图中。仅 deny 的子 agent 也能看到 deny 列表未命名的后来全局工具。这些是有意的活组合语义,而非不可升权保证。 + +安全设计需要独立的授权表示、传播规则和执行时强制点。创建时的授权快照、父级子集授权、显式的未来授权 API,以及通用的能力/输出/终止标签均不在本功能范围内。 + +## 曾考虑的替代方案 + +**为每种人设或工具集创建一个提供方。** 这会使共享相同传输和生命周期实现的提供方成倍增加,使动态部署配置变得笨拙,且仍需要递归机制。提供方的职责是执行传输;请求承载每个子 agent 的组合。 + +**复制父级的完整工具视图。** 注册作用域设计上是扁平的,生命周期所有权不意味着可见性继承。复制已解析视图还会冻结动态全局注册,并在未完整定义任一契约的情况下混淆组合与授权。 + +**在子 agent 创建时快照允许的全局工具。** 冻结的 allow 集合使未来注册统一不可用,但它改变了热注册语义并开启了授权设计。已实现的过滤器保持为活跃的注册表谓词,并直接记录 allow 与 deny 的行为。 + +**仅隐藏工具 schema。** 仅呈现层的过滤让模型可以通过 Code Mode 或伪造调用执行一个提示词声称不存在的工具。改为由一个解析器同时管控呈现和执行。 + +**把深度上限编码为自动工具过滤器。** 创建时过滤器会快照一个可能依赖运行时状态的决策,只影响一个已配置工具名,且不保护直接服务调用方或替代委派工具。提供方改为在每次启动时强制绝对上限。 + +## 后果 + +贡献者可以配置子 agent 的角色、可见全局工具和递归深度,而无需定义新的提供方。能力检查在所有权开始之前失败,未发布设置使第一次请求一致,单一工具解析器防止呈现/执行漂移。 + +代价是部署方必须理解活跃的 allow/deny 行为以及可见性与授权的区别。当前深度策略禁止再创建子 agent 后,模型仍可能调用可见的委派工具并收到错误。提供方作者必须准确声明每个受支持的控制,进程内提供方必须在发布前安装所有请求的贡献。这些控制有意不解决安全隔离或父到子的不可升权问题。 diff --git a/.agents/notes/implemented/feature/2026-07-19-model-facing-goal-tools.i18n.yaml b/.agents/notes/implemented/feature/2026-07-19-model-facing-goal-tools.i18n.yaml index e53c591aa5..70ca07b414 100644 --- a/.agents/notes/implemented/feature/2026-07-19-model-facing-goal-tools.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-07-19-model-facing-goal-tools.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -2026-07-19-model-facing-goal-tools.md: 7cc3907d708115207e166455ea988120a03d768b -2026-07-19-model-facing-goal-tools.zh.md: 1a381160354d6a2a24f957f41bc9e375c1ab01ca +2026-07-19-model-facing-goal-tools.md: 286329390a058c0302520fd2203e5becb8c81395 +2026-07-19-model-facing-goal-tools.zh.md: b0b4fc99ada3597fbab58081f52309e21dd43bac diff --git a/.agents/notes/implemented/feature/2026-07-19-model-facing-goal-tools.md b/.agents/notes/implemented/feature/2026-07-19-model-facing-goal-tools.md index 7cc3907d70..286329390a 100644 --- a/.agents/notes/implemented/feature/2026-07-19-model-facing-goal-tools.md +++ b/.agents/notes/implemented/feature/2026-07-19-model-facing-goal-tools.md @@ -16,11 +16,11 @@ The surface also needs to preserve the separation between durable state and live ### Tools and model contract -`get_goal()` returns the current goal or `null`. A non-null result contains the compare-and-set id and revision, objective, durable phase, admitted and maximum goal rounds, any blocker reason, plus the process-local activation observation. `create_goal(objective, max_goal_rounds?)` creates one long-running same-session objective. `update_goal(goal_id, revision, action, objective?, max_goal_rounds?, blocked_reason?)` supports `edit`, `pause`, `resume`, `complete`, and `blocked`; replacement fields are valid only for `edit`, while a non-empty `blocked_reason` is required only for `blocked` and persists under the stable `model-reported` code. +`get_goal()` returns the current goal or `null`. A non-null result contains the compare-and-set id and revision, objective, durable phase, admitted and maximum goal rounds, any blocker reason, plus the process-local activation observation. `create_goal(objective, max_goal_rounds?)` creates one long-running same-session objective. `update_goal(goal_id, revision, action, objective?, max_goal_rounds?, blocked_reason?)` supports `edit`, `pause`, `resume`, `complete`, and `blocked`; replacement fields are valid only for `edit`, while a non-empty `blocked_reason` is required only for `blocked` and persists under the stable `model-reported` code. The executor treats exact empty-string optional fields and a zero `max_goal_rounds` as strict-schema fillers: they count as omitted, an edit still requires at least one meaningful replacement, and all non-filler values retain the action restrictions. The prompt tells the model that it may infer goal intent from a direct human request in any wording or language, but should not convert routine single-turn work into a goal. It must read the current goal before updating and copy the exact id and revision. On a restored or forked active-but-disarmed goal, a semantic human request to continue is grounds for `resume`. Completion is reserved for an achieved objective, and difficulty or uncertainty alone is not a blocker; a block report must name the concrete condition. -All three tools use exclusive execution so a model-ordered batch observes prior mutations and their new revisions. Results are compact JSON. ACP presentation is a pure function of arguments and uses generic read or mutation cards; activation is reported only as live observation and is never written into replay state. +All three tools use exclusive execution so a model-ordered batch observes prior mutations and their new revisions. Results are compact JSON. ACP presentation is a pure function of arguments and uses generic read or mutation cards; mutation cards select meaningful action values before the goal id, so accepted fillers cannot blank their input. Activation is reported only as live observation and is never written into replay state. An autonomous goal round that successfully reports completion or blocking contributes the existing terminal `agent/turn-stop` decision for that physical turn, preventing an unnecessary follow-up request. Direct-human mutations do not contribute a terminal stop: the assistant can acknowledge the change, and concurrent human steering remains available to ordinary continuation folding. @@ -38,7 +38,7 @@ Complete and blocked accept either direct-human authority or the exact current g ## Testing -Unit coverage pins registration and disposal, exclusive scheduling, generated prompt policy, generic presentation, direct-human creation in a non-English turn, exact/stale/non-running agent and driver checks, live-child rejection, resumed-fork root authority, steering, mismatched initiators, read/create/edit/pause/resume behavior, conditional blocker explanations, rearming after a session-start edge, authority-before-conditional-argument failures, exact goal-round completion, autonomous-only terminal stopping, the configured blocking threshold, and immediate human blocking. A keyless replay snapshot mounts the goal domain and tools into the real headless one-shot application, drives `create_goal` and `get_goal` through the shipped loop and persistence stack, pins its stream-json transcript, and inspects the externally persisted goal change. The echo-agent fixture is intentionally not used as an application-UX surrogate. +Unit coverage pins registration and disposal, exclusive scheduling, generated prompt policy, filler-safe generic presentation, direct-human creation in a non-English turn, exact/stale/non-running agent and driver checks, live-child rejection, resumed-fork root authority, steering, mismatched initiators, read/create/partial-edit/pause/resume behavior including strict-schema fillers, conditional blocker explanations, rearming after a session-start edge, authority-before-conditional-argument failures, exact goal-round completion, autonomous-only terminal stopping, the configured blocking threshold, and immediate human blocking. A keyless replay snapshot mounts the goal domain and tools into the real headless one-shot application, drives a strict-filler `update_goal` probe plus `create_goal` and `get_goal` through the shipped loop and persistence stack, pins its stream-json transcript, and inspects the externally persisted goal change. The echo-agent fixture is intentionally not used as an application-UX surrogate. ## Alternatives considered @@ -48,6 +48,7 @@ Unit coverage pins registration and disposal, exclusive scheduling, generated pr - **Authorize from persisted root or fork metadata** — rejected because a fork that becomes an independently resumed top-level session should accept new human authority, while a currently owned child should not. - **Let autonomous rounds edit or resume the goal** — rejected because continuation authority is narrower than authority to redefine or restart the human objective. - **Treat the blocked threshold as an evaluator** — rejected because event counts cannot prove that an obstacle is semantically unchanged or truly terminal. +- **Reject every present action-specific field** — rejected because strict-schema providers can serialize zero-value placeholders for every optional field; only meaningful values can express a conflicting action. ## Consequences @@ -56,6 +57,7 @@ Unit coverage pins registration and disposal, exclusive scheduling, generated pr - Human requests can create and rearm goals through ordinary natural language, while restored sessions remain inert until such input arrives. - Goal rounds can finish or report a repeated blocker but cannot broaden their own mandate. - Deployment policy selects the blocking lower bound; the same resolved value controls enforcement and prompt guidance. +- Strict-schema provider fillers interoperate without allowing meaningful cross-action updates. ## Known limitations and deferred work diff --git a/.agents/notes/implemented/feature/2026-07-19-model-facing-goal-tools.zh.md b/.agents/notes/implemented/feature/2026-07-19-model-facing-goal-tools.zh.md index 1a38116035..b0b4fc99ad 100644 --- a/.agents/notes/implemented/feature/2026-07-19-model-facing-goal-tools.zh.md +++ b/.agents/notes/implemented/feature/2026-07-19-model-facing-goal-tools.zh.md @@ -16,11 +16,11 @@ Status: implemented ### 工具与模型契约 -`get_goal()` 返回当前目标或 `null`。非空结果包含用于比较并交换的 id 与修订号、目标描述、持久阶段、已接纳和最大目标回合数、可能存在的阻塞原因,以及进程本地激活态观察。`create_goal(objective, max_goal_rounds?)` 创建一个长时间运行的同会话目标。`update_goal(goal_id, revision, action, objective?, max_goal_rounds?, blocked_reason?)` 支持 `edit`、`pause`、`resume`、`complete` 和 `blocked`;替换字段仅对 `edit` 有效,非空的 `blocked_reason` 仅在 `blocked` 时必填,并以稳定代码 `model-reported` 持久化。 +`get_goal()` 返回当前目标或 `null`。非空结果包含用于比较并交换的 id 与修订号、目标描述、持久阶段、已接纳和最大目标回合数、可能存在的阻塞原因,以及进程本地激活态观察。`create_goal(objective, max_goal_rounds?)` 创建一个长时间运行的同会话目标。`update_goal(goal_id, revision, action, objective?, max_goal_rounds?, blocked_reason?)` 支持 `edit`、`pause`、`resume`、`complete` 和 `blocked`;替换字段仅对 `edit` 有效,非空的 `blocked_reason` 仅在 `blocked` 时必填,并以稳定代码 `model-reported` 持久化。执行器把值恰好为空字符串的可选字段和值为 0 的 `max_goal_rounds` 视为严格 schema 占位值:这些值等同于省略;编辑时仍必须提供至少一个有实际意义的替换字段;所有非占位值仍受对应操作的限制。 提示词告诉模型:它可以从任何措辞或语言的直接人类请求中推断目标意图,但不应把常规单轮工作转换为目标。更新前必须读取当前目标,并复制准确的 id 和修订号。对于恢复或派生后处于活跃但未激活状态的目标,人类在语义上要求继续即可成为执行 `resume` 的依据。只有目标已经实现时才能标记完成,困难或不确定性本身不构成阻塞;阻塞报告必须说明具体条件。 -三个工具都采用独占执行,使模型排序的批次可以观察此前变更及其新修订号。结果为紧凑 JSON。ACP 展示是参数的纯函数,使用通用读取或变更卡片;激活态仅作为实时观察返回,绝不会写入回放状态。 +三个工具都采用独占执行,使模型排序的批次可以观察此前变更及其新修订号。结果为紧凑 JSON。ACP 展示是参数的纯函数,使用通用读取或变更卡片;变更卡片选择输入时,先取有实际意义的操作值,再取目标 id,因此允许的占位值不会使卡片输入留空。激活态仅作为实时观察返回,绝不会写入回放状态。 自主目标回合成功报告完成或阻塞后,插件会为该物理轮次贡献现有的终止型 `agent/turn-stop` 决策,避免再发起一次不必要的模型请求。直接人类发起的变更不会贡献终止决策:智能体可以确认该变更,并且并发的人类 steering(转向)仍可参与普通的继续执行折叠。 @@ -38,7 +38,7 @@ Status: implemented ## 测试 -单元测试固定注册与释放、独占调度、生成的提示词策略、通用展示、非英语轮次中的直接人类创建、精确/陈旧/非运行中智能体与驱动检查、实时子智能体拒绝、恢复后派生根的权限、steering、发起者不匹配、读取/创建/编辑/暂停/恢复行为、条件式阻塞说明、会话启动边沿后的重新激活、权限先于条件参数失败、准确目标回合的完成、仅自主回合触发终止、可配置阻塞阈值,以及人类立即阻塞。无密钥回放快照把目标领域和工具挂载到真实的 headless 单次运行应用中,通过随附循环与持久化栈驱动 `create_goal` 和 `get_goal`,固定 stream-json 转录,并检查外部持久化的目标变更。这里有意不把 echo-agent 测试夹具当作应用 UX 的替代品。 +单元测试固定注册与释放、独占调度、生成的提示词策略、可安全处理占位值的通用展示、非英语轮次中的直接人类创建、精确/陈旧/非运行中智能体与驱动检查、实时子智能体拒绝、恢复后派生根的权限、steering、发起者不匹配、读取/创建/部分字段编辑/暂停/恢复行为(包括严格 schema 占位值)、条件式阻塞说明、会话启动边沿后的重新激活、权限先于条件参数失败、准确目标回合的完成、仅自主回合触发终止、可配置阻塞阈值,以及人类立即阻塞。无密钥回放快照把目标领域和工具挂载到真实的 headless 单次运行应用中,通过随附循环与持久化栈驱动一次携带严格 schema 占位值的 `update_goal` 探测,以及对 `create_goal` 和 `get_goal` 的调用,固定 stream-json 转录,并检查外部持久化的目标变更。这里有意不把 echo-agent 测试夹具当作应用 UX 的替代品。 ## 考虑过的替代方案 @@ -48,6 +48,7 @@ Status: implemented - **根据持久的根或派生元数据授权**——不予采纳,因为成为独立恢复顶层会话的派生应接受新的人类权限,而当前仍受所有权约束的子智能体则不应接受。 - **允许自主回合编辑或恢复目标**——不予采纳,因为继续执行权限比重新定义或重启人类目标的权限更窄。 - **把阻塞阈值当作评估器**——不予采纳,因为事件计数无法证明障碍在语义上未改变或确实不可继续。 +- **拒绝所有已提供的特定操作字段**——不予采纳,因为采用严格 schema 的提供方可能为每个可选字段序列化零值占位符;只有有实际意义的字段值才能表示与指定操作相冲突的另一项操作。 ## 后果 @@ -56,6 +57,7 @@ Status: implemented - 人类可以通过普通自然语言请求创建和重新激活目标,而恢复后的会话在收到此类输入前保持静止。 - 目标回合可以完成或报告重复阻塞,但不能自行扩大任务权限。 - 部署策略选择阻塞下限;同一个解析后的值同时控制执行与提示词指导。 +- 系统可兼容采用严格 schema 的提供方所填入的占位值,同时不会放行有实际意义的跨操作更新。 ## 已知限制与延期工作 diff --git a/.agents/notes/implemented/process/2026-06-11-doc-sync-enforcement.i18n.yaml b/.agents/notes/implemented/process/2026-06-11-doc-sync-enforcement.i18n.yaml new file mode 100644 index 0000000000..19b6055f0a --- /dev/null +++ b/.agents/notes/implemented/process/2026-06-11-doc-sync-enforcement.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-11-doc-sync-enforcement.md: 375059312c312dff7b5ddcb95ea5b82ac8cd4d06 +2026-06-11-doc-sync-enforcement.zh.md: 5c17263bdc2b4908a82237d1fc3b08f1f22a62d9 diff --git a/.agents/notes/implemented/process/2026-06-11-doc-sync-enforcement.md b/.agents/notes/implemented/process/2026-06-11-doc-sync-enforcement.md index 67cdfd6771..375059312c 100644 --- a/.agents/notes/implemented/process/2026-06-11-doc-sync-enforcement.md +++ b/.agents/notes/implemented/process/2026-06-11-doc-sync-enforcement.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-06-11-doc-sync-enforcement.zh.md) + ## Problem AGENTS.md promises that docs and code stay strictly in sync, but the promise was verified by eyeball. Review caught drift twice — a cookbook example contradicting the type policy, and a README citing the wrong `registerAdapter` call. Out-of-sync docs are worse than no docs, and this codebase is built primarily by agents that follow gates far more reliably than prose (mechanical quality gates). Two classes of doc drift are mechanically checkable: code blocks that no longer compile, and the event-taxonomy table that duplicates the `interface Events` declarations. diff --git a/.agents/notes/implemented/process/2026-06-11-doc-sync-enforcement.zh.md b/.agents/notes/implemented/process/2026-06-11-doc-sync-enforcement.zh.md new file mode 100644 index 0000000000..5c17263bdc --- /dev/null +++ b/.agents/notes/implemented/process/2026-06-11-doc-sync-enforcement.zh.md @@ -0,0 +1,32 @@ +# Agent Note: Doc-sync 强制 + +Status: implemented + +[English](2026-06-11-doc-sync-enforcement.md) | 中文 + +## 问题 + +AGENTS.md 承诺文档与代码严格同步,但这一承诺此前仅靠人眼核查。评审曾两次发现漂移:一次是实操手册(cookbook)示例与类型策略矛盾,一次是 README 引用了错误的 `registerAdapter` 调用。失去同步的文档比没有文档更糟;而本代码库主要由 agent(智能体)构建,agent 遵守门禁远比遵守行文约定可靠(机械质量门禁)。有两类文档漂移可以被机械检查:不再能编译的代码块,以及与 `interface Events` 声明重复的事件分类体系表。 + +## 决策 + +两道门禁,沿用既有的 `scripts/` 风格(tsx ESM,每个脚本一项职责): + +1. **`doc-typecheck`** 从 `README.md`、`docs/**` 和 `packages/*/README.md` 中提取所有 ` ```ts ` 围栏代码块,写入一个继承根 `tsconfig.json` 的临时项目,然后用 `tsc -b` 编译。临时项目复用源码的 `paths` 映射和根 project references,因此文档示例能看到源码,而 vendor 代码仍在其自身的 tsconfig 设置下被检查。刻意作为草图的代码块可通过显式的 ` ```ts ignore-check ` 信息字符串来 opt-out;脚本会报告 opt-out 比例,超过一半即失败,防止该豁免机制悄然成为常态。 +2. **`verify-event-taxonomy`** 从 `packages/*/src` 中的 `interface Events` 块和 `docs/architecture.md` 中的分类体系表分别提取事件名称,断言两个集合完全一致。只校验,不生成:表格保留手写的 Mode/Purpose 列,仅检查名称集合。(落地此门禁时发现了表格遗漏的三个事件:`tools/change`、`llm/adapter-change`、`system-prompt/change`。)**已被取代**:由[生成式 Cordis 目录](2026-06-20-generated-cordis-catalog.md)取代。此门禁及其 `architecture.md` 表格已退役,取而代之的是完全生成的 `docs/cordis-catalog/events.md` + `docs/cordis-catalog/services.md` 及其 `verify-cordis-catalog` 新鲜度门禁。本 Agent Note(agent 决策记录)中的其他门禁(`doc-typecheck` 以及下文修订中的 `verify-md-wrap`)不受影响。 + +两者都通过 package.json 中共享的 `doc-sync` 脚本运行;贡献者在相关文档变更中调用它,CI 则执行完整检查。[快速本地 Git 钩子](2026-07-22-fast-local-git-hooks.md)决策使这类按变更面选择的工作不进入 commit 和 push 钩子。 + +**修订(2026-06-17):** 第三道门禁 **`verify-md-wrap`** 随后被纳入 `doc-sync`。它使用 `mdast-util-from-markdown` + GFM 解析范围内的每个 Markdown 文件(`README.md`、`docs/**`、`packages/*/README.md`,加上 `AGENTS.md` / `packages/AGENTS.md`),如果任何 `paragraph` 节点跨越多个源码行则失败,从而强制执行 docs/AGENTS.md 中「一个段落一个物理行」的写作规则。同样遵循只校验不生成的原则:它报告硬换行但从不重写,因此不会引入格式化噪音。`doc-sync` 现在包含三道门禁。 + +## 曾考虑的替代方案 + +- **API-extractor 基准报告**([已推迟的提案](../../proposed/process/2026-06-11-api-extractor-reports.md)):有意推迟。对于评审者已能直接看到源码 diff 的内部 monorepo 而言价值有限,且依赖重、配置繁琐。 +- **从源码生成分类体系表**而非仅校验名称:否决,机制比问题本身更重;表格保留了手写的 Mode/Purpose 列,直到[生成式 Cordis 目录](2026-06-20-generated-cordis-catalog.md)完全取代了这项检查。 + +## 后果 + +- 可检查类别中的文档漂移会直接使 `doc-sync` 和 CI 失败,而不是等评审人发现。这是「机械门禁优于行文规范」原则的具体应用。 +- 让文档代码片段可编译需要少量 stub import/`declare`;`ignore-check` 比例必须保持低位,否则门禁形同虚设(比例守卫强制执行此约束)。 +- 分类体系检查仅限名称——Mode 或 Purpose 列的错误仍需人工评审。 +- 如果包(package)未来对外发布,API 报告方案仍可重新考虑。 diff --git a/.agents/notes/implemented/process/2026-06-11-quality-gates.i18n.yaml b/.agents/notes/implemented/process/2026-06-11-quality-gates.i18n.yaml new file mode 100644 index 0000000000..6d017a8961 --- /dev/null +++ b/.agents/notes/implemented/process/2026-06-11-quality-gates.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-11-quality-gates.md: e1af110387936d644208dc1829fde4a4fdf8a3f9 +2026-06-11-quality-gates.zh.md: a4e57b7a08ecf20babb33b55d8c94414df1b10b1 diff --git a/.agents/notes/implemented/process/2026-06-11-quality-gates.md b/.agents/notes/implemented/process/2026-06-11-quality-gates.md index 5e1db16e52..e1af110387 100644 --- a/.agents/notes/implemented/process/2026-06-11-quality-gates.md +++ b/.agents/notes/implemented/process/2026-06-11-quality-gates.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-06-11-quality-gates.zh.md) + The hook/CI symmetry in this record is superseded by [Fast local Git hooks](2026-07-22-fast-local-git-hooks.md); CI remains the exhaustive enforcement path. ## Problem diff --git a/.agents/notes/implemented/process/2026-06-11-quality-gates.zh.md b/.agents/notes/implemented/process/2026-06-11-quality-gates.zh.md new file mode 100644 index 0000000000..a4e57b7a08 --- /dev/null +++ b/.agents/notes/implemented/process/2026-06-11-quality-gates.zh.md @@ -0,0 +1,30 @@ +# Agent Note: 以机械质量门禁取代行文约定 + +Status: implemented + +[English](2026-06-11-quality-gates.md) | 中文 + +本记录中的钩子/CI 对称设计已由[快速本地 Git 钩子](2026-07-22-fast-local-git-hooks.md)取代;CI 仍是执行完整检查的路径。 + +## 问题 + +本代码库主要由 coding agent(智能体)开发。相比行文约定,agent 遵守强制门禁的可靠性远高得多;而当劳动由 agent 承担时,「工作量大」不构成成本论据。早期证据:未通过类型检查的测试被提交(vitest 不做类型检查),仅在评审中才被发现。 + +## 决策 + +每条可机械检查的 AGENTS.md 承诺都有一个以非零状态退出的命令。CI 执行完整集合,而 Git 钩子将延迟预算留给可低成本发现的本地缺陷: + +- 最严格的 TypeScript 配置(`noUncheckedIndexedAccess`、`exactOptionalPropertyTypes` 等);示例、测试和脚本通过根目录的 no-emit `tsconfig.json` 在 CI 中进行类型检查,而包(package)/vendor 代码保持在各自 project-reference 边界之后。 +- ESLint strict-type-checked + @stylistic(作为强制执行的统一代码风格),包括文件内重复逻辑检查;vendor 代码排除在外。 +- jscpd 检测包的生产 TypeScript 代码与仓库脚本中的跨文件克隆;窄范围的源码区间例外用于记录有意为之的并行实现。 +- `packages/*/*/src` 下按文件 100% 覆盖率(v8);不可达的防御性守卫使用 `/* v8 ignore */ ` 并注明理由,而非删除。 +- knip(死代码/依赖)、publint(包的正确性)、workspace 约束(workspace 规则:private、cordis peer+dev、统一版本、ESM),以及对构建出的包声明文件进行 NodeNext 消费方类型检查。 +- lefthook pre-commit 修复已暂存文件的 lint 问题、拒绝已暂存的空白问题并检查 vendor manifest;pre-push 运行增量类型检查。CI 在 Node 22.19/24/26 上运行完整矩阵,并对 Headless、TUI、ACP(Agent Client Protocol)、JSON-RPC、工作流和代码运行时入口路径执行已构建应用的冒烟测试。 + +## 后果 + +- 约定不会因 agent 更替而失效;可低成本发现的 commit/push 缺陷在本地失败,其余完整规则违规在 CI 中失败。 +- 门禁本身也是需要维护的代码;配置变更与其他变更一样需要评审。 +- 100% 覆盖率的压力可能催生无断言的测试——变异测试是计划中的对策(见[变异测试提案](../../proposed/testing/2026-06-11-mutation-testing.md))。 + +<!-- agent-note-format: alternatives-not-recorded (pre-format Agent Note) --> diff --git a/.agents/notes/implemented/process/2026-06-11-tsdown-over-dumble.i18n.yaml b/.agents/notes/implemented/process/2026-06-11-tsdown-over-dumble.i18n.yaml new file mode 100644 index 0000000000..4ac1a926c4 --- /dev/null +++ b/.agents/notes/implemented/process/2026-06-11-tsdown-over-dumble.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-11-tsdown-over-dumble.md: e8cdaeb1e3331ffb04de024acff5b0e6ca3e6366 +2026-06-11-tsdown-over-dumble.zh.md: bb5feef585c1748f41d1b204313f1a4d8b357a17 diff --git a/.agents/notes/implemented/process/2026-06-11-tsdown-over-dumble.md b/.agents/notes/implemented/process/2026-06-11-tsdown-over-dumble.md index 0629acabb4..e8cdaeb1e3 100644 --- a/.agents/notes/implemented/process/2026-06-11-tsdown-over-dumble.md +++ b/.agents/notes/implemented/process/2026-06-11-tsdown-over-dumble.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-06-11-tsdown-over-dumble.zh.md) + ## Problem The initial build used **dumble**, the cordiverse zero-config esbuild wrapper that upstream Cordis itself builds with — maximum alignment with the vendored packages' conventions (it reads each package.json and infers entries/formats from the `exports` field). But dumble is a liability as a load-bearing tool in this repo: v0.2.x, ~530 npm downloads/week, effectively one maintainer, and we were invoking it through a custom orchestration script (`scripts/build.ts`) because it has no workspace mode. diff --git a/.agents/notes/implemented/process/2026-06-11-tsdown-over-dumble.zh.md b/.agents/notes/implemented/process/2026-06-11-tsdown-over-dumble.zh.md new file mode 100644 index 0000000000..bb5feef585 --- /dev/null +++ b/.agents/notes/implemented/process/2026-06-11-tsdown-over-dumble.zh.md @@ -0,0 +1,30 @@ +# Agent Note: 使用 tsdown 替代 dumble 进行 JS 打包 + +Status: implemented + +[English](2026-06-11-tsdown-over-dumble.md) | 中文 + +## 问题 + +最初的构建使用 **dumble**,即 cordiverse 的零配置 esbuild 包装层——上游 Cordis 自身也用它构建——与 vendor 包(package)的约定最大程度对齐(它读取每个 package.json 并从 `exports` 字段推断入口/格式)。但 dumble 作为本仓库的承重工具存在隐患:v0.2.x,每周约 530 次 npm 下载,实质上只有一位维护者,而且由于它没有 workspace 模式,我们不得不通过自定义编排脚本(`scripts/build.ts`)来调用它。 + +目前构建产物只在 `pnpm run build` + publint 中有意义(尚未发布任何包;开发/测试/演示通过 tsx 直接运行未打包的源码),因此切换成本现在最低,一旦包开始发布就只会更高。 + +## 决策 + +用 **tsdown**(基于 rolldown,每周约 250 万次下载,VoidZero 支持,活跃发布)替代 dumble: + +- 根目录 `tsdown.config.ts`,配置 `workspace: ['vendor/*', 'packages/*/*']`(显式 glob 将打包范围限定在 vendor 的 Cordis 与 TypeScript 包目录树内;`workspace: true` 还会发现示例 manifest 和不需要打包的 workspace 成员)。 +- 共享形状:入口为 `lib/types/index.js`,`outDir: 'lib'`,ESM,`platform: node`,`target: es2024`,`fixedExtension: false`(为 `"type": "module"` 包保留 `.js`),`dts: false`(声明归 tsc -b 所有),`clean: false`(lib/ 还保存 TSC 的 `lib/types` 中间树)。入口最初是 `src/index.ts`;[TSC 优先构建 Agent Note(agent 决策记录)](2026-06-17-ts-build-config.md)随后将 tsdown 改为打包 TSC 输出的 JS,使 TypeScript 转换行为统一由一个编译器提供。 +- vendor/ 中有两个按包覆盖的配置(属于我们自己的修改,与重新生成的 tsconfig 类似;记录在 vendor/README.md 中):schemastery(通过 `outExtensions` 输出双格式 `.mjs`/`.cjs`)、logger-console(两次单入口 pass,使共享基类被内联到每个入口而非生成哈希命名的分片,与上游发布形态一致)。 +- `scripts/build.ts` 删除;`pnpm run build` = `tsc -b && tsdown`(根 solution 拥有 emit 图)。 + +## 曾考虑的替代方案 + +- **直接编写 esbuild 脚本**:最成熟的引擎,零包装层风险,但需要手动维护 tsdown workspace 模式自动提供的按包规格表。 +- **pkgroll**:理念上最接近的直接替代品,但每周仅 78k 下载且基于 Rollup,维护前景严格弱于 tsdown。 +- **保留 dumble**:与上游完美对齐,但巴士因子不可接受。 + +## 后果 + +运行时 bundle 输出仍沿用 dumble 时代的公开入口形状(`lib/index.js`,以及包特有的变体,例如 `schemastery` 的 `lib/index.mjs`/`lib/index.cjs` 与 `logger-console` 的 `lib/browser.js`);根据 [TSC 优先构建 Agent Note](2026-06-17-ts-build-config.md),声明现位于 `lib/types` 下。External 仍来自各包的 dependencies/peerDependencies。我们放弃了 dumble 的 exports 字段推断:采用非默认形状的新包需要逐包提供 `tsdown.config.ts`,不能只依赖 package.json 字段。未来如果 `tsc -b` 成为瓶颈,tsdown 也可以接管声明打包(isolatedDeclarations);这需要另写一份 Agent Note。 diff --git a/.agents/notes/implemented/process/2026-06-11-vendor-cordis-as-source.i18n.yaml b/.agents/notes/implemented/process/2026-06-11-vendor-cordis-as-source.i18n.yaml new file mode 100644 index 0000000000..0e0c6693a2 --- /dev/null +++ b/.agents/notes/implemented/process/2026-06-11-vendor-cordis-as-source.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-11-vendor-cordis-as-source.md: ae6f5438c5817c61a549d9edb2041d538fbcebe6 +2026-06-11-vendor-cordis-as-source.zh.md: 8d6f0e39d53e1c85eaaa50c4c4bf1d9ef648d953 diff --git a/.agents/notes/implemented/process/2026-06-11-vendor-cordis-as-source.md b/.agents/notes/implemented/process/2026-06-11-vendor-cordis-as-source.md index a8895ba5e8..ae6f5438c5 100644 --- a/.agents/notes/implemented/process/2026-06-11-vendor-cordis-as-source.md +++ b/.agents/notes/implemented/process/2026-06-11-vendor-cordis-as-source.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-06-11-vendor-cordis-as-source.zh.md) + ## Problem DeepSeek Harness SDK is built on the Cordis framework. Cordis core was at 4.0.0-rc.6 (a release candidate) when this repo started; the harness depends on framework internals (fiber lifecycle, effect disposal, waterfall dispatch) whose exact behavior matters to the agent loop's correctness guarantees. diff --git a/.agents/notes/implemented/process/2026-06-11-vendor-cordis-as-source.zh.md b/.agents/notes/implemented/process/2026-06-11-vendor-cordis-as-source.zh.md new file mode 100644 index 0000000000..8d6f0e39d5 --- /dev/null +++ b/.agents/notes/implemented/process/2026-06-11-vendor-cordis-as-source.zh.md @@ -0,0 +1,27 @@ +# Agent Note: 将 Cordis 以源码形式收录,而非作为 npm 依赖 + +Status: implemented + +[English](2026-06-11-vendor-cordis-as-source.md) | 中文 + +## 问题 + +DeepSeek Harness SDK 构建于 Cordis 框架之上。本仓库启动时,Cordis core 处于 4.0.0-rc.6(一个候选发布版本);harness 依赖框架内部实现(fiber 生命周期、dispose(资源释放)、waterfall(瀑布式事件)分发),其确切行为直接关系到 agent loop(智能体循环)的正确性保证。 + +## 决策 + +将所需的 Cordis 包(core、loader、include、group、timer、hmr、logger-console)与 cordiverse 基础库(cosmokit、schemastery)以源码形式复制到 `vendor/`,扁平化放置,保留其原始 npm 包名以实现透明的 workspace 解析。真正的第三方依赖(js-yaml、chokidar、@standard-schema/spec 等)仍从 npm 获取。 + +`vendor/README.md` 是 manifest(元数据清单):记录每个包(package)的上游仓库 + commit SHA,以及一份详尽的本地修改日志。pre-commit 守卫(`scripts/check-vendor-manifest.sh`)会拒绝未在同一次提交中更新 manifest 的 vendor 源码变更。 + +## 曾考虑的替代方案 + +- **依赖 npm 包**:否决。core 处于候选发布阶段,harness 依赖框架内部实现(fiber 生命周期、dispose、waterfall 分发),agent loop 的正确性保证取决于这些行为的确切表现;上游 RC 版本升级可能在没有本地修复路径的情况下破坏它们。 +- **递归收录所有传递依赖**:否决。真正的第三方依赖(js-yaml、chokidar、@standard-schema/spec 等)仍从 npm 获取;只有内部实现对我们有影响的框架层才需要自行持有。 + +## 后果 + +- harness 完全持有其框架层:可审计、可打补丁、版本锁定。上游 RC 无法影响我们,框架 bug 可以在仓库内直接修复。 +- 上游同步是手动操作(流程记录在 manifest 中)。修改日志使 diff 范围始终可知。 +- 收录的包保留上游代码风格;lint 与严格性门禁将其排除(它们的 tsconfig 在本地放宽了我们较新的编译器选项)。 +- 从第一天起就有一个本地补丁:移除了 hmr 的 locale-YAML 导入(运行时 YAML 导入钩子未被收录)。 diff --git a/.agents/notes/implemented/process/2026-06-16-pnpm-over-yarn.i18n.yaml b/.agents/notes/implemented/process/2026-06-16-pnpm-over-yarn.i18n.yaml new file mode 100644 index 0000000000..6ae4e17a2b --- /dev/null +++ b/.agents/notes/implemented/process/2026-06-16-pnpm-over-yarn.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-16-pnpm-over-yarn.md: 9dee405f509897e2a173399e466d574c518fa9ab +2026-06-16-pnpm-over-yarn.zh.md: 3a5ff5e9b1fb0511a9191b2e3c35b61f00b705cd diff --git a/.agents/notes/implemented/process/2026-06-16-pnpm-over-yarn.md b/.agents/notes/implemented/process/2026-06-16-pnpm-over-yarn.md index 42eb4228b6..9dee405f50 100644 --- a/.agents/notes/implemented/process/2026-06-16-pnpm-over-yarn.md +++ b/.agents/notes/implemented/process/2026-06-16-pnpm-over-yarn.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-06-16-pnpm-over-yarn.zh.md) + ## Problem The repo shipped on **Yarn 4** with the `node-modules` linker — a deliberately conservative choice that behaves like npm's flat layout while giving us Yarn's workspaces and `yarn constraints`. It worked. But Yarn 4's Plug'n'Play heritage makes the `node-modules` linker the off-the-beaten-path mode, and the broader JS ecosystem — tooling defaults, CI actions, Corepack examples, contributor familiarity — increasingly centers on pnpm. For a repo that is built primarily by agents and read by occasional human contributors, "the package manager most tools and people expect" has real value: fewer surprises, better-trodden failure paths, more copy-pasteable answers. diff --git a/.agents/notes/implemented/process/2026-06-16-pnpm-over-yarn.zh.md b/.agents/notes/implemented/process/2026-06-16-pnpm-over-yarn.zh.md new file mode 100644 index 0000000000..3a5ff5e9b1 --- /dev/null +++ b/.agents/notes/implemented/process/2026-06-16-pnpm-over-yarn.zh.md @@ -0,0 +1,43 @@ +# Agent Note: 使用 pnpm 替代 Yarn 4 作为包管理器 + +Status: implemented + +[English](2026-06-16-pnpm-over-yarn.md) | 中文 + +## 问题 + +本仓库最初使用 **Yarn 4** 搭配 `node-modules` 链接器启动。这是一个刻意保守的选择:行为类似 npm 的扁平布局,同时享有 Yarn 的 workspaces 和 `yarn constraints`。它能正常工作。但 Yarn 4 源自 Plug'n'Play 的血统,使得 `node-modules` 链接器成为非主流模式;而更广泛的 JS 生态——工具默认值、CI action、Corepack 示例、贡献者的熟悉度——正日益以 pnpm 为中心。对于一个主要由 agent(智能体)构建、偶尔有人类贡献者阅读的仓库而言,「大多数工具和人所期望的包管理器」具有实际价值:更少的意外、更成熟的故障路径、更多可直接复用的解答。 + +切换成本目前处于最低点。本仓库尚无任何包(package)发布(每个包都是 `private: true`);开发/测试/演示全部通过 tsx **未构建**运行,因此包管理器只需做到:(a)解析并链接 `node_modules`,(b)运行 workspace 脚本,(c)强制执行 workspace 约束。唯一的 Yarn 特有资产是 `yarn.config.cjs`(`@yarnpkg/types` 约束引擎),体量小且可机械地重新表达。这与 [tsdown 决策](2026-06-11-tsdown-over-dumble.md)的逻辑一致:在爆炸半径尚小时,将承重工具换为生态更健康的选项。 + +## 决策 + +采用 **pnpm 11.7.0**,通过 `packageManager` 字段固定版本,经 Corepack 安装(与 Yarn 使用的机制相同): + +- **Workspaces** 从 `package.json` 的 `workspaces` 数组 + `.yarnrc.yml` 迁移到 `pnpm-workspace.yaml`(`vendor/*`、`packages/*`——同样的 glob;`examples/*` 保持非 workspace,与先前设置及 tsdown 的显式 glob 一致)。 +- **严格符号链接链接器**(pnpm 默认)取代 Yarn 的提升式 `node-modules` 链接器。我们刻意**不**添加 `node-linker=hoisted` / `shamefully-hoist` 逃生口:pnpm 的非扁平 `node_modules` 会让幻影依赖(引用未声明的传递依赖)大声失败,这对于一个以机械门禁为核心质量保障的仓库(见[机械质量门禁](2026-06-11-quality-gates.md))是一项*优势*。门禁套件(类型检查、lint、test、build、knip)是证明不存在此类幻影导入的安全网。 +- **构建脚本白名单。** pnpm 10+ 不运行依赖的生命周期脚本,除非将其加入白名单。`pnpm-workspace.yaml` 携带一份显式的 `allowBuilds` 映射(`esbuild`、`lefthook`、`@google/genai`、`protobufjs`)——与本仓库对模型/工具输出已有的供应链加固姿态一致,现在也应用于安装时的代码执行。`peerDependencyRules.allowedVersions.typescript: '>=5 <7'` 消除仓库内 TypeScript 的良性 peer 范围警告。 +- **约束变为包管理器无关。** `yarn.config.cjs`(导入 `@yarnpkg/types`,使用 `Yarn.workspaces()` / `workspace.set()`)被 `scripts/check-workspace-constraints.ts` 取代——一个纯 tsx 脚本,通过 `pnpm run constraints` 运行。它在相同的 `vendor` + `packages` 范围上强制执行完全相同的不变式:每个包 `private: true`;`@deepseek-ai/dsh-*` 包将 `cordis` 同时声明为对等依赖(peer dependency)和 dev 依赖且范围一致、使用根 `package.json` 的版本、设置 `type: module`;vendor 包仅检查 privacy。 +- 所有 CI、lefthook 钩子、`package.json` 脚本和文档中的 `yarn …` 动词变为 `pnpm …` / `pnpm run …`。`yarn.lock` → `pnpm-lock.yaml`(lockfile v9)。`.gitignore` 将 `.yarn/` 换为 `.pnpm-store/`。vendor README(如 `vendor/cordis/README.md`)按 Vendoring Policy 保持其上游 `yarn` 示例不变。 + +## 曾考虑的替代方案 + +- **保留 Yarn 4**——零变动,但押注于使用率较低的链接器模式和一个绑定单一包管理器的约束引擎。 +- **npm workspaces**——无处不在,但没有约束方案,monorepo 开发体验也较差。 +- **pnpm 搭配提升式链接器**——迁移更平滑,但放弃了幻影依赖安全性,而这正是迁移的核心正确性理由。 + +## 后果 + +约束检查失去了 Yarn 的自动**修复**能力(`workspace.set()` 能原地改写 manifest);tsx 脚本仅做检查,不通过时以非零退出码和消息退出。这是可接受的:CI 从未运行过 `--fix`,且需要手动编辑的情况很少。贡献者现在为 pnpm 而非 Yarn 运行 `corepack enable`;`pnpm exec lefthook install` 取代 `yarn lefthook install`(`postinstall` 钩子仍会运行 `lefthook install`)。 + +性能(迁移时在开发 NFS 文件系统上测量;单次运行样本,方差大——仅供方向性参考,非基准测试套件): + +| 场景 | Yarn 4 | pnpm 11 | +|---|---|---| +| 冷启动(空缓存/store,无 `node_modules`) | ~14 s | ~16 s | +| 热重链接(缓存/store 已热,`node_modules` 已删除) | ~12–14 s | ~15–22 s | +| 冻结,`node_modules` 存在(无操作重验证) | ~2–8 s | ~0.5–7 s | + +在快速本地磁盘上,pnpm 的内容寻址 store 通常在冷/热安装中胜出,尤其在多个检出之间的**磁盘占用**方面优势明显(一个全局 store 通过硬链接接入每个 `node_modules`,而 Yarn 每个 worktree 复制约 279 MB——部分开发者经常为本仓库保持约 10 个或更多 worktree)。该去重优势在上述迁移时数据中**未能**体现,因为测试 store 和 `node_modules` 位于不同文件系统,硬链接失效;在单文件系统的开发机或 CI 缓存上则适用。诚实的总结:在我们的 NFS 开发文件系统上,安装速度在噪声范围内不分伯仲;迁移的理由是生态对齐、幻影依赖安全性和跨检出磁盘去重,而非原始安装时间的胜出。 + +所有质量门禁(constraints、类型检查、lint、doc-sync、达到 100% 的 test:coverage、构建、knip、publint 以及已构建应用的冒烟测试)均在 pnpm 下通过,证明更换 linker 没有引入幽灵依赖故障。 diff --git a/.agents/notes/implemented/process/2026-06-17-ts-build-config.i18n.yaml b/.agents/notes/implemented/process/2026-06-17-ts-build-config.i18n.yaml new file mode 100644 index 0000000000..80f7838d45 --- /dev/null +++ b/.agents/notes/implemented/process/2026-06-17-ts-build-config.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-17-ts-build-config.md: 1275a635242ea887c941db9dc0554fd33acd4102 +2026-06-17-ts-build-config.zh.md: 7691118dd152874e2849f1ace686069c9ea3f61f diff --git a/.agents/notes/implemented/process/2026-06-17-ts-build-config.md b/.agents/notes/implemented/process/2026-06-17-ts-build-config.md index 529400b8d7..1275a63524 100644 --- a/.agents/notes/implemented/process/2026-06-17-ts-build-config.md +++ b/.agents/notes/implemented/process/2026-06-17-ts-build-config.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-06-17-ts-build-config.zh.md) + > Root project topology (which tsconfig owns which graph) has since moved to a solution root over two aggregate programs; see the [solution-root note](2026-07-22-tsconfig-solution-root-two-aggregates.md). The tsc-first pipeline decided here is unchanged. ## Problem diff --git a/.agents/notes/implemented/process/2026-06-17-ts-build-config.zh.md b/.agents/notes/implemented/process/2026-06-17-ts-build-config.zh.md new file mode 100644 index 0000000000..7691118dd1 --- /dev/null +++ b/.agents/notes/implemented/process/2026-06-17-ts-build-config.zh.md @@ -0,0 +1,80 @@ +# Agent Note: TSC 优先构建与编译器单一归属 + +Status: implemented + +[English](2026-06-17-ts-build-config.md) | 中文 + +> 根项目拓扑(即哪个 tsconfig 拥有哪张图)后来改为由一个 solution 根文件统辖两个聚合 program;见[solution 根文件 Agent Note](2026-07-22-tsconfig-solution-root-two-aggregates.md)。本文确定的 TSC 优先流水线保持不变。 + +## 问题 + +此前的 TypeScript 构建与类型检查配置存在以下问题: + +- `build` 使用 `tsc` 将 `packages/<group>/<pkg>` 和 `vendor/*` 下的 `.ts` 转换为 `.d.ts` 文件,然后使用 `tsdown` 将 `.ts` 转换为打包后的 `.js` 文件。这导致两个工具各自执行 TypeScript 转换。 +- `typecheck` 倾向于通过一个根目录的类型检查配置来校验包(package)、vendor 源码、示例、测试和脚本。 + +目标是让构建与类型检查使用一致的 tsconfig 边界和 TypeScript 解析/转换行为。构建应通过单一编译器和配置生成 `.js`、`.d.ts`、`.js.map` 和 `.d.ts.map`,使发布产物与类型校验保持一致。 + +验证过程中发现了若干具体的技术问题和可能的路径: + +- `tsdown` 使用 `oxc` 进行 TypeScript 转换,其行为与 `tsc` 不同。 + - `tsdown` 输出的打包 `.d.ts` 与 Cordis 内部的相对模块增强(module augmentation)结构冲突。 + - tsc 的输出受 `allowImportingTsExtensions` 影响,因此需要确保生成的 `.js` 文件不会导入 `.ts` 文件,且生成的 `.d.ts` 文件保留 NodeNext/Node16 接受的显式相对说明符。为此,包内相对导入在 TypeScript 源码中使用显式 `.ts` 说明符,由 `rewriteRelativeImportExtensions` 在输出的 JS 中将其重写为 `.js`。 + - `tsdown` 输出的打包 `.js` 与 `tsc -b` 逐文件输出的 `.js` 行为不同,例如装饰器转换行为。 +- `vendor/*/src`、示例、测试和脚本无法全部以 plain-include 方式纳入一个根目录的严格程序。 + - 在根目录严格配置下直接对 `vendor/*/src` 做类型检查,会触发大量不属于本项目所有权范围的类型错误。 + - `packages/*/*` 对 `vendor` 的包依赖解析到 `vendor/*/lib`,以适应不同的 tsconfig 严格度。 + + +## 决策 + +包内相对导入使用显式 `.ts` 说明符。 + +`pnpm run build` 是两阶段构建: + +- 阶段 1:在根 solution 上执行 `tsc -b`,将逐模块的 `.js`、声明文件 `.d.ts`、JS sourcemap `.js.map` 和声明 sourcemap `.d.ts.map` 输出到各包的 `lib/types`。这是权威的 TypeScript 编译结果。发布时保留 `.d.ts` / `.d.ts.map`,忽略 `.js` / `.js.map`。 + - 该图是从根 solution `tsconfig.json` 经两个聚合可达的 project-reference 图([拓扑](2026-07-22-tsconfig-solution-root-two-aggregates.md)),用于校验并输出包/vendor 的构建结果。 +- 阶段 2:打包器读取 `lib/types` 下输出的 JS,将打包后的运行时入口写为 `lib/index.js` 或 `lib/index.mjs`(沿用当前行为)。此阶段仅做打包,禁止读取 TypeScript 源码或输出声明文件。 + +`tsdown` 不再负责 TypeScript 编译或声明文件输出。 + +`pnpm run typecheck` 运行同一张 `tsc -b` 图。 +- 两个聚合(`tsconfig.host.json`、`tsconfig.client.json`)以 `noEmit` 方式检查示例、测试和脚本,并通过 references 校验包/vendor 源码。 +- 被引用的包/vendor 项目保持与构建相同的输出行为,因此类型检查会刷新它们的 `lib/types` 输出,而无需使用独立的 no-emit 图。项目特定的严格度变更放在各自的 `packages/*/*/tsconfig.json` 或 `vendor/*/tsconfig.json` 中。 +- 两个 no-emit 聚合禁用 `rewriteRelativeImportExtensions`;它们不输出任何文件,且包含跨 project-reference 边界导入 helper 的测试。包/vendor 的 emit 项目保持重写开启。 + +命令编排结构如下: + +```sh +pnpm run build: +tsc -b +tsdown + +pnpm run verify-node-next-types: +tsx scripts/verify-node-next-types.ts + +pnpm run typecheck: +tsc -b +``` + +`pnpm run demo:*` 仍通过 tsx 和根路径直接运行 `src`,无需编译步骤。 + +## 曾考虑的替代方案 + +- **继续使用 `tsdown`/oxc 作为 TypeScript 转换器**:oxc 的转换行为与 `tsc` 不同(装饰器转换有差异、打包 JS 与逐文件输出不同),且其打包 `.d.ts` 与 Cordis 内部的相对模块增强结构冲突。 +- **用一个根目录严格程序覆盖包、vendor、示例、测试和脚本**:vendor 源码在根目录严格标志下会触发不属于本项目所有权范围的类型错误;带有逐项目严格度的 project references 才是可行的边界。 + +## 后果 + +构建职责更加清晰: + +- `packages/<group>/<pkg>` 和 `vendor/*` 下的每个模块有一份本地 tsconfig,同时服务于构建、类型检查和直接运行源码的工具(如 `tsx` 和 `vitest`)。 +- `build` 命令驱动根 solution 图。`tsc -b` 负责可发布的逐模块 `.js` 和 `.d.ts` 输出,打包器仅负责 `lib/index.*`。 + - `lib/types/*.d.ts` 和 `.d.ts.map` 是发布用的声明输出。 + - `lib/types/*.d.ts` 使用显式 `.ts` 相对说明符,TypeScript 的 NodeNext/Node16 解析器会将其映射到同级的 `.d.ts` 文件。 + - `lib/types/*.js` 仅作为打包器输入,禁止用作运行时入口或公开导入目标。 + - `lib/index.*` 是发布用的运行时输出,由打包器(当前为 `tsdown`)生成。 +- `pnpm run verify-node-next-types` 扫描构建出的声明文件,检查是否存在缺少文件扩展名的相对说明符,然后以 `moduleResolution: "NodeNext"` 对构建出的 `types`/`exports` 接口进行临时外部 ESM 消费方的类型检查,确保声明说明符的回归在发布前被捕获。 +- `typecheck` 命令使用 `tsconfig.json`。示例、测试和脚本由根 no-emit 项目检查,包和 vendor 模块保持与 `build` 相同的输出行为。包和 vendor 源码始终处于 project-reference 边界之后。 + +Cordis 的 vendor 副本现在与上游多了一处类型结构差异。在上游同步时,该差异必须被重新应用或明确废弃。 diff --git a/.agents/notes/implemented/process/2026-06-18-markdown-cross-link-lint.i18n.yaml b/.agents/notes/implemented/process/2026-06-18-markdown-cross-link-lint.i18n.yaml new file mode 100644 index 0000000000..601a077189 --- /dev/null +++ b/.agents/notes/implemented/process/2026-06-18-markdown-cross-link-lint.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-18-markdown-cross-link-lint.md: 2e3b0f1fcd03f244756b0030f2da758c516a2bbb +2026-06-18-markdown-cross-link-lint.zh.md: cfe973ae939eceb50d6381ecf35c80df508907c3 diff --git a/.agents/notes/implemented/process/2026-06-18-markdown-cross-link-lint.md b/.agents/notes/implemented/process/2026-06-18-markdown-cross-link-lint.md index e57c75575b..2e3b0f1fcd 100644 --- a/.agents/notes/implemented/process/2026-06-18-markdown-cross-link-lint.md +++ b/.agents/notes/implemented/process/2026-06-18-markdown-cross-link-lint.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-06-18-markdown-cross-link-lint.zh.md) + ## Problem Docs in this repo link to each other by relative path — `[topic](../implemented/2026-…-….md)`, `[the cookbook](adding-a-tool.md)`, `[architecture.md](../../architecture.md)`. Nothing verified those targets exist. A rename or a move silently breaks every inbound link, and the break is invisible until a reader clicks it. [Doc-sync enforcement](2026-06-11-doc-sync-enforcement.md) already mechanized two classes of doc drift (uncompilable code blocks, a stale event-taxonomy table) and [verify-md-wrap](2026-06-11-doc-sync-enforcement.md) a third (hard-wrapped prose) — but a dead cross-link is a fourth, equally mechanical class that was still verified by eyeball. diff --git a/.agents/notes/implemented/process/2026-06-18-markdown-cross-link-lint.zh.md b/.agents/notes/implemented/process/2026-06-18-markdown-cross-link-lint.zh.md new file mode 100644 index 0000000000..cfe973ae93 --- /dev/null +++ b/.agents/notes/implemented/process/2026-06-18-markdown-cross-link-lint.zh.md @@ -0,0 +1,33 @@ +# Agent Note: Markdown 交叉链接有效性检查 + +Status: implemented + +[English](2026-06-18-markdown-cross-link-lint.md) | 中文 + +## 问题 + +本仓库的文档通过相对路径互相链接:`[topic](../implemented/2026-…-….md)`、`[the cookbook](adding-a-tool.md)`、`[architecture.md](../../architecture.md)`。此前没有任何机制验证这些目标是否存在。重命名或移动文件会静默破坏所有指向它的链接,且在读者点击之前不可见。[Doc-sync 强制](2026-06-11-doc-sync-enforcement.md)已经将两类文档漂移机械化(无法编译的代码块、陈旧的事件分类表),[verify-md-wrap](2026-06-11-doc-sync-enforcement.md) 覆盖了第三类(硬换行的段落),但死链是第四类同样可机械检查、却仍靠肉眼验证的问题。 + +引入这道门禁的直接动因是 Agent Note(agent 决策记录)目录树重组:将 `docs/adr/` 与 `.agents/notes/` 统一到同一个 `.agents/notes/` 下,并设置 `proposed/`、`implemented/`、`rejected/` 子目录,需要手工重命名约 40 条文档间链接。只要有一处路径输入错误,就会在没有任何检查拦截的情况下交付断链。 + +## 决策 + +新增第四道 `doc-sync` 门禁 `verify-md-links`(`scripts/verify-md-links.ts`),风格与 `verify-md-wrap` 一致(tsx ESM、基于 AST、只验证不生成): + +- 使用 `mdast-util-from-markdown` + GFM 解析每个范围内的 Markdown 文件,遍历所有 `link`、`image` 和 `definition` 节点。 +- 仅当目标是**相对路径**时才检查。跳过带协议的 URL(`https:`、`mailto:` 等)、协议相对路径(`//host`)、根绝对路径(`/path`,在检出目录中没有稳定基准)以及纯页内锚点(`#section`)。剥除 `#fragment`/`?query`,相对于链接所在文件的目录解析路径,并断言目标在磁盘上存在。 +- 只报告、不改写;发现第一条死链即以非零状态退出。 + +检查范围与其他门禁一致,并额外包含 AGENTS.md 文件对以及 `.agents/skills/` 下仓库自有的 agent-skill(技能)Markdown(这些 skill 文件会交叉链接到 docs 目录树,因此本次重组也改写了其中的链接):`README.md`、`docs/**/*.md`、`packages/*/README.md`、`AGENTS.md`、`packages/AGENTS.md`、`.agents/skills/**/*.md`。系统按真实路径去重(`CLAUDE.md` symlink 会解析到 AGENTS.md 文件)。该检查接入 `doc-sync`,因此相关文档变更与 CI 执行同一套断链检查。 + +本门禁检查的是*文件存在性*,而非锚点有效性:指向一个真实文件但带有 `#wrong-heading` 片段的链接仍会通过(文件可解析;片段被剥除)。 + +## 曾考虑的替代方案 + +**锚点级有效性检查**:更重且价值更低;实际造成问题的是文件级死链。这一范围裁剪是有意为之:作者在链接到某个锚点时自行验证 `#fragment`。 + +## 后果 + +- 造成交叉链接失效的重命名与移动会直接使 `doc-sync` 和 CI 失败,而不是等读者点击死链才暴露。由此,引入该门禁的 Agent Note 重组具备自校验能力:同一个 PR(Pull Request)在改写 40 条链接的同时,也添加了证明这些链接均未悬空的检查。 +- `doc-sync` 链中多了一个快速 tsx 脚本;无新增依赖(mdast/GFM 技术栈已作为 `verify-md-wrap` 的 devDependencies 存在)。 +- 该门禁强制执行的约定是:文档交叉引用必须使用可机械检查的相对链接,绝不能只写纯文本或编号。[docs/AGENTS.md](../../../../docs/AGENTS.md)记录了这项约定,使作者了解该门禁及其理由。 diff --git a/.agents/notes/implemented/process/2026-06-20-agent-note-classification.i18n.yaml b/.agents/notes/implemented/process/2026-06-20-agent-note-classification.i18n.yaml new file mode 100644 index 0000000000..cc0a877084 --- /dev/null +++ b/.agents/notes/implemented/process/2026-06-20-agent-note-classification.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-20-agent-note-classification.md: 094233ed108e35e390cdc66b419179249c2d9173 +2026-06-20-agent-note-classification.zh.md: b424b07e051507a894c8f5961feb5fe24a9da3c6 diff --git a/.agents/notes/implemented/process/2026-06-20-agent-note-classification.md b/.agents/notes/implemented/process/2026-06-20-agent-note-classification.md index 750a3586e0..094233ed10 100644 --- a/.agents/notes/implemented/process/2026-06-20-agent-note-classification.md +++ b/.agents/notes/implemented/process/2026-06-20-agent-note-classification.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-06-20-agent-note-classification.zh.md) + ## Problem A lifecycle-only Agent Note tree — `proposed/` / `implemented/` / `rejected/` — does not record what *kind* of decision each file contains. A reader browsing one lifecycle cannot distinguish a new capability from a removal or a tooling-policy change without opening each file. diff --git a/.agents/notes/implemented/process/2026-06-20-agent-note-classification.zh.md b/.agents/notes/implemented/process/2026-06-20-agent-note-classification.zh.md new file mode 100644 index 0000000000..b424b07e05 --- /dev/null +++ b/.agents/notes/implemented/process/2026-06-20-agent-note-classification.zh.md @@ -0,0 +1,48 @@ +# Agent Note: 通过路径编码的子目录对 Agent Note 进行分类 + +Status: implemented + +[English](2026-06-20-agent-note-classification.md) | 中文 + +## 问题 + +仅按生命周期组织的 Agent Note(agent 决策记录)目录树(`proposed/` / `implemented/` / `rejected/`)无法记录每个文件包含哪一*类*决策。读者浏览某个生命周期时,如果不逐一打开文件,就无法区分新功能、移除项或工具策略变更。 + +本仓库一贯的倾向是[机械质量门禁优于行文规范](2026-06-11-quality-gates.md):不被机器检查的约定终将腐烂。因此这里的分类方案必须可强制执行,而非靠自觉的文件头。 + +## 决策 + +增加第二个维度,即 Agent Note 的**类别**,并将其编码在路径中:`{lifecycle}/{class}/yyyy-mm-dd-topic.md`。文件夹*就是*标签。文件位置声明其类别;封闭集合限定为「这些文件夹且仅限这些」;既有的 [verify-md-links](2026-06-18-markdown-cross-link-lint.md) 门禁已经保护移动文件所需的路径改写。 + +### 六个类别的封闭集合 + +| 类别 | 涵盖范围 | +|---|---| +| `feature` | 面向用户或模型的新功能。 | +| `bug-fix` | 修正缺陷或填补事后复盘暴露的空白。 | +| `simplification` | 移除代码、行为或对外表面积,不引入新功能。 | +| `architecture` | 关于**交付源码**的结构性决策——包(package)之间的关系、运行时词汇。 | +| `process` | **围绕**代码的工具、策略或工作流,而非运行时行为。 | +| `testing` | 测试基础设施与策略。 | + +`architecture` 与 `process` 的分界是:**architecture** 关乎我们交付的源码;**process** 关乎源码周边的工具与工作流。本 Agent Note 本身属于 `process` 决策:它改变仓库的组织方式与门禁,而不是 harness 的运行时行为,因此位于 `implemented/process/` 下。 + +### 两道门禁 + +两者都是 `doc-sync`(文档同步门禁)的成员,风格与 `verify-md-wrap` 一致(tsx ESM,只校验不生成,首个违规即以非零退出码退出): + +- **`scripts/verify-agent-note-classification.ts`**:定义封闭的生命周期与类别集合。它断言生命周期文件夹下的每个文件都位于规范集合中的类别文件夹内(生命周期根目录下散落的 `.md` 或未知类别文件夹都会失败),并拒绝集中式 `INDEX.md`。规范集合位于 `scripts/agent-note-tree.ts` 中,[README](../../README.md)则以行文记录每个类别。 +- **`scripts/verify-doc-refs.ts`**:检查引用文档的源码注释。Agent Note 路径不仅出现在 Markdown 中,也出现在 TypeScript 文档注释中(例如以仓库根为起点的 `.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.md`)。`verify-md-links` 看不到这些引用,因此目录重组可能静默留下失效引用。该门禁扫描 `packages/**` 与 `examples/**` 下仓库自有的 `.ts` 文件(排除已构建的 `lib/` 与 `vendor/`),查找 `docs/….md` 和 `.agents/notes/….md` token,解析每个以仓库根为起点的路径并断言其存在。它要求使用 `.md` 扩展名,因此不处理无扩展名的行文。 + +## 曾考虑的替代方案 + +- **在每个文件中添加 `Classification:` 行文行**(紧邻 `Status:`),由门禁解析。可行,但它将路径已能承载的事实重复到文件中,且行内容可能与所在文件夹不一致。路径编码使标签与其存储合二为一,没有需要保持同步的东西。 +- **设立 `refactor` 类别。** 与 `simplification` 几乎完全重叠;唯一有人试图用来区分的标准是「可观察行为是否改变?」,而 `simplification` 已经编码了这一点(它不改变)。一个类别即可,无需两个。 +- **生成或手工维护的语料索引。** 不予采纳:生命周期/类别目录树才是权威结构;集中式清单会制造合并热点,却没有提供目录树导航或仓库搜索无法实现的发现能力。单独的[索引提案](../../rejected/process/2026-07-04-generate-agent-note-index-tables.md)记录了被放弃的生成形状。 + +## 后果 + +- 每份 Agent Note 都位于一个类别文件夹下。读者浏览单个文件夹,即可查看某个生命周期内的全部简化或测试决策。 +- `doc-sync` 链中多了两个快速 tsx 脚本;无新依赖(mdast/GFM 栈已因 `verify-md-wrap`/`verify-md-links` 而存在)。 +- 新增类别必须是显式决策:修改 `scripts/agent-note-tree.ts` 中的 `const` 与 [Classification 章节](../../README.md#classification),而不是只用 `mkdir` 创建文件夹。门禁会拒绝未知文件夹,因此临时类别无法悄然混入。 +- 源码注释中的文档引用同样受门禁约束:被 `.ts` 注释引用的文档一旦移动或重命名,`doc-sync` 与 CI 中的 `verify-doc-refs` 就会失败,从而堵住 `verify-md-links` 在结构上无法发现的一类漂移。 diff --git a/.agents/notes/implemented/process/2026-06-20-core-data-structures-catalog.i18n.yaml b/.agents/notes/implemented/process/2026-06-20-core-data-structures-catalog.i18n.yaml new file mode 100644 index 0000000000..f59c523dce --- /dev/null +++ b/.agents/notes/implemented/process/2026-06-20-core-data-structures-catalog.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-20-core-data-structures-catalog.md: d7e9d3d9b14fe723e3396c8167fe714b7613e2b5 +2026-06-20-core-data-structures-catalog.zh.md: 8d2f16a46216cba8df0539be0abd2f1ad840eec3 diff --git a/.agents/notes/implemented/process/2026-06-20-core-data-structures-catalog.md b/.agents/notes/implemented/process/2026-06-20-core-data-structures-catalog.md index 6e832fb73b..d7e9d3d9b1 100644 --- a/.agents/notes/implemented/process/2026-06-20-core-data-structures-catalog.md +++ b/.agents/notes/implemented/process/2026-06-20-core-data-structures-catalog.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-06-20-core-data-structures-catalog.zh.md) + ## Problem A reader trying to understand the harness could find its *behavior* in [architecture.md](../../../../docs/architecture.md) (the service map, the session/turn/step lifecycle, the event taxonomy) but had no single place describing its *vocabulary* — the data structures that behavior moves around. The type shapes lived only in source, scattered across `packages/*/src/types.ts`, so understanding "what is a `Message`, a `SessionEvent`, a `StreamChunk`" meant reading the declarations directly. A prose catalog would help, but a catalog that paraphrases or paste-copies type definitions rots the instant a field changes — and an out-of-sync type doc is worse than none, because a reader trusts it. diff --git a/.agents/notes/implemented/process/2026-06-20-core-data-structures-catalog.zh.md b/.agents/notes/implemented/process/2026-06-20-core-data-structures-catalog.zh.md new file mode 100644 index 0000000000..8d2f16a462 --- /dev/null +++ b/.agents/notes/implemented/process/2026-06-20-core-data-structures-catalog.zh.md @@ -0,0 +1,60 @@ +# Agent Note: 核心数据结构目录与 `ts type-equiv` 漂移门禁 + +Status: implemented + +[English](2026-06-20-core-data-structures-catalog.md) | 中文 + +## 问题 + +试图理解 harness 的读者可以在 [architecture.md](../../../../docs/architecture.md) 中找到它的*行为*(服务图、会话/轮次/步骤生命周期、事件分类),却找不到一个统一描述其*词汇*的地方,也就是这些行为所传递的数据结构。类型形状只存在于源码中,散落在 `packages/*/src/types.ts` 各处,因此要理解“什么是 `Message`、`SessionEvent`、`StreamChunk`”,就必须直接阅读声明。文字目录会有所帮助,但复述或复制粘贴类型定义的目录会在字段发生变化时立即腐化,而不同步的类型文档比没有文档更糟,因为读者会信任它。 + +因此,这项工作有两个相互交织的问题:**这样的目录应包含什么**(范围问题——harness 有数十种跨包(package)边界的类型,把它们全部倾倒进来对谁都没有帮助),以及**如何避免粘贴的类型定义发生漂移**(持久性问题)。本 Agent Note(agent 决策记录)记下了这两项决策。与它配套的[生成式 Cordis 事件与服务目录](2026-06-20-generated-cordis-catalog.md)从*接线*维度形成补充:本文对数据结构编目,另一篇则对传递这些结构的事件和服务编目。 + +## 决策 + +新增的 `docs/core-data-structures/` 目录对这些词汇编目,并配有新的 `verify-type-equiv` 文档同步门禁,使每个粘贴的类型声明及其 JSDoc 与源码保持同步。 + +### 何为"核心"——主干与 seam 的分界线 + +范围界定并非自上而下拍定,而是将候选定义逐一对照具体的边界类型反复测试,直到一条规则在所有案例中都成立。决定性的测试是 `BashExecRequest`/`BashExecSpec`/`BashRunResult`:bash 是一个能力 *seam*,不属于 agent loop(智能体循环)主干;如果这些算"核心",那么"核心"就意味着*所有跨包词汇*,目录沦为平铺罗列;如果不算,"核心"就意味着*中央主干*,bash 词汇归入子页面。后者胜出,由此确定了整体结构:一个**分层文件夹**,而非一份平铺文档。 + +确定其余案例的规则是:***你编写、持有或接收的类型是核心;为其提供类型推导、渲染或持久化的机制是子页面细节。*** 逐一验证如下: + +- 一个数据结构是**核心**的,如果它流经 agent loop 主干——无论加载了哪些插件,循环在每个轮次都会持有、派生、流式输出或记录它(`Message`、`StreamChunk`、`SessionEvent`、`Agent` 句柄)——**或者**它是插件作者面对某条流水线时编写的唯一标志性类型(`ToolDefinition`)。 +- `ToolDefinition` 是核心(它是每个工具作者编写的东西),**即使循环从不持有它**——对于这一个标志性类型,撰写重要性压过了严格的"流经主干"规则。但它的类型推导机制——`ValueSchemaSpec`、`ParameterSchemaSpec`、`InferValue` 与 `InferArgs`——是子页面细节。这就是主干与 seam 分界线的精确表述。 +- `ToolSchema` 是核心(它是流经每个步骤的模型请求 `GenerateOptions` 的一个字段),即使它在概念上属于工具流水线——当*流经主干*与*概念归属*冲突时,前者胜出。 +- 工具展示词汇(`ToolCallView`/`ToolResultView` 等)、`SessionPersistence` 持久性 seam 以及 bash 词汇是子页面。 + +`core.md` 是一份**自包含的主干文档**:它给出每个主干结构的确切类型定义,辅以最少的行文,并链接到子页面获取各 seam 的细节。子页面包括 `llm-streaming.md`、`session.md`、`persistence.md`(沿内存模型与持久性 seam 的分界线从会话页面拆出)、`tools.md` 和 `bash.md`。 + +### `ts type-equiv` 机制——既逐字又防漂移 + +持久性要求很具体:文档展示当前类型声明与原始 JSDoc 的**逐字**内容(让读者看到真实形状和源码契约,而非复述),**并且**以机械方式保证其与源码匹配。仓库已经会编译 ` ```ts ` 围栏块(`doc-typecheck`),但真正接受类型检查的块需要导入噪音,而且只能证明*可赋值性*——字段改名或 JSDoc 变化仍可能通过。因此: + +- 完整的类型声明及其 JSDoc 会逐字粘贴到专用的 ` ```ts type-equiv ` 围栏中。简洁的 ` ```ts public-api ` 围栏承载与源码等价的类环境投影,用于实现体不应进入目录的类。`doc-typecheck` 会识别并跳过这两种围栏(裸声明无法独立编译),并且**将它们排除在 opt-out 比例之外**——它们是单独受检的类别,而不是未经检查的草图。 +- 新增的 `scripts/verify-type-equiv.ts` 通过 TypeScript 解析器提取每个块,并断言其声明结构和每条 JSDoc 注释都与所声明的符号匹配,只忽略格式空白和非 JSDoc 注释。普通块保留完整声明。`public-api` 投影保留类的公共字段、构造函数、访问器和方法及其原始 JSDoc,同时移除实现体以及私有或受保护成员。之所以选择它而非编译式 `_Check` 断言,是因为目录所保留的是源码名称与文档一致性,而不是可赋值性。 +- 来源信息存放在集中的 `scripts/type-equiv.manifest.json`(`{ doc, symbol, source }` 条目)中,**而非**行文中的指令注释。脚本强制执行 **1:1 对应**:每个 type-equiv 块恰好有一条 manifest 条目,反之亦然;因此一个块永远不会被静默漏检,一条条目也永远不会腐烂。 +- 接入 `doc-sync`,因此相关文档变更会在本地运行它,CI 也会与其他文档检查一起运行它。 + +### 维护是作者的职责,门禁作为兜底 + +`verify-type-equiv` 能捕获已记录类型的*粘贴漂移*,但无法告诉你一个全新的核心类型没有被记录。因此 AGENTS.md 和 `dsh-code-review` skill(技能)已更新,要求在变更添加或重塑已记录类型时同步更新目录——门禁处理漂移,人处理新增表面。 + +## 曾考虑的替代方案 + +- **平铺罗列所有跨包词汇**:`BashExecRequest` 测试案例否决了它。如果 seam 词汇算"核心",目录对谁都没帮助;分层的主干与 seam 结构胜出。 +- **用编译式 `_Check` 可赋值性断言**代替源码匹配:否决。可赋值性不会保留名称或 JSDoc;同类型字段改名或契约注释变化仍会通过。 +- **来源信息作为行文中的指令注释**:否决,改用集中 manifest;其强制的 1:1 对应确保一个块永远不会被静默漏检,一条条目也永远不会腐烂。 + +## 验证教训 + +主干与 seam 规则在采纳前经过了 `BashExecRequest`、工具 schema 与定义、schema DSL、展示类型以及会话/持久化拆分的逐一测试。 + +`verify-type-equiv` 必须扫描完整的 Markdown 范围,而不仅是清单点名的文档。否则,未列入清单的 `type-equiv` 块就会逃过所宣称的一一检查。因此,门禁会将此类块报告为孤儿。本 Agent Note 将这条失败关闭扫描规则,连同主干与 seam 的分界决策及逐字匹配决策一并记录;生成式 Cordis 目录在[其 Agent Note](2026-06-20-generated-cordis-catalog.md) 中有对称的设计记录。 + +## 后果 + +- 这些词汇现在有一个**无法悄然漂移**的唯一归属:源码中的字段或公共类成员发生变化后,`doc-sync` 和 CI 中的 `verify-type-equiv` 会持续失败,直至粘贴内容刷新。Cordis 服务方法仍由生成式服务目录负责,而不会在此重复。 +- 主干与 seam 分界线是一个可复用的范围界定工具,而非一次性的:同一条「你编写/持有/接收的东西是核心;为其提供类型推导/渲染/持久化的机制是细节」规则,后来也被用于界定事件/服务目录的 harness 层与继承层分层。 +- `ts type-equiv` 围栏是继 ` ```ts `(编译)和 ` ```ts ignore-check `(草稿)之后的第三种文档块类别。后续的姊妹门禁又增加了第四种 ` ```ts cordis-catalog `(生成签名),复用了相同的跳过并排除处理。 +- 添加或重塑核心类型现在附带一项文档义务,作者必须履行(门禁无法检测缺失的*新*类型),由 `dsh-code-review` 检查清单兜底。 diff --git a/.agents/notes/implemented/process/2026-06-20-generated-cordis-catalog.i18n.yaml b/.agents/notes/implemented/process/2026-06-20-generated-cordis-catalog.i18n.yaml new file mode 100644 index 0000000000..16fb9e2d1e --- /dev/null +++ b/.agents/notes/implemented/process/2026-06-20-generated-cordis-catalog.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-20-generated-cordis-catalog.md: b5957cf06a9316447aae70183de462024bb24be3 +2026-06-20-generated-cordis-catalog.zh.md: 35ed06c4a8e13245a37adaa4d5da7a842e97c0c7 diff --git a/.agents/notes/implemented/process/2026-06-20-generated-cordis-catalog.md b/.agents/notes/implemented/process/2026-06-20-generated-cordis-catalog.md index 4ca9b7e42c..b5957cf06a 100644 --- a/.agents/notes/implemented/process/2026-06-20-generated-cordis-catalog.md +++ b/.agents/notes/implemented/process/2026-06-20-generated-cordis-catalog.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-06-20-generated-cordis-catalog.zh.md) + ## Problem A plugin author needs two reference surfaces that no single document gave them: every cordis **event** they can listen to (with its exact signature and dispatch mode) and every `ctx.<key>` **service** they can call (with its exact interface). The pieces existed but were scattered — a hand-maintained event-taxonomy *table* in `docs/architecture.md` (names + prose Mode/Purpose, name-set-checked by `verify-event-taxonomy`), a Service-map table (8 rows of role prose), and the `interface Events` / `interface Context` declarations themselves. The taxonomy table also could not catch a brand-new *undocumented* event: a name-set verifier only checks the names that are already in the table on both sides. diff --git a/.agents/notes/implemented/process/2026-06-20-generated-cordis-catalog.zh.md b/.agents/notes/implemented/process/2026-06-20-generated-cordis-catalog.zh.md new file mode 100644 index 0000000000..35ed06c4a8 --- /dev/null +++ b/.agents/notes/implemented/process/2026-06-20-generated-cordis-catalog.zh.md @@ -0,0 +1,41 @@ +# Agent Note: 生成式 Cordis 事件与服务目录 + +Status: implemented + +[English](2026-06-20-generated-cordis-catalog.md) | 中文 + +## 问题 + +插件作者需要两个参考面,而此前没有任何单一文档能提供:他们可以监听的每一个 Cordis **事件**(含精确签名与分发模式),以及他们可以调用的每一个 `ctx.<key>` **服务**(含精确接口)。相关信息虽然存在,但散落各处:`docs/architecture.md` 中一张手工维护的事件分类*表格*(名称 + 行文描述的 Mode/Purpose,由 `verify-event-taxonomy` 做名称集合校验)、一张服务映射表(8 行角色描述),以及 `interface Events` / `interface Context` 声明本身。分类表格还有一个盲区:它无法捕获全新的*未记录*事件——名称集合校验器只检查两侧已有的名称。 + +这是对[核心数据结构目录](../../../../docs/core-data-structures/core.md)([其 Agent Note(agent 决策记录)](2026-06-20-core-data-structures-catalog.md))在接线维度上的补充:前者对循环传递的*数据结构*编目(经验证的手工粘贴),本文则对传递它们的*事件和服务*编目。 + +## 决策 + +从源码生成目录,取代手工维护表格并校验子集的方式。 + +`scripts/gen-cordis-catalog.ts` 使用 TypeScript 编译器 API,根据声明和源码 JSDoc 分别生成事件与服务参考。事件包含分派模式及其原始成员 JSDoc;服务包含公共签名及各方法的原始 JSDoc。确定性的 `--write` 和 `--check` 模式使两个页面成为生成产物,并由 `doc-sync` 强制检查新鲜度。 + +纯生成在此处是正确的,因为代码库足够规范,AST 就是全部事实:每个事件/服务名称都是字符串字面量,可以往返映射到静态声明——不存在动态命名的事件,也不存在仅运行时的服务。因此生成的文档不可能出错,且从结构上消除了未记录事件的缺口(生成器枚举源码,而非校验手写子集)。 + +具体选择: + +- **`@mode` 标签,交叉校验。** 每个 harness 事件的 JSDoc 携带一个显式的 `@mode emit|waterfall|parallel|serial` 标签;缺少标签时生成器直接报错。当签名形状具有决定性时——尾部参数为 `next: () => …` 在结构上即为 waterfall(瀑布式事件)——生成器断言标签与之一致,矛盾时直接报错。emit/parallel/serial 的区别在结构上不可见(`session/flush` 返回 `Promise<void> | void` 且无 `next`,有序的 `agent/pre-step` 检查点亦然),因此信任标签。编写规则见 [AGENTS.md](../../../../AGENTS.md)。 +- **分层范围。** harness 层(8 个 `@deepseek-ai/dsh-*` 服务及其事件)从源码完整渲染。继承层(cordis-core 的 `ctx.on/emit/effect/provide/…` + `internal/*` 事件 + loader/hmr/timer)是插件同样可见的固定 vendor 源码;它从生成器中一张人工维护的表格简洁渲染(名称 + 一行描述 + 源码指针),而非遍历 vendor AST。原因是 cordis-core 的 `Context` 混合了真正的 ctx 成员与非服务字段(`root`、`baseUrl`、`logger`),且 vendor 接口面仅在有意的 vendor 同步时才变化。 +- **指向数据结构目录的交叉链接。** 签名中由仓库拥有的每个类型名(`GenerateOptions`、`StreamChunk`、`ToolDefinition`……)都会通过人工维护的映射链接到其主要核心数据结构页面。AST 遍历采用失败关闭策略:每个参数、泛型约束/默认值和返回类型引用都必须已映射、是签名自身的类型参数、是点名的 TypeScript/Cordis 基础类型,或带有点名的例外及其非目录文档归属。违规会连同源码位置汇总报告,并点明相应的归属列表。该映射不会复用 `type-equiv.manifest.json`,因为后者记录 `…Map` 符号,而签名引用派生的联合类型名,并且会在多个页面列出某些符号。 +- **专用围栏。** 签名块使用 ` ```ts cordis-catalog ` 信息字符串,并把原始事件或公共方法 JSDoc 直接放在其声明之前。`doc-typecheck` 会识别并跳过这些裸片段,将其排除在 opt-out 比例之外——与 `type-equiv` 块的处理相同。 + +本决策**取代** [doc-sync 强制](2026-06-11-doc-sync-enforcement.md)中事件分类的那一半:`verify-event-taxonomy` 及其 `docs/architecture.md` 表格退役(architecture.md 的标题保留,正文改为指向目录;服务映射的角色表格作为人工行文保留)。doc-typecheck、verify-md-wrap、verify-md-links 和 verify-type-equiv 不受影响。 + +## 曾考虑的替代方案 + +- **校验而非生成(退役的分类检查所做的事)**:*仅对本参考面*反转了这一策略。此处的数据可以机械地完整获取,因此生成严格强于对手工表格做名称集合校验(完整签名、不会漂移、能捕获未记录事件)。 +- **遍历 vendor AST 以获取继承层**:否决,改用人工维护表格。cordis-core 的 `Context` 混合了真正的 ctx 成员与非服务字段,且固定的 vendor 接口面仅在有意同步时才变化。 +- **复用 `type-equiv.manifest.json` 作为签名交叉链接映射**:否决,改用完整的人工维护常量和失败关闭覆盖。清单记录 `…Map` 符号,而签名引用派生的联合类型名,并且会在多个页面列出某些符号。显式映射让每个渲染目标和每个非目录例外都成为可评审的决策。 + +## 后果 + +- 目录不会发生漂移:提交文件未反映的源码变化会使 `doc-sync` 和 CI 中的 `verify-cordis-catalog` 失败。新事件缺少 `@mode` 标签、标签与其签名冲突,或签名类型未分类,都会直接使生成器失败。 +- 事件与服务方法契约只有一个归属——声明处的 JSDoc。目录会在生成的签名块中重复该原始 JSDoc,并使用其描述部分作为条目正文,因此单薄的源码文档只会生成单薄的目录条目。 +- 继承层是手工摘要,因此 vendor 同步若新增或重命名了 cordis-core 事件或 `ctx` 成员,需要同步编辑 `gen-cordis-catalog.ts` 中的人工维护表格。这是不遍历固定 vendor 源码的有意代价;它很少变化,且在生成器中有明确标注。 +- `verify-event-taxonomy.ts` 被删除,`docs/architecture.md` 的事件表格也已移除;之前链接到特定表格行的人现在会落在生成目录上。 diff --git a/.agents/notes/implemented/process/2026-07-02-bilingual-docs-and-pairing-gate.i18n.yaml b/.agents/notes/implemented/process/2026-07-02-bilingual-docs-and-pairing-gate.i18n.yaml index a1d901ad15..3bfc8414e7 100644 --- a/.agents/notes/implemented/process/2026-07-02-bilingual-docs-and-pairing-gate.i18n.yaml +++ b/.agents/notes/implemented/process/2026-07-02-bilingual-docs-and-pairing-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 -2026-07-02-bilingual-docs-and-pairing-gate.md: 3be1d5d8fd9dba20cfca34c79cb01d89fad8097a -2026-07-02-bilingual-docs-and-pairing-gate.zh.md: a8aa8812934e755fe0175c8f3f20d194e4d24b4a +2026-07-02-bilingual-docs-and-pairing-gate.md: 4bc02878a0ea3f998e411ecc2b064c1626eacf3c +2026-07-02-bilingual-docs-and-pairing-gate.zh.md: 90a0c2f07f68b0fb4e26cd1c4b537a30a829b10f diff --git a/.agents/notes/implemented/process/2026-07-02-bilingual-docs-and-pairing-gate.md b/.agents/notes/implemented/process/2026-07-02-bilingual-docs-and-pairing-gate.md index 3be1d5d8fd..4bc02878a0 100644 --- a/.agents/notes/implemented/process/2026-07-02-bilingual-docs-and-pairing-gate.md +++ b/.agents/notes/implemented/process/2026-07-02-bilingual-docs-and-pairing-gate.md @@ -13,8 +13,14 @@ This repo's README and docs tree are read by people and agents inside and outsid - **Paired sibling files with equal authority.** A documentation pair is three sibling files: English `foo.md`, Chinese `foo.zh.md`, and a consistency record `foo.i18n.yaml`. Neither language is canonical — a document may be authored and reviewed Chinese-first and translated to English afterwards, or the reverse; what binds the pair is that both sides must say the same thing, and pairs merge whole (both languages plus the record, never one alone). Policy: [docs/i18n/README.md](../../../../docs/i18n/README.md); translation rules: [docs/i18n/translation-rules.md](../../../../docs/i18n/translation-rules.md); terminology source of truth: [docs/i18n/terminology.md](../../../../docs/i18n/terminology.md). - **A sidecar record of both blob hashes makes consistency checkable.** `foo.i18n.yaml` holds the full git blob hash of each side as of the last confirmed-consistent state. An edit to either side without re-confirming the pair is then mechanically detectable as a pure content comparison — no history lookup — and the hashes are computable for files edited in the same PR, which a commit-hash record is not. Re-recording (`verify-translation-pairing --write`) produces a reviewable yaml diff: confirming consistency is an explicit, visible act in the PR. - **`verify-translation-pairing` joins `doc-sync`.** The gate ([scripts/verify-translation-pairing.ts](../../../../scripts/verify-translation-pairing.ts)) enforces: required pairs exist, every existing pair is complete (all three files) and consistent (both hashes match, switcher links both ways, structural signatures identical), excluded (generated or bilingual-by-construction) files stay unpaired, and date-named documents on or after the manifest's `requiredSince` cutoff have complete pairs. The `required` list in [scripts/translation-pairing.manifest.json](../../../../scripts/translation-pairing.manifest.json) is a ratchet: each merged translation batch adds its files, so coverage only grows. +- **The enforcement frontier advances in coherent review batches.** A related set enters `required` only when reviewers can evaluate it as a unit. The core frontier groups [architecture](../../../../docs/architecture.md), the [Cordis primer](../../../../docs/cordis-primer.md), [defensive patterns](../../../../docs/defensive-patterns.md), the [glossary](../../../../docs/glossary.md), and [testing](../../../../docs/testing.md) because their terminology, links, and contributor contracts inform one another; admitting only part would leave the enforced corpus internally inconsistent. A site-published pair uses `pairedPages()` so the root locale projects `.zh.md` and `/en/` projects `.md`; creating a counterpart alone does not publish it. +- **Pairing records are metadata, not Cordis Loader configuration.** Cordis configuration discovery accepts actual `.cordis.yml` and `.cordis.yaml` files while excluding `*.i18n.yaml`, even when the document name contains `cordis`. This preserves validation of executable Loader entries without parsing translation hashes as configuration. - **Translation is agent work with human review.** The committed workflow is [.agents/skills/dsh-translate-docs](../../../skills/dsh-translate-docs/SKILL.md), following the same pattern as [dsh-code-review](../../../skills/dsh-code-review/SKILL.md): the skill carries the workflow and defers to the docs as sources of truth. The skill directs the orchestrating agent to delegate translation writing to a subagent. +## Verification + +The verification contract covers each boundary independently. `verify-translation-pairing` pins pair completeness, hashes, switchers, and structure; [`project-doc-site.spec.ts`](../../../../scripts/project-doc-site.spec.ts) pins locale-specific source selection for published pairs; [`cordis-config-files.spec.ts`](../../../../scripts/cordis-config-files.spec.ts) pins discovery of Loader YAML and exclusion of translation records; and the [translation-prompt runnable snapshot](../../../../scripts/translation-prompt.snapshot.ts) pins the rendered system message, five reviewed example pairs, source request, and consumed response. Together these checks make pair drift, publication drift, configuration misclassification, and model-visible prompt drift review-visible. + ## Alternatives considered - **English as the canonical source with a fingerprint inside the translation** — the design first proposed for this Agent Note: `.zh.md` files carried an HTML comment recording the English source's blob hash, and translation flowed EN → ZH only. Revised in review: the team wants Chinese-first authoring (write and review a Chinese Agent Note, then translate to English) with the two languages holding equal authority, which a one-directional canonical model cannot express. The sidecar record covering BOTH sides replaced the in-file one-directional fingerprint; the blob-hash mechanics survived unchanged. diff --git a/.agents/notes/implemented/process/2026-07-02-bilingual-docs-and-pairing-gate.zh.md b/.agents/notes/implemented/process/2026-07-02-bilingual-docs-and-pairing-gate.zh.md index a8aa881293..90a0c2f07f 100644 --- a/.agents/notes/implemented/process/2026-07-02-bilingual-docs-and-pairing-gate.zh.md +++ b/.agents/notes/implemented/process/2026-07-02-bilingual-docs-and-pairing-gate.zh.md @@ -13,8 +13,14 @@ Status: implemented - **配对兄弟文件,两种语言同权。** 一对文档由三个兄弟文件组成:英文 `foo.md`、中文 `foo.zh.md`,以及一份一致性记录 `foo.i18n.yaml`。没有哪种语言是正典:一篇文档可以先用中文撰写和评审、之后再译成英文,反之亦可;约束配对的是:两侧必须表达相同的内容,且配对整体合并(两种语言加记录,绝不单独落一侧)。政策见 [docs/i18n/README.md](../../../../docs/i18n/README.md);翻译规则见 [docs/i18n/translation-rules.md](../../../../docs/i18n/translation-rules.md);术语真源见 [docs/i18n/terminology.md](../../../../docs/i18n/terminology.md)。 - **伴随记录保存两侧 blob hash,使一致性可检查。** `foo.i18n.yaml` 保存两侧文件在上一次确认一致时各自的完整 git blob hash。此后修改了任一侧而未重新确认配对,都能被机械检测出来(纯内容比较,无需查询历史),而且同一个 PR(Pull Request)内改动的文件也能计算出 hash,commit hash 式的记录做不到这一点。重新记录(`verify-translation-pairing --write`)会产生一份可评审的 yaml diff:确认一致在 PR 中是一个显式、可见的动作。 - **`verify-translation-pairing` 加入 `doc-sync`。** 门禁([scripts/verify-translation-pairing.ts](../../../../scripts/verify-translation-pairing.ts))强制执行以下规则:required 的配对必须存在;任何已存在的配对必须完整(三个文件齐全)且一致(两个 hash 匹配、切换行双向互链、结构签名一致);被排除的文件(生成物或本身即双语的)不得配对;凡文件名以日期开头且日期不早于 manifest(元数据清单)中 `requiredSince` 分界日期的文档,也必须有完整配对。[scripts/translation-pairing.manifest.json](../../../../scripts/translation-pairing.manifest.json) 中的 `required` 清单只进不退:每个合并的翻译批次将自己的文件加入其中,覆盖面只增不减。 +- **执行红线按连贯的评审批次推进。** 一组相关文档只有在评审者能够将其作为整体评估时,才进入 `required`。核心红线将[架构](../../../../docs/architecture.md)、[Cordis 入门](../../../../docs/cordis-primer.md)、[防御性模式](../../../../docs/defensive-patterns.md)、[术语表](../../../../docs/glossary.md)和[测试](../../../../docs/testing.md)归为一组,因为它们的术语、链接和贡献者契约相互关联;只纳入其中一部分会使受门禁约束的文档集合内部不一致。发布到文档站的配对使用 `pairedPages()`,由根 locale 投影 `.zh.md`,由 `/en/` 投影 `.md`;仅创建对侧文件并不会发布它。 +- **配对记录是元数据,而不是 Cordis Loader 配置。** Cordis 配置发现会接受实际的 `.cordis.yml` 和 `.cordis.yaml` 文件,同时排除 `*.i18n.yaml`,即使文档名中包含 `cordis` 也不例外。这样既能继续校验可执行的 Loader 配置项,又不会把翻译 hash 当作配置来解析。 - **翻译是 agent 的工作,由人评审。** 仓库内置的工作流是 [.agents/skills/dsh-translate-docs](../../../skills/dsh-translate-docs/SKILL.md),与 [dsh-code-review](../../../skills/dsh-code-review/SKILL.md) 模式相同:skill(技能)承载工作流,并将文档作为真源。该 skill 要求编排 agent 把翻译写作委派给 subagent。 +## 验证 + +验证契约分别覆盖每个边界。`verify-translation-pairing` 固定配对完整性、hash、切换行和结构;[`project-doc-site.spec.ts`](../../../../scripts/project-doc-site.spec.ts) 固定已发布配对按 locale 选择对应源文件;[`cordis-config-files.spec.ts`](../../../../scripts/cordis-config-files.spec.ts) 固定 Loader YAML 的发现以及翻译记录的排除;[翻译提示词可运行快照](../../../../scripts/translation-prompt.snapshot.ts)则固定渲染后的系统消息、五对经评审的示例、源请求和响应消费结果。这些检查共同使配对漂移、发布漂移、配置误分类和模型可见提示词漂移都可在评审中看见。 + ## 曾考虑的替代方案 - **英文为正典源、指纹放在译文内**:本 Agent Note 最初提出的设计:`.zh.md` 文件携带一条 HTML 注释记录英文源的 blob hash,翻译只沿 EN → ZH 单向流动。评审中修订:团队需要中文先行的撰写方式(先写、先审中文 Agent Note,再译英文),两种语言同权,而单向正典模型无法表达这一点。覆盖**两侧**的伴随记录取代了文件内的单向指纹;blob hash 的机制本身保持不变。 diff --git a/.agents/notes/implemented/process/2026-07-02-tool-schema-catalog.i18n.yaml b/.agents/notes/implemented/process/2026-07-02-tool-schema-catalog.i18n.yaml new file mode 100644 index 0000000000..65a2b2da28 --- /dev/null +++ b/.agents/notes/implemented/process/2026-07-02-tool-schema-catalog.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-02-tool-schema-catalog.md: c8cc69df428f6eee0f66ed976865afe2a0702448 +2026-07-02-tool-schema-catalog.zh.md: f08cb5b5312dd07f91037a4382bf5e416cae552d diff --git a/.agents/notes/implemented/process/2026-07-02-tool-schema-catalog.md b/.agents/notes/implemented/process/2026-07-02-tool-schema-catalog.md index 814331af8b..c8cc69df42 100644 --- a/.agents/notes/implemented/process/2026-07-02-tool-schema-catalog.md +++ b/.agents/notes/implemented/process/2026-07-02-tool-schema-catalog.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-07-02-tool-schema-catalog.zh.md) + ## Problem The repository had no single reference for the names, descriptions, and JSON Schemas actually exposed to the model. Source declarations are scattered and runtime-composed, while the existing Cordis and data-structure catalogs cover wiring and vocabulary rather than tools. diff --git a/.agents/notes/implemented/process/2026-07-02-tool-schema-catalog.zh.md b/.agents/notes/implemented/process/2026-07-02-tool-schema-catalog.zh.md new file mode 100644 index 0000000000..f08cb5b531 --- /dev/null +++ b/.agents/notes/implemented/process/2026-07-02-tool-schema-catalog.zh.md @@ -0,0 +1,55 @@ +# Agent Note: 生成式工具 schema 目录(启动并采集) + +Status: implemented + +[English](2026-07-02-tool-schema-catalog.md) | 中文 + +## 问题 + +仓库此前没有一份统一的参考文档来记录实际暴露给模型的工具名称、描述与 JSON Schema。源码声明分散各处且在运行时组合,而既有的 Cordis 目录和数据结构目录覆盖的是接线与词汇,而非工具。 + +## 决策 + +目录通过**启动每个工具插件并读取其已注册 schema** 来生成,而不是解析源码。`scripts/gen-tool-catalog.ts` 在全新的 Cordis `Context` 上挂载每个已发布工具包(package);该上下文还提供 `SystemPrompt`、`ToolRegistry` 以及插件 `apply` 所读取的注入 seam。生成器调用 `ctx.tools.schemas()`——也就是发送给模型的确切 `ToolSchema[]`——随后释放上下文,并为每个包渲染一个 `## <package>` 章节,每个工具附带一个 ` ```json ` `parameters` 块。它与 `gen-cordis-catalog` / `gen-module-graph` 的 CLI 形状一致:默认 `--write` 重新生成;提交副本陈旧时 `--check` 失败;输出具有确定性(按清单排序,工具按名称排序)。`verify-tool-catalog`(即 `--check`)在 `doc-sync` 内运行,因此相关文档变更和 CI 会执行同一项新鲜度检查。 + +### 为何启动而非解析(核心要点) + +Cordis 目录是纯 TypeScript AST 遍历,因为每个事件/服务名都是字符串字面量,可以往返映射到静态声明——AST 即全部事实。**工具 schema 在静态层面不可知**,因此同样的技术会产出一份说谎的文档: + +- `tool-todo` 写了 `enum: [...STATUSES]`——对一个运行时 `const` 的展开。AST 看到的是展开表达式,而非 `["pending","in_progress","completed"]`。 +- 每条 description 都通过字符串**拼接**构建(`'…' + '…'`)。AST 看到的是拼接节点,而非模型实际读到的最终文本。 +- `tool-subagent` 的工具名是 `config.toolName ?? 'subagent'`——加载时选定,并非字面量。 +- MCP 插件可以通过 `ctx.tools.register()` 直接注册**原始 JSON Schema**,完全不经过 `defineTool`,因此结构化枚举 `defineTool(` 调用点会遗漏。 + +唯一准确的真源,是插件加载后注册表实际持有的 schema。启动插件是把[测试策略](../../../../docs/testing.md)中“验证现实,而非自我报告”的准则应用到文档生成器:读取已发布产物,而非重新推导一份。 + +### 恢复「不会静默遗漏」的保证 + +启动有一项 AST 遍历不存在的代价:没有源码声明集合可供枚举,新工具包可能被遗忘。一个**完整性守卫**恢复了这项保证——`assertManifestComplete` 对 `packages/` 下所有 `tool-*` 包进行 glob,若有任何一个不在生成器的启动 manifest 中则直接报错。新工具包在注册之前会导致生成器失败,进而导致 `doc-sync` 失败。这与 Cordis 生成器通过枚举源码免费获得的结构性属性相同,只是为基于启动的生成器重新实现了一遍。 + +### 手动维护的启动 manifest 是不可化约的策略 + +文件系统负责发现工具包清单,完整性守卫负责拒绝遗漏。`TOOL_PACKAGES` 仍然为每个包持有一份显式的启动配方,因为所需的 seam 实现和配置属于策略,不是能从目录布局或注入名称安全推断的事实。 + +### 范围 + +`packages/*/tool-*` 下已发布的产品工具包,每个都使用默认配置启动,包括 `dsh-tool-bash`(`bash`)、`dsh-tool-tasks`(`task_output`、`task_list`、`task_kill`)和 `dsh-tool-subagent`(`subagent`)。仅供示例使用的工具不在范围内。 + +目录的单位是包,而非每个配置化的工具实例。每个包以默认配置启动一次;加载时的别名(如 `subagent_fork`)会注明,但不枚举所有部署排列。部署清单是一个独立的、无界的接口。 + +### 使用普通 `json` 围栏 + +schema 块使用 ` ```json `,而非自定义的 `ts` 系围栏。`doc-typecheck` 只提取 `ts*` 围栏,因此 JSON 块对它不可见——无需 `BlockKind` 接线(不同于 Cordis 目录的 `ts cordis-catalog` 围栏,后者需要加入白名单以避免裸签名片段被编译)。 + +## 曾考虑的替代方案 + +- **纯 TypeScript AST 遍历,如 Cordis 目录**:工具 schema 在静态层面不可知(见上文核心要点):运行时展开、字符串拼接、配置选定的名称,以及原始 `ctx.tools.register()` 注册,都会让 AST 推导出的文档说谎。 +- **从各包的 inject 推断启动配方**:属于[发现包清单提案](../../proposed/process/2026-06-20-discover-package-inventory.md)所警告的「过度聪明」路径;配方保持为手写策略,清单由文件系统发现并由完整性守卫把关。 +- **为 schema 块使用自定义 `ts` 系围栏**:不必要。普通 ` ```json ` 围栏对 `doc-typecheck` 不可见,无需 `BlockKind` 白名单。 + +## 后果 + +- 目录不会发生漂移:提交文件未反映的工具 schema 变化会使 `doc-sync` 和 CI 中的 `verify-tool-catalog` 失败。新增的 `tool-*` 包若未加入清单,会直接使完整性守卫失败。 +- 工具描述文本有唯一归属——源码中 `defineTool` 的 `description`——生成的条目质量取决于它,与 Cordis 目录对事件 JSDoc 施加的强制力相同。 +- 生成器导入并执行工作区包(这是仓库中第一个这样做的脚本;其他脚本只读文本)。它通过根 `tsconfig` 的 `paths` 映射在 `tsx` 下运行,使用与演示和测试相同的未构建源码路径,因此不需要构建步骤。 +- 未来某个工具背后新增一个能力 seam,意味着 manifest 中需要新增一条配方条目(声明要挂载哪些 seam)。这正是上文指出的有意为之的手写成本;仅在新增工具包时才需变更。 diff --git a/.agents/notes/implemented/process/2026-07-03-documentation-graph-atlas.i18n.yaml b/.agents/notes/implemented/process/2026-07-03-documentation-graph-atlas.i18n.yaml new file mode 100644 index 0000000000..dbaa77f5ef --- /dev/null +++ b/.agents/notes/implemented/process/2026-07-03-documentation-graph-atlas.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-03-documentation-graph-atlas.md: 9a30b13f9db6ceb2715517230e349cbe083850ec +2026-07-03-documentation-graph-atlas.zh.md: 0734a2c659459f40ee81b9960f259681cb35891c diff --git a/.agents/notes/implemented/process/2026-07-03-documentation-graph-atlas.md b/.agents/notes/implemented/process/2026-07-03-documentation-graph-atlas.md index 7969f0e80c..9a30b13f9d 100644 --- a/.agents/notes/implemented/process/2026-07-03-documentation-graph-atlas.md +++ b/.agents/notes/implemented/process/2026-07-03-documentation-graph-atlas.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-07-03-documentation-graph-atlas.zh.md) + ## Problem The repo already had several high-trust documentation surfaces, each on a different axis: [module-graph.md](../../../../docs/module-graph.md) is generated from package `peerDependencies`, the generated [Cordis events](../../../../docs/cordis-catalog/events.md) and [services](../../../../docs/cordis-catalog/services.md) catalogs are generated from Cordis `Events` and `Context` declarations, [tool-catalog.md](../../../../docs/tool-catalog.md) is generated by booting shipped tool plugins, and [core-data-structures/](../../../../docs/core-data-structures/core.md) uses `ts type-equiv` blocks to keep pasted type definitions synchronized with source. diff --git a/.agents/notes/implemented/process/2026-07-03-documentation-graph-atlas.zh.md b/.agents/notes/implemented/process/2026-07-03-documentation-graph-atlas.zh.md new file mode 100644 index 0000000000..0734a2c659 --- /dev/null +++ b/.agents/notes/implemented/process/2026-07-03-documentation-graph-atlas.zh.md @@ -0,0 +1,70 @@ +# Agent Note: 面向维护者与 SDK 用户的文档关系图索引 + +Status: implemented + +[English](2026-07-03-documentation-graph-atlas.md) | 中文 + +## 问题 + +仓库已经有若干高可信文档表面,各自覆盖不同维度:[module-graph.md](../../../../docs/module-graph.md) 根据包(package)的 `peerDependencies` 生成;生成式 [Cordis 事件](../../../../docs/cordis-catalog/events.md)和[服务](../../../../docs/cordis-catalog/services.md)目录根据 Cordis `Events` 和 `Context` 声明生成;[tool-catalog.md](../../../../docs/tool-catalog.md) 通过启动已发布工具插件生成;[core-data-structures/](../../../../docs/core-data-structures/core.md) 则使用 `ts type-equiv` 块使粘贴的类型定义与源码保持同步。 + +这些参考文档是准确的,但大多是目录式的。维护者仍需自行综合关系:哪些包构成一个能力 seam、哪个应用组装了具体的主干、哪些事件是持久的而哪些是实时的、钩子或策略插件在哪里可以拦截工作、以及哪个面向模型的工具依赖哪个服务。SDK 用户从另一个角度面临同样的问题:「我想要某种行为,应该安装或加载哪个包?应该扩展哪个事件/服务/工具?」 + +钩子子系统使事件的生产者/消费方拓扑与拦截点变得更加重要;文件系统 seam 使能力 seam、策略否决、工具呈现与 SDK 组装路径变得更加重要。如果关系图的范围仅限于一个小的 bash/todo/subagent 表面,它们会立即陈旧。 + +## 决策 + +新增生成式关系图文档,由聚焦的生成器产出并在 [docs/graph-atlas.md](../../../../docs/graph-atlas.md) 建立索引;作为 `doc-sync` 的一部分,通过 `pnpm run verify-doc-graphs` / 现有目录新鲜度检查进行验证。 + +该索引是既有目录之上的关系层。它不取代精确的参考文档,而是链接到它们并解释各部分如何组合在一起。 + +### 维护模式 + +每个关系图页面声明一种维护模式: + +- **Generated(生成)**:所有节点和边均从源码发现;如果已提交的产物陈旧,`--check` 失败。 +- **Hybrid generated(混合生成)**:源码发现清单,一个小型 manifest 对不可约的策略进行分类,完整性守卫在发现的条目未被分类时失败。 +- **Curated(人工策划)**:图表解释设计意图、时序或归属;它由生成器输出以使关系图文档保持为可重新生成的整体,但内容是有意撰写的。 + +### 首批发布的索引 + +该索引链接十一种关系表面。包拓扑和工具包所提供的功能位于已经拥有这些事实的现有生成式目录中;其余聚焦图表由 `scripts/gen-doc-graphs.ts` 生成。 + +| 关系图 | 维护模式 | 真源 | +|---|---|---| +| [模块依赖图](../../../../docs/module-graph.md) | 生成式 | `packages/*/*/package.json` 的对等依赖(peer dependency)与包分组路径 | +| [工具 schema 目录与包映射](../../../../docs/tool-catalog.md) | 生成式 | 启动后采集的工具 schema,以及工具包服务/效应元数据 | +| [能力 seam 与核心服务](../../../../docs/capability-seams.md) | 混合生成式 | Cordis 服务声明,以及 `gen-doc-graphs.ts` 中的角色清单 | +| [tui-agent 应用组合](../../../../examples/tui-agent/composition.md) | 混合生成式 | `examples/tui-agent/cordis.yml` 插件列表,以及人工维护的应用/bundle 展开 | +| [headless-agent 应用组合](../../../../examples/headless-agent/composition.md) | 混合生成式 | `examples/headless-agent/cordis.yml` 插件列表,以及人工维护的应用/bundle 展开 | +| [cordis-agent 应用组合](../../../../examples/cordis-agent/composition.md) | 混合生成式 | `examples/cordis-agent/cordis.yml` 插件列表,以及人工维护的应用/bundle 展开 | +| [acp-agent 应用组合](../../../../examples/acp-agent/composition.md) | 混合生成式 | `examples/acp-agent/cordis.yml` 插件列表加人工策划的应用/bundle 展开 | +| [事件生产者/消费方矩阵](../../../../docs/event-producer-consumer.md) | 混合生成式 | Cordis 事件声明、经 AST 扫描的 `ctx.on/emit/parallel/serial/waterfall` 位置,以及显式动态分派覆盖 | +| [agent 轮次与步骤生命周期](../../../../docs/agent-lifecycle.md) | 人工维护 | architecture.md 循环生命周期、Cordis 目录链接,以及会话事件语义 | +| [工具执行管线](../../../../docs/tool-execution-pipeline.md) | 人工维护 | 工具管线语义与 `tools/execute` waterfall(瀑布式事件)| +| [ACP(Agent Client Protocol)快照回放](../../../../packages/ui/acp/snapshot-replay.md) | 人工策划 | 快照 harness 行为 | + +### 为什么由生成器拥有文档 + +包拓扑留在 `gen-module-graph.ts`,工具-包能力映射留在 `gen-tool-catalog.ts`,因为这些生成器已经拥有权威事实和新鲜度门禁。`gen-doc-graphs.ts` 拥有其余关系页面和索引。代价是人工策划的图表需要在 TypeScript 字符串块中编辑,而非直接编辑 Markdown。对于首版来说这是可接受的,因为面向用户的产物仍然是纯 Markdown/Mermaid;未来如果撰写体验比可重新生成更重要,可以将人工策划的页面拆分出去。 + +### 完整性守卫 + +混合生成的页面在其 manifest 陈旧时必须显式报错: + +- 模块图读取每个包的 `peerDependencies`,并按 `packages/<group>/<pkg>` 路径对包进行分组。 +- 工具目录通过启动收集已发布的工具,并从同一份 manifest 渲染包/服务/副作用映射(其完整性守卫已在检查该 manifest)。 +- 能力 seam 图导入 Cordis 服务收集器,断言每个发现的 harness `ctx.<key>` 都已在 `SERVICE_ROLES` 中分类,且每个已分类的 key 仍然存在。 +- 事件生产者/消费方矩阵标记为 hybrid,因为 subagent 生命周期事件有意使用 `ctx.events.dispatch` 实现逐监听器隔离;这些动态边是显式覆盖而非无声遗漏。 +- `verify-mermaid` 使用 Mermaid 自身的解析器解析仓库中每个 ` ```mermaid ` 围栏,因此语法错误在本地和 CI 的 `doc-sync` 阶段即被捕获,而非在 GitHub 渲染时才显示为损坏的图表。 + +## 曾考虑的替代方案 + +已提交的图表使用 Mermaid,因为 GitHub 在 Markdown 中原生渲染它且不引入新的文档构建依赖;密集的多对多数据(如事件生产者/消费方关系)改用 Markdown 表格。**PlantUML、托管图表服务和生成的 SVG** 曾被考虑,但在 Mermaid 成为瓶颈之前有意不采用。 + +## 后果 + +- 维护者获得了拓扑、seam、事件流、生命周期、应用组合与快照行为的可视化入口。 +- SDK 用户获得了从用例到包组合的路径,而非仅有自底向上的包参考。 +- `doc-sync` 现在包含 `verify-doc-graphs` 和 `verify-mermaid`,因此关系图漂移和 Mermaid 语法错误与其他文档新鲜度门禁一起被捕获。 +- 未来的文件系统和钩子工作有了承载新复杂度的具体位置:文件系统应扩展能力文档和工具目录,钩子应扩展事件矩阵和工具执行流水线。 diff --git a/.agents/notes/implemented/process/2026-07-04-cordis-jsdoc-completeness-gate.i18n.yaml b/.agents/notes/implemented/process/2026-07-04-cordis-jsdoc-completeness-gate.i18n.yaml new file mode 100644 index 0000000000..21465703e1 --- /dev/null +++ b/.agents/notes/implemented/process/2026-07-04-cordis-jsdoc-completeness-gate.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-04-cordis-jsdoc-completeness-gate.md: c7c39986414437ce4d0d4c64f9e25f47485fdf5c +2026-07-04-cordis-jsdoc-completeness-gate.zh.md: f1e7ec824ebae119c1cb27ca4dd9f0d8330dde1a diff --git a/.agents/notes/implemented/process/2026-07-04-cordis-jsdoc-completeness-gate.md b/.agents/notes/implemented/process/2026-07-04-cordis-jsdoc-completeness-gate.md index 3945382217..c7c3998641 100644 --- a/.agents/notes/implemented/process/2026-07-04-cordis-jsdoc-completeness-gate.md +++ b/.agents/notes/implemented/process/2026-07-04-cordis-jsdoc-completeness-gate.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-07-04-cordis-jsdoc-completeness-gate.zh.md) + ## Problem The generated Cordis catalog enforced event dispatch modes but not complete service and event contracts. Methods could lack descriptions, and parameters or returns could be undocumented on the cross-plugin API surface where IDE guidance matters most. diff --git a/.agents/notes/implemented/process/2026-07-04-cordis-jsdoc-completeness-gate.zh.md b/.agents/notes/implemented/process/2026-07-04-cordis-jsdoc-completeness-gate.zh.md new file mode 100644 index 0000000000..f1e7ec824e --- /dev/null +++ b/.agents/notes/implemented/process/2026-07-04-cordis-jsdoc-completeness-gate.zh.md @@ -0,0 +1,41 @@ +# Agent Note: 针对 Cordis 对外服务接口的 JSDoc 完整性门禁 + +Status: implemented + +[English](2026-07-04-cordis-jsdoc-completeness-gate.md) | 中文 + +## 问题 + +生成的 Cordis 目录此前强制了事件分发模式,但未强制要求完整的服务与事件契约。方法可以缺少描述,参数或返回值可以在跨插件 API 接口上不写文档——而这恰恰是 IDE 引导最重要的地方。 + +AGENTS.md 中的规则(「每个导出都有解释语义的 JSDoc」)只能靠评审以行文形式检查;本仓库的既定偏好是将不变式编码为机械门禁。「Cordis 服务函数与事件」这一范围有精确的机器定义,只有目录生成器知道:事件是 `declare module 'cordis'` 内 `interface Events` 的成员,服务接口是每个 `interface Context` 键所指向的类的公开方法。ESLint 规则看不到这层映射;生成器在每次运行时计算它。 + +## 决策 + +扩展 `scripts/gen-cordis-catalog.ts`——复用同一次遍历和同一套 `@mode` 先例——对它编目的所有内容强制执行 JSDoc 完整性要求。`verify-cordis-catalog` 在 `doc-sync` 内运行,因此相关文档变更和 CI 会执行同一门禁,无需另行接线。 + +契约如下: + +- **事件**需要描述性文字,以及为每个**载荷参数**提供非空的 `@param`。载荷参数是携带事件数据的签名参数;`this` 接收者注解和尾部的 waterfall(瀑布式事件) `next` 免检——`next` 是分发机制,其语义已由 `@mode waterfall` 标签(及其结构交叉检查)拥有,逐事件重述只是样板代码。为免检参数写文档是允许的;只有缺失才被检查。 +- **服务类**需要类级 JSDoc,每个公开方法需要描述性文字、为每个参数提供非空的 `@param`,以及非空的 `@returns`——除非标注的返回类型是 `void`/`Promise<void>`(此时 `@returns` 可选——resolve 时机有时值得记录——但从不强制要求)。 +- **陈旧标签报错**:`@param` 命名了一个不存在的参数即为违规,与 `@mode` 与签名矛盾的检查对称。标签描述必须非空;超出此范围的语义质量由评审负责。 +- **遍历可检查的显式性**:门禁是纯 AST 遍历(不使用类型检查器),因此服务方法必须显式标注返回类型(推断的返回类型无法分类),接口参数必须是简单标识符(解构模式没有名称供 `@param` 匹配)。 +- **违规聚合**为一条错误信息,列出所有违规项——修复时一次看到完整清单。此前快速失败的 `@mode` 检查也移入同一份聚合报告,消息文本不变。 + +生成器保留同一源码注释的两种视图:`parseJsDoc` 在第一个块标签处结束条目正文,而 `ts cordis-catalog` 签名块包含原始 JSDoc,并完整保留 `@param`、`@returns` 和 `@mode`。因此,读者可以看到完整的源码契约,而块标签文本不会泄漏到周围正文中。 + +`packages/core/agent/tests/gen-cordis-catalog.spec.ts` 中的负路径测试对合成 fixture(测试前置数据)运行 `collectEvents`/`collectServices`,验证每条守卫都会触发且免检规则成立。撰写规则写在根 [AGENTS.md](../../../../AGENTS.md) 的约定条目中,与 `@mode` 规则并列。 + +## 曾考虑的替代方案 + +- **ESLint 规则**:无法看到该范围的机器定义(哪些 `interface Events` 成员、哪些 `ctx.<key>` 类构成 Cordis 对外服务接口);目录生成器在每次运行时恰好计算这层映射,因此门禁放在那里。 +- **将每个方法展开为单独的正文小节**:否决。目录保留一个服务章节和一个签名块,以维持可扫读性;附着于每个声明的 JSDoc 则在原处保留完整的方法契约。 +- **逃逸标签**:不设。该接口面小且经过策展(采纳时 12 个服务、57 个方法、27 个事件),要点在于检查不可豁免。 + +## 后果 + +- 新事件或服务方法不能带着未记录的参数或结果落地:生成器会拒绝重新生成,`verify-cordis-catalog` 也会使 `doc-sync` 和 CI 失败。采纳时发现的约 139 处缺口已在同一变更中补齐,因此门禁以绿色状态落地。 +- 服务接口必须显式标注返回类型并使用标识符参数。两项约束在采纳时均未构成限制(所有方法已有标注;不存在解构的 seam 参数);但二者现在是承重要求,违反时会被机械检测到。 +- AGENTS.md 中通用的 JSDoc 规则(「一行能说清就用一行」)在此接口上获得了更严格的特例:仅当方法无参数且返回 void 时,一行摘要才足够。 +- 为 `next` 或 `this` 写 `@param` 合法但不检查——这是有意的不对称:门禁强制载荷契约,拒绝要求样板代码。 +- 每个生成的事件或方法片段都带有其原始 JSDoc,而正文摘要不含标签。因此,源码编辑会同时刷新可读索引和签名旁展示的确切契约。 diff --git a/.agents/notes/implemented/process/2026-07-04-doc-tiers-and-budgets.i18n.yaml b/.agents/notes/implemented/process/2026-07-04-doc-tiers-and-budgets.i18n.yaml new file mode 100644 index 0000000000..d49010e985 --- /dev/null +++ b/.agents/notes/implemented/process/2026-07-04-doc-tiers-and-budgets.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-04-doc-tiers-and-budgets.md: 9993eda6b0c7f1f8e5908dbd85fcfb4e5c6b3d1d +2026-07-04-doc-tiers-and-budgets.zh.md: a40e7c2fe56ef86137bb7bb3ee8c818bdeed7eb9 diff --git a/.agents/notes/implemented/process/2026-07-04-doc-tiers-and-budgets.md b/.agents/notes/implemented/process/2026-07-04-doc-tiers-and-budgets.md index 68e055f0a2..9993eda6b0 100644 --- a/.agents/notes/implemented/process/2026-07-04-doc-tiers-and-budgets.md +++ b/.agents/notes/implemented/process/2026-07-04-doc-tiers-and-budgets.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-07-04-doc-tiers-and-budgets.zh.md) + ## Problem Standing docs accumulated repeated rules, retold incidents, duplicated package maps, and stale Agent Note summaries despite existing writing guidance. Because review alone did not prevent that growth, the repository needed a mechanical budget alongside its documentation taxonomy. diff --git a/.agents/notes/implemented/process/2026-07-04-doc-tiers-and-budgets.zh.md b/.agents/notes/implemented/process/2026-07-04-doc-tiers-and-budgets.zh.md new file mode 100644 index 0000000000..a40e7c2fe5 --- /dev/null +++ b/.agents/notes/implemented/process/2026-07-04-doc-tiers-and-budgets.zh.md @@ -0,0 +1,28 @@ +# Agent Note: 文档分层、预算与上限门禁 + +Status: implemented + +[English](2026-07-04-doc-tiers-and-budgets.md) | 中文 + +## 问题 + +尽管已有写作指导,常设文档仍不断累积重复规则、反复讲述的事件、重复的包(package)映射,以及陈旧的 Agent Note(agent 决策记录)摘要。仅靠评审无法阻止这种增长,因此仓库需要在文档分类之外再配一套机械预算。 + +## 决策 + +- **每项事实只归属一处的层级分类。**[docs/AGENTS.md](../../../../docs/AGENTS.md) 是文档标准:它为每种 Markdown 层级分配单一职责(常设指令、系统图、类型目录、决策记录、事件故事、操作指南、各包契约、生成式目录、工作流),禁止在事实归属层级之外重复陈述(应改为链接),并包含编写或评审任何文档时使用的赘余检查清单。 +- **范围窄且严格的预算门禁。**[scripts/verify-doc-budgets.ts](../../../../scripts/verify-doc-budgets.ts) 接入 `doc-sync`:[scripts/doc-budgets.manifest.json](../../../../scripts/doc-budgets.manifest.json) 列出的每份文档都必须低于其字数上限(采用 `wc -w` 语义,统计整个文件);预算内文件缺失也会使门禁失败,使重命名无法悄然遗落其预算。范围刻意只涵盖容易膨胀的常设文档——根目录和子树中的 `AGENTS.md` 文件、`architecture.md`、`packages/README.md`,以及它们将内容移入的常设策略文档(`docs/testing.md`、`docs/defensive-patterns.md`)。参考文档、Agent Note 和包 README 不设预算:只要每一行都是事实,长度在这些位置就是合理的;评审和赘余检查清单负责约束它们。 +- **上限是只进不退的执行红线。** 上限设定为文档当前字数的至少 105%(留出工作余量,使日常措辞调整能通过,而真正的膨胀仍会触发门禁),并随着文档被精简到目标预算而同步下调、保持该余量(根 `AGENTS.md` ≤ 1,500 词;`architecture.md` ≤ 1,800;子树 `AGENTS.md` ≤ 600;`packages/README.md` ≤ 600)。推进机制与[翻译配对的 `required` 清单](2026-07-02-bilingual-docs-and-pairing-gate.md)相同。门禁变红时,修复方式是按分类体系迁移或压缩内容;只有在 PR(Pull Request)描述中给出明确理由时才允许提高上限,manifest(元数据清单)的 diff 本身即为可评审的动作。 +- **精简的工作流 skill(技能),契约归文档。**[.agents/skills/dsh-doc-standards](../../../skills/dsh-doc-standards/SKILL.md) 承载放置/审计/红灯门禁工作流,并以文档标准为真源,与 [dsh-translate-docs](../../../skills/dsh-translate-docs/SKILL.md) 和 i18n 契约之间的分工相同。 + +## 曾考虑的替代方案 + +- **仅靠 skill 和评审纪律,不设门禁**:否决。上述膨胀正是在现行规则和评审注意力已经存在的情况下发生的;一条没有机械后盾的行文规则在此处已被证明无法维持,而本仓库自身的[质量门禁立场](2026-06-11-quality-gates.md)认为值得保持的不变式就值得编码。 +- **对所有文档层级全面设限**:否决。一刀切的上限恰好惩罚了那些正当的长文档(如特性矩阵或类型目录,每一行都是事实,例如 `packages/ui/acp/acp-feature-support.md`),并产生逐文件的例外变更,训练贡献者机械地批准提限。 +- **将标准放在 skill 内部**:否决。契约归文档,工作流归 skill;如果标准被塞进 SKILL.md,那些不调用该 skill 而直接编辑文档的 agent(智能体)就看不到它,而 `docs/AGENTS.md` 已经作为子树指令被任何在 `docs/` 下工作的人加载。 + +## 后果 + +- 向受预算约束的文档添加内容现在需要置换:将新增内容迁移到其分类体系归属地并留下指针,或压缩现有行文来腾出空间。只增不减会导致 CI 失败。 +- 精简到目标预算的重写以堆叠的后续 PR 落地,每次合并时同步下调 manifest 中的上限;在各自落地之前,文档冻结的上限仅阻止进一步膨胀。 +- 字数是一个粗糙的代理指标,这是有意接受的:它无法判断质量,但它在内容被添加的那一刻强制触发迁移决策,而那正是作者拥有足够上下文来正确放置内容的时刻。 diff --git a/.agents/notes/implemented/process/2026-07-04-persistence-log-catalog.i18n.yaml b/.agents/notes/implemented/process/2026-07-04-persistence-log-catalog.i18n.yaml new file mode 100644 index 0000000000..00db07d233 --- /dev/null +++ b/.agents/notes/implemented/process/2026-07-04-persistence-log-catalog.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-04-persistence-log-catalog.md: 1529f41b485c1bc8ca029c0a9264574fa7a886a0 +2026-07-04-persistence-log-catalog.zh.md: f3f77bb66f8798d953fed16bc79cadadc35c036a diff --git a/.agents/notes/implemented/process/2026-07-04-persistence-log-catalog.md b/.agents/notes/implemented/process/2026-07-04-persistence-log-catalog.md index bde0f08497..1529f41b48 100644 --- a/.agents/notes/implemented/process/2026-07-04-persistence-log-catalog.md +++ b/.agents/notes/implemented/process/2026-07-04-persistence-log-catalog.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-07-04-persistence-log-catalog.zh.md) + ## Problem `SessionEventMap` is the on-disk vocabulary, but its declarations are split across the owning session package and declaration merges. The generated persistence catalog is the single reference for every event, its complete payload declaration and source JSDoc, and the shared `SessionEvent` envelope; hand-maintained tables drift and are removed. These records are not Cordis events—observers receive them through the single `session/event` bus event—so the Cordis catalog cannot cover them. The generator discovers all declarations and the doc-sync freshness gate rejects omissions or stale output. diff --git a/.agents/notes/implemented/process/2026-07-04-persistence-log-catalog.zh.md b/.agents/notes/implemented/process/2026-07-04-persistence-log-catalog.zh.md new file mode 100644 index 0000000000..f3f77bb66f --- /dev/null +++ b/.agents/notes/implemented/process/2026-07-04-persistence-log-catalog.zh.md @@ -0,0 +1,36 @@ +# Agent Note: 生成式持久化日志事件目录 + +Status: implemented + +[English](2026-07-04-persistence-log-catalog.md) | 中文 + +## 问题 + +`SessionEventMap` 是磁盘格式的词汇,但其声明分散在所属的会话包(package)和声明合并中。生成式持久化目录是所有事件、各自完整 payload 声明与源码 JSDoc,以及共享 `SessionEvent` 信封的唯一参考;手工维护的表格会发生漂移,因此被移除。这些记录不是 Cordis 事件——观察者通过唯一的 `session/event` 总线事件接收它们——所以 Cordis 目录无法覆盖。生成器会发现所有声明,文档同步新鲜度门禁会拒绝遗漏或陈旧输出。 + +## 决策 + +从源码生成 `docs/persistence-catalog.md`,配合新鲜度门禁,作为第四个参考面:持久化会话日志可以包含的*记录*,与 Cordis 目录(接线)、核心数据结构(词汇)和工具目录(工具)互补。 + +`gen-persistence-catalog.ts` 使用 TypeScript AST 扫描每个所属及声明合并的 `SessionEventMap`。它从前置 JSDoc 开始渲染每个成员,直至完整的 payload 类型,保留嵌套属性注释且只移除其容器缩进;同时粘贴构成持久化信封的所属 `SessionEventType`、`SurfaceEventType`、`SurfaceOp` 和 `SessionEvent` 声明。派生的 surface 徽章、参考链接和源码位置仍位于声明块之外。文档同步新鲜度检查会拒绝目录尚未重新生成的词汇或信封变更。 + +具体选择: + +- **强制保证 JSDoc 完整性。** 每个成员和渲染出的信封类型都必须带有描述正文,完整的源码 JSDoc 会在目录中保持附着于其声明。`@mode` 标签是硬错误:分派模式属于 Cordis 总线事件,持久化记录没有这种模式。所有违规会汇总为一条错误,列出每个违规项。 +- **surface 徽章由派生得出,而非手工列举。** `SurfaceEventType`(产生 LLM(大语言模型)消息且可能携带 `surfaceOp` 的子集)从拥有方包中的 union 声明解析;如果 union 成员命名了一个未声明的事件,则为硬错误(否则陈旧的 union 成员会静默地不标注任何内容)。其余一律渲染为 **log-only**。 +- **专用围栏。** 声明块使用 ` ```ts persistence-catalog ` 信息字符串,`doc-typecheck` 会识别并跳过这些块,将其排除在 opt-out 比例之外——处理方式与 `ts cordis-catalog` 相同(这些声明引用所属模块中的类型,无法独立编译)。 +- **仓库范围。** 目录枚举本仓库中的包,与兄弟文档的 packages-only 范围一致;下游插件可以合并更多事件类型,它们在设计上不在目录范围内。遍历过程用硬错误保护自身假设:拥有方的顶层 `interface SessionEventMap` 必须是 `@deepseek-ai/dsh-session` 中唯一的导出声明(无关的、局部的或同名重复的接口不能被当作磁盘词汇编入目录);任何声明不得携带 `extends`(继承的键会加入 `keyof SessionEventMap` 却没有对应的目录行);每个成员必须是带有显式 payload 类型的属性签名(方法形式的成员会加入 `keyof` 却在静默遍历中被漏过);跨声明的重复成员也会失败。 + +本方案取代了手工副本:session.md 的 `hook/*` 表格、精简版 README 的事件表格、hook-protocol README 的 payload 条目列表,以及会话 README 的名称列表现在链接到目录,而不再重述 payload(周围的语义说明文字保留原位)。hook-protocol 合并成员上的两个误加的 `@mode emit` 标签已被移除——新门禁将它们作为类别错误拒绝。 + +## 曾考虑的替代方案 + +- **基于启动的生成器(类似工具目录)**:日志词汇完全是静态的,AST 遍历无需启动任何东西即可读取全部真相。 +- **保留手工副本**:手工副本只能检查作者已经写下的名称;目录落地时,会话 README 的合并说明已经漂移。 + +## 后果 + +- 目录不会发生漂移:提交文件未反映的词汇或信封变化会使 `doc-sync` 和 CI 中的 `verify-persistence-catalog` 失败,而没有 JSDoc 的新增合并事件会直接使生成器失败——插件不能再添加未记录的磁盘记录类型。 +- 事件正文只有一个归属,即声明处的 JSDoc;目录会保留该 JSDoc 和所有嵌套字段注释,不会将其扁平化或复述。 +- `SurfaceEventType` union 现在对文档具有结构性承载作用:重命名事件而不更新 union(或反过来)会导致生成器失败,而不仅仅是编译器失败。 +- 徽章派生假设 union 始终是一组封闭的字符串字面量且只有一个拥有方;如果重构偏离了这一形状,必须在同一个变更中更新生成器。 diff --git a/.agents/notes/implemented/process/2026-07-05-uniform-agent-note-format.i18n.yaml b/.agents/notes/implemented/process/2026-07-05-uniform-agent-note-format.i18n.yaml new file mode 100644 index 0000000000..1cf70223f5 --- /dev/null +++ b/.agents/notes/implemented/process/2026-07-05-uniform-agent-note-format.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-05-uniform-agent-note-format.md: 06082251c1b96c90ed470d84224662e00e29791b +2026-07-05-uniform-agent-note-format.zh.md: df6b0f4dfacf122f452807491680091827f69c25 diff --git a/.agents/notes/implemented/process/2026-07-05-uniform-agent-note-format.md b/.agents/notes/implemented/process/2026-07-05-uniform-agent-note-format.md index 1a6aa40477..06082251c1 100644 --- a/.agents/notes/implemented/process/2026-07-05-uniform-agent-note-format.md +++ b/.agents/notes/implemented/process/2026-07-05-uniform-agent-note-format.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-07-05-uniform-agent-note-format.zh.md) + ## Problem Agent Note paths encoded lifecycle and class, but file contents still mixed headings, status formats, ADR and proposal templates, and proposal-era sections in implemented records. Authors copied whichever neighbor they found, and lifecycle moves could skip the required rewrite because no gate enforced an in-file contract. diff --git a/.agents/notes/implemented/process/2026-07-05-uniform-agent-note-format.zh.md b/.agents/notes/implemented/process/2026-07-05-uniform-agent-note-format.zh.md new file mode 100644 index 0000000000..df6b0f4dfa --- /dev/null +++ b/.agents/notes/implemented/process/2026-07-05-uniform-agent-note-format.zh.md @@ -0,0 +1,30 @@ +# Agent Note: Agent Note 的统一受门禁约束的文件内格式 + +Status: implemented + +[English](2026-07-05-uniform-agent-note-format.md) | 中文 + +## 问题 + +Agent Note(agent 决策记录)的路径编码了生命周期和类别,但文件内容仍混杂着不同标题、状态格式、ADR 与提案模板,以及已实现记录中的提案阶段章节。作者会复制随手找到的相邻文件,而生命周期迁移可能跳过必要的改写,因为没有门禁强制执行文件内契约。 + +## 决策 + +[README.md § 文件格式](../../README.md#the-file-format)是文件内契约——头部块(`# Agent Note: <title>`,加上无日期且与文件夹一致的 `Status:` 枚举,其中只有拒绝原因可作为额外内容)、各生命周期的正文骨架(所有文件均以 `Problem` 开篇;`proposed/` 使用 `Proposal`/`Acceptance criteria`/`Risks`;`implemented/` 使用现在时的 `Decision`/`Consequences`,并禁止提案阶段标题;`rejected/` 冻结提案形状)、强制的 `Alternatives considered` 章节,以及规范章节词汇;定制技术章节可在这些规范章节之间保持自由形式。`pnpm run verify-agent-note-format`([scripts/verify-agent-note-format.ts](../../../../scripts/verify-agent-note-format.ts))作为 `doc-sync` 的一部分强制执行每项机械规则,因此跳过改写的生命周期迁移现在会使 CI 失败,而不再依赖评审者记忆。 + +定义该格式的同一变更规范化了整个语料库——遵循预发布立场:不设过渡期,不容忍双格式。唯一受既有条款豁免的是内容,而非格式:替代方案只能记录、不能杜撰,因此若某份格式制定前的 Agent Note 无法从记录中还原替代方案,就会携带确切的 `agent-note-format: alternatives-not-recorded` 注释;门禁只对日期早于本文的文件接受该注释。 + +## 曾考虑的替代方案 + +- **完整的刚性模板**(每个生命周期使用固定章节顺序,重构每份 Agent Note 以适配):否决。大型设计 Agent Note 包含八到十五个定制技术章节(包(package)拓扑、线协议、schema),它们是承载设计的内容,而非漂移;刚性顺序会迫使我们现在进行破坏性改写,并永远与模板较劲。 +- **仅规范化头部**(H1 和 Status,正文不动):否决。债务标记指出的是*正文*的体裁分裂,让 `Context`/`Decision` 与 `Problem`/`Proposal` 无限期并存什么也解决不了。 +- **不设 Status 行**(文件夹已经表示状态;格式制定前最新的三份 Agent Note 及其中一份的中文对应文件省略了该行):否决,保留文件的自描述性。通过门禁校验该行与文件夹一致,消除了原本促使我们删除它的漂移风险。 +- **带日期的 Status**(`Status: implemented (accepted YYYY-MM-DD)`):否决。接受日期属于叙述性历史,写作规则将其排除在文档之外;文件名承载首次提出日期,git 承载其余信息;门禁能检查日期格式,但永远无法检查其真实性。 +- **裸 `# <title>` H1**:否决。文件脱离目录树单独阅读时,`Agent Note: ` 前缀能自描述其体裁,而格式门禁可防止它漂移。 +- **以 `## What we give up` 作为已实现记录的结尾**(README 对 Agent Note 所记录内容的原有表述):否决。它只点出成本,而诚实的后果章节也会记录取舍换来了什么。 +- **只有约定没有门禁**(写下契约,靠评审强制执行):否决。slop checklist 已经通过约定禁止在 `implemented/` 中使用 spec 语气,而十九个文件展示了仅靠约定在此处能达到什么效果。 +- **独立的 `FORMAT.md` 契约文件**:否决。由一个入口同时承载布局、分类和格式,比维护两个契约文件更易发现和维护。 + +## 后果 + +现在每份 Agent Note 都需要稍多一些结构,而强制的 `Alternatives considered` 章节是有意设置的阻力:记录决策却不记录它胜过什么,会招致 Agent Note 本应防止的重新争论。无法还原替代方案的格式制定前 Agent Note 会永久保留既有条款注释——这是记录中诚实的缺口,而不是杜撰的理由。`doc-sync` 增加一道门禁;在生命周期文件夹之间移动 Agent Note 时,现在必须当场完成真正的工作(迁移本就应包含的正文改写),而不是推迟为无人跟踪的清理任务。三十九个债务标记已经消失,由它们一直等待的模板解决。 diff --git a/.agents/notes/implemented/process/2026-07-06-export-surface-jsdoc-gate.i18n.yaml b/.agents/notes/implemented/process/2026-07-06-export-surface-jsdoc-gate.i18n.yaml new file mode 100644 index 0000000000..966ac24d13 --- /dev/null +++ b/.agents/notes/implemented/process/2026-07-06-export-surface-jsdoc-gate.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-06-export-surface-jsdoc-gate.md: 93d8a41fc2ffb235de5c56ffeb5569bc95249392 +2026-07-06-export-surface-jsdoc-gate.zh.md: 64b4bcc620046f2c94a2ce3fbeb67e59ada888d4 diff --git a/.agents/notes/implemented/process/2026-07-06-export-surface-jsdoc-gate.md b/.agents/notes/implemented/process/2026-07-06-export-surface-jsdoc-gate.md index 734fbeab21..93d8a41fc2 100644 --- a/.agents/notes/implemented/process/2026-07-06-export-surface-jsdoc-gate.md +++ b/.agents/notes/implemented/process/2026-07-06-export-surface-jsdoc-gate.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-07-06-export-surface-jsdoc-gate.zh.md) + ## Problem The [cordis JSDoc completeness gate](2026-07-04-cordis-jsdoc-completeness-gate.md) made undocumented parameters and results impossible on the cordis surface — `interface Events` members and `ctx.<key>` service classes — but that surface is a fraction of what a plugin author imports. The AGENTS.md rule "every export (and non-obvious method) has a JSDoc explaining semantics" stayed prose-checkable only by review everywhere else, and nothing at all asked for `@param`/`@returns` on ordinary exported functions. A survey at adoption found 203 under-documented module-level exports across 34 packages: seam-adjacent helpers (`runBash`, `readForEdit`, `htmlToMarkdown`), format codecs, whole undocumented interfaces and type aliases — exactly the names an IDE consumer hovers. diff --git a/.agents/notes/implemented/process/2026-07-06-export-surface-jsdoc-gate.zh.md b/.agents/notes/implemented/process/2026-07-06-export-surface-jsdoc-gate.zh.md new file mode 100644 index 0000000000..64b4bcc620 --- /dev/null +++ b/.agents/notes/implemented/process/2026-07-06-export-surface-jsdoc-gate.zh.md @@ -0,0 +1,45 @@ +# Agent Note: 导出表面 JSDoc 门禁 + +Status: implemented + +[English](2026-07-06-export-surface-jsdoc-gate.md) | 中文 + +## 问题 + +[Cordis JSDoc 完整性门禁](2026-07-04-cordis-jsdoc-completeness-gate.md)使得 Cordis 表面上的参数和返回值不可能缺少文档——`interface Events` 成员和 `ctx.<key>` 服务类——但这只是插件作者所导入内容的一小部分。AGENTS.md 中的规则「每个导出(以及非显而易见的方法)都必须有解释语义的 JSDoc」在其他地方只能靠评审以行文方式检查,而且没有任何机制要求普通导出函数带 `@param`/`@returns`。采纳时的一次调查发现 34 个包(package)中有 203 个文档不完整的模块级导出:seam 相关辅助函数(`runBash`、`readForEdit`、`htmlToMarkdown`)、格式编解码器、完全无文档的接口和类型别名——恰恰是 IDE 消费方悬停查看的那些名称。 + +## 决策 + +新增门禁 `scripts/verify-export-jsdoc.ts`(`pnpm run verify-export-jsdoc`,接入 `doc-sync`(文档同步门禁),与 `verify-cordis-catalog` 并列),遍历每个 `packages/<group>/<pkg>/src/` 目录树下的所有模块级导出名称。解析与检查辅助函数从 `gen-cordis-catalog.ts` 移入共享的 `scripts/jsdoc.ts`,使得「已文档化」在两个表面上含义一致:描述性文字在第一个块标签处截止、每个可检查参数需要非空 `@param`、非 void 且有显式标注的返回值需要非空 `@returns`、过时的 `@param` 报错,违规项汇总为一份报告。 + +按声明类型划分的契约: + +- 每个导出名称都需要带有非空描述文字的 JSDoc。 +- 函数类导出(函数声明;初始化器为函数或带有内联可调用标注的 const;非标识符的函数默认导出)遵循完整的函数契约,分类前会剥离包装表达式(括号、`as`/`satisfies` 类型断言、非空断言)。如果 const 声明器标注了一个具名类型(`export const f: Handler = …`),签名契约推迟到该类型自身的声明处,`@returns` 保持可选;内联的 `(x: T) => U` 标注或单调用签名字面量本身就是表面签名,适用完整契约;而混合了调用/构造签名与其他成员的字面量则直接拒绝(没有单一签名可供标签对照——请提取具名类型)。 +- 导出类需要类级别的描述文字;公开方法(包括静态方法——可通过导出名称访问)遵循函数契约;公开属性和访问器需要描述文字(get/set 对由 getter 覆盖)。重载实现体免检——签名承载文档。 +- 导出接口、类型别名和枚举需要声明级别的描述文字;成员级别的强制有意推迟(承载关键成员契约的 seam 服务类已在 Cordis 门禁之下)。 +- 导出命名空间递归检查(在 ambient `declare` 命名空间内,每个成员隐式导出);命名空间本身仅在不与同名的已文档化声明合并时才需要描述文字(Config-namespace 惯用法只需文档化插件一次)。 +- `declare module`/`declare global` 体和 `export … from` 重导出语句被跳过:augmentation 不是包的导出,重导出的定义在其定义处检查。`export import X = N.member` 别名需要文档化自身——其目标可能是遍历不会访问的非导出命名空间成员——且门禁仅支持纯描述文字的目标类型:可调用、类或命名空间目标携带别名描述文字无法承载的签名/成员契约,门禁会拒绝并要求直接导出该声明。 +- 其余情况按封闭原则失败:`export =` 直接拒绝;基类从未命名的参数即使作为绑定模式仍需 `@param`;dispatch 不识别的导出语句类型本身就是违规——没有任何导出形式能因遗漏而免检。 + +三类豁免避免门禁要求样板代码,精神与 Cordis 门禁的 `this`/`next` 豁免一致(为已豁免的名称编写文档是允许的;只有缺失才不被检查): + +- **继承成员。** 重写从其基类声明继承文档。新增的公开表面仍需文档:新增参数、将 protected 成员公开重写、或在 void 基类之上返回具体类型。继承查找和推断返回值分类是门禁唯一需要类型检查器的工作;其他检查使用 AST。 +- **插件协议槽位。** 顶层的 `name`/`inject`/`reusable`/`Config` 常量和 `apply` 入口,以及插件类上的同名静态成员,属于框架协议:其形状由 Cordis 固定,模块文档注释加 `interface Config` 承载插件的真实语义。 +- **构造函数**,与 Cordis 门禁一致:插件类由框架构造,类文档承载全部说明。 + +`collectExportJsdocViolations()` 返回违规列表(CLI(命令行界面)在非空时以 1 退出),因此 `packages/core/agent/tests/verify-export-jsdoc.spec.ts` 中的负路径测试直接断言发现项,通过 fixture(测试前置数据)包驱动每一种拒绝和每一种豁免。 + +## 曾考虑的替代方案 + +- **eslint-plugin-jsdoc**(`require-jsdoc`/`require-param`/`require-returns`):覆盖了机械核心,但无法表达本仓库的契约。继承成员豁免需要跨包的类型解析,协议槽位和命名空间合并惯用法是 Cordis 特有的,而完整性语义(标签前描述文字、过时标签报错、汇总报告)已在 `scripts/jsdoc.ts` 中与 catalog 生成器共享。两套微妙不同的「已文档化」定义,正是本仓库「单一归属」规则所要防止的失败模式。 +- **扩展 `gen-cordis-catalog.ts`**:catalog 生成器渲染一个精选表面并守卫其新鲜度;仓库级遍历没有 catalog 可渲染。共享辅助函数、保持遍历独立,使每个门禁的职责清晰可读。 +- **强制接口/类型别名的成员文档**:推迟。这会使检查表面成倍增长,而这些成员大多是自描述的字段;承载关键成员契约的 seam 服务类已有门禁。如果评审中出现成员文档漂移再重新考虑。 + +## 后果 + +- 新导出不能在缺少文档的情况下落地:`verify-export-jsdoc` 会使 `doc-sync` 和 CI 失败。采纳时发现的 203 处缺口已在同一变更中补齐,因此门禁以绿色状态落地。 +- 导出函数必须标注返回类型(采纳时已全面满足,现在成为门禁依赖),并在 `@param` 需要命名参数时使用标识符参数。 +- seam 文档是权威的:实现从其继承链继承文档,值得保留在实现上的行为说明是补充,而非必需。 +- 门禁构建一个 `ts.Program`(约 6 秒)——唯一需要类型解析的文档门禁;在已编译文档片段的 `doc-sync` 内可以接受。 +- 协议槽位名称按约定保留在模块顶层;一个恰好命名为 `apply` 或 `Config` 的非协议导出将不被检查——已接受,记录于此。 diff --git a/.agents/notes/implemented/process/2026-07-06-generated-config-catalog.i18n.yaml b/.agents/notes/implemented/process/2026-07-06-generated-config-catalog.i18n.yaml new file mode 100644 index 0000000000..17473bf069 --- /dev/null +++ b/.agents/notes/implemented/process/2026-07-06-generated-config-catalog.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-06-generated-config-catalog.md: f39f5138526d3278e839ee0053d5051bb8bc1c36 +2026-07-06-generated-config-catalog.zh.md: 825046914dad8e1a7d87340a310b252f03cbecb9 diff --git a/.agents/notes/implemented/process/2026-07-06-generated-config-catalog.md b/.agents/notes/implemented/process/2026-07-06-generated-config-catalog.md index f876191be4..f39f513852 100644 --- a/.agents/notes/implemented/process/2026-07-06-generated-config-catalog.md +++ b/.agents/notes/implemented/process/2026-07-06-generated-config-catalog.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-07-06-generated-config-catalog.zh.md) + ## Problem The repository had no source-backed reference for plugin configuration. Package READMEs documented fields inconsistently, did not enumerate which packages are loadable, and did not verify that runtime schemas agree with declared config types. diff --git a/.agents/notes/implemented/process/2026-07-06-generated-config-catalog.zh.md b/.agents/notes/implemented/process/2026-07-06-generated-config-catalog.zh.md new file mode 100644 index 0000000000..825046914d --- /dev/null +++ b/.agents/notes/implemented/process/2026-07-06-generated-config-catalog.zh.md @@ -0,0 +1,40 @@ +# Agent Note: 生成式插件配置目录 + +Status: implemented + +[English](2026-07-06-generated-config-catalog.md) | 中文 + +## 问题 + +仓库此前没有以源码为后盾的插件配置参考。各包(package)的 README 对字段的记录方式不一致,未列举哪些包可被加载,也未校验运行时 schema 与声明的配置类型是否一致。 + +## 决策 + +`scripts/gen-config-catalog.ts` 根据各插件声明的 config 类型和 JSDoc 生成 [docs/config-catalog.md](../../../../docs/config-catalog.md),并包含注入要求、被引用类型的链接和源码位置。包内类型会以传递方式纳入;workspace 类型和外部类型则会链接或点名。确定性的 `--write` 和 `--check` 模式使提交页面成为生成产物。 + +此处采用纯 AST 生成是正确的,原因与事件/服务目录相同,而与工具目录不同:配置类型是静态声明,仓库中每个 schemastery schema 都是静态的 `z.object`/`z.intersect` 字面量,因此源码即全部真相——配置表面没有任何部分是运行时组合的。 + +具体选择: + +- **配置类型是第二参数的类型。** catalog 记录的是 `apply(ctx, config)` / 服务构造函数 `(ctx, config)` 的声明参数类型——即 Cordis 实际传入的值——而非按命名约定定位的 `Config` 导出。这使得遍历是全量的:无论接口叫 `AcpConfig` 还是 `BasicCompactConfig`,无论类型声明在兄弟文件中,还是插件完全没有验证 schema,都能正常工作。 +- **分类是全量的。** 每个 `packages/<group>/<pkg>` 条目都会被解析(镜像 Loader 的 `unwrapExports`:`exports.default ?? exports`),归入可配置插件、无配置插件、抽象 seam 类或库之一——各自渲染在独立小节中——无法归类的条目直接报错。新包不可能被悄悄遗漏。 +- **逐字段 JSDoc 强制要求。** 粘贴的声明中每个属性(包括嵌套的类型字面量)都需要非空的 JSDoc 描述,否则生成失败。粘贴本身就是文档,因此这与 events catalog 通过 `@mode` 施加的强制函数相同:源码文档过于单薄时门禁报错,而非产出单薄的 catalog。 +- **Schema 键与声明类型做比对。** 生成器通过局部和 workspace 类型解析嵌套的对象与数组路径。确定缺失的路径报错;无法枚举的外部或动态形状则跳过。比对有意设计为单向的,因为声明类型可能包含被排除在 loader 配置之外的运行时专用字段。 +- **专用围栏。** 粘贴的声明使用 ` ```ts config-catalog ` 信息字符串,`doc-typecheck` 会跳过它(引用了导入类型的孤立声明无法独立编译),并将其排除在 opt-out 比例之外——与 `cordis-catalog` 和 `persistence-catalog` 围栏的处理方式相同。 +- **单文件 `docs/config-catalog.md`**,而非一个单文件目录:该页面面向单一受众(`cordis.yml` 的编写者),只有一个维度,不同于 `cordis-catalog/`(其中包含两个并列页面)。 + +各包 README 中的 `## Config` 小节保留。重叠是有意接受的:README 是经过策划的逐包契约(在部署上下文中描述配置语义,连同限制与扩展点),catalog 则是穷举式的生成枚举。由于 catalog 是生成的,二者不一致时说明 README 有误,修复方式是编辑 README——catalog 不会漂移。 + +## 曾考虑的替代方案 + +- **合成式逐字段渲染**:为每个字段生成项目符号列表、表格或带注释的 YAML 片段,从解析的 JSDoc 加 schema 元数据组装。否决,改用逐字粘贴:接口连同其 JSDoc 本身就是以原始形式撰写的契约,合成渲染器会重新格式化它不拥有的行文,增加一个可能歪曲原意的渲染层。 +- **运行时启动 + schema 内省(如工具目录所做的那样)**:否决。此处没有任何内容是运行时组合的,且 schema 本身对配置表面的文档化不足(以行文记录的默认值、运行时专用字段、完全没有 schema 的插件)。启动只会增加脆弱性而不增加真相。 +- **双向 schema/接口等价检查**:否决,改用子集检查。声明类型合理地包含 schema 拒绝从配置接受的成员(运行时专用 seam)。 +- **在同一变更中废除 README `## Config` 小节**:否决。保留可接受的重叠使逐包契约在原处可读,而清理工作需要先把每个 README 的额外事实折入字段 JSDoc——这是可分离的工作,catalog 不依赖它。 + +## 后果 + +- 目录不会发生漂移:提交文件未反映的源码变化会使 `doc-sync` 和 CI 中的 `verify-config-catalog` 失败。config 字段未记录、被引用类型名无法解析,或 schema 键未出现在 config 类型中,都会直接使生成器失败。 +- 配置行文现在有了声明处的强制函数:编写新配置字段意味着编写其 JSDoc,而该 JSDoc 将逐字成为 catalog 条目。 +- 生成器对无法静态遍历的形状直接报错——别名化的包内配置导入、非 `object`/`intersect` 组合构建的 schema、未列入的全局类型名。引入此类形状时必须同时教会生成器(否则该形状不能进入仓库),这正是设计意图:catalog 始终是全部真相。 +- `gen-cordis-catalog.ts` 导出其 JSDoc/指针辅助函数与 `LINK_MAP` 供复用,因此两个 catalog 以相同方式交叉链接类型,新增一条 link-map 条目同时服务于两者。 diff --git a/.agents/notes/implemented/process/2026-07-06-node-engine-floor.i18n.yaml b/.agents/notes/implemented/process/2026-07-06-node-engine-floor.i18n.yaml new file mode 100644 index 0000000000..2cb7f1009d --- /dev/null +++ b/.agents/notes/implemented/process/2026-07-06-node-engine-floor.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-06-node-engine-floor.md: f1754ea7ca32452a04c6cd8a0599568f602e47dd +2026-07-06-node-engine-floor.zh.md: 9d376a639378d3a0b9b645aa36c1a5d320d1d147 diff --git a/.agents/notes/implemented/process/2026-07-06-node-engine-floor.md b/.agents/notes/implemented/process/2026-07-06-node-engine-floor.md index 507641a99a..f1754ea7ca 100644 --- a/.agents/notes/implemented/process/2026-07-06-node-engine-floor.md +++ b/.agents/notes/implemented/process/2026-07-06-node-engine-floor.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-07-06-node-engine-floor.zh.md) + ## Problem The Node 22 branch of the root `engines.node` range is a contract for the installed workspace, not only for the runtime APIs the harness source calls directly. It must be no lower than package `engines.node` declarations for dependencies the workspace installs on that branch; otherwise `pnpm install --engine-strict` fails at an advertised LTS version, and non-strict installs run outside a dependency's supported runtime. diff --git a/.agents/notes/implemented/process/2026-07-06-node-engine-floor.zh.md b/.agents/notes/implemented/process/2026-07-06-node-engine-floor.zh.md new file mode 100644 index 0000000000..9d376a6393 --- /dev/null +++ b/.agents/notes/implemented/process/2026-07-06-node-engine-floor.zh.md @@ -0,0 +1,39 @@ +# Agent Note: 将 Node LTS 引擎下限提升至 22.19 + +Status: implemented + +[English](2026-07-06-node-engine-floor.md) | 中文 + +## 问题 + +根 `engines.node` 范围中的 Node 22 分支是对已安装工作区的契约,而不仅仅是 harness 源码直接调用的运行时 API 的契约。它不得低于工作区在该分支上安装的依赖包(package)所声明的 `engines.node`;否则 `pnpm install --engine-strict` 会在一个已宣传的 LTS 版本上失败,而非严格模式的安装则会在依赖所支持的运行时范围之外运行。 + +## 决策 + +将 `engines.node` 设为 `^22.19.0 || >=24.0.0`,并在 keyless CI 兼容性矩阵中测试 `['22.19', 24, 26]`。每条矩阵分支都运行 TypeScript 类型检查加一次 keyless 的源码模式 worker 冒烟测试,因此引擎下限通过完整的源码类型检查和真实的未构建运行时路径两条路径得到验证。真实 API 的 e2e 工作流保持在 Node 24 上,因为它验证的是 API 集成而非运行时下限。 + +两个 Node 特性决定了源码运行时的门槛: + +- **`node:sqlite`**:`packages/session-persistence/session-persistence-sqlite` 在顶层执行 `import { DatabaseSync } from 'node:sqlite'`。该模块在 **22.13**(LTS)和 **23.4**(Current)取消了 `--experimental-sqlite` 标志要求;在此之前,导入它会在加载时抛出异常。 +- **原生 TypeScript 类型剥离**——构建模式的 `examples/headless-agent/tests/keyless-smoke.e2e.ts` 冒烟测试使用纯 `node`(无 tsx)启动 `dsh-cli-demo` 已发布的 `lib/bin.js`,并加载示例的 `.ts` 测试适配器(`cli-mock-llm.ts`)。类型剥离从 **22.18**(LTS)和 **23.6**(Current)起成为默认行为;更早版本需要 `--experimental-strip-types`。 + +这些源码特性在 22.x 线上于 **22.18** 全部就绪,但已安装的 Pi 适配器依赖将宣传的 LTS 下限进一步提高。`@deepseek-ai/dsh-llm-pi-ai` 依赖 `@earendil-works/pi-ai@0.79.3`,后者的包声明 `engines.node >=22.19.0`,因此 LTS 下限为 **22.19**。24.x 分支保持 `>=24.0.0`。该不相交范围完全排除了 Node 23:Node 23.0–23.5 至少还有一个源码特性需要标志,而 23 线是非 LTS/已 EOL 的,宣传 `>=23.6` 会增加一条已终止的发布线和一条 CI 分支,而没有任何部署应当使用它。 + +`@types/node` 继续固定在 22.x 线(`^22.20.0`),以匹配 LTS 支持线:使用 Node 23+/24+/25+ 的 API 会在所有机器和类型检查门禁中导致 `tsc` 失败,而不是编译通过、直到仅下限矩阵分支才能捕获的运行时错误才暴露。目前整个代码树在 Node 22 类型表面上类型检查全部通过,因此这一固定没有任何代价。 + +## 后果 + +- 宣传的 LTS 分支不再低于 Pi 适配器依赖的下限。 +- CI 通过 Node 22.19 直接验证 Node 22 LTS 下限,Node 24 分支保持 `node: 24`,Node 26 用于下一个偶数线;每条分支都对源码图执行类型检查,并实际启动未构建的工作流 worker。 +- built-bin 冒烟测试无需版本条件标志:在 22.19 上类型剥离已是默认行为,因此测试保持其文档所述的纯 `node lib/bin.js` 路径。 +- 未来若依赖或源码 API 提高运行时下限,必须在同一变更中同步调整 `engines.node`、兼容性矩阵和本 Agent Note(agent 决策记录)。 + +## 曾考虑的替代方案 + +- **保持 `^22.18.0 || >=24.0.0`。** 否决:它宣传的 LTS 版本低于 Pi 适配器依赖的下限。`@earendil-works/pi-ai@0.79.3` 要求 `>=22.19.0`。 +- **降级或固定 `@earendil-works/pi-ai` 以保留 22.18 的宣传范围。** 否决:当前 Pi 适配器依赖是预期工作区的一部分,且 22.19 仍在 Node 22 LTS 线内。 +- **下限 `>=22.13`(`node:sqlite` 边界)加上在 22.13–22.17 的 built-bin 冒烟测试中使用 `--experimental-strip-types`。** 否决:它为一个狭窄范围增加了版本条件测试标志,并将实验性标志依赖包装为正式支持。Pi 适配器依赖已经要求更高的 LTS 下限。 +- **开放式 `>=22.19`。** 否决:它宣传支持 Node 23.0–23.5,而在这些版本上 `node:sqlite`(直到 23.4)或类型剥离(直到 23.6)仍需标志。 +- **包含 Node 23.6+(`^22.19.0 || >=23.6.0`)。** 否决:23.6+ 确实能无标志运行两个源码特性,但 Node 23 已 end-of-life;宣传一条已终止的发布线会增加一个范围项和一条 CI 分支,而没有任何部署应当使用该运行时。 +- **矩阵 `[22, 24, 26]` 而非固定 `22.19`。** 否决:浮动的主版本号条目会随时间上漂,悄然不再验证所声明的 LTS 下限。 +- **保持 `@types/node` 超前于运行时下限(`^25`)。** 否决:类型定义超前于运行时下限会让仅 Node 24/25 才有的 API 编译通过,仅在 22.x 上运行时才失败。将 `@types/node` 固定在 22.x 线上可将此类问题转化为所有环境下的编译错误。 diff --git a/.agents/notes/implemented/process/2026-07-06-parallel-github-ci-gates.i18n.yaml b/.agents/notes/implemented/process/2026-07-06-parallel-github-ci-gates.i18n.yaml new file mode 100644 index 0000000000..9aa8a03c52 --- /dev/null +++ b/.agents/notes/implemented/process/2026-07-06-parallel-github-ci-gates.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-06-parallel-github-ci-gates.md: 5c276f6a75936021369bc5ad9494c9aa6e4e3fc3 +2026-07-06-parallel-github-ci-gates.zh.md: 7d98f842ef1d60a3a5b727f975cb1d93ea6f253c diff --git a/.agents/notes/implemented/process/2026-07-06-parallel-github-ci-gates.md b/.agents/notes/implemented/process/2026-07-06-parallel-github-ci-gates.md index fef5852153..5c276f6a75 100644 --- a/.agents/notes/implemented/process/2026-07-06-parallel-github-ci-gates.md +++ b/.agents/notes/implemented/process/2026-07-06-parallel-github-ci-gates.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-07-06-parallel-github-ci-gates.zh.md) + ## Problem The keyless GitHub CI gates are mostly orthogonal: typecheck, lint, documentation freshness, coverage, snapshot replay, build, package-publication hygiene, demo smoke, and built-bin smoke fail for different reasons and do not need each other's runtime state. Running them as one ordered command chain makes the workflow wall clock equal the sum of those gates, while splitting every short leaf into its own GitHub job repeats checkout, Node setup, pnpm restore, and install work until orchestration overhead becomes the bottleneck. diff --git a/.agents/notes/implemented/process/2026-07-06-parallel-github-ci-gates.zh.md b/.agents/notes/implemented/process/2026-07-06-parallel-github-ci-gates.zh.md new file mode 100644 index 0000000000..7d98f842ef --- /dev/null +++ b/.agents/notes/implemented/process/2026-07-06-parallel-github-ci-gates.zh.md @@ -0,0 +1,50 @@ +# Agent Note: 并行 GitHub CI 门禁 + +Status: implemented + +[English](2026-07-06-parallel-github-ci-gates.md) | 中文 + +## 问题 + +无密钥 GitHub CI 门禁大多相互正交:类型检查、lint、文档新鲜度、覆盖率、快照重放、构建、包(package)的发布卫生检查、demo 冒烟和已构建二进制冒烟会因不同原因失败,也不需要彼此的运行时状态。将它们作为一条有序命令链运行,会使工作流墙钟时间等于所有门禁耗时之和;而把每个短小叶子拆成独立 GitHub job,又会反复执行 checkout、Node 设置、pnpm 恢复和安装,直到编排开销成为瓶颈。 + +随着 workspace 增长,原有的宽车道拆分不再满足这一平衡。PR(Pull Request)#404 合并时,Linux 的静态、覆盖率、快照和产物 job 分别耗时 148、195、94 和 230 秒;Windows 的静态和产物 job 分别耗时 251 和 482 秒。每个包都调用一次包管理器打包,主导了两个产物验证器的耗时;覆盖率在仅运行源码的套件前无谓地重建输出;CPU 密集型门禁则在静态与覆盖率车道内争用资源。 + +产物边界仍然承载关键约束。`publint`、`verify-node-next-types`、已编译不变量加载和已构建二进制冒烟测试都需要生成的 `lib/` 输出。分片不能让这些消费方抢在构建前运行,也不能用源码执行取代它们对已发布产物的信号。 + +## 决策 + +下述生产拓扑已经成为历史,并由[基于证据采用更大的托管 runner](2026-07-22-evidence-based-larger-hosted-runners.md) 取代。更大 runner 的决策移除了其分片选择器和工作流 job;本文保留早期拓扑为何被实现的记录。 + +[CI](../../../../.github/workflows/ci.yml) 将非 Windows job 的一分钟和 Windows job 的三分钟视为观测所得的性能目标,而非取消截止时间。托管 runner 的波动应留下完整计时证据和有用的失败日志,而不是取消本来正确的门禁。[串行跨平台 CI 参考](2026-07-21-serial-cross-platform-ci-reference.md)会在 Linux、macOS 和 Windows 上独立运行完整、未分片的主 Node 聚合,使优化后的车道清单不会成为自身完整性的唯一判据。 + +在该拓扑中,[scripts/run-gates.ts](../../../../scripts/run-gates.ts) 是通用的有界调度器,GitHub 则为昂贵的门禁族提供显式分片名称。`scripts/static-shards.ts` 将静态门禁划分为基础、文档类型、API 契约、目录、正文、文档投影和文档构建等归属,并拒绝缺失或重复的门禁分配。Linux lint 使用互不重叠的 A-C、D-M、N-S、T-Z 包源码和包测试车道,Windows 则使用完整的包源码与包测试车道;两者都包含从 `.` 开始的仓库补集,使新增顶层目标无法消失在分片之间,并负责唯一一次跨文件重复检查。`scripts/coverage-shards.ts` 把每个 workspace 包恰好分配给一个源码覆盖率车道。目录过滤器保留尾部分隔符,因为 Vitest 位置过滤器按子字符串匹配,否则会纳入具有同名前缀的相邻项。每个覆盖率车道只包含其拥有的源码文件,重复运行穷尽式伴随拓扑测试,并且不先执行构建,因为从删除了所有生成式 `lib/` 的树开始,完整覆盖率套件仍可通过。 + +快照重放使用两个显式多文件车道,以及大型 ACP(Agent Client Protocol)文件的八个场景分区。`scripts/snapshot-shards.ts` 拥有该清单,其测试会发现快照配置允许的每个文件。每个快照 job 在其 Linux runner 准备 Bubblewrap 的同时安装依赖,随后构建已发布运行时,并且只运行分配给它的重放表面。该套件保留五个子进程的有界并发,因为重放的大部分时间都在等待子进程协议 I/O。fixture(测试前置数据)守卫仍会在每个分区中检查完整 ACP 场景表。 + +冷启动的独立文档类型检查会重建完整的项目引用图,因此专用文档类型车道只构建一次,再用这些声明检查 Markdown 块。Linux 文档车道使用 VitePress 的 MPA 构建,在观测所得的非 Windows 目标内保留页面渲染与死链接验证;单独的阻塞式 Windows 构建和生产站点车道保留已生成包与已发布站点检查,同时避免把两条关键路径放进同一个 job。 + +产物使用两个车道:一个元数据车道负责 `publint`、NodeNext 声明和已编译不变量加载,另一个负责已构建二进制冒烟。每个车道都会在其消费方之前自行构建。重复短时构建会消耗 runner 分钟数,但避免了上传/下载依赖,并使每个 job 的关键路径保持有界。 + +[scripts/publint-all.ts](../../../../scripts/publint-all.ts) 在进程内针对内存发布视图调用 publint 支持的 API;该视图由每份清单声明的文件和 npm 强制元数据文件构成。这样无需生成 103 次包管理器打包命令,也能保留 workspace 文件与已发布文件之间的区别。[scripts/verify-built-package-invariants.mjs](../../../../scripts/verify-built-package-invariants.mjs) 在真实包下暂存这些经过结构验证、由清单声明的 `lib/` 文件,再通过纯 Node 和 Cordis Loader 规范化导入已编译的自引用。若伴随项触及未声明的运行时分片,仍会失败。 + +兼容性车道会在每条声明支持的 Node 版本线上运行源码 worker 和 Zstandard 运行时冒烟。TypeScript 在专用的主 Node 24 车道中只检查一次源码图;在运行时兼容性 job 中重复同一编译器分析只会增加耗时,不会提供运行时特有信号。 + +工作流缓存 pnpm store,将每个不可变 ESLint 缓存的键绑定到其所属 lint 分片,为 Windows 测量保留原生 PowerShell,并保留一个聚合的 `all checks passed` 状态用于分支保护。Windows 复用三个穷尽式 lint 分区,并在共享 runner 设置后组合基础/目录/正文门禁与文档类型/API 契约门禁;只有调度方式与 Linux 分区不同。Windows 构建和生产站点验证继续阻塞,而更广泛的 Windows 静态、lint 和产物矩阵仍为观察性检查。 + +## 曾考虑的替代方案 + +- **保留宽车道**:最大限度减少工作流 YAML,但会保留观测到的数分钟反馈周期。 +- **让每个叶子门禁分别成为 GitHub job**:最大化扇出,但短小的生成器和正文检查准备 runner 的时间会超过检查仓库的时间。 +- **向产物消费方上传一次构建**:避免重复编译,但上传/下载和依赖调度会延长墙钟时间;干净构建足够短,可以在有界车道内重复。 +- **在两个发布门禁中保留包管理器打包**:把清单选择委托给 pnpm,但会重复启动 200 多个包管理器进程。清单结构门禁加发布视图 fixture 使优化后的清单契约显式化,并会在存在磁盘上有但未发布的依赖时失败。 +- **在覆盖率前保留构建**:提供源码套件已不再消费的生成输出;干净树覆盖率证明表明这只是纯粹的延迟。 +- **在每个 Node 版本上执行类型检查**:重复编译器工作,而兼容性冒烟已经验证实际的 Node 特有加载与压缩行为。 + +## 后果 + +上述分片清单和矩阵 job 不属于当前仓库契约。取而代之的更大 runner 决策在单个进程中保留完整主清单,并以串行套件作为独立完整性判据。 + +优化后的发布验证器依赖由 `verify-package-invariants` 强制执行的清单 `files` 契约。如果发布规则超出该契约,结构门禁和两个暂存视图必须一起变化。 + +兼容性 job 不再声称 TypeScript 本身已在每个 Node 运行时下执行。它们证明 Node 22、24 和 26 上对运行时敏感的源码加载,而主运行时负责唯一一次源码图类型检查。 diff --git a/.agents/notes/implemented/process/2026-07-06-parallel-pre-push-gates.i18n.yaml b/.agents/notes/implemented/process/2026-07-06-parallel-pre-push-gates.i18n.yaml new file mode 100644 index 0000000000..0360eacf60 --- /dev/null +++ b/.agents/notes/implemented/process/2026-07-06-parallel-pre-push-gates.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-06-parallel-pre-push-gates.md: f2e8f0054e595be20a320ec7095f0fe674eb93c6 +2026-07-06-parallel-pre-push-gates.zh.md: 03b8773e475a9d1c82cea830cae6806a1c016f01 diff --git a/.agents/notes/implemented/process/2026-07-06-parallel-pre-push-gates.md b/.agents/notes/implemented/process/2026-07-06-parallel-pre-push-gates.md index 87b1c0847b..f2e8f0054e 100644 --- a/.agents/notes/implemented/process/2026-07-06-parallel-pre-push-gates.md +++ b/.agents/notes/implemented/process/2026-07-06-parallel-pre-push-gates.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-07-06-parallel-pre-push-gates.zh.md) + The local-hook portion of this record is superseded by [Fast local Git hooks](2026-07-22-fast-local-git-hooks.md). The bounded gate scheduler and package-level `publint` parallelism remain in force for CI, `doc-sync`, and explicit local commands. ## Problem diff --git a/.agents/notes/implemented/process/2026-07-06-parallel-pre-push-gates.zh.md b/.agents/notes/implemented/process/2026-07-06-parallel-pre-push-gates.zh.md new file mode 100644 index 0000000000..03b8773e47 --- /dev/null +++ b/.agents/notes/implemented/process/2026-07-06-parallel-pre-push-gates.zh.md @@ -0,0 +1,33 @@ +# Agent Note: 并行 pre-push 门禁 + +Status: implemented + +[English](2026-07-06-parallel-pre-push-gates.md) | 中文 + +本记录中的本地 hook 部分已由[快速本地 Git hook](2026-07-22-fast-local-git-hooks.md) 取代。有界门禁调度器和包(package)级 `publint` 并行机制仍用于 CI、`doc-sync` 和显式本地命令。 + +## 问题 + +文档同步等聚合 job 隐藏了很长的串行链,其成员只读且相互独立。在工作流 YAML 中重复这些叶子清单,会使未来脚本变更有多个位置可以发生漂移;而串行运行包发布检查,会使一道门禁的耗时与包数量成正比。 + +## 决策 + +[scripts/run-gates.ts](../../../../scripts/run-gates.ts) 拥有 CI、`doc-sync` 和选择启用的 `check:all` 命令所使用的有界调度器。它将具名模式展开为叶子门禁,遵守产物依赖,缓冲可归因的输出,并在调用方需要不同 worker 上限时接受 `DSH_GATE_CONCURRENCY`。 + +[scripts/publint-all.ts](../../../../scripts/publint-all.ts) 从 `packages/<group>/<pkg>` 发现包,并以根据 `availableParallelism()` 确定大小的 worker 池运行 `publint`。`DSH_PUBLINT_CONCURRENCY` 可以针对资源配置不同的本地机器和 CI runner 限制或提高 worker 数量。结果按包缓冲,并按确定性的包顺序打印,因此并行执行不会打乱各包的日志块。 + +各门禁的包脚本仍是临时本地运行所用的词汇。`hygiene` 继续作为聚合 `&&` 链,而 `doc-sync` 在调度器中拥有其成员列表([通过门禁调度器运行 doc-sync](2026-07-21-doc-sync-through-gate-scheduler.md))。 + +## 曾考虑的替代方案 + +- **保持聚合 job 串行**:执行更简单,但墙钟时间等于各独立检查之和,并重复启动命令包装器。 +- **每个叶子门禁声明一个 CI job**:暴露最大工作流并行度,但会重复 checkout、设置和安装开销,并在 YAML 中复制调度器清单。 +- **在 shell 脚本内后台运行子命令**:可以并行处理,但会失去各门禁计时、确定性的失败分组和直接的信号处理。 +- **每个包声明一个 `publint` job**:暴露最大包级并行度,但会创建手工维护的包清单,包发生变化时就会漂移。 +- **以无界并发运行 `publint`**:只有通过拿进程数、内存压力、包 tarball 创建和可读日志冒险,才能最大限度缩短小型仓库的耗时。 + +## 后果 + +由调度器支持的命令耗时取最慢依赖链,而非各独立门禁之和,并会报告主导耗时的门禁。代价是维护一个具有显式模式清单的定制调度器。 + +`publint-all.ts` 采用异步执行并缓冲命令输出,而不是实时继承 stdio。换来的是具有稳定输出顺序的包级并行,以及用于资源调节的单一环境变量。 diff --git a/.agents/notes/implemented/process/2026-07-10-readme-known-limitations-gate.i18n.yaml b/.agents/notes/implemented/process/2026-07-10-readme-known-limitations-gate.i18n.yaml new file mode 100644 index 0000000000..f24a929889 --- /dev/null +++ b/.agents/notes/implemented/process/2026-07-10-readme-known-limitations-gate.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-10-readme-known-limitations-gate.md: 2ca1168d795692730d17b6ab23dd113e8be277e5 +2026-07-10-readme-known-limitations-gate.zh.md: 4e42492f501cca1a45a90694acea4ca78e920780 diff --git a/.agents/notes/implemented/process/2026-07-10-readme-known-limitations-gate.md b/.agents/notes/implemented/process/2026-07-10-readme-known-limitations-gate.md index 0d294feb0f..2ca1168d79 100644 --- a/.agents/notes/implemented/process/2026-07-10-readme-known-limitations-gate.md +++ b/.agents/notes/implemented/process/2026-07-10-readme-known-limitations-gate.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-07-10-readme-known-limitations-gate.zh.md) + ## Problem The [documentation standard](../../../../docs/AGENTS.md) assigns limitations to package READMEs. Without a shared shape, an omitted section cannot distinguish an audited absence from forgotten documentation, and variant headings prevent a repository-wide search. diff --git a/.agents/notes/implemented/process/2026-07-10-readme-known-limitations-gate.zh.md b/.agents/notes/implemented/process/2026-07-10-readme-known-limitations-gate.zh.md new file mode 100644 index 0000000000..4e42492f50 --- /dev/null +++ b/.agents/notes/implemented/process/2026-07-10-readme-known-limitations-gate.zh.md @@ -0,0 +1,29 @@ +# Agent Note: 每个包(package)README 中受门禁保护的 Known Limitations 章节 + +Status: implemented + +[English](2026-07-10-readme-known-limitations-gate.md) | 中文 + +## 问题 + +[文档标准](../../../../docs/AGENTS.md)规定限制项归属包 README。没有共享形状时,缺少章节无法区分“经审计确认没有限制”与“忘记编写文档”,不同的标题还会妨碍全仓库搜索。 + +## 决策 + +`packages/<group>/<pkg>/package.json` 下的每份包清单都有一个同级 README,其中包含规范的 `## Known Limitations and Deferred Work` 章节。其项目符号记录由该包拥有的持久消费方缺口和不明显的维护者约束;普通清理仍留在源码 TODO 或所属 Agent Note(agent 决策记录)中。[`verify-package-readme-limitations` 门禁](../../../../scripts/verify-package-readme-limitations.ts)从清单推导包集合,拒绝缺失 README,并要求恰好一个规范 h2 且至少包含一个顶层项目符号。“Limitations”“Deferred”“What is NOT here”或“Non-goals”等近似标题都会失败。 + +如果一个包确实没有需要声明的限制事项,则将其列入 `NO_LIMITATIONS` 并省略该章节。新增限制事项时须移除该条目;重命名或移除条目会失败,因为每个条目都必须对应一个被扫描的包。 + +门禁检查存在性、形状和允许列表。按照文档与[正文](../../../skills/dsh-prose-standard/SKILL.md)标准进行的评审负责覆盖面和准确性。常设规则位于 [packages/AGENTS.md](../../../../packages/AGENTS.md)。 + +## 曾考虑的替代方案 + +- **自由格式标题**:无法统一搜索,仍需近似标题检测。 +- **要求空章节或写 "None."**:样板文字可能在包新增限制事项后仍然残留;白名单使「确无限制」这一状态显式且可评审。 +- **设置字数上限**:合理的限制事项数量因包而异,因此由评审管控这一不设预算的 README 层级。 + +## 后果 + +- 新建的包须声明符合条件的限制事项,或显式加入白名单;缺失、漂移或空的章节会在本地和 CI 的 `doc-sync` 中失败。 +- 门禁为 `doc-sync` 新增一个无外部依赖的 TypeScript 脚本。 +- 重命名受强制的标题需要同时修改脚本和所有包 README。 diff --git a/.agents/notes/implemented/process/2026-07-12-package-model-experience-contract.i18n.yaml b/.agents/notes/implemented/process/2026-07-12-package-model-experience-contract.i18n.yaml new file mode 100644 index 0000000000..ab312d8bcd --- /dev/null +++ b/.agents/notes/implemented/process/2026-07-12-package-model-experience-contract.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-12-package-model-experience-contract.md: 92a8e5a1a81d00dae085e4af89456896373058e6 +2026-07-12-package-model-experience-contract.zh.md: 54b181738b8276c634f777ad3424191c8652baec diff --git a/.agents/notes/implemented/process/2026-07-12-package-model-experience-contract.md b/.agents/notes/implemented/process/2026-07-12-package-model-experience-contract.md index dd986f3661..92a8e5a1a8 100644 --- a/.agents/notes/implemented/process/2026-07-12-package-model-experience-contract.md +++ b/.agents/notes/implemented/process/2026-07-12-package-model-experience-contract.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-07-12-package-model-experience-contract.zh.md) + ## Problem A package README can explain APIs and runtime mechanics without answering the questions that dominate an agent harness's behavior and cost: what from this package reaches a model request, under which conditions, how long those tokens remain, and whether later requests preserve a reusable KV-cache prefix. The omission is especially hard to audit in a plugin architecture. A consumer may turn a backend result into a tool message, a policy plugin may replace success with an error, compaction may remove old history, and an agent-scoped registration may change one agent's prompt or schemas while leaving every other agent unchanged. Reading only the nominally model-facing packages therefore misses real context effects, while reading source across every dependency is too expensive for routine review. diff --git a/.agents/notes/implemented/process/2026-07-12-package-model-experience-contract.zh.md b/.agents/notes/implemented/process/2026-07-12-package-model-experience-contract.zh.md new file mode 100644 index 0000000000..54b181738b --- /dev/null +++ b/.agents/notes/implemented/process/2026-07-12-package-model-experience-contract.zh.md @@ -0,0 +1,33 @@ +# Agent Note: 包(package)的模型体验契约 + +Status: implemented + +[English](2026-07-12-package-model-experience-contract.md) | 中文 + +## 问题 + +包 README 可以解释 API 和运行时机制,却不回答主导 agent harness(智能体框架)行为与成本的问题:该包的哪些内容会进入模型请求、在什么条件下进入、这些 token 会保留多久,以及后续请求是否会保留可复用的 KV cache 前缀。在插件架构中,这种遗漏尤其难以审计。消费方可能把后端结果转为工具消息,策略插件可能以错误取代成功结果,压缩可能移除旧历史,而 agent 范围的注册可能改变某个 agent 的提示词或 schema,却不影响其他 agent。因此,只阅读名义上面向模型的包会遗漏真实的上下文效应,而在每次常规评审中跨所有依赖阅读源码又成本过高。 + +## 决策 + +每个具有面向模型或邻近模型契约的 workspace 包 README 都以规范的[模型体验章节](../../../../docs/cookbook/adding-a-package.md#4-write-the-package-readme)收尾,位置紧邻 `## Known Limitations and Deferred Work` 之前;位于“无限制项”允许列表中的包则以模型体验本身结尾。经审计确认与模型无关的通用包通过 `NO_MODEL_EXPERIENCE_SECTION` 省略该章节。 + +具有直接、条件式、有上限、全生命周期、多表面或辅助模型效应的包,为每个上下文表面使用一个 H3。每个表面包含三个有序 H4 字段——`What the model sees`、`Token effect` 和 `KV Cache effect`——每个字段都以一个正文段落开头。cache 字段区分仅追加增长、稳定重复前缀、替换先前 token,以及独立模型请求;它点明由包拥有、且能在新内容追加前改变请求的每项配置、范围、生命周期、压缩或路由变化。“Does not invalidate”表示该包保留一个已经可复用的前缀,并非承诺提供方一定命中 cache 或保留某段时间。由包拥有的稳定文本按原文精确引用:系统提示词正文和其他长字面量在引入它们的字段下使用带标题的 H5 加 `markdown` 围栏,通常位于 `What the model sees`;短字面量则以内联形式保留,并点名插值占位符。工具 schema 表面链接生成式[工具目录](../../../../docs/tool-catalog.md)中带锚点的章节,并且只陈述组合或配置增量;仅运行时定义解释目录为何省略它们。依赖数据和由提供方拥有的文本采用摘要。agent 范围的可见性须显式说明;当范围可隐藏提示词与 schema 中的一者而不影响另一者时,两种表面保持分离。 + +没有模型上下文效应的包,或某条路径完全由另一个包渲染的包,使用验证器审计过的短格式:一句以 `None, as ` 或 `Indirectly, through ` 开头的句子,随后是一个 `KV Cache effect` H4 和一个正文段落。纯传输包和无密钥测试支持包若不创建任何进入模型的内容,就使用 none 格式。提供方后端即使会限制或过滤数据也使用 indirect 格式;具名子项拥有全部效应时,接线 bundle 也使用该格式。这些章节定位贡献并声明不会直接使 cache 失效,同时不重复陈述消费方。结构化章节同样只记录由包拥有的输入、变换和增量。 + +`verify-package-readme-model-experience` 发现包清单,并验证三种分类、规范末尾章节顺序、确切字段标题深度与顺序、非空字段段落、逐字块的 H5 归属、具体字面量证据,以及带锚点的工具目录链接。它在 `doc-sync` 和并行门禁 runner 中运行。评审仍负责覆盖面、链接相关性和事实准确性。 + +## 曾考虑的替代方案 + +- **只记录注册提示词或工具的包**:否决。后端、策略插件、适配器、持久化、作用域和压缩都会改变 token 的内容或生命周期,却不拥有面向模型的 schema。 +- **从源码生成一份集中式上下文成本目录**:否决。AST 能找到注册点,但无法推断语义条件,如历史保留、输出截断、父子可见性或辅助模型边界。包 README 是实现本地的契约;集中副本会增加又一个漂移面。 +- **要求给出精确 token 数**:否决。精确数量取决于所选模型的 tokenizer、适配器序列化方式、配置和运行时数据。稳定的契约是增长形状:每请求固定、每调用条件性、保留、替换、有上限或零直接影响。 +- **使用表格**:否决。精确源码文本和条件式结果形状会使单元格密集而难以扫读。重复的小节在保留相同字段的同时,为每个上下文表面提供易读的纵向空间。 +- **允许所有零影响包省略该章节**:否决。无约束的缺失在「经审计的零影响」和「忘记写文档」之间有歧义。省略仅限于在验证器中以理由命名的模型无关通用包;模型相邻的零影响包保留一句显式说明。 +- **要求经审计的零效应包或简单间接包使用完整结构化格式**:否决。它会围绕一个事实重复标签。受门禁约束的句子加 cache 字段既保留显式覆盖,又没有多余仪式。 +- **只有约定而无门禁**:否决。仓库级契约必须覆盖未来的每个包;评审者的记忆无法可靠地检测到遗漏的 README 章节。 + +## 后果 + +评审者可以从任何面向模型或邻近模型的包开始,看到它对对话模型、子模型和辅助调用的贡献,无需重建完整插件图。token 预算工作可以区分重复请求开销和依赖数据的历史,而 cache 敏感工作可以识别仅追加路径,以及最早由包引起的前缀变更。agent 范围变更有明确的文档检查点。每当模型可见行为发生变化时,包作者都要维护一个或多个紧凑的上下文表面块,或一种已分类的短格式;经审计的通用包不携带无关的模型样板。结构化字段不承诺由提供方给出的精确 token 数或 cache 命中;测量仍取决于具体模型、提供方和工作负载,而所记录的增长、可见性和前缀稳定性契约保持稳定。 diff --git a/.agents/notes/implemented/simplification/2026-06-19-drop-mutable-session-summary.i18n.yaml b/.agents/notes/implemented/simplification/2026-06-19-drop-mutable-session-summary.i18n.yaml new file mode 100644 index 0000000000..bf29a5ddca --- /dev/null +++ b/.agents/notes/implemented/simplification/2026-06-19-drop-mutable-session-summary.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-19-drop-mutable-session-summary.md: 80fe043e365352b17d2a5b3efa1ab8d396d311c4 +2026-06-19-drop-mutable-session-summary.zh.md: e875d96d003367dbe8a671e6057a6b4a6a44ca74 diff --git a/.agents/notes/implemented/simplification/2026-06-19-drop-mutable-session-summary.md b/.agents/notes/implemented/simplification/2026-06-19-drop-mutable-session-summary.md index f1a9c9aa3c..80fe043e36 100644 --- a/.agents/notes/implemented/simplification/2026-06-19-drop-mutable-session-summary.md +++ b/.agents/notes/implemented/simplification/2026-06-19-drop-mutable-session-summary.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-06-19-drop-mutable-session-summary.zh.md) + ## Problem The [session-persistence seam](../architecture/2026-06-14-session-persistence.md) split a session's out-of-log metadata into two types owned by `dsh-session`: an immutable `SessionHeader` (`version`, `id`, `createdAt`, `cwd?`, `parentSession?`) written once at creation, and a mutable `SessionSummary` (`updatedAt`, `title?`, `firstPrompt?`) "updateable without touching the append-only log". Their union was `SessionMeta = SessionHeader & SessionSummary`, and the abstract `SessionPersistence` service carried a seventh method — `update(id, summary)` — for rewriting the summary. Each backend implemented the mutable store its own way: JSONL wrote a separate atomic `.summary.json` **sidecar** beside the log (temp-write + rename, best-effort), SQLite kept `updated_at`/`title`/`first_prompt` **columns** bumped inside the append transaction. diff --git a/.agents/notes/implemented/simplification/2026-06-19-drop-mutable-session-summary.zh.md b/.agents/notes/implemented/simplification/2026-06-19-drop-mutable-session-summary.zh.md new file mode 100644 index 0000000000..e875d96d00 --- /dev/null +++ b/.agents/notes/implemented/simplification/2026-06-19-drop-mutable-session-summary.zh.md @@ -0,0 +1,35 @@ +# Agent Note: 移除可变的会话摘要 + +Status: implemented + +[English](2026-06-19-drop-mutable-session-summary.md) | 中文 + +## 问题 + +[会话持久化 seam](../architecture/2026-06-14-session-persistence.md)将会话的日志外元数据拆分为 `dsh-session` 拥有的两种类型:一个不可变的 `SessionHeader`(`version`、`id`、`createdAt`、`cwd?`、`parentSession?`),在创建时一次性写入;一个可变的 `SessionSummary`(`updatedAt`、`title?`、`firstPrompt?`),「可在不触碰仅追加日志的情况下更新」。二者的联合类型为 `SessionMeta = SessionHeader & SessionSummary`,抽象的 `SessionPersistence` 服务为此多出第七个方法 `update(id, summary)`,用于重写摘要。各后端各自实现可变存储:JSONL 在日志旁写一个独立的原子 `.summary.json` **伴随文件**(临时写入 + rename,尽力保证);SQLite 在追加事务内更新 `updated_at`/`title`/`first_prompt` **列**。 + +摘要是为未来的会话选择器设计的(通过 `updatedAt` 排序近期会话,用 `title`/`firstPrompt` 做预览)。该选择器从未实现。对整个仓库的审计表明,`SessionSummary` 的全部表面积都是**死状态**: + +- `SessionPersistence.update()` **零个生产调用方**(所有 `.update(` 匹配都是 `createHash().update()` 或测试代码)。 +- `firstPrompt` 在生产代码中**从未被读取**。 +- `title` *确实*在 ACP(Agent Client Protocol)桥接层被读取过,但读的是工具调用的 **presenter**(`present.title`),从未读取存储的会话元数据。 +- `updatedAt` **没有消费方**:`list()` 唯一的生产调用方读取的是 `meta.cwd`(`SessionHeader` 字段),用于在 `session/load` 时校验工作区;恢复会话读取的是 `createdAt`/`cwd`/`parentSession`——全是 header 字段。 +- 决定性的一点:活跃的 `Session.header` 类型本来就是 `SessionHeader` 而非 `SessionMeta`——摘要从未存在于活跃会话对象上;它只存在于持久化层,除了自身的契约测试外无人写入、无人读取。 + +## 决策 + +彻底删除可变的会话摘要。`SessionSummary` 与 `SessionMeta` 这个名称一并移除;后端存储和返回的元数据仅为 `SessionHeader`。`SessionPersistence.update()` 从抽象服务和所有后端中移除。JSONL 去掉整套伴随文件机制(`writeSidecar`/`readSidecar`/`touchSummary`/`removeSidecars`/`sidecarPath` 以及 load/list 的覆盖逻辑);SQLite 去掉 `updated_at`/`title`/`first_prompt` 列以及每次追加时的 `updated_at` 更新,其 `SCHEMA_VERSION` 从 `1 → 2`。 + +摘要原本要提供的一切,在消费方真正需要时都**可从仅追加日志中派生**(`firstPrompt` = 第一条 `user/message`;近期度 = 最后一个事件的 `time` 或文件 mtime),或者已经存在于不可变 header 中(`createdAt`、`cwd`)。唯一*不可*派生的是用户*手动编辑*的标题,但它从未实现,纯属 YAGNI;如果未来真有功能需要,它可以作为独立的日志事件或 header 字段回归。 + +这被记录为一项决策,因为它具有**持久性**(它同时收窄两个后端的公共服务契约和磁盘格式)、**争议性**(summary 是有意为未来设计的结果,而非意外),也具有**意外性**(未来读者在原 Agent Note(agent 决策记录)描述 `SessionMeta` 的位置发现 `SessionHeader`,否则会追问 summary 为何消失)。它还为[共享持久化写入协调器](../architecture/2026-06-18-shared-persistence-write-coordinator.md)扫清障碍:不再有可变 summary 后,协调器的钩子接口不需要 `updateSummary` 钩子,JSONL sidecar 与 SQLite 列之间的持久性分歧也随之消失,使两个后端的写入路径趋于一致。 + +## 无需迁移 + +这是未发布的软件(见[根 AGENTS.md](../../../../AGENTS.md)「Pre-release stance: foundation over blast radius」一节),因此没有需要保留的磁盘数据库或日志。SQLite 不迁移 v1 数据库:`openDatabase` 守卫现在拒绝任何非当前版本的磁盘 `user_version`(`onDisk !== 0 && onDisk !== SCHEMA_VERSION`),无论更旧*还是*更新,因此陈旧的 v1 数据库会被干净地拒绝,而非在新列集下被半读取。新建数据库写入当前版本号;这是唯一需要正常工作的路径。 + +## 后果 + +未来的会话选择器现在必须从日志派生预览/排序信息(或重新引入一个类型化字段),而不能直接读取现成的摘要行。这是正确的代价:为一个尚不存在的功能维护缓存,是每个后端都要付出维护成本、每个契约测试都要付出断言成本的死重。这一原则——**通过的测试固定的是当前行为,不一定是正确行为;行为可能是过去妥协的产物**——现已作为独立约定记录在[根 AGENTS.md](../../../../AGENTS.md) 中,本次变更即为其实例。 + +<!-- agent-note-format: alternatives-not-recorded (pre-format Agent Note) --> diff --git a/.agents/notes/implemented/simplification/2026-06-20-collapse-trace-only-session-events.i18n.yaml b/.agents/notes/implemented/simplification/2026-06-20-collapse-trace-only-session-events.i18n.yaml new file mode 100644 index 0000000000..e30531e02d --- /dev/null +++ b/.agents/notes/implemented/simplification/2026-06-20-collapse-trace-only-session-events.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-20-collapse-trace-only-session-events.md: fce5c48ef6fcb1abc6e2fbb95dc7e83d22956660 +2026-06-20-collapse-trace-only-session-events.zh.md: 5be2d77644c7b4084b892013a2c1e5b97a333d74 diff --git a/.agents/notes/implemented/simplification/2026-06-20-collapse-trace-only-session-events.md b/.agents/notes/implemented/simplification/2026-06-20-collapse-trace-only-session-events.md index 4e8a092989..fce5c48ef6 100644 --- a/.agents/notes/implemented/simplification/2026-06-20-collapse-trace-only-session-events.md +++ b/.agents/notes/implemented/simplification/2026-06-20-collapse-trace-only-session-events.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-06-20-collapse-trace-only-session-events.zh.md) + ## Problem The session event vocabulary includes first-class events that are not part of replayable conversation history and have little or no production consumption. `usage` is already present as a model stream chunk before the loop also appends a separate `usage` event. `error` duplicates the `turn/end { kind: 'error', message, code }` reason for loop failures; ACP settlement reads the turn-end reason, ACP rendering ignores the `error` event, and `deriveMessages()` skips it. diff --git a/.agents/notes/implemented/simplification/2026-06-20-collapse-trace-only-session-events.zh.md b/.agents/notes/implemented/simplification/2026-06-20-collapse-trace-only-session-events.zh.md new file mode 100644 index 0000000000..5be2d77644 --- /dev/null +++ b/.agents/notes/implemented/simplification/2026-06-20-collapse-trace-only-session-events.zh.md @@ -0,0 +1,44 @@ +# Agent Note: 将仅用于追踪的会话事实折叠进承载性事件 + +Status: implemented + +[English](2026-06-20-collapse-trace-only-session-events.md) | 中文 + +## 问题 + +会话事件词汇中包含一些一等事件,它们不属于可回放的对话历史,在生产环境中几乎没有消费方。`usage` 已经作为模型流分片存在,之后循环又追加了一个独立的 `usage` 事件。`error` 与 `turn/end { kind: 'error', message, code }` 中的循环失败原因重复;ACP(Agent Client Protocol)结算读取轮次结束原因,ACP 渲染忽略 `error` 事件,`deriveMessages()` 也跳过它。 + +这些事件让规范的 transcript(文本记录)看起来比实际更像遥测数据。它们增加了事件变体、不变式、测试、快照和持久化用例,但作为独立记录并不承载实际功能。它们携带的事实仍然有用:token 用量应当保留以供计费,错误的步骤编号也不应悄然消失。简化的方式是将这些事实折叠进消费方本已必须理解的邻近事件,而非减少记录的信息量。 + +## 决策 + +仅在信息已被保留、无需并行记录的情况下,移除独立的追踪事件: + +- 成功步骤的 usage 折叠进匹配的 `assistant/message`(`assistant/message { turn, step, content, usage? }`),使组装好的模型输出与其计费信息一同传递。 +- 失败或中止的步骤如果有 usage 但没有 assistant 内容,则将 usage 放在一个空内容的 `assistant/message` 上(下方实现说明给出了无信息丢失的证明)——不会有已持久化的 usage 分片无处安放。 +- 独立 `error` 事件中的步骤编号折叠进 `turn/end.reason`(当 `kind: 'error'` 时:`{ kind: 'error', step, message, code? }`)——`turn/end` 是 ACP 和恢复机制已经消费的持久轮次结果。 +- `agent/error` 与日志保留用于实时诊断;`turn/end` 之后不再有第二条会话日志错误记录。 + +用户对话日志包含渲染、恢复、审计和计费所需的全部信息,消费方无需协调重复的追踪行。 + +## 曾考虑的替代方案 + +**保留独立行作为遥测**——这些事件让规范 transcript 看起来比实际更像遥测数据,代价是增加了事件变体、不变式、测试、快照和持久化用例,却没有任何消费方使用。如果分析需求真正出现,正确的形态是投影辅助工具或带有独立保留策略的专用遥测存储,而非对话日志中的重复追踪行。 + +## 验证 + +`SessionEventMap` 不再包含独立的 `usage` 或 `error`;agent loop(智能体循环)不再追加独立的 usage 事件,持久性失败通过 `turn/end { kind: 'error', step, message, code? }` 记录;ACP 快照和持久化测试断言不存在仅追踪行;已录制的 fixture(测试前置数据)使用新事件形状,会话格式版本固定为 `0`(后端按预发布格式策略拒绝任何非 `0` 的存储日志);文档说明了 token 用量和操作错误的观测位置。 + +## 后果 + +消费方不能再从规范日志中筛选独立的 `usage` 或步骤级 `error` 行,必须从承载它们的 assistant/failure 事件中读取这些事实。只有在实现 PR(Pull Request)证明相同事实仍然存在的前提下,这才是合理的简化;否则独立事件应予保留。 + +## 实现说明 + +按提案落地,但有一处范围细化(遵循 AGENTS.md 所述“Agent Note(agent 决策记录)是提案,而非绝对真理”): + +- **空内容 `assistant/message` 承载 usage,无数据丢失。** 提案要求的证明(不会有已持久化的 usage 分片无处安放)落在 max-tokens 路径上:一个被截断的步骤有 usage 但内容为空(例如只有一个被丢弃的工具调用),以前会发出独立的 `usage`。现在它记录一个空内容的 `assistant/message { content: [], usage }`。为防止这向提供方 transcript 注入一个无内容的虚假 assistant 轮次,`deriveMessages()` 跳过空内容的 `assistant/message` 事件。回归测试断言 usage 仍被表示,且派生历史未被破坏。 + +**格式版本。** 此变更影响已持久化的事件,但预发布会话格式仍固定为 `0`,拒绝任何其他版本且不做迁移。`dsh-session` 拥有写入方和加载校验使用的常量。单调递增的格式版本从首次正式发布开始。 + +Usage 现在通过 `assistant/message.usage` 观测;操作错误的步骤编号通过 `turn/end.reason`(当 `kind: 'error'` 时)观测。`agent/error` 与日志用于实时诊断,保持不变。 diff --git a/.agents/notes/implemented/simplification/2026-06-20-drop-unconsumed-llm-adapter-change-event.i18n.yaml b/.agents/notes/implemented/simplification/2026-06-20-drop-unconsumed-llm-adapter-change-event.i18n.yaml new file mode 100644 index 0000000000..9529343206 --- /dev/null +++ b/.agents/notes/implemented/simplification/2026-06-20-drop-unconsumed-llm-adapter-change-event.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-20-drop-unconsumed-llm-adapter-change-event.md: a3c7c089d7dfa1a4cd6a891c416bf270dc7eff3d +2026-06-20-drop-unconsumed-llm-adapter-change-event.zh.md: d9129386dc95bae0716253fdf50236b25ebfdf75 diff --git a/.agents/notes/implemented/simplification/2026-06-20-drop-unconsumed-llm-adapter-change-event.md b/.agents/notes/implemented/simplification/2026-06-20-drop-unconsumed-llm-adapter-change-event.md index d8d4015b0d..a3c7c089d7 100644 --- a/.agents/notes/implemented/simplification/2026-06-20-drop-unconsumed-llm-adapter-change-event.md +++ b/.agents/notes/implemented/simplification/2026-06-20-drop-unconsumed-llm-adapter-change-event.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-06-20-drop-unconsumed-llm-adapter-change-event.zh.md) + ## Problem `LlmService.registerAdapter()` emits `llm/adapter-change` on registration and disposal ([packages/llm/llm/src/index.ts](../../../../packages/llm/llm/src/index.ts)). Grepping `llm/adapter-change` across `packages/*/src` and `examples/*/src` finds only the declaration, emit sites, docs, and tests; no production listener subscribes to it. diff --git a/.agents/notes/implemented/simplification/2026-06-20-drop-unconsumed-llm-adapter-change-event.zh.md b/.agents/notes/implemented/simplification/2026-06-20-drop-unconsumed-llm-adapter-change-event.zh.md new file mode 100644 index 0000000000..d9129386dc --- /dev/null +++ b/.agents/notes/implemented/simplification/2026-06-20-drop-unconsumed-llm-adapter-change-event.zh.md @@ -0,0 +1,36 @@ +# Agent Note: 移除未被消费的 `llm/adapter-change` 事件 + +Status: implemented + +[English](2026-06-20-drop-unconsumed-llm-adapter-change-event.md) | 中文 + +## 问题 + +`LlmService.registerAdapter()` 在注册和 dispose(资源释放)时发出 `llm/adapter-change` 事件([packages/llm/llm/src/index.ts](../../../../packages/llm/llm/src/index.ts))。在 `packages/*/src` 和 `examples/*/src` 中搜索 `llm/adapter-change`,只能找到声明、emit 站点、文档和测试;没有任何生产环境的监听器订阅它。 + +这与 `tools/change` 和 `system-prompt/change` 不同。如今这两个事件同样没有消费方,但它们有望成为未来实时工具/提示词 UI 的注册表变更信号。LLM(大语言模型)适配器注册更像是启动时的实现细节:适配器不是用户可见的选项面板,真正的模型调用拦截 seam 是 `llm/stream`。保留一个没有监听器的适配器变更事件,只是在更小范围内重复[删除无用 summary](2026-06-19-drop-mutable-session-summary.md) 的模式。 + +这个事件并非零成本。`registerAdapter()` 在发出 `llm/adapter-change` 之前先 yield 回滚 disposer,这样抛出异常的监听器会回退变更而非泄漏适配器条目;包内还有针对该监听器抛出路径的测试。这种防御性排序保护的是一个只有测试才能触发的失败模式。 + +## 决策 + +只移除 `llm/adapter-change`:包括 `dsh-llm` 的 `interface Events` 中的声明、`ctx.emit('llm/adapter-change')` 调用,以及 `LlmService.registerAdapter` JSDoc 中“在注册和释放时发出 `llm/adapter-change`”的句子。`registerAdapter()` 的效应生成器为 HMR(热模块替换)/释放保留变更与回滚 disposer,但移除仅因该事件而存在的监听器抛错回滚顺序。适配器 disposer 测试断言返回的 disposer 会移除适配器,不再订阅事件;监听器抛错回滚测试则随其测试对象一起消失。[docs/architecture.md](../../../../docs/architecture.md) 和 [packages/llm/llm/README.md](../../../../packages/llm/llm/README.md) 中的事件分类也在同一变更中更新。 + +## 曾考虑的替代方案 + +### 为什么不移除所有注册表变更事件? + +由注册表通告变更的微内核是一种一致的约定。当 UI 能够实时刷新可用工具或提示词章节时,`tools/change` 和 `system-prompt/change` 可能会有用。本 Agent Note(agent 决策记录)在存在合理用户侧消费方的位置保留该约定,只删除当前及可能的未来消费方都不明确的适配器变更事件。 + +如果将来需要 LLM 适配器浏览器或动态模型选择器用到此信号,届时再连同消费方一起重新引入,并提供比「something changed」更清晰的 payload。 + +## 验证 + +`llm/adapter-change` 及其 emit 已消失,重新生成的 Cordis 目录保持新鲜;HMR 安全性仍成立(释放贡献该适配器的 fiber 会移除它);`tools/change` 和 `system-prompt/change` 仍有文档与测试;ACP(Agent Client Protocol)快照和无密钥 Headless Loader 冒烟则固定了未变的生产路径。 + +## 后果 + +- **移除一个已文档化的 emit 事件属于公开接口变更。** 它出现在分类体系表中,读起来像有意设计的 API。但「已声明且已发出」不等于「已被消费」——这与移除可变 summary 时的判断依据相同。分类体系表在同一个变更中更新,因此文档不会漂移。 +- **注册表变更约定变得不均匀。** 这是可接受的,因为 LLM 适配器注册与工具或提示词段落不是同一层面的面向用户概念。不均匀但诚实,胜过统一但无用。 + +这是一个小裁剪,但它退役了一条守护着并不存在的消费方的正确性不变式。 diff --git a/.agents/notes/implemented/simplification/2026-06-20-drop-unconsumed-llm-assembled-surfaces.i18n.yaml b/.agents/notes/implemented/simplification/2026-06-20-drop-unconsumed-llm-assembled-surfaces.i18n.yaml new file mode 100644 index 0000000000..ad842ae732 --- /dev/null +++ b/.agents/notes/implemented/simplification/2026-06-20-drop-unconsumed-llm-assembled-surfaces.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-20-drop-unconsumed-llm-assembled-surfaces.md: b6b596e822b4bd6fd1bd891c336c622ad675ad45 +2026-06-20-drop-unconsumed-llm-assembled-surfaces.zh.md: bafc5d3bc630d89c776bbcf53719b29223e1c90d diff --git a/.agents/notes/implemented/simplification/2026-06-20-drop-unconsumed-llm-assembled-surfaces.md b/.agents/notes/implemented/simplification/2026-06-20-drop-unconsumed-llm-assembled-surfaces.md index b482a444b5..b6b596e822 100644 --- a/.agents/notes/implemented/simplification/2026-06-20-drop-unconsumed-llm-assembled-surfaces.md +++ b/.agents/notes/implemented/simplification/2026-06-20-drop-unconsumed-llm-assembled-surfaces.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-06-20-drop-unconsumed-llm-assembled-surfaces.zh.md) + ## Problem `LlmService` ([packages/llm/llm/src/index.ts](../../../../packages/llm/llm/src/index.ts)) exposes three call surfaces over a model: diff --git a/.agents/notes/implemented/simplification/2026-06-20-drop-unconsumed-llm-assembled-surfaces.zh.md b/.agents/notes/implemented/simplification/2026-06-20-drop-unconsumed-llm-assembled-surfaces.zh.md new file mode 100644 index 0000000000..bafc5d3bc6 --- /dev/null +++ b/.agents/notes/implemented/simplification/2026-06-20-drop-unconsumed-llm-assembled-surfaces.zh.md @@ -0,0 +1,39 @@ +# Agent Note: 移除未被消费的 LLM 组装便捷接口 + +Status: implemented + +[English](2026-06-20-drop-unconsumed-llm-assembled-surfaces.md) | 中文 + +## 问题 + +`LlmService`([packages/llm/llm/src/index.ts](../../../../packages/llm/llm/src/index.ts))在模型之上暴露了三个调用接口: + +- `stream()`:原始 `StreamChunk`,通过 `llm/stream` waterfall(瀑布式事件)分发。 +- `streamBlocks()`:一个「便捷视图」,将分片送入 `BlockAssembler` 并按流顺序产出已组装的 `ContentBlock`([index.ts:137-144](../../../../packages/llm/llm/src/index.ts))。 +- `generate()`:一个完整组装的 `GenerateResult`,通过第二条 `llm/generate` waterfall 分发([index.ts:151-157](../../../../packages/llm/llm/src/index.ts))。 + +LLM(大语言模型)服务唯一的生产消费方是 agent loop(智能体循环),它只使用 `stream()`:将原始分片送入自己的 `BlockAssembler`,以便在并行组装的同时记录分片,保证回放保真度([packages/core/agent-loop/src/loop.ts](../../../../packages/core/agent-loop/src/loop.ts),`ctx.llm.stream(req)` 步骤)。在 `packages/*/src` 和 `examples/*/src` 中 grep `streamBlocks` 与 `ctx.llm.generate`,找不到任何生产调用方。仅有的引用来自服务方法定义、文档和测试;适配器测试用 `generate()` 作为便捷驱动,但它们完全可以通过同一个 assembler 辅助函数手动消费 `stream()`,无需为此保留一个公开的生产 API。 + +这属于[删除可变会话 summary](2026-06-19-drop-mutable-session-summary.md) 的同类模式:带有受测契约的组装视图 API,由测试而非生产代码消费。它们是为不关心 token 级增量的消费方推测性构建的,但唯一的真实消费方恰恰关心增量,以便持久化高保真重放数据。 + +`streamBlocks()` 拖带了 `BlockAssembler` 的一块专用逻辑:`flushReady()` 与 `flushRemaining()`([packages/llm/llm/src/assembler.ts:138-168](../../../../packages/llm/llm/src/assembler.ts))以及 `flushed` 游标字段,仅为支持按序增量产出而存在。`generate()` 拖带了 `GenerateResult`、`BlockAssembler.result()` 以及 `llm/generate` waterfall——在同一底层流之上的第二个拦截面。agent loop 对 assembler 的使用仅限于 `push()` / `message()` / `usage` / `finish`,不涉及流式 flush 或一次性服务组装。 + +## 决策 + +`stream()` 是唯一的公开 LLM 调用接口。移除 `streamBlocks`、`generate`、其事件/结果类型,以及仅被该路径使用的 assembler 辅助方法。适配器测试通过本地辅助函数对公开流进行组装;`BlockAssembler` 仅保留有生产消费方的操作。 + +## 曾考虑的替代方案 + +**保留 `generate()` 作为仅供测试的便捷方法**:否决。适配器测试通过共享 assembler 手动消费 `stream()`,走的是与生产完全相同的流式路径;一个唯一调用方只有测试的公开方法,正是 [drop-mutable-summary 先例](2026-06-19-drop-mutable-session-summary.md)所淘汰的死接口形态。未来如果有消费方需要不带增量的组装块,届时再为该消费方引入一个聚焦的辅助方法。 + +## 验证 + +`streamBlocks`、`generate`、`llm/generate` 及仅供它们使用的 assembler 辅助函数均已移除,且未产生新的无用导出;两个真实适配器都通过 `stream()` 和共享 assembler 接受测试;循环行为保持一致(ACP(Agent Client Protocol)快照预期输出未变);README、架构文档和模块文档也不再提及已删除表面。 + +## 后果 + +- **从一个核心词汇包中移除了公开方法。** 未来如果有插件需要不带增量的组装块,它需要直接调用 `stream()` 并使用 `BlockAssembler`,或在有真实消费方时重新引入一个聚焦的辅助方法。鉴于预发布阶段「基础优先于预设未来」的立场([AGENTS.md](../../../../AGENTS.md)),现在正是裁剪仅供测试的公开接口的合适时机。 +- **适配器测试变得更显式。** 它们失去了便捷的 `generate()` 包装层,但这是有益的压力:测试走的是与生产相同的流式路径。 +- **waterfall 使用者失去 `llm/generate`。** 不存在生产监听者。未来的缓存/重试/日志插件应包装 `llm/stream`,它仍然是唯一的提供方调用路径。 + +改动规模不大,但它从 LLM 包中干净地移除了预设的接口面积,为生产和测试留下唯一一份模型调用契约。 diff --git a/.agents/notes/implemented/simplification/2026-06-20-prune-dead-seam-methods.i18n.yaml b/.agents/notes/implemented/simplification/2026-06-20-prune-dead-seam-methods.i18n.yaml new file mode 100644 index 0000000000..ed0b63a28d --- /dev/null +++ b/.agents/notes/implemented/simplification/2026-06-20-prune-dead-seam-methods.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-20-prune-dead-seam-methods.md: 70596d908bb1d7559e876d93bce0e25874ce1ff0 +2026-06-20-prune-dead-seam-methods.zh.md: 1fbc7dbf2f7abb5b17b1df10ef06e490b11335a4 diff --git a/.agents/notes/implemented/simplification/2026-06-20-prune-dead-seam-methods.md b/.agents/notes/implemented/simplification/2026-06-20-prune-dead-seam-methods.md index f74de250ef..70596d908b 100644 --- a/.agents/notes/implemented/simplification/2026-06-20-prune-dead-seam-methods.md +++ b/.agents/notes/implemented/simplification/2026-06-20-prune-dead-seam-methods.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-06-20-prune-dead-seam-methods.zh.md) + > **Implementation note:** Only `SessionPersistence.has()` and `.delete()` were removed. `BashExecutor.get()` and `.list()` remain because removing their one-line lookup surface required substantially more completion-tracking machinery in consumers. Their id branding is covered by the [branded-ids Agent Note](../architecture/2026-06-20-branded-ids.md). ## Problem diff --git a/.agents/notes/implemented/simplification/2026-06-20-prune-dead-seam-methods.zh.md b/.agents/notes/implemented/simplification/2026-06-20-prune-dead-seam-methods.zh.md new file mode 100644 index 0000000000..1fbc7dbf2f --- /dev/null +++ b/.agents/notes/implemented/simplification/2026-06-20-prune-dead-seam-methods.zh.md @@ -0,0 +1,43 @@ +# Agent Note: 从持久化 seam 中移除无用方法 + +Status: implemented + +[English](2026-06-20-prune-dead-seam-methods.md) | 中文 + +> **实现说明:** 仅移除了 `SessionPersistence.has()` 和 `.delete()`。`BashExecutor.get()` 和 `.list()` 仍然保留,因为删除它们的单行查找表面会要求消费方增加显著更多的完成跟踪机制。其 id 品牌化由[品牌化 id Agent Note(agent 决策记录)](../architecture/2026-06-20-branded-ids.md)负责。 + +## 问题 + +能力 seam([接口 / 实现 / 消费方](../architecture/2026-06-13-capability-seams.md))承载了没有消费方调用的抽象方法。seam 的存在是为了让实现和消费方独立演进——但没有消费方以之编程的方法不是 seam,而是每个实现仍必须实现和测试的推测性表面。 + +### `SessionPersistence.has()` 与 `.delete()` + +该抽象服务在 create/append 之外声明了更多操作:`load`、`list`、`has`、`delete`。`ctx.sessionPersistence` 的生产消费方只用了两个:agent loop(智能体循环)的恢复路径调用 `load()`([packages/core/agent-loop/src/index.ts:176](../../../../packages/core/agent-loop/src/index.ts)),ACP(Agent Client Protocol)桥接层为 `session/list` 调用 `list()`([packages/ui/acp/src/index.ts:494](../../../../packages/ui/acp/src/index.ts))。在 `packages/*/src` 和 `examples/` 中 grep 所有 `sessionPersistence.*` / `persistence.*` 的使用,找不到对该服务的 `has(` 或 `delete(` 调用。`packages/ui/acp/src/index.ts` 中的 `.has(`/`.delete(` 调用作用于内存中的 `SessionStore` 和一个本地的 loading id `Set`,而非持久化。`has`/`delete` 的唯一调用者是契约测试套件和各后端的 spec。 + +`has()` 不仅未被使用:在 `loadStored(id)` 已负责持久化存在性检查的情况下,它仍增加了协调器的已跟踪/未跟踪探测和一个契约分支。`delete()` 则拖入每个后端都必须实现的 `deleteStored` 后端钩子。这属于[删除可变会话 summary](2026-06-19-drop-mutable-session-summary.md) 的同类模式:契约测试覆盖了两者,但已发布代码从不会询问“这个会话是否已持久化?”或删除某个会话。 + +## 决策 + +没有消费方使用的方法被移除——从抽象 seam、实现,以及仅为覆盖它们而存在的契约/spec 测试套件中移除: + +- `SessionPersistence.has()` / `.delete()` 已移除:抽象声明、协调器的 `has`/`delete`/`deleteCore`,以及 `PersistenceBackend.deleteStored` 钩子均消失(jsonl 和 sqlite 都只是为了满足该钩子才实现 `deleteStored`,这些实现也一并移除)。后端属于[双后端](../architecture/2026-06-14-session-persistence.md)设计,其他方面不在范围内;删除它们为没有消费方的钩子所做的实现,是删除钩子的一部分,而非重新设计后端。 +- 所有文档和源码注释引用都已更新为保留下来的四方法、仅含 `list()` 的契约——不仅包括字面上的 `has(`/`delete(`/`deleteStored` 拼写,还包括 `{@link has}`/`{@link delete}` JSDoc 链接和“六个公共方法”的计数——涉及 seam 和后端 README、[docs/architecture.md](../../../../docs/architecture.md)、[会话持久化](../architecture/2026-06-14-session-persistence.md)与[写入协调器](../architecture/2026-06-18-shared-persistence-write-coordinator.md) Agent Note,以及协调器/后端 JSDoc。 + +## 曾考虑的替代方案 + +### 为什么不以「seam 应当完整」为由保留? + +「持久化 seam 理应提供 delete」这种直觉是真实的——但它恰恰是预发布阶段所警惕的投机性完整([AGENTS.md](../../../../AGENTS.md):为正确的基础优化,而非为你并不拥有的假想调用者优化)。`delete()` 是一个方法,等消费方真正需要时再加回来即可:一个删除旧会话的会话管理 UI 会需要它——到那时再加,基于该 UI 的真实需求来设计(软删除?级联?确认?),而非现在猜测。 + +在有活跃消费方的情况下重新添加一个 seam 方法,成本低且设计更优,因为消费方锚定了契约。在无人使用的情况下保留它,意味着每个实现(以及未来的每个后端)都必须实现和测试一个无实际作用的方法。 + +## 验证 + +`has`/`delete`/`deleteStored` 已从持久化 seam、实现和契约测试套件中移除,没有新增无用导出;剩余操作(`create`/`append`/`load`/`list`)未受影响,ACP `session/list` 和崩溃恢复行为完全一致;seam README 和 `docs/architecture.md` 仅列出存留的方法。 + +## 后果 + +- **`delete()` 是产品最终会需要的操作。** 确实如此,但「最终」正是关键。现在删除、将来基于真实消费方重新添加,严格优于发布一份猜测的契约。两个后端各自减少了一个 `deleteStored` 实现,这是在本次范围之外的包中的有限改动。 +- **低耦合。** 移除局限于持久化 seam + 实现 + 测试;没有跨包消费方引用被移除的方法,因此除文档外没有涟漪效应。 + +规模不大,但它将 seam 从「实现必须为无人提供什么」恢复为「恰好是消费方使用的东西」。 diff --git a/.agents/notes/implemented/simplification/2026-06-20-public-agent-stop-surface.i18n.yaml b/.agents/notes/implemented/simplification/2026-06-20-public-agent-stop-surface.i18n.yaml new file mode 100644 index 0000000000..7a5f7fdb48 --- /dev/null +++ b/.agents/notes/implemented/simplification/2026-06-20-public-agent-stop-surface.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-20-public-agent-stop-surface.md: 81a21de30bfbc25688069efbffb21647889b1bdb +2026-06-20-public-agent-stop-surface.zh.md: 1f5a9ea3c1c3dd6f598c258574a81e52e291f3b7 diff --git a/.agents/notes/implemented/simplification/2026-06-20-public-agent-stop-surface.md b/.agents/notes/implemented/simplification/2026-06-20-public-agent-stop-surface.md index 824efc804c..81a21de30b 100644 --- a/.agents/notes/implemented/simplification/2026-06-20-public-agent-stop-surface.md +++ b/.agents/notes/implemented/simplification/2026-06-20-public-agent-stop-surface.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-06-20-public-agent-stop-surface.zh.md) + > **Implementation note:** Only `abort()` was removed. `whenIdle()` remains because it is the public quiescence signal and safely handles waiter settlement and replacement-turn races; consumers should not reconstruct that behavior from status transitions. ## Problem diff --git a/.agents/notes/implemented/simplification/2026-06-20-public-agent-stop-surface.zh.md b/.agents/notes/implemented/simplification/2026-06-20-public-agent-stop-surface.zh.md new file mode 100644 index 0000000000..1f5a9ea3c1 --- /dev/null +++ b/.agents/notes/implemented/simplification/2026-06-20-public-agent-stop-surface.zh.md @@ -0,0 +1,39 @@ +# Agent Note: 保留单一公开停止原语 + +Status: implemented + +[English](2026-06-20-public-agent-stop-surface.md) | 中文 + +> **实现说明:** 仅移除了 `abort()`。`whenIdle()` 予以保留,因为它是公开的完全停稳信号,能安全处理等待者结算与替换轮次竞态;消费方不应从状态转换中自行重建该行为。 + +## 问题 + +公共 `Agent` handle 暴露了两种相互重叠的在途工作停止方式:仅针对步骤的 `abort()` 和感知队列的 `cancel()`。前者保留已排队输入,后者则清除已排队和 steering(中途引导)工作,并中止活动轮次。在生产中,ACP(Agent Client Protocol)对 `session/cancel` 使用 `cancel()`,生命周期拥有者则通过 `AgentHandle.dispose()` 拆除 agent(智能体)。没有生产调用方需要一个裸的、仅针对步骤的 abort。 + +行为差异确实存在,但已发布代码不需要较窄的操作。AgentLoop 改为为整个轮次拥有一个私有取消 holder。`cancel(cause?)` 携带类型化的 `user` 或 `parent` 原因,默认为 `user`,并丢弃待处理输入;释放仍是单独的生命周期中断。完整的归属与传播契约位于[显式轮次取消 Agent Note(agent 决策记录)](../architecture/2026-07-16-explicit-turn-cancellation.md)。 + +多余的公开接口使得循环不得不承载一个本质上属于内部拆卸的公开动词:`abort()` 必须被文档描述为有别于队列感知的取消,尽管 UI 取消几乎总是需要更广泛的操作。 + +## 决策 + +`cancel()` 是 `Agent` 上唯一的公共*停止*原语。生命周期拥有者使用 `AgentHandle.dispose()` 停止并注销 agent;非拥有者使用 `cancel()` 放弃当前和已排队工作。实现保留一个私有轮次取消 holder,但它不属于面向插件的 `Agent` 契约。 + +`whenIdle()` **保留**为公开的完全停稳观测原语(agent 从 `running` 状态稳定后 resolve,已处于 idle 时立即 resolve,dispose 后等待循环退出)。它不是停止动词;它是非所有者在不 dispose agent 的前提下观测停止*完成*的方式。它的活跃消费方是 ACP 和通过此公开 seam 等待结算的 agent 测试(`packages/ui/acp/tests`、`packages/core/agent-loop/tests`);生产环境的 ACP 桥接层拥有其 agent 并通过 `AgentHandle.dispose()` 销毁它们,因此 `packages/ui/acp/src` 本身没有 `whenIdle()` 调用。 + +公共 `abort()` 已不存在,disposer 仍为异步并等待循环停止。测试通过公共类型化原因和显式 signal seam 验证取消,而不会伸入 holder 内部。 + +## 曾考虑的替代方案 + +**同时移除 `whenIdle()`**:最初提案的形态,在对照代码验证前提后被推翻(上方的实现说明记录了完整过程):它是承重的完全停稳原语,迫使消费方手动观测 `running`→`idle` 转换正是防御性模式所警告的脆弱路径。 + +## 验证 + +`Agent` 不再暴露公开的 `abort()`,而 `cancel()`、`whenIdle()` 和 `steer()` 保留;ACP 取消调用 `cancel()`;拆卸通过 handle disposal 等待完全停稳,`whenIdle()` 在完全停稳时为非所有者观测者 resolve;测试套件覆盖取消和 disposal 作为两条受支持的停止路径。 + +## 后果 + +未来的插件无法通过公开接口仅中止当前模型/工具步骤而保留队列中的提示词。如果该用例变为现实需求,它应当带着一个具名消费方和更窄的契约回归。目前它是将私有循环机制保持公开的潜在泛化。 + +## 相关 + +本 Agent Note 只移除冗余的停止动词。轮次中途 steering 仍是一条有意保留的消息路径;完全停稳观察仍通过 `whenIdle()` 完成。最终公共表面包括 `send()`、`steer()`、`inject()`、`cancel()`、`whenIdle()`、status、options、会话和 identity。 diff --git a/.agents/notes/implemented/simplification/2026-06-20-remove-agent-boundary-mirror-events.i18n.yaml b/.agents/notes/implemented/simplification/2026-06-20-remove-agent-boundary-mirror-events.i18n.yaml new file mode 100644 index 0000000000..9e90a3a343 --- /dev/null +++ b/.agents/notes/implemented/simplification/2026-06-20-remove-agent-boundary-mirror-events.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-20-remove-agent-boundary-mirror-events.md: 8c5bb74f2347fe0269cbb9c6504137de761ab919 +2026-06-20-remove-agent-boundary-mirror-events.zh.md: 1bb166b7f4453b4f0605e2b1b9120bc5a05266b0 diff --git a/.agents/notes/implemented/simplification/2026-06-20-remove-agent-boundary-mirror-events.md b/.agents/notes/implemented/simplification/2026-06-20-remove-agent-boundary-mirror-events.md index 910eb46e92..8c5bb74f23 100644 --- a/.agents/notes/implemented/simplification/2026-06-20-remove-agent-boundary-mirror-events.md +++ b/.agents/notes/implemented/simplification/2026-06-20-remove-agent-boundary-mirror-events.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-06-20-remove-agent-boundary-mirror-events.zh.md) + <!-- Shipped in AMENDED, narrowed form: the four turn/step BOUNDARY mirrors are removed; `agent/steering` and `agent/stream-chunk` were RETAINED here (they are not durable-boundary mirrors — see "Scope: what is and isn't removed"). diff --git a/.agents/notes/implemented/simplification/2026-06-20-remove-agent-boundary-mirror-events.zh.md b/.agents/notes/implemented/simplification/2026-06-20-remove-agent-boundary-mirror-events.zh.md new file mode 100644 index 0000000000..1bb166b7f4 --- /dev/null +++ b/.agents/notes/implemented/simplification/2026-06-20-remove-agent-boundary-mirror-events.zh.md @@ -0,0 +1,47 @@ +# Agent Note: 停止将持久化边界镜像为 agent 事件 + +Status: implemented + +[English](2026-06-20-remove-agent-boundary-mirror-events.md) | 中文 + +<!-- 以修订、收窄后的形式落地: + 移除了四个轮次/步骤边界镜像;此处保留了 `agent/steering` 和 + `agent/stream-chunk`(它们不是持久边界镜像——参见 + “范围:移除什么、不移除什么”)。原始提案将 `agent/steering` 与其他项一并 + 移除;把它排除在外,使本 Agent Note 的范围保持在边界上。后来每个保留事件 + 都由各自的决策移除——参见 + [停止将 token 流镜像为 agent 事件](2026-07-02-remove-stream-chunk-mirror.md) + 和[移除 `agent/steering` 镜像 emit](2026-07-04-remove-agent-steering-mirror.md)。 --> + +## 问题 + +循环在 `SessionEvent` 中记录规范 transcript(文本记录),同时还发出一组并行的实时 `agent/*` 边界镜像事件:`agent/turn-start`、`agent/turn-end`、`agent/step-start` 和 `agent/step-end`。这些镜像迫使消费方在同一持久事实的两个真源之间做选择。ACP(Agent Client Protocol)已经为面向编辑器的 transcript 选择会话日志,因为它是唯一持久、可重放的记录;消费实时镜像需要把它的时序与日志中已经存储的边界进行调和。stdio UI 是唯一仍从镜像事件渲染轮次边界的生产消费方;它已经从 `session/event` 渲染工具调用和结果。 + +这种重复并非零成本。每次生命周期变更都需要同时更新会话事件、镜像事件、文档、不变式、测试和快照预期。重复的边界事件还使失败排序变得微妙:一个轮次可能在实时 `agent/turn-end` 监听器运行之前就已被持久化关闭,因此边界之后的监听器失败在日志中已没有合法位置可以插入,只能带外上报。 + +## 决策 + +将 `session/event` 作为唯一的实时边界/transcript(文本记录)流。需要渲染轮次、工具调用、工具结果、助手消息和持久化边界的消费方统一订阅 `session/event`,从持久化层使用的同一套事件词汇中派生 UI。 + +四个持久边界镜像——`agent/turn-start`、`agent/turn-end`、`agent/step-start`、`agent/step-end`——已从 agent(智能体)事件分类中移除。希望在边界处取得 agent handle 的 UI 会保留来自 `agent/created`/`agent/disposed` 的实时目标对象,并直接比较其会话;`dsh-ui-stdio` 据此为应用拥有的 agent 标记 `[main turn N]` 头部,其他会话则渲染其持久 id。规范记录仍是事件溯源会话日志。 + +步骤镜像(完全没有消费方)最先在[事件域语义 Agent Note(agent 决策记录)](../architecture/2026-06-30-event-domain-semantics.md) 中移除;该 Agent Note 当时以 stdio UI 需要在轮次边界取得 `Agent` handle 为由,保留了轮次镜像。本 Agent Note 完成余下工作:`dsh-ui-stdio` 是可随时丢弃的测试 REPL,其渲染可以自由变化,因此“ui-stdio 需要它”并不是保留镜像的理由——它读取 `session/event`,只保留自己的实时目标对象。 + +## 范围:移除什么、不移除什么 + +已移除(持久边界镜像——每项都以会话日志为权威):`agent/turn-start`、`agent/turn-end`、`agent/step-start`、`agent/step-end`。 + +保留——不是持久边界镜像,因此不在本决策范围内: + +- `agent/steering`——不是边界,因此不在本决策范围内(原始提案将其一并移除;在此会造成范围蔓延)。它镜像持久的 `steering/message` 控制记录,而非边界,后来由自己的后续决策移除:[移除 `agent/steering` 镜像 emit](2026-07-04-remove-agent-steering-mirror.md)。 +- `agent/stream-chunk`——实时 token 流。不在本决策范围内(它镜像持久的 `assistant/chunk`,而非边界),后来由自己的后续决策移除:[停止将 token 流镜像为 agent 事件](2026-07-02-remove-stream-chunk-mirror.md)。 +- `agent/created`、`agent/disposed`、`agent/status`、`agent/error`、`agent/queued`——不属于 transcript 数据的生命周期/控制事件。尤其是 `agent/queued`,它是在任何持久事件存在之前触发的 inbox 确认(取消的排队工作可能永远不会进入日志),所以有意只保留为实时事件。 + +## 曾考虑的替代方案 + +- **将 `agent/steering` 一并移除**——原始提案的形状;作为范围蔓延被排除:它镜像持久的 `steering/message` 控制记录,而非边界,后来由[自己的决策](2026-07-04-remove-agent-steering-mirror.md)移除(`agent/stream-chunk` 也由[流分片镜像 Agent Note](2026-07-02-remove-stream-chunk-mirror.md)移除)。 +- **为 stdio UI 保留轮次镜像**——[事件域语义 Agent Note](../architecture/2026-06-30-event-domain-semantics.md) 的原始立场;在此否决,因为 `dsh-ui-stdio` 是可随时丢弃的测试 REPL,而非承载关键约束的消费方,并且它改为根据 `session/event` 加自己的实时目标对象渲染边界。 + +## 后果 + +插件不能再从便捷的 `Agent` 优先事件观察轮次/步骤边界。它需要订阅 `session/event`;如果需要实时对象,则通过 `ctx.agents` 解析共享 id,或保留自己已经拥有的对象。这是可以接受的取舍:边界消费方不应依赖可能与持久日志发生漂移的第二条事件 feed。 diff --git a/.agents/notes/implemented/simplification/2026-06-20-unify-agent-and-session-id.i18n.yaml b/.agents/notes/implemented/simplification/2026-06-20-unify-agent-and-session-id.i18n.yaml new file mode 100644 index 0000000000..291dd7d009 --- /dev/null +++ b/.agents/notes/implemented/simplification/2026-06-20-unify-agent-and-session-id.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-20-unify-agent-and-session-id.md: c55152f4f13fe0acb530503e84f465799007cff7 +2026-06-20-unify-agent-and-session-id.zh.md: 1fa2fe1fd64478bfe17c590e45abd0cf8281cbe4 diff --git a/.agents/notes/implemented/simplification/2026-06-20-unify-agent-and-session-id.md b/.agents/notes/implemented/simplification/2026-06-20-unify-agent-and-session-id.md index a8a2c375b5..c55152f4f1 100644 --- a/.agents/notes/implemented/simplification/2026-06-20-unify-agent-and-session-id.md +++ b/.agents/notes/implemented/simplification/2026-06-20-unify-agent-and-session-id.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-06-20-unify-agent-and-session-id.zh.md) + ## Problem A live agent/session pair needs one identity for registry routing, event sourcing, and persistence. Giving the factory independent `agentId` and `sessionId` inputs would permit pairings no production path can use, while forcing every consumer to choose or translate between two names for the same lifecycle. diff --git a/.agents/notes/implemented/simplification/2026-06-20-unify-agent-and-session-id.zh.md b/.agents/notes/implemented/simplification/2026-06-20-unify-agent-and-session-id.zh.md new file mode 100644 index 0000000000..1fa2fe1fd6 --- /dev/null +++ b/.agents/notes/implemented/simplification/2026-06-20-unify-agent-and-session-id.zh.md @@ -0,0 +1,40 @@ +# Agent Note: 统一 agent id 与会话 id + +Status: implemented + +[English](2026-06-20-unify-agent-and-session-id.md) | 中文 + +## 问题 + +一个实时 agent(智能体)/会话对需要使用同一 identity 完成注册表路由、事件溯源和持久化。让 factory 接受相互独立的 `agentId` 和 `sessionId` 输入,会允许任何生产路径都无法使用的配对,同时迫使每个消费方为同一生命周期在两个名称之间选择或转换。 + +ACP(Agent Client Protocol)对两种 identity 使用相同值。Stdio 和钩子也在会话事件流上工作,并且直接需要对应的实时 agent;没有生产路径会把一个实时 agent 对象重新附着到多个会话,或通过多个 agent id 驱动一个会话。 + +[agent 范围运行时](../architecture/2026-07-12-agent-scope-runtime-design.md)使用同一个 `AgentCreationTransaction` 执行创建和恢复,agent/会话条目共享相同的最终条目冲突规则。第二个 identity 并不代表单独的存活性、回滚或完全停稳;它只会围绕同一事务增加 API 与转换状态。 + +会话 identity 同样只有一个归属,即 `Session.header.id`;`Session.id` 是派生访问器,而非需要重复验证的独立状态。 + +## 决策 + +agent 的注册表 id 等于其会话 id。`CreateAgentOptions` 接受一个 `sessionId`,同时用于两个最终注册表条目;恢复时以 `resumeSessionId` 注册 agent;进程内 subagent 创建使用子会话 id;`Session.id` 则派生自 `header.id`。远程 ACP 运行没有本地 agent/会话对:它保留一个由父项铸造的生命周期 id,而子服务器线协议内的会话 id 仅用于 ACP 调用。现有创建事务、最终条目冲突检查和精确条目分离语义保持不变;唯一职责是在本地 id 之间转换的 map 与字段已经消失。 + +配置驱动路径保留 `agents[].id` 作为稳定配置标签,而非实时路由 identity。普通的全新启动会铸造组合 id `${label}-session-${randomUUID()}`,使持久重启不会冲突。耦合应用可以预先铸造并传入精确的 `sessionId`:首次使用时创建它,而当持久化服务已经存在时,AgentLoop 重新挂载会在同一 identity 下恢复已物化历史。`resumeSessionId` 则要求已有的持久化 identity。两个精确 id 输入互斥。Stdio 使用“恢复或创建”形式,使配置创建的 agent 和 UI 在循环重载之间共享一个不透明 identity,而不是根据前缀猜测。日志可以使用稳定标签,而所有实时与持久查找都使用同一个 `SessionId`。 + +`agent/created` 和 `agent/disposed` 保留。它们是成对的发布生命周期事件,而非 identity 别名;以后若发现没有消费方并要移除,必须先重新搜索,再提出独立提案。 + +## 曾考虑的替代方案 + +**保持路由与日志 identity 分离。** 稳定的配置标签加全新的持久对话确实有用,但不需要两个实时 identity:标签可以继续作为配置/显示元数据,而每次运行的组合 `SessionId` 负责路由和持久化。保留两个 id 会让转换 map 持续存在,允许不可能的配对,却不会增加生命周期功能。 + +## 验证 + +- Agent 创建/恢复和 subagent 创建只携带一个 identity,`Session` 也只在一个位置存储它。 +- 创建事务继续覆盖最终条目冲突、精确条目分离、回滚和完全停稳,无需 identity 特有的生命周期状态。 +- ACP、stdio、钩子、bash 归属、持久化和 lineage 直接使用共享 `SessionId`。ACP subagent 后端在父命名空间中铸造其生命周期 id,因为子服务器返回的会话 id 仅在服务器本地有效;ACP bridge 根据正向会话 map 验证精确的 `Agent` 归属;JSON-RPC 只转发生命周期事件中由服务快照保存的 `local` 标记为 true 的事件,从带范围的事件 carrier 取得委托父项,并且不保留子 identity 或 lineage cache。 +- 配置驱动的恢复还是创建策略是显式的,并在持久化重启场景下得到覆盖。 +- 生产监听器搜索确认保留 `agent/created`/`agent/disposed` 及其发布语义。 +- 类型检查、覆盖率、快照、doc-sync、module-graph 校验、构建与 hygiene 全部通过。 + +## 后果 + +这排除了潜在的多会话 actor 和会话交接设计,并使由客户端选择、已持久化的会话 identity 成为注册表 identity。如果独立路由 identity 成为真实需求,就需要显式的生命周期设计,而不是由调用方提供一对不受约束的值。 diff --git a/.agents/notes/implemented/simplification/2026-06-26-fsspec-style-fs-seam.i18n.yaml b/.agents/notes/implemented/simplification/2026-06-26-fsspec-style-fs-seam.i18n.yaml new file mode 100644 index 0000000000..6e428fa348 --- /dev/null +++ b/.agents/notes/implemented/simplification/2026-06-26-fsspec-style-fs-seam.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-26-fsspec-style-fs-seam.md: d496f273e2635624e0ab8e70e06c8729563c5466 +2026-06-26-fsspec-style-fs-seam.zh.md: 18e4be5177f593253dc100a864b6c741904a90b2 diff --git a/.agents/notes/implemented/simplification/2026-06-26-fsspec-style-fs-seam.md b/.agents/notes/implemented/simplification/2026-06-26-fsspec-style-fs-seam.md index 3753fb803a..d496f273e2 100644 --- a/.agents/notes/implemented/simplification/2026-06-26-fsspec-style-fs-seam.md +++ b/.agents/notes/implemented/simplification/2026-06-26-fsspec-style-fs-seam.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-06-26-fsspec-style-fs-seam.zh.md) + ## Problem The filesystem capability from [filesystem-capability-seam](../architecture/2026-06-17-filesystem-capability-seam.md) currently makes one abstract `FileSystem` service own two different jobs: diff --git a/.agents/notes/implemented/simplification/2026-06-26-fsspec-style-fs-seam.zh.md b/.agents/notes/implemented/simplification/2026-06-26-fsspec-style-fs-seam.zh.md new file mode 100644 index 0000000000..18e4be5177 --- /dev/null +++ b/.agents/notes/implemented/simplification/2026-06-26-fsspec-style-fs-seam.zh.md @@ -0,0 +1,130 @@ +# Agent Note: 拆分文件系统 seam——提供方文本变更操作与 `dsh-fs-policy` 插件 + +Status: implemented + +[English](2026-06-26-fsspec-style-fs-seam.md) | 中文 + +## 问题 + +[文件系统能力 seam](../architecture/2026-06-17-filesystem-capability-seam.md)中的文件系统能力目前让一个抽象 `FileSystem` 服务同时负责两项不同工作: + +1. **提供方操作**——解析目标、stat/版本元数据、文本读取/流式读取、原子写入,以及受保护的字面编辑。 +2. **面向 agent(智能体)的策略**——行窗口、字面编辑语义,以及读后写/编辑的观测状态。 + +这导致每个未来的后端都要重新实现面向模型的读取语义和观测策略。`readPage` 返回带行号的行和视图元数据;基础服务按 owner 存储文件状态,并区分 `full` 与 `partial` 读取。这些是有用的策略,但它们不是文件系统提供方的原语。字面文本变更则不同:版本守卫、字面匹配、歧义检测与原子重写必须留在提供方的变更边界内,但当前的 `applyEdit` 命名及其周围的 seam 将这一提供方操作绑定到了旧的读后编辑策略形状上。 + +这还造成了一个真实的用户体验死胡同:窗口化读取记录 `view: partial`,而 partial 视图无法授权 `edit`。一个模型读取了大文件的第 100-150 行,如果想编辑第 120 行,就必须先获取一次 `full` 读取,而对于超过读取上限的文件这可能做不到。字面编辑实际上只需要新鲜度:被匹配的字节仍然来自模型所读取的那个版本即可。 + +旧 Agent Note(agent 决策记录)已经推迟了独立的 `@deepseek-ai/dsh-fs-policy` 包。本 Agent Note 构建该层,使 `ctx.fs` 保持接近 fsspec 风格的存储原语(`info`/`cat`/`open`),但不把它变成完整的 fsspec。 + +## 决策 + +将栈拆为四层: + +```text +tool dsh-tool-fs model-facing schemas + read windowing + text rendering; the EXECUTOR (reads/writes/edits via ctx.fs, dispatches the fs/* events) +policy dsh-fs-policy observed-state + read-before-edit + write/edit freshness, contributed through the fs/* event gate (no service) +provider seam dsh-fs ctx.fs: text IO + atomic mutation primitives (optional version guard) +provider dsh-fs-local local implementation of ctx.fs +``` + +`dsh-tool-fs` 保持相同的面向模型的 `read`/`write`/`edit` schema。它是执行器:注入 `fs`(不是策略服务)并直接访问 `ctx.fs`,拥有读取窗口化逻辑,并分发 `fs/*` 事件以便 `dsh-fs-policy` 进行门控和记录。 + +本 Agent Note 决定了四层拆分、提供方契约和新鲜度策略。随后,[事件门禁 Agent Note](../architecture/2026-06-26-file-context-as-event-gate.md) 细化了工具↔策略耦合:`dsh-fs-policy` 是通过 `fs/*` 事件参与的门禁插件,而非 `ctx.fileContext` 方法服务,因此工具不会在方法层与其耦合;读取窗口和 fs I/O 位于 `dsh-tool-fs`。本文描述已经落地的事件门禁形状;提供方的版本守卫可选(省略即无条件裸提供方)。 + +## 提供方契约 + +`@deepseek-ai/dsh-fs` 收缩为提供方文本 IO 加受保护的文本变更: + +```ts ignore-check +abstract resolve(path: string, opts?: { cwd?: string; signal?: AbortSignal }): Promise<FsTarget> +abstract stat(target: FsTarget, signal?: AbortSignal): Promise<FsInfo | undefined> +abstract readText(target: FsTarget, signal?: AbortSignal): Promise<string> +abstract streamText(target: FsTarget, signal?: AbortSignal): Promise<AsyncIterable<string>> +abstract writeText(target: FsTarget, content: string, expected: FsWriteIntent, signal?: AbortSignal): Promise<FsWriteOutcome> +abstract editText(target: FsTarget, edit: FsEditRequest, expected: { version: FsVersion }, signal?: AbortSignal): Promise<FsEditOutcome> + +interface FsInfo { + version: FsVersion + type: 'file' | 'directory' | 'other' + size?: number +} + +type FsWriteIntent = + | { kind: 'createIfAbsent' } + | { kind: 'replaceIfVersion'; version: FsVersion } +``` + +`stat` 返回元数据而非内容。`version` 是新鲜度令牌;`type` 让执行器在读取前拒绝目录/特殊文件;`size` 让 `read` 工具无需通过失败探测即可选择 `readText` 还是 `streamText`。`undefined` 表示目标不存在。 + +`readText` 读取整个常规文本文件。`streamText` 以相同的文本语义流式读取大文件。两个提供方原语负责常规文件检查、UTF-8 解码、二进制/NUL 拒绝以及 `FS_NOT_TEXT`;策略层从不处理原始字节,也不重新实现跨分片解码。`readText` 是小文件/直接全文件原语,而面向模型的大文件读取使用 `streamText`。 + +`writeText` 是原子的临时文件 + rename,带有显式的写入期望。`createIfAbsent` 创建不存在的目标,对已存在的目标以 `FS_NOT_OBSERVED` 拒绝;这是 owner 没有先前读取时使用的路径。`replaceIfVersion` 仅在目标以观测到的版本存在时替换;目标不存在或版本不匹配时抛出 `FS_STALE_VERSION`。 + +`editText` 是提供方级别的受保护文本变更。启用守卫时,它首先验证目标仍以 `expected.version` 存在,然后读取当前文本、应用字面替换并原子写入。陈旧检查必须在字面匹配之前发生,这样基于旧读取的编辑会报告 `FS_STALE_VERSION`,而不是对更新内容进行匹配后报告 `FS_EDIT_NOT_FOUND` 或 `FS_AMBIGUOUS_EDIT`。将此原语保留在提供方 seam 上,保持了后端本地锁定的能力,也让未来的远程后端能够实现原生的 compare-and-edit,而无需策略层拉取整个文件。 + +这是一个*文本存储* seam,刻意比字节级 fsspec(`cat`/`open` 返回原始字节)高半个层次。UTF-8 解码、二进制/NUL 拒绝、受保护的全文件写入和受保护的字面文本编辑都在提供方内完成,因此策略层从不接触原始字节、不重新实现跨分片解码、也不将陈旧检查与变更临界区分离。面向模型的概念仍然不下沉到提供方:行窗口、带行号的行、渲染的页脚、观测状态存储都不会泄漏下去。 + +从 `dsh-fs` 删除:`readPage`、`FsExpectation`、`FsView`、`FsStateSource`、`FsReadRequest`、`FsTextLine`、行/窗口常量、`formatReadBody` 和 observed-state `WeakMap`。`applyEdit` 由更窄的提供方原语 `editText` 取代,其契约是带版本守卫的字面文本变更,而非策略层读取授权。`FS_PARTIAL_OBSERVATION` code 也从 `FsErrorCode` 分类中移除:新鲜度授权没有部分/完整之分,因此没有任何路径会抛出它。`FsTargetKey` 和 `FsVersion` 按现有[品牌化 id Agent Note](../architecture/2026-06-20-branded-ids.md) 成为品牌化不透明 id。 + +## 策略契约 + +`@deepseek-ai/dsh-fs-policy` 是插件,而非服务:它不注册任何 `ctx.*` 键,也不注入任何内容。它拥有不应位于 `FileSystem` 提供方基类上的写入/编辑新鲜度策略和 observed state(否则沙箱/远程后端会继承不该由其承载的面向模型观察策略)。它通过执行器分派的 `fs/*` 事件门禁贡献该策略。(本 Agent Note 最初提议带有 `read`/`write`/`edit` 方法的具体 `ctx.fileContext` 服务;[事件门禁 Agent Note](../architecture/2026-06-26-file-context-as-event-gate.md) 将其细化为本文所述插件,使工具永远不会在方法层与策略耦合。) + +观测状态以 `WeakMap<owner, Map<targetKey, FsVersion>>` 的形式存放于此。当且仅当 owner 读取、写入或编辑过该目标时,条目才存在(每次成功都会发出 `fs/observed`),因此条目的存在*本身就是*先前观测的记录——没有单独的 `hasRead` 标志。owner 从不透明的事件 actor(`{ agent?: { session? } }`)结构化派生,该形状定义在 `dsh-fs-policy` 中而非 `dsh-fs` 中。 + +该插件决定三个 `fs/*` 事件: + +- `fs/write-intent`——无先前观测 ⇒ `{ kind: 'createIfAbsent' }`(只有新文件可以盲创建);有先前观测 ⇒ `{ kind: 'replaceIfVersion', version: vObserved }`(已有文件仅在自观测以来未变时才替换)。单槽决策;不调用 `next()`。 +- `fs/edit-intent`——要求 owner 有先前观测(否则 `FS_NOT_OBSERVED`);返回 `{ version: vObserved }` 作为 CAS 基础。它不实现字面替换——它授权并提供版本,提供方的变更临界区负责应用守卫,因此基于同一观测版本的并发编辑仍然是一赢一陈旧。 +- `fs/observed`——在成功的读取/写入/编辑后,为该 owner+target 记录 `{ version }`。同步、仅副作用的 `WeakMap.set`。 + +该插件不做任何文件系统 I/O:「你是否观测过此文件?」是一次 `WeakMap` 查找,而「你读取的版本是否仍然是当前版本?」在 `ctx.fs.editText`/`writeText` 内部、与执行变更相同的原子锁中决定——插件只提供 `vObserved` 作为基础。 + +## 工具契约 + +`dsh-tool-fs` 保持相同的 schema 和提示词表面。`read` 仍然暴露 `file_path`、`offset` 和 `limit`;`write` 和 `edit` 不变。它是执行器:验证模型参数,通过 `ctx.fs` 直接读取/写入/编辑,拥有行窗口化和结果渲染(`N: text`、页脚、`<path>/<content>` 信封),并分发 `fs/*` 事件。 + +每个变更操作先分发其 intent waterfall(瀑布式事件),带有 `undefined` 裸提供方默认值,然后调用 `ctx.fs`,再发出 `fs/observed`。例如 `write` 执行 `ctx.waterfall('fs/write-intent', target, exec, () => undefined)` → `ctx.fs.writeText(target, content, intent)` → `ctx.emit('fs/observed', …)`。`read` 先 stat 一次,然后读取/流式读取,构建窗口,最后发出 `fs/observed`。将 `exec` 作为 actor 传递,让 `dsh-fs-policy` 无需工具深入策略即可派生 owner。 + +由于策略通过带有 `undefined` 默认值的事件贡献,`dsh-tool-fs` 不与 `dsh-fs-policy` 产生方法耦合:在插件缺席时,每个 intent waterfall 都落到 `undefined`(无条件裸提供方写入/编辑),`fs/observed` 没有监听器。加载插件后即可叠加读后写/编辑策略。 + +## 并发边界 + +进程内更新是安全的:本地后端保持既有的按目标变更锁,因此版本检查-然后-rename 是串行化的,失败的更新会看到 `FS_STALE_VERSION`。 + +进程内创建由同一个按目标变更锁保护:两个调用者以 `createIfAbsent` 竞争时串行化,一个创建成功,另一个看到目标已存在并收到 `FS_NOT_OBSERVED`。跨进程创建仅为尽力而为;本地的 stat-then-rename 守卫无法在所有未来后端上提供可移植的排他创建保证。 + +跨进程写入是尽力而为的新鲜度加原子替换:`mtime:size` 通常能捕获编辑器保存,但同一 tick 相同大小的写入可能遗漏;原子的 temp+rename 防止文件撕裂但不能防止所有丢失更新。 + +## 取代 + +本 Agent Note 推翻[文件系统能力 seam](../architecture/2026-06-17-filesystem-capability-seam.md)中的两项决策,并收窄第三项: + +- 读后写/编辑策略从 `ctx.fs` 移出,进入 `dsh-fs-policy` 插件(通过 `fs/*` 事件门控)。 +- 文本读取不再返回后端编号的行记录或 `full`/`partial` 视图;授权基于版本新鲜度,因此窗口化读取在文件未变时即可授权编辑。 +- 字面编辑不再位于旧的 `applyEdit` API 之后(该 API 混合了后端变更与 seam 拥有的观测策略)。它作为 `editText` 保留为提供方原语,因为版本守卫 + 字面匹配 + 原子重写必须留在提供方的变更临界区内。 + +保留的内容:接口/实现/消费方纪律、消费方不导入后端规则、后端定义的 target/version/display 元数据、原子本地写入,以及共享的 `FsError` 分类体系。 + +## 验证 + +`dsh-fs` 精确暴露 `resolve`/`stat`/`readText`/`streamText`/`writeText`/`editText`(`stat` 返回 `FsInfo | undefined`,`writeText` 接受 `FsWriteIntent`),已删除的类型/原语不再存在;`dsh-fs-local` 不包含行、视图或 `formatReadBody` 逻辑;面向模型的 schema 保持逐字节不变。测试固定了以下行为:窗口化读取授权对未变文件的后续编辑;基于陈旧读取的编辑在尝试字面匹配之前报告 `FS_STALE_VERSION`;版本 CAS 行为得以保留;观测契约成立(`read` 工具的读取记录观测状态;直接 `ctx.fs` 读取不记录);`dsh-fs-policy` 具有 HMR(热模块替换)/dispose(资源释放)覆盖率。 + +## 后续扩展 + +后来,[为文件系统 seam 添加直接目录列表](../architecture/2026-07-03-filesystem-directory-listing-seam.md)进一步扩展了该 seam。该后续工作单独跟踪,使本 Agent Note 的验收标准继续描述最初落地的 fsspec 风格改造。 + +## 曾考虑的替代方案 + +- **字节级 fsspec(`cat`/`open` 返回原始字节)**:否决。该 seam 刻意定位为文本存储,比字节级高半个层次,这样 UTF-8 解码、二进制/NUL 拒绝和受保护的文本变更只在提供方实现一次,策略层从不接触原始字节,也不将陈旧检查与变更临界区分离。 +- **具体的 `ctx.fileContext` 方法服务**——本 Agent Note 最初的策略形状;[事件门禁 Agent Note](../architecture/2026-06-26-file-context-as-event-gate.md) 将其重做为门禁插件,使工具永远不会在方法层与策略耦合。 +- **在提供方保留 `readPage` 和 `full`/`partial` 视图授权**:「取代」一节所逆转的重构前形态。视图完整性不是编辑安全所需的,版本新鲜度才是;而视图规则使超过读取上限的大文件无法编辑。 + +## 后果 + +- 新增第四个 fs 包和一个新的插件层。这是有意为之:它是此前推迟的策略层,而非第二个抽象后端 seam。 +- 直接使用 `ctx.fs` 会绕过策略:直接 `ctx.fs.readText` 不发出 `fs/observed`,因此在默认策略下,后续 `edit` 会以 `FS_NOT_OBSERVED` 拒绝,直到通过 `read` 工具读取该文件。这一失败是显式且有文档记录的。 +- 大文件行窗口化从后端移至 `dsh-tool-fs` 中的 `read` 工具;文本解码和二进制拒绝留在 `ctx.fs.streamText` 中,因此这只是窗口化逻辑的迁移,而非第二套文本 IO 实现。 +- 将 `editText` 保留在提供方 seam 上意味着每个后端都必须实现字面替换契约。这是有意为之:该操作不是纯存储,但陈旧守卫 + 字面匹配 + 原子重写是必须保持在一起的单元,以确保正确的错误归因和并发行为。该契约应保持窄且仅限文本,以便未来后端可以原生实现或通过全文件重写实现。 +- 新鲜度允许在窗口化读取后进行全文件 `write`。这比旧的视图检查更弱,但避免了大文件无法编辑的问题;提示词引导仍然不鼓励盲目的全文件替换。 diff --git a/.agents/notes/implemented/simplification/2026-07-02-remove-stream-chunk-mirror.i18n.yaml b/.agents/notes/implemented/simplification/2026-07-02-remove-stream-chunk-mirror.i18n.yaml new file mode 100644 index 0000000000..b6b4adcc16 --- /dev/null +++ b/.agents/notes/implemented/simplification/2026-07-02-remove-stream-chunk-mirror.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-02-remove-stream-chunk-mirror.md: 5dd816940a4b2c2b63980e01f1bd4e0aac53a3e2 +2026-07-02-remove-stream-chunk-mirror.zh.md: ca65a3c2ad46d14835416c14d0087ef542de03bb diff --git a/.agents/notes/implemented/simplification/2026-07-02-remove-stream-chunk-mirror.md b/.agents/notes/implemented/simplification/2026-07-02-remove-stream-chunk-mirror.md index c79202b95a..5dd816940a 100644 --- a/.agents/notes/implemented/simplification/2026-07-02-remove-stream-chunk-mirror.md +++ b/.agents/notes/implemented/simplification/2026-07-02-remove-stream-chunk-mirror.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-07-02-remove-stream-chunk-mirror.zh.md) + ## Problem The loop records every model token delta as a durable `assistant/chunk` session event AND emitted a parallel live `agent/stream-chunk` Cordis event carrying the identical data. In `packages/core/agent-loop/src/loop.ts` the two sat one line apart: diff --git a/.agents/notes/implemented/simplification/2026-07-02-remove-stream-chunk-mirror.zh.md b/.agents/notes/implemented/simplification/2026-07-02-remove-stream-chunk-mirror.zh.md new file mode 100644 index 0000000000..ca65a3c2ad --- /dev/null +++ b/.agents/notes/implemented/simplification/2026-07-02-remove-stream-chunk-mirror.zh.md @@ -0,0 +1,47 @@ +# Agent Note: 停止将 token 流镜像为 agent 事件 + +Status: implemented + +[English](2026-07-02-remove-stream-chunk-mirror.md) | 中文 + +## 问题 + +agent loop(智能体循环)将模型的每个 token delta 同时记录为持久的 `assistant/chunk` 会话事件,并发射一个携带相同数据的并行实时 `agent/stream-chunk` Cordis 事件。在 `packages/core/agent-loop/src/loop.ts` 中,二者仅相隔一行: + +```ts ignore-check +const chunkEvent = session.append('assistant/chunk', { turn, step, chunk }) +chunkSeqs.push(chunkEvent.seq) +ctx.emit('agent/stream-chunk', agent, turn, step, chunk) // ← the mirror +``` + +- 持久事件:`assistant/chunk: { turn, step, chunk }`。 +- 实时发射:`agent/stream-chunk(agent, turn, step, chunk)`——相同的 `StreamChunk`,相同的 `turn`/`step`。 + +实时发射相比会话事件唯一多出的东西是实时的 `Agent` 句柄,而唯一的消费方直接丢弃了它(其处理函数签名为 `(_agent, _turn, _step, chunk)`)。 + +这与[移除边界镜像](2026-06-20-remove-agent-boundary-mirror-events.md)为轮次/步骤边界消除的重复相同:消费方面对同一持久事实的两个真源,每次变更都必须同时触及两者。该 Agent Note(agent 决策记录)没有把分片流一并纳入,而是推迟处理(“`assistant/chunk` 持久化仍承载关键约束,所以以后可以将分片流作为镜像评估,但那是一项独立决策”)。本 Agent Note 就是那项独立决策。 + +推迟所依赖的前提已经明确:分片持久化是权威的,且将保留。停止持久化分片、仅保留瞬态实时流事件的提案已被[否决](../../rejected/simplification/2026-06-20-assembled-assistant-messages-only.md)——高保真回放、部分失败的流以及快照回放都依赖持久化的 `assistant/chunk` 序列。因此 `session/event` 上的 `assistant/chunk` 是持久的、承重的 token 流,而 `agent/stream-chunk` 是它的纯冗余镜像。 + +## 决策 + +从 agent 事件分类体系中移除 `agent/stream-chunk`。token 流通过 `session/event` 以 `assistant/chunk` 的形式读取——持久化与回放已经使用的正是同一个序列。`session/event` 是唯一的实时 transcript(文本记录)流(assistant 分片、轮次/步骤边界、工具活动、todo)。 + +**消费方。** 唯一重要的生产消费方——ACP(Agent Client Protocol)桥接(`dsh-acp`,面向编辑器的真实流式输出接口)——已经从 `session/event` 渲染 `assistant/chunk`,从未使用 `agent/stream-chunk`,因此不受影响。stdio UI(`dsh-ui-stdio`,一个一次性的测试 REPL)是唯一的实时消费方;它在边界迁移时已经有了 `session/event` 监听器,因此其分片渲染被折叠进该监听器作为 `assistant/chunk` 分支。合并为一个监听器还消除了一个潜在隐患:`inReasoning` dim-SGR 标志此前在两个独立监听器(`agent/stream-chunk` 和 `session/event`)之间共享,分片与边界在该标志上竞争时没有确定的顺序;单一监听器按追加顺序处理,使交错变为确定性的。 + +## 范围 + +移除:`agent/stream-chunk`。 + +未触及: +- `assistant/chunk`(持久会话事件)——权威 token 流,原样保留。本 Agent Note 移除的是实时镜像,而非持久化(移除持久化的提案已单独遭到拒绝——见上文)。 +- `agent/steering`——本决策未触及(它是控制信号,不是 token 流)。其持久孪生事件是 `steering/message`,镜像发射由其自身的后续 Agent Note 移除:[移除 `agent/steering` 镜像发射](2026-07-04-remove-agent-steering-mirror.md)。 +- `agent/status`、`agent/error`、`agent/created`/`agent/disposed`、`agent/queued`、`agent/session-start`——生命周期/控制事件,不是 transcript 数据,也没有持久副本。 + +## 曾考虑的替代方案 + +**移除持久化、仅保留瞬态实时流**——反向裁剪,已被[单独否决](../../rejected/simplification/2026-06-20-assembled-assistant-messages-only.md):高保真回放、部分失败的流以及快照回放都依赖持久化的 `assistant/chunk` 序列。在此前提确定后,实时发射才是配对中冗余的那一半。 + +## 后果 + +插件不能再从 `Agent` 优先事件观察 token 增量。它需要订阅 `session/event`、过滤 `assistant/chunk`,并在需要时通过 `ctx.agents.get(session.id)` 直接查找对应的实时 handle。没有生产消费方需要在分片时刻取得实时 `Agent`;这与移除边界镜像所作的取舍相同,均可接受。 diff --git a/.agents/notes/implemented/simplification/2026-07-04-drop-image-content-block.i18n.yaml b/.agents/notes/implemented/simplification/2026-07-04-drop-image-content-block.i18n.yaml new file mode 100644 index 0000000000..464ffc54d4 --- /dev/null +++ b/.agents/notes/implemented/simplification/2026-07-04-drop-image-content-block.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-04-drop-image-content-block.md: 566803ab5b9f213b7dc87fcf779ed7a963d988fd +2026-07-04-drop-image-content-block.zh.md: 667ddbc1b7bce2a276fe7528f46d3e43916bad83 diff --git a/.agents/notes/implemented/simplification/2026-07-04-drop-image-content-block.md b/.agents/notes/implemented/simplification/2026-07-04-drop-image-content-block.md index df63f2a78f..566803ab5b 100644 --- a/.agents/notes/implemented/simplification/2026-07-04-drop-image-content-block.md +++ b/.agents/notes/implemented/simplification/2026-07-04-drop-image-content-block.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-07-04-drop-image-content-block.zh.md) + ## Problem `ImageBlock` (`packages/llm/llm/src/types.ts`) had no production producer, and every consumer on every path DROPPED it: the deepseek adapter's serializer skipped image blocks (a documented MVP limitation), the pi-ai converter skipped them as unrepresentable, the ACP codec neither advertises image prompt capability nor forwarded image blocks outbound and REJECTS image prompt content inbound, and the compaction estimator charged a flat token constant and rendered `[image]`. An `ImageBlock` constructed then would silently vanish from the wire — the vocabulary advertised a capability no path honored, which is the silent-data-loss shape AGENTS.md's defensive patterns warn against. The only constructors anywhere were tests pinning the skip/drop/estimate branches. diff --git a/.agents/notes/implemented/simplification/2026-07-04-drop-image-content-block.zh.md b/.agents/notes/implemented/simplification/2026-07-04-drop-image-content-block.zh.md new file mode 100644 index 0000000000..667ddbc1b7 --- /dev/null +++ b/.agents/notes/implemented/simplification/2026-07-04-drop-image-content-block.zh.md @@ -0,0 +1,29 @@ +# Agent Note: 移除 `image` 内容块,直到有路径能真正处理它 + +Status: implemented + +[English](2026-07-04-drop-image-content-block.md) | 中文 + +## 问题 + +`ImageBlock`(`packages/llm/llm/src/types.ts`)没有任何生产环境的生产者,而每条路径上的每个消费方都将其丢弃:deepseek 适配器的序列化器跳过 image 块(这是文档中注明的 MVP 限制);pi-ai 转换器因无法表示而跳过;ACP(Agent Client Protocol)编解码器既不宣告图像提示词能力、也不向外转发 image 块,并且会拒绝入站的图像提示词内容;压缩(compaction)估算器对其收取一个固定 token 常量并渲染为 `[image]`。此时构造的 `ImageBlock` 会在协议格式(wire format)上静默消失——词汇宣告了一种没有任何路径兑现的能力,这正是 AGENTS.md 防御性模式所警告的静默数据丢失形态。唯一的构造调用出现在测试中,用于覆盖 skip/drop/estimate 分支。 + +## 决策 + +移除 `ImageBlock`、其 map 条目,以及适配器、ACP 渲染和压缩中的 image 专用分支。在同一个变更中更新所属的词汇文档与生成的引用。未知扩展块仍然覆盖默认分支,ACP 继续独立于 harness 词汇拒绝入站的图像提示词内容。 + +## 曾考虑的替代方案 + +### 为什么不保留? + +当适配器、ACP 和压缩全部支持 image 时,`ContentBlockMap` 可以重新引入。保留一个唯一实现就是拒绝的核心类型,等于宣告一个不可用的对外服务接口;移除后,生产者会立即得到编译期错误。 + +评审中记录的回退方案(假如评审决定保留该槽位):保留 `ImageBlock`,但将所有静默跳过替换为显式拒绝,并在词汇文档中记录该策略——静默丢弃是唯一没有辩护者的状态。评审最终决定移除;此回退方案作为文档化的替代方案保留,以备该槽位在完整功能就绪之前回归。 + +## 验证 + +除 Agent Note(agent 决策记录)之外,没有任何地方构造 harness `ImageBlock`。ACP 独立的入站图像拒绝路径仍有测试;适配器、codec 和压缩的默认分支则使用插件定义的块类型覆盖。 + +## 后果 + +日后重新添加核心词汇类型需要同时改动多个包(package)——但这种协调变更本就是真正的多模态功能所需的形态(适配器映射、ACP 能力宣告、压缩定价),而当前并不存在需要保留的实现。 diff --git a/.agents/notes/implemented/simplification/2026-07-04-drop-inert-request-knobs.i18n.yaml b/.agents/notes/implemented/simplification/2026-07-04-drop-inert-request-knobs.i18n.yaml new file mode 100644 index 0000000000..4d018139c5 --- /dev/null +++ b/.agents/notes/implemented/simplification/2026-07-04-drop-inert-request-knobs.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-04-drop-inert-request-knobs.md: 06fa6c1c539f9ff0cfabf76bc41c53800bd46c8c +2026-07-04-drop-inert-request-knobs.zh.md: 42aadde2b279a453fac9444060b8ac34bf9e3c8b diff --git a/.agents/notes/implemented/simplification/2026-07-04-drop-inert-request-knobs.md b/.agents/notes/implemented/simplification/2026-07-04-drop-inert-request-knobs.md index dadab43f76..06fa6c1c53 100644 --- a/.agents/notes/implemented/simplification/2026-07-04-drop-inert-request-knobs.md +++ b/.agents/notes/implemented/simplification/2026-07-04-drop-inert-request-knobs.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-07-04-drop-inert-request-knobs.zh.md) + ## Problem Two request-contract knobs rode the whole request pipeline, yet neither could do anything: diff --git a/.agents/notes/implemented/simplification/2026-07-04-drop-inert-request-knobs.zh.md b/.agents/notes/implemented/simplification/2026-07-04-drop-inert-request-knobs.zh.md new file mode 100644 index 0000000000..42aadde2b2 --- /dev/null +++ b/.agents/notes/implemented/simplification/2026-07-04-drop-inert-request-knobs.zh.md @@ -0,0 +1,35 @@ +# Agent Note: 移除 `GenerateOptions.prefill` 与 `ToolSchema.strict`——无端到端可用路径的请求旋钮 + +Status: implemented + +[English](2026-07-04-drop-inert-request-knobs.md) | 中文 + +## 问题 + +两个请求契约旋钮贯穿了整条请求流水线,却都无法产生任何效果: + +- **`prefill`**(`packages/llm/llm/src/types.ts`)没有生产级的 setter:agent loop(智能体循环)组装的是 `model`/`system`/`tools`/`messages` 加 `sessionId`/`signal`,上下文压缩(context compaction)后端只追加 `maxTokens`;而且两个适配器都拒绝它:`packages/llm/llm-deepseek/src/serialize.ts` 和 `packages/llm/llm-pi-ai/src/adapter.ts` 各自在 `prefill` 非 undefined 时抛出 `LlmError('UNSUPPORTED')`。该字段的全部可观测行为就是两个 throw,各由一条适配器测试固定。DeepSeek 的 chat-prefix completion 是一个 Beta 功能,运行在两个适配器都未指向的 base URL 上。 +- **`strict`**(`ToolSchema`,同一文件)穿过了 `DefineToolOptions`/`defineTool`(`packages/core/tools/src/schema.ts`)、注册表的 `schemas()` 允许列表(`packages/core/tools/src/index.ts`)、deepseek 协议格式(wire format)映射(`packages/llm/llm-deepseek/src/serialize.ts`,其 wire-type 注释记录了 strict 模式需要适配器未使用的 `/beta` base URL)、`packages/llm/llm-pi-ai/src/adapter.ts` 中的逐工具 payload 修补逻辑,以及 tool-catalog 渲染器(`scripts/gen-tool-catalog.ts`)中的条件 `Strict:` 行。没有任何已发布的工具设置过它——在所有 `tool-*` 包的 src 和 `examples/` 中执行 `rg` 搜索,`strict:` 的生产者为零;唯一的 setter 出现在 dsh-tools 单元测试中。 + +两个旋钮在适配器间是对称的,因此移除操作将它们从两个孪生适配器中一并剥离——[孪生适配器设计](../architecture/2026-06-13-twin-llm-adapters.md)不受影响。 + +## 决策 + +- 从 `GenerateOptions` 中移除 `prefill`,同时移除两个适配器的 UNSUPPORTED 守卫、固定抛错行为的测试、[core.md](../../../../docs/core-data-structures/core.md) 中的粘贴行,以及记录该拒绝行为的适配器 README 表格行。实操手册中的 UNSUPPORTED 指导([adding-an-llm-adapter.md](../../../../docs/cookbook/adding-an-llm-adapter.md))改为通用表述规则——提供方无法遵守的 `GenerateOptions` 字段应抛出 `LlmError(..., 'UNSUPPORTED')`——而不再以 prefill 为例。[内容块词汇 Agent Note(agent 决策记录)](../architecture/2026-06-11-content-block-vocabulary.md)的后果按照 [implemented/AGENTS.md](../AGENTS.md),将 prefill 记录为由生产者门控,而不是已有归属。 +- 从 `ToolSchema`、`DefineToolOptions`、`defineTool`、`schemas()` 允许列表、deepseek 序列化分支及其 wire-type 字段,以及工具目录渲染器的 `Strict:` 行中移除 `strict`。pi-ai 的 payload 修补逻辑简化为对 pi-ai 自身逐工具 strict 默认值的无条件清除(pi-ai 在每个序列化的工具上打 `strict: false`;手写的孪生适配器不发送此字段,因此清除逻辑为保持协议格式对等而保留,由其序列化器测试固定)。setter 测试和 core.md 粘贴行已移除;`GenerateOptions` 与 `ToolSchema` 在 `scripts/type-equiv.manifest.json` 中保留各自的行,因为两个类型只是少了一个字段,本身仍然存在。 + +本 Agent Note 刻意不触及 `temperature`、`stop` 或 `maxTokens`:两个适配器都会端到端遵守它们,而且它们自然是 `agent/request` 上修改请求的钩子插件首批目标。 + +## 曾考虑的替代方案 + +### 为什么不保留? + +「显式的 UNSUPPORTED throw 是诚实的契约行为」——但一个在两个孪生适配器中唯一的实现就是拒绝的旋钮,什么也没承诺;删除它反而升级了失败模式:意外的 setter 变成编译错误而非运行时 throw。「Strict schema 遵循是官方文档记载的提供方功能,且管道完整」——但一个旋钮在有已发布的工具设置它并且有端点兑现它之前,不构成产品表面;今天两者都不成立。它们各自随首个真实 producer 回归:`prefill` 随实现了 chat-prefix completion 的适配器(以及对不支持该功能的适配器的明确策略)一起回来;`strict` 随需要它的工具和 beta 端点方案一起回来。 + +## 验证 + +`rg prefill` 只返回 Agent Note 记录(本文及[内容块词汇 Agent Note](../architecture/2026-06-11-content-block-vocabulary.md)中由生产者门控的后果);限定在工具 schema 范围内的 `rg strict` 只返回本 Agent Note、保留下来的 pi-ai 清理逻辑,以及 `strictEqual` 等无关正文。两个适配器的契约测试都能在没有守卫的情况下通过,pi-ai 修正仍会清理库的 strict 默认值——其 serializer 测试固定了线协议一致性。 + +## 后果 + +已发布的钩子桥接不设置任何请求字段,而请求变更插件(`agent/request` waterfall(瀑布式事件)监听器)使用的是 `temperature`/`stop`(保留且可用),而非适配器拒绝的字段。如果 chat-prefix completion 或 strict 模式成为产品功能,重新添加将随适配器/端点工作一起落地,届时契约能说明实际发生了什么,而不是「所有人都 throw」。 diff --git a/.agents/notes/implemented/simplification/2026-07-04-drop-unconsumed-web-observation-surface.i18n.yaml b/.agents/notes/implemented/simplification/2026-07-04-drop-unconsumed-web-observation-surface.i18n.yaml new file mode 100644 index 0000000000..2845b37a05 --- /dev/null +++ b/.agents/notes/implemented/simplification/2026-07-04-drop-unconsumed-web-observation-surface.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-04-drop-unconsumed-web-observation-surface.md: 5b1cb1307c63ef7c298200ee1655119026b9ebf5 +2026-07-04-drop-unconsumed-web-observation-surface.zh.md: c4351c7e66d00f47e1bf9ed117c5f7b043045808 diff --git a/.agents/notes/implemented/simplification/2026-07-04-drop-unconsumed-web-observation-surface.md b/.agents/notes/implemented/simplification/2026-07-04-drop-unconsumed-web-observation-surface.md index 80faa2ac07..5b1cb1307c 100644 --- a/.agents/notes/implemented/simplification/2026-07-04-drop-unconsumed-web-observation-surface.md +++ b/.agents/notes/implemented/simplification/2026-07-04-drop-unconsumed-web-observation-surface.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-07-04-drop-unconsumed-web-observation-surface.zh.md) + ## Problem `WebService` exposes an observation surface no production code observes: diff --git a/.agents/notes/implemented/simplification/2026-07-04-drop-unconsumed-web-observation-surface.zh.md b/.agents/notes/implemented/simplification/2026-07-04-drop-unconsumed-web-observation-surface.zh.md new file mode 100644 index 0000000000..c4351c7e66 --- /dev/null +++ b/.agents/notes/implemented/simplification/2026-07-04-drop-unconsumed-web-observation-surface.zh.md @@ -0,0 +1,34 @@ +# Agent Note: 移除未被消费的 web 观测接口——`providers-change` 事件与 status 方法 + +Status: implemented + +[English](2026-07-04-drop-unconsumed-web-observation-surface.md) | 中文 + +## 问题 + +`WebService` 暴露了一组没有任何生产代码观测的观测接口: + +- **`web/providers-change`**(`packages/web/web/src/index.ts`)在每次提供方注册和 dispose(资源释放)时声明并发出,且每个注册 effect 的回滚 yield 被刻意排在 emit 之前,唯一目的是让抛出异常的 change listener 能回退注册。在该包自身的两个单元测试之外没有任何 listener(其中一个测试的存在仅仅是为了固定那个回滚顺序)。 +- **`searchStatus()` / `fetchStatus()` 与 `WebCapabilityStatus` 联合类型**(同一包)没有生产调用方:`dsh-tool-web` 直接通过 `ctx.web.search()`/`fetch()` 执行,并把不可用性呈现为 seam 在执行时抛出的结构化 `WebError` code(`packages/web/tool-web/src/search.ts`、`packages/web/tool-web/src/fetch.ts`);唯一的 status 调用方是 web 包自己的测试。`packages/web/tool-web/README.md` 和 [architecture.md](../../../../docs/architecture.md) 中的正文声称工具“只读取聚合的 `searchStatus()`/`fetchStatus()`”——这种漂移之所以存续,只是因为没有机制对照调用位置检查正文。 + +seam 自身的设计使这两个接口天然没有消费方:工具注册跟随产品 ENABLEMENT 而非提供方可用性(`packages/web/tool-web/src/index.ts`),提供方选择在执行时解析且从不缓存——因此没有需要失效的缓存、没有需要重算的注册集合、也没有调用方需要一个有别于「执行并路由结构化错误」的可用性探测。HMR(热模块替换)清理由 effect disposer 自身承载。 + +这与[删除无人消费的 `llm/adapter-change` 事件](2026-06-20-drop-unconsumed-llm-adapter-change-event.md)相呼应;后者从 `LlmService` 移除了相同的通知形状、相同的 emit 前回滚机制和相同的监听器抛错测试。该 Agent Note(agent 决策记录)的保留/删除标准是:为可能面向用户的工具列表消费方保留 `tools/change`,删除启动时后端注册表信号。按这一标准,web 提供方注册表明确属于删除一侧;status 方法则是把同一判断应用于拉取表面,而非推送表面。 + +## 决策 + +移除注册表变更事件、聚合 status 方法与类型,以及它们的专属测试。提供方私有的 status 保留用于执行时选择。面向调用方的覆盖率现在断言成功执行或结构化的选择错误,web 文档描述该按需调用契约。 + +## 曾考虑的替代方案 + +### 为什么不保留? + +web seam Agent Note 刻意规定了两者——事件作为最小 HMR 可见性信号,status 方法作为工具的聚合诊断——未来也可以设想提供方状态面板。但同一 Agent Note 的其他选择让它们失去了生存条件:调用时派生选择和基于启用状态的注册,使任何消费方都不可能需要其中任一项;已发布工具展示了真实模式(执行并路由结构化错误);发生漂移的 README 句子则表明承诺中的消费方从未出现。按照 AGENTS.md 所述“Agent Note 是提案,而非绝对真理”,代码后来证明提案中的这些部分超出了需要;未来的观察者应根据真实消费方的形状,重新引入它实际消费的最小信号或查询。 + +## 验证 + +除 Agent Note 历史外,不再存在 `providers-change`、`searchStatus`、`fetchStatus` 或 `WebCapabilityStatus` 拼写;目录保持新鲜(`verify-cordis-catalog` 为绿色);注册/释放 HMR 安全性测试通过执行行为证明清理;tool-web README 和架构段落也描述了工具实际拥有的执行时错误路由契约。 + +## 后果 + +未来若有提供方选择器 UI 或诊断面板需要变更通知或 status 查询,它将重新添加自身所消费的最小接口;相同的判断及其反转条件已记录在 LLM(大语言模型)先例中。 diff --git a/.agents/notes/implemented/simplification/2026-07-04-fold-stdio-ui-helper.i18n.yaml b/.agents/notes/implemented/simplification/2026-07-04-fold-stdio-ui-helper.i18n.yaml new file mode 100644 index 0000000000..3e67070db5 --- /dev/null +++ b/.agents/notes/implemented/simplification/2026-07-04-fold-stdio-ui-helper.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-04-fold-stdio-ui-helper.md: 01165df19942e8e0adf84ede3a371f53ad12e464 +2026-07-04-fold-stdio-ui-helper.zh.md: 37b316283e96d7640e1e7af5fdbb05ab487aa6fa diff --git a/.agents/notes/implemented/simplification/2026-07-04-fold-stdio-ui-helper.md b/.agents/notes/implemented/simplification/2026-07-04-fold-stdio-ui-helper.md index b05dd22357..01165df199 100644 --- a/.agents/notes/implemented/simplification/2026-07-04-fold-stdio-ui-helper.md +++ b/.agents/notes/implemented/simplification/2026-07-04-fold-stdio-ui-helper.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-07-04-fold-stdio-ui-helper.zh.md) + The later [redundant-agent removal](2026-07-20-remove-stdio-and-echo-agents.md) supersedes this package-placement decision and removes the folded package, app, and line-oriented surface entirely. ## Problem diff --git a/.agents/notes/implemented/simplification/2026-07-04-fold-stdio-ui-helper.zh.md b/.agents/notes/implemented/simplification/2026-07-04-fold-stdio-ui-helper.zh.md new file mode 100644 index 0000000000..37b316283e --- /dev/null +++ b/.agents/notes/implemented/simplification/2026-07-04-fold-stdio-ui-helper.zh.md @@ -0,0 +1,30 @@ +# Agent Note: 将 stdio UI 辅助模块折入 stdio 应用 + +Status: implemented + +[English](2026-07-04-fold-stdio-ui-helper.md) | 中文 + +后来的[冗余 agent(智能体)移除](2026-07-20-remove-stdio-and-echo-agents.md)取代了这项包放置决策,并完整移除合并后的包、应用和面向行的表面。 + +## 问题 + +readline UI 曾是一个完整的包(`packages/support/` 下的 `@deepseek-ai/dsh-ui-stdio`),其唯一的运行时导入方是应用包 `@deepseek-ai/dsh-stdio-demo`。示例通过加载应用来使用 readline UI,从不自行组合该辅助模块;仓库中所有其他引用都是因为包边界存在而存在的机械性或描述性表面:manifest(元数据清单)与 tsconfig 条目、生成的 module-graph 行、依赖图与 README 行,以及命名该包的文档注释。ui 组 README 记录了 support 放置的理由("主要为示例和覆盖率门禁而存在,`ui/` 保留给作为产品交付的界面"),这留下了一个持续的张力:一个已交付的产品应用依赖一个被明确标注为非产品表面的 support 包。 + +这条边界换来的是:包元数据、workspace 与 tsconfig 引用、module-graph 行、README 条目,以及 publint 表面——服务于一个并不可独立替换的辅助模块:stdio 应用的前门集群始终包含 readline UI,且没有其他消费方能有意义地使用它。 + +## 决策 + +当时,该辅助函数移入 `@deepseek-ai/dsh-stdio`,成为终端通道插件。`createStdioChat`、其 `StdioRuntime` 测试 seam 和单元测试随之一同迁移,使 EOF 处理、渲染、释放以及管道/TTY 行为继续受逐文件覆盖率门禁约束,而不会劫持进程全局量。该模块保留应用挂载所消费的具名 `name`/`inject`/`Config`/`apply` 导出形状;当时的 Echo 和 REPL Loader 冒烟证明组合树,插件形状套件则固定显式 `unwrapExports` 行为。上方取代本文的移除记录负责当前包和示例状态。 + +早期的支持辅助包已移除:其清单、tsconfig 引用、模块图行和 README 行均已消失,其余文档改为描述包内模块。 + +## 曾考虑的替代方案 + +### 为什么不将其提升到 `ui/` 而是折入? + +提升可以解决 support 与 product 之间的错位,同时保留边界——只有在 readline UI 是一个可独立替换的集成或有第二个组合方时才是正确选择,而消费方普查表明两者皆非。结构化的 ACP(Agent Client Protocol)桥接保留为独立包,因为它是具有自身契约和快照层级的产品协议表面;readline 辅助模块只是一个应用前门的脚手架。在发布前重新拆分成本很低:如果将来有第二个产品应用需要 readline UI,届时再拆出来,由那个消费方来塑造包契约。 + +## 后果 + +- stdio 应用完整拥有自己的前门;叶子 `cordis.yml` 仍然只加载一个应用包,演示的形态没有变化。 +- 未来如果有独立的终端 UI 需要将该辅助模块作为包使用,届时由那个第二消费方驱动重新引入,而非仓库为假设性的复用保留一条边界。 diff --git a/.agents/notes/implemented/simplification/2026-07-04-prune-producerless-vocabulary-variants.i18n.yaml b/.agents/notes/implemented/simplification/2026-07-04-prune-producerless-vocabulary-variants.i18n.yaml new file mode 100644 index 0000000000..c343b6ff92 --- /dev/null +++ b/.agents/notes/implemented/simplification/2026-07-04-prune-producerless-vocabulary-variants.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-04-prune-producerless-vocabulary-variants.md: 34492e6906cd2d795f880310b1bcd120e3953fcf +2026-07-04-prune-producerless-vocabulary-variants.zh.md: a68a8b04fedefed8a2ab92f08baf5e8b3ea90222 diff --git a/.agents/notes/implemented/simplification/2026-07-04-prune-producerless-vocabulary-variants.md b/.agents/notes/implemented/simplification/2026-07-04-prune-producerless-vocabulary-variants.md index aa61e859d2..34492e6906 100644 --- a/.agents/notes/implemented/simplification/2026-07-04-prune-producerless-vocabulary-variants.md +++ b/.agents/notes/implemented/simplification/2026-07-04-prune-producerless-vocabulary-variants.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-07-04-prune-producerless-vocabulary-variants.zh.md) + ## Problem The merge-extensible vocabulary maps are designed to grow by declaration merging, and the codebase already states the admission policy on `TurnEndReasonMap` (`packages/core/session/src/types.ts`): a variant like `refusal` is "deliberately omitted until" an adapter or loop first emits it. Three declared vocabulary items violated that policy — each had no producer and no consumer, and two had not even a test: diff --git a/.agents/notes/implemented/simplification/2026-07-04-prune-producerless-vocabulary-variants.zh.md b/.agents/notes/implemented/simplification/2026-07-04-prune-producerless-vocabulary-variants.zh.md new file mode 100644 index 0000000000..a68a8b04fe --- /dev/null +++ b/.agents/notes/implemented/simplification/2026-07-04-prune-producerless-vocabulary-variants.zh.md @@ -0,0 +1,33 @@ +# Agent Note: 裁剪无生产者的词汇变体(块缓存提示、`agent` 消息来源、`continuation` 轮次触发器) + +Status: implemented + +[English](2026-07-04-prune-producerless-vocabulary-variants.md) | 中文 + +## 问题 + +可合并扩展的词汇映射表设计上通过声明合并来增长,代码库已在 `TurnEndReasonMap`(`packages/core/session/src/types.ts`)上明确了准入策略:像 `refusal` 这样的变体「在适配器或循环首次发出它之前,有意不纳入」。三个已声明的词汇项违反了该策略——每个都既无生产者也无消费方,其中两个甚至没有测试: + +- **`TextBlock`/`ToolResultBlock` 上的 `CacheHint` 及其 `cache?: CacheHint` 块字段**(`packages/llm/llm/src/types.ts`;图像块曾有第三个此类字段,已随图像块一同移除——参见[删除图像 Agent Note(agent 决策记录)](2026-07-04-drop-image-content-block.md))。任何地方都没有构造带 `cache:` 的块——src、测试和文档粘贴均为空——两个适配器也都不读取 `.cache`:DeepSeek 的提示词缓存是自动的,因此适配器会从响应中映射出 `prompt_cache_hit_tokens`,却从不向请求中发送 hint。这是没有任何提供方能够遵守的 Anthropic 风格 `cache_control` 表面。 +- **`MessageSourceMap.agent`**(`{ kind: 'agent'; agentId: string }`,同一文件)。零个构造点,包括测试在内。它预期的生产者在实现时并未使用它:subagent 后端将父级的提示词发送给子级时不带 `source`,因此记录为 `{ kind: 'user' }`,通用信封渲染器在插值 `source.kind` 时也从未对其做路由。 +- **`TurnTriggerMap.continuation`**(`packages/core/session/src/types.ts`)。agent loop(智能体循环)在结构上不可能发出它——continuation 发生在一个轮次*内部*作为后续步骤,而非作为新轮次——循环只构造 `message` 和 `injection` 触发器。唯一的写入者是一个手工构建的测试 fixture(测试前置数据),它只需要一个任意的非消息触发器(`packages/support/llm-replay/tests/llm-replay.spec.ts`),`injection` 触发器同样满足需求;唯一的生产环境触发器读取方 ACP(Agent Client Protocol)桥接层只过滤 `kind === 'message'`。 + +## 决策 + +`CacheHint`、其 `cache?` 块字段、`agent` 消息来源变体和 `continuation` 轮次触发器变体均已删除:已发布词汇不再携带它们。llm-replay fixture 使用 `injection` 触发器(任何非 `message` 触发器都能满足其用途)。[core.md](../../../../docs/core-data-structures/core.md) 和 [session.md](../../../../docs/core-data-structures/session.md) 中的 type-equiv 粘贴与裁剪后的 map 匹配——两个符号仍保留在 `scripts/type-equiv.manifest.json` 中的行,因为每个 map 都只是少了一个成员而继续存在——并且[内容块词汇 Agent Note](../architecture/2026-06-11-content-block-vocabulary.md)的后果按照 [implemented/AGENTS.md](../AGENTS.md),将 cache hint 记录为由生产者门控,而不是已有归属。 + +每个变体在获得真正的生产者之日回归,这正是映射表设计的增长方式:缓存功能连同传输它的适配器一起重新添加 `cache`;subagent 归属连同打标的后端和路由它的消费方一起重新添加 `agent`;真正启动新轮次的自动续行功能连同发出它的插件一起重新添加 `continuation`。 + +## 曾考虑的替代方案 + +### 为什么不保留它们? + +[内容块词汇 Agent Note](../architecture/2026-06-11-content-block-vocabulary.md)曾把“cache hint……有了归属”列为设计后果,预留槽位也确实能表明意图。但空槽位是每个实现和消费方都必须考虑的契约表面(我的适配器是否必须遵守 `cache`?我的 renderer 是否必须路由 `agent` 来源?),而相邻 map 自身的 JSDoc 已经拒绝“无 emitter 先预留”——`refusal` 和 `max_turn_requests` 被点名为*首次有内容发出它们时*再添加的变体,而不是提前声明。让已经声明但无用的变体遵守同一标准,才能使词汇真正有意义:只要它位于 map 中,就必须有内容生产它。 + +## 验证 + +对 `CacheHint`、`agent` 消息来源拼写和 `continuation` 触发器拼写运行 `rg`,只会返回 Agent Note 记录(本文,以及[删除图像 Agent Note](2026-07-04-drop-image-content-block.md)对图像块自身 `cache` 字段的说明);llm-replay fixture 使用 `injection` 触发器断言相同的重放行为;核心数据结构粘贴和 type-equiv 清单保持同步。 + +## 后果 + +操作行为没有变化——原本就没有内容能够构造这些值。镜像事件移除([边界镜像 Agent Note](2026-06-20-remove-agent-boundary-mirror-events.md)、[流分片 Agent Note](2026-07-02-remove-stream-chunk-mirror.md))只触及瞬态 `agent/*` 事件,从不触及持久词汇,因此不存在冲突。其他位置已经遵守准入策略:`rejected`、`prompt/blocked` 和 `hook/invoked`/`hook/result` 都有实时生产者——本 Agent Note 将同一门槛扩展到缺少生产者的三个变体。图像块自身的 `cache?` 字段归属[删除图像 Agent Note](2026-07-04-drop-image-content-block.md),后者将其与该块一同移除;本 Agent Note 覆盖剩余块类型上的两个字段。 diff --git a/.agents/notes/implemented/simplification/2026-07-04-prune-write-only-fs-surface.i18n.yaml b/.agents/notes/implemented/simplification/2026-07-04-prune-write-only-fs-surface.i18n.yaml new file mode 100644 index 0000000000..e7aabd9dc2 --- /dev/null +++ b/.agents/notes/implemented/simplification/2026-07-04-prune-write-only-fs-surface.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-04-prune-write-only-fs-surface.md: 6cfd5d9ab8a2fc6322814d384fba735c06681976 +2026-07-04-prune-write-only-fs-surface.zh.md: cb7494b5e958c8ed86ffa3ba8ffbe82748d1db03 diff --git a/.agents/notes/implemented/simplification/2026-07-04-prune-write-only-fs-surface.md b/.agents/notes/implemented/simplification/2026-07-04-prune-write-only-fs-surface.md index 97652ef50c..6cfd5d9ab8 100644 --- a/.agents/notes/implemented/simplification/2026-07-04-prune-write-only-fs-surface.md +++ b/.agents/notes/implemented/simplification/2026-07-04-prune-write-only-fs-surface.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-07-04-prune-write-only-fs-surface.zh.md) + ## Problem The [fs seam split](2026-06-26-fsspec-style-fs-seam.md) moved read routing and policy out of the backend into `dsh-tool-fs` and `dsh-fs-policy`. Four pieces of surface kept the pre-split shape — populated on every call, read by nobody: diff --git a/.agents/notes/implemented/simplification/2026-07-04-prune-write-only-fs-surface.zh.md b/.agents/notes/implemented/simplification/2026-07-04-prune-write-only-fs-surface.zh.md new file mode 100644 index 0000000000..cb7494b5e9 --- /dev/null +++ b/.agents/notes/implemented/simplification/2026-07-04-prune-write-only-fs-surface.zh.md @@ -0,0 +1,32 @@ +# Agent Note: 从 fs seam 中移除只写字段与一个无效的路由旋钮 + +Status: implemented + +[English](2026-07-04-prune-write-only-fs-surface.md) | 中文 + +## 问题 + +[fs seam 拆分](2026-06-26-fsspec-style-fs-seam.md)将读取路由与策略从后端移至 `dsh-tool-fs` 和 `dsh-fs-policy`。有四处接口保留了拆分前的形态——每次调用都填充,却无人读取: + +1. **`dsh-fs-local` 中的 `STREAM_MIN_SIZE` + `FsIoInternals.streamMinSize`**——*在本次变更之前已被「禁止硬编码可调参数」审计移除,该审计将路由阈值改为 `dsh-tool-fs` 的 `readStreamMinSize` 配置;此处记录是为了完整呈现整次清理。* 原始位置(`packages/fs/fs-local/src/fsio.ts`,从 `packages/fs/fs-local/src/index.ts` 重导出):包括 fs-local 自身源码和测试在内,全仓库零读取者。后端没有读取路由——`readWholeText`/`streamWholeText` 是调用方自行选择的两个独立原语——真正的路由常量位于消费方(`packages/fs/tool-fs/src/read.ts`,与 `info.size` 比较)。同一个 10 MiB 事实的两份镜像;后端那份是死代码,且该旋钮的 JSDoc 声称提供一个实际不存在的「read routing」覆盖。 +2. **`FsTarget.inputPath`**(`packages/fs/fs/src/types.ts`):每个后端和每个测试 mock 都必须为这个「仅供诊断」的字段编造一个值,而生产环境零读取者——策略插件和所有错误消息使用的是 `targetKey`/`displayPath`。`listDir` 的生产者暴露了语义上的摇摆:目录子项得到的是裸条目名,这不是任何人的「input」。 +3. **`FsEditOutcome.replacements` + `.replaceAll`**(`packages/fs/fs/src/types.ts`):`replacements` 生产环境零读取者(单匹配策略本身保留——它由后端内部 `FS_AMBIGUOUS_EDIT`/`FS_EDIT_NOT_FOUND` 抛出来强制执行,错误消息保留了内部计数);`replaceAll` 仅被 `packages/fs/tool-fs/src/edit.ts` 中的 `formatEditOutput` 读取——作为工具本身已持有的 `replace_all` 参数的回声。精简后,`FsEditOutcome` 变为 `{ version, before, after }`,与 `FsWriteOutcome` 中真正由后端发现的字段对齐。 +4. **`FileReadOutcome.limit` + `.version`**(`packages/fs/tool-fs/src/read-render.ts`):由读取工具填充,但 `formatReadOutput` 只渲染 `offset`/`lines`/`totalLines`/`truncatedByBytes`,且 `fs/observed` 事件发射直接使用 `info.version` 而非 outcome 的副本。 + +## 决策 + +删除 fs-local 常量、其再导出和 `streamMinSize` 配置项(其余 `FsIoInternals` 配置项确实由原子写入测试使用);从 `FsTarget` 删除 `inputPath`;将 `FsEditOutcome` 收窄为 `{ version, before, after }`,并把解析参数中的 `replaceAll` 传给 `formatEditOutput`;从 `FileReadOutcome` 删除 `limit`/`version`。[filesystem.md](../../../../docs/core-data-structures/filesystem.md) 中的粘贴、`packages/fs/fs/README.md`,以及不得不虚构已删除字段的测试 fake 都随类型一同收窄。 + +## 曾考虑的替代方案 + +### 为什么不保留? + +未来的权限/隔离层可能需要解析前的路径来生成错误文本——但它需要的是*请求*,每个调用点仍然持有请求。「替换了 N 处」可能成为面向模型的文本——这是一个需要时再设计的行为变更,且后端内部的计数为其错误消息而保留。读取页脚可能展示 `limit`——但页脚展示的一切已经可以从 `lines`/`totalLines` 推导。与此同时,每个现有和未来的后端(远程、原生)都必须编造无人消费的协议字段,每个测试 mock 都必须满足它们。 + +## 验证 + +已删除表面不复存在——`dsh-fs-local` 中的 `STREAM_MIN_SIZE`/`streamMinSize`、`FsTarget.inputPath`、`FsEditOutcome.replacements`/`.replaceAll`,以及 `FileReadOutcome.limit`/`.version`——而请求侧 `replaceAll`(`FsEditRequest`)和其他 outcome 类型上的版本字段保持不变;测试 fake 随类型一同收窄。`formatEditOutput` 在两个 `replace_all` 分支中生成的文本都没有变化,因此没有快照预期输出发生改动。 + +## 后果 + +后端不增加新义务,反而卸下了四个无人消费的字段。fs 发现功能(glob/grep 工具)涉及相同的 `dsh-fs` 类型文件——这是文本层面而非设计层面的重叠,可以机械地合并解决。 diff --git a/.agents/notes/implemented/simplification/2026-07-04-remove-agent-steering-mirror.i18n.yaml b/.agents/notes/implemented/simplification/2026-07-04-remove-agent-steering-mirror.i18n.yaml new file mode 100644 index 0000000000..8b6bb07da2 --- /dev/null +++ b/.agents/notes/implemented/simplification/2026-07-04-remove-agent-steering-mirror.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-04-remove-agent-steering-mirror.md: 9f7cd5abe968ff216cbd7012163ea1c04dc00599 +2026-07-04-remove-agent-steering-mirror.zh.md: 63f575347d989f288b3129e0a53e5690b85bb4e8 diff --git a/.agents/notes/implemented/simplification/2026-07-04-remove-agent-steering-mirror.md b/.agents/notes/implemented/simplification/2026-07-04-remove-agent-steering-mirror.md index ebfc774792..9f7cd5abe9 100644 --- a/.agents/notes/implemented/simplification/2026-07-04-remove-agent-steering-mirror.md +++ b/.agents/notes/implemented/simplification/2026-07-04-remove-agent-steering-mirror.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-07-04-remove-agent-steering-mirror.zh.md) + ## Problem `agent/steering` was the last remaining transient mirror of a durable session event. The loop's steering drain appends the durable `steering/message { turn, content, source }` and, on the very next line, emitted `agent/steering(agent, turn, content, source)` — the identical fact as a fire-and-forget event (`packages/core/agent-loop/src/loop.ts`, `drainSteering`). It had zero production listeners: the only subscriber anywhere was a loop regression test asserting the emit carried `source` — the same fact the durable event already records one line above. diff --git a/.agents/notes/implemented/simplification/2026-07-04-remove-agent-steering-mirror.zh.md b/.agents/notes/implemented/simplification/2026-07-04-remove-agent-steering-mirror.zh.md new file mode 100644 index 0000000000..63f575347d --- /dev/null +++ b/.agents/notes/implemented/simplification/2026-07-04-remove-agent-steering-mirror.zh.md @@ -0,0 +1,33 @@ +# Agent Note: 移除 `agent/steering` 镜像 emit + +Status: implemented + +[English](2026-07-04-remove-agent-steering-mirror.md) | 中文 + +## 问题 + +`agent/steering` 是最后一个仍存在的、对持久会话事件的瞬态镜像。agent loop(智能体循环)的 steering(中途引导)drain 逻辑先追加持久事件 `steering/message { turn, content, source }`,紧接着下一行就 emit `agent/steering(agent, turn, content, source)`——同一个事实以 fire-and-forget 事件的形式重复发出(`packages/core/agent-loop/src/loop.ts`,`drainSteering`)。它在生产环境中没有任何监听者:唯一的订阅方是一个 agent loop 回归测试,断言 emit 携带了 `source`——而这同一个事实已经由上一行的持久事件记录。 + +`agent/steering` 以相同的 payload 重复了紧接其前的持久事件 `steering/message`。`agent/queued` 仍保留为纯瞬态信号,因为它在持久化之前触发,覆盖了可能在进入日志前被取消的工作。 + +Steering 承载真实生产流量——钩子 bridge 的轮次延续决策通过 `inbox.steer()` 注入其理由,最终成为由钩子矩阵预期输出固定的持久 `steering/message` 事件——而这些消费方无一例外都观察持久事件。没有任何内容观察镜像。 + +## 决策 + +`agent/steering` 已从 agent 事件分类中移除:包括 `packages/core/agent/src/types.ts` 中的声明(以及其中实时事件 JSDoc 列表对它的提及)、`drainSteering` 中的 emit(当时已无用的 `ctx` 参数也随之移除)、`packages/core/agent/README.md` 中的表格行,以及循环伪代码块(`packages/core/agent-loop/src/loop.ts` 模块文档和 [architecture.md](../../../../docs/architecture.md))中的 emit 行;Cordis 目录重新生成后不再包含它。唯一的回归测试改为在持久 `steering/message` 事件上固定来源保留行为——所固定的事实存在于日志上。 + +三份已实现 Agent Note(agent 决策记录)曾说明保留该事件;按照 [implemented/AGENTS.md](../AGENTS.md),每份记录都已修改并指向本文作为移除记录:包括[边界 Agent Note](2026-06-20-remove-agent-boundary-mirror-events.md) 的保留列表条目、[流分片 Agent Note](2026-07-02-remove-stream-chunk-mirror.md) 的范围条款,以及[事件域语义 Agent Note](../architecture/2026-06-30-event-domain-semantics.md) 的瞬态 emit 枚举。 + +## 曾考虑的替代方案 + +### 为什么不保留? + +“它是控制信号,不是边界”——但该分类的实际区分是镜像/仅实时,而非控制/边界,并且该事件确实是镜像。希望在入队时收到通知的消费方可以使用 `agent/queued`(及其 steering 标记);希望在排空时收到通知的消费方,本质上是在要求获知 `steering/message` 被追加的时刻,而 `session/event` 会交付相同 payload 并附带持久性。遭拒绝的[退役轮次中途 steering Agent Note](../../rejected/simplification/2026-06-20-retire-mid-turn-steering.md)所捍卫的是 steering *功能*——`steer()`、持久事件、强制延续——本次移除不会触及其中任何一项。 + +## 验证 + +`agent/steering` 拼写只存在于 Agent Note 正文中(本 Agent Note、上方三份已修改 Agent Note,以及已冻结的[遭拒绝 steering 功能 Agent Note](../../rejected/simplification/2026-06-20-retire-mid-turn-steering.md),其正文记录了它所否决的提案);目录已重新生成;重新定向的测试在 `steering/message` 上固定来源保留行为。 + +## 后果 + +生产环境中没有需要迁移的监听者,两种瞬态通知需求各有归宿:入队时由 `agent/queued`(带 `steering` flag)承载,drain 时由 `session/event` 在持久事件 `steering/message` 落地时承载。 diff --git a/.agents/notes/implemented/simplification/2026-07-04-share-app-bin-boot-glue.i18n.yaml b/.agents/notes/implemented/simplification/2026-07-04-share-app-bin-boot-glue.i18n.yaml new file mode 100644 index 0000000000..32517c2c50 --- /dev/null +++ b/.agents/notes/implemented/simplification/2026-07-04-share-app-bin-boot-glue.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-04-share-app-bin-boot-glue.md: 7a763eba8a229ec5017387edb54657a5c367105b +2026-07-04-share-app-bin-boot-glue.zh.md: d65a6613f7b05cdea0f99529808c992aff4256e9 diff --git a/.agents/notes/implemented/simplification/2026-07-04-share-app-bin-boot-glue.md b/.agents/notes/implemented/simplification/2026-07-04-share-app-bin-boot-glue.md index f054f168a2..7a763eba8a 100644 --- a/.agents/notes/implemented/simplification/2026-07-04-share-app-bin-boot-glue.md +++ b/.agents/notes/implemented/simplification/2026-07-04-share-app-bin-boot-glue.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-07-04-share-app-bin-boot-glue.zh.md) + ## Problem The stdio and ACP bins duplicated environment loading, fail-loud handling, entry validation, and boot logic, including subtle Loader failure behavior. Their copies had already drifted and lived in self-executing files excluded from unit coverage, making their helper exports unusable. diff --git a/.agents/notes/implemented/simplification/2026-07-04-share-app-bin-boot-glue.zh.md b/.agents/notes/implemented/simplification/2026-07-04-share-app-bin-boot-glue.zh.md new file mode 100644 index 0000000000..d65a6613f7 --- /dev/null +++ b/.agents/notes/implemented/simplification/2026-07-04-share-app-bin-boot-glue.zh.md @@ -0,0 +1,27 @@ +# Agent Note: 共享应用 bin 的启动胶水代码,而非维护两份副本 + +Status: implemented + +[English](2026-07-04-share-app-bin-boot-glue.md) | 中文 + +## 问题 + +stdio 和 ACP(Agent Client Protocol)两个 bin 各自重复了环境加载、fail-loud 处理、入口校验与启动逻辑,包括微妙的 Loader 失败行为。两份副本已经发生漂移,且位于自执行文件中、被排除在单元测试覆盖率之外,导致其导出的辅助函数无法被复用。 + +## 决策 + +辅助函数只存在一处:[`@deepseek-ai/dsh-app-boot`](../../../../packages/ui/app-boot)(`packages/ui/app-boot`,归入 `ui` 分组,因为 bin 是已发布产物,其运行时依赖本身也必须是已发布的包,而非 `support/`)。包含:`resolveConfigPath`(快照感知,两个 bin 共用的唯一路径解析器)、`loadEnv`、`installFailLoud`、`assertEntriesLoaded` 与 `boot`,每个函数都通过 bin 的诊断前缀参数化,并在其副作用 seam(warn sink、process slice)处支持注入,使单元测试套件能覆盖每个分支——包括 `boot()` 在进程内驱动真实 Loader、使用相对路径 specifier 配置的场景,既覆盖已稳定树的正常路径,也覆盖无 fiber 入口的拒绝路径。该包启用逐文件 100% 覆盖率门禁;Loader 失败的相关知识只有一个归属地。 + +每个 `bin.ts` 都是在共享辅助函数之上加应用特有生命周期的精简自执行组合(ACP bin:重放模式环境变量跳过和 stdin EOF 释放;stdio bin:没有额外逻辑)。这些 bin 仍排除在覆盖率之外且不导出任何内容;已发布产物守卫保持不变——按照“真实入口路径即已发布产物”的防御模式,已构建 bin 冒烟仍在具有 node_modules 形状的临时目录中用纯 node 运行每个 bin(现在也会符号链接 `ui/app-boot`),并继续断言缺失配置时以非零状态退出。[提取示例应用包 Agent Note(agent 决策记录)](../architecture/2026-06-20-extract-example-app-packages.md)中的 bin 归属事实已据此修改。 + +## 曾考虑的替代方案 + +### 为何不保留重复? + +这些 bin 当时被定位为归属相互独立的已发布产物,而新包会带来固定开销(清单、README、tsconfig 引用、publint 表面),与去重的行数相当。但创建 bin 的 Agent Note 从未权衡应用间共享——它把三份示例 `start.ts` 副本合并进 bin 后便止步于此;漂移是已经观察到的事实;覆盖率缺口的理由也独立于去重理由:这是仓库中唯一免受逐文件 100% 门禁约束的非平凡运行时逻辑。记录的后备方案(只将纯逻辑提取到各应用模块)会结束豁免,但会继续让相关知识拥有两个归属。 + +## 后果 + +- 启动胶水代码的变更(新增守卫、修复路径解析)只需落地一次,两个已发布 bin 自动继承;bin 之间不会再次漂移。 +- `dsh-app-boot` 保持轻量依赖(cordis + loader/include 对)——它是启动机制,不是应用表面积。 +- bin 自身的文件几乎是平凡的组合;所有含分支的逻辑都在覆盖率门禁之下。 diff --git a/.agents/notes/implemented/simplification/2026-07-04-tighten-hook-protocol-contract.i18n.yaml b/.agents/notes/implemented/simplification/2026-07-04-tighten-hook-protocol-contract.i18n.yaml new file mode 100644 index 0000000000..b2c35d276c --- /dev/null +++ b/.agents/notes/implemented/simplification/2026-07-04-tighten-hook-protocol-contract.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-04-tighten-hook-protocol-contract.md: a1972ee8ef486982268ba8886b2413f3557061b4 +2026-07-04-tighten-hook-protocol-contract.zh.md: 4917a8f551672f51b0ebc27b1267c7e8e8eb2178 diff --git a/.agents/notes/implemented/simplification/2026-07-04-tighten-hook-protocol-contract.md b/.agents/notes/implemented/simplification/2026-07-04-tighten-hook-protocol-contract.md index 82830b1366..a1972ee8ef 100644 --- a/.agents/notes/implemented/simplification/2026-07-04-tighten-hook-protocol-contract.md +++ b/.agents/notes/implemented/simplification/2026-07-04-tighten-hook-protocol-contract.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-07-04-tighten-hook-protocol-contract.zh.md) + ## Problem Four pieces of the `dsh-hook-protocol`/bridge contract missed the discipline the [subagent-observe-enrich Agent Note](../feature/2026-06-30-subagent-observe-enrich.md) records — it dropped an `agentType` lifecycle field for lacking a consumer, and these failed the same test: diff --git a/.agents/notes/implemented/simplification/2026-07-04-tighten-hook-protocol-contract.zh.md b/.agents/notes/implemented/simplification/2026-07-04-tighten-hook-protocol-contract.zh.md new file mode 100644 index 0000000000..4917a8f551 --- /dev/null +++ b/.agents/notes/implemented/simplification/2026-07-04-tighten-hook-protocol-contract.zh.md @@ -0,0 +1,32 @@ +# Agent Note: 收紧 hook-protocol 契约——dialect、废弃字段、双重默认值与 lib 拥有的 `hook/result` 语义 + +Status: implemented + +[English](2026-07-04-tighten-hook-protocol-contract.md) | 中文 + +## 问题 + +`dsh-hook-protocol`/bridge 契约中有四部分没有遵守 [subagent observe/enrich Agent Note(agent 决策记录)](../feature/2026-06-30-subagent-observe-enrich.md)记下的准则——后者因缺少消费方而删除 `agentType` 生命周期字段,以下各项没有通过同一检验: + +1. **`HookDialect` 的 `'native'` 变体**(`packages/hooks/hook-protocol/src/types.ts`)没有生产者——bridge 会标记 `'claude'` 和 `'codex'`;所有位置中唯一构造 `'native'` 的是该库自己的单元测试。字段自身的 JSDoc 将 `dialect` 定义为“运行它的 bridge”,而 native 不是 bridge:[拦截 seam Agent Note](../feature/2026-06-30-interception-seams.md) 记载 native 钩子不是一个包,并且“native 插件无需持久钩子日志即可使用类型化 Decision”;旗舰 native 插件实践示例恰好断言了这一点(完全没有 `hook/*` 事件)。 +2. **`HookOutput.suppressOutput`**(同一文件)被 codec 解析后在所有路径上均被丢弃:没有 bridge 分支处理它、没有合并 fold、没有 warn、没有 deferred-list 行——在所有「被解析但未兑现」的同类字段中它是唯一没有明确延期声明的(`updatedInput` → 一条 warn 日志加 [pre-tool-input-rewrite 提案](../../proposed/feature/2026-06-30-pre-tool-input-rewrite.md);`systemMessage` → 一条 warn 日志加 README deferred 行;`continue`/`stopReason` → 一个 `TODO(hook-continue-false)` 锚点加 `'stop'` decision 记录)。从结构上看根本无物可抑制:钩子 stdout 从不进入任何 transcript(文本记录)(上下文仅通过 `additionalContext` 流入;日志只记录 `decision`/`stderrSummary`),因此钩子作者设置 `suppressOutput: true` 得到的是无声的空操作,且无任何警告。 +3. **`defaultTimeoutMs` 在两个 bridge 配置中以浮动字面量双重默认**——schema 的 `.default(600_000)` 加上一个 `?? 600_000` 回退(`packages/hooks/hooks-claude/src/index.ts`、`packages/hooks/hooks-codex/src/index.ts`),一个协议级常量在每个 bridge 中有两个归属地,两个 bridge 可能在共享默认值上悄然分歧。*提案最初的补救措施是彻底删除该旋钮,但被 no-hardcoded-tunables 审计所取代:审计保留了该旋钮作为 bridge 拥有的显式配置(并在旁边新增了 `stderrSummaryMaxChars`);剩下要修的是字面量的归属地。* +4. **`hook/result` 的语义存在于两个 bridge 中(各一份),而非拥有该事件的 lib。** `summarize()`——stderr 截断规则——在 `packages/hooks/hooks-claude/src/index.ts` 与 `packages/hooks/hooks-codex/src/index.ts` 中逐字节相同;decision 字符串规则 `output.decision ?? (output.continue === false ? 'stop' : 'pass')` 同样如此。然而 `dsh-hook-protocol` 声明了 `hook/result`、在文档中将 `stderrSummary` 描述为「已截断」却不拥有截断逻辑,记录了 decision 值却不拥有映射逻辑。如果某个 bridge 漂移(不同的上限、不同的回退),共享持久化事件的语义就会悄然分叉。 + +## 决策 + +`HookDialect` 是封闭的 bridge 集合:`'claude' | 'codex'`;`HookOutput` 移除了不受支持的 `suppressOutput`。`hook/result.durationMs` 保留为持久化的审计计时,仅在快照中做归一化。参考默认值各只存在一处:`DEFAULT_HOOK_TIMEOUT_MS` 与 `DEFAULT_STDERR_SUMMARY_MAX_CHARS`。`HookResultRecord` 与 `appendHookResult` 为两个 bridge 统一拥有 stderr 摘要化和 decision 推导逻辑。`BLOCKING_EXIT_CODE` 为 codec 内部常量。 + +## 曾考虑的替代方案 + +### 为什么不保留它们? + +不受支持的词汇可以在真正有消费方时回归。`durationMs` 保留,因为持久化的审计计时独立于当前是否有读取方而有价值。Bridge 特有的 payload 构造留在各自 bridge 中,而共享持久化事件的归一化属于协议库。 + +## 验证 + +`HookDialect` 仅包含 Claude 和 Codex,`suppressOutput` 在源码、已解析字段文档和归一化逻辑中均不存在。`durationMs` 保留在事件和 fixture(测试前置数据)中,回放时做清洗。`600_000` 和 `500` 两个默认值各只在协议库中出现一次;每个钩子的超时覆盖仍然生效;两个 bridge 的测试套件均验证了由库拥有的 stderr 截断和 decision 规则。 + +## 后果 + +`dialect`、`suppressOutput`、可调参数和语义变更在线协议和预期输出中均不可见。代价是 `dsh-hook-protocol` 和两个 bridge 中的改动——在预发布立场下成本很低,也比让一项持久事件语义的两个副本各自老化更便宜。 diff --git a/.agents/notes/implemented/simplification/2026-07-04-trim-acp-bridge-unreachable-surface.i18n.yaml b/.agents/notes/implemented/simplification/2026-07-04-trim-acp-bridge-unreachable-surface.i18n.yaml new file mode 100644 index 0000000000..0aa39a18ff --- /dev/null +++ b/.agents/notes/implemented/simplification/2026-07-04-trim-acp-bridge-unreachable-surface.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-04-trim-acp-bridge-unreachable-surface.md: ce0c623930192d02c8347c3956c497ee13048904 +2026-07-04-trim-acp-bridge-unreachable-surface.zh.md: e89b0e7c9c7c8438fb71adacf1b525a0b94bf04b diff --git a/.agents/notes/implemented/simplification/2026-07-04-trim-acp-bridge-unreachable-surface.md b/.agents/notes/implemented/simplification/2026-07-04-trim-acp-bridge-unreachable-surface.md index 7d1065d250..ce0c623930 100644 --- a/.agents/notes/implemented/simplification/2026-07-04-trim-acp-bridge-unreachable-surface.md +++ b/.agents/notes/implemented/simplification/2026-07-04-trim-acp-bridge-unreachable-surface.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-07-04-trim-acp-bridge-unreachable-surface.zh.md) + ## Problem Two pieces of `dsh-acp` surface were unreachable from any shipped configuration: diff --git a/.agents/notes/implemented/simplification/2026-07-04-trim-acp-bridge-unreachable-surface.zh.md b/.agents/notes/implemented/simplification/2026-07-04-trim-acp-bridge-unreachable-surface.zh.md new file mode 100644 index 0000000000..e89b0e7c9c --- /dev/null +++ b/.agents/notes/implemented/simplification/2026-07-04-trim-acp-bridge-unreachable-surface.zh.md @@ -0,0 +1,26 @@ +# Agent Note: 裁剪不可达的 ACP 桥接层表面——品牌配置项与 kind 嗅探回退 + +Status: implemented + +[English](2026-07-04-trim-acp-bridge-unreachable-surface.md) | 中文 + +## 问题 + +`dsh-acp` 有两处对外表面在任何已交付的配置中都不可达: + +1. **`AcpConfig.agentName` / `agentVersion`**(`packages/ui/acp/src/index.ts`)。已发布应用包只向 bridge 传递 `{ model }`(`packages/examples/acp-demo/src/index.ts`),因此没有任何叶子 `cordis.yml`——唯一的生产配置表面——能够设置这些配置项;只有直接挂载 bridge 才能设置它们,而这种做法只存在于一个单元测试中。每份快照预期输出——包括钩子矩阵场景——都固定 schema 默认值(`deepseek-harness-acp` / `0.0.1`)。这对配置项还带有一个尚未解决的 `TODO(double-default)`:字面量存在两次(schema `.default(...)` 加 `??` 后备值),TODO 要求为它们选择一个归属。 +2. **`toolKindFor` 名称启发式**(同一文件)在通用回退路径中对 `bash*`/`read*`/`write`/`edit*` 工具名做了特殊处理。自[render-intent 联合类型](../architecture/2026-07-02-tool-render-intent-union.md)以来,这些分支匹配到的每个第一方工具都自带 `presentCall` 并携带其 kind,而没有 presenter 的生产工具(`subagent`、`subagent_fork`)本来就落入 `other`。这些分支只有在工具拒绝自行呈现调用时才在生产中可达:`presentCall` 抛出异常(容错回退),或模型参数未通过工具 schema 导致 `defineTool` 的 `presentCall` 包装层返回 `undefined`(例如 `bash` 调用缺少必需的 `description`)。而桥接层自身的模块文档明确声明了该启发式所违反的设计规则:"桥接层绝不对工具名做特殊处理"。 + +## 决策 + +在初始化时硬编码现有的握手标识 `{ name: 'deepseek-harness-acp', version: '0.0.1' }`,移除不可达的配置字段与重复默认值。在两个 presenter 回退处,将 `toolKindFor` 替换为中性的 `'other'`。正常的第一方呈现不受影响;格式错误或失败的呈现现在会渲染一个诚实的通用卡片,而非从工具名推断 kind。初始化测试和快照固定握手标识;只有 `hook-codex-posttool-block` 中格式错误的调用改变了回退卡片的 kind。 + +## 曾考虑的替代方案 + +### 为什么不保留? + +品牌配置可以在 app 包将其暴露给部署环境时再回来。从未知工具名推断呈现方式违反了 render-intent 契约;中性回退卡片还能为格式错误的调用和损坏的 presenter 保留原始输入。 + +## 后果 + +除上述回退渲染的取舍外没有其他影响——退化路径下,中性卡片比推断出的第一方卡片更易于诊断。 diff --git a/.agents/notes/implemented/simplification/2026-07-12-drop-unconsumed-skill-provider-events.i18n.yaml b/.agents/notes/implemented/simplification/2026-07-12-drop-unconsumed-skill-provider-events.i18n.yaml new file mode 100644 index 0000000000..6c3e5859e7 --- /dev/null +++ b/.agents/notes/implemented/simplification/2026-07-12-drop-unconsumed-skill-provider-events.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-12-drop-unconsumed-skill-provider-events.md: b0ed7585882328b6abdcf57974200053d9c26048 +2026-07-12-drop-unconsumed-skill-provider-events.zh.md: fd380b2c0421abfc3032b88b550b4a3e8b88bf38 diff --git a/.agents/notes/implemented/simplification/2026-07-12-drop-unconsumed-skill-provider-events.md b/.agents/notes/implemented/simplification/2026-07-12-drop-unconsumed-skill-provider-events.md index a719e20f1e..b0ed758588 100644 --- a/.agents/notes/implemented/simplification/2026-07-12-drop-unconsumed-skill-provider-events.md +++ b/.agents/notes/implemented/simplification/2026-07-12-drop-unconsumed-skill-provider-events.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-07-12-drop-unconsumed-skill-provider-events.zh.md) + ## Problem Two skill-registry notifications are produced but have no production listener. The generated producer/consumer matrix and exact event-name searches find only declarations, emit sites, tests, generated catalogs, and prose for `skill/provider-added` and `skill/provider-removed`. diff --git a/.agents/notes/implemented/simplification/2026-07-12-drop-unconsumed-skill-provider-events.zh.md b/.agents/notes/implemented/simplification/2026-07-12-drop-unconsumed-skill-provider-events.zh.md new file mode 100644 index 0000000000..fd380b2c04 --- /dev/null +++ b/.agents/notes/implemented/simplification/2026-07-12-drop-unconsumed-skill-provider-events.zh.md @@ -0,0 +1,29 @@ +# Agent Note: 移除无消费方的 skill 提供方事件 + +Status: implemented + +[English](2026-07-12-drop-unconsumed-skill-provider-events.md) | 中文 + +## 问题 + +skill(技能)注册表产出两个通知事件,但没有生产环境的监听方。生成的生产者/消费方矩阵以及对事件名的精确搜索表明,`skill/provider-added` 与 `skill/provider-removed` 仅出现在声明、emit 站点、测试、生成的 catalog 和行文中。 + +skill 发现按需读取当前的提供方映射表,提供方注册时同步清除已完成的 catalog,而 await 后的版本检查阻止了陈旧的发现结果进入缓存。没有兄弟插件通过这些事件等待 skill 提供方——与之形成对比的是活跃的 `subagent/provider-added` 消费方,它容忍兄弟并发加载。 + +`tools/change` 与 `system-prompt/change` 明确不在本提案范围内。既有的简化决策将它们保留为面向实时工具和提示词 UI 的有意观测点,且自引用的已挂载插件已在使用 `tools/change`。本提案同样不改动 `subagent/provider-added`/`removed`,因为 `tool-subagent` 有生产环境的生命周期消费方。 + +## 决策 + +skill 注册表不再声明和 emit 提供方成员变更事件。提供方的注册与 dispose(资源释放)仍为 effect 所有的直接状态变更,同步使已完成的 catalog 失效;查找与发现按需读取当前提供方映射表。测试通过提供方查找和收集到的输出来观察清理行为,而非依赖生命周期通知。 + +生成式事件目录、API 目录和生产者/消费方矩阵均不再包含已删除通知。skill system Agent Note(agent 决策记录)和包文档改为通过其由 effect 直接拥有的状态与 cache 失效契约描述注册。 + +## 曾考虑的替代方案 + +**为未来插件保留 skill 提供方通知。** 第三方插件可能想观察提供方的可用性,但直接提供方注册与按需查找才是扩展契约;当前没有消费方需要推送信号。如果将来出现兄弟加载竞态,可以像 subagent 注册表那样,引入一个带有该消费方实际所需的身份与就绪语义的通知。 + +## 后果 + +生成的事件矩阵中不再有 `skill/provider-added` 或 `skill/provider-removed` 的行。skill 发现、直接运行时注册、提供方 effect 回滚/dispose、缓存失效与注册表查找清理保持不变;监听方触发的回滚随事件一起消失。`tools/change`、`system-prompt/change` 以及已被消费的 subagent 提供方生命周期事件不受影响。 + +预发布消费方失去 skill 提供方观测点,但仍保留两种贡献 skill 的方式:直接运行时注册与提供方注册。未来若有消费方需要实时的提供方可用性信息,必须新增一个带有其实际所需的身份与就绪语义的专用通知。 diff --git a/.agents/notes/implemented/simplification/2026-07-12-prune-unused-web-seam-fields.i18n.yaml b/.agents/notes/implemented/simplification/2026-07-12-prune-unused-web-seam-fields.i18n.yaml new file mode 100644 index 0000000000..1f8a055362 --- /dev/null +++ b/.agents/notes/implemented/simplification/2026-07-12-prune-unused-web-seam-fields.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-12-prune-unused-web-seam-fields.md: c50bf44161579a44b09113fc501f3d67fb5d6855 +2026-07-12-prune-unused-web-seam-fields.zh.md: 401bdd0c812175cffc572e722141d2829a3fc2d5 diff --git a/.agents/notes/implemented/simplification/2026-07-12-prune-unused-web-seam-fields.md b/.agents/notes/implemented/simplification/2026-07-12-prune-unused-web-seam-fields.md index 68ced83876..c50bf44161 100644 --- a/.agents/notes/implemented/simplification/2026-07-12-prune-unused-web-seam-fields.md +++ b/.agents/notes/implemented/simplification/2026-07-12-prune-unused-web-seam-fields.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-07-12-prune-unused-web-seam-fields.zh.md) + ## Problem The web capability carries request/result/status values that every shipped implementation populates but no production consumer reads. `WebSearchResult.providerId` and `query` and `WebFetchResult.providerId` are result echoes; `tool-web` formats only content/sources/truncation or final URL/status/body/truncation, and no other runtime reads them. Search providers return `WebProviderStatus.reason`, but resolution checks only `available` and intentionally emits a generic unavailable diagnostic. diff --git a/.agents/notes/implemented/simplification/2026-07-12-prune-unused-web-seam-fields.zh.md b/.agents/notes/implemented/simplification/2026-07-12-prune-unused-web-seam-fields.zh.md new file mode 100644 index 0000000000..401bdd0c81 --- /dev/null +++ b/.agents/notes/implemented/simplification/2026-07-12-prune-unused-web-seam-fields.zh.md @@ -0,0 +1,27 @@ +# Agent Note: 裁剪 web seam 中未使用的字段 + +Status: implemented + +[English](2026-07-12-prune-unused-web-seam-fields.md) | 中文 + +## 问题 + +web 能力携带的 request/result/status 值,虽然每个已交付的实现都会填充,但没有任何生产环境的消费方读取它们。`WebSearchResult.providerId`、`query` 与 `WebFetchResult.providerId` 是结果回显;`tool-web` 只格式化 content/sources/truncation 或最终 URL/status/body/truncation,没有其他运行时读取这些字段。搜索提供方返回 `WebProviderStatus.reason`,但可用性检查只看 `available`,并有意输出一条通用的不可用诊断信息。 + +`WebFetchRequest.timeoutMs` 同样从未被生产调用方设置。`tool-web` 只提供 URL,使用工具定义的 timeout 加 `exec.signal` 作为调用方截止时间,并依赖本地提供方的配置默认值作为兜底。这个未使用的逐请求覆盖迫使 `web-fetch-local` 暴露 `maxTimeoutMs`、对两个 timeout 来源做 clamp,并为没有任何产品路径能选中的优先级规则编写文档和测试。`WebExecContext` 则是另一个单字段包装层:每个调用方分配 `{ signal }`,每个提供方立即解包 `exec?.signal`;不存在第二个执行控制字段。 + +## 决策 + +web seam 移除搜索/抓取结果中的 `providerId` 回显和搜索的 `query` 回显;调用方本身已持有请求和提供方选择信息。提供方以返回布尔值的方法暴露可用性。抓取请求不再有逐请求 timeout 或 `maxTimeoutMs` clamp;本地提供方保留其可配置的默认 timeout,工具保留自身的截止时间。提供方方法直接接收一个可选的 `AbortSignal`,而非单字段的 `WebExecContext` 包装层。 + +所有 web 实现与面向模型的工具使用更精简的契约。接口/实现/消费方的包(package)拆分、提供方选择、来源引用、最终 URL/状态数据、截断报告与安全限制保持不变。 + +## 曾考虑的替代方案 + +**保留自描述结果、逐请求截止时间与可扩展的执行上下文对象。** 结果回显可以帮助通用遥测,请求级 timeout 可以帮助受信的程序化调用方,包装层则为未来的控制字段留出空间。但目前不存在这样的消费方或第二个字段;在每个提供方中携带重复的身份标识、第二套截止时间策略以及包装/解包管道,使当前契约更难实现和解释。如果遥测或逐调用预算控制到来,届时应当定义哪个截止时间优先、在哪里观测提供方身份,以及多个控制字段是否足以证明需要一个上下文对象。 + +## 后果 + +保留下来的每个 web request/result 字段,要么被生产代码消费,要么是执行提供方请求所必需的。工具可见的搜索/抓取输出、提供方回退、中止行为、可配置的 timeout 兜底、截断与引用仍然被覆盖,无需请求级 timeout 优先级分支或执行上下文包装层。 + +预发布阶段的程序化调用方失去了结果来源回显和逐请求的抓取截止时间。提供方仍具备部署级可配置 timeout 并尊重取消信号,因此这次精简移除的是可配置性,而非安全边界。 diff --git a/.agents/notes/implemented/simplification/2026-07-12-simplify-session-log-representation.i18n.yaml b/.agents/notes/implemented/simplification/2026-07-12-simplify-session-log-representation.i18n.yaml new file mode 100644 index 0000000000..64bea6aec8 --- /dev/null +++ b/.agents/notes/implemented/simplification/2026-07-12-simplify-session-log-representation.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-12-simplify-session-log-representation.md: a40f4013a97a9c940012dbb37d59beb2faf8fb22 +2026-07-12-simplify-session-log-representation.zh.md: a4ecd8c7340affda71d95505ab44910539e36bb9 diff --git a/.agents/notes/implemented/simplification/2026-07-12-simplify-session-log-representation.md b/.agents/notes/implemented/simplification/2026-07-12-simplify-session-log-representation.md index 97a89e5be7..a40f4013a9 100644 --- a/.agents/notes/implemented/simplification/2026-07-12-simplify-session-log-representation.md +++ b/.agents/notes/implemented/simplification/2026-07-12-simplify-session-log-representation.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-07-12-simplify-session-log-representation.zh.md) + ## Problem The session log maintains two representations that cost more machinery than their consumers require: a pseudo-linked surface and custom request-header deltas. diff --git a/.agents/notes/implemented/simplification/2026-07-12-simplify-session-log-representation.zh.md b/.agents/notes/implemented/simplification/2026-07-12-simplify-session-log-representation.zh.md new file mode 100644 index 0000000000..a4ecd8c734 --- /dev/null +++ b/.agents/notes/implemented/simplification/2026-07-12-simplify-session-log-representation.zh.md @@ -0,0 +1,35 @@ +# Agent Note: 简化会话日志表示 + +Status: implemented + +[English](2026-07-12-simplify-session-log-representation.md) | 中文 + +## 问题 + +会话日志维护着两种表示,其机制复杂度超出了消费方的实际需求:一个伪链表 surface 和自定义的请求头增量。 + +`SurfaceManager` 同时在数组、seq map 和可变 `prev`/`next` 链接中存储相同顺序。生产代码从不读取任一链接:compact 的工具配对 balance 根据按 surface 顺序缓存的每个切点 balance 作答。替换已经使用 `indexOf`,因此链接并未使其主导操作成为常数时间。使用线性替换查找的 seq 数组具有相同的渐近替换成本,却只有一种表示需要验证。 + +请求头子系统实现了一套自定义的系统/工具增量编解码器和传输决策层,尽管其契约声明增量只是编码优化,而非可重建性要求。在每个 agent loop(智能体循环)实例边界保留初始/恢复的完整快照,然后在该实例的组装头发生变化时写入一条规范的完整 `request/header`,即可保留回放能力,同时删除 `SystemDelta`、`ToolsDelta`、往返回退逻辑以及持久化的 `request/header-delta` 变体。编解码器专属的词汇随编解码器一起消失,并非因为其各分支本身无效。 + +实现保留追加与替换 `sourceEventSeqs`、崩溃修复 provenance,以及所有 `SessionStartSource` 变体,因为这些字段承担审计/拦截职责,当前没有读取方并不能推翻这一点。 + +## 决策 + +`SurfaceManager.nodes` 是由事件序号组成的 `readonly number[]`;公共 `SurfaceNode` 形状、node 链接和 seq-to-node map 均已移除。内部替换 generation 信号保留。session-query 使用的完整 `foldSurface()` 读取会返回相同的数字数组表示和替换元数据,而无需让增量 manager 保留历史。工具配对 balance 和压缩使用事件序号与 surface 位置;由 compact 拥有的每切点 balance cache 不依赖 node 链接。 + +请求头只使用规范的完整快照。初始与恢复锚点即使没有变化也仍是完整快照;实例内变化会追加另一个完整 `request/header`,reason 为 `change`。delta 事件、codec 类型、diff/apply 辅助函数,以及仅供 codec 使用的 `fallback` reason 均已移除。请求重建选择最新快照。 + +`SESSION_FORMAT_VERSION` 仍固定为 `0`,因此 seed、追加和持久化加载验证会显式拒绝旧 v0 `request/header-delta` 事件,以及携带已删除 `fallback` reason 的完整快照。不存在兼容性 fold 或迁移。JSONL 与 SQLite 测试固定了这一响亮失败边界;ACP(Agent Client Protocol)快照 harness 则把合法的会话中途变更表示为完整固定请求头和完整可读提示词。 + +## 曾考虑的替代方案 + +**保留链表节点和紧凑增量以备未来扩展。** 链接可能有助于未来的游标 API,增量在大型工具 schema 仅有少量变化时可以缩减日志。但没有已发布的游标使用这些链接,而完整快照以磁盘空间换取了显著更简单的正确性。如果头部体积确实成为问题,可以基于真实 trace 设计压缩方案或经过度量的规范增量方案。 + +## 验证 + +单元覆盖率固定有序 surface 的追加/替换行为、工具配对、压缩、完整请求头 fold/记录、请求重建和开发不变量。Seed 验证以及 JSONL、SQLite 加载测试会在重放前拒绝旧事件。无密钥 ACP 套件以新形状覆盖记录、刷新、重放、变化请求头固定,以及沙箱模式切换 fixture(测试前置数据)。 + +## 后果 + +完整请求头会增加日志体积,线性替换查找在极大 surface 上也可能较慢。由于先前实现调用 `indexOf`,替换原本就是线性的;benchmark 推迟到真实 trace 表明更简单的数组成为瓶颈时再进行。格式版本仍为 `0`,因此显式拒绝旧事件是预发布格式边界的永久组成部分。作为交换,surface 顺序和请求头状态现在各自只有一种表示,删除了链接维护、map、codec 分支、往返 fallback 和感知 delta 的快照规范化。 diff --git a/.agents/notes/implemented/testing/2026-06-11-property-based-testing.i18n.yaml b/.agents/notes/implemented/testing/2026-06-11-property-based-testing.i18n.yaml new file mode 100644 index 0000000000..e118ff7330 --- /dev/null +++ b/.agents/notes/implemented/testing/2026-06-11-property-based-testing.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-11-property-based-testing.md: a1bd4147a26a3d562899310e238096939fc2d01a +2026-06-11-property-based-testing.zh.md: 0e1934a24fcf22442420a664c9824bb74c0fe7f7 diff --git a/.agents/notes/implemented/testing/2026-06-11-property-based-testing.md b/.agents/notes/implemented/testing/2026-06-11-property-based-testing.md index 5109aa1c80..a1bd4147a2 100644 --- a/.agents/notes/implemented/testing/2026-06-11-property-based-testing.md +++ b/.agents/notes/implemented/testing/2026-06-11-property-based-testing.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-06-11-property-based-testing.zh.md) + > Merges the original proposal and the decision record for one topic. It found a real BlockAssembler duplicate-`block-end` bug on first run. ## Problem diff --git a/.agents/notes/implemented/testing/2026-06-11-property-based-testing.zh.md b/.agents/notes/implemented/testing/2026-06-11-property-based-testing.zh.md new file mode 100644 index 0000000000..0e1934a24f --- /dev/null +++ b/.agents/notes/implemented/testing/2026-06-11-property-based-testing.zh.md @@ -0,0 +1,29 @@ +# Agent Note: 对协议形态代码进行基于属性的测试 + +Status: implemented + +[English](2026-06-11-property-based-testing.md) | 中文 + +> 将原始提案与同一主题的决策记录合并为一篇。首次运行即发现了 BlockAssembler 重复 `block-end` 的真实 bug。 + +## 问题 + +基于示例的测试只能固定我们想到的用例。harness 的核心是协议形态的代码:分片流、事件日志、schema 转换、收件箱调度。这些场景的输入空间是组合式的,有趣的 bug 藏在没人写过示例的交错序列中。佐证:一个块组装的排序 bug 曾在 happy path 100% 行覆盖率下存活。逐文件 100% 覆盖率证明每一行都跑过了,但不能证明每种交错都是正确的。 + +## 决策 + +引入 `fast-check`(作为根 devDependency),在每个协议形态的包(package)中编写一个 `tests/properties.spec.ts`。生成器调优为*逼真但对抗性*的输入(而非均匀噪声),`numRuns` 控制在本地套件总耗时远低于约 10 秒。失败时打印可复现的 seed。(原始提案还草拟了一个夜间 CI job,以 100 倍迭代运行;该部分未交付。属性测试套件仅在常规的 `push`/`pull_request` CI 中运行,定时高迭代 job 仍属可能的后续工作。) + +- **dsh-llm / BlockAssembler:** 任意分片流(合法 + 畸形:重复索引、滞后分片、缺少 block-start)。不变式:`blocks()` 计数 ≤ 已见到的不同索引数;重组幂等(`blocks()` 在重复调用间稳定,且 `message().content` 与之一致);`blocks()` 从不抛异常且仅产出合法的 content-block 标签;`finish` 反映最后一个 `finish` 分片,无此类分片时默认为 `{kind:'stop'}`。 +- **dsh-session:** 任意事件日志。不变式:`deriveMessages` 确定性;从 seed 回放结果一致;seq 严格单调递增;非消息事件不影响推导出的历史;推导出的内容与日志解耦。 +- **dsh-tools:** 任意 `ParameterSchemaSpec`。不变式:JSON Schema 的 `required` 等于每一层 `required:true` 的键集;转换对合法声明而言是全函数;**并且与[运行时参数校验](../architecture/2026-06-11-runtime-arg-validation.md)组合验证**——满足 spec 的生成参数通过 `validateArgs`,而定向破坏(删除必填键、顶层非对象)被拒绝。聚焦用例覆盖每种根值类型、恰好一项匹配中的分支重叠与无匹配、显式开放性、原始默认值以及有损 JSON。这封堵了编译器、validator 与 `InferArgs` 之间的漂移风险。 +- **dsh-agent-loop:** 任意发送调度,对接一个永不耗尽的适配器,通过 `agent/status` settle 信号驱动(无挂钟 sleep)。不变式:无消息丢失;轮次编号严格递增;状态转换保持在合法状态机上。 + +## 后果 + +- 生成器质量是价值杠杆——生成器偏向小索引池和短字符串,使碰撞与交错频繁发生。 +- **它已经带来回报:** BlockAssembler 流发现了一个真实 bug——同一索引处重复的 `block-end` 会改写已经完成的块。现已修复(首次关闭优先,与现有迟到项规则一致),并加入专用回归测试。 +- 属性测试因超时而 flake 是一个发现,不应通过重试消除。循环属性测试在设计上是确定性的(通过 `agent/status` settle),因此挂起即为真实缺陷。 +- 属性测试是对示例测试的补充而非替代;示例测试固定特定分支,服务于 100% 覆盖率门禁。 + +<!-- agent-note-format: alternatives-not-recorded (pre-format Agent Note) --> diff --git a/.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.i18n.yaml b/.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.i18n.yaml new file mode 100644 index 0000000000..15551560ba --- /dev/null +++ b/.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-19-acp-snapshot-tests.md: 43900632c4e5e3904c2d0e3b75f2a3fe3b3a50cc +2026-06-19-acp-snapshot-tests.zh.md: a4613b19001afe87c1f6bdb61196fabbfa947a4c diff --git a/.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.md b/.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.md index ebc48ba183..43900632c4 100644 --- a/.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.md +++ b/.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-06-19-acp-snapshot-tests.zh.md) + ## Problem Unit tests do not exercise the complete ACP subprocess transcript, while real-API tests are nondeterministic and key-gated. Editor-facing `session/update` output can therefore regress despite green unit coverage, as the [default-export postmortem](../../../../docs/postmortem/0001-acp-default-export-drops-inject.md) demonstrated. diff --git a/.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.zh.md b/.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.zh.md new file mode 100644 index 0000000000..a4613b1900 --- /dev/null +++ b/.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.zh.md @@ -0,0 +1,84 @@ +# Agent Note: ACP 快照测试——一次录制 / 确定性回放 + +Status: implemented + +[English](2026-06-19-acp-snapshot-tests.md) | 中文 + +## 问题 + +单元测试不会覆盖完整的 ACP(Agent Client Protocol)子进程 transcript(文本记录),而真实 API 测试不具确定性且受密钥门控。因此,即使单元覆盖率为绿色,面向编辑器的 `session/update` 输出仍可能回归,[默认导出事后分析](../../../../docs/postmortem/0001-acp-default-export-drops-inject.md)已经证明了这一点。 + +全 transcript 测试的阻塞因素在于模型:agent(智能体)的输出由非确定性的 LLM(大语言模型)驱动,而每次运行都命中真实 API 的密钥门控测试既不确定也无法在 CI 中运行。我们需要真实运行的保真度与 fixture(测试前置数据)的确定性兼得。 + +本 Agent Note(agent 决策记录)记下了新增第三层测试——**快照测试**——的决策,以及让它具备确定性、在 CI 中无需密钥、且维护成本低廉的设计选择。 + +## 决策 + +快照测试会启动真实 ACP 示例,通过确定性脚本驱动其 stdio 协议,并将规范化输出与已提交的预期输出比较。从真实 API 一次记录的会话日志为后续所有模型流提供数据。fixture 就是产品普通的持久化 JSONL。 + +### fixture 即持久化的会话 JSONL + +每个场景的 `session.jsonl` 都从真实运行中采集。`assistant/chunk` 事件复现模型流;工具、消息和边界事件捕获 harness 行为。因此,一份普通会话产物同时充当重放来源和行为预期输出。 + +当场景固定另一种物理存储布局时,其 fixture 会从真实的未打包对应项机械派生。场景测试要求包含每一种预期存储行类型,并在解码后逐事件精确相等;随后,普通重放与日志比较才会证明组合后的进程能够消费并复现该布局。 + +### 回放从日志推导模型脚本 + +`llm-replay` 短路了提供方无关的 `llm/stream` waterfall(瀑布式事件)。`deriveReplayScript()` 按 `(turn, step)` 对已录制的分片分组,每次模型调用服务一组。agent loop(智能体循环)每个步骤发起一次流调用,因此分组精确对应,错误结束分片也无需特殊处理。 + +### 内存中的回放条目遵守完整的 LLM 契约 + +`deriveReplayScript` 产出一组 `ReplayEntry`,即回放监听器按位置服务的内存单元: + +``` +{ kind: 'chunks', chunks: StreamChunk[] } +| { kind: 'throw', chunks: StreamChunk[], message: string, code: string } +| { kind: 'hang' } +``` + +日志推导出分片条目。流开始前的抛出和挂起没有可重建的分片表示,因此这些场景提供 `replay.override.json`。throw 条目可以包含前缀分片以模拟流中途失败。显式覆盖避免了从有损的轮次结束原因推断适配器行为。 + +### 位置式回放,单个在途流 + +回放是位置式的,因此每个场景只允许一个在途模型流。并发会话快照需要按请求键索引的条目。调用顺序变更需要重新录制,fixture 缺失或耗尽时立即报错。 + +### 录制采集日志;无密钥回放需要无提供方的配置 + +记录模式使用真实 `llm-deepseek` 适配器和配置为 `persistenceCompression: 'none'` 的 JSONL 持久化后端运行场景,再把生成的 `.jsonl` 复制到场景目录。显式 raw 模式让已提交重放 fixture 保持逐行可读,而普通部署使用后端的压缩默认值。逐事件追加具有持久性,但 harness 会在采集前优雅关闭子进程(关闭 stdin → `await ctx.dispose()`),以确保最终事件已刷出。`llm-replay` 本身不执行记录——它只负责重放。 + +重放使用 `cordis.snapshot.yml` overlay,以 `llm-replay` 替换真实适配器,同时保留实时组合。记录使用普通配置和由 harness 提供的持久化根目录。重放模式跳过 `.env` 加载,因此意外存在的 API 密钥不会触发实时调用。参见[单一来源配置 Agent Note](2026-07-04-single-source-acp-replay-config.md)。 + +### 两个表面:归一化后比对 + +快照运行断言**两个**归一化后的表面,因为 harness 的外部表面是不同的: + +1. **stdout transcript**——编辑器看到的、经过 framing 的 `session/update` JSON-RPC。用于捕获 ACP bridge 中事件→更新转换(`streamSessionEventUpdate`)的回归。与已提交的 `stdout.expected.jsonl` 比较。 +2. **重新持久化的会话 JSONL**,经过规范化后与 `session.jsonl` 比较。同一 fixture 同时作为重放来源和预期日志。提示词文本会被清理;按照[请求头固定 Agent Note](2026-07-06-pin-request-header-content-in-one-scenario.md)所述,每种请求头类别由一个场景固定可读提示词与工具内容。Override 场景仅从其 sidecar 派生模型行为。 + +两个表面互补:stdout 覆盖 bridge 投影,JSONL 覆盖投影所省略的 loop、工具和 boundary 结构。 + +规范化会替换会话、cwd、协议 id、时间戳、路径和进程易变值,同时保留确定性序号。场景把真实 bash 使用限制在稳定命令上。stdout 预期输出仍是线协议形状的 JSONL,每个原始行都必须可解析为 JSON。Vitest 只更新 stdout 预期输出;规范化会话相等性检查从不覆盖重放 fixture。 + +### 隔离:当前靠归一化,后续可加沙箱 + +工具确定性来自生成的 cwd、清理后的环境、全新的非登录 shell、受限命令和规范化。cwd 默认为平台临时目录;当临时目录是始终可写的策略根,而行为需要独立项目位置时,场景可以改为提供其父目录。并发重放运行各自拥有独立 cwd、持久化目录和由定长场景键区分的 spill 根目录,因此一个场景的拆除无法删除另一个场景仍在进行的完整输出恢复,同时真实路径预览预算保持稳定。该层不声称提供 OS 级隔离。如果需要更强层级,沙箱执行器可以通过现有[能力 seam](../architecture/2026-06-13-capability-seams.md)替换本地后端。 + +### 回放插件是独立的包 + +`@deepseek-ai/dsh-llm-replay` 是一个支撑包(package),而非示例本地的胶水代码。它通过用从 JSONL 重建的流短路 `llm/stream` 来替换真实适配器,其包级放置使回放逻辑处于正常覆盖率门禁之下。 + +### 两个子命令,回放在默认门禁中 + +`pnpm run test:snapshot` 无需密钥即可重放已提交 fixture;`test:snapshot:record` 使用真实 API,并重写采集的会话日志与 stdout 预期输出。缺少 fixture 时会响亮失败。每个场景都包含 `input.json`、`stdout.expected.jsonl` 和 `session.jsonl`;不调用模型的情况使用仅有请求头的日志。只有标记为 `overridden` 的场景才需要 `replay.override.json`,因为它一旦存在就会取代派生重放。Fixture 守卫会拒绝缺失、不匹配和孤立文件。两个命令都接受场景过滤器。 + +## 曾考虑的替代方案 + +- **手工编写包含模型分片的 `llm.json`**——早期草案;复用真实会话日志,使 fixture 成为系统的真实产物而非手工构建的 mock,并让它同时充当行为预期输出。 +- **字节级 HTTP 录制库(Polly/nock/MSW)**:否决。与适配器耦合,处理流式 SSE(Server-Sent Events)时笨拙,且层级低于被测对象。 +- **从 `turn/end {kind:'error'|'aborted'}` 合成抛错/取消条目**:否决。这会将 `llm-replay` 耦合到 loop 内部的轮次关闭语义,且 `turn/end` 原因是有损的(无法区分抛出的 401 与 finish-error);显式的 `replay.override.json` 伴随文件是更清晰的 seam。 + +## 后果 + +新测试层为每个场景增加经过评审的输入、会话、stdout、可选 override 和可选 workspace fixture。记录与重放都会把 workspace seed 复制到生成的 cwd。作为回报,该层通过真实 Loader 和工具组合提供确定性的无密钥 transcript 覆盖。子进程、输入、workspace、规范化和重放 harness 也可以支持 ACP 之外的示例。 + +本 Agent Note 与[拟议的确定性 Agent Note](../../proposed/testing/2026-06-11-deterministic-and-stress-testing.md)相关,但不取代它:该提案的“通用重放 fixture”在每次测试后重新派生会话*消息历史*(内部一致性不变量),而快照测试固定*外部协议输出*。两者相互补充——一个守护事件溯源不变量,另一个守护面向编辑器的契约。 diff --git a/.agents/notes/implemented/testing/2026-06-19-real-api-e2e-ci.i18n.yaml b/.agents/notes/implemented/testing/2026-06-19-real-api-e2e-ci.i18n.yaml new file mode 100644 index 0000000000..0ca80ac88b --- /dev/null +++ b/.agents/notes/implemented/testing/2026-06-19-real-api-e2e-ci.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-19-real-api-e2e-ci.md: a9289980ada8ab6390b5daa488f07ec258db1bd5 +2026-06-19-real-api-e2e-ci.zh.md: dcb5759d26e7680d392a4855665b2eb88551ba79 diff --git a/.agents/notes/implemented/testing/2026-06-19-real-api-e2e-ci.md b/.agents/notes/implemented/testing/2026-06-19-real-api-e2e-ci.md index 05da5152ff..a9289980ad 100644 --- a/.agents/notes/implemented/testing/2026-06-19-real-api-e2e-ci.md +++ b/.agents/notes/implemented/testing/2026-06-19-real-api-e2e-ci.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-06-19-real-api-e2e-ci.zh.md) + ## Problem The harness leans hard on real-API tests by policy: [docs/testing.md](../../../../docs/testing.md) argues that a no-key suite proves the plumbing but not the product, and the [ACP inject postmortem](../../../../docs/postmortem/0001-acp-default-export-drops-inject.md) is the standing proof — 178 keyless tests stayed green while a real editor session crashed instantly. The real-API e2e suite (`pnpm run test:e2e`, the `*.e2e.ts` files) exists precisely to close that gap: it drives the agent against the live DeepSeek API — real model calls, real bash tools, multi-turn, resume, ACP-over-stdio. diff --git a/.agents/notes/implemented/testing/2026-06-19-real-api-e2e-ci.zh.md b/.agents/notes/implemented/testing/2026-06-19-real-api-e2e-ci.zh.md new file mode 100644 index 0000000000..dcb5759d26 --- /dev/null +++ b/.agents/notes/implemented/testing/2026-06-19-real-api-e2e-ci.zh.md @@ -0,0 +1,102 @@ +# Agent Note: 在 CI 中对外部 DeepSeek API 运行真实 API e2e 测试 + +Status: implemented + +[English](2026-06-19-real-api-e2e-ci.md) | 中文 + +## 问题 + +根据策略,harness 高度依赖真实 API 测试:[docs/testing.md](../../../../docs/testing.md) 指出,无密钥套件证明的是管线,而非产品;[ACP(Agent Client Protocol)inject 事后分析](../../../../docs/postmortem/0001-acp-default-export-drops-inject.md)则是常设证据——178 项无密钥测试保持绿色时,真实编辑器会话却立即崩溃。真实 API e2e 套件(`pnpm run test:e2e`,即 `*.e2e.ts` 文件)的存在正是为了弥合这一缺口:它针对实时 DeepSeek API 驱动 agent(智能体)——真实模型调用、真实 bash 工具、多轮次、恢复、ACP-over-stdio。 + +默认门禁([.github/workflows/ci.yml](../../../../.github/workflows/ci.yml))刻意无密钥:不携带 secret,可供 fork 运行。`test:e2e` 在无密钥时自动跳过(`describe.skipIf(!process.env.DEEPSEEK_API_KEY)`),因此将其加入该工作流只会报绿而不会真正执行真实套件。要让真实 API 覆盖率成为合并信号,需要一个独立的、携带 secret 的工作流。 + +本 Agent Note(agent 决策记录)记下了新增**第二条消费 secret 的工作流**以在 CI 中运行真实 API 套件的决策;由于向未来可能公开的仓库引入第一个 CI secret 属于安全/隔离决策,本文也记录其依赖的威胁模型,以及仓库公开时需要做出的变更。 + +## 决策 + +添加一个专用工作流 [.github/workflows/e2e.yml](../../../../.github/workflows/e2e.yml),与 ci.yml 分离。它仅使用 repo secret 对外部 API 运行 `pnpm run test:e2e`,仅在可信事件上触发,并带有一个 preflight 检查:将缺失的 secret 转化为明确的失败而非虚假的绿色。无密钥工作流保持独立,使可 fork 的质量门禁与消费 secret 的真实 API 门禁各自拥有不同的触发和凭证策略。 + +### 独立工作流,而非 ci.yml 中的一个 job + +ci.yml 的价值在于它无密钥、可 fork、始终为绿:任何贡献者(包括外部 fork)都能获得完整的无密钥信号,secret 不在爆炸半径内。在其中添加消费 secret 的 job 会将这个始终为绿的门禁耦合到凭证可用性和不同的触发策略上。将携带 secret 的工作放在独立文件中,隔离了 secret、触发和并发策略,并为 fork 保留了 ci.yml 的特性。不同的生命周期→不同的文件。 + +### 约束不是成本,而是可靠性 + +内部推理成本不是限制因素,因此工作流针对覆盖面和信号优化。它会在多种触发条件和每个受信任 PR(Pull Request)上运行所有匹配的 `*.e2e.ts` 文件,以落实 [docs/testing.md](../../../../docs/testing.md) 的有密钥策略。 + +### 触发条件:仅限可信事件 + +`workflow_dispatch` + `push` 到 `main`/`master` + 每夜 `schedule`(`17 0 * * *`,即北京时间 08:17)+ `pull_request`。push 提供合并后信号;schedule 捕捉外部 API 漂移;dispatch 是手动逃生通道;可信 pull request 获得合并前门禁。该合并前信号有意接受 § 安全性中描述的更大密钥暴露面。 + +### 不可信 PR 的门禁 + +GitHub 对两类 PR 扣留 repo secret:来自 **fork** 的 PR,以及 **Dependabot** PR(同仓库分支,`head.repo.fork == false`,但 secret 仍被扣留)。一个 job 级 `if:` 对两者都跳过整个 job: + +``` +github.event_name != 'pull_request' + || !(github.event.pull_request.head.repo.fork || github.event.pull_request.user.login == 'dependabot[bot]') +``` + +Dependabot 子句基于 PR **作者**(`pull_request.user.login`)而非 `github.actor`(运行触发者):维护者重新打开或重跑 Dependabot PR 时,`github.actor` 会变成人类,但该 PR 仍然无密钥;基于作者的判断在这种情况下依然正确。被 **job 级** `if:` 跳过的 job 报告为*成功*检查(不同于工作流/触发级跳过会保持 pending),因此如果需要将此工作流标记为 required status check 也是安全的——fork/Dependabot PR 的跳过但绿色的检查不会阻塞合并。 + +该门禁是一个*干净跳过的便利措施*,而非 secret 的安全边界(见 § 安全性——边界是 GitHub 自身在 `pull_request` 下对 fork 的 secret 扣留机制)。没有该门禁,fork 仍然无法读取密钥;只是会遇到令人困惑的 preflight 硬失败并浪费计算资源。 + +### Preflight:大声失败,绝不虚假为绿 + +由于 job 仅在 secret 应当存在的可信事件上运行,preflight 是一个无条件的存在性检查:密钥为空→`exit 1` 并附带 `::error::` 注解指明需要配置的 secret 名称。这是让自跳过套件可以安全地作为门禁的关键。没有它,被删除/重命名/错误配置的 secret 会让 `test:e2e` 跳过所有真实套件并报告全绿——整个安全网的静默退化。该守卫将「secret 缺失」从不可见的虚假通过转化为可见的失败。(其正确性已在实际中验证:secret 存在之前的运行恰好在此步骤失败。) + +### Secret 映射与卫生 + +repo secret 命名为 `DEEPSEEK_API_KEY_EXTERNAL`;映射到适配器和测试读取的 `DEEPSEEK_API_KEY` 环境变量(`process.env.DEEPSEEK_API_KEY`)。独立的 secret 名称记录了意图(这是*外部*公开 API 密钥,不是内部端点密钥),并允许内部端点密钥日后无冲突地共存。以下卫生选择均为防御性设计: + +- **步骤级 secret。** `DEEPSEEK_API_KEY` 仅在 preflight 和 e2e 步骤的 `env:` 中设置,从不在 job 级设置——因此 checkout/setup-node/install 永远看不到它。依赖中被入侵的安装时生命周期脚本无法读取不在其环境中的 secret。 +- **`permissions: contents: read`。** job 仅读取仓库以运行测试;不需要写权限(无 PR 评论、无 status 写入),因此 `GITHUB_TOKEN` 降至最小权限。 +- **`DEEPSEEK_BASE_URL` 固定**为 e2e 步骤上的 `https://api.deepseek.com`。适配器在未设置时会默认使用此值([packages/llm/llm-deepseek/src/index.ts](../../../../packages/llm/llm-deepseek/src/index.ts) `PUBLIC_BASE_URL`),但显式固定具有自文档性和密封性——仓库根目录的 `.env`(`vitest.e2e.config.ts` 存在时会加载)无法静默地将运行重定向到其他端点。 +- **不回显 secret。** preflight 仅打印 `DEEPSEEK_API_KEY present.`——不打印值或长度。 + +### 范围与运行时形态 + +job 仅在 Node 24 上运行 `test:e2e`;无密钥门禁和版本兼容性属于主 CI 工作流。测试通过 workspace paths 映射以未构建形式运行,使用有界的可配置 worker 池、逐测试重试和 job 超时。被取代的 PR 运行会被取消,而 push 和 schedule 运行完整执行以提供合并后信号。 + +DeepSeek 原生 `web_search` 探测已注册但会跳过。实时 Anthropic 兼容端点可能返回成功响应却没有结构化来源块,因此对来源存在性的正向断言不是可靠的合并信号;单元覆盖率仍会固定响应解析,但 CI 不会证明实时来源块的线协议形状。 + +## 安全性 + +仓库的首个 CI secret 需要一份记录在案的威胁模型,因为同仓库 PR、fork PR 和 Dependabot PR 的访问权限各不相同,且仓库公开后会发生变化。 + +### 当前谁能触及 secret(私有仓库) + +- **无写权限(fork PR):不能。** 两个独立事实阻止了它。第一,工作流使用 `pull_request` 而**非** `pull_request_target`——GitHub 不会将 repo secret 传递给 fork PR 的 `pull_request` 运行,因此 `secrets.DEEPSEEK_API_KEY_EXTERNAL` 在 fork runner 上解析为空。第二,`if:` 门禁完全跳过 fork PR。secret 扣留是真正的边界;门禁是纵深防御和用户体验。 +- **有写(push)权限:能。** 同仓库分支 PR 会收到 secret,因此有写权限的作者可以修改测试代码(或安装生命周期脚本,或其分支上的工作流 YAML)来窃取密钥。这**是 GitHub Actions 的固有特性,并非本文引入的**:任何对任何仓库有 push 权限的人都可以通过编写工作流来窃取该仓库的任何 Actions secret。写权限⇒secret 访问权,始终如此。缓解措施在于谁被授予写权限以及分支保护,而非本文件。 + +因此「任何能开 PR 的人都能窃取它」是错误的:只有写权限集合内的人能,而这些人本来就能窃取仓库持有的任何 secret。 + +### `pull_request` 触发器增加的残余暴露面 + +由于启用了 PR 运行,密钥会在合并前被交给**写权限作者 PR 分支上的代码**。这比 `push` + `schedule` + `workflow_dispatch` 的暴露面更大,为在可信写权限集合内获得合并前信号而接受。如果这一权衡发生变化,可移除 `pull_request` 触发器,同时保留合并后、每夜和按需覆盖。 + +### 仓库公开后的变化 + +**通过本工作流**,secret 对公众仍然受保护:`pull_request` 在公开仓库上行为一致——fork PR(现在任何人都能开)仍然收不到 secret,且在公开仓库上 GitHub 额外要求维护者批准 fork PR 运行,即使批准后运行也不会获得 secret(批准运行不等于交出密钥)。写权限集合不因可见性改变而改变,因此内部人员的现实也不变。 + +变差的是*周边*模型,以下是翻转可见性之前需要处理的事项: + +- **日志变为全球可读。** 今天泄露给组织成员的粗心 secret 回显,公开后会泄露给整个互联网并在数分钟内被爬取。secret 处理纪律(不回显值/长度——已做到)的重要性大幅提升。 +- **`pull_request_target` 陷阱变为灾难性的。** 如果有人为了「修复」PR 运行而将触发器切换为 `pull_request_target`,工作流将在 base-repo 上下文中运行不可信的 fork 代码并**携带** secret——完整的密钥泄露向量。在私有仓库中这勉强无害,在公开仓库中则是灾难。e2e.yml 中触发器上的 `SECURITY —` 注释禁止此更改并指向本文。 +- **翻转时轮换密钥。** 密钥曾存在于私有仓库的 CI 中;将公开视为「假定已暴露」,在那一刻轮换 `DEEPSEEK_API_KEY_EXTERNAL`。 +- **将 secret 置于控制之下。** 确认 Settings → Actions → *"Send secrets to workflows from fork pull requests"* 保持**关闭**(这是唯一真正会打破 fork 边界的设置),并考虑将密钥移入带有 required reviewers 的 GitHub **Environment**,使即使已合并的代码也只在受控条件下使用它,且轮换有单一归属。 + +以上均不需要修改工作流即可公开;它们是运维步骤加上已添加的 `pull_request_target` 守卫注释。 + +## 曾考虑的替代方案 + +- **在 ci.yml 中添加消费 secret 的 job**:否决。会将无密钥、可 fork、始终为绿的门禁耦合到凭证可用性和不同的触发/并发策略上;不同的生命周期,不同的文件。 +- **省略 `pull_request` 触发器**(更小的密钥暴露面):为获得合并前信号而否决;安全性章节承载了已接受的暴露分析。 + +## 后果 + +新增一个 CI 工作流和仓库的首个需要维护的 secret。真实 API 套件现在作为合并门禁(可信 PR 上的合并前门禁、主分支上的合并后门禁)并每夜运行,因此 agent 与外部 API 交互中的真实故障会在 CI 中浮现,而非仅在开发者的本地运行中出现——代价是每个可信 PR 和合并都会产生真实的(但内部免费的)API 调用。preflight 使 secret 配置错误变为自我通告而非静默禁用安全网。 + +该设计带有已记录的约束表面:`pull_request` 触发器在密钥暴露方面的取舍(删除它可加强防护)、`if:` 门禁对基于作者的 Dependabot 检查的依赖,以及对 `pull_request_target` 的严格禁止。上方公开仓库检查清单是操作配套——未来维护者在更改触发器集合或切换仓库可见性之前,应重新阅读本 Agent Note,而不是从头推导 fork/secret 模型。 + +schedule 触发器在仓库不活跃 60 天后会自动禁用(GitHub 行为);push/PR/dispatch 是后备,活跃的 monorepo 不会触及此限制。假设 runner 对 `https://api.deepseek.com` 有出站连通性——GitHub 托管的 `ubuntu-latest` 具备此条件;受出站限制的自托管 runner 需要在依赖每夜运行之前确认连通性。 diff --git a/.agents/notes/implemented/testing/2026-06-20-remove-redundant-snapshot-log-expected-output.i18n.yaml b/.agents/notes/implemented/testing/2026-06-20-remove-redundant-snapshot-log-expected-output.i18n.yaml new file mode 100644 index 0000000000..9ea114c43e --- /dev/null +++ b/.agents/notes/implemented/testing/2026-06-20-remove-redundant-snapshot-log-expected-output.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-20-remove-redundant-snapshot-log-expected-output.md: c2452f971d3cb76dceb766072dbc0a5c81465e78 +2026-06-20-remove-redundant-snapshot-log-expected-output.zh.md: e6175181589eabae064c34044f353efae537961b diff --git a/.agents/notes/implemented/testing/2026-06-20-remove-redundant-snapshot-log-expected-output.md b/.agents/notes/implemented/testing/2026-06-20-remove-redundant-snapshot-log-expected-output.md index b17ecad098..c2452f971d 100644 --- a/.agents/notes/implemented/testing/2026-06-20-remove-redundant-snapshot-log-expected-output.md +++ b/.agents/notes/implemented/testing/2026-06-20-remove-redundant-snapshot-log-expected-output.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-06-20-remove-redundant-snapshot-log-expected-output.zh.md) + ## Problem Model-driving ACP snapshot scenarios ship both `session.jsonl` and `session.expected.jsonl`. For normal recorded scenarios, `session.jsonl` is the replay fixture harvested from a real run, and the replay test normalizes the newly persisted log and compares it to `session.expected.jsonl`. In the current fixtures, the two normalized logs are identical for ordinary recorded scenarios. diff --git a/.agents/notes/implemented/testing/2026-06-20-remove-redundant-snapshot-log-expected-output.zh.md b/.agents/notes/implemented/testing/2026-06-20-remove-redundant-snapshot-log-expected-output.zh.md new file mode 100644 index 0000000000..e617518158 --- /dev/null +++ b/.agents/notes/implemented/testing/2026-06-20-remove-redundant-snapshot-log-expected-output.zh.md @@ -0,0 +1,37 @@ +# Agent Note: 使用 `session.jsonl` 作为唯一的快照会话日志产物 + +Status: implemented + +[English](2026-06-20-remove-redundant-snapshot-log-expected-output.md) | 中文 + +## 问题 + +驱动模型的 ACP(Agent Client Protocol)快照场景同时包含 `session.jsonl` 和 `session.expected.jsonl`。对于普通记录场景,`session.jsonl` 是从真实运行采集的重放 fixture(测试前置数据);重放测试会规范化新持久化的日志,并将其与 `session.expected.jsonl` 比较。在当前 fixture 中,普通记录场景的两份规范化日志完全相同。 + +手工编写的 override 场景(`error-finish`、`cancel`)目前使用 `replay.override.json` 驱动模型行为,并把 `session.jsonl` 保留为最小 dummy fixture,而 `session.expected.jsonl` 存放预期的持久化日志。override 文件是由 `ReplayEntry` 对象组成的 JSON 数组:`{ "kind": "chunks", "chunks": StreamChunk[] }`、`{ "kind": "throw", "chunks": StreamChunk[], "message": string, "code": string }` 或 `{ "kind": "hang" }`。这种拆分同样没有必要:override sidecar 存在时,`llm-replay` 会替换派生脚本,不需要从 `session.jsonl` 取得模型分片,因此 `session.jsonl` 仍可作为场景的预期会话日志产物。 + +## 决策 + +彻底移除 `session.expected.jsonl` 概念。每个场景最多只有一个已提交会话日志产物,即 `session.jsonl`: + +- 对于录制场景,`session.jsonl` 仍是原始采集的日志。回放仍从中派生模型分片,快照测试将回放运行归一化后的持久化日志与归一化后的 `session.jsonl` 进行比较。 +- 对于手工编写的覆盖场景,`replay.override.json` 驱动模型行为,`session.jsonl` 存放预期产出的会话日志。当覆盖文件存在时,回放适配器不从 fixture 获取模型分片,因此同一个文件既可作为预期日志,又不影响回放行为。 +- 对于无模型场景,`session.jsonl` 可保留为引导 `llm-replay` 所需的最小 fixture;除非场景创建了持久化会话,否则无需进行会话日志比较。 + +Stdout 预期输出保持不变;它们是面向编辑器的投影,与会话 fixture 并不重复。 + +## 曾考虑的替代方案 + +**对两侧基于共享的(回放运行)上下文做归一化**:否决。`normalizeSessionLog` 通过精确字符串匹配擦除 cwd,因此 fixture 中录制的 cwd 不会被擦除,每次比较都会失败。两侧各自基于自身 header 派生的上下文做归一化——下方的实现说明描述了具体机制。 + +## 验证 + +快照 harness、fixture、孤立项守卫和文档中都不再出现 `session.expected.jsonl`;对于每个模型场景,快照测试都从 `session.jsonl` 派生预期会话日志;手工编写 sidecar 的场景把预期生成日志提交为 `session.jsonl`,并以 `replay.override.json` 覆盖模型行为;孤立 fixture 守卫知道每种场景类型所需的文件。[ACP 快照测试 Agent Note(agent 决策记录)](2026-06-19-acp-snapshot-tests.md)描述了精简后的 fixture 集合。 + +## 后果 + +评审者失去了一个能在视觉上区分预期持久化日志与重放 fixture 的产物名。stdout 预期输出仍然保护编辑器 transcript(文本记录),而将重放输出与 `session.jsonl` 比较,无需复制文件即可保留循环/持久化回归检查。 + +## 实现说明 + +两侧各自基于自身 header 值做归一化,因为录制与回放具有不同的 id、路径和时间戳。`fixtureContext()` 从 fixture 的 header 派生上下文,使已归一化的 fixture 具有幂等性。会话日志使用普通相等比较而非文件快照更新,因此比较过程不会改写 fixture。 diff --git a/.agents/notes/implemented/testing/2026-06-22-fork-child-replay-seed-boundary.i18n.yaml b/.agents/notes/implemented/testing/2026-06-22-fork-child-replay-seed-boundary.i18n.yaml new file mode 100644 index 0000000000..822fc921b4 --- /dev/null +++ b/.agents/notes/implemented/testing/2026-06-22-fork-child-replay-seed-boundary.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-22-fork-child-replay-seed-boundary.md: d3cbbb1dae1d64a10973bd5895ccc47d877eba28 +2026-06-22-fork-child-replay-seed-boundary.zh.md: a944538b9dcb74eb15142593089c7905efc3f565 diff --git a/.agents/notes/implemented/testing/2026-06-22-fork-child-replay-seed-boundary.md b/.agents/notes/implemented/testing/2026-06-22-fork-child-replay-seed-boundary.md index 93280ed62e..d3cbbb1dae 100644 --- a/.agents/notes/implemented/testing/2026-06-22-fork-child-replay-seed-boundary.md +++ b/.agents/notes/implemented/testing/2026-06-22-fork-child-replay-seed-boundary.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-06-22-fork-child-replay-seed-boundary.zh.md) + ## Problem The [per-session snapshot replay Agent Note](2026-06-22-subagent-snapshot-replay.md) made the snapshot tier express a nested-agent shape: a parent plus one recorded log per in-process subagent, each replayed as its own script keyed by calling session. It noted (§ Scope, final bullet) that a fork snapshot was "a trivial future addition, not a gap in the keying." That was wrong about a fork child specifically — not the keying, but the *script derivation*. diff --git a/.agents/notes/implemented/testing/2026-06-22-fork-child-replay-seed-boundary.zh.md b/.agents/notes/implemented/testing/2026-06-22-fork-child-replay-seed-boundary.zh.md new file mode 100644 index 0000000000..a944538b9d --- /dev/null +++ b/.agents/notes/implemented/testing/2026-06-22-fork-child-replay-seed-boundary.zh.md @@ -0,0 +1,49 @@ +# Agent Note: 持久化 seed 边界以确保 fork 子会话回放正确路由 + +Status: implemented + +[English](2026-06-22-fork-child-replay-seed-boundary.md) | 中文 + +## 问题 + +[逐会话快照重放 Agent Note(agent 决策记录)](2026-06-22-subagent-snapshot-replay.md)使快照层能够表达嵌套 agent 形状:一个父项加上每个进程内 subagent 的一份记录日志,每份日志都按调用会话作为键,以独立脚本重放。它曾指出(§ 范围,最后一个项目符号),fork 快照“只是未来很容易添加的一项,并非键控缺口”。这一判断对 fork 子项而言是错误的——问题不在键控,而在*脚本派生*。 + +subagent 脚本由 [`deriveReplayScript`](../../../../packages/support/llm-replay) 从已录制的会话日志推导:它按 `(turn, step)` 对日志中的 `assistant/chunk` 事件分组,每次 `stream()` 调用对应一条回放条目。对 **spawn** 子会话而言这是正确的,因为其日志只包含自身的模型调用。 + +**fork** 子会话不同。fork 后端用*父日志的一段平衡的已完成轮次前缀*([`dsh-subagent-inprocess`](../../../../packages/subagent/subagent-inprocess))来播种子会话,而该 seed 会成为子会话持久化的 `log`(`Session` 构造函数将 seed 复制进 `this.log`)。因此 fork 子会话的 `.jsonl` 以**父会话**的事件开头——包括父会话的 `assistant/chunk` 事件——之后才是子会话自身的轮次。 + +从 fork 子会话的完整日志推导脚本,会把**父会话**的已录制响应当作**子会话**的模型调用来回放:实际运行的 fork 子会话第一次调用 `stream()` 时,会收到父会话的第一段分片序列而非自身的。目前已录制的场景全部是 spawn,所以这从未触发——但 fork 快照会静默地错误路由,恰好属于快照层存在的意义所要捕获的那类 bug。 + +## 决策 + +记录会话**继承**前缀的结束位置,将其持久化,并让回放 harness 仅从子会话**自身**的事件推导脚本。 + +### 1. 会话头部的 `seedLength` + +`SessionHeader` 新增可选字段 `seedLength: number`——表示有多少前导事件是通过 seed 继承而来、而非本会话产生的。fork 后端在创建子会话时设置它(= 播种前缀的长度);全新的 spawn 子会话不设置(等同于 0)。它通过 `CreateSessionOptions.meta`(及 `CreateAgentOptions.meta`)传递,在 `SessionStore.prepare` 中设置。 + +`seedLength` 是**显式**的,绝不从 `seed.length` 推断。恢复/加载时用会话的完整已存储日志作为 seed,此时 `seed.length` 是全长而非原始边界——恢复路径改为从加载的 header 中取回持久化的 `seedLength`。(形状与 `createdAt` 相同:恢复时显式保留,而非重新默认为当前时间。) + +### 2. 两个持久化后端均完整往返 + +- **JSONL**:header 行上的 `seedLength` 字段(`toHeaderLine`/`fromHeaderLine`)。 +- **SQLite**:`sessions` 表上的 `seed_length` 列。 + +包含 `seed_length`、`source_event_seqs` 和 `surface_op` 的 SQLite 布局为 schema version 4。更早的 version 3 布局存在歧义,因此在预发布策略下,所有非当前 `user_version` 均直接拒绝,不做迁移。 + +### 3. 回放从边界之后推导子会话脚本 + +`dsh-llm-replay` 的 `parseSessionHeader` 现在也读取 `seedLength`(缺失则为 0),`loadSessionScripts` 从 `parseSessionLog(text).slice(seedLength)` 推导子会话条目——即边界及之后的事件,也就是子会话自身的模型调用。对 spawn 子会话而言 `seedLength` 为 0,此操作是空操作,spawn 场景逐字节不变。 + +这关闭了路由正确性的缺口,两个已录制的 fork 场景对其进行端到端验证——见[记录 fork 与混合 spawn+fork 快照场景](2026-06-22-fork-snapshot-scenarios.md)。 + +## 曾考虑的替代方案 + +- **在 `llm-replay` 中启发式推导边界**(播种前缀是连续的父事件,止于子会话第一条 `user/message` 之前的最后一个 `turn/end`)。否决:在测试 harness 中用脆弱的启发式重新推导一个生产者已经知道的事实。在源头(fork 后端)持久化边界,是「在包(package)seam 处显式优于隐式」这条规则跨越持久化边界的应用——子会话 fixture(测试前置数据)的读取者永远不需要重建继承在哪里结束。 +- **固定格式版本而不递增**(事件日志使用的 `SESSION_FORMAT_VERSION = 0`「不稳定」姿态)。对 SQLite *表*布局否决:`SCHEMA_VERSION` 是单调递增并拒绝旧版的旋钮(一组小的、值得区分的修订),与事件词汇表的 `version` 不同。新增列正是它所版本化的那种破坏性表变更,因此需要递增。 + +## 后果 + +- core 与两个后端新增一个持久化 header 字段;核心数据结构目录(`persistence.md`)在同一变更中更新(其 `SessionHeader` / `CreateSessionOptions` 的 `type-equiv` 块)。 +- 既有的 schema v2 SQLite 数据库在打开时被拒绝(预发布阶段无用户数据)。 +- spawn 回放不变(`seedLength` 为 0)。fork 回放现在将子会话路由到自身的脚本;由 `llm-replay` 测试中的一个回归用例覆盖(一个子会话 fixture,其播种前缀包含父会话的分片——推导出的子会话脚本必须排除它,不做 slice 时该用例为红)以及一个持久化往返测试(两个后端,通过共享的 coordinator 契约)。 diff --git a/.agents/notes/implemented/testing/2026-06-22-fork-snapshot-scenarios.i18n.yaml b/.agents/notes/implemented/testing/2026-06-22-fork-snapshot-scenarios.i18n.yaml new file mode 100644 index 0000000000..2e87edf31e --- /dev/null +++ b/.agents/notes/implemented/testing/2026-06-22-fork-snapshot-scenarios.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-22-fork-snapshot-scenarios.md: 46c688a4095a1d8af32b3b99887929f71a1526ce +2026-06-22-fork-snapshot-scenarios.zh.md: 8823611ec02f269e5a21a8065c9ed3cc3911f749 diff --git a/.agents/notes/implemented/testing/2026-06-22-fork-snapshot-scenarios.md b/.agents/notes/implemented/testing/2026-06-22-fork-snapshot-scenarios.md index 272e62ba77..46c688a409 100644 --- a/.agents/notes/implemented/testing/2026-06-22-fork-snapshot-scenarios.md +++ b/.agents/notes/implemented/testing/2026-06-22-fork-snapshot-scenarios.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-06-22-fork-snapshot-scenarios.zh.md) + ## Problem The [seed-boundary Agent Note](2026-06-22-fork-child-replay-seed-boundary.md) made fork-child replay route correctly: `dsh-llm-replay` derives a child's script from the events at or after its persisted `seedLength` boundary, so a fork child's inherited parent prefix is not replayed as the child's own model calls. But it shipped with **no recorded fork scenario** — the slice was exercised only by `llm-replay`'s unit tests (a synthetic child fixture) and a persistence round-trip test. The full-transcript snapshot tier, the one net that boots the real `acp-agent` and replays an end-to-end nested transcript, had only spawn children (`subagent-spawn`, `subagent-multi`). A fork-routing regression that left the unit tests green would still have escaped the tier built to catch transcript regressions. diff --git a/.agents/notes/implemented/testing/2026-06-22-fork-snapshot-scenarios.zh.md b/.agents/notes/implemented/testing/2026-06-22-fork-snapshot-scenarios.zh.md new file mode 100644 index 0000000000..8823611ec0 --- /dev/null +++ b/.agents/notes/implemented/testing/2026-06-22-fork-snapshot-scenarios.zh.md @@ -0,0 +1,31 @@ +# Agent Note: 记录 fork 与混合 spawn+fork 快照场景 + +Status: implemented + +[English](2026-06-22-fork-snapshot-scenarios.md) | 中文 + +## 问题 + +[seed 边界 Agent Note(agent 决策记录)](2026-06-22-fork-child-replay-seed-boundary.md)让 fork 子项重放能够正确路由:`dsh-llm-replay` 根据持久化 `seedLength` 边界处及其后的事件派生子项脚本,因此 fork 子项继承的父前缀不会作为子项自身的模型调用重放。但落地时**没有记录式 fork 场景**——slice 只由 `llm-replay` 单元测试(合成子项 fixture(测试前置数据))和持久化往返测试覆盖。完整 transcript(文本记录)快照层——会启动真实 `acp-agent` 并重放端到端嵌套 transcript 的那张网——只有 spawn 子项(`subagent-spawn`、`subagent-multi`)。如果 fork 路由回归没有让单元测试变红,它仍会逃过专为捕获 transcript 回归而构建的这一层。 + +表达 fork 场景所需的快照基础设施已经就位:两个进程内后端都在 `cordis.yml` / `cordis.snapshot.yml` 中以两个面向模型的工具接入(`subagent` → spawn、`subagent_fork` → fork),harness 会收集每个子会话的日志,回放按 `seedLength` 为键转发各子会话的 fixture。缺少的是一个*已记录的场景*来驱动 fork 子会话走完这条路径。 + +## 决策 + +针对真实 API 记录两个场景,均在默认门禁中以无密钥方式回放: + +- **`subagent-fork`**:父会话完成一个轮次以建立一个事实,然后通过 `subagent_fork` 委派一个子任务。fork 子会话继承对话(其日志携带非零 `seedLength`),因此可以从父会话的上下文中作答。这是聚焦的回归守卫:子会话 fixture 的 `seedLength` 就是回放切片所依赖的边界,来自真实 fork 的记录而非手工合成。 +- **`subagent-mixed`**——父项完成一个轮次,随后在同一 transcript 中通过 `subagent` 委托一次(全新 spawn 子项,`seedLength` 为 0),再通过 `subagent_fork` 委托一次(fork 子项,`seedLength` 非零)。这是 seed 边界与逐会话重放 Agent Note 都点名作为未来新增项的 spawn+fork 混合场景:一份 transcript 覆盖两种传输方式和 slice 的两个分支(`seedLength` 为 0 = 无操作,`seedLength > 0` = 裁剪继承前缀),两个子项按 `createdAt` 排列为先 spawn、后 fork。 + +### 为什么需要一个已完成的第一轮次 + +fork 后端使用父项的**已配平完整轮次前缀**为子项提供 seed。父项若在第一个轮次就执行 fork,没有已完成轮次可供继承,因此 seed 为空(≡ 全新 spawn,`seedLength` 为 0)——这不会覆盖 slice。因此,两个场景都使用双提示词输入:第一个提示词完成一个轮次(建立稍后要求子项回忆的 codeword),第二个提示词委托 fork。子项 transcript 中回忆出的 codeword 只是模型行为的附带结果;承载关键约束的产物是子项 fixture 中记录、由重放 slice 消费的 `seedLength`。 + +## 后果 + +- fork 路由切片现在由全 transcript 层守卫,而不仅仅是单元测试。移除 `slice(seedLength)`(回放整个子会话日志)会让**两个**新场景变红——fork 子会话收到的是父会话记录的分片而非自己的——证明守卫确实生效(场景落地时已验证红→绿)。 +- `subagent-mixed` 是第一个在同一个 transcript 中驱动两种*不同* subagent 后端的快照场景,同时覆盖了跨 spawn 和 fork 子会话的逐会话回放键控。 +- 进程外(ACP(Agent Client Protocol))subagent 回放形态不同(每个子会话是独立进程、有自己的回放),仍以 `TODO(acp-subagent-replay)` 跟踪——本文场景仅限进程内。 +- 重新录制(`pnpm run test:snapshot:record`)会从真实 API 重新生成全部四个 fork/spawn fixture;两个新场景在无密钥时自动跳过,与所有已录制场景一致。 + +<!-- agent-note-format: alternatives-not-recorded (pre-format Agent Note) --> diff --git a/.agents/notes/implemented/testing/2026-06-22-subagent-snapshot-replay.i18n.yaml b/.agents/notes/implemented/testing/2026-06-22-subagent-snapshot-replay.i18n.yaml new file mode 100644 index 0000000000..379054599b --- /dev/null +++ b/.agents/notes/implemented/testing/2026-06-22-subagent-snapshot-replay.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-22-subagent-snapshot-replay.md: 4aad8b6ddd3e4f8b8ad5565e10b263953d81ea31 +2026-06-22-subagent-snapshot-replay.zh.md: 96890bc98a64357d9785b8081c8ba123bb3c716e diff --git a/.agents/notes/implemented/testing/2026-06-22-subagent-snapshot-replay.md b/.agents/notes/implemented/testing/2026-06-22-subagent-snapshot-replay.md index d21a081f9b..4aad8b6ddd 100644 --- a/.agents/notes/implemented/testing/2026-06-22-subagent-snapshot-replay.md +++ b/.agents/notes/implemented/testing/2026-06-22-subagent-snapshot-replay.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-06-22-subagent-snapshot-replay.zh.md) + ## Problem The snapshot tier (`pnpm run test:snapshot`) boots the real `acp-agent` subprocess, replays a recorded session through [`dsh-llm-replay`](../../../../packages/support/llm-replay), and diffs the normalized stdout transcript + re-persisted session log against committed expected outputs. It is the only tier that exercises the full editor-facing transcript end to end. diff --git a/.agents/notes/implemented/testing/2026-06-22-subagent-snapshot-replay.zh.md b/.agents/notes/implemented/testing/2026-06-22-subagent-snapshot-replay.zh.md new file mode 100644 index 0000000000..96890bc98a --- /dev/null +++ b/.agents/notes/implemented/testing/2026-06-22-subagent-snapshot-replay.zh.md @@ -0,0 +1,58 @@ +# Agent Note: 嵌套 agent 的逐会话快照回放 + +Status: implemented + +[English](2026-06-22-subagent-snapshot-replay.md) | 中文 + +## 问题 + +快照层(`pnpm run test:snapshot`)会启动真实 `acp-agent` 子进程,通过 [`dsh-llm-replay`](../../../../packages/support/llm-replay) 重放已记录会话,并将规范化 stdout transcript(文本记录)+ 重新持久化的会话日志与已提交预期输出进行 diff。它是唯一端到端覆盖完整面向编辑器 transcript 的测试层。 + +该层最初为每个进程只有一个会话而构建,这一假设硬编码在两处: + +- **`dsh-llm-replay` 没有做任何键控。** 它用一个全局游标,将第 N 次 `llm/stream` 调用对应到单一录制序列的第 N 条。当父 agent(智能体)和一个进程内 subagent 在同一个上下文上同时流式输出时,调用交错,单一游标会把子 agent 的脚本发给父 agent(反之亦然)。 +- **harness 只收集一份日志。** `findSessionLog` 遍历 sessions 根目录,返回找到的第一个 `.jsonl`。subagent 作为第二个 `Session` 运行,在同一个 cwd bucket 下有自己的日志,因此子 agent 的 transcript 被静默丢弃。 + +这就是 [subagent seam Agent Note(agent 决策记录)](../feature/2026-06-21-subagent-capability-seam.md)中通过 `TODO(subagent-snapshots)` 推迟的工作:进程内后端(PR2)落地时已有单元 + e2e 覆盖,但在这套基础设施落地前,完整 transcript 快照层无法表达嵌套 agent 形状。本 Agent Note 就是该堆叠式后续工作。 + +## 决策 + +回放按**调用方会话**键控,harness 收集**所有**会话日志。 + +### 1. 调用方会话 id 附着在模型请求上 + +`GenerateOptions` 新增可选字段 `sessionId`,在请求组装时从 `agent.session.id` 赋值。适配器忽略它;`llm/stream` 监听器用它按发起会话路由。其类型为 `Branded<'SessionId'>`(来自 `dsh-brand`)而非 `dsh-session` 的 `SessionId`,因为后者所在包(package)导入了 `dsh-llm` 的 `Message`,反向导入会形成循环。两个类型等价,因此会话 id 赋值无需类型转换。将 brand 移到一个专用 ids 包属于独立工作,因为它会影响所有 id 导入。 + +### 2. 回放按首次调用顺序将活跃会话绑定到录制脚本 + +嵌套场景录制多份日志:父会话(`session.jsonl`)加每个 subagent 子会话各一份(`session.1.jsonl`……)。`dsh-llm-replay` 全部加载,为每个录制会话派生一份脚本,并按 header 中的 `createdAt` 排序(父会话先于子会话创建)。 + +活跃会话 id 每次运行都是全新随机值,永远不等于录制时的 id,因此活跃会话无法通过 id 相等绑定到脚本。取而代之的是**首次调用顺序**绑定:第一个发起任何模型调用的活跃会话认领第一份有序脚本(即父会话:`createdAt` 最早,且必然最先流式输出,因为它必须先运行一个轮次才能委派),下一个新活跃会话认领下一份脚本,依此类推。此后每个会话独立推进自己的游标。 + +这种方式按谁在调用键控,而非按全局调用顺序。因此即使 subagent 将来并发或在后台运行(全局游标会导致交错),它仍然正确。不携带 `sessionId` 的调用(直接在单元测试中调用 `stream()`)被视为一个匿名会话、绑定到主脚本,因此单会话路径与旧行为逐字节一致。活跃会话数多于录制脚本数时会快速失败报错(出现了未录制的 subagent),绝不会静默错误路由。 + +子 fixture(测试前置数据)按 `createdAt` 排序,在兄弟会话严格顺序执行时与调用顺序一致。id 平局打破仅使退化碰撞具有确定性。并发或后台子会话必须引入显式的首次调用序号,而非依赖时间戳。 + +## 曾考虑的替代方案 + +曾考虑但否决的方案是:**将父子日志按调用顺序合并**为一份全局脚本(仅在进程内 subagent 执行严格嵌套——父 agent 阻塞等待子 agent——时才正确)。对当前的同步裁剪而言更简单,但将「父阻塞于子」这一不变式固化了进去;未来若引入后台/并发 subagent 就会失效。逐会话键控则不会。 + +### 3. harness 收集所有日志,主会话优先 + +`harvestSessionLogs` 收集 sessions 根目录下每个 cwd bucket 中的所有 `.jsonl`(JSONL 后端将父会话与同 cwd 的子会话放在同一个 bucket),解析各自的 header,并按主会话优先排序:顶层会话(无 `parentSession`)在前,各子会话按 `createdAt` 升序排列。`RunResult.sessionLogs` 是复数结果;spec 在录制时将每份日志写回对应 fixture(`session.jsonl` + `session.<n>.jsonl`),在回放时将每份收集到的日志与其 fixture 做 diff。归一化器已支持复数会话 id 并会折叠任何游离 UUID,因此无需修改归一化器。 + +### 4. 场景 + +新增两个嵌套场景,均对真实 API 录制: + +- **`subagent-spawn`**:父 agent 通过 `subagent` 工具将一个子任务委派给一个新 spawn 的子 agent(2 个会话)。 +- **`subagent-multi`**:父 agent 委派两个子任务,各自交给自己的 spawn 子 agent(3 个会话),以三份并行脚本和同一父 agent 下两个子会话的 `createdAt` 排序来压测逐会话键控。 + +两者均在默认门禁中以 keyless 方式回放。 + +## 后果 + +- `TODO(subagent-snapshots)` 延期项已解决:嵌套 agent 的 transcript 现在是快照层的一等形态。 +- `GenerateOptions.sessionId` 是一个小而诚实的 core-seam 新增,在回放之外同样有用(遥测、请求路由)。 +- `subagent` 工具绑定到单一提供方,因此 `subagent-multi` 中的两个子 agent 都是 spawn(全新创建)。键控按会话路由而非按后端路由,因此对 fork 同样正确。但脚本*派生*逻辑此前不正确:fork 子会话的日志以种子化的父前缀(父会话的 `assistant/chunk` 事件)开头,如果从完整日志派生脚本,就会把父 agent 的响应当作子 agent 的来回放。这一正确性缺口通过持久化种子边界来弥合——见[持久化种子边界,使 fork 子项重放能够正确路由](2026-06-22-fork-child-replay-seed-boundary.md)——录制的 fork 与混合 spawn+fork 场景现在通过一份 transcript 同时验证两种传输方式(见[记录 fork 与混合 spawn+fork 快照场景](2026-06-22-fork-snapshot-scenarios.md))。 +- 进程外(ACP(Agent Client Protocol))subagent 是完全不同的回放形态(每个子 agent 是自己的进程、有自己的回放),作为 `TODO(acp-subagent-replay)` 记录在 PR3 计划中。 diff --git a/.agents/notes/implemented/testing/2026-07-04-hook-snapshot-matrix.i18n.yaml b/.agents/notes/implemented/testing/2026-07-04-hook-snapshot-matrix.i18n.yaml new file mode 100644 index 0000000000..743d7ecbf0 --- /dev/null +++ b/.agents/notes/implemented/testing/2026-07-04-hook-snapshot-matrix.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-04-hook-snapshot-matrix.md: ceb91a70e1f9582cf2a7cb4cec0ba8aaf5699b8e +2026-07-04-hook-snapshot-matrix.zh.md: 250995dd1aae566aa5b9d40a14ed281b14fbfe0b diff --git a/.agents/notes/implemented/testing/2026-07-04-hook-snapshot-matrix.md b/.agents/notes/implemented/testing/2026-07-04-hook-snapshot-matrix.md index 7c2c33460c..ceb91a70e1 100644 --- a/.agents/notes/implemented/testing/2026-07-04-hook-snapshot-matrix.md +++ b/.agents/notes/implemented/testing/2026-07-04-hook-snapshot-matrix.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-07-04-hook-snapshot-matrix.zh.md) + ## Problem The hook bridges — [`dsh-hooks-claude`](../../../../packages/hooks/hooks-claude) (7 Claude Code hook points) and [`dsh-hooks-codex`](../../../../packages/hooks/hooks-codex) (5 Codex points) — map external hook commands onto the harness interception seams. They carry deep unit and coverage-spec coverage (every decision arm, every payload dialect, driven against a mocked seam) plus one key-gated e2e (`hooks.e2e.ts`, a live `PreToolUse` block). But the full-transcript snapshot tier — the one net that boots the real `acp-agent` subprocess, replays a recorded session keyless, and diffs the normalized ACP stdout + re-persisted log against committed expected outputs — covered exactly ONE hook: a Claude `UserPromptSubmit` block (`hook-cc-promptsubmit-block`). diff --git a/.agents/notes/implemented/testing/2026-07-04-hook-snapshot-matrix.zh.md b/.agents/notes/implemented/testing/2026-07-04-hook-snapshot-matrix.zh.md new file mode 100644 index 0000000000..250995dd1a --- /dev/null +++ b/.agents/notes/implemented/testing/2026-07-04-hook-snapshot-matrix.zh.md @@ -0,0 +1,52 @@ +# Agent Note: 钩子快照矩阵——覆盖两种 bridge 的端到端预期输出测试 + +Status: implemented + +[English](2026-07-04-hook-snapshot-matrix.md) | 中文 + +## 问题 + +钩子 bridge——[`dsh-hooks-claude`](../../../../packages/hooks/hooks-claude)(7 个 Claude Code 钩子点)和 [`dsh-hooks-codex`](../../../../packages/hooks/hooks-codex)(5 个 Codex 点)——把外部钩子命令映射到 harness 拦截 seam。它们有深入的单元与覆盖率规格覆盖(每个决策分支、每种 payload dialect,针对 mock seam 驱动),外加一个受密钥门控的 e2e(`hooks.e2e.ts`,实时 `PreToolUse` 阻止)。但完整 transcript(文本记录)快照层——会启动真实 `acp-agent` 子进程、无需密钥重放已记录会话,并将规范化 ACP(Agent Client Protocol)stdout + 重新持久化日志与已提交预期输出进行 diff 的那张网——只覆盖了一个钩子:Claude `UserPromptSubmit` 阻止(`hook-cc-promptsubmit-block`)。 + +这正是 mock 单元测试在结构上无法替代的层级:它验证的是真实 bridge 将真实钩子进程的结果翻译到真实 seam 决策,再到真实 agent loop(智能体循环)的反应,渲染结果与编辑器看到的完全一致。一个 bridge 翻译或 loop 结构的回归,即使让所有单元测试保持绿色,也会在除那一个钩子点之外的所有点上逃逸;而对于 Codex bridge,ACP 示例甚至没有加载它,因此没有任何 Codex 钩子能端到端触发。 + +## 决策 + +实现由两个耦合部分组成: + +### 1. ACP 示例同时加载两种钩子 bridge + +`examples/acp-agent/cordis.yml` 和 `cordis.snapshot.yml` 现在同时加载 `dsh-hooks-codex` 与 `dsh-hooks-claude`,各自指向自己的配置文件(Claude 用 `./hooks.json`,Codex 用 `./codex-hooks.json`——两种方言无法共用一个文件)。这是一个真正的产品接口变更,而非仅用于测试的接线:交付的 ACP 服务器(以及 `demo:acp` 入口)现在同时携带两种 bridge。 + +这是安全的,因为配置文件不存在时 bridge 是**静默无操作**的:`apply()` 捕获读取失败、通过 `ctx.logger` 记录日志、不注册任何东西——零监听器、零会话事件。`acp-agent` 应用不附带 stdout logger,因此警告不会到达 ACP JSON-RPC 通道。只需要 Claude 钩子的场景(或真实项目)只提供 `hooks.json`;Codex bridge 找不到 `codex-hooks.json` 便自动消失。这已通过实验验证:在两种 bridge 同时加载的情况下,所有既有快照(均不附带 `codex-hooks.json`)逐字节一致。 + +同时加载是让快照层能够在产品交付的同一个真实应用上验证每种方言的最低要求。录制(启动 `cordis.yml`)天然加载两者,回放以同样方式继承:`cordis.snapshot.yml` 是 `cordis.yml` 的 include-overlay,只替换 llm 入口(见[单一来源 acp-agent 回放配置](2026-07-04-single-source-acp-replay-config.md)),因此添加到运行时树的 bridge 无需第二次编辑即出现在回放树中。 + +### 2. 每个钩子点 × 其主要结果各一个快照场景,覆盖两种方言 + +`examples/acp-agent/tests/snapshots/` 下共 13 个场景,命名为 `hook-<dialect>-<point>-<outcome>`: + +- **手工编写、无模型轮次**(无密钥、无 sidecar——派生的回放脚本为空;比对的是携带 `hook/*` 事件的 `rejected` 轮次):`hook-cc-promptsubmit-block`、`hook-codex-promptsubmit-block`。 +- **对真实 API 录制、录制期间钩子活跃**(模型对决策的反应是捕获的 transcript 的一部分,此后无密钥回放):`hook-{cc,codex}-promptsubmit-context`(allow + additionalContext 折叠)、`hook-cc-pretool-deny` / `hook-codex-pretool-block`(deny → `isError` 工具结果)、`hook-cc-pretool-ask`(ask → 降级为 deny 并附带 approval-required 原因)、`hook-{cc,codex}-posttool-block`(阻止并附带反馈)、`hook-{cc,codex}-posttool-context`(accept + additionalContext)、`hook-{cc,codex}-stop-continue`(阻塞性 Stop 钩子通过 steering(中途引导)强制多走一步)。 + +每个钩子命令只输出固定字面量字符串(无时间戳/pid/`$RANDOM`/cwd 回显);快照规范化器擦除 `hook/result` 携带的唯一不稳定字段(`durationMs`)。`Stop` 场景通过标记文件(`.stop_fired`)自限,使 force-continue 不会循环——`stop_hook_active` 循环守卫仍是 bridge 的一个 `TODO`,因此无条件的 Stop 钩子会在每一步都 force-continue。 + +`PostToolUse` 阻止场景会在其证明的机制处自行限制。Claude 钩子在首次拒绝后持久化一个 workspace 标记,因此允许一次恢复调用;Codex 提示词发起一次调用并报告注入结果。每份预期输出固定一次遭阻止调用,不会重复阻止/重试循环。 + +### 三个钩子点被有意排除在快照之外 + +在构建矩阵过程中发现,记录于此是因为这些遗漏是决策而非疏忽: + +- **`SessionStart` 和 `SubagentStart`** 通过脱离且尽力而为的 `void runPoint(...).then(agent.inject())` 注入上下文,没有轮次绑定。由此产生的 `context/message` 会与它应先于的工作(首次模型请求 / 子项的第一个轮次)竞速,并落在不确定的日志位置。记录的预期输出甚至无法在自己的重放中复现——对两者执行 10 次重放稳定性检查,结果均为 10/10 次失败。它们继续留在 bridge 的单元覆盖率中,那里会直接驱动 seam 而不存在时序竞速。(如果注入未来改为绑定轮次且具备确定性——`TODO(session-start-gating)` 所指方向——它们就能接受快照测试。) +- **`SubagentStop`** 只观察:其 `subagent/end` handler 不传递轮次(因此没有 `hook/*` 日志事件),也不执行注入。它不会向 transcript 写入任何内容,因此预期输出会与无钩子运行逐字节相同,永远无法证明失败——一道咬不住问题的守卫。它继续由单元覆盖率负责(`bridge.spec.ts` 已断言仅观察调用)。 + +因此,该矩阵覆盖了所有具有确定性、可观测 transcript 足迹的钩子点,涵盖两种方言。 + +## 后果 + +- 现在,两种 dialect 中每个具有可观察 transcript 的 bridge seam 映射,都在真实应用的完整 transcript 层受到守护——包括此前完全没有端到端覆盖的 Codex bridge。记录的预期输出捕获模型对遭拒绝/遭阻止/强制继续轮次的真实反应,而手工编写的 transcript 只能猜测这种反应。 +- `UserPromptSubmit` 阻止场景无需密钥即可编写(没有模型轮次);其余场景从已记录 fixture(测试前置数据)无需密钥重放。`pnpm run test:snapshot:record` 从实时 API 重新生成记录式 fixture,并像所有记录场景一样在缺少密钥时自行跳过。 +- 证明会变红的准则仍成立:篡改钩子配置输出(例如改变拒绝理由)会让相应场景在重放时变红——钩子进程在重放期间真实运行(只有模型被重放),因此预期输出守护的是实际钩子→seam→循环路径,而非其 mock。 +- `acp-agent` 演示现在加载了一个通常会无操作的 Codex bridge(典型项目中没有 `codex-hooks.json`),这正是预期的柔性失败行为,而非代价。 + +<!-- agent-note-format: alternatives-not-recorded (pre-format Agent Note) --> diff --git a/.agents/notes/implemented/testing/2026-07-04-single-source-acp-replay-config.i18n.yaml b/.agents/notes/implemented/testing/2026-07-04-single-source-acp-replay-config.i18n.yaml new file mode 100644 index 0000000000..719884e56c --- /dev/null +++ b/.agents/notes/implemented/testing/2026-07-04-single-source-acp-replay-config.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-04-single-source-acp-replay-config.md: f270d70feca184217503c472c1cb7c536187a249 +2026-07-04-single-source-acp-replay-config.zh.md: 86eb2d3e15c4939d1de3a78150cd0536d46e10f6 diff --git a/.agents/notes/implemented/testing/2026-07-04-single-source-acp-replay-config.md b/.agents/notes/implemented/testing/2026-07-04-single-source-acp-replay-config.md index 3de645deeb..f270d70fec 100644 --- a/.agents/notes/implemented/testing/2026-07-04-single-source-acp-replay-config.md +++ b/.agents/notes/implemented/testing/2026-07-04-single-source-acp-replay-config.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-07-04-single-source-acp-replay-config.zh.md) + ## Problem `examples/acp-agent` shipped two hand-maintained configs: `cordis.yml` (the live tree) and a `cordis.snapshot.yml` that mirrored it entry-for-entry with only the llm backend swapped — stripped of comments, the entire difference was the eight-line `llm-deepseek` stanza versus the two-line `llm-replay` stanza. Every app-shape change had to be made twice, and nothing gated the symmetry: if the copies drifted, the snapshot tier would silently exercise a different app than the one that ships — the ["green units, broken product" class of gap](../../../../docs/postmortem/0001-acp-default-export-drops-inject.md) the snapshot tier exists to close, reintroduced one level up, with reviewer vigilance as the only defense. diff --git a/.agents/notes/implemented/testing/2026-07-04-single-source-acp-replay-config.zh.md b/.agents/notes/implemented/testing/2026-07-04-single-source-acp-replay-config.zh.md new file mode 100644 index 0000000000..86eb2d3e15 --- /dev/null +++ b/.agents/notes/implemented/testing/2026-07-04-single-source-acp-replay-config.zh.md @@ -0,0 +1,27 @@ +# Agent Note: 将 acp-agent 回放配置改为单一来源 + +Status: implemented + +[English](2026-07-04-single-source-acp-replay-config.md) | 中文 + +## 问题 + +`examples/acp-agent` 发布了两份手工维护的配置:`cordis.yml`(实时树)和逐条镜像它、只替换 llm 后端的 `cordis.snapshot.yml`——去除注释后,两者的全部差异就是八行 `llm-deepseek` stanza 与两行 `llm-replay` stanza。每次应用形状变化都必须修改两遍,也没有任何机制约束对称性:如果副本发生漂移,快照层会悄然覆盖与已发布应用不同的应用——快照层本就是为了弥合[“单元测试绿色,产品损坏”这类缺口](../../../../docs/postmortem/0001-acp-default-export-drops-inject.md),如今同类缺口在上一层重新出现,只能依靠评审者警惕。 + +## 决策 + +`cordis.snapshot.yml` include 正式配置,通过 id 和 name 禁用指定的 DeepSeek 适配器,并插入回放适配器。其余所有条目因此来自正式运行树。回放时选择 overlay;录制仍然启动 `cordis.yml`,加载守卫允许被有意禁用的条目。 + +overlay 有意依赖一项 vendored 插件事实:include 加载文件时会应用 `patches`,而其 `refresh()`/`internal/update` 路径会重新读取但不重新打补丁——这恰好足以满足一次性重放启动(重放应用不加载 `hmr`,运行中也没有内容重写配置)。快照套件就是证明:所有场景都能在 overlay 上原样通过,包括逐字节相同的预期输出。 + +## 曾考虑的替代方案 + +### 为何不采用这些替代方案? + +保留完整的双副本并加一道对称性校验门禁是记录在案的退路——它能消除静默漂移这一类问题,但仍保留一份 125 行的近乎复制品,其全部内容只是一个条目的差异,且随应用每增加一个插件而增长。在 bin 侧做替换(解析配置、替换条目、删除文件)则会把 YAML 手术放进发布产物,并把回放差异藏到视线之外;overlay 让差异保持声明式、可读,且紧邻基础配置——这正是双副本支持者真正看重的教学价值。 + +## 后果 + +- 向 `cordis.yml` 添加插件即自动进入回放树,无需第二次编辑;漂移这一类问题从结构上消失,而非靠门禁拦截。 +- overlay 依赖条目携带稳定的 `id:`。禁用补丁上的 `name` 断言防止误定位(id 被复用时补丁跳过而非禁用错误的插件)。如果 id 被重命名,补丁退化为跳过,其警告需要一个回放应用有意不具备的 logger——可观测结果是一条无效的无密钥 `llm-deepseek` 条目与 `llm-replay` 并存,回放输出仍然正确(`llm-replay` 拥有流的短路权);这属于配置腐烂,留给评审发现,不会产生错误的快照。顶层插入一个 id 与既有条目冲突的新条目时,loader 的 id map 以后者为准;当前配置无冲突,新增补丁行才是引入冲突的场所。 +- 如果未来回放树需要第二处差异(另一个后端被替换),只需多加一行补丁,而非再 fork 一份文件。 diff --git a/.agents/notes/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.i18n.yaml b/.agents/notes/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.i18n.yaml new file mode 100644 index 0000000000..2b7c1cc937 --- /dev/null +++ b/.agents/notes/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-06-pin-request-header-content-in-one-scenario.md: bca6d9eb943e758d68efaf3a76ec367179cd15fd +2026-07-06-pin-request-header-content-in-one-scenario.zh.md: e01c84c63583e2fe14b0b4fe0381a18b209d2346 diff --git a/.agents/notes/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md b/.agents/notes/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md index 1dcfc2e085..bca6d9eb94 100644 --- a/.agents/notes/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md +++ b/.agents/notes/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-07-06-pin-request-header-content-in-one-scenario.zh.md) + ## Problem An ACP snapshot suite needs to prove the exact composed system prompt and tool-schema list sent in each `request/header`, but duplicating that content inside every `session.jsonl` makes a prompt or schema edit rewrite dozens of giant one-line JSON records. Keeping one raw header avoids the duplication but still makes prompt review poor: prose is JSON-escaped onto one line and mixed with thousands of characters of tool schemas. diff --git a/.agents/notes/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.zh.md b/.agents/notes/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.zh.md new file mode 100644 index 0000000000..e01c84c635 --- /dev/null +++ b/.agents/notes/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.zh.md @@ -0,0 +1,35 @@ +# Agent Note: 在单个快照场景中固定请求头内容 + +Status: implemented + +[English](2026-07-06-pin-request-header-content-in-one-scenario.md) | 中文 + +## 问题 + +一个 ACP(Agent Client Protocol)快照测试套件需要证明每个 `request/header` 中实际发送的组合系统提示词与工具 schema 列表,但如果在每个 `session.jsonl` 中重复这些内容,一次提示词或 schema 编辑就会改写数十条巨大的单行 JSON 记录。保留一份原始 header 可以避免重复,但提示词的评审体验仍然很差:行文被 JSON 转义到一行中,与数千字符的工具 schema 混在一起。 + +## 决策 + +每种请求头组合类别恰好有一个场景标记为 `pinsHeader`。其目录按评审格式拆分固定内容:`system-prompt.expected.md` 以普通 Markdown 包含规范化的完整提示词序列;`tool-schemas.expected.json` 以结构化 JSON 包含对应的完整 schema 序列;`session.jsonl` 保留 config、reason 和所有模型可见前缀,同时将 `header.system` 与 `header.tools` 存为 `"{{system}}"` / `"{{tools}}"`。其他每份 JSONL 都使用相同的提示词与工具 token,并同样将会话前缀内容 token 化。固定机制位于 [`dsh-acp-snapshot`](../../../../packages/support/acp-snapshot/README.md),其套件 factory 强制每种类别恰好有一个固定场景。 + +纯 `scrubSystemPrompts` 和 `scrubToolSchemas` 规范化器会分别将每个已存储完整请求头 token 化。`scrubRequestHeaders` 还会为非固定场景把会话前缀内容 token 化,同时保留请求头数量、字段存在性、config、reason 和前缀消息数量。记录与刷新写回会在写入 JSONL 前应用适当清理,并根据规范化的实时完整请求头序列重新生成两个 sidecar,因此两条路径都无法把大段提示词/schema 重新引入 JSONL,也不会留下陈旧的评审产物。 + +守卫使这种拆分能够自我强制。在磁盘上,每个 `session*.jsonl` 都是提示词和 schema 清理器的固定点;只有非固定 fixture(测试前置数据)必须是完整请求头清理的固定点;两个 sidecar 恰好位于固定 fixture 旁,并采用规范、以换行符结尾的格式;每种类别都有一个固定场景。在实时运行中,由父项、spawn 子项、fork 子项、初始请求、恢复或实例内变化产生的每个 `request/header`,都必须在易变值规范化后与重建的类别序列匹配。请求头若没有字符串提示词、没有数组值工具列表,或超过固定场景声明的变更请求头数量,就会响亮失败。 + +一个固定场景覆盖整个套件,因为每个会话(parent、spawn 子会话、fork 子会话)组合出的工具列表完全相同、提示词除 cwd 外完全相同,而一致性守卫会在这一前提不再成立时立即使套件失败。如果 header 组合将来在设计上变为会话相关的(例如受限的 subagent 工具集),那么分歧的形态将获得自己的固定场景。 + +## 曾考虑的替代方案 + +- **每次变更重新录制或手动编辑所有 fixture**:保留了精确的 header,但行为差异被重复的提示词和 schema 内容淹没。 +- **仅在比较时 scrub,fixture 保持原始内容**:比较能通过,但已提交的 fixture 保留着陈旧的重复内容,下次录制时会整体重写。存储 token 诚实地表明每个 JSONL 没有固定什么。 +- **全部 scrub,不做任何固定**:丢失了组合 header 实际发送内容(提示词组装、已注册工具顺序、完整 schema)的唯一端到端记录。生成的工具目录只孤立地记录每个工具;只有真实 fixture 才能固定组合后的完整集合。 +- **将完整固定内容全部保留在 JSONL 中**:消除了套件范围的重复,但提示词和 schema 变更仍然是一行转义文本。Markdown 和结构化 JSON 为每种内容提供其自然的评审格式,同时不削弱重建 header 的断言。 +- **收窄会话日志本身(记录内容 digest,把请求头存到其他位置)**——违反可重建性契约:产品日志必须逐 bit 复现每个请求([可重建请求 Agent Note(agent 决策记录)](../architecture/2026-07-05-reconstructable-requests.md))。请求头体积是测试产物问题,应在测试规范化中解决;实时日志保持不变。 + +## 验证 + +该套件针对拆分后的固定内容回放每个场景。单元覆盖率会覆盖独立与完整清理器、两种完整请求头 sidecar 格式、记录/刷新重新生成、规范化提示词/schema 提取、固定点强制、必需文件对称性、重建请求头一致性,以及变更请求头数量拒绝。 + +## 后果 + +系统提示词变更在每个受影响的组合类别中产生一个面向行的 Markdown diff;工具描述变更在每个类别中产生一个结构化 JSON diff;普通行为 fixture 不受影响。会话 fixture 对省略的内容显示 token,运行时一致性守卫使每个拆分固定场景对其类别内的所有会话具有权威性。每个固定场景携带两个生成的、换行规范化的 sidecar 文件。 diff --git a/.agents/notes/implemented/testing/2026-07-08-shared-acp-snapshot-package.i18n.yaml b/.agents/notes/implemented/testing/2026-07-08-shared-acp-snapshot-package.i18n.yaml new file mode 100644 index 0000000000..5c5bad0b1a --- /dev/null +++ b/.agents/notes/implemented/testing/2026-07-08-shared-acp-snapshot-package.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-08-shared-acp-snapshot-package.md: 3e5a2b12114d535490a17361128862f6d1c09a73 +2026-07-08-shared-acp-snapshot-package.zh.md: 072ef692702cb769c428f8b6aa3863a3b77d3d59 diff --git a/.agents/notes/implemented/testing/2026-07-08-shared-acp-snapshot-package.md b/.agents/notes/implemented/testing/2026-07-08-shared-acp-snapshot-package.md index 8d6032d1cc..3e5a2b1211 100644 --- a/.agents/notes/implemented/testing/2026-07-08-shared-acp-snapshot-package.md +++ b/.agents/notes/implemented/testing/2026-07-08-shared-acp-snapshot-package.md @@ -2,6 +2,8 @@ Status: implemented +English | [中文](2026-07-08-shared-acp-snapshot-package.zh.md) + ## Problem The ACP snapshot tier ([snapshot Agent Note](2026-06-19-acp-snapshot-tests.md)) was built from three modules living inside one example's test directory: `snapshot-harness.ts` (boot the real bin subprocess, drive it over ACP JSON-RPC, harvest the persisted logs), `snapshot-normalize.ts` (the pure expected-output normalizers), and the ~150-line scenario body plus fixture guards in `acp.snapshot.ts` (record/replay modes, the stdout expected-output and log comparisons, the pinned-header uniformity guard, the orphan/required-file/single-pin meta-tests). diff --git a/.agents/notes/implemented/testing/2026-07-08-shared-acp-snapshot-package.zh.md b/.agents/notes/implemented/testing/2026-07-08-shared-acp-snapshot-package.zh.md new file mode 100644 index 0000000000..072ef69270 --- /dev/null +++ b/.agents/notes/implemented/testing/2026-07-08-shared-acp-snapshot-package.zh.md @@ -0,0 +1,40 @@ +# Agent Note: 将 ACP 快照套件提取为支持包 + +Status: implemented + +[English](2026-07-08-shared-acp-snapshot-package.md) | 中文 + +## 问题 + +ACP(Agent Client Protocol)快照层([快照 Agent Note(agent 决策记录)](2026-06-19-acp-snapshot-tests.md))由位于一个示例测试目录内的三个模块构建:`snapshot-harness.ts`(启动真实 bin 子进程,通过 ACP JSON-RPC 驱动它,采集持久化日志)、`snapshot-normalize.ts`(纯预期输出规范化器),以及 `acp.snapshot.ts` 中约 150 行的场景主体与 fixture(测试前置数据)守卫(记录/回放模式、stdout 预期输出与日志比较、固定请求头一致性守卫、孤立项/必需文件/单一固定项元测试)。 + +第二个希望获得快照覆盖的 ACP 示例——直接消费方是沙箱/approval 组合——只能复制这些模块,恰好分叉了绝不能漂移的逻辑:记录写回、请求头清理、子会话采集顺序。spawn/client 胶水也在 `acp.e2e.ts`、`hooks.e2e.ts` 和 harness 中重复三份。文件位置决定了测试严格度:逐文件 100% 覆盖率门禁只测量 `packages/*/*/src`,因此这些机制完全未被测量——正是同一种缺口,曾推动 `dsh-llm-replay` 从 `examples/` 移入 [packages/support](../../../../packages/support/README.md)。此外,harness 的 ACP client 硬编码 `requestPermission → cancelled`,因此 approval 往返——沙箱组合的主打行为——完全无法在快照层表达。 + +## 决策 + +这些机制位于 [`packages/support/acp-snapshot`](../../../../packages/support/acp-snapshot/README.md)(`@deepseek-ai/dsh-acp-snapshot`);示例的 `*.snapshot.ts` 只包含场景表、agent 路径和一次工厂调用,依赖自己的 `snapshots/` fixture 与 `cordis.snapshot.yml` overlay([单源回放配置](2026-07-04-single-source-acp-replay-config.md))。读取 `DSH_SNAPSHOT` 留在边缘层——库接收的是已解析的 `mode`。 + +**`src/launcher.ts`**——`launchAcpTestAgent` 拥有通用的未构建进程边界:绝对 tsx loader 解析、`TSX_TSCONFIG_PATH`、隔离的 harness home、stdio 接线、原始字节 stdout tee、stderr 与更新捕获、失败关闭的权限后备、更新 waiter,以及优雅或信号式关闭。快照场景和普通 e2e 套件提供相同的 `AgentUnderTest`(`binScript`、`configPath`、`tsconfigPath`);扮演用户的测试只提供其权限 handler。ACP 与钩子 e2e 套件以及沙箱/approval e2e 套件都使用该 launcher,而不再重新构建 SDK client 边界。 + +**`src/harness.ts`**——`runScenario` 和输入脚本/结果类型在 launcher 之上叠加确定性步骤、临时 workspace、快照环境和持久化日志采集。其 `session/request_permission` handler 消费可选的 `InputScript.permissionAnswers` FIFO 队列,每个条目按选项**类型**进行选择(id 是 agent 生成的随机值,已提交脚本无法预知;类型是 ACP 稳定词汇,会在回答时映射到已提供的 `optionId`);队列不存在或耗尽时回答 `cancelled`,若请求从未提供某种类型则拒绝该次运行——agent 自身收到的回答是 `cancelled`,因此场景 bug 会使 harness 失败,而不会被吸收为 agent 侧拒绝。由此,approval 套件可以根据 `input.json` 确定性地驱动允许/拒绝往返。 + +**`src/normalize.ts`** 是纯规范化器,按策略不含钩子:当未来某个事件携带新的易变字段(例如审批耗时),共享规范化器在同一个变更中学会它,保持「规范化」的含义只有一个归属,而非各套件各自扩展清洗逻辑。 + +**`src/suite.ts`**——包含 `Scenario` 类型和 `defineAcpSnapshotSuite(options)`,注册各场景比较、记录/刷新 fixture 写回、带实时一致性守卫的请求头固定项,以及 fixture 守卫块(没有孤立场景目录、必需文件存在、每种类别恰好一个固定项、每份 JSONL 都是 `scrubSystemPrompts` 固定点、非固定 fixture 同时也是 `scrubRequestHeaders` 固定点)。刷新会先展开打包的计时信封,再对齐现有易变事件时间,因此在打包与未打包布局之间切换不会移动后续记录;全新的分片片段数组仍为权威,因为其边界属于回放行为。场景目录中的 `session.jsonl` 加连续的 `session.<n>.jsonl` 同级文件构成有序主项/子项清单,因此场景表可以声明策略而不重复子项数量。固定请求头契约([固定请求头 Agent Note](2026-07-06-pin-request-header-content-in-one-scenario.md))按套件生效:每种请求头类别恰好标记一个 `pinsHeader` 场景,其 `system-prompt.expected.md` 和 JSONL 工具列表把组合请求头拆成可评审产物;一致性守卫会将两者与该类别的每个实时请求头比较。固定场景可以声明任何合法的变更请求头数量,其 Markdown 产物记录每个完整的已变提示词。纯辅助函数(`sessionFixtureNames`、`fixtureContext`、`normalizedHeaders`、`normalizedSystemPrompts`、`formatSystemPromptSnapshot`、`headerChangeCount`)从模块导出,以便直接进行单元覆盖。 + +## 曾考虑的替代方案 + +- **把模块复制到每个示例中**——这正是本 Agent Note 要防止的分叉:记录/守卫逻辑恰好是必须在各套件间保持逐字节相同的代码,而示例位于覆盖率门禁之外,所以每份副本也都无法测量。 +- **在 `examples/` 下建共享模块目录**:代码仍在覆盖率门禁之外,且需要跨示例边界的相对导入,违反包名导入约定;`examples/` 的叶子节点按设计应保持轻薄。 +- **`dsh-acp-demo` 的 `/testing` 子路径导出**:将测试基础设施耦合到产品包的对外服务接口与依赖集中;`packages/support/` 的存在正是为了真实但兼容性承诺较低的开发/测试包,`dsh-llm-replay` 是先例,本包与之配套。 +- **导出原始测试体函数而非套件工厂**:每个示例将重新拥有 `describe`/`it` 骨架(每套件约 80 行注册样板),却无灵活性收益;工厂使消费方只需一张场景表加一次调用,而导出的纯辅助函数在工厂设计内保留了可单元测试性。 +- **使用可注入 ACP `Client` factory 代替声明式 `permissionAnswers`**——灵活性最大,但会把 SDK client 构造泄漏给每个消费方,并恰好在正在统一的层重新引入逐示例漂移;声明式队列让 `input.json` 保持为唯一脚本表面,并与预期输出规范化兼容。 +- **泛化到 ACP 之外(传输无关的快照 harness)**:不存在第二种传输方式;harness 端到端都是 ACP 形态(SDK 客户端、JSON-RPC 帧、`session/update` 等待器),推测性的抽象将是一个超前于任何消费方的 seam 拆分。 + +## 测试 + +提取一致性得到机械证明:迁移后,`pnpm run test:snapshot` 的结果与基准提交匹配,`examples/acp-agent/tests/snapshots/` 下没有任何字节变化。包的 `src/` 在门禁单元运行中保持逐文件 100% 语句/分支/函数/行覆盖,并通过脚本化 fake ACP bin(`tests/fixtures/fake-acp-agent.ts`,每个场景由 fixture 旁的 `behavior.json` 编排行为)经过真实 launcher 驱动:`harness.spec.ts` 直接覆盖 launcher 默认值、捕获、更新等待、关闭以及环境/配置变体,随后覆盖每种场景步骤操作、两个 expect-error 分支、权限队列(选择、后备、不可能点击)、workspace seed,以及采集顺序/噪音/后备分支;`suite.spec.ts` 在收集时真实运行 factory——一个针对已提交合成 fixture 的回放套件和一个针对临时副本的记录套件(写回从不触及已提交树;`ACP_SNAPSHOT_SPEC_BOOTSTRAP=1` 会重新引导它)——并包含纯辅助函数的直接用例。fake bin 会把 `session/new` cwd 而非 `process.cwd()` 代入脚本化日志,与真实 bin 请求头携带的内容一致(darwin 会将 `/var/folders/…` realpath 为 `/private/var/folders/…`)。 + +## 后果 + +新示例通过场景表加 fixture 即可获得完整快照层,普通 ACP e2e 则通过一次 launcher 调用获得同一条经过测试的进程/client 边界。代价是:`suite.ts` 导入 vitest,因此包入口只能在 vitest 运行中导入——其他包都没有这种形状,其 README 已说明;每个套件还要固定自己的约 8 KB 请求头 fixture(真正不同的组合理应拥有自己的固定项;相同组合则会被该套件的一致性守卫捕获)。 diff --git a/.agents/notes/proposed/architecture/2026-06-16-typed-event-schemas.i18n.yaml b/.agents/notes/proposed/architecture/2026-06-16-typed-event-schemas.i18n.yaml new file mode 100644 index 0000000000..e36caa3f12 --- /dev/null +++ b/.agents/notes/proposed/architecture/2026-06-16-typed-event-schemas.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-16-typed-event-schemas.md: 97a7d0c3787eb5556696e25a6c8b1bb75642aba9 +2026-06-16-typed-event-schemas.zh.md: c19f67c6ff058d42293ff2b6346630fe91c54dec diff --git a/.agents/notes/proposed/architecture/2026-06-16-typed-event-schemas.md b/.agents/notes/proposed/architecture/2026-06-16-typed-event-schemas.md index 500be241c6..97a7d0c378 100644 --- a/.agents/notes/proposed/architecture/2026-06-16-typed-event-schemas.md +++ b/.agents/notes/proposed/architecture/2026-06-16-typed-event-schemas.md @@ -2,6 +2,8 @@ Status: proposed +English | [中文](2026-06-16-typed-event-schemas.zh.md) + ## Problem The harness models its core vocabulary — content blocks, message sources, finish reasons, turn triggers, turn-end reasons, and session events — as **merge-extensible maps**: a TypeScript `interface` (e.g. `SessionEventMap`, `ContentBlockMap`) that plugins augment via declaration merging, with the public union derived as `Map[keyof Map]`. This is the repo's universal extension pattern, documented in [docs/architecture.md](../../../../docs/architecture.md) ("The same merge-extensible-map pattern is used for `MessageSource`, `FinishReason`, `TurnTrigger`, and `TurnEndReason`") and relied on by the `defineTool` `InferArgs` DSL and the `assertNever` exhaustiveness convention. diff --git a/.agents/notes/proposed/architecture/2026-06-16-typed-event-schemas.zh.md b/.agents/notes/proposed/architecture/2026-06-16-typed-event-schemas.zh.md new file mode 100644 index 0000000000..c19f67c6ff --- /dev/null +++ b/.agents/notes/proposed/architecture/2026-06-16-typed-event-schemas.zh.md @@ -0,0 +1,77 @@ +# Agent Note: 事件词汇的运行时 schema(Zod 与 merge-extensible-map 模式之辩) + +Status: proposed + +[English](2026-06-16-typed-event-schemas.md) | 中文 + +## 问题 + +harness 将其核心词汇——内容块、消息来源、结束原因、轮次触发器、轮次结束原因与会话事件——建模为 **merge-extensible map**:一个 TypeScript `interface`(如 `SessionEventMap`、`ContentBlockMap`),插件通过声明合并对其扩展,公开联合类型则以 `Map[keyof Map]` 派生。这是本仓库的通用扩展模式,记录在 [docs/architecture.md](../../../../docs/architecture.md) 中(「The same merge-extensible-map pattern is used for `MessageSource`, `FinishReason`, `TurnTrigger`, and `TurnEndReason`」),`defineTool` 的 `InferArgs` DSL 和 `assertNever` 穷举约定都依赖于它。 + +该模式**仅存在于编译期**。类型在运行时消失:没有 schema 对象可供校验传入值、解析不可信输入或在运行时枚举变体。[会话持久化契约](../../implemented/architecture/2026-06-14-session-persistence.md)暴露了两个后果: + +1. **持久化将 `event.data` 视为不透明 JSON。** JSONL/SQLite 后端对每个事件逐字 `JSON.stringify`/`JSON.parse`;唯一的运行时守卫是 `isJsonValue`(往返可序列化性检查:拒绝 BigInt、函数、循环引用、非有限数等),而非结构校验。一个损坏但仍为合法 JSON 的事件数据(字段类型错误、字段缺失)会静默往返,只有在后续消费方的 `switch` 中才可能被捕获。 +2. **插件新增变体没有运行时契约。** 一个通过声明合并添加新 `SessionEventMap` 键的插件,在自身代码中获得了编译期类型,但没有任何机制校验它产出的值是否符合它所声明的形状——无论是在生产者处、持久化边界处还是重新加载时。 + +由此引出问题:事件词汇是否应迁移到 **Zod** 或其他运行时 schema 库,使持久化和插件边界拥有运行时 schema 而非被擦除的类型。 + +本 Agent Note(agent 决策记录)界定该问题的范围,不提出具体实现。 + +## 为什么这不是一个持久化层的改动 + +很容易把「用 Zod 做序列化」理解为对 `dsh-session-persistence-jsonl/src/format.ts` 的局部修改。但它不是,原因在于一个结构性事实:**插件无法对 Zod schema 进行声明合并。** 声明合并是 TypeScript 编译期机制;Zod schema 是运行时值。要用 Zod 校验事件,就需要一个**运行时注册表**,每个产出事件的包(package)向其贡献自己的 schema(如 `ctx.sessionEvents.register('compaction/marker', z.object({…}))`),每个消费方从中读取。这个注册表——而非持久化后端——将成为词汇的真源,取代 merge-extensible 接口。 + +因此,真正的提案是:**用运行时 schema 注册表替换编译期的 merge-extensible-map 模式,范围覆盖整个仓库。** 这是一次核心词汇的重新设计。 + +## 影响范围(已度量) + +将事件/词汇表面迁移到运行时 schema,至少涉及: + +- **六个 merge-extensible map**(约 370 行核心类型):`ContentBlockMap`、`MessageSourceMap`、`FinishReasonMap`(位于 `dsh-llm`);`TurnTriggerMap`、`TurnEndReasonMap`、`SessionEventMap`(位于 `dsh-session`)。 +- **约 10 处 `declare module` 扩展点**,分布在 `dsh-agent`、`dsh-agent-loop`、`dsh-bash`、`dsh-llm`、`dsh-session`、`dsh-session-persistence`、`dsh-system-prompt`、`dsh-tools` 各包中——每处都将从声明合并改为运行时 `register()` 调用。 +- **事件生产者**——agent loop(智能体循环)中 16 处 `session.append(...)` 调用——形状不变,但现在在边界处被校验。 +- **约 7 个 switch 消费方**,对这些联合类型进行分支:`deriveMessages` 与包自有的不变式 companion(`dsh-session`)、`BlockAssembler`(`dsh-llm`)、两个 LLM(大语言模型)适配器(`dsh-llm-deepseek`、`dsh-llm-pi-ai`)以及工具 schema 层(`dsh-tools`)。`assertNever` 对封闭联合类型的穷举 vs 对可扩展联合类型的 fall-through 约定(一条已记录的 lint 规则)需要重新考量——运行时变体在静态层面不可穷举。 +- **`defineTool` 的 `InferArgs` DSL**(`dsh-tools`),它从编译期 schema 规范派生出零类型转换的 `execute` 参数类型——这是当前方案的标杆用例。 +- **文档**:architecture.md(该模式被描述为基础性的)、[开发模式不变式](../../implemented/architecture/2026-06-11-dev-invariants-over-deep-readonly.md),以及所有引用该模式的 Agent Note。 + +这是一次仓库级别的词汇重新设计,而非持久化的实现细节。 + +## 曾考虑的替代方案 + +### A. 维持现状——merge-extensible 类型 + 持久化边界处 `isJsonValue` +保留编译期模式。持久化继续使用不透明 JSON + 可序列化性守卫。插件通过声明合并扩展;事件*形状*的正确性由生产者负责,并由 TypeScript 在编译期保证。启用包自有的不变式 companion 后,它们会检查选定的跨记录关系,但不提供通用运行时形状 schema。 + +- **优点**:零变动;插件扩展只需一行 `interface` 增补,享有完整类型推断,无需运行时注册仪式;无新运行时依赖;`defineTool` DSL 与 `assertNever` 穷举继续工作。 +- **缺点**:持久化边界和插件 seam 处无运行时结构校验;格式错误但仍为合法 JSON 的数据被延迟捕获。 + +### B. 仅对头部/封闭形状做校验(schemastery),事件仍为不透明 +仅对那些已有手写类型守卫的真正封闭形状加以收紧——例如 JSONL 的 `HeaderLine` 守卫(`isHeaderLine`)——使用 **schemastery**(仓库现有的 schema 库,已用于每个插件的 `static Config`)。merge-extensible 事件联合类型保持不变。 + +- **优点**:改动小,契合现有约定(schemastery,而非新库);用声明式 schema 替换封闭形状上的手写守卫;无核心重新设计。 +- **缺点**:不解决事件数据校验问题;仅固定的元数据记录得到改善。 + +### C. 为整个词汇建立运行时 schema 注册表(Zod 或 schemastery) +用运行时注册表替换 merge-extensible map,生产者向其贡献 schema,持久化/消费路径据此校验。 + +- **优点**:持久化边界和插件 seam 处获得真正的运行时校验;单一真源;可支撑通用工具(自动生成文档、模糊测试、协议格式检查)。 +- **缺点**:上述全部影响范围;**Zod 目前不是直接依赖**(仅作为 `@earendil-works/pi-ai` 的传递依赖),仓库选定的 schema 库是 **schemastery**——广泛引入 Zod 本身就是一个依赖决策;声明合并的易用性(一行插件扩展、完整推断)被运行时注册 + 手动类型接线取代;`assertNever` 穷举保证弱化(运行时变体在静态层面不可穷举)。 + +## 提案 + +推迟。如果需要在持久化边界做运行时校验,**方案 B**(对封闭的头部和元数据形状使用 schemastery)是现有约定下的适度步骤。**方案 C** 是一个架构决策,需要自己的实现 Agent Note,其中包括 Zod 与 schemastery 之间的选择。 + +## 验收标准 + +- 方案 C 只能通过自己的实现 Agent Note 推进,绝不能作为持久化的附带改动。 +- 如果采纳方案 B,封闭的头部/元数据形状(JSONL 的 `isHeaderLine` 守卫及同类)改用 schemastery 校验,替代手写守卫,merge-extensible map 保持不动。 + +## 风险 + +- 推迟意味着事件 `data` 在持久化边界处仍无结构校验:格式错误但仍为合法 JSON 的数据被延迟捕获,由消费方的 `switch` 兜底——这是现状的代价,有意接受。 +- 如果方案 C 最终被采纳,易用性的损失是真实的:一行声明合并变为运行时注册加手动类型接线,`assertNever` 的静态穷举保证弱化。 + +## 待解问题 + +- 如果采用注册表,库选 **schemastery**(已在仓库中,已作为配置 schema 库)还是 **Zod**(生态更丰富,目前仅为传递依赖)?同时维护两个 schema 库本身就是一种成本。 +- 能否采用混合方案:保留编译期推断(使 `defineTool` 和插件开发体验不受影响),同时为每个变体添加*可选*的运行时 schema,仅在持久化/协议边界校验,而非每次进程内 append 都校验? +- `ctx.invariants` 服务启用后是否已覆盖了足够多的运行时形状缺口,使得边界校验仅在面对真正不可信输入(重新加载外部修改过的日志)时才有必要? diff --git a/.agents/notes/proposed/architecture/2026-07-24-separate-context-injection-from-turn-execution.i18n.yaml b/.agents/notes/proposed/architecture/2026-07-24-separate-context-injection-from-turn-execution.i18n.yaml new file mode 100644 index 0000000000..233cc3901c --- /dev/null +++ b/.agents/notes/proposed/architecture/2026-07-24-separate-context-injection-from-turn-execution.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-24-separate-context-injection-from-turn-execution.md: 652c3d410ab625d91a828f854bce302adcb0c9e0 +2026-07-24-separate-context-injection-from-turn-execution.zh.md: 1064e7a869ab9ea46c0145eb010119894a03aacf diff --git a/.agents/notes/proposed/architecture/2026-07-24-separate-context-injection-from-turn-execution.md b/.agents/notes/proposed/architecture/2026-07-24-separate-context-injection-from-turn-execution.md new file mode 100644 index 0000000000..652c3d410a --- /dev/null +++ b/.agents/notes/proposed/architecture/2026-07-24-separate-context-injection-from-turn-execution.md @@ -0,0 +1,75 @@ +# Agent Note: Separate context injection from turn execution + +Status: proposed + +English | [中文](2026-07-24-separate-context-injection-from-turn-execution.zh.md) + +## Problem + +The agent API currently represents supplementary model-facing input in three overlapping ways: callers attach `HookContext[]` through `SendOptions.contexts`, interception and tool hooks return `additionalContexts`, and plugins call `agent.inject()`. These paths eventually write context into the same model history, but they carry different placement, metadata, admission, queue, and turn-lifecycle rules. + +Atomic attachment to an inbox message forces the loop to preserve context through prompt admission, steering conversion, cancellation, and terminal discard. `prompt-prefix` placement then combines context and the direct prompt into one event, requiring a model-hidden envelope so transcript consumers can recover what the user actually wrote. The result makes outbox entries, session projection, and UI replay responsible for a distinction that belongs to the producer. + +Idle `inject()` exposes a second mismatch. Injection does not request model execution, yet the current implementation opens and closes a zero-step `injection` turn solely to satisfy the turn-enclosure invariant and obtain a durability checkpoint. A turn therefore sometimes means “run the agent loop” and sometimes means “persist context without running it.” + +`HookContext` also names its producer rather than its role. The value may come from a native plugin, a hook bridge, prompt admission, or tool post-processing. Its stable meaning is simply additional model-facing context with provenance. + +## Proposal + +Make `inject()` the only caller-facing operation for adding supplementary model-facing input, and define a turn exclusively as one execution of the model loop. + +Remove `SendOptions.contexts`. A caller that owns context delivers it with `inject()` and independently submits the direct message with `send()` or `steer()`. Rename `HookContext` to `AdditionalContext`; retain only `content` and `source`, and remove placement and model-hidden metadata from this shared shape. + +Prompt and tool extension points may still return `additionalContexts`. These values are outputs of the extension point, not attachments captured from a caller's inbox item. Prompt admission runs before `run()` opens a turn. An allowed prompt enters the outbox together with its returned additional contexts; a blocked prompt writes neither and opens no turn. Tool-produced additional contexts enter the same outbox after the corresponding tool results. + +Every additional context becomes an independent `user/message` whose `source` records provenance. Remove `context/message`, prompt-prefix placement, the stable request delimiter, and the prompt envelope. Transcript and UI consumers distinguish direct user messages from injected context by `source`, not by recovering a hidden direct-prompt field from combined model content. + +## Injection lifecycle + +When a turn is open, `inject()` stages the context in the loop outbox. The loop drains the outbox at a safe step boundary, preserving tool protocol adjacency: a context accepted during an assistant tool-call batch appears only after that batch's complete ordered results. Taking the outbox as a whole makes steering and injected context accepted for one boundary visible to the same following request. + +When no turn is open, `inject()` appends its `user/message` immediately and starts a session flush. It does not increment turn numbering, emit `turn/start` or `turn/end`, change agent status, or run the model. The synchronous API still returns before the asynchronous flush settles; `whenIdle()` and agent disposal include outstanding idle-injection flushes in their quiescence boundary. + +A failed idle flush has no legitimate turn or step coordinates. It is reported through logging or a persistence-owned error surface, not by inventing an `agent/error` payload for a nonexistent turn. The in-memory event remains accepted and a later flush may retry persistence. + +The session invariant therefore permits `user/message` between turns while continuing to require turn enclosure for execution events, steering, assistant output, tools, and package-added events by default. Persistence, recovery, resume, fork, and compaction code must treat a valid out-of-turn `user/message` as committed session history rather than an interrupted or discardable turn tail. + +## Extension and caller semantics + +`PromptDecision.content` continues to replace only the direct prompt. `PromptDecision.additionalContexts` and tool-result `additionalContexts` retain FIFO order and individual provenance, but no longer select placement. A waterfall listener that delegates with `next()` must preserve downstream prompt content and additional contexts unless it intentionally returns replacements. + +Caller-driven injection and hook-produced additional context deliberately have different admission ownership. A hook's additional contexts materialize only after that hook allows the prompt or tool result. A caller that invokes `inject(context)` and then `send(prompt)` has already committed context independently; if prompt admission later blocks the prompt, the injected context remains in history. Callers requiring all-or-nothing domain behavior must perform their own preparation before either operation or expose a domain-specific admission seam. + +Cross-session references follow the ordinary composition: the host prepares the snapshot, injects it with session-reference provenance, then sends or steers the readable direct prompt. The target log contains two simple messages, so later source mutation cannot change replay and transcript consumers do not need a prompt envelope. This supersedes the attachment mechanism in the [cross-session reference decision](../../implemented/feature/2026-07-21-cross-session-references.md) while retaining its snapshot and trust-boundary rules. + +This proposal preserves the caller-owned framing decision from [unwrapped injected content](../../implemented/simplification/2026-07-20-unwrap-injected-content-envelopes.md), the one-item turn rule from [one send, one turn](../../implemented/simplification/2026-07-17-one-send-one-turn.md), and narrows the [turn-enclosure decision](../../implemented/architecture/2026-06-15-turn-enclosure-invariant.md) so turns enclose execution rather than every session event. + +## Alternatives considered + +**Keep `SendOptions.contexts` as an atomic attachment.** This preserves all-or-nothing delivery when prompt admission blocks, but it keeps context inside inbox lifecycle state and requires every queue transition and observation event to carry it. The generic agent API should not encode a domain transaction that most callers can express as context injection followed by message delivery. + +**Keep a distinct `context/message` session event.** A separate event makes the out-of-turn exception narrower, but user-role model input would again have two event types with identical projection. `user/message.source` already carries the distinction needed by policy, transcript, and replay consumers. + +**Keep one-shot turns for idle injection.** This retains universal turn enclosure and a convenient flush boundary, but it makes turn counts and turn observers report work that never ran the model. Durability is an independent session concern and can be awaited without fabricating execution. + +**Keep `prompt-prefix` as an optional placement.** Prefix baking can make the context and request appear in one provider message, but it introduces a second representation of the direct prompt and spreads placement handling across admission, steering, logging, replay, and UI code. Producers that require textual framing may include it in their own context content. + +**Let hooks call `inject()` directly instead of returning additional contexts.** Direct injection would erase the extension point's admission ownership: a listener could append context before a downstream listener blocks the operation. Returning `additionalContexts` keeps the waterfall result authoritative while sharing the same post-admission outbox path. + +## Acceptance criteria + +- `SendOptions` and steering inbox records contain no attached contexts; `agent/queued` reports only the retained message and steering facts. +- `AdditionalContext` replaces `HookContext` across prompt interception, tool execution, hook bridges, guards, and context producers, with only `content` and `source`. +- Prompt-prefix placement, prompt envelopes, and `context/message` are absent from public types, durable events, projection, and UI replay. +- Idle `inject()` appends and flushes one sourced `user/message` without a turn or model call; `whenIdle()` and disposal await the flush. +- Active-turn injection and hook-produced contexts drain at safe boundaries after complete tool-result batches and before the request that consumes them. +- Blocked prompt admission opens no turn and appends neither the prompt nor hook-produced additional contexts; independently injected caller context remains. +- Unit, persistence/resume, invariant, ACP/TUI replay, and keyless assembled-application snapshots cover the new event order and durability semantics. + +## Risks + +- Allowing one surface event outside turns weakens a simple invariant and may expose hidden assumptions in persistence scanning, crash repair, forking, compaction, and session queries. +- Consecutive user-role messages replace one baked prompt message; provider adapters and cache behavior must accept and preserve that ordering. +- `inject()` followed by a blocked `send()` leaves context without its intended direct prompt unless the caller accepts the independent-commit contract. +- A synchronous injection API cannot return flush failure. Logging alone is less structured than `agent/error`, while adding a new persistence event solely for this case may create another unnecessary seam. +- Removing attachment, placement, metadata, envelopes, and a durable event type is a broad pre-release migration that must update every producer and consumer atomically. diff --git a/.agents/notes/proposed/architecture/2026-07-24-separate-context-injection-from-turn-execution.zh.md b/.agents/notes/proposed/architecture/2026-07-24-separate-context-injection-from-turn-execution.zh.md new file mode 100644 index 0000000000..1064e7a869 --- /dev/null +++ b/.agents/notes/proposed/architecture/2026-07-24-separate-context-injection-from-turn-execution.zh.md @@ -0,0 +1,75 @@ +# Agent Note: 将上下文注入与轮次执行分离 + +Status: proposed + +[English](2026-07-24-separate-context-injection-from-turn-execution.md) | 中文 + +## 问题 + +agent API 目前用三种相互重叠的方式表示面向模型的补充输入:调用方通过 `SendOptions.contexts` 附加 `HookContext[]`,拦截钩子和工具钩子返回 `additionalContexts`,插件则调用 `agent.inject()`。这些路径最终都会把上下文写入同一份模型历史,但各自携带不同的放置、元数据、准入、队列和轮次生命周期规则。 + +将上下文原子附加到收件箱消息后,agent loop(智能体循环)必须让上下文跟随提示词准入、steering(中途引导)转换、取消和终止丢弃的完整生命周期。`prompt-prefix` 放置方式又会把上下文与直接提示词合并为一个事件,因此 transcript(文本记录)消费方需要依赖模型不可见的封套,才能还原用户实际输入。这样一来,outbox 条目、会话投影和 UI 回放都必须处理本应由生产方负责的区分。 + +空闲状态下的 `inject()` 还暴露了另一处语义错位。注入并不请求模型执行,但当前实现仅为了满足轮次封闭不变量并获得持久性检查点,就会打开并关闭一个零步骤的 `injection` 轮次。于是,轮次有时表示「运行 agent loop」,有时却表示「不运行 agent,仅持久化上下文」。 + +`HookContext` 的名字也描述了生产方,而非该值的职责。它可能来自原生插件、hook bridge、提示词准入或工具后处理;其稳定含义只是带来源信息的额外模型上下文。 + +## 提案 + +将 `inject()` 设为调用方添加补充模型输入的唯一操作,并把轮次严格定义为一次模型循环执行。 + +移除 `SendOptions.contexts`。拥有上下文的调用方通过 `inject()` 交付上下文,再独立使用 `send()` 或 `steer()` 提交直接消息。将 `HookContext` 重命名为 `AdditionalContext`;这个共享结构只保留 `content` 和 `source`,移除放置方式与模型不可见元数据。 + +提示词和工具扩展点仍可返回 `additionalContexts`。这些值是扩展点的输出,而不是从调用方收件箱条目捕获的附件。提示词准入在 `run()` 打开轮次之前执行。提示词获准后,它与返回的额外上下文一同进入 outbox;提示词被阻止时,两者都不写入,也不打开轮次。工具产生的额外上下文则在对应工具结果之后进入同一个 outbox。 + +每项额外上下文都成为独立的 `user/message`,并由 `source` 记录来源。移除 `context/message`、prompt-prefix 放置方式、稳定请求分隔符和提示词封套。transcript 与 UI 消费方通过 `source` 区分直接用户消息和注入上下文,无需从合并后的模型内容中恢复隐藏的直接提示词字段。 + +## 注入生命周期 + +轮次打开时,`inject()` 将上下文暂存在 loop outbox 中。agent loop 会在安全的步骤边界排空 outbox,同时保持工具协议要求的相邻关系:在助手工具调用批次期间接纳的上下文,只能出现在该批次所有有序结果之后。系统整体取走 outbox,确保同一边界接纳的 steering 和注入上下文对后续同一次请求可见。 + +没有打开的轮次时,`inject()` 会立即追加对应的 `user/message` 并启动会话刷新。它不会增加轮次编号、发出 `turn/start` 或 `turn/end`、改变 agent 状态,也不会运行模型。同步 API 仍会在异步刷新完成前返回;`whenIdle()` 和 agent dispose(资源释放)会把尚未结束的空闲注入刷新纳入静止边界。 + +空闲刷新失败时不存在合法的轮次或步骤坐标。系统通过日志或持久化所属的错误接口报告该失败,而不是为不存在的轮次伪造 `agent/error` 载荷。内存中的事件仍已接纳,后续刷新可以重试持久化。 + +因此,会话不变量允许 `user/message` 位于两个轮次之间,同时继续要求执行事件、steering、助手输出、工具事件以及默认的包扩展事件均受轮次边界约束。持久化、恢复、resume、fork、压缩和查询逻辑必须把合法的轮次外 `user/message` 当作已提交会话历史,而不是中断轮次或可丢弃的日志尾部。 + +## 扩展点与调用方语义 + +`PromptDecision.content` 仍只替换直接提示词。`PromptDecision.additionalContexts` 和工具结果的 `additionalContexts` 保留 FIFO 顺序及各自来源,但不再选择放置方式。waterfall(瀑布式事件)监听器调用 `next()` 委托时,必须保留下游返回的提示词内容和额外上下文,除非它有意返回替代值。 + +调用方主动注入与钩子产生的额外上下文具有不同的准入归属。钩子的额外上下文只会在该钩子允许提示词或工具结果后落入日志。调用方执行 `inject(context)` 后再执行 `send(prompt)` 时,上下文已独立提交;后续提示词准入即使阻止该提示词,注入上下文仍保留在历史中。需要领域级全有或全无语义的调用方,必须在执行任一操作前自行完成准备,或提供领域专用的准入 seam。 + +跨会话引用使用普通组合方式:宿主先准备快照,以会话引用来源调用 `inject()`,再发送或 steer 可读的直接提示词。目标日志包含两条简单消息,因此来源会话后续变化不会改变回放,transcript 消费方也不需要提示词封套。本提案取代[跨会话引用决策](../../implemented/feature/2026-07-21-cross-session-references.md)中的附件机制,但保留其快照与信任边界规则。 + +本提案保留[移除注入内容封套](../../implemented/simplification/2026-07-20-unwrap-injected-content-envelopes.md)确立的调用方自主管理框架原则,以及[一次 send、一个轮次](../../implemented/simplification/2026-07-17-one-send-one-turn.md)确立的单条目轮次规则;同时收窄[轮次封闭决策](../../implemented/architecture/2026-06-15-turn-enclosure-invariant.md),使轮次约束执行过程,而不是约束所有会话事件。 + +## 曾考虑的替代方案 + +**保留 `SendOptions.contexts` 作为原子附件。** 提示词准入阻止消息时,这种方式能保留全有或全无交付,但也会让上下文继续成为收件箱生命周期状态的一部分,并迫使每次队列转换和观察事件携带它。大多数调用方都可以通过先注入上下文、再交付消息来表达需求,通用 agent API 不应内置领域事务。 + +**保留独立的 `context/message` 会话事件。** 独立事件可以缩小轮次外事件的例外范围,但面向模型的 user-role 输入会再次拥有两个投影完全相同的事件类型。`user/message.source` 已能为策略、transcript 和回放消费方提供所需区分。 + +**为空闲注入保留一次性轮次。** 这种方式能保留通用轮次封闭和方便的刷新边界,却会让轮次计数与轮次观察方报告从未运行模型的工作。持久性是独立的会话关注点,无需伪造执行即可等待。 + +**保留 `prompt-prefix` 可选放置方式。** 前缀烘焙可以让上下文和请求位于同一条提供方消息中,但它会引入直接提示词的第二种表示,并把放置处理扩散到准入、steering、日志、回放和 UI 代码。需要文本框架的生产方可以直接把它写入自身上下文内容。 + +**让钩子直接调用 `inject()`,而不是返回额外上下文。** 直接注入会破坏扩展点的准入归属:下游监听器阻止操作之前,上游监听器就可能已经追加上下文。返回 `additionalContexts` 能维持 waterfall 结果的最终权威性,同时复用准入后的 outbox 路径。 + +## 验收标准 + +- `SendOptions` 与 steering 收件箱记录不再包含附加上下文;`agent/queued` 只报告保留的消息和 steering 事实。 +- `AdditionalContext` 在提示词拦截、工具执行、hook bridge、guard 和上下文生产方中取代 `HookContext`,且只包含 `content` 与 `source`。 +- 公共类型、持久事件、投影和 UI 回放中均不存在 prompt-prefix 放置方式、提示词封套与 `context/message`。 +- 空闲 `inject()` 在不产生轮次或模型调用的情况下,追加并刷新一条带来源的 `user/message`;`whenIdle()` 和 dispose 会等待该刷新。 +- 活跃轮次注入和钩子产生的上下文会在完整工具结果批次之后的安全边界排空,并在消费它们的请求之前进入日志。 +- 被提示词准入阻止的消息不会打开轮次,也不会追加提示词或钩子产生的额外上下文;调用方此前独立注入的上下文仍保留。 +- 单元测试、持久化与 resume 测试、不变量测试、ACP/TUI 回放测试,以及无需密钥的组装应用快照覆盖新的事件顺序和持久性语义。 + +## 风险 + +- 允许一个表层事件位于轮次之外,会削弱一条简单不变量,并可能暴露持久化扫描、崩溃恢复、fork、压缩和会话查询中的隐含假设。 +- 两条连续的 user-role 消息会取代一条烘焙后的提示词消息;提供方适配器和缓存行为必须接受并保留这一顺序。 +- 如果调用方不能接受独立提交契约,`inject()` 后跟一个被阻止的 `send()` 会留下缺少预期直接提示词的上下文。 +- 同步注入 API 无法返回刷新失败。只记录日志的结构化程度低于 `agent/error`,但仅为此场景增加新的持久化事件也可能产生另一个不必要的 seam。 +- 移除附件、放置方式、元数据、封套和一种持久事件类型,是一次影响面较广的预发布迁移,必须原子更新所有生产方和消费方。 diff --git a/.agents/notes/proposed/feature/2026-06-30-pre-tool-input-rewrite.i18n.yaml b/.agents/notes/proposed/feature/2026-06-30-pre-tool-input-rewrite.i18n.yaml new file mode 100644 index 0000000000..ba5d8cd8c9 --- /dev/null +++ b/.agents/notes/proposed/feature/2026-06-30-pre-tool-input-rewrite.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-30-pre-tool-input-rewrite.md: 5de605e7edf63046b14a125d53072aab9bb5d37e +2026-06-30-pre-tool-input-rewrite.zh.md: eab80764f5dfbd0448dabf0dc3c893ba2ec94928 diff --git a/.agents/notes/proposed/feature/2026-06-30-pre-tool-input-rewrite.md b/.agents/notes/proposed/feature/2026-06-30-pre-tool-input-rewrite.md index e6c5d9eb1e..5de605e7ed 100644 --- a/.agents/notes/proposed/feature/2026-06-30-pre-tool-input-rewrite.md +++ b/.agents/notes/proposed/feature/2026-06-30-pre-tool-input-rewrite.md @@ -2,6 +2,8 @@ Status: proposed +English | [中文](2026-06-30-pre-tool-input-rewrite.zh.md) + ## Problem The [interception-seams Agent Note](../../implemented/feature/2026-06-30-interception-seams.md) defines `tools/pre-execute` as an allow/deny/ask gate over an execution whose identity is already protected and whose arguments are deeply frozen. Claude Code's `PreToolUse` hook also offers `updatedInput`, so a faithful bridge needs an explicit rewrite mechanism. A rewrite cannot be a mutation escape hatch on the existing execution object: it must keep the durable history, audit record, presentation, and executed value consistent. diff --git a/.agents/notes/proposed/feature/2026-06-30-pre-tool-input-rewrite.zh.md b/.agents/notes/proposed/feature/2026-06-30-pre-tool-input-rewrite.zh.md new file mode 100644 index 0000000000..eab80764f5 --- /dev/null +++ b/.agents/notes/proposed/feature/2026-06-30-pre-tool-input-rewrite.zh.md @@ -0,0 +1,53 @@ +# Agent Note: 工具执行前输入重写——一致性设计 + +Status: proposed + +[English](2026-06-30-pre-tool-input-rewrite.md) | 中文 + +## 问题 + +[拦截 seam Agent Note(agent 决策记录)](../../implemented/feature/2026-06-30-interception-seams.md) 将 `tools/pre-execute` 定义为一道针对执行的允许/拒绝/询问门禁,此时执行的身份标识已受保护、参数已被深度冻结。Claude Code 的 `PreToolUse` 钩子还提供了 `updatedInput`,因此忠实的桥接需要一个显式的重写机制。重写不能是对现有执行对象的可变逃逸口:它必须保持持久化历史、审计记录、展示层与实际执行值之间的一致性。 + +## 问题本质:执行前参数的三个读取方 + +在 agent loop(智能体循环)中,工具调用的参数在工具执行之前就已提交到日志并被实时消费方读取: + +1. **`assistant/message`** 在工具分发之前追加——它是 `deriveMessages()` 回放时的模型历史来源,因此携带模型自身输出的工具调用参数。 +2. **`tool/call`** 是持久化的审计记录,在 `ctx.tools.execute()` 之前追加。 +3. **展示层实时读取 `tool/call.arguments`**:ACP(Agent Client Protocol)桥接记住这些参数并传给 `presentResult`;`dsh-tool-bash` 从中派生卡片标题、rawInput、cwd 以及终端/后台处理方式。 + +如果只做执行层面的重写,UI 会显示一条命令而实际运行的是另一条,并且结果会对着错误的参数渲染。注册表目前通过以下方式防止这种失败模式:对 `arguments` 做 structured-clone 并深度冻结,将执行身份属性设为不可写,且不暴露任何可替换它们的测试 shim 或监听路径。重写设计必须维护这一受保护的身份边界,而非削弱它。 + +## 提案 + +重写是一个「身份标识创建前的一致性事务」。当钩子提供 `updatedInput` 时,有效值必须在注册表构造其不可变的 `ToolExecution` 之前确定,并且必须原子地反映到全部三个读取方: + +- `tool/call` 审计事件记录重写后的参数(原始参数保留在一个伴随字段中,作为审计线索——钩子修改了调用,原始参数与生效参数都是值得保留的事实)。 +- 派生历史中的 `assistant/message` 必须与实际执行一致。待评估的选项:就地重写 assistant 消息中的工具调用块(改变模型「看到自己说了什么」),或记录一条单独的修正让下一次请求携带。Claude Code 的模型是让模型看到重写已生效。 +- 展示层(`presentCall`/`presentResult`)读取重写后的参数,使 UI 显示实际运行的内容。 + +在 `PreToolDecision` 当前的触发点上做扩展是不够的:此时两条持久化记录已经存在,执行身份已受保护。实现必须将相关决策移到日志提交之前,或者增加一个专门的、更早的重写决策点来处理待定的模型调用。agent loop 将生效参数提交到历史和审计之后,再构造普通的不可变执行对象,并照常运行现有的允许/拒绝/询问和工具流水线。 + +## 曾考虑的替代方案 + +### 为什么不直接修改执行对象? + +允许 pre-execute 监听器赋值 `exec.arguments` 只能提供执行层面的重写,模型历史、审计和展示层不会随之改变。保持身份标识受保护使得这种局部行为不可表达。在一致性事务实现之前,CC/Codex 桥接对 `updatedInput` 记录日志并发出警告,而非声称已兑现;循环分发点的 `TODO(pre-tool-input-rewrite)` 标记了缺失的更早阶段。 + +## 验收标准 + +- 请求的重写在 `ToolExecution` 身份标识创建之前解决,并原子地反映到全部三个读取方:`tool/call` 审计记录重写后的参数(原始参数保留在伴随字段中)、派生历史与实际执行一致、展示层渲染重写后的参数。 +- 生效的 `ToolExecution.arguments` 在 pre-policy、守卫、分发、post-policy 和最终观测全程保持深度冻结且不可写;不引入任何可变 shim。 +- CC/Codex 桥接兑现 `updatedInput`,不再记录忠实但降级的警告。 + +## 风险 + +- 重写 `assistant/message` 中的工具调用块会改变模型「看到自己说了什么」;是否有提供方在回放时拒绝这种改动,是一个需要通过实验确定的开放问题,必须在决策形状冻结之前解决。 +- 更早的重写阶段改变了 `assistant/message`、`tool/call`、钩子审计事件与执行之间的顺序关系;设计必须固定这一顺序,同时不削弱轮次封闭性或调用/结果邻接性。 + +## 开放问题 + +- 重写 `assistant/message` 中的工具调用块是否会破坏某些提供方在回放时的预期?还是单独的修正更安全? +- 原始参数是否应保留在 `tool/call` 事件(审计)上?如果是,放在什么字段? +- 重写决策是移到日志提交之前,还是成为一个专门的更早 seam?现有的 pre-tool 允许/拒绝钩子如何避免运行两次? +- 这与未来的权限 `ask` 流程(用户批准一个被重写的调用)如何交互? diff --git a/.agents/notes/proposed/feature/2026-07-07-claude-code-and-codex-subagent-backends.i18n.yaml b/.agents/notes/proposed/feature/2026-07-07-claude-code-and-codex-subagent-backends.i18n.yaml new file mode 100644 index 0000000000..ecb4e98def --- /dev/null +++ b/.agents/notes/proposed/feature/2026-07-07-claude-code-and-codex-subagent-backends.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-07-claude-code-and-codex-subagent-backends.md: ee8576f97a9fdef8c88dcad3a73f28b63ca3ebe1 +2026-07-07-claude-code-and-codex-subagent-backends.zh.md: 14e8dde04d9526aaffc0e58be049e13858362887 diff --git a/.agents/notes/proposed/feature/2026-07-07-claude-code-and-codex-subagent-backends.md b/.agents/notes/proposed/feature/2026-07-07-claude-code-and-codex-subagent-backends.md index 620f39c4a4..ee8576f97a 100644 --- a/.agents/notes/proposed/feature/2026-07-07-claude-code-and-codex-subagent-backends.md +++ b/.agents/notes/proposed/feature/2026-07-07-claude-code-and-codex-subagent-backends.md @@ -2,6 +2,8 @@ Status: proposed +English | [中文](2026-07-07-claude-code-and-codex-subagent-backends.zh.md) + ## Problem The subagent seam ([the seam Agent Note](../../implemented/feature/2026-06-21-subagent-capability-seam.md)) hosts multiple named providers on `ctx.subagents`, and the ACP backend ([the ACP backend Agent Note](../../implemented/feature/2026-06-22-acp-subagent-backend.md)) proved the seam generalizes across a process boundary; its Future-providers section explicitly named the Codex app-server and the Claude Code Agent SDK as mechanically similar siblings. Those two are the engines actually worth delegating to today: a harness turn should be able to hand a self-contained task to a real Claude Code or a real Codex — a separate product with its own model, tools, and sandbox — and get back one final answer, without the parent deployment leaking its secrets into the child or the child's behavior silently depending on whatever `~/.claude` / `~/.codex` state exists on the host machine. diff --git a/.agents/notes/proposed/feature/2026-07-07-claude-code-and-codex-subagent-backends.zh.md b/.agents/notes/proposed/feature/2026-07-07-claude-code-and-codex-subagent-backends.zh.md new file mode 100644 index 0000000000..14e8dde04d --- /dev/null +++ b/.agents/notes/proposed/feature/2026-07-07-claude-code-and-codex-subagent-backends.zh.md @@ -0,0 +1,89 @@ +# Agent Note: Claude Code 与 Codex subagent 后端(向外部编码 agent(智能体)的进程外委派) + +Status: proposed + +[English](2026-07-07-claude-code-and-codex-subagent-backends.md) | 中文 + +## 问题 + +subagent seam([seam Agent Note(agent 决策记录)](../../implemented/feature/2026-06-21-subagent-capability-seam.md))在 `ctx.subagents` 上托管多个命名提供方,ACP(Agent Client Protocol)后端([ACP 后端 Agent Note](../../implemented/feature/2026-06-22-acp-subagent-backend.md))证明了该 seam 能跨越进程边界泛化;其「未来提供方」一节明确将 Codex app-server 与 Claude Code Agent SDK 列为机械上相似的兄弟。如今真正值得委派的就是这两个引擎:harness 的一个轮次应能把一个自包含任务交给真实的 Claude Code 或真实的 Codex——一个拥有自身模型、工具与沙箱的独立产品——并取回一个最终答案,同时父部署不向子进程泄漏密钥,子进程行为也不静默依赖宿主机上碰巧存在的 `~/.claude` / `~/.codex` 状态。 + +## 提案 + +两个兄弟提供方包(package),作为 ACP 后端的结构变体,另加一次提取: + +- `@deepseek-ai/dsh-subagent-claude-code`:通过 `@anthropic-ai/claude-agent-sdk` 的 `query()` 驱动一个 Claude Code 子进程(SDK 在父进程中运行,并将其内置的 `claude` CLI(命令行界面)作为子进程 spawn)。提供方名称为 `claude-code`:子进程是 Claude Code 这个*产品*,而非 Anthropic 模型适配器——「claude」保留给未来的 `dsh-llm` 适配器。 +- `@deepseek-ai/dsh-subagent-codex`:spawn `codex app-server`,通过其 JSON-RPC-over-stdio 协议驱动一个 thread/turn,使用包内一个手写的换行 JSON 客户端(约 200–300 行)。 +- `@deepseek-ai/dsh-subagent-process`:纯库(沿用 `subagent-inprocess` 的先例),提取 `dsh-subagent-acp` 已有且两个新后端都需要的内容:凭证环境清洗(`buildChildEnv`)、EOF → SIGTERM → SIGKILL 的 dispose(资源释放)阶梯,以及新的隔离配置目录辅助函数(`mkdtemp` 创建、尽力删除)。ACP 后端迁移到该库上;`bash-local` 的兄弟副本保持不动以限制变更范围。 + +两个提供方逐字复制 ACP 后端的 seam 姿态:每次 `start` 创建全新子进程、恰好一次提示词往返、所有能力均为 `false`、`inheritsParentContext: false`、忽略 `request.parent`/`request.agentOptions`、`id = SessionId(randomUUID())`,且 `result` 从不 reject——子进程级失败扁平化为 stop reason,原始错误则通过 `onError` spec 回调送到 `ctx.logger`。模型暴露无需新代码:每个提供方各加载一次 `dsh-tool-subagent`,使用不同的 `toolName`(`subagent_claude_code`、`subagent_codex`)。无需新的会话事件——唯一的模型可见产物是工具结果,因此可重建性与 ACP 完全相同。明确边界:会话日志重建模型可见的 transcript(文本记录),而不是工作区变更历史——获准写入的子进程将文件作为日志之外的环境副作用进行修改,与 bash 工具和 ACP 后端现有行为完全一致;回放复现请求,而非磁盘。 + +## 已验证的接口事实(固定版本) + +两个集成面在本提案之前均已针对固定版本进行了验证——阅读类型与打包源码、运行无需密钥的 spike——而非仅依赖厂商文档。固定版本是验证基线,不是运行时契约:后端不执行运行时版本探测(无 `codex --version` 门禁、无 SDK 版本嗅探)。兼容性在开发时强制执行——每次依赖升级都会针对真实加载路径重跑无密钥套件——在运行时则通过大声失败来保障:协议层面的意外通过 `onError` 结算为 `error`,绝不静默异常。 + +**`@anthropic-ai/claude-agent-sdk` 0.3.202。** `options.env` 会替换子进程环境(不与 `process.env` 合并),恰好满足清洗需求。`settingSources` 默认加载所有文件系统设置——隔离要求显式传入 `[]`。结果子类型为 `success` | `error_during_execution` | `error_max_turns` | `error_max_budget_usd` | `error_max_structured_output_retries`。中止时 SDK 自行逐级加强对 CLI 子进程的终止措施:立即关闭 stdin,约 2 秒后若子进程未退出则发送 SIGTERM(已观察到;无残留进程)——无需自定义 kill 回退。`outputFormat: {type: 'json_schema'}` 和 `agents` 选项已存在,为 seam 的 `outputSchema` 能力和命名 subagent 类型提供了未来着陆点;两者均不在本 Agent Note 范围内。 + +**codex CLI 0.142.5,`codex app-server`(v2 词汇)。** LF 分隔的 JSON,JSON-RPC 2.0 形状但省略 `"jsonrpc"` 头。 + +- 生命周期:`initialize{clientInfo}` + `initialized` → `thread/start`(接受 `cwd`、`model`、`sandbox`、`approvalPolicy`、`ephemeral`;未认证即可成功)→ `turn/start{threadId, input:[{type:'text',text}]}` 立即返回一个 `inProgress` 的轮次;终止信号是携带 `Turn{status: completed|interrupted|failed|inProgress, error}` 的 `turn/completed` 通知。 +- 审批是服务端发起的请求——`item/commandExecution/requestApproval`、`item/fileChange/requestApproval`、`item/permissions/requestApproval`、`item/tool/requestUserInput`、`mcpServer/elicitation/request`——以 `accept`/`decline` 系列决策应答。 +- 认证:`account/login/start{type:'apiKey', apiKey}` 是一等 RPC,`account/read` 报告 `requiresOpenaiAuth`——且未认证的 `turn/start` 不会快速失败(它会挂在重试中),因此后端必须预检认证状态,并在失败时大声结算为 `error`,而非等待轮次。 +- 隔离:`CODEX_HOME` 重定向被尊重(`initialize` 响应会回显它,测试可据此断言隔离),`ephemeral: true` 的 thread 不留任何会话文件。 + +## 隔离与凭证 + +部署只使用 API key 认证,子进程不得看到宿主用户的 Claude Code / Codex 配置:行为必须只由 `cordis.yml` 决定。每次运行获得一个全新的 `mkdtemp` 配置目录——Claude Code 使用 `CLAUDE_CONFIG_DIR`(并显式设置 `settingSources: []`),Codex 使用 `CODEX_HOME`——dispose 时尽力删除;配置字段也可以固定一个持久目录。子进程环境通过提取逐字复用 ACP 后端的 `buildChildEnv` 语义:转发环境变量,但移除凭证形态的变量(`/KEY|SECRET|TOKEN/i`),再叠加 `config.env`——因此 `PATH`、`HOME`、`TMPDIR`、locale 和代理变量保留,CLI 正常运行;只有环境中的凭证形态变量被清洗(Claude Code 的 `ANTHROPIC_API_KEY` 通过 `config.env` 显式进入),Codex key 则通过 `account/login/start` RPC 进入隔离的 `CODEX_HOME`,而非手写 `auth.json`。 + +## 权限与审批策略 + +每个后端不压缩为 ACP 单一的 `permission: allow|reject` 旋钮,而把引擎原生词汇作为配置暴露,并采用保守默认值:Claude Code 获得 `permissionMode`(默认 `default`)以及 `permission: allow|reject`(默认 `reject`),后者作为所有漏过请求的 `canUseTool` 自动应答;Codex 获得 `sandboxMode`(默认 `read-only`)和 `approvalPolicy`(默认 `never`),以及同一个 `permission` 后备值,用来应答仍然到达的审批请求。默认值刻意做到不造成损害(开箱即用的子进程无法写文件);示例演示如何开放权限(`acceptEdits` / `workspace-write`)。机械规则是:每一个服务端发起的请求都由程序迅速结算——枚举出的审批/用户输入/elicitation 请求按配置策略应答,未知请求方法用 JSON-RPC method-not-found 错误响应(绝不保持 pending),未知通知被消费——因此任何子进程请求都不会因等待永远不会到来的应答而卡住轮次。这一版中提示词不会到达人类,与 ACP 一致。 + +## StopReason 映射 + +Claude Code:`success` → `completed`;`error_max_turns`、`error_during_execution`、`error_max_budget_usd`、`error_max_structured_output_retries` → `error`(与 ACP 对 `max_turn_requests` 的处理对齐:未完成的任务不是成功);生成器中止 → `aborted`;未知值 → `error`。Codex:`Turn.status` 为 `completed` → `completed`;`interrupted` → `aborted`;`failed` 且 `codexErrorInfo: 'contextWindowExceeded'` → `max-tokens`,其他 `failed` → `error`;传输/spawn/认证预检失败 → `error`(若已请求取消则为 `aborted`)。两者中,`cancel()` 采用 ACP 形状:标志位 + abort/interrupt + 一个 cancel-settled 竞争分支,使不合作的子进程无法阻塞结果。 + +活性姿态,明确声明:teardown 时序是配置项,轮次时长不是。两个后端将 dispose 阶梯的宽限期作为带默认值的已验证配置字段(ACP 后端的 `disposeEofGraceMs`/`disposeGraceMs` 形状,由提取库承载),但刻意不设轮次时长或启动超时——与 ACP 一致:轮次期间的活性由调用方通过 `cancel()`/abort signal 掌控,subagent 轮次持续数分钟也属合理,而 Codex 认证预检消除了唯一已验证的必然挂起场景;需要墙钟上限的部署从父侧取消即可。 + +## 测试 + +依照根 AGENTS.md 规则在每个层级明确命名,并预先消除风险: + +- **无密钥单元/集成测试**:每个后端都镜像 ACP spec 清单(往返和输出累积、每种 stop 映射、两条取消路径、已中止、两种策略下的权限自动应答、未知消息容错、错误命令的 spawn 失败、HMR(热模块替换)提供方清理、导出形状、子进程环境隔离断言和临时目录删除;Codex 另加认证预检失败路径)。Claude Code harness 是通过 `pathToClaudeCodeExecutable` 接入真实 SDK 的脚本化假 `claude` 可执行文件——一个 spike 已在 24ms 内完成端到端无密钥验证(假 CLI 应答一次 `control_request/initialize`,并讲 plain stream-json,约 40 行)。Codex harness 是讲已验证协议格式的脚本化 mock app-server 子进程,沿用 `mock-acp-server.ts` 形状。 +- **有密钥 e2e 测试**:每个后端的真实引擎执行并由磁盘验证真实文件工作,固定使用开放后的配置,以免验收与不造成损害的默认值冲突——Claude Code 使用 `permissionMode: 'acceptEdits'`,Codex 使用 `sandboxMode: 'workspace-write'` + `approvalPolicy: 'never'`;自跳过会准确报告缺失的是二进制还是 key。CI 没有密钥,因此依照有密钥策略在本地运行。 +- **快照测试**:以 `TODO(claude-code-subagent-replay)` / `TODO(codex-subagent-replay)` 推迟——即 ACP 后端也推迟的独立回放形状([按会话回放 Agent Note](../../implemented/testing/2026-06-22-subagent-snapshot-replay.md));在此期间由无密钥套件提供确定性覆盖。 + +## 曾考虑的替代方案 + +### 为什么不用官方 `@openai/codex-sdk` 而手写客户端? + +dispose 阶梯和环境清洗要求拥有子进程(spawn 参数、env、信号、exit 等待);SDK 隐藏了进程。协议格式(wire format)极其简单(LF JSON),形状可按固定版本生成(`codex app-server generate-json-schema`),仓库先例(`hook-protocol`)是拥有薄协议核心而非包装他人的运行时。SDK 能节省协议演进的维护成本,但代价是失去本后端存在的意义所在的精确控制。 + +### 为什么不用模型可见的 `subagent_type` 参数(单一 Task 风格工具)? + +Claude Code 自身的 Task 工具将 subagent 类型放在模型可见的 schema 中,选择一个提示词 + 工具集人格。这里的选择是在执行引擎之间做出的,而只有部署者知道哪些引擎配置了凭证——因此选择留在部署配置层,保持 `dsh-tool-subagent` 文档中的「一个提供方对应一个工具」契约。人格风格的类型选择器应是针对工具的另一个 Agent Note,而非针对后端。 + +### 为什么不用登录态凭证和用户自身的配置? + +继承 `~/.claude` / `~/.codex`(订阅登录、用户设置、skill(技能)、MCP 服务器)会使子进程行为依赖宿主机状态,并在 ACP 后端和 bash 执行器确立的「凭证通过 `config.env` 显式进入,绝不隐式继承」规则上打开一个隐式例外。仅 API key 加强制配置目录隔离使运行可复现;需要共享状态的部署可以有意将配置目录字段指向一个持久目录。 + +### 为什么不为 Claude Code 无密钥测试注入驱动层 seam? + +注入假的 `query()` 会 mock 我们自己的边界,使真实 SDK 加载路径未被测试(docs/testing.md 中的 real-over-mock 策略)。曾考虑此方案的风险——SDK↔CLI 的 stream-json 控制协议是内部实现——已被 spike 消除:假 CLI harness 今天能对真实固定版本的 SDK 正常工作。如果 SDK 升级破坏了 mock,无密钥套件会让升级 PR(Pull Request)失败,这正是门禁在发挥作用。 + +### 为什么不用 ACP 适配器(如 `claude-code-acp`)复用既有后端? + +社区 shim 将两个引擎包装为 ACP,这会使它们在 `dsh-subagent-acp` 上变成「仅配置」。但这在 harness 与引擎之间插入了一个非官方的第三方层,抹去了本 Agent Note 暴露的原生控制面(permissionMode、sandboxMode/approvalPolicy、配置目录隔离、apiKey RPC),并以 shim 的发布节奏替换了第一方协议的稳定性。第一方接口——Agent SDK 和 app-server——才是受支持的集成点。 + +## 验收标准 + +在两个引擎和密钥均已配置的机器上:一个 REPL 驱动的模型通过 `subagent_claude_code` 完成一个真实文件任务,通过 `subagent_codex` 完成另一个,工具结果为子进程的最终答案,父会话日志中仅有 `tool/call` + `tool/result`。无密钥套件在无凭证环境下以逐文件 100% 覆盖率通过,断言隔离(清洗后的子进程环境、dispose 后无残留临时配置目录),并断言 `~/.claude` / `~/.codex` 的存在与否不影响子进程行为。取消父轮次后,两个后端在有界时间内完全停稳,无残留子进程。e2e 套件干净地自跳过,命名缺失的前置条件。 + +## 风险 + +- `codex app-server` 被 CLI 标记为实验性,其 v1/v2 词汇共存;客户端固定 0.142.5、仅实现 v2、对未知方法/通知消费而不崩溃,但未来 codex 升级仍可能迫使返工(每次升级重新生成 schema 并重跑无密钥套件——这是上述「不做运行时版本探测」立场背后的开发时强制执行)。 +- Claude Code 假 CLI mock 依赖一个内部协议:任何 SDK 升级都必须通过无密钥套件,控制协议的破坏性变更意味着返工 mock(回退方案:上面否决的驱动注入 seam 成为逃生舱口)。 +- SDK 的 optionalDependencies 每平台约 280MB——已接受,限制在单个后端包内。 +- SDK 的 SIGKILL 分支(EOF→SIGTERM 之后)未被观察到,信任其实现;e2e 保留无残留进程断言。 +- Codex 是部署前置条件(无 npm 内置二进制);缺失或不兼容的二进制以大声的 spawn/协议 `error` 呈现,而非版本探测。 +- 每次运行付出一个全新子进程的代价,且仅最终答案浮出——思考、工具卡片和用量被消费后丢弃;连接池、中间进度浮出、`sendMessage`/`resume`、通过 SDK 的 `outputFormat` 实现 `outputSchema`、以及通过 SDK 的 `agents` 选项实现命名 subagent 类型,均为刻意推迟。 diff --git a/.agents/notes/proposed/feature/2026-07-08-interactive-side-sessions.i18n.yaml b/.agents/notes/proposed/feature/2026-07-08-interactive-side-sessions.i18n.yaml new file mode 100644 index 0000000000..b815cfdd2a --- /dev/null +++ b/.agents/notes/proposed/feature/2026-07-08-interactive-side-sessions.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-08-interactive-side-sessions.md: dfd325babe215782c9c1cbec3fd9f874783af7ab +2026-07-08-interactive-side-sessions.zh.md: 9bc9d5c94fdef893134844551a594acc39a99d3b diff --git a/.agents/notes/proposed/feature/2026-07-08-interactive-side-sessions.md b/.agents/notes/proposed/feature/2026-07-08-interactive-side-sessions.md index f2e3e74ca1..dfd325babe 100644 --- a/.agents/notes/proposed/feature/2026-07-08-interactive-side-sessions.md +++ b/.agents/notes/proposed/feature/2026-07-08-interactive-side-sessions.md @@ -2,6 +2,8 @@ Status: proposed +English | [中文](2026-07-08-interactive-side-sessions.zh.md) + ## Problem A user may want to explore a question from a live session without changing its main context. Existing primitives do not expose that product shape: [session-store fork](../../implemented/feature/2026-06-30-session-store-fork-api.md) creates an unattached session, while [fork subagents](../../implemented/feature/2026-06-21-subagent-capability-seam.md) are model-driven tasks whose transcript collapses into one tool result. Neither gives the user a separate conversation, and neither records a conclusion back into the parent with provenance. diff --git a/.agents/notes/proposed/feature/2026-07-08-interactive-side-sessions.zh.md b/.agents/notes/proposed/feature/2026-07-08-interactive-side-sessions.zh.md new file mode 100644 index 0000000000..9bc9d5c94f --- /dev/null +++ b/.agents/notes/proposed/feature/2026-07-08-interactive-side-sessions.zh.md @@ -0,0 +1,41 @@ +# Agent Note: 交互式侧会话与合并回写 + +Status: proposed + +[English](2026-07-08-interactive-side-sessions.md) | 中文 + +## 问题 + +用户可能希望在不改变当前会话主上下文的前提下,探索一个来自活跃会话的问题。现有原语无法提供这种产品形态:[会话存储 fork](../../implemented/feature/2026-06-30-session-store-fork-api.md)创建的是一个无关联的会话,而 [fork subagent](../../implemented/feature/2026-06-21-subagent-capability-seam.md)是模型驱动的任务,其 transcript(文本记录)会折叠为一条工具结果。两者都不能给用户一个独立的对话,也都不能将结论带着出处信息记录回父会话。 + +## 提案 + +**侧会话(side session)** 是一个普通的活跃会话,从源会话的最后一个已完成轮次 fork 而来,绑定到自己的 agent(智能体),定位为只读顾问,并能**合并回写**一条精简笔记。 + +- **Fork 并绑定:** 以父会话的平衡已完成轮次前缀创建子会话,并在其元数据中标记 `parentSession` 与 `seedLength`。这组合了 `ctx.agents.create({ seed, meta })`;不新增核心服务或会话存储方法。 +- **顾问定位:** 创建后注入一条插件来源的 `context/message`,告知子会话只做解释,不执行变更或继续任务。保持系统提示词逐字节一致,可在继承的历史上保留提供方的前缀缓存。 +- **合并回写:** 向子会话请求一条有长度上限的 handback,然后向父会话注入一条插件来源的 `context/message`。父会话的下一次请求在其日志位置看到该消息,保持回放与[请求可重建性](../../implemented/architecture/2026-07-05-reconstructable-requests.md),无需新增会话事件。 +- **呈现:** 调用方式、会话切换与 handback 渲染属于首个客户端拥有的界面。本 Agent Note(agent 决策记录)仅规定与界面无关的机制。 + +回退产品化、会话树视图、面向模型的侧会话工具,以及 `forkName`/`mergedInto` 元数据均不在本 Agent Note 范围内。一次真实适配器 spike 已验证了源日志隔离、继承上下文、多轮子会话交互,以及合并回写在父会话下一轮次中的可见性。 + +## 曾考虑的替代方案 + +- **使用 subagent seam:** 否决。侧会话是用户驱动的、客户端可见的,且可能存活超过父会话的一个轮次;subagent 是模型驱动的运行,返回一条工具结果。 +- **修改子会话的系统提示词:** 默认否决,因为任何字节变化都会从第零个 token 起使前缀缓存失效。部署方仍可选择这种更强的隔离方式。 +- **新增 `sidechat/*` 事件:** 延后。插件来源的 `context/message` 已提供持久性、出处与回放能力;只有当某个界面需要差异化渲染时,专用事件才有正当理由。 +- **现在就绑定一个协议界面:** 否决。当前 UI 由客户端拥有。实时呈现最终必须从持久消息派生,以使回放渲染出相同的记录。 + +## 验收标准 + +- Fork 不改变源会话,创建的子会话具有平衡的已完成轮次前缀、`parentSession`、`seedLength`,以及逐字节一致的系统提示词。 +- 顾问定位在子会话追加历史的头部恰好添加一条插件来源的 `context/message`,而非修改其系统提示词。 +- 合并回写恰好添加一条有长度上限的 `context/message`,来源为 `plugin: sidechat`;父会话的下一次请求与回放在相同位置看到它。 +- 父会话与子会话并发运行,日志和流之间无串扰。 +- 单元测试覆盖 fork/attach 与合并回写;快照覆盖率随首个绑定界面一起落地。 + +## 风险 + +- 只读行为在 `tools/pre-execute` 拒绝门禁强制执行之前仅为建议性质;[拦截 seam](../../implemented/feature/2026-06-30-interception-seams.md) 可在不改变本机制的前提下添加该门禁。 +- 经过压缩(compaction)的源会话 fork 出的是其压缩视图,因此绑定的界面应当告知用户子会话继承的是摘要而非被替换的轮次。 +- 反复的 handback 会消耗父会话上下文。每次合并的长度上限约束了单条笔记的大小;后续的合并整理属于上下文压缩的职责。 diff --git a/.agents/notes/proposed/feature/2026-07-13-stream-workflow-progress-through-tool-calls.i18n.yaml b/.agents/notes/proposed/feature/2026-07-13-stream-workflow-progress-through-tool-calls.i18n.yaml new file mode 100644 index 0000000000..5c7c7e9cc1 --- /dev/null +++ b/.agents/notes/proposed/feature/2026-07-13-stream-workflow-progress-through-tool-calls.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-13-stream-workflow-progress-through-tool-calls.md: 668d38b38cab90f6ee9b613d1101d4d44302aa8a +2026-07-13-stream-workflow-progress-through-tool-calls.zh.md: b0daba0c62c9b06f33f5e3c6319f90670941e762 diff --git a/.agents/notes/proposed/feature/2026-07-13-stream-workflow-progress-through-tool-calls.md b/.agents/notes/proposed/feature/2026-07-13-stream-workflow-progress-through-tool-calls.md index 0c6516080a..668d38b38c 100644 --- a/.agents/notes/proposed/feature/2026-07-13-stream-workflow-progress-through-tool-calls.md +++ b/.agents/notes/proposed/feature/2026-07-13-stream-workflow-progress-through-tool-calls.md @@ -2,6 +2,8 @@ Status: proposed +English | [中文](2026-07-13-stream-workflow-progress-through-tool-calls.zh.md) + ## Problem The workflow engine intentionally emits balanced `workflow/*` observation events for run, phase, narration, and child-agent progress, but no production consumer presents them. Editors therefore show one pending workflow tool card until the final result even while the engine already reports which phase is active, what the script logged, and which children started or settled. The [dynamic-workflows decision](../../implemented/feature/2026-07-05-dynamic-workflows.md) explicitly reserves ACP progress UI for this event stream. diff --git a/.agents/notes/proposed/feature/2026-07-13-stream-workflow-progress-through-tool-calls.zh.md b/.agents/notes/proposed/feature/2026-07-13-stream-workflow-progress-through-tool-calls.zh.md new file mode 100644 index 0000000000..b0daba0c62 --- /dev/null +++ b/.agents/notes/proposed/feature/2026-07-13-stream-workflow-progress-through-tool-calls.zh.md @@ -0,0 +1,43 @@ +# Agent Note: 通过工具调用流式传输工作流进度 + +Status: proposed + +[English](2026-07-13-stream-workflow-progress-through-tool-calls.md) | 中文 + +## 问题 + +工作流引擎有意为 run、phase、narration 和子 agent(智能体)进度发出成对的 `workflow/*` observation 事件,但目前没有生产消费方呈现这些事件。因此,编辑器在最终结果返回之前只显示一张 pending 状态的工作流工具卡片,尽管引擎已经报告了当前活跃的 phase、脚本日志内容以及哪些子 agent 已启动或已结束。[动态工作流决策](../../implemented/feature/2026-07-05-dynamic-workflows.md)明确将 ACP(Agent Client Protocol)进度 UI 保留给这一事件流。 + +如果让 `dsh-acp` 直接监听工作流事件,就会反转能力边界:通用的 UI 桥接层将依赖一个可选的工作流包(package),并对一个工具名做特殊处理。工具流水线已经拥有实时更新所需的路由信息(agent 和 call id),但只暴露了纯粹的 pending/final 展示器,因此长时间运行的工具没有提供方无关的方式在二者之间报告瞬态 UI 状态。 + +## 提案 + +为 `dsh-tools` 添加一条实时进度通道。注册表所有的 `ToolExecution` 新增 `reportProgress(view): boolean`,其中 `view` 是一个独立的、提供方无关的通用进度快照,包含可选的替换标题和面向 UI 的内容块。进度不能更改调用的 args 派生卡片标签、kind、原始输入、locations、terminal intent 或 diff intent;它只更新在最初选定的展示方式内的实时标题/内容。当执行处于活跃状态时,该方法校验并快照 view,然后分发一个受限的、agent 作用域的 `tools/progress` observation,携带权威的执行标识与快照。一旦 final-result 处理开始,方法返回 `false` 且不再分发,因此迟到的异步报告者无法覆盖终态卡片。观察者异常会被记录日志,不会导致工具失败。 + +`dsh-acp` 以通用方式消费 `tools/progress`。它通过既有的 agent 到会话映射解析执行所属的 agent,并为同一 call id 发出 in-progress 的 `tool_call_update`。由于报告仅在工具执行流水线内可用,持久化的 `tool/call` 及其 ACP `tool_call` 始终先于第一条 update;在 `tools/result` 之前关闭报告者,确保进度更新不会出现在 completed/failed 卡片之后。进度是实时 UI 状态,而非模型输入或持久历史:会话回放继续从 `tool/call` 和 `tool/result` 重建 pending 与 final 卡片,无需重放瞬态更新。 + +`dsh-tool-workflow` 成为第一个生产者。每次工具执行在调用 `ctx.workflows.start()` 之前安装一个紧凑的事件捕获器,因为合法的引擎可能在 `start()` 内部同步发出进度。在调用返回之前,捕获器将观察到的事件按 `WorkflowRunInfo.id` 归约为候选状态;随后选取返回的 `WorkflowRun.id`,丢弃其他候选,报告累积的快照,并将后续匹配事件直接路由。如果 `start()` 抛出异常,捕获器被 dispose(资源释放),其候选状态被丢弃。这在不向 `WorkflowStartRequest` 添加观察者关联、也不要求进度等到 `start()` 返回的前提下,保持了引擎的可替换性。 + +归约器消费既有的 start、phase、log、agent-start、agent-end 和 end 事件,报告一个替换快照,包含当前 phase、最新日志行、活跃子 agent 标签以及 completed/failed/cancelled 计数。它不累积 narration transcript(文本记录);已结束的子 agent 离开活跃集合,变为计数器。`workflow/end`、工具结算或插件 dispose 移除归约器条目和事件捕获器。六种工作流事件及其元数据、成对的子 agent 生命周期、run handle、取消通道和观察者隔离保持不变;第三方观察者可继续直接消费这些事件。 + +更新工具执行/展示文档、生成的事件与 API 目录、工作流包文档以及工作流数据结构目录。ACP 集成覆盖率必须使用脚本化的模型边界测试真实的工作流工具和 worker seam;主 ACP 快照套件新增一个 workflow-progress 场景,因为这改变了面向编辑器的 transcript。 + +## 曾考虑的替代方案 + +**删除工作流 observation 表面。** 在[折叠工作流简化提案](../../rejected/simplification/2026-07-12-collapse-workflow-to-foreground-core.md)中被否决:这些事件及其成对生命周期是有意设计的,缺少的是消费方。 + +**让 ACP 直接了解工作流。** 这可以将 `WorkflowRunInfo` 映射到会话和卡片,但会使通用桥接层依赖一个可选能力,并绕过「工具拥有展示意图」的规则。工具进度通道为每个长时间运行的工具解决了相同的路由问题。 + +**将每条进度更新持久化为会话事件。** 这会使实时 narration 可回放,但会用一种状态永久膨胀日志,而该状态的权威持久结果已经是工具调用/结果对。如果可恢复的工作流进度成为产品需求,需要一个工作流日志化设计,而非伪装成持久事实的 UI 快照。 + +## 验收标准 + +- `ToolExecution.reportProgress()` 由注册表所有、agent 作用域、快照化、观察者隔离,且在终态处理开始后返回 `false` 而不分发。 +- ACP 将进度路由到正确的实时会话中的正确调用;不同会话中的并发工作流不能串扰,且 `tool_call_update` 不会出现在其 `tool_call` 之前或终态更新之后。 +- 工作流进度显示当前 phase、最新日志行、活跃子 agent 和结果计数,同时保留所有既有 `workflow/*` 事件和 run 语义;一个在 `start()` 内部同步发出 start、phase、log、child 和 end 事件的 seam 测试引擎不会丢失任何归约器状态。 +- 取消、worker 死亡、工具失败、会话关闭和插件 dispose 释放归约器状态;回放仅发出持久的 pending/final 卡片对。 +- 单元测试、工作流集成测试、ACP 集成测试、快照、类型检查、覆盖率、doc-sync(文档同步门禁)、module-graph、构建和 hygiene 门禁全部通过。 + +## 风险 + +本提案向工具 seam 添加了一个公开的实时进度方法和事件,因此实现方必须精确维护 active/terminal 边界,并在观察者看到快照之前将其分离。pre-start 捕获器可能短暂观察到无关的工作流 run,因此它仅按 run id 持有紧凑的候选状态,并在 `start()` 返回后立即丢弃所有不匹配的候选。一个工作流可能发出大量进度变更;有界归约器避免了 transcript 增长,但在关联完成后仍会为每个有意义的事件发送一条 UI 更新。如果经测量的客户端需要合并更新,这必须是一个带默认值的、经过校验的桥接配置,而非硬编码的节流。瞬态进度在回放时有意消失,因此最终工具结果仍是唯一持久的工作流卡片内容。 diff --git a/.agents/notes/proposed/process/2026-06-11-api-extractor-reports.i18n.yaml b/.agents/notes/proposed/process/2026-06-11-api-extractor-reports.i18n.yaml new file mode 100644 index 0000000000..8f00d8b537 --- /dev/null +++ b/.agents/notes/proposed/process/2026-06-11-api-extractor-reports.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-11-api-extractor-reports.md: f110bfe3353e65442f218336aca3e9d492ac2341 +2026-06-11-api-extractor-reports.zh.md: 8cb7353e10a8811b20ccd539de15f8e06b76e6ae diff --git a/.agents/notes/proposed/process/2026-06-11-api-extractor-reports.md b/.agents/notes/proposed/process/2026-06-11-api-extractor-reports.md index b32dc7e2af..f110bfe335 100644 --- a/.agents/notes/proposed/process/2026-06-11-api-extractor-reports.md +++ b/.agents/notes/proposed/process/2026-06-11-api-extractor-reports.md @@ -2,6 +2,8 @@ Status: proposed +English | [中文](2026-06-11-api-extractor-reports.zh.md) + > Split out from the original "Doc-sync and API reports" Agent Note (2026-06-11). Parts 1-2 (doc-block typechecking, event-taxonomy verification) shipped — see [doc-sync enforcement](../../implemented/process/2026-06-11-doc-sync-enforcement.md). This is the deferred part 3, kept as a standalone proposal. ## Problem diff --git a/.agents/notes/proposed/process/2026-06-11-api-extractor-reports.zh.md b/.agents/notes/proposed/process/2026-06-11-api-extractor-reports.zh.md new file mode 100644 index 0000000000..8cb7353e10 --- /dev/null +++ b/.agents/notes/proposed/process/2026-06-11-api-extractor-reports.zh.md @@ -0,0 +1,32 @@ +# Agent Note: API extractor 报告 + +Status: proposed + +[English](2026-06-11-api-extractor-reports.md) | 中文 + +> 从最初的「doc-sync(文档同步门禁)与 API 报告」Agent Note(agent 决策记录)中拆出(首次提出于 2026-06-11)。第 1 至第 2 部分(文档块类型检查、事件分类体系校验)已交付,见 [doc-sync 强制](../../implemented/process/2026-06-11-doc-sync-enforcement.md)。本文是被推迟的第 3 部分,作为独立提案保留。 + +## 问题 + +公开 API 的变更是不可见的:没有任何机制将「此次提交改变了公开接口」变为一个显式、可评审的事实。评审者阅读 diff 时可能遗漏某个导出类型新增了字段,或某个方法签名发生了变化。 + +## 提案 + +使用 api-extractor(或 `tsc --emitDeclarationOnly` 加一份规范化的公开接口导出)为每个包(package)生成一份签入仓库的 `etc/<pkg>.api.md`;CI 在重新生成结果与已签入报告不一致时失败。这样,每一次公开 API 变更都会成为评审者(或评审 agent(智能体))必须看到的一行 diff。 + +## 曾考虑的替代方案 + +**`tsc --emitDeclarationOnly` 加规范化的公开接口导出**:如果 api-extractor 过于笨重,这是更轻量的机制;两者都能满足提案所需的「签入仓库、可 diff」的报告形态。 + +## 验收标准 + +- 每个包都有一份签入仓库的 `etc/<pkg>.api.md`;CI 在重新生成结果与已提交报告不一致时失败。 +- 公开 API 变更(新增导出、字段放宽、签名变化)在评审中以报告 diff 行的形式可见。 + +## 风险 + +该依赖笨重且难以调教(这正是它被推迟的原因),且报告格式会随编译器升级而变动,增加一个维护面;在各包尚未发布的阶段,收益有限。 + +## 推迟原因 + +在 doc-sync 落地时被推迟:对于一个内部 monorepo,评审者已经能看到源码 diff,价值不高;且依赖笨重、难以调教。如果各包将来对外发布,再重新评估——届时一份稳定、可 diff 的公开接口报告才值得其维护成本。 diff --git a/.agents/notes/proposed/process/2026-06-11-architectural-conformance.i18n.yaml b/.agents/notes/proposed/process/2026-06-11-architectural-conformance.i18n.yaml new file mode 100644 index 0000000000..624b671a37 --- /dev/null +++ b/.agents/notes/proposed/process/2026-06-11-architectural-conformance.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-11-architectural-conformance.md: f7cb0d7397d4e03df225f68417da43b1fec8de62 +2026-06-11-architectural-conformance.zh.md: aa25ef6d2772642885ef268bd548fc6dad40d3cf diff --git a/.agents/notes/proposed/process/2026-06-11-architectural-conformance.md b/.agents/notes/proposed/process/2026-06-11-architectural-conformance.md index 006aa76ad1..f7cb0d7397 100644 --- a/.agents/notes/proposed/process/2026-06-11-architectural-conformance.md +++ b/.agents/notes/proposed/process/2026-06-11-architectural-conformance.md @@ -2,6 +2,8 @@ Status: proposed +English | [中文](2026-06-11-architectural-conformance.zh.md) + ## Problem Two architectural guarantees currently live only in prose: (1) nothing depends on the concrete loop package ([the microkernel promise](../../implemented/architecture/2026-06-11-microkernel-event-taxonomy.md)), and (2) every LlmAdapter speaks the chunk protocol correctly. Both should be mechanical ([the quality-gates principle](../../implemented/process/2026-06-11-quality-gates.md)). diff --git a/.agents/notes/proposed/process/2026-06-11-architectural-conformance.zh.md b/.agents/notes/proposed/process/2026-06-11-architectural-conformance.zh.md new file mode 100644 index 0000000000..aa25ef6d27 --- /dev/null +++ b/.agents/notes/proposed/process/2026-06-11-architectural-conformance.zh.md @@ -0,0 +1,36 @@ +# Agent Note: 架构一致性——依赖规则与适配器套件 + +Status: proposed + +[English](2026-06-11-architectural-conformance.md) | 中文 + +## 问题 + +目前有两项架构保证仅存在于行文中:(1)没有任何组件依赖具体的 loop 包(package)([微内核承诺](../../implemented/architecture/2026-06-11-microkernel-event-taxonomy.md));(2)每个 LlmAdapter 都正确遵循分片协议。二者都应由机制强制执行([质量门禁原则](../../implemented/process/2026-06-11-quality-gates.md))。 + +## 提案 + +**dependency-cruiser** 配合以下规则: + +- `packages/*`(除 agent-loop(智能体循环)自身的 tests 和 examples/ 外)禁止导入 `@deepseek-ai/dsh-agent-loop`。 +- 禁止跨包深层导入(`@deepseek-ai/dsh-*/src/...` 路径)——只允许使用公开入口点。 +- packages/ 内禁止导入循环。 +- `vendor/*` 禁止从 `packages/*` 导入。 +- 分层:dsh-llm 不导入其他 dsh 包;dsh-session 仅导入 dsh-llm;以此类推(packages/README.md 中的依赖表,强制执行)。 + +**适配器一致性套件**位于 dsh-llm(`@deepseek-ai/dsh-llm/conformance`):一个以适配器工厂为参数的可复用 vitest 套件,用于断言分片协议契约,包括每个块内的索引单调递增、某个索引出现 `block-end` 后不再接收增量、恰好出现一个 `finish`、用量至多出现一次、每个 `tool-call-delta` 都携带调用 id,并且及时响应 abort。当前先对 mock 运行;DeepSeek V4 适配器从第一天起继承该套件。还可以选择提供开发模式下的 `strictAdapter()` 包装层,在调试标志开启时于运行时强制执行相同规则(与 [开发模式不变式](../../implemented/architecture/2026-06-11-dev-invariants-over-deep-readonly.md) 配对)。 + +## 计划 + +先落地 dependency-cruiser 配置与 CI 步骤(约一小时工作量,换来永久保证);一致性套件随其首个消费方测试(针对 MockAdapter)一起落地,并作为 V4 适配器阶段的前置条件。 + +## 验收标准 + +- dependency-cruiser 在 CI 中运行上述规则族;违规导入导致构建失败。 +- 一致性套件对 mock 适配器和两个正式适配器运行,新适配器包通过调用该套件并传入自己的工厂即可继承测试。 + +## 风险 + +随着包的增加,dep-cruiser 规则需要维护——规则应基于模式(`dsh-*`)而非逐一枚举。 + +<!-- agent-note-format: alternatives-not-recorded (pre-format Agent Note) --> diff --git a/.agents/notes/proposed/process/2026-06-11-supply-chain-and-vendor-drift.i18n.yaml b/.agents/notes/proposed/process/2026-06-11-supply-chain-and-vendor-drift.i18n.yaml new file mode 100644 index 0000000000..bf98665195 --- /dev/null +++ b/.agents/notes/proposed/process/2026-06-11-supply-chain-and-vendor-drift.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-11-supply-chain-and-vendor-drift.md: a27ae64556dc7366279824f1480e5681b1e86bf1 +2026-06-11-supply-chain-and-vendor-drift.zh.md: 25c27650709faf1a462ce9779ee6f0a909746311 diff --git a/.agents/notes/proposed/process/2026-06-11-supply-chain-and-vendor-drift.md b/.agents/notes/proposed/process/2026-06-11-supply-chain-and-vendor-drift.md index a79f719751..a27ae64556 100644 --- a/.agents/notes/proposed/process/2026-06-11-supply-chain-and-vendor-drift.md +++ b/.agents/notes/proposed/process/2026-06-11-supply-chain-and-vendor-drift.md @@ -2,6 +2,8 @@ Status: proposed +English | [中文](2026-06-11-supply-chain-and-vendor-drift.zh.md) + ## Problem The vendor manifest ([the vendoring decision](../../implemented/process/2026-06-11-vendor-cordis-as-source.md)) is enforced at commit time in the *forward* direction (vendored change ⇒ manifest update) but nothing verifies the manifest's *claims*: that vendor/ actually equals upstream-at-SHA plus exactly the logged modifications. And the handful of true npm dependencies have no advisory monitoring or update cadence. diff --git a/.agents/notes/proposed/process/2026-06-11-supply-chain-and-vendor-drift.zh.md b/.agents/notes/proposed/process/2026-06-11-supply-chain-and-vendor-drift.zh.md new file mode 100644 index 0000000000..25c2765070 --- /dev/null +++ b/.agents/notes/proposed/process/2026-06-11-supply-chain-and-vendor-drift.zh.md @@ -0,0 +1,35 @@ +# Agent Note: 供应链检查与 vendor 漂移验证 + +Status: proposed + +[English](2026-06-11-supply-chain-and-vendor-drift.md) | 中文 + +## 问题 + +vendor manifest(元数据清单)(见[引入 vendor 的决策](../../implemented/process/2026-06-11-vendor-cordis-as-source.md))在提交时仅在*正向*强制执行(vendor 变更 ⇒ manifest 更新),但没有任何机制验证 manifest 的*声明*:即 vendor/ 确实等于上游指定 SHA 的内容加上所记录的修改。此外,少量真正的 npm 依赖也没有安全公告监控或更新节奏。 + +## 提案 + +1. **Vendor 漂移检查**(夜间 CI):以 manifest 中记录的 SHA 浅克隆上游仓库,复制对应的包(package)源码,与 `vendor/*/src` 做 diff。除非 diff 与已记录的本地修改一致(每项修改以签入的 patch 文件保存——日志条目从行文描述变为可验证的产物),否则任务失败。 +2. **依赖安全公告**:对 lockfile 运行 osv-scanner(或 `pnpm audit`),按计划定期执行,并在涉及 lockfile 变更的 PR(Pull Request)上触发。 +3. **许可证清单**:一个脚本断言每个 vendor 包都携带其 LICENSE 文件,且 package.json 的 `license` 字段与 vendor/README.md 中的清单一致(我们混合了 vendor 的 MIT 与自有的 BSD-3)——作为 CI 步骤运行。 +4. **Renovate**(或定时 agent(智能体)任务)以小 PR 的形式提议 npm 依赖更新,这些 PR 走完整门禁套件;vendor 包不在其列(它们的更新遵循 manifest 同步流程,理想情况下是半自动化的 agent 工作流:拉取上游、重新应用 patch、运行门禁、以更新后的 manifest 表格开 PR)。 + +## 计划 + +第 3 项最简单,先做。第 1 项需要 CI 能通过网络访问上游仓库(私有仓库,需要 token),并将现有两项已记录的修改转换为 patch 文件。第 2 项和第 4 项是配置工作。 + +## 曾考虑的替代方案 + +- **用 `pnpm audit` 替代 osv-scanner**:两者都满足安全公告扫描的需求;具体选择推迟到实现阶段决定。 +- **用定时 agent 任务替代 Renovate**:在提议小型更新 PR 并走完整门禁套件方面效果等价;vendor 包无论哪种方案都不在其列(它们的更新遵循 manifest 同步流程)。 + +## 验收标准 + +- 许可证清单脚本在 CI 中运行,缺少 LICENSE 或 `license` 字段与 `vendor/README.md` 中的清单矛盾时失败。 +- 夜间漂移任务从 manifest SHA 加签入的 patch 文件重建 `vendor/`,出现任何无法解释的 diff 时失败。 +- 安全公告扫描按计划定期运行,并在涉及 lockfile 变更的 PR 上运行。 + +## 风险 + +上游仓库是私有镜像;CI 凭证与可用性是漂移检查的主要阻力。如果受阻,可改为本地定时 agent 任务而非 CI。 diff --git a/.agents/notes/proposed/process/2026-06-20-discover-package-inventory.i18n.yaml b/.agents/notes/proposed/process/2026-06-20-discover-package-inventory.i18n.yaml new file mode 100644 index 0000000000..bf44db6bee --- /dev/null +++ b/.agents/notes/proposed/process/2026-06-20-discover-package-inventory.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-20-discover-package-inventory.md: 50e42686cea48985dedc7fa290e06bc959ecc5d4 +2026-06-20-discover-package-inventory.zh.md: dc79162dd3ec5ba2bf3225fc8e9d44c552a514cb diff --git a/.agents/notes/proposed/process/2026-06-20-discover-package-inventory.md b/.agents/notes/proposed/process/2026-06-20-discover-package-inventory.md index f9286aeefd..50e42686ce 100644 --- a/.agents/notes/proposed/process/2026-06-20-discover-package-inventory.md +++ b/.agents/notes/proposed/process/2026-06-20-discover-package-inventory.md @@ -2,6 +2,8 @@ Status: proposed +English | [中文](2026-06-20-discover-package-inventory.zh.md) + ## Problem Package and gate inventories are repeated across TypeScript project references, package docs, CI prose, and Knip overrides. Most restate package layout, manifest data, or aggregate command contents. Each new package therefore creates avoidable synchronization points. diff --git a/.agents/notes/proposed/process/2026-06-20-discover-package-inventory.zh.md b/.agents/notes/proposed/process/2026-06-20-discover-package-inventory.zh.md new file mode 100644 index 0000000000..dc79162dd3 --- /dev/null +++ b/.agents/notes/proposed/process/2026-06-20-discover-package-inventory.zh.md @@ -0,0 +1,35 @@ +# Agent Note: 通过发现机制获取包清单,而非维护静态列表 + +Status: proposed + +[English](2026-06-20-discover-package-inventory.md) | 中文 + +## 问题 + +包(package)与门禁清单在 TypeScript project references、包文档、CI 描述和 Knip 覆盖项中反复出现。大多数只是重述包布局、manifest(元数据清单)数据或聚合命令内容。因此每新增一个包都会产生本可避免的同步点。 + +[包层级结构](../../implemented/architecture/2026-06-20-package-hierarchy.md)已经手动消除了其中若干:`scripts/publint-all.ts` 现在从 `packages/<group>/<pkg>` 布局推导列表,两份 `tsconfig` 的 `paths` 映射也合并为一个 `@deepseek-ai/dsh-*` 通配符。剩下的是无法用 glob 消除的清单,主要是聚合配置(`tsconfig.host.json`、`tsconfig.client.json`)的 project `references`——TypeScript 要求它们是显式数组(没有通配符形式)。 + +当静态列表编码的是策略时,它们是合理的;当它们只是重复 `package.json`、workspace glob 或包层级结构中已有的 manifest 数据或布局事实时,就是不必要的摩擦。 + +## 提案 + +让剩余的包与门禁清单可被发现。一个唯一的权威来源,即 `packages/<group>/<pkg>` 层级结构加上包 manifest,应当驱动聚合配置的 `references`、模块图以及任何全量包列表,并配合一个生成加校验步骤(沿用现有的 `gen-module-graph` / `gen-cordis-catalog` 模式:生成器写出产物,`--check` 模式在 `hygiene` / `doc-sync`(文档同步门禁)中发现已提交副本陈旧时失败)。模块图生成已经在读取包 manifest。`doc-sync` 应当成为定义并打印其子门禁的唯一命令,文档链接到该命令,而非重述第二份列表。 + +层级结构不需要编码关于包的所有事实,但应当编码宽泛的维护策略:core/product 包、集成包、能力 seam 包与 support/test/example 包不应在脚本能区分它们之前先要求一份手工维护的例外列表。 + +有一项已编目的内容根本不需要生成器:将 e2e 入口 glob 折入 Knip 的默认配置段,即可直接删除逐包的重复声明。 + +## 验收标准 + +- 聚合配置的 project `references` 由层级结构生成(生成器输出它们;`--check` 门禁在提交副本陈旧时报错),而非手工维护。 +- 新增一个包时,不需要为任何门禁编辑静态包列表。 +- 文档描述真源,而非重复生成的清单。 +- CI 调用聚合命令,由这些命令自行管理其子门禁列表。 +- `knip.json` 仅在编码真实信息(额外入口文件、被忽略的依赖)时才携带逐包覆盖项,绝不重述默认配置段。 + +## 风险 + +发现脚本可能变得过于精巧。实现应当保持朴素:读取 manifest、按显式字段过滤、打印解析后的列表,并在出错时明确失败。收益在于消除手工清单的漂移,而非发明一套构建系统。 + +<!-- agent-note-format: alternatives-not-recorded (pre-format Agent Note) --> diff --git a/.agents/notes/proposed/simplification/2026-07-04-prune-dead-core-spine-surface.i18n.yaml b/.agents/notes/proposed/simplification/2026-07-04-prune-dead-core-spine-surface.i18n.yaml new file mode 100644 index 0000000000..024adc68d9 --- /dev/null +++ b/.agents/notes/proposed/simplification/2026-07-04-prune-dead-core-spine-surface.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-04-prune-dead-core-spine-surface.md: 432aaa848540fe7d1db3039399345a02afed5bd3 +2026-07-04-prune-dead-core-spine-surface.zh.md: 2c7cc4c0dc234afc107bdfc715cf717e5ad8c55c diff --git a/.agents/notes/proposed/simplification/2026-07-04-prune-dead-core-spine-surface.md b/.agents/notes/proposed/simplification/2026-07-04-prune-dead-core-spine-surface.md index 1f52bfac25..432aaa8485 100644 --- a/.agents/notes/proposed/simplification/2026-07-04-prune-dead-core-spine-surface.md +++ b/.agents/notes/proposed/simplification/2026-07-04-prune-dead-core-spine-surface.md @@ -2,6 +2,8 @@ Status: proposed +English | [中文](2026-07-04-prune-dead-core-spine-surface.zh.md) + ## Problem Several package-root exports, result fields, and convenience methods have no production consumer. They survive because tests import internals through public entry points or because a type anticipated a caller that never arrived. Each item is small in isolation, but together they enlarge the SDK contract, generated catalogs, documentation, and regression matrix without enabling a shipped path. diff --git a/.agents/notes/proposed/simplification/2026-07-04-prune-dead-core-spine-surface.zh.md b/.agents/notes/proposed/simplification/2026-07-04-prune-dead-core-spine-surface.zh.md new file mode 100644 index 0000000000..2c7cc4c0dc --- /dev/null +++ b/.agents/notes/proposed/simplification/2026-07-04-prune-dead-core-spine-surface.zh.md @@ -0,0 +1,63 @@ +# Agent Note: 裁剪无用的公开与结果接口 + +Status: proposed + +[English](2026-07-04-prune-dead-core-spine-surface.md) | 中文 + +## 问题 + +若干包(package)根导出、结果字段和便利方法没有生产消费方。它们之所以存活,要么是因为测试通过公开入口导入了内部实现,要么是因为某个类型预期了一个从未出现的调用者。每一项单独看都很小,但合在一起,它们扩大了 SDK 契约、生成的 catalog、文档和回归矩阵,却没有支撑任何已交付的路径。 + +生产语料库是 `packages/*/*/src`、示例源码/配置和运行时脚本。测试、包 README 和 Agent Note(agent 决策记录)行文是发布的证据,但不是固定调用者。`cordis_inspect` 使 `packages/cordis/tool-cordis/src/api-catalog.ts` 对模型可见,`cordis_mount` 可以通过受保护的真实服务代理调用注入的服务,因此 catalog 中的服务方法和返回形状是真正的动态产品接口。下表因此区分「没有固定的仓库调用者」与「不可达」:涉及 catalog 词汇的行有意收缩模型编写的 mount 能发现和调用的内容,而包根实现辅助函数并不通过该服务门面可达。精确符号搜索得出以下清单: + +| 接口 | 生产证据 | 简化方式 | +| --- | --- | --- | +| `SurfaceManager.invalidate()` | 只有其单元测试调用它;seeding 在惰性创建的 manager 存在之前就已完成,且会话从不替换其日志引用。 | 删除它及其不可能触发的整体替换契约。 | +| `ToolExecutionResult.callId` | 每个钩子已经接收不可变的 `ToolExecution`;循环和 ACP(Agent Client Protocol)通过调用/会话事件关联。没有消费方读取这个重复的结果字段。 | 移除该字段、复制/不匹配守卫,以及证明该重复不可能不一致的测试。 | +| `ReactLoopAgent` 根导出 | 包外的命名导入都是测试;生产代码面向 `Agent` 编程,通过 `ctx.agents` 创建/恢复。 | 返回/接口类型为 `Agent`,将具体循环类改为包内部;保留有意设计的同步、仅配置的 `AgentLoop.create()` 路径。 | +| `workflow-workerthread` 的 protocol/runtime/session 再导出与命名的 `WorkerWorkflowEngine` | 每个包名消费方都使用默认引擎;工作流 Agent Note 已将 worker 协议格式(wire format)定义为私有。 | 保留默认插件类/配置契约;移除重复的命名类导出,将协议模块保持为源码私有。 | +| `code-runtime-worker` 的 protocol/bootstrap 再导出 | 包外的生产/e2e 消费方使用 `WorkerCodeRuntime` 和配置,而非 `BootstrapPort`、`PatchableStream` 或 worker 消息/启动类型。 | 保留运行时类/配置契约,将其协议格式/bootstrap 词汇改为源码私有。 | +| ACP 的 translation/presenter 根导出 | `agentOptions`、`streamSessionEventUpdate`、`todosToPlan`、`ToolPresenter`、`nullToolPresenter` 和 `TerminalRendering` 只有同文件或 ACP 测试消费方;唯一的包外生产消费方挂载的是插件命名空间。 | 保留 `name`、`inject`、`Config`、`AcpConfig` 和 `apply`;将 translation/presentation 辅助函数改为源码私有,在包内测试。 | +| `providerWording` 与 `completedTurnPrefix` 根导出 | 各有一个同包生产调用者;只有 balanced-prefix 辅助函数有一个同包白盒测试。 | 改为源码私有,测试提供方行为。 | +| `depthOf`、`SubagentDepthError`、`SENSITIVE_ENV_PATTERN`、`waitForExit` 与 `exitsWithin` 根导出 | 生产 subagent 后端消费的是进程内 runner 和子进程构造/dispose(资源释放)辅助函数,而非这些强制/测试内部实现。 | 保留深度/环境/退出行为,但将辅助函数和 error/regex 改为源码私有;通过 spawn 和 dispose 测试。 | +| `PersistenceCoordinator.inits`、后端 `inits` 访问器、`seedCoversPrefix` 与 `assertSerializable` | 访问器为白盒测试而存在;`seedCoversPrefix` 没有包外生产导入者;`assertSerializable` 没有生产调用者,且与 coordinator append 边界的无损快照重复。 | 通过 `session/flush` 观察初始化,将 `seedCoversPrefix` 改为源码私有,删除 `assertSerializable`。保留两个后端、`SessionHeader` 和 SQLite 的版本契约。 | +| `LlmError.status` 与回放 status | 适配器/回放填充它,但生产分支基于稳定的错误码/消息判断,从不读取原始 status。 | 移除未读字段和回放管道,保留错误分类。 | +| `BlockAssembler.push()` 返回值 | 两个生产调用者都忽略返回的已完成块。 | 返回 `void`;保留有意公开的 `blocks()`/`message()` 契约。 | +| `compactRegion` 的独立 `session` 参数 | 固定调用者传入的对象与 `agent.session` 上已有的是同一个;模型可见的 mount API 也能调用该方法,但接受两个身份允许挂载的插件提供不一致的配对。 | 保留手动 region seam,同时有意将其收窄为以 `agent.session` 为唯一真源。 | +| `CompactionResult.startSeq`、`summarySeq`、`endSeq` 与 `summary` | 生产消费方只读取 shadowed range/seq/token 统计;持久日志拥有 summary 和事件标识。 | 移除四个结果回显,保留两个共享的 transcript(文本记录)渲染器。 | +| `BasicCompactService` 的 estimation/summarization 可见性 | 没有包外生产调用者调用这五个方法;已实现的 Agent Note 只将 `estimateContentTokens()` 和 `summarize()` 命名为子类钩子。 | 将这两个方法改为 `protected`,其余三个编排专用的估算器改为 private。 | +| `CodeLogEntry.source`/`level` 与 `RunCodeMeta.dispatches` | 每个生产消费方都将日志映射为文本;没有 presenter/模型路径读取其他字段或持久化的 dispatch 计数。 | 将 code-runtime 日志改为字符串(或纯文本条目),移除 result-meta 的 dispatch 管道;保留用于生成确定性 dispatch id 的本地计数器。 | +| `CodeRuntime.language` 与 `CodeRuntime.isolation` | worker 后端提供唯一的生产值,而 Code Mode 及其他所有生产调用方只调用 `run()`。 | 移除未读描述符,同时保留 worker 的语言、隔离、预算、取消与资源释放行为。 | +| `ToolNotFoundError.toolName`、`SystemPrompt.config` 与 `BashTask.command` | 每个存储的公开值都没有生产读取者。 | 移除未读字段,保留错误消息、已解析的配置行为和任务生命周期。 | +| 后端包根实现辅助函数 | 下方精确清单仅通过相对路径的同包导入调用。生产命名空间导入挂载的是保留的插件契约,不读取这些属性;命名根消费方都是测试。 | 保留每个适配器/提供方/服务及其配置/错误契约;停止在包根导出所列辅助函数/常量。 | +| 消费方包根实现辅助函数 | 下方精确清单只有同包生产调用者。生产命名空间导入挂载的是插件契约,不读取辅助属性;命名根消费方都是测试。 | 保留插件契约和稳定的错误码;将测试迁移到包内模块或公开行为,停止在包根导出所列辅助函数。 | + +### 分组辅助导出清单 + +- `dsh-llm-deepseek`:`httpErrorCode`、`serializeMessages`、`serializeRequest`、`DONE`、`parseSse`、`mapFinishReason`、`mapUsage` 与 `translate`;`dsh-llm-pi-ai`:`buildModel`、`mapStopReason`、`mapUsage`、`toPiContext` 与 `toStreamChunks`。 +- `dsh-bash-local`:`DEFAULT_GRACE_MS`、`ENV_OVERRIDES`、`killGroup`、`OutputCollector` 与 `runBash`;`dsh-bash-sandbox`:`shellQuote`、`classifyDenial` 与 `classifyRunnerFailure`;`dsh-sandbox-local`:`bwrapProfileArgs`、`landlockProfileArgs` 与 `seatbeltProfileArgs`。公开的可变测试注入字段及其类型不在本提案范围内。 +- `dsh-fs-local`:`applyLiteralEdit`、`listDirectory`、`probe`、`readForEdit`、`readTextForDiff`、`readWholeText`、`resolveLocalTarget`、`restoreLineEndings`、`streamWholeText` 与 `writeFileAtomic`。 +- `dsh-web-fetch-local`:`classifyContentType`、`decoderForCharset`、`isSameOrigin`、`parseCharset` 与 `validateFetchUrl`;`dsh-web-search-exa`:`mapExaResponse` 与 `mapExaResult`;`dsh-web-search-deepseek`:`citationSnippets` 与 `mapAnthropicResponse`;`dsh-web-search-perplexity`:`mapPerplexityResponse` 与 `mapPerplexityResult`。 +- `dsh-tool-fs`:`READ_LIMIT`、`STREAM_MIN_SIZE`、`READ_MAX_BYTES`、`READ_MAX_LINE_LENGTH`、`DIFF_CONTEXT`、`applyReadTool`、`parseReadArgs`、`applyWriteTool`、`formatWriteOutput`、`parseWriteArgs`、`applyEditTool`、`formatEditOutput`、`parseEditArgs`、`buildWindow`、`formatReadOutput`、`computeHunkDiffs` 与 `diffsFromMeta`。 +- `dsh-tool-web`:`WEB_SEARCH_MAX_RESULTS`、`applyWebSearchTool`、`formatSearchOutput`、`parseSearchArgs`、`presentSearchCall`、`applyWebFetchTool`、`formatFetchOutput`、`parseFetchArgs`、`presentFetchCall`、`renderBody` 与 `htmlToMarkdown`;`dsh-timeout-policy`:`toolTimeoutResult`;`dsh-compact-basic`:`resolveConfig`;`dsh-tool-bash`:`renderResult`。 + +## 提案 + +以一次有界的、协调的公开接口清理,移除或降级上述每一行。同步更新包 README、JSDoc、生成的 API/事件 catalog、type-equiv 记录、必要的 exports map 以及测试,使测试通过所属的公开 seam 验证行为,而非保留仅为测试而存在的入口。不折叠任何能力 seam、LLM(大语言模型)适配器、持久化后端或生命周期完全停稳契约。 + +## 曾考虑的替代方案 + +**保留测试便利函数和自包含的结果字段为公开。** 公开辅助函数可以让白盒测试更方便,自包含的结果字段看起来更易用,未来的嵌入者可能需要具体循环类或枚举方法。这些好处是假设性的;当前它们让每处实现和文档都要解释没有已交付调用者能观察到的状态。真正的消费方可以引入它所需的最小契约,其所有权和失败语义明确。 + +**保留所有 catalog 成员以供模型编写的 mount 使用。** 自引用工具集是一条真实的通用消费路径,而非生成文档的噪音。然而,它的价值来自准确、可组合的服务接口,而非无限期保留重复字段或不一致的参数对;上述每一项 catalog 收缩都移除了在同一次执行、同一个 agent(智能体)或同一结果中其他位置已可获得的事实,并在同一变更中更新 API 参考。 + +## 验收标准 + +- 精确符号搜索显示:在本 Agent Note 及任何已实现 Agent Note 修正之外,没有被移除的接口。 +- 本 Agent Note 列出的每个接口均按指定方式缺失或降级;清单之外有意保留的扩展/测试契约不变。 +- 工具执行、上下文压缩(context compaction)、两个 LLM 适配器、两个持久化后端、工作流隔离以及 agent 创建/恢复保持其已交付行为。 +- 类型检查、覆盖率、快照、doc-sync(文档同步门禁)、module-graph 校验、构建和 hygiene 通过。 + +## 风险 + +大多数移除在编译时可见但对运行时无影响。上下文压缩参数清理有意禁止会话/上下文不匹配,同时保留手动 region seam。外部预发布嵌入者和现有模型编写的 mount 可能导入更少的辅助函数、传递更少的参数或接收更窄的结果形状;这是有意的产品接口收缩,而非仅仅是生成 catalog 的清理。仓库尚未发布,因此承载不受支持的接口才是更大的基础成本。 diff --git a/.agents/notes/proposed/testing/2026-06-11-deterministic-and-stress-testing.i18n.yaml b/.agents/notes/proposed/testing/2026-06-11-deterministic-and-stress-testing.i18n.yaml new file mode 100644 index 0000000000..8ca0473ebe --- /dev/null +++ b/.agents/notes/proposed/testing/2026-06-11-deterministic-and-stress-testing.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-11-deterministic-and-stress-testing.md: d9977be835af05f9ee303b63ec6015bc9e153170 +2026-06-11-deterministic-and-stress-testing.zh.md: eff9eecb699344dff388bafec270f6b6677f71ee diff --git a/.agents/notes/proposed/testing/2026-06-11-deterministic-and-stress-testing.md b/.agents/notes/proposed/testing/2026-06-11-deterministic-and-stress-testing.md index c3b17c401a..d9977be835 100644 --- a/.agents/notes/proposed/testing/2026-06-11-deterministic-and-stress-testing.md +++ b/.agents/notes/proposed/testing/2026-06-11-deterministic-and-stress-testing.md @@ -2,6 +2,8 @@ Status: proposed +English | [中文](2026-06-11-deterministic-and-stress-testing.zh.md) + ## Problem Several loop tests synchronize with `setTimeout(30)` sleeps — flakiness debt that wastes agent cycles on retries and can mask ordering bugs. Separately, our core architectural promise (any session log replays to identical derived history) is asserted in two tests but is cheap to assert *everywhere*. And the inbox wakeup race was verified by hand exactly once; nothing re-verifies it continuously. diff --git a/.agents/notes/proposed/testing/2026-06-11-deterministic-and-stress-testing.zh.md b/.agents/notes/proposed/testing/2026-06-11-deterministic-and-stress-testing.zh.md new file mode 100644 index 0000000000..eff9eecb69 --- /dev/null +++ b/.agents/notes/proposed/testing/2026-06-11-deterministic-and-stress-testing.zh.md @@ -0,0 +1,33 @@ +# Agent Note: 确定性测试、回放不变式 fixture(测试前置数据)与竞态压力测试 + +Status: proposed + +[English](2026-06-11-deterministic-and-stress-testing.md) | 中文 + +## 问题 + +若干 agent loop(智能体循环)测试通过 `setTimeout(30)` 睡眠来同步——这是一笔不稳定性债务,浪费 agent 的重试周期,还可能掩盖时序 bug。另外,我们的核心架构承诺(任何会话日志回放后都能得到相同的派生历史)目前只在两个测试中断言,但在*所有*测试中断言的成本极低。此外,inbox 唤醒竞态只被手动验证过一次,没有任何机制持续复验。 + +## 提案 + +三项措施: + +1. **测试中禁止挂钟睡眠。** 将 `setTimeout(N)` 等待替换为事件驱动等待(既有的 `waitForIdle` 模式,扩展为 `waitForStatus`、`waitForEvent(n)`),或在需要测试时间本身时使用 vitest 的 fake timer。通过 lint 规则禁止 `setTimeout`,适用范围是 `packages/*/tests`,白名单辅助模块除外。 +2. **通用回放 fixture。** 一个共享测试辅助函数包装 agent loop harness,使每个测试结束后,agent 的会话日志被回放到一个全新的 Session 中,并自动断言 `deriveMessages()` 相等。这样该不变式在每次 CI 运行中会被套件产生的所有场景检查数百次,而非仅两次。 +3. **夜间竞态压力测试。** 一个 CI job 以 `vitest --repeat=200`(加 `--shuffle`)运行 agent-loop 和 inbox 套件,以暴露调度依赖的失败;发现的任何不稳定测试都视为 bug 修复,绝不靠重试掩盖。 + +## 计划 + +措施 1 和 2 一起落地(它们改动相同的辅助模块);在套件消除所有睡眠后再添加夜间 job,以确保重复运行速度快。 + +## 验收标准 + +- 不再使用 `setTimeout`;lint 规则在 `packages/*/tests` 中强制执行,白名单辅助模块除外。 +- 共享 harness 将每个测试的会话日志回放到全新的 `Session` 中,并自动断言 `deriveMessages()` 相等,覆盖整个套件。 +- 夜间 job 以 `--repeat` 和 `--shuffle` 运行 agent-loop 和 inbox 套件;发现的不稳定测试作为 bug 分诊,绝不靠重试掩盖。 + +## 风险 + +Fake timer 与 agent loop 中的 Promise 调度存在微妙交互——优先使用事件驱动等待;仅在测试 timer 服务行为本身时才使用 fake timer。 + +<!-- agent-note-format: alternatives-not-recorded (pre-format Agent Note) --> diff --git a/.agents/notes/proposed/testing/2026-06-11-mutation-testing.i18n.yaml b/.agents/notes/proposed/testing/2026-06-11-mutation-testing.i18n.yaml new file mode 100644 index 0000000000..d593656c04 --- /dev/null +++ b/.agents/notes/proposed/testing/2026-06-11-mutation-testing.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-11-mutation-testing.md: 591d9012644a19ee2c67a916b63092d79f78db1f +2026-06-11-mutation-testing.zh.md: 9c22ed2f42e5c44e6be98f132614886bbdb188fd diff --git a/.agents/notes/proposed/testing/2026-06-11-mutation-testing.md b/.agents/notes/proposed/testing/2026-06-11-mutation-testing.md index 35df228b85..591d901264 100644 --- a/.agents/notes/proposed/testing/2026-06-11-mutation-testing.md +++ b/.agents/notes/proposed/testing/2026-06-11-mutation-testing.md @@ -2,6 +2,8 @@ Status: proposed +English | [中文](2026-06-11-mutation-testing.zh.md) + ## Problem The per-file 100% coverage gate ([the quality-gates decision](../../implemented/process/2026-06-11-quality-gates.md)) proves every line *executes* under test — not that any assertion would notice if the line were wrong. Under agent-written tests, coverage pressure can produce execution-without-assertion. Mutation testing measures what coverage cannot: whether the suite *kills* deliberately injected bugs. diff --git a/.agents/notes/proposed/testing/2026-06-11-mutation-testing.zh.md b/.agents/notes/proposed/testing/2026-06-11-mutation-testing.zh.md new file mode 100644 index 0000000000..9c22ed2f42 --- /dev/null +++ b/.agents/notes/proposed/testing/2026-06-11-mutation-testing.zh.md @@ -0,0 +1,36 @@ +# Agent Note: 变异测试作为覆盖率的制衡手段 + +Status: proposed + +[English](2026-06-11-mutation-testing.md) | 中文 + +## 问题 + +逐文件 100% 覆盖率门禁([质量门禁决策](../../implemented/process/2026-06-11-quality-gates.md))证明每一行代码在测试中都被*执行*了,但不能证明如果该行出错,任何断言会注意到。在 agent(智能体)编写测试的场景下,覆盖率压力可能产出「执行但不断言」的测试。变异测试衡量的正是覆盖率无法衡量的:测试套件是否能*杀死*被刻意注入的缺陷。 + +## 提案 + +使用 Stryker(`@stryker-mutator/vitest-runner`)对 `packages/*/src` 运行变异测试: + +- **PR(Pull Request)范围的增量运行**(仅变更文件),作为一个 CI job。调优后速度足以作为合并门禁。 +- **每夜全量运行**,跟踪变异分数;先记录基线,再将阈值设为观测到的基线并只升不降(与覆盖率策略一致:阈值只收紧)。 +- 存活的变异体是待办项:agent 选取一个存活体、编写杀死它的测试、循环往复——一个形态良好的自主循环。 +- 等价变异体(可证明不改变行为的)加注释排除并附理由,与 `/* v8 ignore */` 策略一致。 + +## 计划 + +1. 添加 Stryker 配置,范围限定在一个包(package),即 llm(最小、最具算法性),并测量运行时间。 +2. 扩展到所有包;在配置中记录基线分数。 +3. 接入每夜 job;运行时间可接受后再添加 PR 范围的增量 job。 + +## 验收标准 + +- Stryker 配置在 `packages/*/src` 上以 vitest runner 运行;每夜 job 记录变异分数,当分数低于记录的基线时,通过只升不降的阈值使运行失败。 +- PR 范围的增量运行在运行时间可接受后作为合并门禁;或者明确保持仅每夜运行,并将该结论记录于此。 +- 等价变异体带有注释排除及理由,与 `/* v8 ignore */` 策略一致。 + +## 风险 + +运行时间:变异测试开销大;逐文件 100% 覆盖率有所帮助(每个变异体至少会被执行到)。如果 PR 范围的运行始终过慢,则保持仅每夜运行,依赖分数只升不降的机制。 + +<!-- agent-note-format: alternatives-not-recorded (pre-format Agent Note) --> diff --git a/.agents/notes/rejected/architecture/2026-06-11-immutable-public-surfaces.i18n.yaml b/.agents/notes/rejected/architecture/2026-06-11-immutable-public-surfaces.i18n.yaml new file mode 100644 index 0000000000..6201a380e7 --- /dev/null +++ b/.agents/notes/rejected/architecture/2026-06-11-immutable-public-surfaces.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-11-immutable-public-surfaces.md: c9009ad923720efaecb25e2017ceab6e3eb0dbf4 +2026-06-11-immutable-public-surfaces.zh.md: 4ef67734d712e538c5858fbc05efbc6dd983c704 diff --git a/.agents/notes/rejected/architecture/2026-06-11-immutable-public-surfaces.md b/.agents/notes/rejected/architecture/2026-06-11-immutable-public-surfaces.md index 0c6652a94d..c9009ad923 100644 --- a/.agents/notes/rejected/architecture/2026-06-11-immutable-public-surfaces.md +++ b/.agents/notes/rejected/architecture/2026-06-11-immutable-public-surfaces.md @@ -2,6 +2,8 @@ Status: rejected — the pervasive `DeepReadonly<T>` type flip is replaced by source-owned runtime immutability in `Session` plus relational development assertions. See [source-owned session immutability and dev-mode invariants](../../implemented/architecture/2026-06-11-dev-invariants-over-deep-readonly.md). +English | [中文](2026-06-11-immutable-public-surfaces.zh.md) + ## Problem The rejected proposal targeted an ownership hole that a `readonly SessionEvent[]` type alone cannot close: its elements remain mutable at runtime, so a cast or plain JavaScript can rewrite nested history. The implemented design closes that hole in `Session` by materializing and deep-freezing every accepted event and returning frozen array snapshots. In-flight prompt waterfalls remain intentionally transformable, so immutability is an ownership boundary rather than a blanket type rule. diff --git a/.agents/notes/rejected/architecture/2026-06-11-immutable-public-surfaces.zh.md b/.agents/notes/rejected/architecture/2026-06-11-immutable-public-surfaces.zh.md new file mode 100644 index 0000000000..4ef67734d7 --- /dev/null +++ b/.agents/notes/rejected/architecture/2026-06-11-immutable-public-surfaces.zh.md @@ -0,0 +1,29 @@ +# Agent Note: 深度只读的公开接口 + +Status: rejected — 普遍采用 `DeepReadonly<T>` 的类型翻转已由 `Session` 中归属源的运行时不可变性与关系型开发断言取代。见[归属源的会话不可变性与开发模式不变式](../../implemented/architecture/2026-06-11-dev-invariants-over-deep-readonly.md)。 + +[English](2026-06-11-immutable-public-surfaces.md) | 中文 + +## 问题 + +被否决的提案针对的是一个所有权漏洞:仅靠 `readonly SessionEvent[]` 类型无法封堵该漏洞,因为其元素在运行时仍然可变,类型强制转换或纯 JavaScript 代码可以改写嵌套的历史记录。已实现的设计在 `Session` 中封堵了这一漏洞:对每个被接受的事件进行物化并深度冻结,返回冻结的数组快照。进行中的提示词 waterfall(瀑布式事件)有意保持可变换,因此不可变性是一条所有权边界,而非一条全局类型规则。 + +## 提案 + +> **实际采用了不同的实现方式——见 Status 行与[源拥有的会话不可变性与开发模式不变式](../../implemented/architecture/2026-06-11-dev-invariants-over-deep-readonly.md)。** 下文的 `DeepReadonly<T>` 设计已被否决:它仅在编译期生效、对消费方噪音大、且可被强制转换绕过。`Session` 改为在每次组合中对已接受的事件和公开日志快照进行快照与深度冻结;`deriveMessages()` 返回分离的冻结投影;开发插件检查跨记录与跨 seam 的关系。 + +在类型层面为「突变即损坏」的场景引入不可变性: + +- `SessionEvent` 数据在从会话输出时(`events`、`session/event` 监听器)变为 `DeepReadonly`;`append()` 仍接受普通可变输入。一个 `DeepReadonly<T>` 工具类型放在 dsh-llm 中,与 brand/never 辅助类型相邻。 +- `deriveMessages()` 返回深度只读的消息;agent loop(智能体循环)在将可变请求交给 `agent/request` waterfall 之前先克隆(该处的突变是被允许的——克隆使边界显式且代价低廉,每个步骤仅一次)。 +- `PromptAssembly` 在其 waterfall 流经期间保持可变(被允许),但注册表内部的 section 列表在每次组装时被克隆(已有此行为)。 + +## 计划 + +引入 `DeepReadonly`,翻转会话的读取路径,并修复消费方中由此产生的编译错误。 + +## 风险 + +`DeepReadonly` 类型在 waterfall 边界处(突变本身就是 API 的地方)可能产生噪音较大的错误。应将可变/只读边界精确地划在「已记录 vs 进行中」,并在会话 README 中加以说明。 + +<!-- agent-note-format: alternatives-not-recorded (pre-format Agent Note) --> diff --git a/.agents/notes/rejected/architecture/2026-06-20-providerless-example-base.i18n.yaml b/.agents/notes/rejected/architecture/2026-06-20-providerless-example-base.i18n.yaml new file mode 100644 index 0000000000..6a1baa8a80 --- /dev/null +++ b/.agents/notes/rejected/architecture/2026-06-20-providerless-example-base.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-20-providerless-example-base.md: 2f41476a487775e6f9da2f113efe566e44786ff3 +2026-06-20-providerless-example-base.zh.md: e767d6b3a35dcfd52194f8a59edc496b86414b6e diff --git a/.agents/notes/rejected/architecture/2026-06-20-providerless-example-base.md b/.agents/notes/rejected/architecture/2026-06-20-providerless-example-base.md index 81dbe40ee4..2f41476a48 100644 --- a/.agents/notes/rejected/architecture/2026-06-20-providerless-example-base.md +++ b/.agents/notes/rejected/architecture/2026-06-20-providerless-example-base.md @@ -2,6 +2,8 @@ Status: rejected — superseded by [Extract example apps into packages](../../implemented/architecture/2026-06-20-extract-example-app-packages.md), which moves the spine into a `dsh-agent-spine-demo` bundle and deletes the `base*.yml` files, so there is no shared base YAML left to rename. +English | [中文](2026-06-20-providerless-example-base.zh.md) + ## Problem The examples had two shared base files: `examples/base-core.yml` was providerless, while `examples/base.yml` included that core plus the real `llm-deepseek` adapter. Snapshot replay needs the providerless core with `llm-replay`, because loading the real adapter without a key throws. The normal demos need the real adapter. The result was a naming inversion: the file named `base.yml` was not the reusable base for all examples, while the true base was `base-core.yml`. diff --git a/.agents/notes/rejected/architecture/2026-06-20-providerless-example-base.zh.md b/.agents/notes/rejected/architecture/2026-06-20-providerless-example-base.zh.md new file mode 100644 index 0000000000..e767d6b3a3 --- /dev/null +++ b/.agents/notes/rejected/architecture/2026-06-20-providerless-example-base.zh.md @@ -0,0 +1,31 @@ +# Agent Note: 使共享示例基础配置与提供方无关 + +Status: rejected — 已由[将示例应用提取到 packages 中](../../implemented/architecture/2026-06-20-extract-example-app-packages.md)取代;后者把主干移入 `dsh-agent-spine-demo` bundle 并删除 `base*.yml` 文件,因此已不存在可重命名的共享基础 YAML。 + +[English](2026-06-20-providerless-example-base.md) | 中文 + +## 问题 + +示例曾有两个共享基础文件:`examples/base-core.yml` 与提供方无关,而 `examples/base.yml` 在该核心基础上加入了真实的 `llm-deepseek` 适配器。快照回放需要与提供方无关的核心配合 `llm-replay` 使用,因为在没有密钥的情况下加载真实适配器会抛出异常。常规演示则需要真实适配器。结果是命名与实际含义倒挂:名为 `base.yml` 的文件并非所有示例可复用的基础,而真正的基础反倒是 `base-core.yml`。 + +这种拆分可以理解,但它让每次解释配置都变得更冗长。它还导致了别扭的测试搭建方式,例如无密钥冒烟测试不得不携带一个虚拟 API key,仅仅为了让适配器能启动——尽管模型根本不会被调用。 + +## 提案 + +将与提供方无关的核心重命名为 `examples/base.yml`,让适配器选择在每个具体示例中显式声明。编码和 ACP(Agent Client Protocol)真实配置添加一小段 `llm-deepseek` include 或本地块;快照配置添加 `llm-replay`。删除 `examples/base-core.yml`。 + +共享基础应仅包含提供方无关的服务与工具:`llm`、会话、系统提示词、工具、agent(智能体)、不变式、bash 执行器和 bash 工具 schema。任何涉及模型提供方选择的内容都应放在叶子配置中。 + +## 验收标准 + +- `examples/base.yml` 与提供方无关。 +- `examples/base-core.yml` 已删除。 +- 真实演示配置显式添加 DeepSeek 适配器。 +- 快照回放配置 include 同一个与提供方无关的基础,并加入其回放适配器。 +- [examples README](../../../../examples/README.md)、各示例 README 及 Agent Note(agent 决策记录)引用不再解释「base = base-core 加适配器」。 + +## 放弃了什么 + +真实演示失去了一层便利:每个演示都必须显式引入适配器。对于示例而言这是正确的默认行为,因为适配器选择是可变部分,而与提供方无关的接线才是共享的产品核心。 + +<!-- agent-note-format: alternatives-not-recorded (pre-format Agent Note) --> diff --git a/.agents/notes/rejected/process/2026-07-04-generate-agent-note-index-tables.i18n.yaml b/.agents/notes/rejected/process/2026-07-04-generate-agent-note-index-tables.i18n.yaml new file mode 100644 index 0000000000..449f33cbff --- /dev/null +++ b/.agents/notes/rejected/process/2026-07-04-generate-agent-note-index-tables.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-04-generate-agent-note-index-tables.md: 6e5221f018942a0629f30b6e6f22cedfb9f4145e +2026-07-04-generate-agent-note-index-tables.zh.md: f8ebcd51933b3ad91e0197fc71c0d8aae568bbcf diff --git a/.agents/notes/rejected/process/2026-07-04-generate-agent-note-index-tables.md b/.agents/notes/rejected/process/2026-07-04-generate-agent-note-index-tables.md index 90c942411d..6e5221f018 100644 --- a/.agents/notes/rejected/process/2026-07-04-generate-agent-note-index-tables.md +++ b/.agents/notes/rejected/process/2026-07-04-generate-agent-note-index-tables.md @@ -2,6 +2,8 @@ Status: rejected — a centralized generated list is merge-prone and adds little discovery value +English | [中文](2026-07-04-generate-agent-note-index-tables.zh.md) + ## Problem Per-lifecycle/per-class tables would list facts that are fully derivable: an Agent Note's path encodes lifecycle and class, its filename encodes the first-proposed date, and its H1 carries the title. A hand-maintained copy of those facts would also be a high-contention docs hotspot because concurrent Agent Note branches append rows to the same few lines. [The classification Agent Note](../../implemented/process/2026-06-20-agent-note-classification.md) makes the tree itself authoritative. diff --git a/.agents/notes/rejected/process/2026-07-04-generate-agent-note-index-tables.zh.md b/.agents/notes/rejected/process/2026-07-04-generate-agent-note-index-tables.zh.md new file mode 100644 index 0000000000..f8ebcd5193 --- /dev/null +++ b/.agents/notes/rejected/process/2026-07-04-generate-agent-note-index-tables.zh.md @@ -0,0 +1,38 @@ +# Agent Note: 生成 Agent Note 索引表 + +Status: rejected — 集中生成的列表容易产生合并冲突,且几乎不增加发现价值 + +[English](2026-07-04-generate-agent-note-index-tables.md) | 中文 + +## 问题 + +按生命周期和分类划分的表格只会列出完全可推导的事实:Agent Note(agent 决策记录)的路径编码其生命周期和分类,文件名编码首次提出日期,H1 承载标题。手工维护这些事实的副本还会成为高冲突文档热点,因为并发的 Agent Note 分支会向相同的几行追加条目。[分类 Agent Note](../../implemented/process/2026-06-20-agent-note-classification.md) 将目录树本身定为权威来源。 + +## 提案 + +保留策展文本,并将列表生成为完全生成的 `.agents/notes/INDEX.md`。共享的 `scripts/agent-note-index.ts` 模块将同时负责目录树遍历器和渲染器。两个轻量消费方会共用它: + +- `scripts/gen-agent-note-index.ts`(`pnpm run gen-agent-note-index`)将根据目录树完整重写 INDEX.md。 +- `scripts/verify-agent-note-classification.ts` 将检查结构,并断言已提交的 INDEX.md 与新鲜渲染结果逐字节一致。 + +添加、移动或删除 Agent Note 时,只需编辑 Agent Note 文件并运行生成器。 + +## 曾考虑的替代方案 + +### 为什么不在 README.md 中使用标记分隔区域? + +README.md 中由标记分隔的表格会混合生成内容与策展文本,因而需要拼接机制并保护周围的契约。专用生成文件至少能将这些关注点分开。 + +### 为什么不采用纯校验器模式? + +它能捕获错误,但每次提案编辑仍然要在手工维护的表格中触碰共享热点。作者已经命名并放置了文件,因此索引副本不增加任何信息。这与[包(package)清单提案](../../proposed/process/2026-06-20-discover-package-inventory.md)对 tsconfig 引用和 knip 配置段所做的手写列表与推导之间的判断相同。 + +## 后果 + +- 生成文件将是显式的,且不包含任何策展区域。 +- H1 格式错误或缺失将是硬错误,因为 H1 为每一行提供标题。 +- 即使可以通过重新运行生成器解决冲突,并发分支仍会修改同一个已提交产物。 + +## 相关 + +已落地的[不建立索引决策](../../implemented/process/2026-07-19-remove-generated-agent-note-index.md)保留目录树和仓库搜索作为发现机制。 diff --git a/.agents/notes/rejected/simplification/2026-06-20-assembled-assistant-messages-only.i18n.yaml b/.agents/notes/rejected/simplification/2026-06-20-assembled-assistant-messages-only.i18n.yaml new file mode 100644 index 0000000000..6685685e24 --- /dev/null +++ b/.agents/notes/rejected/simplification/2026-06-20-assembled-assistant-messages-only.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-20-assembled-assistant-messages-only.md: ba8135a3d63f292cfedd23de8b4b9d43b4455e8c +2026-06-20-assembled-assistant-messages-only.zh.md: 9a42a202425158edd85d7a3f2ef4b0b97e00da90 diff --git a/.agents/notes/rejected/simplification/2026-06-20-assembled-assistant-messages-only.md b/.agents/notes/rejected/simplification/2026-06-20-assembled-assistant-messages-only.md index 62dd7609e8..ba8135a3d6 100644 --- a/.agents/notes/rejected/simplification/2026-06-20-assembled-assistant-messages-only.md +++ b/.agents/notes/rejected/simplification/2026-06-20-assembled-assistant-messages-only.md @@ -2,6 +2,8 @@ Status: rejected — high-fidelity chunk replay, partial failed streams, and snapshot replay currently depend on persisted `assistant/chunk` events. Dropping chunks is only viable with a no-information-loss replay/artifact replacement. +English | [中文](2026-06-20-assembled-assistant-messages-only.zh.md) + ## Problem The canonical session log currently persists every `assistant/chunk` exactly as streamed by the model. The [session persistence Agent Note](../../implemented/architecture/2026-06-14-session-persistence.md) chose this for token-level replay fidelity and contiguous `seq`, but the cost has grown: JSONL fixtures are dominated by tiny delta records, snapshot scenarios replay the model by grouping chunk events, ACP load reconstructs prior assistant output from chunks, and any future log reader must distinguish durable message history from token-level trace. diff --git a/.agents/notes/rejected/simplification/2026-06-20-assembled-assistant-messages-only.zh.md b/.agents/notes/rejected/simplification/2026-06-20-assembled-assistant-messages-only.zh.md new file mode 100644 index 0000000000..9a42a20242 --- /dev/null +++ b/.agents/notes/rejected/simplification/2026-06-20-assembled-assistant-messages-only.zh.md @@ -0,0 +1,36 @@ +# Agent Note: 仅持久化组装后的 assistant 消息,不存储流式分片 + +Status: rejected — 高保真分片回放、部分失败流与快照回放目前依赖持久化的 `assistant/chunk` 事件。只有具备不丢失信息的回放/产物替代方案后,才能删除分片。 + +[English](2026-06-20-assembled-assistant-messages-only.md) | 中文 + +## 问题 + +当前的规范会话日志会持久化模型流式输出的每一个 `assistant/chunk`。[会话持久化 Agent Note(agent 决策记录)](../../implemented/architecture/2026-06-14-session-persistence.md)选择这一方案是为了 token 级别的回放保真度和连续的 `seq`,但其代价日益增长:JSONL fixture(测试前置数据)被大量微小的 delta 记录占据,快照场景通过对分片事件分组来回放模型,ACP(Agent Client Protocol)加载时从分片重建先前的 assistant 输出,而任何未来的日志读取方都必须区分持久的消息历史与 token 级别的追踪。 + +对于成功组装出完整内容的步骤,agent loop(智能体循环)已经追加了一条 `assistant/message`。这正是 `deriveMessages()` 用来构造下一次模型请求的事件。换言之,正常的可恢复会话状态无需分片即已具备;分片是实时渲染和确定性测试的产物,不是必需的会话历史。失败或中止的流则不同:部分 assistant 输出可能仅以分片形式存在,而空的 max-token 步骤可能根本不产生 `assistant/message`。 + +## 提案 + +停止在规范会话日志中存储 `assistant/chunk`。持久日志保留 `assistant/message`、`tool/call`、`tool/result`、`usage`(如保留)以及轮次边界。实时 UI 仍可通过一个刻意设计为瞬态的流事件接收 token 增量。快照回放应将其模型脚本移入显式的 fixture 伴随文件,或从记录的适配器产物中派生,而非将规范的用户会话当作 token 磁带。需要部分失败流输出的场景必须在回放 fixture 中记录该输出。 + +ACP `session/load` 可以将先前的 assistant 消息作为完整内容块回放,而非模拟原始的 token 流。加载后的 transcript(文本记录)无需重现每一个历史 delta;它必须展示相同的已完成 assistant 内容,并以有效的提供方历史恢复运行。 + +## 验收标准 + +- `SessionEventMap` 移除 `assistant/chunk`,或在需要过渡性实时事件时将其标记为非持久化。 +- [会话持久化文档](../../../../packages/session-persistence/session-persistence/README.md)不再要求逐字存储每个流式分片。 +- `llm-replay` 和 ACP 快照使用显式的回放 fixture 格式或伴随文件来存储模型分片。 +- `session/load` 从 `assistant/message` 渲染已完成的 assistant 消息。 +- 存储的日志大幅缩小,且在没有分片缺口的情况下保持 `seq` 连续。 +- 会话格式版本与已记录的 fixture 一并刷新;按预发布格式策略拒绝非当前版本的存储日志。 + +## 放弃了什么 + +规范的用户会话不再能重建旧轮次的精确 token 流。它也会丢失失败或中止流的部分 assistant 输出,除非另有事件或 fixture 记录。对于当前的恢复、加载和快照契约而言,这是过大的信息损失。需要精确确定性流的测试应当直接拥有该 fixture,前提是生产会话日志为用户可见的恢复保留了足够的保真度。 + +## 相关 + +本 Agent Note 取代 [会话持久化](../../implemented/architecture/2026-06-14-session-persistence.md) 中关于分片持久化的决策,并影响 [ACP 快照测试](../../implemented/testing/2026-06-19-acp-snapshot-tests.md)——其当前的回放插件从 `assistant/chunk` 事件派生脚本。 + +<!-- agent-note-format: alternatives-not-recorded (pre-format Agent Note) --> diff --git a/.agents/notes/rejected/simplification/2026-06-20-drop-acp-session-load.i18n.yaml b/.agents/notes/rejected/simplification/2026-06-20-drop-acp-session-load.i18n.yaml new file mode 100644 index 0000000000..d06734c3ea --- /dev/null +++ b/.agents/notes/rejected/simplification/2026-06-20-drop-acp-session-load.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-20-drop-acp-session-load.md: 2b6edf173506929f2d64e910b47aa70fb4f1d854 +2026-06-20-drop-acp-session-load.zh.md: 8e03acad17cf2831a15d5992a0419a73f275719d diff --git a/.agents/notes/rejected/simplification/2026-06-20-drop-acp-session-load.md b/.agents/notes/rejected/simplification/2026-06-20-drop-acp-session-load.md index b8b9b29987..2b6edf1735 100644 --- a/.agents/notes/rejected/simplification/2026-06-20-drop-acp-session-load.md +++ b/.agents/notes/rejected/simplification/2026-06-20-drop-acp-session-load.md @@ -2,6 +2,8 @@ Status: rejected — Zed is the current target ACP client, advertises and exercises load-capable sessions, and keeps pending-load state for concurrent `session/load`. The bridge should keep `session/load` and make the resume contract solid. +English | [中文](2026-06-20-drop-acp-session-load.zh.md) + ## Problem ACP advertises `loadSession: true` and implements `session/load` by injecting persistence into the bridge, validating cwd against stored metadata, reconstructing an agent from the persisted log, and replaying prior transcript updates to the client. That path has its own race handling, loading-id guard, replay presenter logic, and tests. It also depends on the canonical log retaining enough UI data to reconstruct old chunks and tool presentations. diff --git a/.agents/notes/rejected/simplification/2026-06-20-drop-acp-session-load.zh.md b/.agents/notes/rejected/simplification/2026-06-20-drop-acp-session-load.zh.md new file mode 100644 index 0000000000..8e03acad17 --- /dev/null +++ b/.agents/notes/rejected/simplification/2026-06-20-drop-acp-session-load.zh.md @@ -0,0 +1,29 @@ +# Agent Note: 移除 ACP(Agent Client Protocol)session/load,直到恢复具备产品形态 + +Status: rejected — Zed 是当前目标 ACP 客户端,它声明并实际使用支持加载的会话,还为并发的 `session/load` 保留待加载状态。桥接层应保留 `session/load` 并巩固恢复契约。 + +[English](2026-06-20-drop-acp-session-load.md) | 中文 + +## 问题 + +ACP 声明 `loadSession: true` 并实现 `session/load`:向 bridge 注入持久化能力、校验 cwd 与存储元数据的一致性、从持久化日志重建 agent(智能体),并向客户端回放先前的 transcript(文本记录)更新。该路径有自己的竞态处理、loading-id 守卫、回放展示逻辑和测试。它还依赖规范日志保留足够的 UI 数据,以重建旧的分片和工具展示。 + +持久化仍然是基础能力,但编辑器可见的恢复尚未经过产品流程设计。目前没有会话选择器、没有标题/预览元数据,也没有明确的加载失败或部分加载的用户体验。bridge 正在为一个仅被测试、文档和当前目标客户端的会话模型所使用的功能付出复杂度代价。 + +## 提案 + +当前阶段,ACP 仅启动全新会话。`initialize` 声明 `loadSession: false` 或省略该能力,`session/load` 不予支持。持久化仍可供 agent loop(智能体循环)和测试使用;如果其他消费方需要,恢复仍可作为底层工厂存在。编辑器 bridge 应在具备真正的会话选择 UX 和稳定的 load transcript 契约后,再重新引入 `session/load`。 + +## 验收标准 + +- ACP 不再注入 `sessionPersistence`;它原本仅供 `session/load` 使用。 +- `initialize` 不再声明 load 支持。 +- `session/load` handler、loading-id 追踪、已加载会话的 cwd 预检以及 load 回放测试均被移除。 +- 快照 fixture(测试前置数据)不再依赖 load 回放展示。 +- [ACP 文档](../../../../packages/ui/acp/README.md)仅描述全新会话的支持。 + +## 放弃的能力 + +编辑器无法通过 ACP 重新打开先前持久化的会话。这确实是一项产品功能,但当前实现超前于 UX 设计,且将 bridge 绑定到 token 级别的日志回放。保留持久化但移除编辑器 load,可将 bridge 收窄到它当前能干净呈现的工作流。 + +<!-- agent-note-format: alternatives-not-recorded (pre-format Agent Note) --> diff --git a/.agents/notes/rejected/simplification/2026-06-20-drop-acp-terminal-meta.i18n.yaml b/.agents/notes/rejected/simplification/2026-06-20-drop-acp-terminal-meta.i18n.yaml new file mode 100644 index 0000000000..45949d3fcf --- /dev/null +++ b/.agents/notes/rejected/simplification/2026-06-20-drop-acp-terminal-meta.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-20-drop-acp-terminal-meta.md: 79da387ac1a7a0e6767e3bf24baa6039e39ef90d +2026-06-20-drop-acp-terminal-meta.zh.md: d29fd54618611f56fd071a0ee4a63bc207895d89 diff --git a/.agents/notes/rejected/simplification/2026-06-20-drop-acp-terminal-meta.md b/.agents/notes/rejected/simplification/2026-06-20-drop-acp-terminal-meta.md index 8ce4803f73..79da387ac1 100644 --- a/.agents/notes/rejected/simplification/2026-06-20-drop-acp-terminal-meta.md +++ b/.agents/notes/rejected/simplification/2026-06-20-drop-acp-terminal-meta.md @@ -2,6 +2,8 @@ Status: rejected — Zed is the current target client, and the terminal `_meta` convention is intentional Zed UX with a plain ACP fallback for other clients. +English | [中文](2026-06-20-drop-acp-terminal-meta.zh.md) + ## Problem The ACP bridge implements a Zed-specific terminal-card convention through `_meta.terminal_info`, `_meta.terminal_output`, and `_meta.terminal_exit`. The implemented [rich ACP bash rendering Agent Note](../../implemented/feature/2026-06-18-acp-terminal-and-tool-rendering.md) deliberately avoided ACP's client-side `terminal/create` because bash execution belongs in the harness, but still adopted the reference agents' display-only `_meta` convention. That gives a nicer Zed card at the cost of bridge state, capability negotiation, terminal ids, special update mapping, text fallback tests, and exit-pill parsing in `dsh-tool-bash`. diff --git a/.agents/notes/rejected/simplification/2026-06-20-drop-acp-terminal-meta.zh.md b/.agents/notes/rejected/simplification/2026-06-20-drop-acp-terminal-meta.zh.md new file mode 100644 index 0000000000..d29fd54618 --- /dev/null +++ b/.agents/notes/rejected/simplification/2026-06-20-drop-acp-terminal-meta.zh.md @@ -0,0 +1,31 @@ +# Agent Note: 移除 ACP(Agent Client Protocol)终端 `_meta` 渲染 + +Status: rejected — Zed 是当前目标客户端,terminal `_meta` 约定是有意设计的 Zed UX,同时为其他客户端保留普通 ACP 回退。 + +[English](2026-06-20-drop-acp-terminal-meta.md) | 中文 + +## 问题 + +ACP 桥接层通过 `_meta.terminal_info`、`_meta.terminal_output` 和 `_meta.terminal_exit` 实现了一套 Zed 特有的终端卡片约定。已实现的[富 ACP bash 渲染 Agent Note(agent 决策记录)](../../implemented/feature/2026-06-18-acp-terminal-and-tool-rendering.md)刻意回避了 ACP 客户端侧的 `terminal/create`(因为 bash 执行属于 harness 职责),但仍采用了参考 agent(智能体)的纯展示 `_meta` 约定。这在 Zed 中带来了更好的卡片效果,代价是桥接状态、能力协商、终端 id、特殊的 update 映射、文本回退测试,以及 `dsh-tool-bash` 中的 exit-pill 解析。 + +回退路径已经存在:将工具调用和完成输出渲染为普通 ACP 内容块。非 Zed 客户端本来就依赖这条路径,但 Zed 终端卡片是当前目标客户端的功能特性,而非推测性装饰。 + +## 提案 + +忽略 `clientCapabilities._meta.terminal_output`,通过纯 ACP 内容路径渲染 bash 结果。执行仍由 agent 侧的 `dsh-bash` 完成;仅移除展示相关的终端元数据。如果 ACP 日后标准化了 agent 执行的终端,或产品决定 Zed 特有展示值得其维护成本,终端卡片可以再回来。 + +本提案比[收拢工具自有 UI 展示](2026-06-20-generic-tool-rendering.md)更窄:如果通用的 `presentCall`/`presentResult` 保留,本提案不影响它们,只移除终端子形态与 `_meta` 映射。 + +## 验收标准 + +- ACP 不再读取或存储 `_meta.terminal_output` 能力状态。 +- `TerminalRendering`、终端 id、终端 cwd 解析与 `_meta.terminal_*` update 映射从 `@deepseek-ai/dsh-acp` 中消失。 +- `ToolTerminal` 从 `@deepseek-ai/dsh-tools` 中消失,或在展示清理中因未使用而删除。 +- Bash 结果展示不再为终端 pill 解析退出状态。 +- 已实现的[富 ACP bash 渲染 Agent Note](../../implemented/feature/2026-06-18-acp-terminal-and-tool-rendering.md) 作为已交付历史保留在 `implemented/` 中;如被本提案取代,则加上交叉链接。 + +## 放弃的内容 + +Zed 用户将失去专用终端卡片:没有 cwd 头部、终端展示或 exit pill。他们仍能以纯内容形式看到命令和输出。在 ACP 桥接层尚未发布、`_meta` 键只是约定而非标准的阶段,这是合理的简化。 + +<!-- agent-note-format: alternatives-not-recorded (pre-format Agent Note) --> diff --git a/.agents/notes/rejected/simplification/2026-06-20-drop-bash-output-spill-files.i18n.yaml b/.agents/notes/rejected/simplification/2026-06-20-drop-bash-output-spill-files.i18n.yaml new file mode 100644 index 0000000000..e09db8fbbf --- /dev/null +++ b/.agents/notes/rejected/simplification/2026-06-20-drop-bash-output-spill-files.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-20-drop-bash-output-spill-files.md: b2bd1a04ee1524bab29814ffa7c22712a83ee5f7 +2026-06-20-drop-bash-output-spill-files.zh.md: c1b5670fac28a90cc4eb229ba0013e39067af8eb diff --git a/.agents/notes/rejected/simplification/2026-06-20-drop-bash-output-spill-files.md b/.agents/notes/rejected/simplification/2026-06-20-drop-bash-output-spill-files.md index 939255f91e..b2bd1a04ee 100644 --- a/.agents/notes/rejected/simplification/2026-06-20-drop-bash-output-spill-files.md +++ b/.agents/notes/rejected/simplification/2026-06-20-drop-bash-output-spill-files.md @@ -2,6 +2,8 @@ Status: rejected — full-output recovery is a real bash behavior. A future artifact/blob service may generalize it, but dropping spill files before that replacement would lose useful command output. +English | [中文](2026-06-20-drop-bash-output-spill-files.zh.md) + ## Problem `dsh-bash-local` keeps bounded in-memory output and spills large stdout/stderr streams into private temp files. That requires a private directory, random owner-only file creation, close-failure handling, byte-offset incremental reads, lossy read reporting, path rendering in model-facing text, and cleanup discipline. The tool then tells the model to read a local spill path when output was truncated. diff --git a/.agents/notes/rejected/simplification/2026-06-20-drop-bash-output-spill-files.zh.md b/.agents/notes/rejected/simplification/2026-06-20-drop-bash-output-spill-files.zh.md new file mode 100644 index 0000000000..c1b5670fac --- /dev/null +++ b/.agents/notes/rejected/simplification/2026-06-20-drop-bash-output-spill-files.zh.md @@ -0,0 +1,31 @@ +# Agent Note: 移除 bash 完整输出溢出文件 + +Status: rejected — 完整输出恢复是真实的 bash 行为。未来的产物/blob 服务或许能将其泛化,但在替代方案就位前删除溢出文件会丢失有用的命令输出。 + +[English](2026-06-20-drop-bash-output-spill-files.md) | 中文 + +## 问题 + +`dsh-bash-local` 在内存中保留有界的输出,并将大体量的 stdout/stderr 流溢出到私有临时文件。这要求一个私有目录、仅所有者可写的随机文件创建、关闭失败处理、基于字节偏移的增量读取、有损读取报告、在面向模型的文本中渲染路径,以及清理纪律。当输出被截断时,该工具会告知模型去读取一个本地溢出路径。 + +这解决了一个真实问题,但方式狭隘且有泄漏。溢出路径是一个暴露在模型输出中的进程级文件系统产物,而非具有作用域访问控制、保留策略或 UI 支持的持久化 harness 产物。它还使后台任务的读取变得复杂,因为有损增量读取必须指向一个或两个溢出文件。 + +## 提案 + +保留尾部截断,移除完整输出溢出文件。bash 结果包含有界的尾部内容加一个明确的截断标记;不输出路径。如果用户需要恢复完整输出,则添加一个通用的产物/blob 服务(具有明确的所有权、清理和 UI 渲染),然后让 bash 将大体量输出附加到该服务。 + +本提案可以独立于[通用长时间运行工具运行时](../../implemented/architecture/2026-06-20-generic-long-running-tool-runtime.md)落地。如果后台任务保留,`bash_output` 仍应报告输出已被丢弃,但不再提供溢出路径。 + +## 验收标准 + +- `CollectedOutput` 不再携带溢出路径。 +- `OutputCollector` 仅保留有界缓冲区,删除临时文件机制。 +- `renderResult()` 报告截断时不包含文件系统路径。 +- 测试覆盖尾部截断,不再断言完整输出文件的内容。 +- [docs/defensive-patterns.md](../../../../docs/defensive-patterns.md) 中的安全指导不再将私有溢出文件视为面向模型的接口。 + +## 放弃的能力 + +模型或用户无法再从临时文件恢复大体量命令输出中被省略的前缀。在真正的产物服务出现之前,这是可以接受的。当前的溢出路径为一个生命周期和权限均未经设计的功能引入了过多的定制机制。 + +<!-- agent-note-format: alternatives-not-recorded (pre-format Agent Note) --> diff --git a/.agents/notes/rejected/simplification/2026-06-20-drop-durable-step-boundaries.i18n.yaml b/.agents/notes/rejected/simplification/2026-06-20-drop-durable-step-boundaries.i18n.yaml new file mode 100644 index 0000000000..698d5a5ad6 --- /dev/null +++ b/.agents/notes/rejected/simplification/2026-06-20-drop-durable-step-boundaries.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-20-drop-durable-step-boundaries.md: c5c4f269a378e334c4dc509d1288146d77d9a520 +2026-06-20-drop-durable-step-boundaries.zh.md: f2150699c74b16557d936d6833fcba02e7d76e69 diff --git a/.agents/notes/rejected/simplification/2026-06-20-drop-durable-step-boundaries.md b/.agents/notes/rejected/simplification/2026-06-20-drop-durable-step-boundaries.md index b2bf42a348..c5c4f269a3 100644 --- a/.agents/notes/rejected/simplification/2026-06-20-drop-durable-step-boundaries.md +++ b/.agents/notes/rejected/simplification/2026-06-20-drop-durable-step-boundaries.md @@ -2,6 +2,8 @@ Status: rejected — `step/end` is the durable indication that a model step finished, and keeping the symmetric `step/start` / `step/end` pair makes crash repair, invariants, and transcript inspection clearer than inferring completion from adjacent step-scoped events. +English | [中文](2026-06-20-drop-durable-step-boundaries.zh.md) + ## Problem The session log stores `step/start` and `step/end` events even though every step-scoped event already carries `{ turn, step }`: assistant chunks, assistant messages, tool calls, tool results, usage, and errors. `deriveMessages()` ignores step boundaries, ACP ignores them for UI, and the main consumers are invariants, tests, snapshot expected outputs, and crash repair. diff --git a/.agents/notes/rejected/simplification/2026-06-20-drop-durable-step-boundaries.zh.md b/.agents/notes/rejected/simplification/2026-06-20-drop-durable-step-boundaries.zh.md new file mode 100644 index 0000000000..f2150699c7 --- /dev/null +++ b/.agents/notes/rejected/simplification/2026-06-20-drop-durable-step-boundaries.zh.md @@ -0,0 +1,32 @@ +# Agent Note: 移除持久化的步骤边界事件 + +Status: rejected — `step/end` 是模型步骤已完成的持久信号;保留对称的 `step/start` / `step/end` 对,比从相邻的步骤作用域事件推断完成状态更便于理解崩溃修复、不变式与 transcript(文本记录)检查。 + +[English](2026-06-20-drop-durable-step-boundaries.md) | 中文 + +## 问题 + +会话日志存储了 `step/start` 和 `step/end` 事件,尽管每个步骤作用域的事件本身已经携带 `{ turn, step }`:assistant 分片、assistant 消息、工具调用、工具结果、用量和错误。`deriveMessages()` 忽略步骤边界,ACP(Agent Client Protocol)在 UI 层面也忽略它们,主要消费方是不变式检查、测试、快照预期输出和崩溃恢复。 + +被否决的论点是:边界事件使日志更像仪式而非信息。实际上,`step/end` 是具体信息:读者无需从下一个事件推导状态,就能判断一次模型请求是已完成、已崩溃还是正在修复。同样,一个孤立的 `step/start` 对于「模型请求已发起但在产生任何分片之前就失败了」的场景也有价值。 + +## 提案 + +将轮次作为唯一的持久化边界。`step/start` 和 `step/end` 将从 `SessionEventMap` 中移除;在需要分组的事件上保留数值型 `step` 字段。agent loop(智能体循环)递增步骤计数器并以该编号记录步骤作用域的事件,但不再追加开/关边界事件。消费方通过共享 `(turn, step)` 的连续事件推断步骤分组。 + +不变式插件应当强制步骤作用域的事件在一个已打开的轮次内具有有效的正整数步骤编号,而非要求独立的边界记录包围它们。崩溃恢复不应合成 `step/end`;如果一个被中断的轮次被保留,修复路径仍然可以关闭该轮次而无需捏造步骤边界记录。 + +## 验收标准 + +- `SessionEventMap` 不再包含 `step/start` 或 `step/end`。 +- agent loop 中不再有 `closeStep()` 终结路径。 +- ACP 快照和持久化契约 fixture(测试前置数据)不再期望步骤边界行。 +- `deriveMessages()` 和回放从步骤作用域的事件推导出相同的消息历史。 +- [事件分类体系文档](../../../../docs/architecture.md)将轮次描述为持久化边界,将步骤描述为步骤作用域记录上的一个字段。 +- 会话格式版本和已记录的 fixture 被刷新;按预发布格式策略,非当前版本的已存储日志被拒绝。 + +## 放弃了什么 + +日志不再将「一次模型请求已发起但进程死亡前未产生任何事件」记录为持久化事实,也不再有显式的「此步骤已完成」标记。在会话日志仍是持久化回放与审计表面的当下,这一损失不可接受。 + +<!-- agent-note-format: alternatives-not-recorded (pre-format Agent Note) --> diff --git a/.agents/notes/rejected/simplification/2026-06-20-drop-unused-session-lineage.i18n.yaml b/.agents/notes/rejected/simplification/2026-06-20-drop-unused-session-lineage.i18n.yaml new file mode 100644 index 0000000000..a9913a8849 --- /dev/null +++ b/.agents/notes/rejected/simplification/2026-06-20-drop-unused-session-lineage.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-20-drop-unused-session-lineage.md: 605f1949999435b24404e0c5a72320416303ae52 +2026-06-20-drop-unused-session-lineage.zh.md: 981f44189f4b8f11f513261db7094afdc650dffa diff --git a/.agents/notes/rejected/simplification/2026-06-20-drop-unused-session-lineage.md b/.agents/notes/rejected/simplification/2026-06-20-drop-unused-session-lineage.md index c85e943476..605f194999 100644 --- a/.agents/notes/rejected/simplification/2026-06-20-drop-unused-session-lineage.md +++ b/.agents/notes/rejected/simplification/2026-06-20-drop-unused-session-lineage.md @@ -2,6 +2,8 @@ Status: rejected — `parentSession` is part of the documented fork/sub-agent seam and is already preserved by the agent/session resume path. The field is future-facing, but it is not accidental dead state. +English | [中文](2026-06-20-drop-unused-session-lineage.zh.md) + ## Problem `SessionHeader.parentSession` records the session a new session was forked from. It is defined in `dsh-session`, preserved by persistence backends, copied through resume, documented as lineage metadata, and covered by round-trip tests. The repo has no production fork UI or sub-agent flow that reads it. The planned sub-agent/fork seam is still a TODO, so the field is currently stored future shape. diff --git a/.agents/notes/rejected/simplification/2026-06-20-drop-unused-session-lineage.zh.md b/.agents/notes/rejected/simplification/2026-06-20-drop-unused-session-lineage.zh.md new file mode 100644 index 0000000000..981f44189f --- /dev/null +++ b/.agents/notes/rejected/simplification/2026-06-20-drop-unused-session-lineage.zh.md @@ -0,0 +1,31 @@ +# Agent Note: 移除未使用的会话血缘元数据 + +Status: rejected — `parentSession` 是已记录的 fork/subagent seam 的一部分,并已由 agent(智能体)/会话恢复路径保留。该字段面向未来,但并非意外遗留的死状态。 + +[English](2026-06-20-drop-unused-session-lineage.md) | 中文 + +## 问题 + +`SessionHeader.parentSession` 记录新会话从哪个会话 fork 而来。它在 `dsh-session` 中定义,被持久化后端保留,在恢复流程中复制,作为血缘元数据被文档记录,并有往返测试覆盖。然而仓库中没有任何生产环境的 fork UI 或 subagent 流程读取它。计划中的 subagent/fork seam 仍是 TODO,因此该字段目前只是预存的未来形状。 + +单个文件的成本虽小,但在格式层面影响面广:每个后端 schema 和元数据序列化器都在保留一个尚无已完成功能读取的值。由于 header 是磁盘契约,即使是占位字段也会成为未来重构必须维护、迁移或有意打破的东西。 + +## 提案 + +移除 `parentSession`,使其不再属于 `SessionHeader`,直到真正的 fork/恢复功能需要血缘信息时再引入。如果存在相应 API,fork 仍然可以用先前事件来初始化新会话,但持久化的父指针应当与读取它的功能和解释它的 UX 一同引入。 + +如果血缘信息回归,届时再决定它应放在不可变 header 中、会话图索引中,还是作为一等事件。当前字段不应预先锁定那个设计。 + +## 验收标准 + +- `SessionHeader` 仅包含 version、id、createdAt 和可选的 cwd。 +- JSONL 与 SQLite 元数据 schema 不再存储父会话 id。 +- 恢复与列表 API 不再往返传递 `parentSession`。 +- 文档和测试移除没有生产消费方支撑的 fork 血缘声明。 +- 会话格式版本、后端 schema 版本与记录的 fixture(测试前置数据)按需刷新;按预发布格式策略,非当前版本的存储数据将被拒绝,不提供迁移路径。 + +## 放弃了什么 + +代码库失去了一个为未来 fork/subagent UX 预备的现成血缘钩子。这是有意为之。该字段在功能存在时很容易重新引入,而未发布的立场允许格式变更无需迁移。 + +<!-- agent-note-format: alternatives-not-recorded (pre-format Agent Note) --> diff --git a/.agents/notes/rejected/simplification/2026-06-20-fold-session-persistence-interface.i18n.yaml b/.agents/notes/rejected/simplification/2026-06-20-fold-session-persistence-interface.i18n.yaml new file mode 100644 index 0000000000..5f3e15ee98 --- /dev/null +++ b/.agents/notes/rejected/simplification/2026-06-20-fold-session-persistence-interface.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-20-fold-session-persistence-interface.md: 895b868b2a80d8655284bae1364a85e19e174da7 +2026-06-20-fold-session-persistence-interface.zh.md: c124b16531f904eb72cb8ac3842642d819309e14 diff --git a/.agents/notes/rejected/simplification/2026-06-20-fold-session-persistence-interface.md b/.agents/notes/rejected/simplification/2026-06-20-fold-session-persistence-interface.md index 8e5d59172f..895b868b2a 100644 --- a/.agents/notes/rejected/simplification/2026-06-20-fold-session-persistence-interface.md +++ b/.agents/notes/rejected/simplification/2026-06-20-fold-session-persistence-interface.md @@ -2,6 +2,8 @@ Status: rejected — the separate persistence interface package is the intended modular capability seam for durable backends. Folding it into `dsh-session` would reduce package count at the cost of a cleaner backend boundary. +English | [中文](2026-06-20-fold-session-persistence-interface.zh.md) + ## Problem `dsh-session-persistence` is an interface package whose main concepts are already owned by `dsh-session`: `SessionHeader`, `SessionEvent`, `SessionId`, `session/event`, and `session/flush`. The package adds the abstract `SessionPersistence` service, the shared write coordinator, and contract helpers. Backend packages depend on it, and `agent-loop` has to optionally find a sibling service for resume. diff --git a/.agents/notes/rejected/simplification/2026-06-20-fold-session-persistence-interface.zh.md b/.agents/notes/rejected/simplification/2026-06-20-fold-session-persistence-interface.zh.md new file mode 100644 index 0000000000..c124b16531 --- /dev/null +++ b/.agents/notes/rejected/simplification/2026-06-20-fold-session-persistence-interface.zh.md @@ -0,0 +1,31 @@ +# Agent Note: 将持久化接口合并进 dsh-session + +Status: rejected — 独立的持久化接口包是为持久后端设计的模块化能力 seam。将其折叠进 `dsh-session` 虽能减少包数量,却会牺牲更清晰的后端边界。 + +[English](2026-06-20-fold-session-persistence-interface.md) | 中文 + +## 问题 + +`dsh-session-persistence` 是一个接口包(package),其核心概念已经由 `dsh-session` 拥有:`SessionHeader`、`SessionEvent`、`SessionId`、`session/event` 与 `session/flush`。该包额外添加了抽象的 `SessionPersistence` 服务、共享写入协调器和契约辅助工具。后端包依赖它,`agent-loop`(智能体循环)也需要可选地查找一个同级服务来实现恢复。 + +当持久化还是一个全新的可替换后端设计时,能力 seam 的拆分是合理的。但在可变摘要被移除之后,这个接口包基本上只是包装了会话日志自身的存储关切。继续保持独立可能带来的仪式感多于清晰度。 + +## 提案 + +将抽象的 `SessionPersistence` 服务、协调器和持久化契约辅助工具移入 `dsh-session`。JSONL 和 SQLite 仍作为独立的后端包,注册由会话包拥有的服务。这样既保留了后端可替换性,又删除了一个支撑包和一条跨包 seam。 + +实施 PR(Pull Request)应更新[能力 seam](../../implemented/architecture/2026-06-13-capability-seams.md) 指南,补充此例外:持久化不同于 bash 或 LLM(大语言模型),因为它的词汇和生命周期事件本就属于会话包的核心领域。 + +## 验收标准 + +- `@deepseek-ai/dsh-session-persistence` 作为包被移除。 +- `dsh-session` 导出持久化服务类型、协调器和契约辅助工具。 +- JSONL 和 SQLite 后端包直接依赖 `dsh-session`。 +- `agent-loop` 的恢复功能使用会话包拥有的服务键。 +- [会话持久化](../../implemented/architecture/2026-06-14-session-persistence.md)、[共享持久化写入协调器](../../implemented/architecture/2026-06-18-shared-persistence-write-coordinator.md)与[包文档](../../../../packages/session-persistence/session-persistence/README.md)说明后端实现为何仍保持独立。 + +## 放弃了什么 + +`dsh-session` 变得更重:它同时拥有内存日志和持久化接口。这就是代价。如果第三方持久化后端已经形成公开生态,独立的接口包会是更清晰的 SDK 边界;但在预发布阶段,在尚无外部消费方时,多出的包看起来更像是过早的抽象。 + +<!-- agent-note-format: alternatives-not-recorded (pre-format Agent Note) --> diff --git a/.agents/notes/rejected/simplification/2026-06-20-generic-tool-rendering.i18n.yaml b/.agents/notes/rejected/simplification/2026-06-20-generic-tool-rendering.i18n.yaml new file mode 100644 index 0000000000..da93063670 --- /dev/null +++ b/.agents/notes/rejected/simplification/2026-06-20-generic-tool-rendering.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-20-generic-tool-rendering.md: 6fc610546da04e7d1e16fc17ada87483a142aa3c +2026-06-20-generic-tool-rendering.zh.md: 11386b87d845129950a8473eb1cf4ea6ce697ac8 diff --git a/.agents/notes/rejected/simplification/2026-06-20-generic-tool-rendering.md b/.agents/notes/rejected/simplification/2026-06-20-generic-tool-rendering.md index dbc6ffed44..6fc610546d 100644 --- a/.agents/notes/rejected/simplification/2026-06-20-generic-tool-rendering.md +++ b/.agents/notes/rejected/simplification/2026-06-20-generic-tool-rendering.md @@ -2,6 +2,8 @@ Status: rejected — tool-owned presentation should wait for more real tools before being generalized or deleted. Bash and ACP currently need the existing richer presentation path. +English | [中文](2026-06-20-generic-tool-rendering.zh.md) + ## Problem Tools can define `presentCall()` and `presentResult()` callbacks that return `ToolCallPresentation`, `ToolResultPresentation`, and optional `ToolTerminal` fields. The code itself flags the design as muddy: title, kind, raw input, content, terminal cwd, terminal output, exit code, and signal grew incrementally into a bag of optional fields. ACP then maintains pending call state to pair a result with the original args, creates replay-only presenters on `session/load`, and maps terminal subfields into Zed-specific `_meta`. `dsh-tool-bash` even parses exit status back out of rendered text because the pure replay-safe presenter no longer has the structured `BashRunResult`. diff --git a/.agents/notes/rejected/simplification/2026-06-20-generic-tool-rendering.zh.md b/.agents/notes/rejected/simplification/2026-06-20-generic-tool-rendering.zh.md new file mode 100644 index 0000000000..11386b87d8 --- /dev/null +++ b/.agents/notes/rejected/simplification/2026-06-20-generic-tool-rendering.zh.md @@ -0,0 +1,35 @@ +# Agent Note: 收拢工具自有的 UI 展示逻辑 + +Status: rejected — 工具拥有的呈现机制应等到出现更多真实工具后再进行泛化或删除。Bash 与 ACP(Agent Client Protocol)目前仍需要现有的丰富呈现路径。 + +[English](2026-06-20-generic-tool-rendering.md) | 中文 + +## 问题 + +工具可以定义 `presentCall()` 和 `presentResult()` 回调,返回 `ToolCallPresentation`、`ToolResultPresentation` 以及可选的 `ToolTerminal` 字段。代码本身就标记了这个设计的混乱:title、kind、raw input、content、terminal cwd、terminal output、exit code 和 signal 逐步增长为一堆可选字段。ACP 随后维护 pending call 状态以将 result 与原始 args 配对,在 `session/load` 时创建仅用于回放的 presenter,并将 terminal 子字段映射为 Zed 特有的 `_meta`。`dsh-tool-bash` 甚至从渲染后的文本中反向解析退出状态,因为纯回放安全的 presenter 已经拿不到结构化的 `BashRunResult`。 + +真正的第一方用途是为 ACP 提供 bash 展示。这不足以作为冻结一个跨包(package)UI 展示 API 的依据。 + +## 提案 + +暂时移除工具自有的 UI 展示回调。规范的工具事件已经携带工具名、原始参数字符串、结果内容和错误状态。UI 从这些字段渲染一个通用的工具卡片。工具特有的富展示可以在至少有两个真实工具和两个真实消费方来验证词汇之后,以带标签的 render-intent union 形式回归。 + +## 曾考虑的替代方案 + +作为更小的替代方案,可以在一个 PR(Pull Request)中将当前的可选字段集合替换为一个显式 union;但如果目标是简化,更彻底的做法是删除回调、保留通用路径。 + +## 验收标准 + +- `ToolDefinition` 移除 `presentCall` 和 `presentResult`。 +- `ToolCallPresentation`、`ToolResultPresentation`、`ToolTerminal` 和 `ToolCallKind` 消失,除非一个最小的通用 UI 类型仍需要其中之一。 +- ACP 不再维护 presenter pending 状态,也不再在实时流式输出/加载回放期间调用工具回调。 +- `dsh-tool-bash` 不再解析渲染文本来恢复退出状态以供 UI pill 使用。 +- 快照预期输出展示通用工具卡片和文本结果。 + +## 放弃了什么 + +Bash 失去其自定义的终端风格卡片和模型生成描述的放置位置。回退方案仍然合理:命令作为工具输入展示,输出作为文本展示。富展示应当在产品拥有足够的 UI/工具多样性、足以支撑一份稳定的展示契约时再行设计。 + +## 相关 + +这是[移除 ACP terminal 元数据](2026-06-20-drop-acp-terminal-meta.md)的宽泛版本。如果本 Agent Note(agent 决策记录)被接受,那个更窄的 Agent Note 就不再必要。 diff --git a/.agents/notes/rejected/simplification/2026-06-20-retire-mid-turn-steering.i18n.yaml b/.agents/notes/rejected/simplification/2026-06-20-retire-mid-turn-steering.i18n.yaml new file mode 100644 index 0000000000..3ca6a50ef7 --- /dev/null +++ b/.agents/notes/rejected/simplification/2026-06-20-retire-mid-turn-steering.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-20-retire-mid-turn-steering.md: a8812b3222739244d77f4d4dab60cf7c0cd6907d +2026-06-20-retire-mid-turn-steering.zh.md: 81a211a167daeb8c57b98f2a1c1451dbc54d09e4 diff --git a/.agents/notes/rejected/simplification/2026-06-20-retire-mid-turn-steering.md b/.agents/notes/rejected/simplification/2026-06-20-retire-mid-turn-steering.md index b26243f197..a8812b3222 100644 --- a/.agents/notes/rejected/simplification/2026-06-20-retire-mid-turn-steering.md +++ b/.agents/notes/rejected/simplification/2026-06-20-retire-mid-turn-steering.md @@ -2,6 +2,8 @@ Status: rejected — mid-turn steering is an intentional agent capability for between-step user/plugin input and future goal/loop workflows. It is complexity with a product direction, not an accidental duplicate of `send()`. +English | [中文](2026-06-20-retire-mid-turn-steering.zh.md) + ## Problem The agent exposes two user-message paths that look close but have different lifecycle semantics: `send()` queues a normal user turn, while `steer()` injects a message between steps of the currently running turn and falls back to `send()` when idle. That distinction leaks through the whole stack: `Agent.steer()` is public API, the session log has a durable `steering/message` event, the agent event taxonomy has `agent/steering`, the loop maintains a steering FIFO beside the queued-message FIFO, cancellation clears both queues, and `deriveMessages()` has to render steering as a tagged synthetic user message rather than a normal prompt. diff --git a/.agents/notes/rejected/simplification/2026-06-20-retire-mid-turn-steering.zh.md b/.agents/notes/rejected/simplification/2026-06-20-retire-mid-turn-steering.zh.md new file mode 100644 index 0000000000..81a211a167 --- /dev/null +++ b/.agents/notes/rejected/simplification/2026-06-20-retire-mid-turn-steering.zh.md @@ -0,0 +1,37 @@ +# Agent Note: 移除轮次中途引导 + +Status: rejected — 轮次中途 steering(中途引导)是一项有意设计的 agent(智能体)能力,用于接收步骤之间的用户/插件输入以及未来的 goal/loop 工作流。它是面向产品方向的复杂度,而非 `send()` 的意外重复。 + +[English](2026-06-20-retire-mid-turn-steering.md) | 中文 + +## 问题 + +agent 暴露了两条用户消息路径,外观相近但生命周期语义不同:`send()` 将一条普通用户轮次排入队列,而 `steer()` 在当前运行轮次的步骤之间注入一条消息,空闲时则回退为 `send()`。这一区分贯穿整个栈:`Agent.steer()` 是公开 API;会话日志有持久化的 `steering/message` 事件;agent 事件分类体系有 `agent/steering`;agent loop(智能体循环)在排队消息 FIFO 之外还维护一个 steering FIFO;取消操作需要清空两个队列;`deriveMessages()` 必须将 steering 渲染为带标签的合成用户消息,而非普通提示词。 + +续行 seam 进一步放大了成本。`agent/turn-continuation` 默认条件为 `hadToolCalls || steeringInjected`,因此同一轮次内的 steering 消息即使模型未请求工具调用,也会强制循环再次调用模型。注释中提到了未来 `/goal`、`/loop` 和预算守卫的用途,但当前仓库没有生产级监听器;只有测试注册了该 waterfall(瀑布式事件)。另外,唯一调用 `steer()` 的生产 UI 是 stdio 演示。ACP(Agent Client Protocol)在轮次运行期间已经通过普通队列发送提示词。 + +## 提案 + +暂时删除轮次中途的用户 steering。`Agent.send()` 成为提交用户内容的唯一公开方式;当 agent 正在运行时,内容等待下一个轮次。循环仅因工具调用而在轮次内继续,不因用户在某个步骤运行期间输入内容而继续。调用方若要中断当前轮次,使用 `cancel()` 后再 `send()`。 + +移除 `Agent.steer()`、steering FIFO、`steering/message`、`agent/steering`、由 steering 驱动的续行逻辑,以及取消操作中区分排队消息与 steering 消息的逻辑。除非实现 PR(Pull Request)发现了生产级监听器,否则在同一变更中一并移除 `agent/turn-continuation`;没有 steering 后,当前仓库不再有具体的续行消费方。如果将来真正的预算或目标插件需要强制续行,应以该插件为具体消费方重新引入一个更窄的 seam。 + +## 验收标准 + +- `Agent` 暴露唯一的用户消息入口 `send()`。 +- 持久化会话事件词汇不再包含 `steering/message`。 +- `deriveMessages()` 渲染普通用户消息和上下文注入,不存在 steering 标签路径。 +- 循环只有一个排队消息 FIFO,没有同轮次用户消息续行路径。 +- `agent/turn-continuation` 被移除,或收窄到有具名的生产级消费方。 +- stdio UI 和文档将运行期间的输入描述为「排入下一轮次的输入」。 +- 会话格式版本和已录制的 fixture(测试前置数据)已刷新;非当前版本的存储日志按预发布格式策略被拒绝。 + +## 放弃了什么 + +用户无法在模型处于工具步骤之间时添加同轮次 steering 内容。这种行为在理论上对「你已经在工作了,也考虑一下 X」的场景有用,但它不是 ACP 当前暴露的行为,且使轮次边界更难推理。更简单的行为是合理的:用户输入成为下一条提示词,取消操作仍是替换进行中工作的显式手段。 + +## 相关 + +本提案与[移除持久化步骤边界](2026-06-20-drop-durable-step-boundaries.md)天然配对,因为移除同轮次 steering 和 `agent/turn-continuation` 后,工具调用成为一个轮次包含多个模型步骤的唯一原因。 + +<!-- agent-note-format: alternatives-not-recorded (pre-format Agent Note) --> diff --git a/.agents/notes/rejected/simplification/2026-06-20-single-session-acp-bridge.i18n.yaml b/.agents/notes/rejected/simplification/2026-06-20-single-session-acp-bridge.i18n.yaml new file mode 100644 index 0000000000..66138d0995 --- /dev/null +++ b/.agents/notes/rejected/simplification/2026-06-20-single-session-acp-bridge.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-20-single-session-acp-bridge.md: e99de76854390a0979d1b66866d1d48aacbc0036 +2026-06-20-single-session-acp-bridge.zh.md: 660e4ccf6f2fba8672315bfed30872870f401554 diff --git a/.agents/notes/rejected/simplification/2026-06-20-single-session-acp-bridge.md b/.agents/notes/rejected/simplification/2026-06-20-single-session-acp-bridge.md index 83c6f598d4..e99de76854 100644 --- a/.agents/notes/rejected/simplification/2026-06-20-single-session-acp-bridge.md +++ b/.agents/notes/rejected/simplification/2026-06-20-single-session-acp-bridge.md @@ -2,6 +2,8 @@ Status: rejected — Zed is the current target ACP client and its ACP implementation is explicitly multi-session: it stores live sessions in a `HashMap<SessionId, AcpSession>`, tracks `pending_sessions`, joins concurrent loads for the same id, and tests close-during-load behavior. +English | [中文](2026-06-20-single-session-acp-bridge.zh.md) + ## Problem The ACP bridge now supports multiple live sessions on one JSON-RPC connection. That capability brings multi-entry session maps, reverse session/agent lookups, per-session prompt state, loading ids, demux for every event, cross-session teardown, and isolation concerns for future permission prompts and background tasks. The older [multi-session ACP proposal](../../implemented/feature/2026-06-14-acp-multi-session.md) still tracks the unfinished permission-ownership piece; this Agent Note is the competing simplification path. diff --git a/.agents/notes/rejected/simplification/2026-06-20-single-session-acp-bridge.zh.md b/.agents/notes/rejected/simplification/2026-06-20-single-session-acp-bridge.zh.md new file mode 100644 index 0000000000..660e4ccf6f --- /dev/null +++ b/.agents/notes/rejected/simplification/2026-06-20-single-session-acp-bridge.zh.md @@ -0,0 +1,31 @@ +# Agent Note: 将 ACP(Agent Client Protocol)桥接恢复为每连接一个活跃会话 + +Status: rejected — Zed 是当前目标 ACP 客户端,其 ACP 实现明确支持多会话:它把活跃会话存入 `HashMap<SessionId, AcpSession>`,跟踪 `pending_sessions`,合并同一 id 的并发加载,并测试加载期间关闭的行为。 + +[English](2026-06-20-single-session-acp-bridge.md) | 中文 + +## 问题 + +ACP 桥接现在支持在一条 JSON-RPC 连接上承载多个活跃会话。这一能力带来了多条目会话映射、反向会话/agent(智能体)查找、逐会话的提示词状态、加载中 id、每条事件的解复用、跨会话拆除,以及未来权限提示与后台任务的隔离问题。较早的[多会话 ACP 提案](../../implemented/feature/2026-06-14-acp-multi-session.md)仍在追踪未完成的权限归属部分;本 Agent Note(agent 决策记录)是与之竞争的简化路径。 + +产品目标已经证明它需要在一个 harness 进程上承载并发的编辑器对话:Zed 的 ACP 连接拥有多个会话和加载状态。快照回放层仍然避免并发模型流,因为其回放条目是位置相关的;这是测试 fixture(测试前置数据)的局限,而非移除桥接多路复用的理由。 + +## 提案 + +将 ACP 的范围收回到每连接一个活跃会话。`session/new` 或 `session/load` 创建唯一的会话记录;在现有会话被 dispose(资源释放)或连接关闭之前,第二个活跃会话请求将被拒绝。如果编辑器需要多个聊天标签页,可以启动多个 agent 子进程,直到桥接具备具体的多会话 UX 和权限模型。 + +移除多会话映射和解复用逻辑,改用单一的 `SessionRecord | undefined` 即可。桥接仍可保留使 dispose 正确的 agent/会话生命周期 seam;简化仅针对在同一传输层上多路复用多个活跃会话这一点。 + +## 验收标准 + +- ACP 每连接只有一条活跃会话记录。 +- 当该记录存在时,`session/new` 和 `session/load` 拒绝请求。 +- 事件处理器不再在 `Map<sessionId, record>` 上做解复用。 +- 多会话测试被移除,或移至继续支持多路复用的提案下。 +- 既有的[多会话 ACP 提案](../../implemented/feature/2026-06-14-acp-multi-session.md)更新为链接本 Agent Note,并继续作为当前方向。 + +## 放弃了什么 + +ACP 客户端无法在一个服务器进程上承载多个并发对话。这是一项有实质意义的能力削减。对于一个尚未发布的 harness 而言,更简单的模型仍然合理:一个编辑器对话对应一个 agent 进程,跨会话的权限/后台任务隔离不再是活跃的正确性负担。 + +<!-- agent-note-format: alternatives-not-recorded (pre-format Agent Note) --> diff --git a/.agents/notes/rejected/simplification/2026-06-20-truncate-interrupted-turns.i18n.yaml b/.agents/notes/rejected/simplification/2026-06-20-truncate-interrupted-turns.i18n.yaml new file mode 100644 index 0000000000..98845d7e03 --- /dev/null +++ b/.agents/notes/rejected/simplification/2026-06-20-truncate-interrupted-turns.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-06-20-truncate-interrupted-turns.md: af18618ad4c41af125e37c51b9fd971dd8eae64e +2026-06-20-truncate-interrupted-turns.zh.md: a20d0169f7735aa7a9437c10c958580c00704171 diff --git a/.agents/notes/rejected/simplification/2026-06-20-truncate-interrupted-turns.md b/.agents/notes/rejected/simplification/2026-06-20-truncate-interrupted-turns.md index a685765197..af18618ad4 100644 --- a/.agents/notes/rejected/simplification/2026-06-20-truncate-interrupted-turns.md +++ b/.agents/notes/rejected/simplification/2026-06-20-truncate-interrupted-turns.md @@ -2,6 +2,8 @@ Status: rejected — a single turn can contain substantial real work, including many steps and large tool output. Preserving interrupted turns is preferable to silently dropping that tail on load. +English | [中文](2026-06-20-truncate-interrupted-turns.zh.md) + ## Problem The current persistence contract preserves a final turn that was durably written but never closed. On load, `interruptedTurnClosers()` scans the tail, synthesizes error `tool/result` events for unanswered tool calls, appends a `step/end` when a step is open, appends `turn/end { kind: 'interrupted' }`, and asks the backend to durably commit that repair. The coordinator, JSONL backend, SQLite backend, session event vocabulary, invariants, docs, and tests all model this synthetic close path. diff --git a/.agents/notes/rejected/simplification/2026-06-20-truncate-interrupted-turns.zh.md b/.agents/notes/rejected/simplification/2026-06-20-truncate-interrupted-turns.zh.md new file mode 100644 index 0000000000..a20d0169f7 --- /dev/null +++ b/.agents/notes/rejected/simplification/2026-06-20-truncate-interrupted-turns.zh.md @@ -0,0 +1,36 @@ +# Agent Note: 加载时截断被中断的最终轮次 + +Status: rejected — 单个轮次可以包含大量真实工作,包括多个步骤和大量工具输出。保留被中断的轮次,优于在加载时静默丢弃这段尾部。 + +[English](2026-06-20-truncate-interrupted-turns.md) | 中文 + +## 问题 + +当前的持久化契约会保留已持久写入但从未关闭的最终轮次。加载时,`interruptedTurnClosers()` 扫描尾部,为未应答的工具调用合成 error `tool/result` 事件,在步骤处于打开状态时追加 `step/end`,追加 `turn/end { kind: 'interrupted' }`,并要求后端持久提交这次修复。协调器、JSONL 后端、SQLite 后端、会话事件词汇、不变式、文档和测试都对这条合成关闭路径进行了建模。 + +这是一套庞大的机制,只为保留上次崩溃轮次中的部分工作。它还会凭空创造从未发生过的事件。合成的工具结果虽然有用(因为它使提供方历史保持合法),但也意味着恢复后的日志中包含了模型可见、却并非任何工具产出的文本。当前设计在尚无已发布产品、也没有真实恢复 UX 来证明部分轮次恢复确有价值的情况下,就优化了最大化尾部保留。 + +## 提案 + +加载时只保留最后一个已完成的轮次。后端仍然容忍并截断撕裂的最终记录,但如果解析出的持久前缀止于一个打开的 `turn/start` 之后,规范的修复方式是丢弃上一个 `turn/end` 之后的所有事件。不合成 `tool/result`,不合成 `step/end`,不追加 `turn/end { interrupted }`,也不引入 `interrupted` 轮次结束原因。 + +这使持久化的轮次边界变得简单:一个已完成的 `turn/end` 就是检查点。最后一个检查点之后的内容都是崩溃尾部。下一次提示词从最后一个已知合法的提供方 transcript(文本记录)恢复,而不是从部分重建的最终轮次恢复。 + +## 验收标准 + +- `TurnEndReasonMap` 移除 `interrupted` 变体。 +- `interruptedTurnClosers()` 及其测试删除。 +- 持久化协调器的修复钩子截断后端特有的撕裂/打开尾部状态,不追加关闭事件。 +- [会话持久化文档](../../../../packages/session-persistence/session-persistence/README.md)说明加载返回最后一个已完成的轮次,不包含部分最终轮次。 +- 快照与契约测试随其所固定的行为一同更新。 +- 会话格式版本与记录的 fixture(测试前置数据)刷新;按预发布格式策略,非当前版本的存储日志被拒绝,不提供迁移路径。 + +## 放弃的内容 + +崩溃可能丢失最终轮次中的真实工作:上一个 `turn/end` 之后追加的助手文本、工具调用和工具输出。这是有意为之的简化。产品尚未发布,最终轮次恢复的语义未经用户验证,而一个干净的「已完成轮次即检查点」模型在解释、测试和实现上都容易得多。未来若需「恢复部分崩溃工作」功能,应设计为面向用户的显式恢复视图,而非静默插入规范 transcript 的合成事件。 + +## 相关 + +本提案是对[会话持久化](../../implemented/architecture/2026-06-14-session-persistence.md)与[轮次封闭不变式](../../implemented/architecture/2026-06-15-turn-enclosure-invariant.md)的直接简化。它还移除了持久化步骤边界事件的大部分动机,使[移除持久化步骤边界事件](2026-06-20-drop-durable-step-boundaries.md)的改动更小。 + +<!-- agent-note-format: alternatives-not-recorded (pre-format Agent Note) --> diff --git a/.agents/notes/rejected/simplification/2026-07-04-prune-unimplemented-subagent-vocabulary.i18n.yaml b/.agents/notes/rejected/simplification/2026-07-04-prune-unimplemented-subagent-vocabulary.i18n.yaml new file mode 100644 index 0000000000..9720d3c114 --- /dev/null +++ b/.agents/notes/rejected/simplification/2026-07-04-prune-unimplemented-subagent-vocabulary.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-04-prune-unimplemented-subagent-vocabulary.md: 890aca31f09f97ab6d9bf7c00f738d894695d9ad +2026-07-04-prune-unimplemented-subagent-vocabulary.zh.md: 7837759604a30ee8f58d922bb5f55f6730d1ddcb diff --git a/.agents/notes/rejected/simplification/2026-07-04-prune-unimplemented-subagent-vocabulary.md b/.agents/notes/rejected/simplification/2026-07-04-prune-unimplemented-subagent-vocabulary.md index 1f07492c9c..890aca31f0 100644 --- a/.agents/notes/rejected/simplification/2026-07-04-prune-unimplemented-subagent-vocabulary.md +++ b/.agents/notes/rejected/simplification/2026-07-04-prune-unimplemented-subagent-vocabulary.md @@ -2,6 +2,8 @@ Status: rejected — the deferred capability vocabulary (`outputSchema`/`structured`, `toolFilter`, `sendMessage`/`resume`) is intentionally reserved surface: the seam advertises the full intended contract ahead of its implementations by design, so providers and consumers grow into a stable shape rather than re-negotiating it per capability. The consumer-evidence analysis below records the decision-time state. +English | [中文](2026-07-04-prune-unimplemented-subagent-vocabulary.zh.md) + ## Problem The [subagent seam](../../implemented/feature/2026-06-21-subagent-capability-seam.md) shipped a two-tier capability design: start-time capability flags checked by the service, and optional runtime methods on `SubagentRun`. Three start-time features and both optional runtime methods have zero implementations and zero callers: diff --git a/.agents/notes/rejected/simplification/2026-07-04-prune-unimplemented-subagent-vocabulary.zh.md b/.agents/notes/rejected/simplification/2026-07-04-prune-unimplemented-subagent-vocabulary.zh.md new file mode 100644 index 0000000000..7837759604 --- /dev/null +++ b/.agents/notes/rejected/simplification/2026-07-04-prune-unimplemented-subagent-vocabulary.zh.md @@ -0,0 +1,39 @@ +# Agent Note: 裁剪未实现的 subagent seam 词汇 + +Status: rejected — 延后的能力词汇(`outputSchema`/`structured`、`toolFilter`、`sendMessage`/`resume`)是有意保留的接口面:该 seam 按设计先于实现声明完整的预期契约,使提供方与消费方沿稳定形状演进,而非针对每项能力重新协商。下方的消费方证据分析记录了决策时的状态。 + +[English](2026-07-04-prune-unimplemented-subagent-vocabulary.md) | 中文 + +## 问题 + +[subagent seam](../../implemented/feature/2026-06-21-subagent-capability-seam.md) 交付了一套两层能力设计:启动时由服务检查的能力 flag,以及 `SubagentRun` 上的可选运行时方法。三个启动时功能和两个可选运行时方法的实现数与调用数均为零: + +- **`outputSchema`/`structured` 与 `toolFilter`**(`SubagentCapabilities`、`SubagentStartRequest`、`SubagentResult`,位于 `packages/subagent/subagent/src/types.ts`):在作出决策时,每个真实提供方都声明 `outputSchema: false, toolFilter: false`(`packages/subagent/subagent-spawn/src/index.ts`、`packages/subagent/subagent-fork/src/index.ts`、`packages/subagent/subagent-acp/src/index.ts`);唯一的生产环境 `ctx.subagents.start` 调用方(`packages/subagent/tool-subagent/src/index.ts`)构造 `{ prompt, parent, signal?, agentOptions? }`,结构上无法设置这两个字段;`structured` 仅出现在脚本化测试 fixture(测试前置数据)中。服务的能力检查包含两行 assert,其唯一执行者是拒绝测试。 +- **`SubagentRun.sendMessage` / `SubagentRun.resume`**(同一文件):没有任何提供方实现——包括 mock 也没有;spawn spec 断言的正是它们的*缺失*。 + +在作出决策时,`dsh-subagent` 依赖 `dsh-tools` 的唯一原因是 `outputSchema` 的 schema 类型(现为 `ObjectJsonSchema`)。三个后续 subagent 工作流(按会话快照回放、fork seed 边界、ACP(Agent Client Protocol)后端)都围绕这块接口面落地,却没有增长出哪怕一个消费方。 + +## 提案 + +从 seam 中移除 `outputSchema`/`structured`、`toolFilter`、`sendMessage` 与 `resume`;将 `SubagentCapabilities` 缩减为 `{ depthLimit }`;删除两行能力 assert、三个提供方上的 all-false flag、脚本化 fixture 的 structured 分支和能力旋钮,以及为固定被移除接口面而存在的测试。`dsh-tools` 的 peer/dev 依赖应从 `packages/subagent/subagent/package.json` 中删除。更新 [subagent.md](../../../../docs/core-data-structures/subagent.md) 中的粘贴内容与 type-equiv manifest(元数据清单),以及受影响的提供方 README。实现 PR(Pull Request)按照 [implemented/AGENTS.md](../../implemented/AGENTS.md) 修订 seam Agent Note(agent 决策记录)的能力目录。 + +**保留** `depthLimit`/`maxDepth` 与能力检查。进程内后端已强制执行该限制,尽管当前发布的工具尚未设置它。递归是已知的 seam 风险,因此恰当的后续工作是提供一个工具默认值,而非删除正在工作的强制逻辑。 + +审视过但有意不动的相邻接口面:`SubagentService.getProvider()`/`list()` 仅有测试 harness 消费方,但 [prune-dead-seam-methods 实现说明](../../implemented/simplification/2026-06-20-prune-dead-seam-methods.md)恰好记录了这种形态从 bash 执行器中被移除后又被回退的经过——对于一个基于已跟踪 map 的单行访问器而言,测试 harness 就是消费方。`SubagentRunEndInfo.lastAssistantMessage` 是一个已记录的保留项([subagent 观测/丰富化 Agent Note](../../implemented/feature/2026-06-30-subagent-observe-enrich.md)的评审删除了 `agentType` 但有意保留了它,因为它是进程外子 agent(智能体)唯一的最终消息通道);它当前未接通的桥接转发是一个待补的缺口或待记录的消费方,不是本 Agent Note 要裁剪的接口面。 + +这是[从持久化 seam 裁剪死方法](../../implemented/simplification/2026-06-20-prune-dead-seam-methods.md)在 seam 词汇层面的回响:每个实现都必须为无人声明的成员,甚至更弱,因为这里连一个实现都没有。 + +## 曾考虑的替代方案 + +### 为什么不保留? + +两类能力的设计是 seam Agent Note 的核心亮点,日后重新添加 `outputSchema` 会涉及多个文件。但该设计以 `depthLimit` 作为活跃示例、以 Agent Note 作为记录仍然成立;而且 seam Agent Note 本身承认已交付的 `toolFilter` 形态是错误的(真正的强制需要在子 agent 上下文中实施 `tools/pre-execute` deny,而非 schema 过滤)——该 deny 原语已存在于拦截 seam 上,因此基于真实实现提供方重新添加时,将固定出一份比当前推测性契约更好的契约。 + +## 验收标准 + +- 被移除的拼写仅出现在本 Agent Note 和修订后的 seam Agent Note 中;`SubagentCapabilities` 为 `{ depthLimit: boolean }`;`dsh-tools` 依赖边已消除(`hygiene` 绿色)。 +- 深度强制测试不变且绿色。 + +## 风险 + +subagent 生命周期事件在结束载荷上携带 `lastAssistantMessage`——该增强位于服务模块中,不在本 Agent Note 缩减的 seam 词汇范围内;observe-enrich Agent Note 记录了因缺少消费方而删除 `agentType` 兄弟字段的判断,本 Agent Note 延续了这一判断。CC 钩子桥接是这些生命周期事件的第一个外部消费方,它只读取事件载荷,不涉及本文移除的任何接口面;observe-enrich Agent Note 推迟的控制流重设计将实现 `resume` 列为自身的未来工作——恰好是本 Agent Note 模式所预期的重新添加触发点。 diff --git a/.agents/notes/rejected/simplification/2026-07-12-collapse-workflow-to-foreground-core.i18n.yaml b/.agents/notes/rejected/simplification/2026-07-12-collapse-workflow-to-foreground-core.i18n.yaml new file mode 100644 index 0000000000..1b4e9c4b54 --- /dev/null +++ b/.agents/notes/rejected/simplification/2026-07-12-collapse-workflow-to-foreground-core.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-12-collapse-workflow-to-foreground-core.md: 629e2140523c3ae7caf533de99821206d05f1b8e +2026-07-12-collapse-workflow-to-foreground-core.zh.md: 3ae5e026a0b123a6b695b339010bf14a99515912 diff --git a/.agents/notes/rejected/simplification/2026-07-12-collapse-workflow-to-foreground-core.md b/.agents/notes/rejected/simplification/2026-07-12-collapse-workflow-to-foreground-core.md index dcfdfa13e6..629e214052 100644 --- a/.agents/notes/rejected/simplification/2026-07-12-collapse-workflow-to-foreground-core.md +++ b/.agents/notes/rejected/simplification/2026-07-12-collapse-workflow-to-foreground-core.md @@ -2,6 +2,8 @@ Status: rejected — Workflow progress is an intentional observation surface; make it useful through a consumer instead of deleting it. +English | [中文](2026-07-12-collapse-workflow-to-foreground-core.zh.md) + ## Problem The workflow capability executes foreground JavaScript that composes subagents, but it also carries an unconsumed progress-observation system. No production listener subscribes to any of the six `workflow/*` events; listeners exist only in workflow tests. Nevertheless the seam defines run/phase/agent outcome payloads, the worker sends phase/log/agent lifecycle protocol messages, the host forwards them through a `liveAgents` pairing ledger, and the engine maintains run ids solely to correlate those notifications. diff --git a/.agents/notes/rejected/simplification/2026-07-12-collapse-workflow-to-foreground-core.zh.md b/.agents/notes/rejected/simplification/2026-07-12-collapse-workflow-to-foreground-core.zh.md new file mode 100644 index 0000000000..3ae5e026a0 --- /dev/null +++ b/.agents/notes/rejected/simplification/2026-07-12-collapse-workflow-to-foreground-core.zh.md @@ -0,0 +1,39 @@ +# Agent Note: 将工作流收缩至已使用的前台核心 + +Status: rejected — 工作流进度是有意设计的观测接口面;应通过消费方使其发挥作用,而非删除它。 + +[English](2026-07-12-collapse-workflow-to-foreground-core.md) | 中文 + +## 问题 + +工作流能力执行前台 JavaScript 来编排 subagent,但它同时携带了一套无人消费的进度观测系统。没有任何生产环境的监听器订阅六个 `workflow/*` 事件中的任何一个;监听器仅存在于工作流测试中。尽管如此,seam 定义了 run/phase/agent(智能体) outcome 载荷,worker 发送 phase/log/agent 生命周期协议消息,host 通过一个 `liveAgents` 配对账本转发它们,引擎维护 run id 仅仅是为了关联这些通知。 + +这套进度词汇不仅仅是未被使用;它在不经重新设计的情况下也无法服务于其唯一已命名的未来消费方。`WorkflowRunInfo` 包含 `{id, meta}` 但没有父 agent、会话或工具调用标识,而面向模型的工具也从不暴露 run id。一个全局 ACP(Agent Client Protocol)监听器无法将事件路由到正确的客户端会话。`meta.phases` 从未被查询,`phase(title)` 不对其做校验,phase 的 `detail`/`model` 和 agent 的 `label`/`phase` 仅供事件消费,`whenToUse` 被校验和复制但从未被渲染或用于选择。`phase()` 和 `log()` 仍然跨越 worker 边界,尽管没有接收方。 + +live handle 在观测者消失后仍重复事件时代的数据。`WorkflowRun.id` 没有非事件消费方,而工具读取 `run.meta.name` 只是为了渲染一个它已经以 `args.meta.name` 形式持有的值;两者都不属于执行/取消 handle。 + +取消机制也为一个同步启动提供了两条公开通道。`WorkflowStartRequest.signal` 被传递给 worker host,而唯一的生产调用方另外将同一个 signal 桥接到 `WorkflowRun.cancel()`。因为 `start()` 在控制权让出之前就返回了 run,不存在需要请求时取消的就绪窗口;重复的 signal 增加了 host 的 listener/disarm 状态却没有封堵任何竞态。 + +`WorkflowError.fatal` 是同一种推测性分支的微缩版:所有生产环境的构造都是 fatal 的,`fatal: false` 仅存在于测试中,组合子已经通过 `instanceof` 区分工作流失败。 + +## 提案 + +保留已使用的核心:`agent(prompt, { schema, model })`、`parallel`、`pipeline`、`args`、并发/agent 上限、取消、有界 dispose(资源释放)、结构化结果、worker 隔离与前台工具收集。移除所有 `workflow/*` 事件及其仅供事件使用的 info/outcome 类型;移除 `phase()`、`log()`、agent 的 `label`/`phase`、phase 声明、`whenToUse` 及其 worker 消息/host 观测者;将工作流元数据收缩为工具实际使用的 name;移除仅供事件使用的 run id/meta 快照与合成的 agent-end 账本。将 `WorkflowRun` 收缩为 `result`、`cancel()` 和 `dispose()`;工具渲染请求方持有的 name。移除 `WorkflowStartRequest.signal` 及 worker host 的 input-signal listener/disarm 状态,保留调用方从其 abort signal 到 `run.cancel()` 的桥接。将 `WorkflowError` 变为单一的 fatal 错误类,不再有布尔模式或 `isFatalWorkflowError()` 辅助函数。 + +修订已实施的动态工作流 Agent Note(agent 决策记录),并更新 seam/工具/worker README、工具 schema、生成的 catalog 与包(package)依赖图、worker type-equiv 记录、单元测试以及工作流快照/header fixture(测试前置数据)。如果进度 UI 工作被立项,应从一份命名了父 agent/会话/工具调用的关联契约出发,而非原样复活这套协议。 + +## 曾考虑的替代方案 + +**为未来 UI 保留预建的观测词汇。** 当前形态类似 Claude Code 的动态工作流元数据,host 有意地将每个转发的 agent start 与 worker 的 end 或一个合成的终止 end 配对。移除它意味着放弃形态兼容性,使进度 UI 成为一项全新的设计任务;但现有载荷仍缺少可路由的归属信息,因此仅靠平衡的生命周期也无法在不重新设计的情况下让已命名的 ACP 消费方可行。 + +## 验收标准 + +- 工作流公开 seam 仅包含有生产消费方的执行、取消、结果与 dispose 契约。 +- 不再保留任何工作流事件、phase/log 协议消息、run-id 生成器、仅供进度使用的元数据、host 配对账本或 fatal 模式分支。 +- run handle 不再有 id/meta 回显,取消在同步 `start()` 返回后只有一条持有者拥有的通道。 +- parallel/pipeline 行为、上限、取消后的完全停稳、worker 隔离、结构化输出与面向模型的工作流场景保持测试覆盖。 +- 类型检查、覆盖率、快照、doc-sync(文档同步门禁)、module-graph 校验、构建与 hygiene 全部通过。 + +## 风险 + +这是对工作流 DSL、事件分类体系、handle 与 start request 的编译可见收缩。现有提供描述性元数据的工作流调用,以及使用 `phase`、`log` 或 label 的脚本,都必须相应精简;程序化调用方需自行将 abort source 桥接到返回的 handle;未来的观测者必须添加一个关联性更好的 seam。使工作流有用的执行语义不变。 diff --git a/.agents/notes/rejected/simplification/2026-07-12-prune-unused-skill-registry-surface.i18n.yaml b/.agents/notes/rejected/simplification/2026-07-12-prune-unused-skill-registry-surface.i18n.yaml new file mode 100644 index 0000000000..3b97a7fb1e --- /dev/null +++ b/.agents/notes/rejected/simplification/2026-07-12-prune-unused-skill-registry-surface.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-12-prune-unused-skill-registry-surface.md: 5a13effa04a6cd9954741a0a33ebc6fc3512fab8 +2026-07-12-prune-unused-skill-registry-surface.zh.md: 46d49a02c294c492abdd6e7e611a5c92eb317c12 diff --git a/.agents/notes/rejected/simplification/2026-07-12-prune-unused-skill-registry-surface.md b/.agents/notes/rejected/simplification/2026-07-12-prune-unused-skill-registry-surface.md index e96215a651..5a13effa04 100644 --- a/.agents/notes/rejected/simplification/2026-07-12-prune-unused-skill-registry-surface.md +++ b/.agents/notes/rejected/simplification/2026-07-12-prune-unused-skill-registry-surface.md @@ -2,6 +2,8 @@ Status: rejected — Direct runtime skill registration is an intentional extension path for third-party plugins. +English | [中文](2026-07-12-prune-unused-skill-registry-surface.zh.md) + ## Problem The skill service's embedded-runtime subsystem has zero production caller of `ctx.skills.register()`. It adds a reserved `runtime` provider name, a runtime map/rank/source, duplicate policy, a second revision in cache keys, normalization, disposers, and tests alongside the provider seam every shipped skill already uses. `SkillSummary.whenToUse` and candidate/definition `path` are parsed and copied but never read by a production consumer: the model catalog renders name/description, resource loading uses `resourceBase`, and providers own their locator. The deliberately open `metadata` extension point stays. diff --git a/.agents/notes/rejected/simplification/2026-07-12-prune-unused-skill-registry-surface.zh.md b/.agents/notes/rejected/simplification/2026-07-12-prune-unused-skill-registry-surface.zh.md new file mode 100644 index 0000000000..46d49a02c2 --- /dev/null +++ b/.agents/notes/rejected/simplification/2026-07-12-prune-unused-skill-registry-surface.zh.md @@ -0,0 +1,29 @@ +# Agent Note: 裁剪 skill(技能)注册表中未使用的接口 + +Status: rejected — 直接在运行时注册 skill 是为第三方插件保留的有意扩展路径。 + +[English](2026-07-12-prune-unused-skill-registry-surface.md) | 中文 + +## 问题 + +skill 服务的嵌入式运行时子系统中,`ctx.skills.register()` 没有任何生产调用方。它引入了一个保留的 `runtime` 提供方名称、一套运行时 map/rank/source、重复策略、缓存键中的第二个 revision、规范化逻辑、dispose(资源释放)器以及相应测试——而所有已交付的 skill 都只使用提供方 seam。`SkillSummary.whenToUse` 和 candidate/definition 的 `path` 被解析和复制,但没有任何生产消费方读取它们:模型目录只渲染 name/description,资源加载使用 `resourceBase`,提供方自行管理其定位器。有意开放的 `metadata` 扩展点保留不动。 + +## 提案 + +移除 `SkillService.register()`、`SkillRegistration`、运行时伪提供方及保留名称规则、运行时 revision/缓存分支,以及仅用于运行时的 source/rank 规范化逻辑。需要嵌入式 skill 的测试改为注册一个小型真实提供方。保留 `providerRevision` 作为进行中的发现 epoch,但已完成的目录缓存仅以 cwd 为键:每次提供方变更同步清除缓存,await 之后的 revision 比较已能阻止插入陈旧结果。从 skill 契约和本地提供方副本中移除 `whenToUse`、`SkillCandidate.path` 与 `SkillDefinition.path`,同时保留提供方的 locator/root 路径;保留 `metadata`、`disableModelInvocation`、`source`、`provider`、`locator` 和 `resourceBase`,因为它们要么是有意开放的扩展词汇,要么是生产消费的字段。 + +同步修订 skill 系统 Agent Note(agent 决策记录)、README、JSDoc、目录文件与测试。agent(智能体)作用域的系统提示词段、工具提供方和变量明确不在本提案范围内:[agent 作用域贡献者契约](../../implemented/architecture/2026-07-08-agent-scope-contexts.md)有意允许在 `setup(agentCtx)` 期间通过 agent 拥有的上下文注册这三者,因此仓库内没有固定的作用域注册并不能证明它们未被使用。 + +## 曾考虑的替代方案 + +**保留面向嵌入方的运行时 skill 注册。** 这是已实现的 skill Agent Note 中有意提供的同步直接定义便利接口。一个小型提供方包装层可以在 effect 拥有的生命周期下暴露相同的嵌入数据,但它必须实现异步 `list()`/`get()`、携带提供方身份,并接受提供方的重复语义。本提案选择只保留一条统一的提供方路径,而非维护第二套排序、校验、缓存失效与查找路径。 + +## 验收标准 + +- skill 收集只有一条提供方驱动的路径,已完成缓存仅以 cwd 为键,revision epoch 仅用于进行中的失效检测;保留的 skill 字段要么有生产读取方,要么有记录在案的有意扩展契约。 +- agent 作用域的提示词段、变量、工具提供方、工具守卫,以及原生模式和 Code Mode 下的 structured-output 提交行为保持不变。 +- 类型检查、覆盖率、快照、doc-sync(文档同步门禁)、module-graph 校验、构建与 hygiene 全部通过。 + +## 风险 + +这是对预发布 skill 注册表的编译可见收缩。外部编程式 `list()`/`get()` 消费方将失去 `whenToUse` 路由提示和 candidate/definition 的 `path`;已交付的模型目录从未渲染它们,资源解析保留了显式的 `resourceBase` 加上提供方自有的不透明 locator,但这些字段并非观测等价。skill 本地 frontmatter 解析必须继续保留并校验所支持的 metadata schema,外部提供方仍可提供嵌入式、文件系统、远程或其他 skill 来源。 diff --git a/docs/agent-lifecycle.md b/docs/agent-lifecycle.md index b732708e1f..5f1e43eb17 100644 --- a/docs/agent-lifecycle.md +++ b/docs/agent-lifecycle.md @@ -17,8 +17,8 @@ sequenceDiagram participant Session participant Persistence participant SDK as UI or SDK listener - User->>Agent: send(content) - Agent-->>SDK: <code>agent/queued</code> + User->>Agent: followup(content) + Agent-->>SDK: <code>agent/inbox/enqueue</code> Agent->>Driver: queued work wakes driver Driver-->>SDK: <code>agent/status</code> running Driver->>Session: <code>turn/start</code> diff --git a/docs/architecture.i18n.yaml b/docs/architecture.i18n.yaml index 466a96dd30..214e2c9fba 100644 --- a/docs/architecture.i18n.yaml +++ b/docs/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 -architecture.md: 5a0ff63413a0c2a59d042f935d341dd39234f669 -architecture.zh.md: e1fb143982ad968fe6be2a5f6154722a602a297b +architecture.md: 76c58e03282ef6d736da7d65b05c534c05c4c318 +architecture.zh.md: dddccf1e9238e617a453395731ee3f620ba5749d diff --git a/docs/architecture.md b/docs/architecture.md index 5a0ff63413..76c58e0328 100644 --- a/docs/architecture.md +++ b/docs/architecture.md @@ -6,7 +6,7 @@ English | [中文](architecture.zh.md) ## Overview -Harnesses are [Cordis](cordis-primer.md) contexts whose packages contribute services, typed events, and disposable registrations. +Harnesses are [Cordis](cordis-primer.md) contexts with package-contributed services, typed events, and disposable registrations. `packages/core/` groups the default agent flow; capabilities remain plugins. @@ -49,7 +49,7 @@ Harnesses are [Cordis](cordis-primer.md) contexts whose packages contribute serv ## Event -Events form the service extension API; see the exhaustive [events catalog](cordis-catalog/events.md) and [producer/consumer map](event-producer-consumer.md). +Events form the service extension API; see the [catalog](cordis-catalog/events.md) and [producer/consumer map](event-producer-consumer.md). ### Event Domains @@ -63,11 +63,11 @@ Waterfall events behave like around-middleware: a listener delegates by calling ## Default Loop Lifecycle -The shipped loop runs prompt-to-checkpoint work through plugin services and events. +The loop runs through plugin services and events. -A **session** is append-only. Each ordinary **turn** claims one queued `send()` item; injection claims none. A successor awaits the preceding claimed turn's checkpoint but may share its `running` interval ([decision](../.agents/notes/implemented/simplification/2026-07-17-one-send-one-turn.md)). A turn ends when model and plugins stop it; a **step** is one model request plus tools. In the [sequence below](agent-lifecycle.md), quotes mark durable events. +A **session** is append-only. Each ordinary **turn** claims one queued message; injection claims none. Successors await the preceding checkpoint but may share its `running` interval ([decision](../.agents/notes/implemented/simplification/2026-07-17-one-send-one-turn.md)). A **step** is one model request plus tools; quotes in the [sequence below](agent-lifecycle.md) mark durable events. -Creation without an id mints `<config-id>-session-<uuid>`; `sessionId` restores-or-creates, while `resumeSessionId` requires history. Resume restores lineage and delegation depth before publication. Startup failures emit `agent-loop/config-start-failed`; teardown is otherwise silent. +Creation without an id mints `<config-id>-session-<uuid>`; `sessionId` resumes or creates, while `resumeSessionId` requires history. Resume restores lineage and delegation depth before publication. Setup failures emit `agent-loop/config-start-failed`; teardown is silent. ### Turn Flow @@ -115,39 +115,39 @@ forever: checkpoint persistence and notify idle/running status ``` -Each step assembles ordered prompt sections, tool schemas, and variables; unknown references fail the turn. `dsh-system-prompt` owns identity and persona, while the loop supplies `model` and `cwd` ([prompt ownership](../.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md)). +Steps assemble ordered prompt sections, tool schemas, and variables; unknown references fail turns. `dsh-system-prompt` owns identity and persona; the loop supplies `model` and `cwd` ([ownership](../.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md)). -Tool-time context—including async `inject()` and post-tool `additionalContexts`—settles after results. Steering drains before `agent/post-step`, which sees durable output, results, context, and steering. Leftovers queue. Terminal `agent/turn-stop` remains authoritative through close/flush; later steering is discarded while queued prompts remain. +Async `inject()` and post-tool `additionalContexts` settle after results; steering drains before `agent/post-step`. Leftovers queue. Terminal `agent/turn-stop` remains authoritative through close/flush and discards later steering, not queued prompts. -Pruning precedes summaries; overflow retries require durable progress. Bounded transient retries compose on `agent/request-error`; cancellation wins ([compaction](../.agents/notes/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md), [retry](../.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.md)). +Pruning precedes summaries; overflow retries require durable progress. Bounded retries compose on `agent/request-error`; cancellation wins ([compaction](../.agents/notes/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md), [retry](../.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.md)). ### Failure Boundaries -Adapter failures close the step before `agent/request-error` with exact `Error`, `LlmFailure`, and history. Retry opens another step; success clears history; exhaustion stores failure on `turn/end`. Failed chunks commit no message/tool. +Adapter failures close the step before `agent/request-error` with exact `Error`, `LlmFailure`, and history. Retries open steps; success clears history; exhaustion stores failure on `turn/end`. Failed chunks commit nothing. -Other failures use `agent/error`. Cancellation and disposal beat recovery; undispatched tool calls get synthetic `tool/call`/`ABORTED_BEFORE_DISPATCH` pairs. The turn signal retires before `turn/end`. Effective `cancel()` emits its typed cause before clearing queues and aborting; observers cannot veto, idle calls emit nothing, and durability records `aborted`. Disposal awaits quiescence ([decision](../.agents/notes/implemented/architecture/2026-07-16-explicit-turn-cancellation.md)). +Other failures use `agent/error`. Cancellation and disposal beat recovery; undispatched tools get synthetic `tool/call`/`ABORTED_BEFORE_DISPATCH` pairs. The signal retires before `turn/end`. Effective `cancel()` emits its cause, clears queues, and aborts; observers cannot veto, idle calls emit nothing, and durability records `aborted`. Disposal awaits quiescence ([decision](../.agents/notes/implemented/architecture/2026-07-16-explicit-turn-cancellation.md)). -Session events are turn-enclosed. Reload closes an interrupted tail with a synthetic `interrupted` turn end. Post-close failures report only through `agent/error`; no safe in-turn position remains. Each turn has one `TurnEndReason`; [TurnEndReasonMap](core-data-structures/session.md#why-a-turn-ended-turnendreasonmap) owns the variants. +Session events are turn-enclosed; reload closes an interrupted tail with a synthetic `interrupted` turn end. Post-close failures use `agent/error`. Each turn has one [TurnEndReason](core-data-structures/session.md#why-a-turn-ended-turnendreasonmap). ### Agent Handles -`ctx.agents` owns live agents and returns `AgentHandle { agent, dispose() }`. Plugins use `send()`, `steer()`, `inject()`, `cancel()`, and `whenIdle()`. The caller fiber, factory provider, and consumer handle co-own teardown through one awaited disposer. +`ctx.agents` returns `AgentHandle { agent, dispose() }`. Plugins use intent helpers `followup()`, `queue()`, `steer()`, and `inject()`; callers with exact routing facts use mandatory-field `send()` ([decision](../.agents/notes/implemented/architecture/2026-07-24-intent-named-agent-delivery.md)). `cancel()` and `whenIdle()` control lifecycle. Caller, provider, and handle co-own teardown. ### Agent Scope -Each agent owns a scoped `agent.ctx`; shared storage overlays global tool, prompt, and command entries while preserving domain views ([decision](../.agents/notes/implemented/architecture/2026-07-12-scoped-layers-store.md)). Scoped listeners filter dispatch, and every scoped contribution unwinds with awaited cleanup. `CreateAgentOptions.setup(agentCtx)` composes before publication. Typed resolvers derive carrier checks from merged `Events` and `scopeTarget` ([semantic gates](../.agents/notes/implemented/process/2026-07-14-typescript-program-backed-semantic-gates.md)). See [agent scope](../.agents/notes/implemented/architecture/2026-07-08-agent-scope-contexts.md) and [subagent composition](../.agents/notes/implemented/feature/2026-07-12-subagent-persona-tool-filter-and-depth.md). `AgentLoop` runs inside `ctx.agents.withInitiator()`; private orchestration derives `agent.session`, while turn, step, signal, cwd, and authority remain explicit ([decision](../.agents/notes/implemented/architecture/2026-07-15-agent-initiator-scope.md)). +Each agent owns a scoped `agent.ctx` over global tool, prompt, and command storage ([decision](../.agents/notes/implemented/architecture/2026-07-12-scoped-layers-store.md)); scoped listeners filter and contributions unwind with awaited cleanup. `CreateAgentOptions.setup(agentCtx)` composes before publication; typed resolvers derive carrier checks from `Events` and `scopeTarget` ([gates](../.agents/notes/implemented/process/2026-07-14-typescript-program-backed-semantic-gates.md)). `AgentLoop` runs inside `ctx.agents.withInitiator()`; private orchestration derives `agent.session`, while turn, step, signal, cwd, and authority stay explicit ([decision](../.agents/notes/implemented/architecture/2026-07-15-agent-initiator-scope.md)). See [agent scope](../.agents/notes/implemented/architecture/2026-07-08-agent-scope-contexts.md) and [subagent composition](../.agents/notes/implemented/feature/2026-07-12-subagent-persona-tool-filter-and-depth.md). ## State ### Session Log -The session log is authoritative. `deriveMessages()` projects model history; raw `assistant/chunk` events remain for replay and UI fidelity. Fork, resume, transcript rendering, telemetry, and persistence derive from the same stream. +The session log is authoritative. `deriveMessages()` projects model history; raw `assistant/chunk` events preserve replay and UI fidelity. Fork, resume, transcripts, telemetry, and persistence share that stream. -**Model-visible ⟺ logged**: the log reconstructs every request — messages at `step/start` fronted by the header's session prefix, and headers by folding `request/header` — and the package-owned `dsh-agent-loop/invariant` can assert it through `ctx.invariants` ([reconstructability](../.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.md)). +**Model-visible ⟺ logged**: `step/start` messages plus the header's session prefix and folded `request/header` reconstruct every request; `dsh-agent-loop/invariant` asserts this through `ctx.invariants` ([decision](../.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.md)). -Durability is a plugin concern. Backends buffer synchronous `session/event` notifications. The semantic checkpoint policy drains requests before adapter dispatch, recorded top-level calls before tool dispatch, and complete response/result batches at `agent/post-step`; the loop retains the final turn-end checkpoint. `SessionPersistence` stores `SessionEvent` directly and metadata in `SessionHeader`; JSONL defaults to checksummed Zstandard, with SQLite under one contract ([decision](../.agents/notes/implemented/bug-fix/2026-07-21-semantic-session-checkpoints.md)). +Durability is a plugin concern; backends buffer synchronous `session/event` notifications. Checkpoints drain before adapter dispatch, recorded top-level tool calls before tool dispatch, complete response/result batches at `agent/post-step`, and final turn ends. `SessionPersistence` stores `SessionEvent` plus `SessionHeader` metadata; JSONL defaults to checksummed Zstandard, with SQLite under one contract ([decision](../.agents/notes/implemented/bug-fix/2026-07-21-semantic-session-checkpoints.md)). -`ctx.sessions.appendOutOfBand()` joins log-only events to an open turn or creates a flushed zero-step turn. `session/title` folds latest-wins with source seqs/provenance; fallback and its optional provider never delay responses. Forks inherit titles ([decision](../.agents/notes/implemented/feature/2026-07-21-log-backed-session-titles.md)). +`ctx.sessions.appendOutOfBand()` joins plugin-owned log-only events to an open turn or creates a balanced, flushed zero-step turn. `session/title` folds latest-wins with source seqs and provenance; its immediate fallback and sole optional async provider never delay the agent response. Forks inherit titles ([decision](../.agents/notes/implemented/feature/2026-07-21-log-backed-session-titles.md)). ### Model Content diff --git a/docs/architecture.zh.md b/docs/architecture.zh.md index e1fb143982..dddccf1e92 100644 --- a/docs/architecture.zh.md +++ b/docs/architecture.zh.md @@ -49,7 +49,7 @@ ## 事件 -事件构成服务的扩展 API;完整清单见[事件目录](cordis-catalog/events.md)和[生产方与消费方映射](event-producer-consumer.md)。 +事件构成服务的扩展 API;参见[事件目录](cordis-catalog/events.md)和[生产方与消费方映射](event-producer-consumer.md)。 ### 事件域 @@ -63,11 +63,11 @@ waterfall(瀑布式事件)的行为类似环绕中间件:监听器调用 ` ## 默认循环生命周期 -已交付的循环通过插件服务和事件,处理从提示词到检查点的工作。 +循环通过插件服务和事件运行。 -**会话**采用仅追加方式。每个普通**轮次**领取一项已排队的 `send()` 输入;注入不领取输入。后续轮次会等待前一个已领取轮次的检查点,但可以与其共用同一个 `running` 区间([决策](../.agents/notes/implemented/simplification/2026-07-17-one-send-one-turn.md))。模型和插件停止轮次时,该轮次结束;一个**步骤**包含一次模型请求及其工具。在[下文时序](agent-lifecycle.md)中,引号标记持久事件。 +**会话**采用仅追加方式。每个普通**轮次**领取一条已排队的消息;注入不领取消息。后续轮次会等待前一个检查点,但可以与前一轮次共用同一个 `running` 区间([决策](../.agents/notes/implemented/simplification/2026-07-17-one-send-one-turn.md))。一个**步骤**包含一次模型请求及其工具;在[下文时序](agent-lifecycle.md)中,引号标记持久事件。 -未提供 id 时会生成 `<config-id>-session-<uuid>`;`sessionId` 用于恢复或创建,而 `resumeSessionId` 要求已有历史。恢复流程会在发布前还原沿袭关系和委托深度。初始化失败会发出 `agent-loop/config-start-failed`;其余拆卸过程保持静默。 +未提供 id 时,创建流程会生成 `<config-id>-session-<uuid>`;`sessionId` 用于恢复或创建会话,而 `resumeSessionId` 要求已有历史。恢复流程在发布前还原沿袭关系和委托深度。初始化失败会发出 `agent-loop/config-start-failed`;拆卸过程保持静默。 ### 轮次流程 @@ -115,39 +115,39 @@ forever: checkpoint persistence and notify idle/running status ``` -每个步骤都会组装有序提示词片段、工具 schema 和变量;未知引用会使该轮次失败。`dsh-system-prompt` 负责身份和角色设定,循环则提供 `model` 和 `cwd`([提示词归属](../.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md))。 +各步骤会组装有序提示词片段、工具 schema 和变量;未知引用会使轮次失败。`dsh-system-prompt` 负责身份和角色设定;循环提供 `model` 和 `cwd`([归属](../.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md))。 -工具执行阶段的上下文,包括异步 `inject()` 和工具执行后的 `additionalContexts`,会在结果产生后稳定。steering(中途引导)会在 `agent/post-step` 前排空;该事件会观察持久输出、结果、上下文和 steering。余留内容进入队列。终止型 `agent/turn-stop` 在关闭和刷写期间始终具有最终决定权;后续 steering 会被丢弃,排队提示词仍予保留。 +异步 `inject()` 和工具执行后的 `additionalContexts` 会在结果产生后稳定;steering(中途引导)会在 `agent/post-step` 前排空。余留内容进入队列。终止型 `agent/turn-stop` 在关闭和刷写期间始终具有最终决定权,会丢弃后续 steering,而不丢弃排队提示词。 -裁剪先于摘要;溢出重试必须取得持久进展。有界的瞬态重试在 `agent/request-error` 上组合;取消优先([压缩](../.agents/notes/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md)、[重试](../.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.md))。 +裁剪先于摘要;溢出重试必须取得持久进展。有界重试在 `agent/request-error` 上组合;取消优先([压缩](../.agents/notes/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md)、[重试](../.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.md))。 ### 失败边界 -适配器故障会先关闭步骤,再进入 `agent/request-error`;该事件会收到准确的 `Error`、`LlmFailure` 和历史记录。重试会开启另一个步骤;成功会清除历史记录;重试耗尽后,故障存入 `turn/end`。失败分片不会提交消息或工具。 +适配器故障会先关闭步骤,再进入 `agent/request-error`;该事件会收到准确的 `Error`、`LlmFailure` 和历史记录。重试会开启步骤;成功会清除历史记录;重试耗尽后,故障存入 `turn/end`。失败分片不会提交任何内容。 -其他故障使用 `agent/error`。取消和资源释放均优先于恢复;尚未分派的工具调用会得到合成的 `tool/call`/`ABORTED_BEFORE_DISPATCH` 对。轮次信号会在 `turn/end` 前失效。实际生效的 `cancel()` 会在清空队列和中止前发出类型化原因;观察方不能否决该操作,空闲状态下的调用不发出任何事件,持久化会记录 `aborted`。dispose(资源释放)会等待系统停稳([决策](../.agents/notes/implemented/architecture/2026-07-16-explicit-turn-cancellation.md))。 +其他故障使用 `agent/error`。取消和资源释放均优先于恢复;尚未分派的工具会得到合成的 `tool/call`/`ABORTED_BEFORE_DISPATCH` 对。信号会在 `turn/end` 前失效。实际生效的 `cancel()` 会发出原因、清空队列并中止;观察方不能否决该操作,空闲状态下的调用不发出任何事件,持久化会记录 `aborted`。dispose(资源释放)会等待系统停稳([决策](../.agents/notes/implemented/architecture/2026-07-16-explicit-turn-cancellation.md))。 -会话事件均位于轮次边界内。重新加载会用合成的 `interrupted` 轮次结束事件闭合中断的日志尾部。关闭后的故障只通过 `agent/error` 报告;此时已没有安全的轮次内位置。每个轮次有一个 `TurnEndReason`;各变体由 [TurnEndReasonMap](core-data-structures/session.md#why-a-turn-ended-turnendreasonmap) 统一定义。 +会话事件均位于轮次边界内;重新加载会用合成的 `interrupted` 轮次结束事件闭合中断的日志尾部。关闭后的故障使用 `agent/error`。每个轮次有一个 [TurnEndReason](core-data-structures/session.md#why-a-turn-ended-turnendreasonmap)。 ### Agent 句柄 -`ctx.agents` 拥有活跃 agent,并返回 `AgentHandle { agent, dispose() }`。插件使用 `send()`、`steer()`、`inject()`、`cancel()` 和 `whenIdle()`。调用方 fiber、工厂提供方和消费方句柄通过同一个需等待完成的 disposer 共同拥有拆卸过程。 +`ctx.agents` 返回 `AgentHandle { agent, dispose() }`。插件使用按意图命名的辅助方法 `followup()`、`queue()`、`steer()` 和 `inject()`;持有确切路由信息的调用方使用各字段均为必填项的 `send()`([决策](../.agents/notes/implemented/architecture/2026-07-24-intent-named-agent-delivery.md))。`cancel()` 和 `whenIdle()` 控制生命周期。调用方、提供方和句柄共同拥有拆卸过程。 ### Agent 作用域 -每个 agent 都拥有一个作用域化的 `agent.ctx`;共享存储会在全局工具、提示词和命令条目之上叠加作用域条目,同时保留各领域视图([决策](../.agents/notes/implemented/architecture/2026-07-12-scoped-layers-store.md))。作用域监听器会过滤分派,每项作用域贡献都会在撤销时等待清理完成。`CreateAgentOptions.setup(agentCtx)` 在发布前完成组合。类型化解析器从合并后的 `Events` 和 `scopeTarget` 推导载体检查([语义门禁](../.agents/notes/implemented/process/2026-07-14-typescript-program-backed-semantic-gates.md))。参见 [agent 作用域](../.agents/notes/implemented/architecture/2026-07-08-agent-scope-contexts.md)和 [subagent 组合](../.agents/notes/implemented/feature/2026-07-12-subagent-persona-tool-filter-and-depth.md)。`AgentLoop` 在 `ctx.agents.withInitiator()` 内运行;私有编排会派生 `agent.session`,而轮次、步骤、信号、cwd 和权限仍保持显式([决策](../.agents/notes/implemented/architecture/2026-07-15-agent-initiator-scope.md))。 +每个 agent 都拥有一个作用于全局工具、提示词和命令存储的作用域化 `agent.ctx`([决策](../.agents/notes/implemented/architecture/2026-07-12-scoped-layers-store.md));作用域监听器会过滤分派,各项贡献会在撤销时等待清理完成。`CreateAgentOptions.setup(agentCtx)` 在发布前完成组合;类型化解析器从 `Events` 和 `scopeTarget` 推导载体检查([门禁](../.agents/notes/implemented/process/2026-07-14-typescript-program-backed-semantic-gates.md))。`AgentLoop` 在 `ctx.agents.withInitiator()` 内运行;私有编排会派生 `agent.session`,而轮次、步骤、信号、cwd 和权限仍保持显式([决策](../.agents/notes/implemented/architecture/2026-07-15-agent-initiator-scope.md))。参见 [agent 作用域](../.agents/notes/implemented/architecture/2026-07-08-agent-scope-contexts.md)和 [subagent 组合](../.agents/notes/implemented/feature/2026-07-12-subagent-persona-tool-filter-and-depth.md)。 ## 状态 ### 会话日志 -会话日志是权威依据。`deriveMessages()` 投影出模型历史;原始 `assistant/chunk` 事件留在日志中,以保证回放和 UI 保真。fork、恢复、transcript(文本记录)渲染、遥测和持久化均派生自同一个事件流。 +会话日志是权威依据。`deriveMessages()` 投影出模型历史;原始 `assistant/chunk` 事件保留回放和 UI 保真。fork、恢复、transcript(文本记录)、遥测和持久化共用该事件流。 -**模型可见 ⟺ 已记录**:日志可以重建每个请求,包括由请求头会话前缀置于开头的 `step/start` 时消息,以及通过折叠 `request/header` 得到的请求头;开发期不变量会断言这一点([可重建性](../.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.md))。 +**模型可见 ⟺ 已记录**:`step/start` 消息、请求头中的会话前缀和折叠后的 `request/header` 共同重建每个请求;`dsh-agent-loop/invariant` 通过 `ctx.invariants` 断言这一点([决策](../.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.md))。 -持久性由插件负责。后端会缓冲同步的 `session/event` 通知。语义检查点策略会在适配器分发前刷写请求,在工具分发前刷写已记录的顶层调用,并在 `agent/post-step` 刷写完整的响应与结果批次;循环仍保留最终的轮次结束检查点。`SessionPersistence` 直接存储 `SessionEvent`,并将元数据存入 `SessionHeader`;JSONL 默认采用带校验和的 Zstandard,SQLite 则遵循同一契约([决策](../.agents/notes/implemented/bug-fix/2026-07-21-semantic-session-checkpoints.md))。 +持久性由插件负责;后端会缓冲同步的 `session/event` 通知。检查点会在适配器分发前排空,在工具分发前刷写已记录的顶层工具调用,在 `agent/post-step` 刷写完整的响应与结果批次,并刷写最终的轮次结束。`SessionPersistence` 存储 `SessionEvent` 和 `SessionHeader` 元数据;JSONL 默认采用带校验和的 Zstandard,SQLite 则遵循同一契约([决策](../.agents/notes/implemented/bug-fix/2026-07-21-semantic-session-checkpoints.md))。 -`ctx.sessions.appendOutOfBand()` 会把纯日志事件加入开放轮次,或创建一个已刷写的零步骤轮次。`session/title` 按后写覆盖方式折叠,并携带源 seq/来源信息;回退标题及其可选提供方都不会延迟响应。fork 会继承标题([决策](../.agents/notes/implemented/feature/2026-07-21-log-backed-session-titles.md))。 +`ctx.sessions.appendOutOfBand()` 会把插件所属的纯日志事件加入开放轮次,或创建一个平衡且已刷写的零步骤轮次。`session/title` 按后写覆盖方式折叠,并携带源 seq 和来源信息;其即时回退标题和唯一可选异步提供方都不会延迟 agent 响应。fork 会继承标题([决策](../.agents/notes/implemented/feature/2026-07-21-log-backed-session-titles.md))。 ### 模型内容 diff --git a/docs/cookbook/extension-cookbook.i18n.yaml b/docs/cookbook/extension-cookbook.i18n.yaml index 5d5dc81f2a..a6d2ca2e38 100644 --- a/docs/cookbook/extension-cookbook.i18n.yaml +++ b/docs/cookbook/extension-cookbook.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -extension-cookbook.md: 056be4298ed2bec2b78ed777d58f1f8a60a34b78 -extension-cookbook.zh.md: 41cdd4a7d14f32494d1dd5ae4a63c098d5640bdc +extension-cookbook.md: c13b46e06a3b34512cd371e6a4868a6e932a575f +extension-cookbook.zh.md: ef099ff318488ba26a3ba4fe736c5f320bdce4f3 diff --git a/docs/cookbook/extension-cookbook.md b/docs/cookbook/extension-cookbook.md index 056be4298e..c13b46e06a 100644 --- a/docs/cookbook/extension-cookbook.md +++ b/docs/cookbook/extension-cookbook.md @@ -36,7 +36,7 @@ This waterfall is the reorderable policy layer. Use `ctx.tools.guard()` when an ## A UI plugin -A UI plugin renders from the `session/event` feed (the assistant token stream as `assistant/chunk`, plus turn/step boundaries and tool activity), and drives input back in via `agent.send()` / `agent.steer()`. +A UI plugin renders from the `session/event` feed (the assistant token stream as `assistant/chunk`, plus turn/step boundaries and tool activity), and drives input back in via `agent.followup()` / `agent.steer()`. ```ts import type { Context } from 'cordis' @@ -54,13 +54,13 @@ export function apply(ctx: Context) { render(event.data.chunk.text) } }) - onUserInput(text => ctx.agents.get(SessionId('client-session'))?.send([{ type: 'text', text }])) + onUserInput(text => ctx.agents.get(SessionId('client-session'))?.followup([{ type: 'text', text }])) } ``` ## A client-driver plugin (external protocol bridge) -A *client driver* is a UI plugin for a wire-protocol peer. It owns stdio, so stdout logging must be disabled, creates or resumes agents through the factory, maps harness events to protocol messages, and maps requests to `send()` or `cancel()`. Settle each request exactly once from durable `turn/end`, even if rendering fails, and tear agents down with `AgentHandle.dispose()` so disposal reaches quiescence. +A *client driver* is a UI plugin for a wire-protocol peer. It owns stdio, so stdout logging must be disabled, creates or resumes agents through the factory, maps harness events to protocol messages, and maps requests to `followup()` or `cancel()`. Settle each request exactly once from durable `turn/end`, even if rendering fails, and tear agents down with `AgentHandle.dispose()` so disposal reaches quiescence. `packages/ui/acp` is the worked example: it bridges the agent to the Agent Client Protocol (JSON-RPC over stdio) so Zed and other ACP editors can drive it. See its README for the full method surface and the permission-prompt answerer it registers on the approval seam. @@ -99,9 +99,9 @@ Every product feature maps to a listener on a documented extension seam — the |---|---| | Hook system (user + project level) | listeners on `agent/session-start`, `agent/prompt-submit`, `agent/request`, `agent/step-result`, `tools/pre-execute`, `tools/post-execute`, `agent/turn-continuation` — each interception waterfall returns a typed Decision; the `dsh-hooks-claude` / `dsh-hooks-codex` bridges map hook config files onto these seams | | `/goal` | `ctx.goals` owns durable state, `dsh-goal-session` schedules same-session rounds through the public `Agent`, and separate command/tool producers expose human/model control | -| `/loop` | on the `turn/end` session event, `send()` the next iteration; or force-continue | +| `/loop` | on the `turn/end` session event, `followup()` the next iteration; or force-continue | | Dynamic workflow | `ctx.workflows` + the worker-thread engine + the `workflow` tool; structured in-process children enforce output with scoped prompt/tool registrations, a monotonic tool guard, final `tools/result` commit (including enclosing `run_code`), and terminal `agent/turn-stop` | -| Queued + steering messages | core `Agent.send()` / `Agent.steer()` | +| Queued + steering messages | core `Agent.followup()` / `Agent.steer()` | | Context compaction (auto + manual) | the `ctx.compact` seam + `dsh-compact-basic`; automatic pressure runs on serial `agent/post-step`, canonical overflow recovery runs on `agent/request-error`, and manual callers use the same compact service ([compaction Agent Note](../../.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.md) — the model-facing `/compact` consumer tool is deferred) | | System prompt configurability | `ctx.systemPrompt.section()` with ordering and scope-local shadowing | | AGENTS.md (root) | a section provider reading the file | @@ -118,8 +118,8 @@ Every product feature maps to a listener on a documented extension seam — the | MCP | one plugin per server: discover tools → `ctx.tools.register()` | | Skills | section + tool registration; `inject()` skill content on invocation | | Memory | section provider + tool | -| Scheduled tasks (cron) | a plugin registers model-callable scheduling tools; timer fires → `send(…, {source: {kind: 'cron', …}})` when idle / `inject()` notification when busy | -| UI (GUI; CLI emits JSONL) | listen `session/event` (assistant chunks, boundaries, tool activity); input → `send()` | +| Scheduled tasks (cron) | a plugin registers model-callable scheduling tools; timer fires → `followup(…, {source: {kind: 'cron', …}})` when idle / `inject()` notification when busy | +| UI (GUI; CLI emits JSONL) | listen `session/event` (assistant chunks, boundaries, tool activity); input → `followup()` | | Telemetry / replayable trace | `session/event` → JSONL; replay = `sessions.create(id, { seed })` | | Model adapters | `LlmAdapter` subclass via `registerAdapter` (`dsh-llm-deepseek`, `dsh-llm-pi-ai`) | | Plugin hot-reload | every registration is a `ctx.effect` → vendored HMR just works | diff --git a/docs/cookbook/extension-cookbook.zh.md b/docs/cookbook/extension-cookbook.zh.md index 41cdd4a7d1..ef099ff318 100644 --- a/docs/cookbook/extension-cookbook.zh.md +++ b/docs/cookbook/extension-cookbook.zh.md @@ -36,7 +36,7 @@ export function apply(ctx: Context) { ## UI 插件 -UI 插件从 `session/event` 事件流渲染(助手 token 流以 `assistant/chunk` 形式到达,加上轮次/步骤边界与工具活动),并通过 `agent.send()` / `agent.steer()` 将输入驱动回去。 +UI 插件从 `session/event` 事件流渲染(助手 token 流以 `assistant/chunk` 形式到达,加上轮次/步骤边界与工具活动),并通过 `agent.followup()` / `agent.steer()` 将输入驱动回去。 ```ts import type { Context } from 'cordis' @@ -54,13 +54,13 @@ export function apply(ctx: Context) { render(event.data.chunk.text) } }) - onUserInput(text => ctx.agents.get(SessionId('client-session'))?.send([{ type: 'text', text }])) + onUserInput(text => ctx.agents.get(SessionId('client-session'))?.followup([{ type: 'text', text }])) } ``` ## 客户端驱动插件(外部协议桥接) -*客户端驱动*是面向协议格式(wire format)对端的 UI 插件。它拥有 stdio,因此必须禁用 stdout 日志;通过工厂创建或恢复 agent(智能体);将 harness 事件映射为协议消息;将请求映射为 `send()` 或 `cancel()`。每个请求从持久的 `turn/end` 恰好结算一次(即使渲染失败),并通过 `AgentHandle.dispose()` 拆除 agent 以使 dispose(资源释放)达到静止状态。 +*客户端驱动*是面向协议格式(wire format)对端的 UI 插件。它拥有 stdio,因此必须禁用 stdout 日志;通过工厂创建或恢复 agent(智能体);将 harness 事件映射为协议消息;将请求映射为 `followup()` 或 `cancel()`。每个请求从持久的 `turn/end` 恰好结算一次(即使渲染失败),并通过 `AgentHandle.dispose()` 拆除 agent,确保 dispose(资源释放)流程完全停稳。 `packages/ui/acp` 是完整的工作示例:它将 agent 桥接到 ACP(Agent Client Protocol)(基于 stdio 的 JSON-RPC),使 Zed 及其他 ACP 编辑器能够驱动它。其 README 描述了完整的方法接口以及它在审批 seam 上注册的权限提示应答器。 @@ -99,9 +99,9 @@ export function apply(ctx: Context) { |---|---| | 钩子系统(用户级 + 项目级) | `agent/session-start`、`agent/prompt-submit`、`agent/request`、`agent/step-result`、`tools/pre-execute`、`tools/post-execute`、`agent/turn-continuation` 上的监听器——每个拦截 waterfall 返回一个类型化 Decision;`dsh-hooks-claude` / `dsh-hooks-codex` 桥接器将钩子配置文件映射到这些 seam 上 | | `/goal` | `ctx.goals` 管理持久状态,`dsh-goal-session` 通过公共 `Agent` 调度同会话回合,独立的命令/工具生产方分别提供人类/模型控制 | -| `/loop` | 在 `turn/end` 会话事件上 `send()` 下一次迭代;或强制继续 | +| `/loop` | 在 `turn/end` 会话事件上 `followup()` 下一次迭代;或强制继续 | | 动态工作流 | `ctx.workflows` + worker-thread 引擎 + `workflow` 工具;结构化的进程内子任务通过作用域化的 prompt/工具注册、单调工具守卫、最终 `tools/result` 提交(包括外层 `run_code`)和终端 `agent/turn-stop` 来强制输出 | -| 排队消息 + steering(中途引导) | 核心 `Agent.send()` / `Agent.steer()` | +| 排队消息 + steering(中途引导) | 核心 `Agent.followup()` / `Agent.steer()` | | 上下文压缩(context compaction)(自动 + 手动) | `ctx.compact` seam + `dsh-compact-basic`;自动压力检查运行在串行 `agent/post-step`,规范化溢出恢复运行在 `agent/request-error`,手动调用方使用同一个压缩服务([压缩 Agent Note](../../.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.md)——面向模型的 `/compact` 消费方工具已推迟) | | 系统提示词可配置性 | `ctx.systemPrompt.section()`,支持排序与作用域局部覆盖 | | AGENTS.md(根目录) | 一个读取该文件的 section provider | @@ -118,8 +118,8 @@ export function apply(ctx: Context) { | MCP | 每个服务器一个插件:发现工具 → `ctx.tools.register()` | | Skill(技能) | section + 工具注册;调用时通过 `inject()` 注入 skill 内容 | | 记忆 | section provider + 工具 | -| 定时任务(cron) | 插件注册面向模型的调度工具;定时器触发 → 空闲时 `send(…, {source: {kind: 'cron', …}})`/忙碌时 `inject()` 通知 | -| UI(GUI;CLI 输出 JSONL) | 监听 `session/event`(助手分片、边界、工具活动);输入 → `send()` | +| 定时任务(cron) | 插件注册面向模型的调度工具;定时器触发 → 空闲时 `followup(…, {source: {kind: 'cron', …}})`/忙碌时 `inject()` 通知 | +| UI(GUI;CLI 输出 JSONL) | 监听 `session/event`(助手分片、边界、工具活动);输入 → `followup()` | | 遥测 / 可回放 trace | `session/event` → JSONL;回放 = `sessions.create(id, { seed })` | | 模型适配器 | 通过 `registerAdapter` 注册 `LlmAdapter` 子类(`dsh-llm-deepseek`、`dsh-llm-pi-ai`) | | 插件热重载 | 每个注册都是一个 `ctx.effect` → vendor 的 HMR(热模块替换)直接生效 | diff --git a/docs/cordis-catalog/events.md b/docs/cordis-catalog/events.md index 6becfd9434..ed9bebdc92 100644 --- a/docs/cordis-catalog/events.md +++ b/docs/cordis-catalog/events.md @@ -32,7 +32,7 @@ Effective broad cancellation was requested, before queued/steering work is clear Types: [Agent](../core-data-structures/core.md) · [AgentCancelCause](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) -Source: [`packages/core/agent/src/types.ts:217`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:350`](../../packages/core/agent/src/types.ts) ### `agent/created` — emit @@ -54,7 +54,7 @@ A fully configured agent and live session were published. Setup is composition-o Types: [Agent](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) -Source: [`packages/core/agent/src/types.ts:179`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:285`](../../packages/core/agent/src/types.ts) ### `agent/disposed` — emit @@ -74,7 +74,7 @@ An agent left the registry; AgentLoop emits this after driver quiescence but bef Types: [Agent](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) -Source: [`packages/core/agent/src/types.ts:188`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:294`](../../packages/core/agent/src/types.ts) ### `agent/error` — emit @@ -96,7 +96,77 @@ A step or turn errored. The loop reports a failure here (plus the logger) even w Types: [Agent](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) -Source: [`packages/core/agent/src/types.ts:365`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:498`](../../packages/core/agent/src/types.ts) + +### `agent/inbox/dequeue` — emit + +The driver claimed one item out of the inbox: a queued item at a turn boundary, or steering drained between steps. Fires after the item leaves its FIFO and before it becomes a durable message. + +```ts cordis-catalog +/** + * The driver claimed one item out of the inbox: a queued item at a turn + * boundary, or steering drained between steps. Fires after the item leaves + * its FIFO and before it becomes a durable message. + * @param agent - the agent whose inbox item was claimed. + * @param message - the claimed message (matching the `id` from its `agent/inbox/enqueue`). + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. + * @mode emit + */ +'agent/inbox/dequeue'(this: Scoped<Agent>, agent: Agent, message: AgentMessage): void +``` + +Types: [Agent](../core-data-structures/core.md) · [AgentMessage](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) + +Source: [`packages/core/agent/src/types.ts:326`](../../packages/core/agent/src/types.ts) + +### `agent/inbox/discard` — emit + +Pending inbox items were dropped without delivering them, so every enqueued id receives exactly one terminal `agent/inbox/dequeue` OR `agent/inbox/discard`. Emitters: `cancel()` without `keepInbox` (after `agent/cancel-requested`, before the abort); a terminal `agent/turn-stop` dropping pending steering (in-turn and on the post-turn late-steering drain); and disposal of any still-pending items (before `agent/status('disposed')`). Fires once per drop with every dropped item. + +```ts cordis-catalog +/** + * Pending inbox items were dropped without delivering them, so every + * enqueued id receives exactly one terminal `agent/inbox/dequeue` OR + * `agent/inbox/discard`. Emitters: `cancel()` without `keepInbox` (after + * `agent/cancel-requested`, before the abort); a terminal `agent/turn-stop` + * dropping pending steering (in-turn and on the post-turn late-steering + * drain); and disposal of any still-pending items (before + * `agent/status('disposed')`). Fires once per drop with every dropped item. + * @param agent - the agent whose inbox items were dropped. + * @param messages - the discarded messages in FIFO order (queued then steering); never empty. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. + * @mode emit + */ +'agent/inbox/discard'(this: Scoped<Agent>, agent: Agent, messages: AgentMessage[]): void +``` + +Types: [Agent](../core-data-structures/core.md) · [AgentMessage](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) + +Source: [`packages/core/agent/src/types.ts:340`](../../packages/core/agent/src/types.ts) + +### `agent/inbox/enqueue` — emit + +A detached, frozen item entered the agent's inbox (queued or steering FIFO). Source defaults are already applied, so `message` holds the exact accepted values. This is the enqueue-time live signal; the durable record is the eventual `user/message`/`steering/message`. Injection through `agent.inject()` or equivalent `send()` routing bypasses the FIFOs and does not emit this. + +```ts cordis-catalog +/** + * A detached, frozen item entered the agent's inbox (queued or steering + * FIFO). Source defaults are already applied, so `message` holds the exact + * accepted values. This is the enqueue-time live signal; the durable record + * is the eventual `user/message`/`steering/message`. Injection through + * `agent.inject()` or equivalent `send()` routing bypasses the FIFOs + * and does not emit this. + * @param agent - the agent whose inbox received the item. + * @param message - the accepted message (its returned `id`, content, source, contexts, steering, and wakeup facts). + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. + * @mode emit + */ +'agent/inbox/enqueue'(this: Scoped<Agent>, agent: Agent, message: AgentMessage): void +``` + +Types: [Agent](../core-data-structures/core.md) · [AgentMessage](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) + +Source: [`packages/core/agent/src/types.ts:316`](../../packages/core/agent/src/types.ts) ### `agent/post-step` — serial @@ -119,7 +189,7 @@ Awaited serial checkpoint after the response, real or synthetic tool results, in Types: [Agent](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) -Source: [`packages/core/agent/src/types.ts:315`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:448`](../../packages/core/agent/src/types.ts) ### `agent/pre-step` — serial @@ -142,7 +212,7 @@ Awaited serial checkpoint before `step/start`; appends land outside the pending Types: [Agent](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) -Source: [`packages/core/agent/src/types.ts:246`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:379`](../../packages/core/agent/src/types.ts) ### `agent/prompt-submit` — waterfall @@ -169,28 +239,7 @@ Allow, rewrite, or block one claimed prompt before it becomes a user message. Ca Types: [Agent](../core-data-structures/core.md) · [ContentBlock](../core-data-structures/core.md) · [MessageSource](../core-data-structures/core.md) · [PromptDecision](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) -Source: [`packages/core/agent/src/types.ts:262`](../../packages/core/agent/src/types.ts) - -### `agent/queued` — emit - -Detached, frozen content entered the agent's inbox. Source defaults have already been applied, so these are the exact values retained for the log. - -```ts cordis-catalog -/** - * Detached, frozen content entered the agent's inbox. Source defaults have - * already been applied, so these are the exact values retained for the log. - * @param agent - the agent whose inbox received the message. - * @param content - the accepted content blocks retained by the inbox. - * @param info - the accepted source, contexts, and whether it entered as steering. - * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. - * @mode emit - */ -'agent/queued'(this: Scoped<Agent>, agent: Agent, content: ContentBlock[], info: { source: MessageSource; contexts: HookContext[]; steering: boolean }): void -``` - -Types: [Agent](../core-data-structures/core.md) · [ContentBlock](../core-data-structures/core.md) · [HookContext](../core-data-structures/core.md) · [MessageSource](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) - -Source: [`packages/core/agent/src/types.ts:207`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:395`](../../packages/core/agent/src/types.ts) ### `agent/request` — waterfall @@ -215,7 +264,7 @@ Replace the frozen call configuration. Model-visible content must use logged cha Types: [Agent](../core-data-structures/core.md) · [LlmCallConfig](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) -Source: [`packages/core/agent/src/types.ts:276`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:409`](../../packages/core/agent/src/types.ts) ### `agent/request-error` — waterfall @@ -241,7 +290,7 @@ Recover a model-request failure after its failed step has closed. `retry` opens Types: [Agent](../core-data-structures/core.md) · [LlmFailure](../core-data-structures/llm-streaming.md) · [RequestError](../core-data-structures/core.md) · [RequestErrorDecision](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) -Source: [`packages/core/agent/src/types.ts:330`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:463`](../../packages/core/agent/src/types.ts) ### `agent/session-prefix` — waterfall @@ -267,7 +316,7 @@ Compose request-only messages placed before derived history. The frozen result i Types: [Agent](../core-data-structures/core.md) · [Message](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) -Source: [`packages/core/agent/src/types.ts:291`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:424`](../../packages/core/agent/src/types.ts) ### `agent/session-start` — emit @@ -289,16 +338,16 @@ The session lifecycle began, once before the first turn. Use `agent.inject()` to Types: [Agent](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) · [SessionStartSource](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:230`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:363`](../../packages/core/agent/src/types.ts) ### `agent/status` — emit -Agent status changed (`idle` ⇄ `running`, or → `disposed`). `send()` does not enter `running` synchronously; drive lifecycle from this event. +Agent status changed (`idle` ⇄ `running`, or → `disposed`). A waking delivery does not enter `running` synchronously; drive lifecycle from this event. ```ts cordis-catalog /** - * Agent status changed (`idle` ⇄ `running`, or → `disposed`). `send()` does - * not enter `running` synchronously; drive lifecycle from this event. + * Agent status changed (`idle` ⇄ `running`, or → `disposed`). A waking + * delivery does not enter `running` synchronously; drive lifecycle from this event. * @param agent - the agent whose status flipped. * @param status - the status just entered (the transition's destination). * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. @@ -309,7 +358,7 @@ Agent status changed (`idle` ⇄ `running`, or → `disposed`). `send()` does no Types: [Agent](../core-data-structures/core.md) · [AgentStatus](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) -Source: [`packages/core/agent/src/types.ts:197`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:303`](../../packages/core/agent/src/types.ts) ### `agent/step-result` — waterfall @@ -332,7 +381,7 @@ Waterfall: post-process the assembled assistant Message before tool dispatch (va Types: [Agent](../core-data-structures/core.md) · [Message](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) -Source: [`packages/core/agent/src/types.ts:303`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:436`](../../packages/core/agent/src/types.ts) ### `agent/turn-continuation` — waterfall @@ -354,7 +403,7 @@ Override whether the turn continues. The default continues after tool calls or s Types: [Agent](../core-data-structures/core.md) · [ContinuationDecision](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) -Source: [`packages/core/agent/src/types.ts:341`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:474`](../../packages/core/agent/src/types.ts) ### `agent/turn-stop` — serial @@ -376,7 +425,7 @@ Monotonic terminal-stop checkpoint after continuation and steering are folded; a Types: [Agent](../core-data-structures/core.md) · [ContinuationStop](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) -Source: [`packages/core/agent/src/types.ts:352`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:485`](../../packages/core/agent/src/types.ts) ## `agent-loop/*` diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 5858799e7c..0d6cc97086 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -1246,7 +1246,7 @@ fork(source: SessionForkSource, boundary?: number, childSessionId?: SessionId): Types: [CreateSessionOptions](../core-data-structures/persistence.md) · [OutOfBandSessionEventType](../core-data-structures/session.md) · [Session](../core-data-structures/session.md) · [SessionEvent](../core-data-structures/core.md) · [SessionEventMap](../core-data-structures/session.md) · [SessionId](../core-data-structures/core.md) · [TurnTrigger](../core-data-structures/session.md) -Source: [`packages/core/session/src/index.ts:605`](../../packages/core/session/src/index.ts) +Source: [`packages/core/session/src/index.ts:606`](../../packages/core/session/src/index.ts) ## `ctx.sessionTitle` — `SessionTitleService` diff --git a/docs/cordis-primer.i18n.yaml b/docs/cordis-primer.i18n.yaml new file mode 100644 index 0000000000..ef52bf6812 --- /dev/null +++ b/docs/cordis-primer.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +cordis-primer.md: ee65e6e702ecaeb506ce7334032c38e09c936cda +cordis-primer.zh.md: ee4f6864ba7864fc95b5eb8e31acbcaea6e99825 diff --git a/docs/cordis-primer.md b/docs/cordis-primer.md index 64230564b7..ee65e6e702 100644 --- a/docs/cordis-primer.md +++ b/docs/cordis-primer.md @@ -1,5 +1,7 @@ # Cordis Primer +English | [中文](cordis-primer.zh.md) + Cordis is the vendored plugin framework underneath the DeepSeek Harness SDK. This primer teaches the Cordis ideas a harness plugin author needs before reading the generated [events](cordis-catalog/events.md) and [services](cordis-catalog/services.md) catalogs; the [Cordis tutorial](cordis-tutorial/index.md) walks the same ideas hands-on. The vendored source and sync procedure live in [vendor/README.md](../vendor/README.md). ## Cordis In Five Ideas diff --git a/docs/cordis-primer.zh.md b/docs/cordis-primer.zh.md new file mode 100644 index 0000000000..ee4f6864ba --- /dev/null +++ b/docs/cordis-primer.zh.md @@ -0,0 +1,48 @@ +# Cordis 入门 + +[English](cordis-primer.md) | 中文 + +Cordis 是 DeepSeek Harness SDK 底层以 vendor 方式引入的插件框架。本文介绍 harness 插件作者在阅读生成的[事件](cordis-catalog/events.md)与[服务](cordis-catalog/services.md)目录之前需要了解的 Cordis 核心概念;[Cordis 教程](cordis-tutorial/index.md)则通过实践逐一讲解这些概念。vendor 源码与同步流程见 [vendor/README.md](../vendor/README.md)。 + +## 五个核心概念 + +- **插件是实现 Service 的对象。** 它可以是一个带有可选 `inject` 和 `apply(ctx)` 字段的函数,也可以是一个 `Service` 子类,其生命周期由 Cordis 挂载到当前上下文中。 +- **上下文是服务的容器。** 一个服务占据一个稳定的 `ctx.<key>`(如 `ctx.tools`、`ctx.llm`、`ctx.sessions`);其他插件通过 key 查找服务,而非导入具体实现。 +- **通过 `inject` 声明服务依赖。** 插件声明所需的服务后,会等待这些服务就绪才启动;加载顺序通过服务依赖表达,而非手动编排启动序列。 +- **类型化事件用于通信。** 服务通过 TypeScript 声明合并注册事件名,然后以 `emit`、`waterfall`(瀑布式事件)、`parallel` 或 `serial` 方式分发,分别对应监听者观察、包装、并行扇出或按序执行。 +- **注册是可逆的副作用。** 提示词片段、工具 schema、适配器、提供方和监听器通过 `ctx.effect()` 或 `ctx.on()` 安装,reload 和 teardown 时可预期地回卷。 + +## 分发模式 + +每个事件具有以下分发模式之一,且只能通过对应方法分发。 + +| 模式 | 是否 await? | 分发顺序 | 是否有返回值? | +|---|---|---|---| +| `emit` | 否 | 监听器按注册顺序观察 | 否 | +| `waterfall` | 否 | 监听器按注册顺序观察 | 是 | +| `parallel` | 是 | 所有监听器并行观察事件 | 否 | +| `serial` | 是 | 监听器按注册顺序观察 | 是 | + +分发模式是事件公开契约的一部分。新的 harness 事件通过 `@mode` 标签记录模式,以便生成的目录可以将声明与分发调用点做交叉校验。 + +<a id="cordis-waterfall-semantics"></a> + +## Cordis Waterfall 语义 + +`ctx.waterfall` 是环绕中间件。监听器接收 `(...args, next)`。调用 `next()` 会执行下游监听器;下游返回值通过 `next()` 返回当前包装层,可由该层包装后继续向外返回。不调用 `next()` 直接返回则短路。 + +协作式监听器通常修改一个共享的请求或决策对象,然后委托。监听器也可以选择完全替换结果,下游监听器将只看到替换后的结果。仅当监听器必须在普通注册之前运行时才使用 `prepend: true`。 + +对于单决策事件,短路是设计意图。策略监听器在拥有决策权时可以不调用 `next()` 直接返回,而仅做标注或观察的监听器则必须委托。 + +<a id="loader-configuration"></a> + +## Loader 配置 + +`@cordisjs/plugin-include` 将 `!!js` 解析为表达式节点,但 Loader 仅在挂载插件前对条目的 `config` 做插值。条目元数据(`id`、`name`、`group`、`disabled`、`inject`、`intercept` 和 `isolate`)保持字面值;因此 `disabled: !!js ...` 是一个 truthy 对象,会始终禁用该条目。需要根据环境选择挂载哪些插件时,请使用显式的配置覆盖层。 + +## 实践规则 + +将行为封装为插件:工具流水线事件属于 `ctx.tools`,模型流式输出属于 `ctx.llm`,实时 agent(智能体)协调属于 `ctx.agents`。拦截和策略优先使用事件;直接能力调用优先使用服务方法。 + +每个注册都应有对应的 disposer(dispose(资源释放)函数):要么从 `ctx.effect()` 返回一个,要么使用 Cordis 提供的辅助方法自动处理。如果 teardown 顺序有要求,请将相关工作放在同一个 effect 中,以确保资源释放按预期顺序回卷。 diff --git a/docs/core-data-structures/approval.i18n.yaml b/docs/core-data-structures/approval.i18n.yaml new file mode 100644 index 0000000000..c9f6b1600c --- /dev/null +++ b/docs/core-data-structures/approval.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +approval.md: c9b411e38508fc7e8ac2e2dd923d9c8cc2f475a3 +approval.zh.md: c3d67b195a0c04186911285ccb76cd89eceb421b diff --git a/docs/core-data-structures/approval.md b/docs/core-data-structures/approval.md index 8634415a62..c9b411e385 100644 --- a/docs/core-data-structures/approval.md +++ b/docs/core-data-structures/approval.md @@ -1,5 +1,7 @@ # User Approval +English | [中文](approval.zh.md) + The user-approval seam of [dsh-user-approval](../../packages/ui/user-approval) answers one question: may this specific action proceed? It owns the shared request/outcome vocabulary, the `ctx.approval` dispatch service, the `approval/request` answerer waterfall, the log-only audit pair, and the per-session `ask`/`never` policy. UI channels such as [dsh-acp](../../packages/ui/acp) provide answerers; callers such as [dsh-tools](../../packages/core/tools) and [dsh-tool-bash](../../packages/bash/tool-bash) consume the closed outcome and fail closed unless it is `allowed-once`. Source: [`packages/ui/user-approval/src/index.ts`](../../packages/ui/user-approval/src/index.ts) diff --git a/docs/core-data-structures/approval.zh.md b/docs/core-data-structures/approval.zh.md new file mode 100644 index 0000000000..c3d67b195a --- /dev/null +++ b/docs/core-data-structures/approval.zh.md @@ -0,0 +1,90 @@ +# 用户审批 + +[English](approval.md) | 中文 + +[dsh-user-approval](../../packages/ui/user-approval) 的用户审批 seam 回答一个问题:这个具体操作是否可以继续?它拥有共享的请求/结果词汇、`ctx.approval` 分发服务、`approval/request` 应答者 waterfall(瀑布式事件)、仅记录日志的审计事件对,以及按会话的 `ask`/`never` 策略。UI 通道如 [dsh-acp](../../packages/ui/acp) 提供应答者;调用方如 [dsh-tools](../../packages/core/tools) 和 [dsh-tool-bash](../../packages/bash/tool-bash) 消费闭合的结果,除非结果为 `allowed-once`,否则一律拒绝。 + +源码:[`packages/ui/user-approval/src/index.ts`](../../packages/ui/user-approval/src/index.ts) + +## 标识与结果 + +每个请求都会获得一个全新的 `ApprovalRequestId`。该品牌类型将 `approval/asked` 与 `approval/decided` 审计事件配对,同时不会让审批 id 与工具调用 id 或 agent(智能体)/会话 id 互换。 + +```ts type-equiv +/** + * Pairs one `approval/asked` audit event with its `approval/decided`. + * Service-issued (one fresh id per {@link ApprovalService.request} call). + */ +type ApprovalRequestId = Branded<'ApprovalRequestId'> +``` + +`ApprovalOutcome` 是闭合的,且默认拒绝。`allowed-once` 仅授权所询问的那一个操作;调用方对 `rejected`、`cancelled` 和 `unavailable` 均执行拒绝。缺失、无所有权、抛异常或不合规的应答者会产生 `unavailable`,而非放行。 + +```ts type-equiv +/** + * Closed approval outcomes: a one-shot grant, explicit rejection, withdrawn + * request, or unavailable answerer. Callers fail closed on `unavailable`. + */ +type ApprovalOutcome = 'allowed-once' | 'rejected' | 'cancelled' | 'unavailable' +``` + +## 按会话策略 + +`ApprovalPolicy` 决定在交互式应答者运行之前发生什么。`ask` 委托给组合的应答者链,链的无应答默认值为 `unavailable`;`never` 确定性地返回 `rejected`,不分发任何应答者。生效值为会话日志中最后一条 `approval/policy` 事件,回退到服务配置。`setApprovalPolicy(session, policy)` 是唯一的写入路径,因此回放能重建覆盖值。 + +```ts type-equiv +/** + * A session's approval policy — what happens to an {@link ApprovalService} + * ask BEFORE any interactive answerer sees it: + * + * - `'ask'` (the default) — delegate to the composed answerers; with none + * composed the chain falls through to the fail-closed `'unavailable'` + * (exactly today's behavior). + * - `'never'` — never prompt anyone: every ask resolves `'rejected'` + * deterministically. The strict headless stance (CI, unattended runs) and + * the only policy value stated in the system prompt — unlike `'ask'`, its + * outcome is knowable without asking, so stating it cannot overclaim. + */ +type ApprovalPolicy = 'ask' | 'never' +``` + +提示词段落会声明 `never` 的确定性行为,并以服务自有的标记记录当前策略。重启后,步骤前叙述器从已记录的请求头中读取该标记,而非从部署 persona 行文中推断状态。ACP(Agent Client Protocol)空闲切换会在 bridge 中保持,直到下一个 `turn/start`,因为审批审计和策略事件必须保持在轮次内,以确保持久回放的正确性。 + +## 审批请求 + +`ApprovalRequest` 以足够精确的方式标识 agent 和工具操作,以便路由和审计该问题。它有意省略工具参数:应答者通过 `callId` 将提示附加到已流式输出的工具调用上,而非渲染一份可能漂移的副本。 + +```ts type-equiv +/** + * Readonly same-process permission question. `callId` links to an already + * presented tool call, so arguments are not duplicated here. + */ +interface ApprovalRequest { + /** + * The agent on whose behalf the question is asked. Routes the question (a + * UI answerer only answers for agents it owns) and receives the audit + * events on its session log. + */ + readonly agent: Agent + /** The tool the question is about (presentation and audit). */ + readonly toolName: string + /** + * The exact tool call being decided, when the asker has one — lets a UI + * attach the prompt to the tool call it already streamed. + */ + readonly callId?: CallId + /** The asker's human-readable explanation of WHY it is asking. */ + readonly reason?: string + /** + * Aborting withdraws the question: the request settles `'cancelled'` + * immediately and a late answer from a still-pending answerer is discarded. + */ + readonly signal?: AbortSignal +} +``` + +## 分发与审计 + +`ctx.approval.request(req)` 要求发起请求的会话处于一个打开的轮次内。它追加 `approval/asked`,获取一个结果,追加对应的 `approval/decided`,然后以该结果 resolve。`never` 策略在服务内部、waterfall 分发之前强制执行,因此即使后来以 `prepend` 注册的应答者也无法绕过它。应答者在拥有该请求时返回结果,否则调用 `next()` 委托;第一个应答占据唯一的决策槽位。 + +审计事件仅写入日志,不进入模型 transcript(文本记录)。模型可见的行为是调用方派生的工具结果,而请求头记录的是模型实际看到的提示词策略。服务 dispose(资源释放)时会一并移除其提示词段落和步骤前叙述器;应答者监听器独立地通过 effect 绑定到其所属插件。 diff --git a/docs/core-data-structures/bash.i18n.yaml b/docs/core-data-structures/bash.i18n.yaml new file mode 100644 index 0000000000..98855cdc0c --- /dev/null +++ b/docs/core-data-structures/bash.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +bash.md: 35cf2061588907dde41123efb01e453eb9cc929d +bash.zh.md: 0cfeb9e1a858f7057e720215c41a757588751122 diff --git a/docs/core-data-structures/bash.md b/docs/core-data-structures/bash.md index b639e55927..35cf206158 100644 --- a/docs/core-data-structures/bash.md +++ b/docs/core-data-structures/bash.md @@ -1,5 +1,7 @@ # Bash Executor +English | [中文](bash.zh.md) + The bash execution seam is split across interface ([dsh-bash](../../packages/bash/bash), `ctx.bash`), implementations ([dsh-bash-local](../../packages/bash/bash-local) and [dsh-bash-sandbox](../../packages/bash/bash-sandbox)), and consumer ([dsh-tool-bash](../../packages/bash/tool-bash), the `bash` schema). Generic background-task ids, ownership, and controls live in [tasks.md](tasks.md); this seam returns a task-free process handle. Source: [`packages/bash/bash/src/types.ts`](../../packages/bash/bash/src/types.ts) diff --git a/docs/core-data-structures/bash.zh.md b/docs/core-data-structures/bash.zh.md new file mode 100644 index 0000000000..0cfeb9e1a8 --- /dev/null +++ b/docs/core-data-structures/bash.zh.md @@ -0,0 +1,241 @@ +# Bash 执行器 + +[English](bash.md) | 中文 + +bash 执行 seam 分为接口([dsh-bash](../../packages/bash/bash),`ctx.bash`)、实现([dsh-bash-local](../../packages/bash/bash-local) 与 [dsh-bash-sandbox](../../packages/bash/bash-sandbox))和消费方([dsh-tool-bash](../../packages/bash/tool-bash),即 `bash` schema)。通用后台任务的 id、所有权与控制位于 [tasks.md](tasks.md);本 seam 返回一个不含任务概念的进程句柄。 + +源码:[`packages/bash/bash/src/types.ts`](../../packages/bash/bash/src/types.ts) + +## 受管 shell 环境命名空间 + +`DSH_*` 变量是归 Harness 所有的子进程事实。面向模型的 bash 工具通过 `ctx.bashEnv` 收集它们,再经由 `BashExecRequest.dshEnv` 传递;执行器在合并当前快照之前会移除继承而来的 `DSH_*` 名称。 + +```ts type-equiv +/** One environment key inside the managed {@link DSH_ENV_PREFIX} namespace. */ +type DshEnvironmentKey = `${typeof DSH_ENV_PREFIX}${string}` +``` + +```ts type-equiv +/** Trusted DeepSeek Harness variables for one bash execution. */ +type DshEnvironment = Readonly<Record<DshEnvironmentKey, string>> +``` + +## 请求与规格:`resolve()` 拆分 + +该 seam 将**面向模型/插件的请求**(`workdir`/`timeoutMs`/`stdoutMaxBytes` 可选,由配置或请求策略补全)与执行器实际使用的**完全解析后的 spec**(这些字段均为必填)分开。工具层在二者之间调用 `ctx.bash.resolve(request)`——这具体落实了仓库的「包(package) seam 上显式优于隐式」规则:`BashExecSpec` 的读者不必猜测工作目录或输出预算来自何处。 + +```ts type-equiv +/** + * A caller's execution REQUEST: `workdir` and `timeoutMs` are optional and + * filled by {@link BashExecutor.resolve} from the implementation's config. + * This is the model-/plugin-facing shape; pass it to `resolve()` to obtain a + * fully-resolved {@link BashExecSpec}. + */ +interface BashExecRequest { + command: string + /** Working directory override (default: implementation-configured). */ + workdir?: string | undefined + /** Timeout override in milliseconds (implementations cap it). */ + timeoutMs?: number | undefined + /** + * Foreground stdout capture budget in bytes. Absent uses the executor's + * default output cap. Trusted in-process consumers use this when they must + * parse complete stdout up to their own bounded limit; the model-facing bash + * tool does not expose it as a parameter. + */ + stdoutMaxBytes?: number | undefined + /** Abort signal — implementations kill the command when it fires. */ + signal?: AbortSignal | undefined + /** + * Bytes to write to the command's stdin, then close it. Absent leaves stdin + * closed/empty (the default for model-driven tool calls). Set by in-process + * plugins (e.g. the hooks bridges, which write a hook command's JSON payload + * to its stdin); the model-facing bash tool does not expose it as a parameter + * (a model that needs stdin uses shell syntax like a heredoc or a pipe). + */ + stdin?: string | undefined + /** + * Ordinary environment entries for the command, merged after the credential + * scrub. `DSH_*` is reserved for {@link dshEnv} and implementations reject it + * here. Set by in-process plugins (the hooks bridges set + * `CLAUDE_PROJECT_DIR`, `CLAUDE_PLUGIN_ROOT`, …); the model-facing bash tool + * does not expose it as a parameter. + */ + env?: Record<string, string> | undefined + /** + * Harness-owned `DSH_*` variables for this execution. Executors discard + * ambient `DSH_*` entries before merging this snapshot, so an unavailable + * current fact cannot inherit a stale value from the harness process, and + * reject non-`DSH_*` names supplied through this managed channel. + */ + dshEnv?: DshEnvironment | undefined + /** Fully resolved per-call sandbox policy; sandboxing executors default it. */ + sandboxPolicy?: SandboxExecutionPolicy | undefined +} +``` + +```ts type-equiv +/** + * A resolved execution spec. {@link BashExecutor.resolve} fills and caps the + * required fields; {@link BashExecutor.start} ignores `timeoutMs` because + * background processes have no executor timeout. + */ +interface BashExecSpec { + command: string + workdir: string + timeoutMs: number + /** + * Resolved foreground stdout capture budget in bytes. `run()` uses it for + * stdout; background tasks and stderr keep the executor's own output cap. + */ + stdoutMaxBytes: number + /** Abort signal — implementations kill the command when it fires. */ + signal?: AbortSignal | undefined + /** Bytes to write to stdin before closing it; absent means no stdin. */ + stdin?: string | undefined + /** + * Ordinary environment entries carried through from + * {@link BashExecRequest.env}. `DSH_*` remains reserved for {@link dshEnv}. + * OPTIONAL on the spec for the same reason as `stdin`: absent means no + * ordinary extra environment. + */ + env?: Record<string, string> | undefined + /** Managed `DSH_*` snapshot; implementations reject ordinary names. */ + dshEnv?: DshEnvironment | undefined + /** Resolved sandbox policy; ignored by executors that do not confine. */ + sandboxPolicy: SandboxExecutionPolicy | undefined +} +``` + +`stdin` 和 `env` 是受信任的进程内插件输入,不由 `dsh-tool-bash` 暴露。本地执行器会先清除环境中的凭据,再合并调用方显式提供的 env。见 [bash-stdin-env Agent Note(agent 决策记录)](../../.agents/notes/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md)。 + +`stdoutMaxBytes` 同样仅供受信任插件使用。它让前台消费方能在有界解析预算内请求完整 stdout,而不会改变 stderr、后台任务或面向模型的 bash 工具的常规输出上限。 + +## 前台运行:`BashRunResult` + +一次已完成(或被终止)的前台运行的结果。正交的结果**独立报告**:一个进程可以同时超时并以退出码 0 退出(因为它捕获了信号),因此 `timedOut`、`aborted`、`signal` 和 `exitCode` 各自独立为一个字段;调用方永远不会把一次被截断的运行误读为干净的成功。 + +```ts type-equiv +/** The outcome of one completed (or killed) foreground run. */ +interface BashRunResult { + /** Exit code; null when the process died from a signal. */ + exitCode: number | null + /** Terminating signal (e.g. 'SIGTERM'); null on normal exit. */ + signal: NodeJS.Signals | null + /** + * True when the executor's own timeout was the FIRST cause to cut the command + * short. Mutually exclusive with {@link aborted}: one fused deadline drives + * both the timeout and the caller's cancellation, so a timeout and an abort + * racing before process close report the single first-abort cause, not both + * (see the [timeout-library Agent Note](../../../../.agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.md)). + */ + timedOut: boolean + /** + * True when the caller's `AbortSignal` was the FIRST cause to kill the command + * (and it was not the executor's own timeout). Mutually exclusive with + * {@link timedOut} — see there for the first-cause classification. + */ + aborted: boolean + /** The effective timeout applied to this run (after defaulting/capping). */ + timeoutMs: number + stdout: CollectedOutput + stderr: CollectedOutput + /** Sandbox execution facts, absent for an unsandboxed executor. */ + sandbox?: BashSandboxInfo +} +``` + +每个流是一个 `CollectedOutput`:(可能被截断的)文本加恢复信息。截断时,`text` 是**尾部**,完整流溢出到一个私有文件: + +```ts type-equiv +/** One captured stream: the (possibly truncated) text plus recovery info. */ +interface CollectedOutput { + /** Collected text — the TAIL of the stream when truncated. */ + text: string + /** True when bytes were dropped from `text`. */ + truncated: boolean + /** Path to a file holding the COMPLETE stream, when truncated and available. */ + spillPath?: string +} +``` + +## 文件沙箱:`BashSandboxInfo` + +使用沙箱的执行器通过 `BashExecutor.sandboxMode` 暴露其已配置的模式回退值。工具层请求 [`@deepseek-ai/dsh-sandbox-policy`](../../packages/sandbox/sandbox-policy/README.md),把每个调用会话的持久 `sandbox/mode` 覆盖值与不可变 cwd 解析为 `BashExecRequest.sandboxPolicy`;经用户批准、严格更宽松的调用只替换模式。模式/root/enforcement 词汇归 [`@deepseek-ai/dsh-sandbox` 沙箱 seam](sandbox.md) 所有;模式仅管辖文件效果。 + +沙箱化运行会报告其模式、保守的拒绝分类与强制执行完整度。`runnerFailed` 标记命令运行前沙箱 runner 已失败;前台执行会抛出 `SANDBOX_UNAVAILABLE`,而已结束的后台进程只能通过其事实通道报告。 + +```ts type-equiv +/** + * Sandbox facts for one run, present iff a sandboxing executor handled it. + * Facts are reported independently of process exit status so callers can + * distinguish command failures from policy denials and runner failures. + */ +interface BashSandboxInfo { + /** The mode the command actually ran under. */ + mode: SandboxMode + /** Whether the sandbox denied a file operation. */ + denied: boolean + /** How completely the selected runner enforced the requested mode. */ + enforcement?: SandboxEnforcement + /** Whether the sandbox runner failed before the command could run. */ + runnerFailed?: boolean +} +``` + +最后一项补全了这套词汇:当受限模式没有可用后端时,`ctx.sandbox` 提供方会抛出、执行器会传播由[沙箱 seam](sandbox.md)所有的 `SANDBOX_UNAVAILABLE` 错误码。选定的 runner 拒绝其 profile 时会触达同一个故障关闭的前台错误;已结束的后台任务则记录 `runnerFailed`。模型会在结果中收到拒绝/runner 事实,仅当拒绝标记指出生效模式时才得知该模式,并可通过 `sandbox_permissions` 加 `justification` 请求一次性、严格更宽松的重试;执行任何操作前,`ctx.approval` 必须批准该次确切调用。完整的策略与切换设计见[沙箱 Agent Note](../../.agents/notes/implemented/feature/2026-07-06-sandbox.md)。 + +## 后台进程:`BashProcess` + +`start()` 返回不含 id 或所有者的句柄。`dsh-tool-bash` 将它适配为 `ctx.tasks.start()` 钩子;随后由通用运行时拥有任务标识与生命周期。`done` 在进程关闭时 resolve 且绝不 reject;进程结束后仍可读取,并且沙箱事实会在 `done` resolve 前写入。 + +```ts type-equiv +/** + * A background process handle returned by {@link BashExecutor.start}. It is the + * only access path; buffered output remains readable after exit. Executor + * disposal kills running processes and awaits {@link done}. + */ +interface BashProcess { + /** Process lifecycle state (settled exactly once). */ + status: BashProcessStatus + /** Exit code once finished (null = killed by signal / still running). */ + exitCode: number | null + /** Terminating signal name, when signal-killed. */ + signal: NodeJS.Signals | null + /** Resolves when the underlying process closes (never rejects — a spawn failure settles as `killed` with the error on stderr). */ + readonly done: Promise<void> + /** Sandbox facts, stamped once a confined process settles. */ + sandbox?: BashSandboxInfo + /** + * Read output produced since the previous read (consuming — consecutive + * reads never re-deliver). Reads that lost data flag `lossy` and point at + * full-stream spill files when available. + */ + readOutput(): BashProcessRead + /** + * Kill the process group. Returns false when it had already finished + * (no-op); idempotent. + */ + kill(): boolean +} +``` + +`readOutput()` 返回增量 delta 与 spill 恢复事实: + +```ts type-equiv +/** One incremental {@link BashProcess.readOutput} read. */ +interface BashProcessRead { + /** Output produced since the previous read (stderr in a marked section). */ + delta: string + /** True when truncation dropped unread bytes the delta cannot include. */ + lossy: boolean + /** Full stdout spill file, when stdout truncation occurred and a safe path is available. */ + stdoutSpillPath?: string + /** Full stderr spill file, when stderr truncation occurred and a safe path is available. */ + stderrSpillPath?: string +} +``` + +## 服务 + +`BashExecutor` 拥有 `resolve`、前台 `run`、后台进程 `start` 以及 `sandboxMode` 能力事实。`dsh-bash-local` 拥有进程组、超时/中止处理、有界收集器、spill 文件、凭据清除以及 dispose(资源释放)后完全停稳。`dsh-tool-bash` 拥有面向模型的渲染,并将后台句柄适配到[通用任务运行时](tasks.md)。 diff --git a/docs/core-data-structures/code-runtime.i18n.yaml b/docs/core-data-structures/code-runtime.i18n.yaml new file mode 100644 index 0000000000..218ef4eea9 --- /dev/null +++ b/docs/core-data-structures/code-runtime.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +code-runtime.md: 64de3c45d4f1d1d981daa6c6f074abb667e0aa52 +code-runtime.zh.md: 4b14aeb2183010e8140540258ce8109df9f59910 diff --git a/docs/core-data-structures/code-runtime.md b/docs/core-data-structures/code-runtime.md index 41009f065e..64de3c45d4 100644 --- a/docs/core-data-structures/code-runtime.md +++ b/docs/core-data-structures/code-runtime.md @@ -1,5 +1,7 @@ # Code Runtime +English | [中文](code-runtime.zh.md) + The code-execution seam — a [capability seam](../../.agents/notes/implemented/architecture/2026-06-13-capability-seams.md) whose interface ([dsh-code-runtime](../../packages/code-runtime/code-runtime), `ctx.codeRuntime`) runs one model-written program against host-provided async bindings and reports what it printed and returned. Code execution is **one optional capability**, not part of the agent-loop spine — so its vocabulary lives here, not in [core.md](core.md). Backends differ by execution substrate and source language, both readonly descriptors on the service; the worker-thread backend and tool-registry consumer are specified by the [Code Mode foundation](../../.agents/notes/implemented/feature/2026-06-15-code-mode.md) and [typed-return contract](../../.agents/notes/implemented/feature/2026-07-20-code-mode-typed-tool-returns.md). Source: [`packages/code-runtime/code-runtime/src/types.ts`](../../packages/code-runtime/code-runtime/src/types.ts) diff --git a/docs/core-data-structures/code-runtime.zh.md b/docs/core-data-structures/code-runtime.zh.md new file mode 100644 index 0000000000..4b14aeb218 --- /dev/null +++ b/docs/core-data-structures/code-runtime.zh.md @@ -0,0 +1,147 @@ +# 代码运行时 + +[English](code-runtime.md) | 中文 + +代码执行 seam 是一个[能力 seam](../../.agents/notes/implemented/architecture/2026-06-13-capability-seams.md):其接口([dsh-code-runtime](../../packages/code-runtime/code-runtime),`ctx.codeRuntime`)针对宿主提供的异步 binding 运行一段模型编写的程序,并报告其打印内容与返回值。代码执行是**一项可选能力**,不属于 agent loop(智能体循环)主干,因此其词汇定义在此而非 [core.md](core.md) 中。各后端的执行基底与源语言不同,这两项均为服务上的只读描述符;worker-thread 后端与工具注册表消费方的契约见 [Code Mode 基础设计](../../.agents/notes/implemented/feature/2026-06-15-code-mode.md)和[类型化返回契约](../../.agents/notes/implemented/feature/2026-07-20-code-mode-typed-tool-returns.md)。 + +源码:[`packages/code-runtime/code-runtime/src/types.ts`](../../packages/code-runtime/code-runtime/src/types.ts) + +## 运行:请求进,结果出 + +`CodeRunRequest` 携带**运行时所需的一切**。按照「包(package)边界处显式优于隐式」的规则,默认值(时间预算、输出上限)来自实现的已校验配置,绝不是 `run()` 内部隐藏的 `??`: + +```ts type-equiv +/** + * One run: the program source plus everything the runtime acts on. Per the + * explicit-over-implicit convention, defaulting (time budgets, output caps) + * is the implementation's validated config — a request carries no optional + * tuning knobs for a hidden `??` to fill in. + */ +interface CodeRunRequest { + /** + * The program source, in the runtime's {@link ../index.ts | language}. It + * runs as the body of an async function: top-level `await` and `return` + * are available, and the completion value becomes + * {@link CodeRunResult.value}. + */ + program: string + /** Host functions exposed to the program, one global object per namespace. */ + bindings: CodeBindingNamespace[] + /** + * Abort the run: the runtime stops the program (hard, even mid-loop) and + * resolves with a {@link CodeRunFailure} of kind `'abort'`. In-flight + * binding calls are the CALLER's to settle — the runtime only stops asking. + */ + signal?: AbortSignal +} +``` + +结果将错误报告为一个**字段**,而非 `run()` 的 rejection。报告失败的程序是调用方的职责,不走异常路径(与 `BashExecutor.run` 的 resolve-on-failure 契约一致): + +```ts type-equiv +/** + * The outcome of one run. An error is a FIELD on a resolved result, never a + * rejection of `run()` — reporting a failed program is the caller's job, not + * an exception path. + */ +interface CodeRunResult { + /** + * The program's completion value (its top-level `return`), when it ran to + * completion and the value crossed the runtime's lossless-JSON boundary. + * Invalid or over-limit completions fail the run instead of substituting a + * rendered string; a failed or value-less run leaves this absent. + */ + value?: CodeJsonValue + /** Text the program emitted, in order, bounded only as part of the outer result. */ + logs: string[] + /** Present iff the run failed; see {@link CodeRunFailure} for the taxonomy. */ + error?: CodeRunFailure +} +``` + +## 绑定:宿主函数作为程序全局变量 + +每个 `CodeBindingNamespace` 在程序内成为一个由异步可调用函数组成的全局对象(Code Mode 消费方传入一个:`tools`)。参数与返回值必须是无损 JSON,且跨越边界时不受 seam 层字节上限约束;运行时可以通过结构化克隆桥接它们。命名空间可以声明程序可见的错误类,而无需让运行时知道消费方的名称:运行时会注入真实构造函数,并将被拒绝的调用转为该类的实例。运行时也将绑定名视为不可信输入(`__proto__` 是普通自有属性,绝不会发生原型碰撞): + +```ts type-equiv +/** + * Program-visible typed rejection for one binding namespace. The runtime + * injects a real error constructor under `name`; rejected member calls become + * its instances and expose the exact member name through + * `memberNameProperty`. Both strings are runtime data rather than knowledge + * of a particular consumer such as Code Mode. + */ +interface CodeBindingErrorClass { + /** Constructor global and resulting `Error.name` (must be a usable JS identifier). */ + name: string + /** Non-empty own property for the member name; cannot replace `name`, `message`, or `stack`. */ + memberNameProperty: string +} +``` + +```ts type-equiv +/** + * A named group of {@link CodeBindingFunction}s the runtime exposes to the + * program as one global object (e.g. `tools`). Function names are arbitrary + * strings — a runtime must treat names like `__proto__` or `constructor` as + * ordinary own properties (null-prototype construction), never as prototype + * collisions. + */ +interface CodeBindingNamespace { + /** The global identifier the program sees (must be a valid JS identifier). */ + global: string + /** The callable members, keyed by the exact name the program calls. */ + functions: Record<string, CodeBindingFunction> + /** Optional program-visible typed rejection contract for this namespace. */ + errorClass?: CodeBindingErrorClass +} +``` + +```ts type-equiv +/** A lossless JSON value transferable across the dependency-light code-runtime seam. */ +type CodeJsonValue = null | boolean | number | string | CodeJsonValue[] | { [key: string]: CodeJsonValue } +``` + +```ts type-equiv +/** + * One host-side function exposed to the program as an async callable. The + * runtime bridges calls to it (possibly across a serialization boundary), so + * `args` and the resolution value MUST be lossless JSON. A runtime rejects a + * lossy or non-cloneable value with a descriptive error rather than corrupting + * the run. No seam-level byte cap applies to a binding resolution. A rejection + * of this function surfaces inside the program as a rejection of the + * corresponding call. + */ +type CodeBindingFunction = (args: unknown) => Promise<CodeJsonValue> +``` + +## 捕获的输出与失败分类体系 + +日志是按发出顺序排列的纯字符串。运行时捕获程序的 console 与流输出,但通道和 console 方法的元数据不属于 seam,因为消费方只渲染文本。实现会对序列化后的外层日志数组,以及完成值或失败消息的组合载荷设置上限;固定的结果封装语法与消费方展示空白不计入这份可变载荷计量。超限会显式失败,而不会在值中插入替代内容。 + +失败类型是**正交的结果,独立报告**(见 [defensive-patterns](../defensive-patterns.md)):预算耗尽不是异常,中止不是超时,基底崩溃(如 OOM)也不是二者中的任何一个: + +```ts type-equiv +/** + * Why a run failed. The kinds are orthogonal outcomes reported independently + * (per docs/defensive-patterns.md): a budget expiry is not an exception, an + * abort is not a timeout, and a substrate death is neither. + * + * - `'exception'` — the program threw or failed to parse/transform. + * - `'timeout'` — an implementation-owned budget expired; the message says which. + * - `'abort'` — {@link CodeRunRequest.signal} fired. + * - `'worker-exit'` — the execution substrate died without settling (e.g. OOM). + * - `'invalid-output'` — the completion value was not lossless JSON. + * - `'output-limit'` — the serialized outer logs/value/diagnostic exceeded the configured cap. + */ +interface CodeRunFailure { + /** The failure class (see the interface doc for each kind's meaning). */ + kind: 'exception' | 'timeout' | 'abort' | 'worker-exit' | 'invalid-output' | 'output-limit' + /** Human-readable detail, suitable for feeding back to a model to self-correct. */ + message: string +} +``` + +## 服务 + +`CodeRuntime`(`ctx.codeRuntime`,抽象服务,定义于 [`packages/code-runtime/code-runtime/src/index.ts`](../../packages/code-runtime/code-runtime/src/index.ts))由 `run(request)` 加两个只读描述符组成:`language`(程序必须使用的语言,`'typescript'` 是已知值;生成语言相关展示的消费方据此切换,遇到无法展示的语言时应显式报错)和 `isolation`(执行基底,`'worker-thread'`、`'process'`、`'container'`;仅为诊断标签,**不构成安全承诺**)。实现必须保证各次运行彼此隔离(无跨运行状态),并在 dispose(资源释放)时等待系统完全停稳:teardown 完成前,进行中的运行都已终止并等待结束。 diff --git a/docs/core-data-structures/compaction.i18n.yaml b/docs/core-data-structures/compaction.i18n.yaml new file mode 100644 index 0000000000..3f192f0194 --- /dev/null +++ b/docs/core-data-structures/compaction.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +compaction.md: 71bbe7d9c17c6a3d35684a6c87d3072ab4f88df1 +compaction.zh.md: 35e9c9ef0050f01c5249d1502bb2782511acc819 diff --git a/docs/core-data-structures/compaction.md b/docs/core-data-structures/compaction.md index 6fa281a96c..71bbe7d9c1 100644 --- a/docs/core-data-structures/compaction.md +++ b/docs/core-data-structures/compaction.md @@ -1,5 +1,7 @@ # Compaction +English | [中文](compaction.zh.md) + The compaction seam — a [capability seam](../../.agents/notes/implemented/architecture/2026-06-13-capability-seams.md) split like bash: interface ([dsh-compact](../../packages/compact/compact), `ctx.compact`), implementation (a backend such as [dsh-compact-basic](../../packages/compact/compact-basic)), and consumer (a `/compact` tool, deferred). Compaction is **one optional capability**, not part of the agent-loop spine — so its vocabulary lives here, not in [core.md](core.md). A tokenizer- or template-based backend is a sibling package implementing the same interface. Unlike bash, the interface necessarily depends on `dsh-session` and `dsh-llm`: its verbs act on an agent-owned `Session`, and its durable summary event uses the `ContentBlock` vocabulary (see the [compaction capability-seam Agent Note](../../.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.md)). Source: [`packages/compact/compact/src/types.ts`](../../packages/compact/compact/src/types.ts) diff --git a/docs/core-data-structures/compaction.zh.md b/docs/core-data-structures/compaction.zh.md new file mode 100644 index 0000000000..35e9c9ef00 --- /dev/null +++ b/docs/core-data-structures/compaction.zh.md @@ -0,0 +1,97 @@ +# 压缩(compaction) + +[English](compaction.md) | 中文 + +压缩 seam 是一个[能力 seam](../../.agents/notes/implemented/architecture/2026-06-13-capability-seams.md),与 bash 一样分为接口([dsh-compact](../../packages/compact/compact),`ctx.compact`)、实现(例如 [dsh-compact-basic](../../packages/compact/compact-basic) 后端)和消费方(延期实现的 `/compact` 工具)。压缩是**一项可选能力**,不属于 agent loop(智能体循环)主干,因此其词汇定义在此而非 [core.md](core.md) 中。基于 tokenizer 或模板的后端是实现同一接口的兄弟包(package)。与 bash 不同,该接口必然依赖 `dsh-session` 和 `dsh-llm`:其动词作用于 agent 所有的 `Session`,而其持久摘要事件使用 `ContentBlock` 词汇(见[压缩能力 seam Agent Note(agent 决策记录)](../../.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.md))。 + +源码:[`packages/compact/compact/src/types.ts`](../../packages/compact/compact/src/types.ts) + +## `compact/*` 会话事件 + +压缩通过声明合并为 [`SessionEventMap`](session.md) 扩展三种事件类型。三者都**仅写入日志**——记录压缩锁及其 provenance,绝不进入 surface。这里有意不扩展 `SurfaceEventType`(只有产生消息的事件才到达模型),因此摘要本身承载在另一条带有 `surfaceOp: { op: 'replace', start, end }` 的 `user/message` 上——这是摘要压缩执行的唯一 surface 变更。关于复用 `user/message` 为何是如实建模而非权宜之计,见对应 Agent Note。 + +| 事件 | 载荷 | 作用 | +|---|---|---| +| `compact/start` | `{ turn }` | 获取日志记录的锁 | +| `compact/summary` | `{ summary, shadowedRange, shadowedSeqs, shadowedTokenCount, provider, model, maxTokens? }` | provenance:摘要块、被遮蔽的 surface 边界对(`start`/`end` seq——位置跨度,而非数值区间)、按 surface 顺序排列的被遮蔽 seq、估算 token 数,以及摘要调用的 envelope(`provider`、`model`,若有生成上限则还包括该上限)——写入日志后,该一次性请求可由日志 + 代码重建(见可重建性 Agent Note) | +| `compact/end` | `{ turn, error? }` | 释放锁(摘要调用抛出异常时设置 `error`) | + +锁括住**整个**操作:先追加 `compact/start`,然后执行摘要生成、写入 `compact/summary` 来源记录与 `user/message` 替换,最后才追加 `compact/end`。最后释放锁意味着操作中途崩溃会表现为可检测的遗留锁(有 `compact/start` 而无匹配的 `compact/end`),而非一个虚假声称压缩已完成的 `compact/end`。 + +这些变体在 `declare module '@deepseek-ai/dsh-session'` 块内合并,因此——与其他子页面上的顶层类型不同——它们不以漂移检查的 ` ```ts type-equiv ` 块粘贴(`verify-type-equiv` 提取器只按名称匹配顶层声明)。上方的载荷表即为目录条目;权威形状请循源码链接查看。 + +## `CompactionResult` + +成功压缩向调用方返回:记账事件 seq、原始摘要、被遮蔽的范围与 seq,以及估算 token 数。 + +```ts type-equiv +/** Result of a successful compaction operation. */ +interface CompactionResult { + /** The seq of the appended `compact/start` event. */ + startSeq: number + /** The seq of the appended `compact/summary` event. */ + summarySeq: number + /** The seq of the appended `compact/end` event. */ + endSeq: number + /** The summary content blocks produced by the backend. */ + summary: ContentBlock[] + /** + * The surface-boundary pair that was shadowed: the seqs of the first + * (`start`) and last (`end`) surface nodes of the replaced range. A + * surface-POSITION span, not a numeric seq interval — after a prior replace + * lands a fresh high-seq summary node at an older range's position, `start` + * can be GREATER than `end`. {@link CompactionResult.shadowedSeqs} is the + * authoritative set of shadowed nodes, in surface order. + */ + shadowedRange: { start: number; end: number } + /** The seqs of all shadowed surface nodes, in surface order. */ + shadowedSeqs: number[] + /** Estimated token count of the shadowed content. */ + shadowedTokenCount: number +} +``` + +## 服务 + +自动调用方会说明策略为何运行;实现可以比普通压力更激进地处理已确认的溢出。 + +```ts type-equiv +/** Why automatic policy is asking a backend to consider compaction. */ +type CompactionTrigger = 'pressure' | 'context-overflow' +``` + +`CompactService` 暴露 `compactIfNeeded(agent, trigger, signal)` 以执行自动 `pressure` 或 `context-overflow` 策略;没有可安全执行的工作时返回 `null`。它还针对显式、两端均包含的 surface 范围暴露 `compactRegion(...)`。每个后端都使用包导出的 `COMPACT_CHECKPOINT_SOURCE` 标记其替换用的 `user/message`;消费方调用 `isCompactCheckpointSource()`,而不是把检查点识别逻辑耦合到某一个后端。实现必须把传入的 signal 转发给摘要流程。该 seam 不拥有计价 API:单例 [`ctx.tokenMeter`](token-meter.md) 直接拥有估算与回放,而 `dsh-compact-basic` 拥有保留策略、事件排序、按路由执行的摘要调用及其配置。 + +压力压缩在串行 `agent/post-step` 中运行:此时成功的 assistant 输出、工具结果、缓冲上下文和 steering(中途引导)已持久化,但 `step/end` 尚未发生。一旦压力或规范化溢出满足条件,compact-basic 会在选择范围前调用可选的 [`ctx.toolResultPrune`](../../packages/compact/compact-tool-result-prune/README.md),再通过 `ctx.tokenMeter` 重新测量,并且可以在不生成摘要的情况下推进 surface。失败请求的恢复在失败的步骤关闭后通过 `agent/request-error` 运行;仅当 surface replacement generation 前进时才批准一个带新编号的步骤重试,即便后续摘要工作在剪枝后抛异常亦如此;取消仍然优先。区域边界保持工具调用/结果配对,但不保持整个轮次,因此一个过大轮次中较早关闭的步骤可以被压缩。`dsh-compact-basic` 拥有阈值、保留尾部策略、溢出上限与失败处理。 + +该 seam 导出 `toolPairingBalancedBefore(session, seq)` 与 `toolPairingBalancedAfter(session, seq)`,用于这些边缘检查。两者都会验证当前 surface 成员关系,并拒绝缺失的 seq 与遗留结果;其缓存语义由[包契约](../../packages/compact/compact/README.md#tool-pairing-boundaries)规定。 + +## 工具结果剪枝产出 + +可选的工具结果剪枝服务会报告每次持久内容替换以及 Unicode code point 的总减少量。其公开结果类型位于 [`compact-tool-result-prune/src/types.ts`](../../packages/compact/compact-tool-result-prune/src/types.ts)。 + +```ts type-equiv +/** Provenance and size accounting for one landed surface replacement. */ +interface PrunedEntry { + /** Full-fidelity tool-result event shadowed by the replacement. */ + readonly originalSeq: number + /** Newly appended pruned tool-result event. */ + readonly replacementSeq: number + /** Tool call shared by the original and replacement. */ + readonly callId: CallId + /** Original text size in Unicode code points. */ + readonly charsBefore: number + /** Replacement text size in Unicode code points. */ + readonly charsAfter: number +} +``` + +```ts type-equiv +/** Aggregate outcome of one stable-surface pruning pass. */ +interface PruneResult { + /** Replacements in the snapshotted surface order. */ + readonly pruned: readonly PrunedEntry[] + /** Total Unicode code points removed across replacements. */ + readonly charsRemoved: number +} +``` diff --git a/docs/core-data-structures/core.i18n.yaml b/docs/core-data-structures/core.i18n.yaml new file mode 100644 index 0000000000..47310dd09b --- /dev/null +++ b/docs/core-data-structures/core.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +core.md: 781267cccdb5bbda33e5be6a9e807fdbe47dbc83 +core.zh.md: d0f67983b98b0cf679a8e599a5f8ab3c64490dd0 diff --git a/docs/core-data-structures/core.md b/docs/core-data-structures/core.md index 86809ddc8b..781267cccd 100644 --- a/docs/core-data-structures/core.md +++ b/docs/core-data-structures/core.md @@ -1,5 +1,7 @@ # Core Data Structures +English | [中文](core.zh.md) + This folder catalogs the **data structures** of the DeepSeek Harness — what each core type represents, its literal shape, and where the full detail lives. It complements [architecture.md](../architecture.md), which describes *behavior* (the service map, the session/turn/step lifecycle, the event taxonomy); this page describes the *vocabulary* that behavior moves around. ## What counts as "core" @@ -163,6 +165,8 @@ Adapters emit a raw **chunk** protocol; the loop logs the chunks (replay fidelit The full union, the adapter contract (usage-before-finish, raw-JSON tool arguments, the two sanctioned error paths), and `BlockAssembler` live on **[llm-streaming.md](llm-streaming.md)**. +<a id="the-model-request-and-result"></a> + ## The model request One model call is a fully-assembled `GenerateOptions`. The adapter answers with a raw `StreamChunk` stream; the consumer assembles it with `BlockAssembler` (see [llm-streaming.md](llm-streaming.md)). @@ -323,7 +327,7 @@ Source: [`packages/core/session/src/types.ts`](../../packages/core/session/src/t * * The {@link sourceEventSeqs} and {@link surfaceOp} fields are conditional: * they only exist on {@link SurfaceEventType} variants (`user/message`, - * `assistant/message`, `tool/result`, `context/message`, `steering/message`). + * `assistant/message`, `tool/result`, `steering/message`). * Non-surface events (boundary markers, chunks, usage, errors) never carry * surface metadata — the compiler enforces this at `Session.append()` * call sites. @@ -351,7 +355,7 @@ type SessionEvent<T extends SessionEventType = SessionEventType> = { }[T] ``` -The fourteen event variants (`turn/start`, `turn/end`, `step/start`, `step/end`, `user/message`, `prompt/blocked`, `context/message`, `assistant/chunk`, `assistant/message`, `tool/call`, `tool/result`, `steering/message`, `todo/write`, `request/header`), the `deriveMessages()` projection rules, the `TurnTrigger`/`TurnEndReason` reasons, and the turn-enclosure invariant are on **[session.md](session.md)**. How the log is made durable — the `SessionPersistence` seam, JSONL/SQLite backends, the `session/flush` checkpoint, crash recovery, and `SessionHeader` — is on **[persistence.md](persistence.md)**. +The thirteen event variants (`turn/start`, `turn/end`, `step/start`, `step/end`, `user/message`, `prompt/blocked`, `assistant/chunk`, `assistant/message`, `tool/call`, `tool/result`, `steering/message`, `todo/write`, `request/header`), the `deriveMessages()` projection rules, the `TurnTrigger`/`TurnEndReason` reasons, and the turn-enclosure invariant are on **[session.md](session.md)**. How the log is made durable — the `SessionPersistence` seam, JSONL/SQLite backends, the `session/flush` checkpoint, crash recovery, and `SessionHeader` — is on **[persistence.md](persistence.md)**. ## The agent handle @@ -361,8 +365,9 @@ Source: [`packages/core/agent/src/types.ts`](../../packages/core/agent/src/types ```ts type-equiv /** - * Message options. An omitted source attests direct human input as `{ kind: 'user' }` - * and may authorize policy consumers, so non-human producers must label their content. + * Options for {@link Agent.followup}, {@link Agent.queue}, and {@link Agent.steer}. + * An omitted source attests direct human input as `{ kind: 'user' }` and may + * authorize policy consumers, so non-human producers must label their content. */ interface SendOptions { source?: MessageSource @@ -372,19 +377,90 @@ interface SendOptions { * records them directly at its next checkpoint. */ contexts?: HookContext[] + /** Opaque JSON state retained on the durable message but hidden from the model. */ + meta?: JsonValue } ``` -`InjectOptions` accepts ordinary message attribution and durable model-hidden JSON metadata. Attached contexts belong only to queued or steering input, so synthetic injection cannot accept them: - ```ts type-equiv /** Options specific to durable synthetic context injection. */ -interface InjectOptions extends Omit<SendOptions, 'contexts'> { - /** Opaque JSON state retained in the session event but hidden from the model. */ +interface InjectOptions { + /** Defaults to `{ kind: 'plugin', plugin: '' }`; non-human producers should identify themselves. */ + source?: MessageSource + /** Opaque JSON state retained on the durable message but hidden from the model. */ meta?: JsonValue } ``` +The advanced acceptance form makes every default explicit and rules out attached contexts on injection: + +```ts type-equiv +/** + * Fully specified input for {@link Agent.send}. Unlike the intent-named + * helpers, this form applies no defaults: callers provide content, source, + * contexts, metadata (including explicit `undefined`), target, and wakeup. + * The union excludes attached contexts from non-waking next-step injection. + */ +type ResolvedAgentInput = { + content: ContentBlock[] + source: MessageSource + meta: JsonValue | undefined +} & ( + | { target: 'next-turn'; wakeup: boolean; contexts: HookContext[] } + | { target: 'next-step'; wakeup: true; contexts: HookContext[] } + | { target: 'next-step'; wakeup: false; contexts: [] } +) +``` + +FIFO delivery methods return an opaque `AgentMessageId`, stable across that message's `agent/inbox/*` events. Injection returns an id but bypasses those events: + +```ts type-equiv +/** + * Opaque id assigned to one accepted agent input. FIFO inputs carry the same id + * on their `agent/inbox/*` events; injection bypasses those events. + */ +type AgentMessageId = Branded<'AgentMessageId'> +``` + +The `agent/inbox/*` live events carry one accepted message; injection bypasses the FIFOs and never appears on them: + +```ts type-equiv +/** + * One accepted FIFO message, carried by the `agent/inbox/*` live events. `id` + * is the value returned by the accepting helper or {@link Agent.send}, + * stable across this message's enqueue, dequeue, and discard events. Source + * defaults, when applicable, are already applied, so these are the exact values + * the item was accepted with. + * `steering` is true for an item drained between steps; otherwise it is claimed + * at a turn boundary. `SendOptions.meta` is intentionally omitted: it is durable + * model-hidden state that lands on the eventual `user/message`/ + * `steering/message`, not live-event routing data. + */ +interface AgentMessage { + /** The id returned by the accepting helper or {@link Agent.send}. */ + id: AgentMessageId + content: ContentBlock[] + source: MessageSource + contexts: HookContext[] + /** Whether the item joined the steering FIFO rather than the queued FIFO. */ + steering: boolean + /** Whether the item wakes the driver or requests another step. */ + wakeup: boolean +} +``` + +```ts type-equiv +/** Options for {@link Agent.cancel}. */ +interface CancelOptions { + /** + * Preserve queued and steering inbox items instead of discarding them. The + * active turn is still aborted, but un-started and pending work survives for a + * later turn and no `agent/inbox/discard` fires. + */ + keepInbox?: boolean +} +``` + ```ts type-equiv /** Stable runtime cause accepted by {@link Agent.cancel}. */ type AgentCancelCause = @@ -392,65 +468,103 @@ type AgentCancelCause = | { readonly kind: 'parent' } ``` +The structural `Agent` interface exposes four intent helpers plus the fully resolved acceptance method. The concrete driver implements the matrix once, and each helper supplies its fixed routing and defaults. + ```ts type-equiv /** Public agent handle; its concrete implementation is internal to `@deepseek-ai/dsh-agent-loop`. */ interface Agent { /** The single identity shared with {@link session}. */ readonly id: SessionId + /** The provider route and model this agent's requests use. */ readonly options: AgentOptions + /** The live session this agent drives; its log is the durable source of truth. */ readonly session: Session + /** The current lifecycle state, mirrored on every `agent/status` transition. */ readonly status: AgentStatus /** Agent-scoped context; its contributions are agent-local, unwind on disposal, and reject registration afterward. */ readonly ctx: Context /** - * Queue one detached, frozen lossless-JSON item. If claimed, it is the sole - * ordinary message in its FIFO-ordered turn; the next claimed item waits for - * that turn's checkpoint. - * Attached contexts share the same snapshot and ownership boundary. Invalid - * input throws synchronously before notification or enqueue. + * Queue an ordinary message as its own FIFO-ordered turn and wake the driver. + * Content, resolved source, and attached contexts are detached, validated, + * and frozen together; invalid input throws synchronously before notification + * or enqueue. + * @param content - the prompt content blocks. + * @param options - source, attached contexts, and durable model-hidden meta. + * @returns the accepted message's {@link AgentMessageId}, stable across its `agent/inbox/*` events. */ - send(content: ContentBlock[], options?: SendOptions): void + followup(content: ContentBlock[], options?: SendOptions): AgentMessageId /** - * Submit steering while the agent is `running`. An open turn records it at - * the next steering checkpoint before a request or continuation decision; - * policy may stop before another step. After turn close and its checkpoint, - * any remainder is queued for a later turn; terminal `agent/turn-stop`, - * cancellation, or disposal may discard it. Uses the same synchronous - * snapshot-and-validation boundary as {@link send}; when idle, delegates to it. + * Queue an ordinary message without waking an idle driver. The item retains + * FIFO order and is claimed only after another input wakes the driver. A lone + * queued item leaves `whenIdle()` resolved. + * @param content - the prompt content blocks. + * @param options - source, attached contexts, and durable model-hidden meta. + * @returns the accepted message's {@link AgentMessageId}, stable across its `agent/inbox/*` events. */ - steer(content: ContentBlock[], options?: SendOptions): void + queue(content: ContentBlock[], options?: SendOptions): AgentMessageId + + /** + * Submit steering into the running turn and request another step. An open turn + * records it at the next steering checkpoint before a request or continuation + * decision; policy may stop before another step. After turn close and its + * checkpoint, any remainder is queued for a later turn; terminal + * `agent/turn-stop`, cancellation, or disposal may discard it. Idle steering + * becomes a waking ordinary turn. + * @param content - the steering content blocks. + * @param options - source, attached contexts, and durable model-hidden meta. + * @returns the accepted message's {@link AgentMessageId}, stable across its `agent/inbox/*` events. + */ + steer(content: ContentBlock[], options?: SendOptions): AgentMessageId /** * Append detached model-facing context without running the model. An open-turn * injection joins at the current log position unless the current tool batch is - * executing; then it waits FIFO until that batch settles and drains before turn - * close even when interrupted. Idle injection uses a one-shot turn and durability - * checkpoint. Disposal awaits idle checkpoints; flush failures report through `agent/error`. + * executing; then it waits FIFO until that batch settles and drains before + * turn close even when interrupted. Idle injection uses a one-shot turn and + * durability checkpoint. Disposal awaits idle checkpoints; flush failures + * report through `agent/error`. An omitted source defaults to + * `{ kind: 'plugin', plugin: '' }`. + * @param content - the injected context content blocks. + * @param options - source and durable model-hidden meta. + * @returns the accepted injection's {@link AgentMessageId}; injection emits no `agent/inbox/*` events. */ - inject(content: ContentBlock[], options?: InjectOptions): void + inject(content: ContentBlock[], options?: InjectOptions): AgentMessageId /** - * Clear all queued and steering work, including items waiting to start, and - * abort the active turn. An effective call first emits - * `agent/cancel-requested` with the resolved typed cause. The first cause wins - * for the active turn, and `whenIdle()` resolves after cancellation reaches - * quiescence. Omission means `{ kind: 'user' }`. Idle cancellation is a no-op - * and does not arm later work. The active turn snapshots and freezes the cause. - * @param cause - the stable caller intent carried by the current turn signal. + * Accept one fully specified input through the same snapshot and routing path + * as the four intent-named helpers. `next-turn` targets the ordinary FIFO; + * `next-step`/wakeup targets steering (falling back to an ordinary waking turn + * while idle); and `next-step` without wakeup injects durable context without + * running the model. Every field is mandatory and no source or routing default + * is applied. Invalid input throws synchronously before notification, enqueue, + * or append. + * @param input - the resolved content, attribution, context, metadata, and routing facts. + * @returns the accepted input's {@link AgentMessageId}, carried by FIFO lifecycle events when applicable. */ - cancel(cause?: AgentCancelCause): void + send(input: ResolvedAgentInput): AgentMessageId + + /** + * Clear queued and steering work — unless `keepInbox` — and abort the active + * turn. An effective call first emits `agent/cancel-requested` with the + * resolved typed cause. The first cause wins for the active turn, and + * `whenIdle()` resolves after cancellation reaches quiescence. Omitted cause + * means `{ kind: 'user' }`. Idle cancellation is a no-op and does not arm + * later work. The active turn snapshots and freezes the cause. + * @param cause - the stable caller intent carried by the current turn signal. + * @param options - cancellation options; `keepInbox` preserves pending work. + */ + cancel(cause?: AgentCancelCause, options?: CancelOptions): void /** Resolve at idle quiescence; disposal waits for driver exit rather than only the status transition. */ whenIdle(): Promise<void> - } ``` `AgentStatus` is `'idle' | 'running' | 'disposed'`, and `SessionId` is branded. `running` describes the driver-wide drain interval, which can span turn close, its durability checkpoint, and consecutive queued turns; it does not prove a turn is still open. `AgentOptions` is merge-extensible: core declares `provider?` and `model?` (dispatch requires both after `agent/request`). Persona belongs to `dsh-system-prompt`: an agent-scoped `deployment:persona` may shadow the global default. -The cause is a TypeScript-enforced same-process input. An active holder copies its discriminant into the runtime-only `AbortSignal.reason`; it is retired before `turn/end` publication. `agentInterruptReasonOf(signal)` recognizes `user`, `parent`, and lifecycle-only `disposed` without consulting ambient initiator state. Durable `turn/end` retains the coarse `{ kind: 'aborted' }` outcome; request provenance would require a separate durable event rather than overloading the terminal result. +The cause is a TypeScript-enforced same-process input. An active `TurnCancellation` holder copies its discriminant into the runtime-only `AbortSignal.reason` and is retired before `turn/end` publication; the frozen `AbortSignal.reason` remains readable after that retirement. `agentInterruptReasonOf(signal)` recognizes `user`, `parent`, and lifecycle-only `disposed` without consulting ambient initiator state. Durable `turn/end` retains the coarse `{ kind: 'aborted' }` outcome; request provenance would require a separate durable event rather than overloading the terminal result. The [event taxonomy](../architecture.md#event) owns the `agent/*` lifecycle, checkpoint, and waterfall contracts. Turn and step boundaries are durable session events rather than agent emits. @@ -460,7 +574,7 @@ The process-local initiator carried by `ctx.agents` is the exact `Agent` above, ## Interception decisions -Each `agent/*` interception waterfall returns a small, seam-specific typed union — the unified Decision idiom (the tool seams' `PreToolDecision`/`PostToolDecision` in [tools.md](tools.md) follow the same shape). A CC/Codex hook bridge maps its `permissionDecision`/`decision`/`continue`/`additionalContext` fields onto these; a native plugin returns them directly. Prompt and post-tool decisions share one model-facing context shape, `HookContext`, which carries a REQUIRED `source` (a missing source would default to `{kind:'user'}` and mislabel plugin context as a user prompt). Its `content` reaches the model verbatim as user-role input, while JSON `meta` persists plugin state without exposing it to the model. Absent or `separate` placement becomes `context/message`; `prompt-prefix` placement is available to prompt and steering inbox attachments and bakes the context before the effective request in the same message. Both decisions carry `additionalContexts[]` so every entry preserves its own provenance, metadata, and placement. Continuation reasons are steering messages instead and deliberately use the narrower content/source shape. +Each `agent/*` interception waterfall returns a small, seam-specific typed union — the unified Decision idiom (the tool seams' `PreToolDecision`/`PostToolDecision` in [tools.md](tools.md) follow the same shape). A CC/Codex hook bridge maps its `permissionDecision`/`decision`/`continue`/`additionalContext` fields onto these; a native plugin returns them directly. Prompt and post-tool decisions share one model-facing context shape, `HookContext`, which carries a REQUIRED `source` (a missing source would default to `{kind:'user'}` and mislabel plugin context as a user prompt). Its `content` reaches the model verbatim as user-role input, while JSON `meta` persists plugin state without exposing it to the model. Absent or `separate` placement becomes an injected `user/message` (plugin/goal source); `prompt-prefix` placement is available to prompt and steering inbox attachments and bakes the context before the effective request in the same message. Both decisions carry `additionalContexts[]` so every entry preserves its own provenance, metadata, and placement. Continuation reasons are steering messages instead and deliberately use the narrower content/source shape. Source: [`packages/core/agent/src/types.ts`](../../packages/core/agent/src/types.ts) @@ -470,8 +584,8 @@ interface HookContext { content: ContentBlock[] source: MessageSource /** - * Model placement. Absent or `separate` records an independent - * `context/message`; `prompt-prefix` prepends this context and a stable + * Model placement. Absent or `separate` records an independent injected + * `user/message`; `prompt-prefix` prepends this context and a stable * request delimiter to the same user-role message as its attached prompt. */ placement?: 'separate' | 'prompt-prefix' diff --git a/docs/core-data-structures/core.zh.md b/docs/core-data-structures/core.zh.md new file mode 100644 index 0000000000..d0f67983b9 --- /dev/null +++ b/docs/core-data-structures/core.zh.md @@ -0,0 +1,671 @@ +# 核心数据结构 + +[English](core.md) | 中文 + +本目录编目 DeepSeek Harness 的**数据结构**:每个核心类型代表什么、它的字面形状,以及完整细节在哪里。它与 [architecture.md](../architecture.md) 互补——后者描述*行为*(服务映射、会话/轮次/步骤生命周期、事件分类体系);本页描述行为所操作的*词汇*。 + +## 什么算"核心" + +harness 是一个微内核:一个极小的核心加上众多插件。大多数类型属于某一个插件或某一项能力。但有少数类型构成**主干**——agent loop(智能体循环)及其事件在*每一个*轮次中使用的语言,无论加载了哪些可选插件。这些就是"核心"。 + +精确地说,一个数据结构是**核心**的,当且仅当满足以下条件之一: + +1. 它流经 agent loop 主干——循环在每个轮次中持有、派生、流式输出或记录它(`Message`、`StreamChunk`、`SessionEvent`、`Agent` 句柄本身),与当前加载了哪些插件无关;**或者** +2. 它是插件作者面向某条流水线编写的代表性类型——`ToolDefinition`(每个工具*是什么*)。 + +其他一切都记录在**子页面**上,而非本页。划线的规则是:*你编写、持有或接收的类型是核心;为它提供类型推导、渲染或持久化的机制是子页面细节*。因此 `ToolDefinition` 是核心,但为它提供类型推导的 `ValueSchemaSpec`/`ParameterSchemaSpec` 机制、为它提供渲染意图的 `ToolCallView`/`ToolResultView` 词汇,以及存储事件日志的 `SessionPersistence` seam 都不是——它们分别在下列子页面中。 + +| 子页面 | 负责内容 | +|---|---| +| [llm-streaming.md](llm-streaming.md) | `StreamChunk` 协议格式(wire format)+ 适配器契约(adapter contract)、`BlockAssembler`、`LlmAdapter` seam | +| [token-meter.md](token-meter.md) | 不可变的标量与位置回放度量,附带已消费日志修订号 | +| [scope.md](scope.md) | 作用域注册标识、dispatch 载体,以及拥有的 `Scope` 上下文 | +| [goal.md](goal.md) | 持久 goal 标识、生命周期快照、激活、变更记录与 Round 归属 | +| [commands.md](commands.md) | 人类命令 seam:定义、适配器发现、直接调用、结果与解析视图 | +| [session.md](session.md) | 完整的 `SessionEventMap` 变体目录、`TurnTrigger`/`TurnEndReason`、`deriveMessages()`、轮次封闭不变式 | +| [persistence.md](persistence.md) | 持久性 seam:`SessionPersistence`、JSONL + SQLite 后端、`session/flush`、崩溃恢复、`SessionHeader` | +| [session-query.md](session-query.md) | 逻辑记录、有界精确事件读取、关系追踪、语义筛选器/文档与全文检索结果页 | +| [session-title.md](session-title.md) | 持久标题快照、来源 provenance 与异步提供方契约 | +| [system-prompt.md](system-prompt.md) | 逐次组装的上下文、工具提供方结果、提示词段落与协作式组装 | +| [tools.md](tools.md) | `ToolDefinition` 完整字段、schema DSL、`ToolExecution`/`ToolResult`、工具展示 UI 类型,以及受保护的执行流水线 | +| [user-interaction.md](user-interaction.md) | UI 支持的人工问答 seam:`AskUserQuestionRequest`、answer/options 词汇、提供方 API、错误分类体系 | +| [approval.md](approval.md) | 一次性用户审批 seam:`ApprovalRequest`、`ApprovalOutcome`、逐会话策略、审计与 answerer 契约 | +| [bash.md](bash.md) | bash 执行器 seam:`BashExecRequest`/`Spec`、`BashRunResult`、后台 `BashProcess` 句柄 | +| [pty.md](pty.md) | 持久化终端 ID、后端/会话契约、发送就绪状态、有界读取与 owner 可见快照 | +| [sandbox.md](sandbox.md) | 每会话策略解析与进程约束 seam:文件效果模式、执行/提供方策略、`ConfinedArgv`、强制执行与故障关闭错误 | +| [code-runtime.md](code-runtime.md) | 代码执行 seam:`CodeRunRequest`/`Result`、绑定命名空间、捕获日志、`CodeRunFailure` 分类体系 | +| [filesystem.md](filesystem.md) | 文件系统 seam:`FsTarget`、读/写/编辑结果、观测到的文件状态、`FsErrorCode` | +| [lsp.md](lsp.md) | LSP 导航 seam:`LspQueryRequest`/`Result`、`LspProvider`/`Service`、四种操作、`LspError` | +| [skills.md](skills.md) | skill(技能)服务:发现优先级、`SkillSummary`/`SkillDefinition`、会话前缀目录、面向模型的 `skill` 加载 | +| [compaction.md](compaction.md) | 压缩(compaction)seam:`compact/*` 会话事件、`CompactionResult`、`CompactService` 接口 | +| [subagent.md](subagent.md) | subagent seam:命名提供方注册表、`SubagentStartRequest`/`Result`/`Run`、启动时与运行时能力拆分 | +| [web.md](web.md) | Web 访问 seam:`WebSearchRequest`/`Result`、`WebFetchRequest`/`Result`、`WebFetchBody`、提供方可用性、`WebError` | +| [spill.md](spill.md) | spill 存储 seam:`SaveTextSpill`、`SpillOwner`/`SpillSource`、`SpillRef`、品牌类型 `SpillLocator` | +| [workflow.md](workflow.md) | 工作流 seam:`WorkflowStartRequest`、`WorkflowMeta`、`WorkflowRun`/`Result`、`workflow/*` 事件载荷、`WorkflowError` 致命性 | + +> 这些页面上的类型声明及其 JSDoc 与源码等价,并由 `pnpm run verify-type-equiv` 检查漂移(见 [development.md](../development.md#documenting-types-verbatim-ts-type-equiv))。普通块保留完整声明;`public-api` 块保留去除实现体的公开 class 声明。Cordis 服务使用生成的[服务目录](../cordis-catalog/services.md)。 + +<a id="the-map--derived-union-pattern"></a> + +## `…Map → derived-union` 模式 + +harness 中几乎所有可扩展的和类型都遵循同一形状:一个以判别标签为键的接口(`…Map`),联合类型由 `keyof` 派生。插件通过**声明合并**添加变体——无需修改拥有该类型的包(package)。 + +```ts ignore-check +// The pattern, schematically: +interface ThingMap { + 'a': { kind: 'a'; /* … */ } + 'b': { kind: 'b'; /* … */ } +} +type ThingKind = keyof ThingMap // 'a' | 'b' +type Thing = ThingMap[keyof ThingMap] // the discriminated union + +// A plugin extends it without touching the source package: +declare module '@deepseek-ai/dsh-llm' { + interface ThingMap { + 'c': { kind: 'c'; /* … */ } + } +} +``` + +六个规范 map 使用此模式;插件作者扩展它们: + +| Map | 包 | 派生 | 目录 | +|---|---|---|---| +| `ContentBlockMap` | dsh-llm | `ContentBlock` | [下文](#content-blocks-and-messages) | +| `MessageSourceMap` | dsh-llm | `MessageSource` | [下文](#content-blocks-and-messages) | +| `FinishReasonMap` | dsh-llm | `FinishReason` | [下文](#the-model-request-and-result) | +| `TurnTriggerMap` | dsh-session | `TurnTrigger` | [session.md](session.md) | +| `TurnEndReasonMap` | dsh-session | `TurnEndReason` | [session.md](session.md) | +| `SessionEventMap` | dsh-session | `SessionEvent` | [session.md](session.md) | + +消费方最常 `switch` 的两个大型判别联合类型是:**`StreamChunk`**(流式协议)和 **`SessionEvent`**(日志条目)。按仓库约定,对标签做 `switch`——不要链式 `if`——这样每个分支都能窄化类型,拼错的标签会编译失败。 + +<a id="branded-ids"></a> + +## 品牌化 ID + +跨越包边界的 ID 都经过**品牌化**——结构上是字符串,但在类型层面不可互换(不能把 `SessionId` 传给需要 `CallId` 的位置)。每种类型通过各自的工厂构造;比较、日志记录和 JSON 行为与普通字符串相同。 + +`Branded<B>` 原语位于独立的纯类型包 [dsh-brand](../../packages/util/brand) 中(没有运行时代码,也不依赖 Harness 包),因此任何包都能品牌化其拥有的 id,而无需依赖无关的能力包。 + +源码:[`packages/util/brand/src/index.ts`](../../packages/util/brand/src/index.ts) + +```ts type-equiv +/** A string carrying a compile-time-only brand `B`. */ +type Branded<B extends string> = string & { readonly [BRAND]: B } +``` + +两个核心 ID 是 `CallId`(关联工具调用及其结果;dsh-llm)和 `SessionId`(活跃 agent 与持久会话共享的标识;dsh-session)。能力包也会品牌化各自的 id,例如 [tasks.md](tasks.md) 中的 `TaskId`。 + +<a id="content-blocks-and-messages"></a> + +## 内容块与消息 + +一段对话由 `Message` 组成;一条消息是一个类型化**内容块**的数组。块的联合类型从 `ContentBlockMap` 派生。 + +源码:[`packages/llm/llm/src/types.ts`](../../packages/llm/llm/src/types.ts) + +```ts type-equiv +/** + * Merge-extensible content blocks keyed by `type`. New core blocks must land + * with adapter, UI, and compaction support. + */ +interface ContentBlockMap { + 'text': TextBlock + 'reasoning': ReasoningBlock + 'tool-call': ToolCallBlock + 'tool-result': ToolResultBlock +} +``` + +各块接口(完整字段见源码):`TextBlock`(`text`)、`ReasoningBlock`(thinking,区别于可见文本)、`ToolCallBlock`(`id: CallId`、`name`、原始 JSON `arguments`)、`ToolResultBlock`(`toolCallId`、嵌套 `content: ContentBlock[]`、`isError?`)。`ContentBlock = ContentBlockMap[ContentBlockType]`。核心集仅限于每条交付路径都尊重的块——多模态内容(图像、音频等)没有核心块类型;需要的功能通过可合并扩展的 map 添加,同时提供适配器/UI/压缩支持。 + +`Message` 由角色和块组成。由循环派生的 assistant 消息携带其持久提供方/模型标识,以及可选的适配器私有回放元数据: + +```ts type-equiv +/** Provider ownership and adapter-private replay data for an assistant message. */ +interface AssistantProvenance { + /** Provider route that produced the message. */ + provider: string + /** Provider model id that produced the message. */ + model: string + /** + * Lossless-JSON adapter state needed to replay the provider response. + * `LlmService` exposes it to a target adapter only when that adapter instance + * currently owns both this historical provider and the target provider. + */ + replayState?: unknown +} +``` + +```ts type-equiv +/** + * A single message in a conversation history. Loop-derived assistant messages + * always carry provenance; callers may omit it on hand-built foreign history. + */ +interface Message { + role: 'system' | 'user' | 'assistant' + content: ContentBlock[] + /** Present only on assistant messages produced by a routed adapter. */ + provenance?: AssistantProvenance +} +``` + +消息来源本身也是一个可合并扩展的和类型: + +```ts type-equiv +/** + * Where a message (or injected content) came from. + * Merge-extensible sum type — plugins add their own `kind`s. + */ +interface MessageSourceMap { + user: { kind: 'user' } + plugin: { kind: 'plugin'; plugin: string } +} +``` + +## 流式输出 + +适配器发出原始**分片**协议;循环记录分片(回放保真度),同时将同一批分片送入 `BlockAssembler` 以重建块和消息。`StreamChunk` 是基于 `type` 的封闭判别联合——`block-start`、`text-delta`、`reasoning-delta`、`tool-call-delta`、`block-end`、`usage`、`finish`。 + +完整联合类型、适配器契约(usage-before-finish、原始 JSON 工具参数、两条认可的错误路径)和 `BlockAssembler` 在 **[llm-streaming.md](llm-streaming.md)** 中。 + +<a id="the-model-request-and-result"></a> + +## 模型请求 + +一次模型调用是一个完全组装好的 `GenerateOptions`。适配器以原始 `StreamChunk` 流作答;消费方用 `BlockAssembler` 组装它(见 [llm-streaming.md](llm-streaming.md))。 + +源码:[`packages/llm/llm/src/types.ts`](../../packages/llm/llm/src/types.ts) + +提供方与模型发现使用小型、提供方无关的描述符。模型目录仅供参考:路由仍以已注册提供方为键,适配器也可以接受未列出的模型 id。 + +```ts type-equiv +/** Display metadata for one registered provider route. */ +interface LlmProviderInfo { + /** Provider route key used by {@link GenerateOptions.provider}. */ + id: string + /** Human-readable provider name for selectors and diagnostics. */ + name: string +} +``` + +```ts type-equiv +/** One adapter-discovered model; catalog membership is advisory, not request validation. */ +interface LlmModelInfo { + /** Provider route that owns this model entry. */ + provider: string + /** Model id passed to {@link GenerateOptions.model}. */ + id: string + /** Human-readable model name for selectors. */ + name: string + /** Optional user-facing distinction from otherwise similar models. */ + description?: string +} +``` + +对正确性敏感的模型容量与参考目录分开查询,并归服务该确切路由的适配器所有。 + +```ts type-equiv +/** Provider-owned context capacity for one exact provider/model route. */ +interface LlmModelContext { + /** Maximum combined request and response context in tokens. */ + contextWindow: number +} +``` + +```ts type-equiv +/** A single model request, fully assembled. */ +interface GenerateOptions { + /** Registered provider route selecting the adapter instance. */ + provider: string + model: string + /** + * Ordered conversation messages, exactly as the provider sees them (after + * the `system` slot). A loop-built request assembles them as + * `EpochHeader.messagePrefix` + the derived history (dsh-agent-loop); a + * hand-built one-shot passes any list. + */ + messages: Message[] + /** System prompt text (adapters map to the provider's system slot). */ + system?: string + /** Tool schemas (adapters map to the provider's `tools` field). */ + tools?: ToolSchema[] + temperature?: number + maxTokens?: number + /** + * Stop sequences: generation halts as soon as the model produces any one of + * these strings (adapters map to the provider's stop field, e.g. OpenAI + * `stop`). The stop string itself is not included in the output. + */ + stop?: string[] + signal?: AbortSignal + /** + * Session identity stamped by the loop for listener routing. Adapters ignore + * it; replay uses it to keep concurrent parent and child cursors independent. + */ + sessionId?: Branded<'SessionId'> + /** + * Provider-neutral classification for an auxiliary model call. Adapters may + * map the purpose to model-hidden transport metadata or purpose-specific + * generation policy. Ordinary conversation requests leave it unset. + */ + purpose?: 'compaction' | 'session-title' +} +``` + +模型响应为何停止由可合并扩展的原因表示。提供方终态失败携带流式契约的 [`LlmFailure`](llm-streaming.md#llmfailure): + +```ts type-equiv +/** + * Why a model response stopped. + * Merge-extensible so adapters can surface provider-specific reasons. + */ +interface FinishReasonMap { + 'stop': { kind: 'stop' } + 'tool-calls': { kind: 'tool-calls' } + 'max-tokens': { kind: 'max-tokens' } + 'aborted': { kind: 'aborted'; failure: LlmFailure } + 'error': { kind: 'error'; failure: LlmFailure } +} +``` + +`FinishReason = FinishReasonMap[keyof FinishReasonMap]`。`TokenUsage`(逐调用计量,含不相交的缓存字段)详见 [llm-streaming.md](llm-streaming.md)。 + +`GenerateOptions.tools` 携带 `ToolSchema`——工具的 JSON Schema 描述,发送给模型。它声明在 dsh-llm(而非 dsh-tools)中,正是因为它是循环每一步组装请求的一部分: + +```ts type-equiv +/** + * JSON-schema description of a tool, as sent to the model. + * + * Declared here (not in dsh-tools) because it is part of {@link GenerateOptions}; + * dsh-tools' ToolDefinition and dsh-system-prompt's PromptAssembly both import + * it from this package. + */ +interface ToolSchema { + name: string + description: string + /** JSON Schema object for the arguments. */ + parameters: Record<string, unknown> +} +``` + +面向模型的 `ToolSchema` 是协议格式;产出它的已注册 `ToolDefinition`(schema + `execute`)在 [tools.md](tools.md) 中。 + +### 请求信封:`LlmCallConfig` 与记录的 header + +循环从已记录状态构建每个请求。`EpochHeader` 通过完整的 `request/header` 快照记录调用配置、渲染后的提示词、权威返回工具顺序(由 `toolOrder` 配置;未配置时按字典序)以及会话前缀。结合派生历史,请求便可由会话日志重建。见 [session.md](session.md#the-request-header-event-requestheader) 与[可重建性 Agent Note(agent 决策记录)](../../.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.md)。 + +`agent/request` 接收冻结的调用配置种子,并可返回替代值以切换提供方、模型或采样参数。`agent/session-prefix` 为每个循环实例组合一次仅用于请求的 prefix 消息,header 记录实际使用的确切结果。到达 `llm/stream` 的请求会被深度冻结,因此变更会抛异常;请求还携带进程本地循环标识,使观察者不会把单独记录的冻结辅助调用误认成对话请求。 + +在协议格式上,循环构建的请求按此顺序读取:`system` 槽位(渲染后的提示词组装)→ `messagePrefix`(冻结的会话前缀)→ 派生历史——边界快照,其尾部在轮次首步是最新的 `user/message`,在后续步骤是上一步的工具结果。前缀从不进入派生历史;它的持久记录是 header 事件,开发不变式针对每个循环构建的请求精确重算此等式。 + +FIXME(call-config-shape):重新审视此类型的精确定义——出于缓存目的,哪些字段确实属于 epoch 层级(`model` 肯定属于;采样标量目前出于谨慎放在这里),以及适配器需要时,提供方特有的额外项(推理选项、额外 body 参数)应归属何处。 + +```ts type-equiv +/** + * Provider + model + sampling scalars of one conversation's requests. Every field maps + * 1:1 onto the same-named `GenerateOptions` field; the loop builds requests + * from the logged header rather than accepting these per call. + */ +interface LlmCallConfig { + provider: string + model: string + temperature?: number + maxTokens?: number + stop?: string[] +} +``` + +## 会话 + +`Session` 是一份类型化 `SessionEvent` 的**仅追加日志**——唯一的真源。LLM(大语言模型)消息历史从日志*派生*(`deriveMessages()`),而非单独存储。事件词汇从 `SessionEventMap` 派生: + +源码:[`packages/core/session/src/types.ts`](../../packages/core/session/src/types.ts) + +```ts type-equiv +/** + * One immutable entry in the session log. + * + * A proper discriminated union over `type` (not independent `type`/`data` + * unions), so `switch (event.type)` narrows `event.data` without casts. + * + * The {@link sourceEventSeqs} and {@link surfaceOp} fields are conditional: + * they only exist on {@link SurfaceEventType} variants (`user/message`, + * `assistant/message`, `tool/result`, `steering/message`). + * Non-surface events (boundary markers, chunks, usage, errors) never carry + * surface metadata — the compiler enforces this at `Session.append()` + * call sites. + */ +type SessionEvent<T extends SessionEventType = SessionEventType> = { + [K in SessionEventType]: { + type: K + /** Monotonic sequence number within the session. */ + seq: number + /** Unix epoch milliseconds. */ + time: number + data: SessionEventMap[K] + } & (K extends SurfaceEventType ? { + /** + * Seq numbers of events that are provenance sources of this event + * (e.g. the `assistant/chunk` seqs that built an `assistant/message`, + * or the surface nodes shadowed by a compaction replace node). An + * `assistant/message` may carry a present empty array for a known empty + * provider stream; omission means unrecorded provenance. + */ + sourceEventSeqs?: number[] + /** How this event entered the surface; absent for non-surface events. */ + surfaceOp?: SurfaceOp + } : object) +}[T] +``` + +十三种事件变体(`turn/start`、`turn/end`、`step/start`、`step/end`、`user/message`、`prompt/blocked`、`assistant/chunk`、`assistant/message`、`tool/call`、`tool/result`、`steering/message`、`todo/write`、`request/header`)、`deriveMessages()` 投影规则、`TurnTrigger`/`TurnEndReason` 原因以及轮次封闭不变量都在 **[session.md](session.md)** 中。日志如何持久化——`SessionPersistence` seam、JSONL/SQLite 后端、`session/flush` 检查点、崩溃恢复与 `SessionHeader`——则在 **[persistence.md](persistence.md)** 中。 + +<a id="the-agent-handle"></a> + +## Agent 句柄 + +`Agent` 是每个插件(UI、钩子、orchestrator)面向编程的 surface。具体实现为 dsh-agent-loop 包内部细节;循环外没有任何组件依赖它。 + +源码:[`packages/core/agent/src/types.ts`](../../packages/core/agent/src/types.ts) + +```ts type-equiv +/** + * Options for {@link Agent.followup}, {@link Agent.queue}, and {@link Agent.steer}. + * An omitted source attests direct human input as `{ kind: 'user' }` and may + * authorize policy consumers, so non-human producers must label their content. + */ +interface SendOptions { + source?: MessageSource + /** + * Model-facing contexts captured with this inbox item. A queued prompt exposes + * them through the default `agent/prompt-submit` allow decision, while steering + * records them directly at its next checkpoint. + */ + contexts?: HookContext[] + /** Opaque JSON state retained on the durable message but hidden from the model. */ + meta?: JsonValue +} +``` + +```ts type-equiv +/** Options specific to durable synthetic context injection. */ +interface InjectOptions { + /** Defaults to `{ kind: 'plugin', plugin: '' }`; non-human producers should identify themselves. */ + source?: MessageSource + /** Opaque JSON state retained on the durable message but hidden from the model. */ + meta?: JsonValue +} +``` + +高级接收形式会显式给出所有默认值,并禁止为注入附加上下文: + +```ts type-equiv +/** + * Fully specified input for {@link Agent.send}. Unlike the intent-named + * helpers, this form applies no defaults: callers provide content, source, + * contexts, metadata (including explicit `undefined`), target, and wakeup. + * The union excludes attached contexts from non-waking next-step injection. + */ +type ResolvedAgentInput = { + content: ContentBlock[] + source: MessageSource + meta: JsonValue | undefined +} & ( + | { target: 'next-turn'; wakeup: boolean; contexts: HookContext[] } + | { target: 'next-step'; wakeup: true; contexts: HookContext[] } + | { target: 'next-step'; wakeup: false; contexts: [] } +) +``` + +FIFO 投递方法返回不透明的 `AgentMessageId`,该 id 在同一条消息的各个 `agent/inbox/*` 事件中保持稳定。注入也返回 id,但会绕过这些事件: + +```ts type-equiv +/** + * Opaque id assigned to one accepted agent input. FIFO inputs carry the same id + * on their `agent/inbox/*` events; injection bypasses those events. + */ +type AgentMessageId = Branded<'AgentMessageId'> +``` + +`agent/inbox/*` 实时事件承载一条已接收的消息;注入绕过两个 FIFO,从不出现在这些事件中: + +```ts type-equiv +/** + * One accepted FIFO message, carried by the `agent/inbox/*` live events. `id` + * is the value returned by the accepting helper or {@link Agent.send}, + * stable across this message's enqueue, dequeue, and discard events. Source + * defaults, when applicable, are already applied, so these are the exact values + * the item was accepted with. + * `steering` is true for an item drained between steps; otherwise it is claimed + * at a turn boundary. `SendOptions.meta` is intentionally omitted: it is durable + * model-hidden state that lands on the eventual `user/message`/ + * `steering/message`, not live-event routing data. + */ +interface AgentMessage { + /** The id returned by the accepting helper or {@link Agent.send}. */ + id: AgentMessageId + content: ContentBlock[] + source: MessageSource + contexts: HookContext[] + /** Whether the item joined the steering FIFO rather than the queued FIFO. */ + steering: boolean + /** Whether the item wakes the driver or requests another step. */ + wakeup: boolean +} +``` + +```ts type-equiv +/** Options for {@link Agent.cancel}. */ +interface CancelOptions { + /** + * Preserve queued and steering inbox items instead of discarding them. The + * active turn is still aborted, but un-started and pending work survives for a + * later turn and no `agent/inbox/discard` fires. + */ + keepInbox?: boolean +} +``` + +```ts type-equiv +/** Stable runtime cause accepted by {@link Agent.cancel}. */ +type AgentCancelCause = + | { readonly kind: 'user' } + | { readonly kind: 'parent' } +``` + +结构化 `Agent` 接口公开四个按意图命名的辅助方法,以及接受完全解析输入的方法。具体驱动器只需实现一次这套路由矩阵,每个辅助方法提供其固定路由与默认值。 + +```ts type-equiv +/** Public agent handle; its concrete implementation is internal to `@deepseek-ai/dsh-agent-loop`. */ +interface Agent { + /** The single identity shared with {@link session}. */ + readonly id: SessionId + /** The provider route and model this agent's requests use. */ + readonly options: AgentOptions + /** The live session this agent drives; its log is the durable source of truth. */ + readonly session: Session + /** The current lifecycle state, mirrored on every `agent/status` transition. */ + readonly status: AgentStatus + /** Agent-scoped context; its contributions are agent-local, unwind on disposal, and reject registration afterward. */ + readonly ctx: Context + + /** + * Queue an ordinary message as its own FIFO-ordered turn and wake the driver. + * Content, resolved source, and attached contexts are detached, validated, + * and frozen together; invalid input throws synchronously before notification + * or enqueue. + * @param content - the prompt content blocks. + * @param options - source, attached contexts, and durable model-hidden meta. + * @returns the accepted message's {@link AgentMessageId}, stable across its `agent/inbox/*` events. + */ + followup(content: ContentBlock[], options?: SendOptions): AgentMessageId + + /** + * Queue an ordinary message without waking an idle driver. The item retains + * FIFO order and is claimed only after another input wakes the driver. A lone + * queued item leaves `whenIdle()` resolved. + * @param content - the prompt content blocks. + * @param options - source, attached contexts, and durable model-hidden meta. + * @returns the accepted message's {@link AgentMessageId}, stable across its `agent/inbox/*` events. + */ + queue(content: ContentBlock[], options?: SendOptions): AgentMessageId + + /** + * Submit steering into the running turn and request another step. An open turn + * records it at the next steering checkpoint before a request or continuation + * decision; policy may stop before another step. After turn close and its + * checkpoint, any remainder is queued for a later turn; terminal + * `agent/turn-stop`, cancellation, or disposal may discard it. Idle steering + * becomes a waking ordinary turn. + * @param content - the steering content blocks. + * @param options - source, attached contexts, and durable model-hidden meta. + * @returns the accepted message's {@link AgentMessageId}, stable across its `agent/inbox/*` events. + */ + steer(content: ContentBlock[], options?: SendOptions): AgentMessageId + + /** + * Append detached model-facing context without running the model. An open-turn + * injection joins at the current log position unless the current tool batch is + * executing; then it waits FIFO until that batch settles and drains before + * turn close even when interrupted. Idle injection uses a one-shot turn and + * durability checkpoint. Disposal awaits idle checkpoints; flush failures + * report through `agent/error`. An omitted source defaults to + * `{ kind: 'plugin', plugin: '' }`. + * @param content - the injected context content blocks. + * @param options - source and durable model-hidden meta. + * @returns the accepted injection's {@link AgentMessageId}; injection emits no `agent/inbox/*` events. + */ + inject(content: ContentBlock[], options?: InjectOptions): AgentMessageId + + /** + * Accept one fully specified input through the same snapshot and routing path + * as the four intent-named helpers. `next-turn` targets the ordinary FIFO; + * `next-step`/wakeup targets steering (falling back to an ordinary waking turn + * while idle); and `next-step` without wakeup injects durable context without + * running the model. Every field is mandatory and no source or routing default + * is applied. Invalid input throws synchronously before notification, enqueue, + * or append. + * @param input - the resolved content, attribution, context, metadata, and routing facts. + * @returns the accepted input's {@link AgentMessageId}, carried by FIFO lifecycle events when applicable. + */ + send(input: ResolvedAgentInput): AgentMessageId + + /** + * Clear queued and steering work — unless `keepInbox` — and abort the active + * turn. An effective call first emits `agent/cancel-requested` with the + * resolved typed cause. The first cause wins for the active turn, and + * `whenIdle()` resolves after cancellation reaches quiescence. Omitted cause + * means `{ kind: 'user' }`. Idle cancellation is a no-op and does not arm + * later work. The active turn snapshots and freezes the cause. + * @param cause - the stable caller intent carried by the current turn signal. + * @param options - cancellation options; `keepInbox` preserves pending work. + */ + cancel(cause?: AgentCancelCause, options?: CancelOptions): void + + /** Resolve at idle quiescence; disposal waits for driver exit rather than only the status transition. */ + whenIdle(): Promise<void> +} +``` + +`AgentStatus` 为 `'idle' | 'running' | 'disposed'`,`SessionId` 是品牌类型。`running` 描述整个驱动器的排空区间,可能跨越轮次关闭、其持久化检查点以及连续的排队轮次;它不能证明某个轮次仍然打开。`AgentOptions` 可合并扩展:core 声明 `provider?` 与 `model?`(在 `agent/request` 后,分发要求两者都存在)。Persona 归 `dsh-system-prompt` 所有:agent 作用域的 `deployment:persona` 可以遮蔽全局默认值。 + +cause 是由 TypeScript 强制约束的同进程输入。活跃的 `TurnCancellation` 持有者会把其判别字段复制到仅运行时的 `AbortSignal.reason`,并在发布 `turn/end` 前退役;冻结后的 `AbortSignal.reason` 仍可读取。`agentInterruptReasonOf(signal)` 无需查询环境中的 initiator 状态,即可识别 `user`、`parent` 与仅用于生命周期的 `disposed`。持久 `turn/end` 保留粗粒度 `{ kind: 'aborted' }` 结果;若需记录请求 provenance,应使用单独的持久事件,而不是让终态结果承担额外含义。 + +[事件分类](../architecture.md#event)拥有 `agent/*` 生命周期、检查点与 waterfall(瀑布式事件)契约。轮次和步骤边界是持久会话事件,而不是 agent emit。 + +## 发起 Agent + +`ctx.agents` 携带的进程本地 initiator 就是上面的确切 `Agent`,不是单独的 frame 或复制的标识。环境中存在该值既不能证明存活,也不代表授权;其生命周期与边界规则由 [initiator 作用域决策](../../.agents/notes/implemented/architecture/2026-07-15-agent-initiator-scope.md)规定。 + +## 拦截决策 + +每个 `agent/*` 拦截 waterfall 都返回一个小型、特定于 seam 的类型化联合——统一的 Decision 惯用形状([tools.md](tools.md) 中工具 seam 的 `PreToolDecision`/`PostToolDecision` 也采用相同形状)。CC/Codex 钩子桥接层把其 `permissionDecision`/`decision`/`continue`/`additionalContext` 字段映射到这些联合上;原生插件则直接返回它们。提示词决策与工具后决策共享一种面向模型的上下文形状 `HookContext`,它必须携带 `source`(缺少 source 会默认成 `{kind:'user'}`,从而把插件上下文错标为用户提示词)。其中的 `content` 作为 user-role 输入逐字到达模型,而 JSON `meta` 持久保存插件状态但不向模型暴露。未指定放置方式或指定为 `separate` 时,上下文会成为一条注入的 `user/message`(来源类别为插件或 goal);`prompt-prefix` 放置方式可用于提示词和 steering 收件箱附件,会在同一条消息中把上下文置于最终生效的请求之前。两种决策都携带 `additionalContexts[]`,使每一项保留各自的 provenance、元数据与放置方式。Continuation reason 则是 steering 消息,并有意使用更窄的 content/source 形状。 + +源码:[`packages/core/agent/src/types.ts`](../../packages/core/agent/src/types.ts) + +```ts type-equiv +/** Model-facing context injected by a listener or atomically attached to one inbox message. */ +interface HookContext { + content: ContentBlock[] + source: MessageSource + /** + * Model placement. Absent or `separate` records an independent injected + * `user/message`; `prompt-prefix` prepends this context and a stable + * request delimiter to the same user-role message as its attached prompt. + */ + placement?: 'separate' | 'prompt-prefix' + /** Opaque JSON state retained in the session event but hidden from the model. */ + meta?: JsonValue +} +``` + +`agent/prompt-submit` 返回 `PromptDecision`(允许该轮次已领取的排队消息——可选地改写其 `content` 或附加 `additionalContexts`——或者记录 `prompt/blocked` 并以 `rejected` 结束这个零步骤轮次): + +```ts type-equiv +/** + * Prompt interception result. `allow.content` replaces the prompt. Each + * `additionalContexts` entry follows its declared placement: separate context + * message by default, or a prefix inside the prompt's user-role message. + * `block` records a durable `prompt/blocked` and ends the claimed prompt's + * zero-step turn as rejected. An `allow` returned by a listener is + * authoritative: a listener wrapping `next()` preserves downstream `content` + * and `additionalContexts` unless it intentionally replaces them. + */ +type PromptDecision = + | { kind: 'allow'; content?: ContentBlock[]; additionalContexts?: HookContext[] } + | { kind: 'block'; reason: string } +``` + +`agent/turn-continuation` 返回 `ContinuationDecision`(步骤有工具调用或注入了 steering 时,循环默认为 `continue`,否则为 `stop`;`continue` 的 `reason` 会记录为同一轮次中下一个步骤的 steering,因此不携带上下文元数据——即类型化 `/goal` 模式): + +```ts type-equiv +/** Turn continuation override; a continue reason is recorded as next-step steering in the same turn. */ +type ContinuationDecision = + | { action: 'stop' } + | { action: 'continue'; reason?: { content: ContentBlock[]; source: MessageSource } } +``` + +`agent/request-error` 接收确切的原始 `RequestError`、其不可变 `LlmFailure`、在连续序列中已批准另一次请求的不可变失败列表、轮次信号以及 `next()`。恢复插件按 `failure.code` 路由,而不是按活跃错误的消息路由;每项策略只统计自身的 code,一次成功请求会清空历史: + +```ts type-equiv +/** Model-request failure with an optional machine-routable provider code. */ +type RequestError = Error & { code?: string } +``` + +它返回 `RequestErrorDecision`;`retry` 在恢复 listener 的持久变更之后打开一个带新编号的步骤,而 `fail` 在 `turn/end` 上保留结构化失败: + +```ts type-equiv +/** Failed-request recovery decision; `retry` opens another numbered step while listeners delegate by calling `next()`. */ +type RequestErrorDecision = { action: 'fail' } | { action: 'retry' } +``` + +`agent/post-step` 会在 assistant 输出、真实或合成的工具结果、缓冲上下文与 steering 持久化之后、`step/end` 之前被 await。被取消的工具批次在排空后携带 aborted signal 到达这里;其签名为 `(agent, turn, step, signal)`,可回放事实保留在会话日志中,而不是瞬态 payload 中。 + +`agent/turn-stop` 返回仅停止的 `ContinuationStop` 子集或 `undefined`。循环在折叠普通决策、其 reason 和待处理 steering 之后调用此串行检查点;stop 是终态,会丢弃待处理的 steering。 + +```ts type-equiv +/** + * The terminal subset of {@link ContinuationDecision}. A listener on + * `agent/turn-stop` returns this to make the already-composed continuation + * outcome terminal; `undefined` abstains. + */ +type ContinuationStop = Extract<ContinuationDecision, { action: 'stop' }> +``` + +`agent/session-start` 携带 `SessionStartSource`(会话生命周期为何开始;桥接层据此匹配其 SessionStart): + +```ts type-equiv +/** Why a session lifecycle began; seeded creates are `startup`, while persisted loads are `resume`. */ +type SessionStartSource = 'startup' | 'resume' | 'clear' | 'compact' +``` + +`agent/session-prefix` 在每个循环实例中组合一次 `Message[]`。深度冻结的结果被记录在请求 header 中,并前置于每次派生历史,使其成为会话稳定开场白的归属。恢复的实例会重新组合;会话中途的变更使用仅追加的上下文通道。该 waterfall 直接返回内容,因为它是贡献而非决策。 + +## `ToolDefinition` + +唯一属于核心的流水线编写类型:每个已注册工具*是什么*——一个面向模型的 `ToolSchema` 加上一个 `execute` 函数,以及可选的最终内容回调与 UI 回调。工具作者很少手动构造它(`defineTool` DSL 会用类型化参数构建),但它是注册表持有、循环分发所经过的契约。 + +其完整字段、`defineTool`/`ValueSchemaSpec`/`ParameterSchemaSpec` 类型化 schema DSL、`ToolExecution`/`ToolExecutionResult` waterfall 形状,以及工具展示 UI 词汇在 **[tools.md](tools.md)** 中。 diff --git a/docs/core-data-structures/filesystem.i18n.yaml b/docs/core-data-structures/filesystem.i18n.yaml new file mode 100644 index 0000000000..e360dd99d3 --- /dev/null +++ b/docs/core-data-structures/filesystem.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +filesystem.md: 110c1fd428b15c5094f9dcc94050cad61c324373 +filesystem.zh.md: aca450364c05c6f756c36fccc11be7246767f3a4 diff --git a/docs/core-data-structures/filesystem.md b/docs/core-data-structures/filesystem.md index 25df997bb0..110c1fd428 100644 --- a/docs/core-data-structures/filesystem.md +++ b/docs/core-data-structures/filesystem.md @@ -1,5 +1,7 @@ # Filesystem +English | [中文](filesystem.zh.md) + The optional filesystem capability has four parts: [dsh-fs](../../packages/fs/fs) owns `ctx.fs` and atomic text operations with optional version guards, [dsh-fs-local](../../packages/fs/fs-local) implements local disk, [dsh-fs-policy](../../packages/fs/fs-policy) adds observed-state and freshness rules through events rather than a service, and [dsh-tool-fs](../../packages/fs/tool-fs) directly executes model-facing read/write/edit calls and renders windows. It is outside the agent-loop spine; alternate backends do not change policy or tool schemas. The model is **additive, not subtractive**: `ctx.fs` alone is a complete, unconstrained text-storage seam (`write` unconditionally creates-or-overwrites, `edit` unconditionally replaces literal text). `dsh-fs-policy` is a plugin that *adds* policy on top by deciding the `fs/*` waterfalls; removing it leaves the bare provider rather than breaking the tool, because the tool is not method-coupled to the policy. A deployment that loads `dsh-tool-fs` is expected to also load `dsh-fs-policy` so the default behavior is read-before-write/edit. diff --git a/docs/core-data-structures/filesystem.zh.md b/docs/core-data-structures/filesystem.zh.md new file mode 100644 index 0000000000..aca450364c --- /dev/null +++ b/docs/core-data-structures/filesystem.zh.md @@ -0,0 +1,259 @@ +# 文件系统 + +[English](filesystem.md) | 中文 + +可选的文件系统能力由四个部分组成:[dsh-fs](../../packages/fs/fs) 拥有 `ctx.fs` 以及带可选版本守卫的原子文本操作;[dsh-fs-local](../../packages/fs/fs-local) 实现本地磁盘后端;[dsh-fs-policy](../../packages/fs/fs-policy) 通过事件(而非服务)添加观测状态与新鲜度规则;[dsh-tool-fs](../../packages/fs/tool-fs) 直接执行面向模型的 read/write/edit 调用并渲染窗口。它位于 agent loop(智能体循环)主干之外;替换后端不会改变策略或工具 schema。 + +该模型是**加法式而非减法式**的:`ctx.fs` 本身就是一个完整、无约束的文本存储 seam(`write` 无条件创建或覆盖,`edit` 无条件替换字面文本)。`dsh-fs-policy` 是一个插件,通过裁决 `fs/*` waterfall(瀑布式事件)在上层*叠加*策略;移除它只会暴露裸提供方,而不会破坏工具,因为工具与策略之间没有方法级耦合。加载了 `dsh-tool-fs` 的部署通常也应加载 `dsh-fs-policy`,使默认行为为「先读后写/编辑」。 + +提供方源码:[`packages/fs/fs/src/types.ts`](../../packages/fs/fs/src/types.ts) 与 [`packages/fs/fs/src/index.ts`](../../packages/fs/fs/src/index.ts)。策略源码:[`packages/fs/fs-policy/src/types.ts`](../../packages/fs/fs-policy/src/types.ts)。读取渲染源码:[`packages/fs/tool-fs/src/read-render.ts`](../../packages/fs/tool-fs/src/read-render.ts)。 + +## 目标标识与元数据(提供方 seam) + +每个操作首先将用户提供的路径解析为不透明的后端目标。消费方可以显示 `displayPath`,但禁止解析 `targetKey`(一个品牌化的不透明 id),也不得假设它是本地绝对路径。 + +```ts type-equiv +/** + * A path resolved by a backend into a stable identity. `resolve()` produces + * this; every other operation takes it. + */ +interface FsTarget { + /** Opaque key for stale guards and target lookup. */ + targetKey: FsTargetKey + /** + * Path for model/UI-facing output. May be a local absolute path, + * workspace-relative path, or remote URI depending on the backend. + */ + displayPath: string +} +``` + +后端拥有文件版本 token,即 write/edit 所守卫的新鲜度 token。策略插件存储它们以进行陈旧检查;消费方不解释其内容。两个 id 都是品牌化的不透明字符串。 + +```ts type-equiv +/** + * Opaque key for stale guards and target lookup. The local backend uses a + * realpath-like string; a remote backend might use a workspace URI or file id. + * Consumers MUST NOT parse it or assume it is a local absolute path. + */ +type FsTargetKey = Branded<'FsTargetKey'> +``` + +```ts type-equiv +/** + * Opaque file-version token — the freshness token a write/edit guards against. + * The local backend derives it from high-resolution stat identity and freshness + * fields; a remote backend might use a revision id. The policy layer records it + * for stale checks; consumers may display related metadata but MUST NOT + * interpret this token. + */ +type FsVersion = Branded<'FsVersion'> +``` + +`stat` 返回元数据(从不返回内容),目标不存在时返回 `undefined`。`type` 让工具在读取前拒绝目录或特殊文件;`size` 让工具无需通过失败探测即可选择 `readText` 还是 `streamText`。 + +```ts type-equiv +/** + * Metadata about a target — what {@link FileSystem.stat} returns. Lets the + * policy layer reject directories/special files before reading and choose + * `readText` vs `streamText` from `size` without probing by failure. `version` + * is the freshness token. `undefined` from `stat` means the target is absent. + */ +interface FsInfo { + /** Opaque freshness token of the target right now. */ + version: FsVersion + /** Whether the target is a regular file, a directory, or something else. */ + type: 'file' | 'directory' | 'other' + /** Byte size of a regular file, when the backend can report it. */ + size?: number +} +``` + +`lstat` 是路径层级、不跟随链接的元数据原语。它接收路径而不是 `FsTarget`,因为 `resolve` 会有意跟随 symlink 以产生稳定标识;需要检查信任边界的消费方可以先调用 `lstat`,在解析前拒绝 `symlink`。 + +```ts type-equiv +/** + * Metadata about a path without following the final path component when it is a + * symbolic link. Unlike {@link FsInfo}, this path-level probe can report + * `symlink` so consumers with trust-boundary rules can reject repository-owned + * links before resolving a target. + */ +interface FsPathInfo { + /** Opaque freshness token of the path entry right now. */ + version: FsVersion + /** Whether the path entry is a regular file, directory, symlink, or other. */ + type: 'file' | 'directory' | 'symlink' | 'other' + /** Byte size of the path entry, when the backend can report it. */ + size?: number +} +``` + +`listDir` 按稳定的名称顺序返回直接子条目。每个条目携带子项的 basename、类型、已解析目标,以及后端能报告时的廉价元数据。它禁止读取文件内容,因此 `size` 仅用于普通文件,`version` 来自元数据。已损坏或已消失的子项可以作为 `other` 返回且不带元数据;列出或解析子项元数据时的权限或后端 I/O 失败会以 `FS_PERMISSION_DENIED` 或 `FS_IO_ERROR` 使整个列表操作失败。 + +```ts type-equiv +/** + * One direct child returned by {@link FileSystem.listDir}. Listing returns + * metadata and resolved targets only; it must not read file contents. + */ +interface FsDirEntry { + /** Basename of the child inside the listed directory. */ + name: string + /** Whether the child is a regular file, a directory, or something else. */ + type: 'file' | 'directory' | 'other' + /** Resolved child target for follow-up operations. */ + target: FsTarget + /** Opaque freshness token when the backend can report metadata cheaply. */ + version?: FsVersion + /** Byte size of a regular file, when the backend can report it. */ + size?: number +} +``` + +## 写入与编辑守卫(提供方 seam) + +`writeText` 和 `editText` 的版本守卫都是可选的:省略它执行无条件(裸提供方)变更,提供它则启用守卫。`writeText` 的守卫是 `FsWriteIntent`:`createIfAbsent` 在目标缺失时创建,目标已存在时以 `FS_NOT_OBSERVED` 拒绝;`replaceIfVersion` 仅在目标存在且版本匹配时替换,否则报 `FS_STALE_VERSION`。省略 `expected` 则无条件创建或覆盖。联合类型本身只包含两种有守卫的意图;「无守卫」通过省略表达,因此 write 和 edit 共享同一个对称的 `expected?` 形状。 + +```ts type-equiv +/** + * Guarded write intent. `createIfAbsent` rejects an existing target with + * `FS_NOT_OBSERVED`; `replaceIfVersion` rejects absence or mismatch with + * `FS_STALE_VERSION`. Omitting the intent from `writeText` means unconditional + * create-or-overwrite, not a third union arm. + */ +type FsWriteIntent = + | { kind: 'createIfAbsent' } + | { kind: 'replaceIfVersion'; version: FsVersion } +``` + +```ts type-equiv +/** Outcome of a full-file write. */ +interface FsWriteOutcome { + /** Whether the write created a new file or replaced an existing one. */ + operation: 'create' | 'update' + /** Opaque version of the file after the write. */ + version: FsVersion + /** + * The file's content BEFORE the write, or `null` when the file did not exist + * (a create) or was undiffable (binary/non-UTF-8). LF-normalized storage text + * (the diff basis), never a diff — a consumer computes the result-time + * contextual diff from `before`/`after` when `before` is present, else falls + * back to a whole-file diff. + */ + before: string | null + /** The file's content AFTER the write, LF-normalized to share `before`'s diff basis. */ + after: string +} +``` + +`editText` 是提供方级别的变更操作,而非在别处组合的 `read` 加 `write`。带守卫时,它在字面匹配之前先验证预期版本(因此对陈旧内容的编辑报 `FS_STALE_VERSION`,而非对更新内容的匹配失败);不带守卫时,它编辑当前内容。无论哪种路径,它都应用替换并原子写入——将匹配、行尾处理、陈旧检查和原子替换保持在一个变更临界区内——目标缺失时两条路径都报 `FS_STALE_VERSION`。 + +```ts type-equiv +/** A literal-replacement edit request. */ +interface FsEditRequest { + /** Literal non-empty text to replace. Must match exactly (after line-ending normalization). */ + oldString: string + /** Literal replacement text. An empty string deletes the matched text. */ + newString: string + /** Replace every match instead of requiring exactly one. */ + replaceAll: boolean +} +``` + +```ts type-equiv +/** Outcome of a literal edit. */ +interface FsEditOutcome { + /** Opaque version of the file after the edit. */ + version: FsVersion + /** + * The file's content BEFORE the edit. Raw storage text (LF-normalized by the + * backend), never a diff — a consumer computes the result-time contextual diff + * (the applied hunk with context) from `before`/`after`. + */ + before: string + /** The file's content AFTER the edit. */ + after: string +} +``` + +## fs 策略事件(提供方 seam 词汇) + +`dsh-fs` 拥有三个事件,由工具分发、策略插件监听,使发射方(`dsh-tool-fs`)与监听方(`dsh-fs-policy`)共享词汇,而发射方无需依赖策略插件。它们只携带 `dsh-fs` 词汇加一个不透明的 `object` actor,不含面向模型的概念,也不含 agent/会话所有者结构。 + +`fs/write-intent` 与 `fs/edit-intent` 是**单槽决策 waterfall**:工具分发时附带一个默认 thunk(返回 `undefined`,即裸提供方),监听方完全决策而不调用 `next()`。该槽按注册顺序先到先得——由策略插件占据是部署约定,而非强制不变式。`fs/observed` 是一个即发即弃的记录事件,通过普通 `ctx.emit` 分发;其监听方必须是同步的、仅产生副作用,因为工具不守卫该 emit——抛异常的监听方会在一次已成功的变更上表现为工具的 `isError` 结果。生成的目录在 [events.md](../cordis-catalog/events.md) 中展示确切签名。 + +## 执行上下文(策略插件) + +策略插件只需要足够的执行上下文,通过收窄 `fs/*` 事件携带的不透明 `object` actor 来推导观测状态的所有者。`ToolExecution` 满足此形状,因此 `dsh-tool-fs` 将其执行对象作为 actor 直接传递,而无需让 `dsh-fs-policy` 导入工具、agent 或会话包(package)。 + +```ts type-equiv +/** + * Minimal structural view of a tool execution the policy plugin needs to derive + * an observed-state owner. `@deepseek-ai/dsh-tools`' `ToolExecution` satisfies + * this shape, so the tool passes its `exec` straight through as the opaque + * `object` actor on the `fs/*` events; this plugin narrows that actor to this + * shape without importing `dsh-tools`, `dsh-agent`, or `dsh-session`. + * + * The owner is `agent.session` when present. It is treated as an opaque object + * identity (a `WeakMap` key); this package never reads any of its fields. + */ +interface FsPolicyExec { + /** The agent on whose behalf the call runs, when there is one. */ + agent?: { + /** The session that owns observed-file state, used as an opaque key. */ + session?: object + } +} +``` + +## 读取结果(消费方 / 读取渲染) + +文本读取受行窗口、字节上限和后端限制约束。达到字节上限后,扫描仍会继续,但不再保留更多行,因此 `totalLines` 仍为精确值。面向模型的 `read` 工具渲染的结果纯粹是展示性的;不存在 `full`/`partial` 视图区分——授权基于新鲜度(工具直接用 stat 的版本 emit `fs/observed`),因此任何窗口化读取在文件未变时都能授权后续的 write/edit。读取窗口化与此结果形状位于 `dsh-tool-fs`(拥有读取操作的执行器)中,而非策略插件中。 + +```ts type-equiv +/** Outcome of a bounded text read — what {@link formatReadOutput} renders. */ +interface FileReadOutcome { + /** 1-based first line requested. */ + offset: number + /** Returned lines, already numbered. */ + lines: FileTextLine[] + /** Exact total line count in the file. */ + totalLines: number + /** Whether selected output hit the byte cap. */ + truncatedByBytes?: true +} +``` + +## 已观测文件状态(策略插件) + +已观测状态是 `dsh-fs-policy` 插件内部持有的 `WeakMap<owner, Map<targetKey, { version }>>`。**当且仅当**所有者已读取、写入或编辑过该目标时(每次成功都 emit `fs/observed`),条目才存在,因此其存在本身就是先前观测的记录——没有单独的 `hasRead` 标志,也没有视图区分。所有者从事件 actor 推导(通常是 `exec.agent.session`),被视为不透明且从不读取。成功的 read/write/edit 会刷新该所有者对应的已记录版本;dispose(资源释放)时丢弃全部数据(HMR(热模块替换)安全)。 + +## 错误分类体系(提供方 seam) + +文件系统故障使用稳定的 `FsErrorCode` 字符串,由 `FsError`(`HarnessError`)携带。工具注册表在错误结果上保留 `{ name, code }`,使重试、权限和 UI 层可以按 code 分支而无需解析文本。 + +```ts type-equiv +/** + * Stable, machine-routable codes for filesystem failures. Carried on + * {@link FsError}; the tool registry surfaces `{ name, code }` on `isError` + * results so retry/permission/UI layers can branch without parsing messages. + */ +type FsErrorCode = + | 'FS_NOT_FOUND' + | 'FS_NOT_DIRECTORY' + | 'FS_NOT_TEXT' + | 'FS_NOT_REGULAR_FILE' + | 'FS_PERMISSION_DENIED' + | 'FS_SANDBOX_DENIED' + | 'FS_IO_ERROR' + | 'FS_STALE_VERSION' + | 'FS_NOT_OBSERVED' + | 'FS_AMBIGUOUS_EDIT' + | 'FS_EDIT_NOT_FOUND' + | 'FS_ABORTED' +``` + +目录列表使用 `FS_NOT_DIRECTORY`、`FS_PERMISSION_DENIED` 与 `FS_IO_ERROR` 区分已存在但并非目录的目标、被拒绝的列表操作和意外的后端 I/O 失败。`FS_SANDBOX_DENIED` 是强制执行沙箱的后端(`dsh-fs-sandbox`)所作的策略拒绝——模式边界拒绝了写入/编辑——与 `FS_PERMISSION_DENIED`(宿主内核拒绝)不同。`FS_NOT_OBSERVED` 表示策略插件没有此所有者的先前观察记录(或 `createIfAbsent` 遇到了现有文件)。`FS_STALE_VERSION` 表示后端版本不再与观察到的版本匹配(或编辑操作遇到缺失目标)。新鲜度授权没有部分/完整之分,因此不存在 `FS_PARTIAL_OBSERVATION`。 + +## 服务与插件 + +`FileSystem`(`ctx.fs`,abstract)拥有提供方原语:`resolve`、`stat`、`lstat`、`readText`、`streamText`、`listDir`、`writeText` 与 `editText`。`dsh-fs-policy` **不注册服务**——它是一个通过 `fs/*` 事件门禁添加策略的插件:对写入/编辑意图 waterfall 作出决策(提供 `createIfAbsent`/`replaceIfVersion`/`{ version }`,或抛出 `FS_NOT_OBSERVED`),并在 `fs/observed` 上记录。执行器是 `dsh-tool-fs`:它通过 `ctx.fs` 读取/写入/编辑,分发 waterfall,并 emit 记录事件。生成的 wiring 目录在 [services.md](../cordis-catalog/services.md#ctxfs--filesystem-abstract-seam) 中展示确切的 `ctx.fs` 签名。 diff --git a/docs/core-data-structures/goal.md b/docs/core-data-structures/goal.md index d45847ba0f..c0351f2f77 100644 --- a/docs/core-data-structures/goal.md +++ b/docs/core-data-structures/goal.md @@ -69,7 +69,7 @@ interface GoalView extends GoalSnapshot { ## Durable changes -Every mutation is a `context/message` whose metadata is either a complete snapshot or a clear tombstone. The version, metadata, goal source, and verbatim rendered content form one replay invariant. +Every mutation is a round-zero goal-sourced `user/message` whose metadata is either a complete snapshot or a clear tombstone. The version, metadata, goal source, and verbatim rendered content form one replay invariant. ```ts type-equiv /** Full-snapshot goal mutation retained in a model-visible context event. */ diff --git a/docs/core-data-structures/llm-streaming.i18n.yaml b/docs/core-data-structures/llm-streaming.i18n.yaml new file mode 100644 index 0000000000..28191bd56c --- /dev/null +++ b/docs/core-data-structures/llm-streaming.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +llm-streaming.md: cb99c935aea2dc9cc769e3056fdb98a2e5c9eacb +llm-streaming.zh.md: 740fa1f796088e63d0195cfbecf975adb236381c diff --git a/docs/core-data-structures/llm-streaming.md b/docs/core-data-structures/llm-streaming.md index 257ce90cda..cb99c935ae 100644 --- a/docs/core-data-structures/llm-streaming.md +++ b/docs/core-data-structures/llm-streaming.md @@ -1,5 +1,7 @@ # LLM Streaming +English | [中文](llm-streaming.zh.md) + The wire-level streaming vocabulary of [dsh-llm](../../packages/llm/llm). [core.md](core.md) introduces `StreamChunk`, `Message`, and `ContentBlock`; this page owns the full chunk protocol, the adapter contract every adapter must obey, and the shared assembler. Source: [`packages/llm/llm/src/types.ts`](../../packages/llm/llm/src/types.ts) diff --git a/docs/core-data-structures/llm-streaming.zh.md b/docs/core-data-structures/llm-streaming.zh.md new file mode 100644 index 0000000000..740fa1f796 --- /dev/null +++ b/docs/core-data-structures/llm-streaming.zh.md @@ -0,0 +1,218 @@ +# LLM(大语言模型)流式输出 + +[English](llm-streaming.md) | 中文 + +[dsh-llm](../../packages/llm/llm) 的协议格式(wire format)级流式输出词汇。[core.md](core.md) 介绍了 `StreamChunk`、`Message` 与 `ContentBlock`;本页拥有完整的分片协议、每个适配器必须遵守的适配器契约(adapter contract),以及共享的 assembler。 + +源码:[`packages/llm/llm/src/types.ts`](../../packages/llm/llm/src/types.ts) + +## `StreamChunk`:原始协议 + +一个流式响应交错包含多种类型的块(文本、推理(reasoning)、多个工具调用)。`index` 将每个 delta 关联到其所属块;`block-end` 携带完整组装好的 `ContentBlock`,消费方无需自行重新组装 delta。这是一个**封闭的**可辨识联合类型:对 `type` 的 `switch` 以 `assertNever` 结尾,因此新增变体会在每个必须处理它的消费方处触发编译错误。 + +```ts type-equiv +/** + * Raw streaming protocol emitted by adapters. + * Block indexes correlate interleaved deltas, and `block-end` carries the + * assembled block. Adapters emit usage before the terminal finish and nothing + * afterward; tool arguments remain raw JSON strings. Failures either throw or + * end with `error`/`aborted`, and consumers must handle both paths. + */ +type StreamChunk = + | { type: 'block-start'; index: number; blockType: ContentBlockType } + | { type: 'text-delta'; index: number; text: string } + | { type: 'reasoning-delta'; index: number; text: string } + | { type: 'tool-call-delta'; index: number; id: CallId; name?: string; argumentsDelta: string } + | { type: 'block-end'; index: number; block: ContentBlock } + | { type: 'usage'; usage: TokenUsage } + | { + type: 'finish' + reason: FinishReason + /** Adapter-private lossless-JSON state for replaying a successful response. */ + replayState?: unknown + } +``` + +## `LlmFailure` + +每个抛出的失败或最终适配器的带内失败都会规范化为一种可序列化、提供方无关的 payload。`providerRetryAfterMs` 是经校验、由提供方请求的正数延迟,而不是重试决策;`ProviderRequestId` 是用于诊断的不透明品牌字符串。 + +```ts type-equiv +/** Serializable provider-boundary facts; policy decides whether they are retryable. */ +interface LlmFailure { + /** Human-readable provider or transport failure. */ + readonly message: string + /** Stable provider-neutral machine-routing code. */ + readonly code: string + /** HTTP status observed at the provider boundary, when available. */ + readonly status?: number + /** Provider-requested delay in milliseconds, when valid and available. */ + readonly providerRetryAfterMs?: number + /** Opaque provider-issued request identifier for diagnostics. */ + readonly requestId?: ProviderRequestId +} +``` + +## 适配器契约 + +每个适配器必须遵守以下规则,每个消费方可以依赖它们: + +- **`usage` 在 `finish` 之前,`finish` 之后不再有任何分片。** 将两者都推迟到提供方的流结束标记,这样尾部的 usage-only 分片就不会违反顺序。 +- **工具调用的 `arguments` 全程保持原始 JSON 字符串。** 部分片段通过 `argumentsDelta` 流式传输;如果提供方返回的是已解析的对象,适配器在 `block-end` 时重新序列化为字符串。 +- **两条受支持的错误路径,一种事实形状。** 失败可以从 `stream()` 抛出(传输/协议错误),**或者**以 `finish {kind:'error'|'aborted', failure}` 结束流(无法在流中途抛异常的适配器用它表示提供方带内错误)。`LlmError.failure` 携带同一个 `LlmFailure`。最终适配器边界保留被抛出的确切 `Error` 对象,并将不可变事实关联到该调用;agent loop(智能体循环)关闭失败的步骤,再把错误、事实与不可变的先前已重试事实提供给 `agent/request-error`。若未恢复,结构化失败会成为轮次错误,并且该次尝试不会提交正常 assistant 消息或工具副作用。 +- **一次适配器调用就是一次提供方尝试。** 适配器禁用库重试。agent 层恢复会打开另一个持久、带编号的步骤;直接调用 `ctx.llm.stream()` 的调用方仍然只尝试一次。 +- **提供方停顿在传输层受到时限约束。** 两个已交付的远程适配器都暴露正数且有限的 `streamIdleTimeoutMs`,默认五分钟。watchdog 只在 iterator `next()` 尚未完成时启动,整个请求使用同一个稳定 signal,把自身到期映射为 `TIMEOUT`,并把更早发生的调用方中止保留为 `ABORTED`。 +- **上下文溢出只有一个规范 code。** 两个 DeepSeek 适配器都通过 `isContextWindowExceededError()` 对提供方的显式细节分类并暴露 `CONTEXT_WINDOW_EXCEEDED`,无论失败以抛出的 HTTP `LlmError` 还是带内 finish error 到达。消费方按 code 路由,绝不依赖提供方文本。 +- **每个提供方 HTTP 请求都携带应用归属头。** 适配器发送 `attributionHeaders()`(见下文)作为 `User-Agent` 基线,并通过协议级测试加以证明(mock 服务器断言收到的 header,或对基于库的适配器使用库的 header 钩子)。 +- **回放状态归适配器所有。** 成功的 `finish` 可以携带重建提供方原生响应所需的无损 JSON 状态。除非 `agent/step-result` listener 改写了内容,否则循环会将其与组装后的 assistant 消息一起存储。后续请求中,仅当历史提供方与目标提供方当前注册到完全相同的适配器实例时,`LlmService` 才会传递该状态。该适配器负责校验状态并拥有所有跨模型或跨提供方转换;其他适配器只会收到提供方无关的内容与 provenance,不会收到私有状态。 + +该契约由两个有意保持独立的实现锁定:`dsh-llm-deepseek`(手写 fetch/SSE(Server-Sent Events))和 `dsh-llm-pi-ai`(通过 `@earendil-works/pi-ai` 实现的通用多提供方适配器)。基于库的适配器覆盖 finish 分片错误路径,而传输边界测试证明每个空闲 watchdog 都会停止其实际请求。 + +## `AppIdentity`:应用归属 + +每个适配器都会向提供方发送的静态公开应用标识([`packages/llm/llm/src/attribution.ts`](../../packages/llm/llm/src/attribution.ts))。`attributionHeaders(identity?)` 只把它映射到标准 `User-Agent` header;该契约有意不支持 OpenRouter 特有的应用归属 header。默认 `APP_IDENTITY` 从包(package) manifest(元数据清单)获取版本;每个字段都是公开产品事实——不含 secret、路径、会话 id 或逐用户标识,且任何逐请求信息都不得影响这些值。设计理由见[强制 `User-Agent` 归属](../../.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.md)。 + +```ts type-equiv +/** + * Static public application identity sent to LLM providers. + * + * Every field is a public product fact, safe on every request: no secrets, + * local paths, session ids, prompt text, or per-user identifiers belong here, + * and nothing per-request may influence the values. + */ +interface AppIdentity { + /** `User-Agent` product token (lowercase, hyphenated). */ + product: string + /** Product version; sourced from package metadata, never hand-copied. */ + version: string + /** Public home URL of the app, used as the `User-Agent` comment. */ + url: string +} +``` + +## `TokenUsage` + +逐调用 token 记账。各计数**互不重叠**:`inputTokens` 只包含未缓存输入;缓存输入单独报告,计费输入是三者之和。若提供方把缓存命中折入单一提示词总数(如 DeepSeek 的 `prompt_tokens`),适配器会再将其扣除。`reasoningTokens` 存在时只是信息性细节,已经包含在 `outputTokens` 中;汇总时不得重复相加。 + +```ts type-equiv +/** + * Token accounting for one model call (cache fields are optional). + * + * Counts are DISJOINT: `inputTokens` is uncached input only; cached input is + * reported separately as `cacheReadTokens`/`cacheWriteTokens` (billed input = + * sum of the three). Adapters whose providers fold cache hits into a total + * prompt count (DeepSeek's `prompt_tokens`) subtract them out. + */ +interface TokenUsage { + inputTokens: number + outputTokens: number + cacheReadTokens?: number + cacheWriteTokens?: number + reasoningTokens?: number +} +``` + +## `BlockAssembler` + +`BlockAssembler`([`packages/llm/llm/src/assembler.ts`](../../packages/llm/llm/src/assembler.ts))是唯一的共享实现,负责把 `StreamChunk` 流折叠回 `ContentBlock`、usage、结束原因与回放状态。循环在记录原始分片的同时,把同一批分片送入 assembler,再将组装后的 assistant 内容连同其提供方/模型 provenance 一起存储。需要组装结果、又不想重新实现 fold 的消费方使用它。 + +```ts public-api +/** + * Incrementally assembles raw {@link StreamChunk}s into complete + * {@link ContentBlock}s and a final assistant {@link Message}. + * + * The agent loop feeds it while logging raw chunks for replay fidelity, then + * reads `blocks()` / `message()` / `usage` / `finish` once the stream ends. + * + * Tolerant of delta-only protocols (no block-start/end); deltas arriving for + * an index already closed by `block-end` are ignored (malformed stream) so a + * misbehaving adapter cannot grow memory or corrupt a completed block. + */ +declare class BlockAssembler { + /** + * Feed one chunk into the assembly state. + * @param chunk - the next raw chunk, in stream order. + */ + push(chunk: StreamChunk): void; + /** + * Assemble all blocks seen so far, in stream order. + * @returns one block per seen index; an open block assembles from its + * accumulated deltas (an unknown block type never closed by `block-end` throws). + */ + blocks(): ContentBlock[]; + /** Usage from the `usage` chunk; undefined until one arrives. */ + get usage(): TokenUsage | undefined; + /** Finish reason from the `finish` chunk; `{kind: 'stop'}` when the stream ended without one. */ + get finish(): FinishReason; + /** Adapter-private replay state from the terminal finish chunk, if any. */ + get replayState(): unknown; + /** + * The assembled assistant message. + * @returns an assistant-role message over `blocks()` (same open-block assembly rules). + */ + message(): Message; +} +``` + +## seam + +`LlmAdapter` 是提供方 seam:创建子类、实现 `stream()`,再用 `ctx.llm.registerAdapter(providers, adapter)` 注册一个适配器实例。`GenerateOptions.provider` 选择已注册适配器;`GenerateOptions.model` 会传给该适配器,无需在生命周期启动时注册。重复提供方路由会原子失败。可选的 `providerInfo()` 与异步 `listModels()` 方法为 `LlmService.listProviders()` / `listModels()` 提供分离的 selector 元数据。该目录仅供参考,不是请求白名单:适配器仍是权威,并可接受未列出的模型 id。单独的 `resolveModelContext()` 查询会暴露确切路由上对正确性敏感的容量信息,但不会让目录成员关系具有权威性;缺失表示元数据未知,而不是路由无效。适配器查找发生在 `llm/stream` waterfall(瀑布式事件)的终端 continuation,因此 listener 可以在查找前短路调用,或路由一个可变的一次性请求。`block-start` / `block-end` 的 `index` 关联与 assembler 共同意味着适配器只需 emit 格式正确的分片——块重组不是每个适配器各自的问题。消费方 surface(`ctx.llm.stream()`)与 `llm/stream` waterfall 见 [architecture.md § 内容块与流式传输](../architecture.md#content-blocks-and-streaming-dsh-llm)。 + +```ts public-api +/** + * Provider-wire adapter for the harness message and stream vocabulary. Register implementations + * with `ctx.llm.registerAdapter(providers, adapter)`. Every provider HTTP request must include + * `attributionHeaders()`; prove that at the wire or library header-hook boundary. The hand-rolled + * DeepSeek and pi-ai adapters intentionally exercise this contract through different internals. + */ +declare abstract class LlmAdapter { + /** + * Describe one provider route owned by this adapter. + * @param provider - a route passed to `registerAdapter()` for this instance. + * @returns detached display metadata whose id must equal `provider`. + */ + providerInfo(provider: string): LlmProviderInfo; + /** + * List models this adapter can currently advertise for one owned provider. + * The result is advisory: an adapter may accept unlisted model ids, and + * consumers must not turn absence into request rejection. + * @param _provider - one provider route owned by this adapter. + * @returns discoverable models in adapter-preferred order. + */ + listModels(_provider: string): Promise<readonly LlmModelInfo[]>; + /** + * Resolve context capacity for one model accepted by this adapter. Absence + * means the adapter does not know the capacity, not that routing is invalid. + * @param _provider - one provider route owned by this adapter. + * @param _model - exact model id passed to {@link GenerateOptions.model}. + * @returns provider-owned context metadata, or `undefined` when unavailable. + */ + resolveModelContext( + _provider: string, + _model: string, + ): Promise<LlmModelContext | undefined>; + /** + * Stream one model call as raw chunks. The only required method. + * @param options - the fully-assembled request; implementations must honor `options.signal`. + * @returns the chunk stream, obeying the adapter contract documented on `StreamChunk`. + */ + abstract stream(options: GenerateOptions): AsyncIterable<StreamChunk>; +} +``` + +`ContentBlockType`(`index` 关联块所携带的键集合)派生自 `ContentBlockMap`: + +```ts type-equiv +/** + * Merge-extensible content blocks keyed by `type`. New core blocks must land + * with adapter, UI, and compaction support. + */ +interface ContentBlockMap { + 'text': TextBlock + 'reasoning': ReasoningBlock + 'tool-call': ToolCallBlock + 'tool-result': ToolResultBlock +} +``` + +块接口详见 [core.md § Content blocks and messages](core.md#content-blocks-and-messages)。 diff --git a/docs/core-data-structures/persistence.i18n.yaml b/docs/core-data-structures/persistence.i18n.yaml new file mode 100644 index 0000000000..b7d8fda4e8 --- /dev/null +++ b/docs/core-data-structures/persistence.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +persistence.md: dc497fd85f44660c0a981579351b5cfbe0040a4d +persistence.zh.md: 5236f4fe2ba8ad1be7e74bffafebfea19014d7aa diff --git a/docs/core-data-structures/persistence.md b/docs/core-data-structures/persistence.md index f45eb0417a..dc497fd85f 100644 --- a/docs/core-data-structures/persistence.md +++ b/docs/core-data-structures/persistence.md @@ -1,5 +1,7 @@ # Session Persistence +English | [中文](persistence.zh.md) + The **durability seam** for the event log. [session.md](session.md) describes the in-memory `Session` — the append-only `SessionEvent` log that is the source of truth. This page describes how that log is made durable: the abstract `SessionPersistence` service, its backends, the flush checkpoint, crash recovery, and the metadata header that travels alongside the log. The event vocabulary the log carries is enumerated, member by member, in the generated [persistence log event catalog](../persistence-catalog.md). The seam is a textbook [capability seam](../../.agents/notes/implemented/architecture/2026-06-13-capability-seams.md): one abstract service ([dsh-session-persistence](../../packages/session-persistence/session-persistence), `ctx.sessionPersistence`) defining locate/create/append, crash-repairing load, non-mutating inspect, and lightweight list/snapshot observation over the existing `SessionEvent` — **no parallel persisted type** — and two interchangeable backends that pass the same `runPersistenceContract` suite. See the [session-persistence Agent Note](../../.agents/notes/implemented/architecture/2026-06-14-session-persistence.md). @@ -53,7 +55,7 @@ interface SessionHeader { readonly version: number /** The session's id (mirrors the {@link Session}'s id). */ readonly id: SessionId - /** Unix epoch milliseconds when the session was created. */ + /** Non-negative safe-integer Unix epoch milliseconds when the session was created. */ readonly createdAt: number /** Absolute working directory the session was created in (if any). */ readonly cwd?: string diff --git a/docs/core-data-structures/persistence.zh.md b/docs/core-data-structures/persistence.zh.md new file mode 100644 index 0000000000..5236f4fe2b --- /dev/null +++ b/docs/core-data-structures/persistence.zh.md @@ -0,0 +1,134 @@ +# 会话持久化 + +[English](persistence.md) | 中文 + +事件日志的**持久性 seam**。[session.md](session.md) 描述了内存中的 `Session`:仅追加的 `SessionEvent` 日志即为真源。本页描述如何使该日志持久化:抽象的 `SessionPersistence` 服务、它的后端、flush 检查点、崩溃恢复,以及随日志一同存储的元数据头。日志承载的事件词汇在生成的[持久化日志事件目录](../persistence-catalog.md)中逐项列举。 + +该 seam 是典型的[能力 seam](../../.agents/notes/implemented/architecture/2026-06-13-capability-seams.md):一个抽象服务([dsh-session-persistence](../../packages/session-persistence/session-persistence),`ctx.sessionPersistence`)在现有 `SessionEvent` 上定义 locate/create/append、会执行崩溃修复的 load、不会修改数据的 inspect,以及轻量的 list/snapshot 观察——**没有平行的持久化类型**——以及两个可互换、通过同一套 `runPersistenceContract` 的后端。见 [session-persistence Agent Note(agent 决策记录)](../../.agents/notes/implemented/architecture/2026-06-14-session-persistence.md)。 + +## flush 检查点 + +`session/event` 是一个*同步*通知;持久化插件会将事件复制到逐会话控制器,并立即启动写入而不阻塞生产方。并发事件会加入当前批次;在该批次写入期间接纳的事件会触发后续批次。`session/flush` 会等待当前与待处理批次全部清空,因此循环仍将其用作在领取下一个普通轮次之前的顺序与错误观察检查点。立即写入被拒绝时会保留对应事件;显式 flush 会重试这些事件,并通过 `agent/error` 和 logger 报告失败,绝不会把失败记录成已关闭轮次之后的会话事件。dispose(资源释放)会执行同样的最终排空。 + +## 崩溃恢复保留被中断的轮次 + +后端重新加载一个在轮次中途崩溃的日志时,会发现一个已打开的 `turn/start` 却没有 `turn/end`。它**不会**截断日志:在长周期任务中,单个轮次可能非常庞大(许多步骤、大量工具输出),而这些事件在崩溃前已被持久追加。后端改为用一个合成的 `turn/end { reason: { kind: 'interrupted' } }` 关闭这个遗留轮次,保持日志平衡与轮次闭合不变式。`interrupted` 是唯一一个不由循环发出的 `TurnEndReason`(见 [session.md](session.md#why-a-turn-ended-turnendreasonmap))。 + +修复仅适用于冷会话。对于活跃 id,`SessionPersistence.load(id)` 会对内存日志拍摄快照,等待该快照完成持久化,并且只在日志平衡时连同已存储的 header 返回;若活跃轮次仍未闭合,则拒绝操作,而不是添加合成的中断边界。由协调器管理的冷加载会在后端读取和修复写入期间占用该 id,因此并发发布同 id 的活跃会话会被拒绝并回滚。HMR 也会接管活跃前缀,而不会关闭其中正在进行的轮次。 + +`SessionPersistence.inspect(id)` 是恢复机制面向观察方的对等操作:它返回已存储有效前缀的独立副本,不截断不完整记录、不添加中断结束事件,也不发布写入状态。同 id 串行化确保它与后端写入保持一致。派生读取模型使用 `inspect`,绝不使用 `load`,因此即使活跃所有权并发建立,观察已落检查点但仍未闭合的轮次也不会修改日志。 + +## `SessionLocation`——可选的逐会话产物目标 + +`SessionPersistence.locate(meta)` 会同步解析一个归后端所有的独立产物,而不会读取、创建或 flush 它。JSONL 返回其绝对目标路径;SQLite 因各会话共享一个数据库而返回 `undefined`。因此,返回的路径可能指向尚不存在、或还不包含当前尚未 flush 的轮次;它是位置提示,不是授权或新鲜度保证。 + +```ts type-equiv +/** + * A backend-resolved, per-session local artifact location. The path is an + * absolute target path and can name an artifact that has not materialized yet. + * Consumers must treat it as a location hint, never as an authorization token. + */ +interface SessionLocation { + /** Backend-specific artifact kind, for example `jsonl`. */ + readonly kind: string + /** Absolute path to this session's backend-owned artifact. */ + readonly path: string +} +``` + +## `SessionHeader`:日志旁的元数据 + +每个会话的元数据与事件日志**分开**存储:格式版本、cwd、血统与 seed 边界是存储层关注点而非对话事件,因此不进入 `SessionEventMap`,也不会到达 `deriveMessages()`。header 通过 `session.header` 附加到 `Session` 上。 + +源码:[`packages/core/session/src/types.ts`](../../packages/core/session/src/types.ts) + +```ts type-equiv +/** + * Immutable validated storage metadata, kept outside the conversation event log. + */ +interface SessionHeader { + /** + * On-disk format version, stamped from {@link SESSION_FORMAT_VERSION} when the + * session is created. A persistence backend rejects any other version on load + * (no migration — see the constant). + */ + readonly version: number + /** The session's id (mirrors the {@link Session}'s id). */ + readonly id: SessionId + /** Non-negative safe-integer Unix epoch milliseconds when the session was created. */ + readonly createdAt: number + /** Absolute working directory the session was created in (if any). */ + readonly cwd?: string + /** The session this one was forked from (seed lineage), if any. */ + readonly parentSession?: SessionId + /** + * How many leading events were inherited through a seed. Persisting this + * boundary lets resume and replay distinguish parent history from child work. + */ + readonly seedLength?: number + /** + * Delegation depth: absent (zero) for a top-level session, parent depth + 1 + * for a subagent child. Persisted so a recursion budget survives restart and + * resume — a runtime-only depth would reset a resumed child to top-level. + */ + readonly delegationDepth?: number +} +``` + +## `CreateSessionOptions`:seed 与元数据 + +通过 store 创建 `Session` 时会接收 `seed`(回放/fork 现有事件日志)与 `meta`(store 折叠进 `SessionHeader` 的存储层字段)。store 填充 `version`/`id` 并为 `createdAt` 提供默认值;调用方提供已校验的绝对 `cwd`、`parentSession` 谱系、`seedLength` 种子边界、`delegationDepth`,以及——仅在重建已持久化会话时——需要保留的原始 `createdAt`。 + +```ts type-equiv +/** + * Options for creating a {@link Session} via the store. `seed` replays/forks + * an existing event log; `meta` carries the caller-supplied storage fields the + * store folds into a {@link SessionHeader}. + */ +interface CreateSessionOptions { + /** Events to seed the new session with (replay/fork). */ + readonly seed?: readonly SessionEvent[] + /** + * Storage metadata read once before publication. `seedLength` is explicit + * because a resumed seed contains the full stored log, not only its inherited prefix. + */ + readonly meta?: { + readonly cwd?: string + readonly parentSession?: SessionId + readonly createdAt?: number + readonly seedLength?: number + readonly delegationDepth?: number + } +} +``` + +因此,回放/fork 的调用方式为 `ctx.sessions.create(id, { seed: seedEvents })`;将一个*持久化*会话恢复为活跃 agent 的调用方式为 `ctx.agents.resume({ resumeSessionId })`。 + +## 轻量源修订号 + +派生状态的消费方会在加载完整事件日志之前比较一个低开销的不透明修订号。其表示由持久化后端拥有,并随 append 或会修改数据的 load 修复以事务方式改变;调用方仅比较修订号是否相等。 + +```ts type-equiv +/** + * Backend-owned token that identifies both one storage source and one revision + * of a persisted session log. + */ +type SessionPersistenceRevision = Branded<'SessionPersistenceRevision'> +``` + +```ts type-equiv +/** Lightweight immutable source identity returned without loading a full log. */ +interface SessionPersistenceSnapshot { + /** Detached metadata for one materialized session. */ + header: SessionHeader + /** Opaque source-qualified token that changes whenever this stored log changes. */ + revision: SessionPersistenceRevision +} +``` + +## 后端 + +两者都实现同一个抽象 `SessionPersistence`(在 `SessionEvent` 上执行 locate/create/append/load/inspect/list/listSnapshots),并通过 `runPersistenceContract`,证明该 seam 确实与后端无关: + +- **[dsh-session-persistence-jsonl](../../packages/session-persistence/session-persistence-jsonl)**——每个会话一份仅追加的逻辑 JSONL 日志,默认存储为带 checksum 的连续 Zstandard frame,也可配置为原始行;支持崩溃安全的原子写入、被中断轮次的恢复以及读取/回放路径。 +- **[dsh-session-persistence-sqlite](../../packages/session-persistence/session-persistence-sqlite)**:基于 `node:sqlite`,每个 `SessionEvent` 一行。行结构 `(session_id, seq, type, time, data, source_event_seqs, surface_op)` 与事件 1:1 映射(包含可选的 surface 元数据),因此没有需要保持同步的并行持久化 schema。 diff --git a/docs/core-data-structures/sandbox.i18n.yaml b/docs/core-data-structures/sandbox.i18n.yaml new file mode 100644 index 0000000000..f8189f4e15 --- /dev/null +++ b/docs/core-data-structures/sandbox.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +sandbox.md: 9bc05fa06f22fdc9ac9e8aacd482c1e7c2f2edec +sandbox.zh.md: 9a52f126758fe0e7988715c7824e963bd6e6ea84 diff --git a/docs/core-data-structures/sandbox.md b/docs/core-data-structures/sandbox.md index bdc86287fb..9bc05fa06f 100644 --- a/docs/core-data-structures/sandbox.md +++ b/docs/core-data-structures/sandbox.md @@ -1,5 +1,7 @@ # Process Sandbox +English | [中文](sandbox.zh.md) + The process-sandbox seam of [dsh-sandbox](../../packages/sandbox/sandbox) wraps a same-world subprocess argv in a file-effect policy without coupling consumers to a platform runner. [dsh-sandbox-local](../../packages/sandbox/sandbox-local) supplies the Linux bwrap/Landlock and macOS Seatbelt backends; [dsh-bash-sandbox](../../packages/bash/bash-sandbox) is the first consumer. Containers, microVMs, and remote execution are sibling implementations of whole capability seams, not providers of `ctx.sandbox`. Source: [`packages/sandbox/sandbox/src/index.ts`](../../packages/sandbox/sandbox/src/index.ts) diff --git a/docs/core-data-structures/sandbox.zh.md b/docs/core-data-structures/sandbox.zh.md new file mode 100644 index 0000000000..9a52f12675 --- /dev/null +++ b/docs/core-data-structures/sandbox.zh.md @@ -0,0 +1,127 @@ +# 进程沙箱 + +[English](sandbox.md) | 中文 + +[dsh-sandbox](../../packages/sandbox/sandbox) 的进程沙箱 seam 将与宿主共享文件系统和内核的子进程 argv 包装在文件效果策略中,而不将消费方耦合到特定平台运行器。[dsh-sandbox-local](../../packages/sandbox/sandbox-local) 提供 Linux bwrap/Landlock 与 macOS Seatbelt 后端;[dsh-bash-sandbox](../../packages/bash/bash-sandbox) 是第一个消费方。容器、microVM 和远程执行是完整能力 seam 的兄弟实现,而非 `ctx.sandbox` 的提供方。 + +源码:[`packages/sandbox/sandbox/src/index.ts`](../../packages/sandbox/sandbox/src/index.ts) + +## 模式与强制执行 + +`SandboxMode` 仅管控文件系统效果。`read-only` 拒绝所有写入(必需的 `/dev/null` 接收器除外);`workspace-write` 允许在工作区根目录及后端承诺的临时区域下写入;`danger-full-access` 绕过隔离。网络与进程可见性不在此处的定义范围内。 + +```ts type-equiv +/** + * File-effect policy for confined processes. `read-only` permits only required + * sinks such as `/dev/null`; `workspace-write` also permits the workspace and a + * backend-defined temp area; `danger-full-access` bypasses confinement. Network + * and process visibility are outside this vocabulary. + */ +type SandboxMode = 'read-only' | 'workspace-write' | 'danger-full-access' +``` + +只有前两种模式可以发送给提供方。`danger-full-access` 的消费方直接 spawn 原始 argv,不调用 `ctx.sandbox`。 + +```ts type-equiv +/** A confining (non-`danger-full-access`) mode — the modes a {@link SandboxPolicy} can carry. */ +type ConfinedSandboxMode = Exclude<SandboxMode, 'danger-full-access'> +``` + +强制执行程度是一个报告事实。`full` 表示后端管控了该模式承诺的所有文件效果;`partial` 表示活跃后端或较旧的内核 ABI 仅管控其中一个子集,因此要求绝对保证的消费方必须拒绝或向上暴露这一区别。 + +```ts type-equiv +/** + * Enforcement completeness for this host. `partial` means an active backend or + * older kernel ABI cannot govern every promised file effect; callers requiring + * an absolute boundary must not treat it as `full`. + */ +type SandboxEnforcement = 'full' | 'partial' +``` + +## 逐调用策略 + +完整执行策略会按每次能力调用解析并携带。它包括 `danger-full-access`,因此消费方可以只解析一次策略,再决定是否绕过约束。普通工具调用从调用会话的不可变 cwd 派生 `workspaceRoot`;部署配置是没有 agent(智能体)时的回退值。root 会先按文件系统语义规范化,再做词法规范化,因此包含 `symlink/..` 的 cwd 会标识所生成进程实际运行的目录。 + +```ts type-equiv +/** + * The complete file-effect policy resolved for one capability call. The root + * is carried even under modes that do not consume it so callers can resolve + * policy once before choosing the enforcement path. + */ +interface SandboxExecutionPolicy { + /** The file-effect mode this execution runs under. */ + mode: SandboxMode + /** Absolute root directory `workspace-write` may write under. */ + workspaceRoot: string +} +``` + +`ctx.sandboxPolicy.resolve()` 接收活跃会话;对于已批准的重试,还接收显式模式。该服务拥有优先级与 root 回退规则,使 bash 和 fs 不必重复实现。 + +```ts type-equiv +/** Inputs that select the sandbox policy for one capability call. */ +interface SandboxPolicyRequest { + /** Calling session; its immutable cwd becomes the workspace boundary. */ + session?: Session + /** Explicit approved mode override, which outranks session policy. */ + mode?: SandboxMode +} +``` + +只有受约束的执行会到达 `ctx.sandbox`;其提供方策略在保留同一 root 的同时收窄模式。这使并发会话、消费方与一次性提权重试可以向同一提供方请求不同边界,而无需改变提供方状态。 + +```ts type-equiv +/** + * What one confined execution is allowed to touch — carried PER CALL, not + * fixed on the provider: two consumers may confine under different policies + * at the same instant (bash under `read-only` while a confined child agent + * needs its state directory writable), and an approved escalated retry is a + * new call with a wider policy. Defaulting/resolution is an explicit step at + * the consumer boundary; the provider treats the policy as fully specified. + */ +interface SandboxPolicy extends SandboxExecutionPolicy { + /** The file-effect mode this execution runs under. */ + mode: ConfinedSandboxMode +} +``` + +## 包装后的 argv 与分类方言 + +`ConfinedArgv` 是消费方实际 spawn 的内容。除了替换后的 argv,它还携带后端的强制执行事实和两种正交的 stderr 方言。`denialSignatures` 用于识别沙箱正常工作时被隔离命令被阻止的情况。`runnerFailureSignatures` 用于识别沙箱运行器在执行命令之前拒绝或失败的情况;消费方应先检查后者,将其作为沙箱基础设施故障上报,而非普通任务失败。 + +```ts type-equiv +/** + * A {@link SandboxProvider.confine} result: the argv to spawn in place of + * the caller's own, plus the enforcement completeness the selected backend + * achieves for it. + */ +interface ConfinedArgv { + /** The wrapped argv (runner, profile, separator, then the caller's argv). */ + argv: string[] + /** How completely the selected backend enforces the policy's file effects. */ + enforcement: SandboxEnforcement + /** + * The selected backend's denial DIALECT: the case-insensitive stderr + * substrings a file effect denied by THIS backend produces (EROFS text + * under bwrap's read-only binds, EACCES under Landlock, EPERM under + * Seatbelt). A consumer that infers denials from a failed run's stderr + * matches against exactly these rather than a cross-backend union — the + * union claims denials a given backend never produces. + */ + denialSignatures: readonly string[] + /** + * Case-insensitive signatures for runner failure before command execution. + * Consumers check these before denial signatures: runner failure means the + * command never ran, while denial means confinement worked and blocked it. + */ + runnerFailureSignatures: readonly string[] +} +``` + +运维人员配置的本地运行器必须为自身的 pre-exec 拒绝方言提供至少一条 `runnerFailureSignatures` 条目;提供方会自动添加外层 shell 的 missing 和 unexecutable 形式。这使得可执行的自定义运行器拒绝其 profile 的情况能够与被包装命令以相同状态码退出的情况区分开来。 + +## 提供方与 fail-closed 错误 + +`ctx.sandbox.confine(argv, policy)` 返回一个 `ConfinedArgv`,或在没有可用后端时抛出 `SandboxUnavailableError`(错误码 `SANDBOX_UNAVAILABLE`)。已选定的运行器也可能在执行时 fail-closed,此时其失败签名承载相同的基础设施含义。对于受限策略,静默的无隔离透传永远不合法。 + +提供方探测在多个候选后端之间仲裁,结果在提供方生命周期内缓存。只有一个候选后端的平台可以直接选定它;执行时拒绝仍保留安全属性。本地提供方将 bwrap 和 Seatbelt 报告为 full,并保留 Landlock 启动器的 full/partial 内核裁定。 diff --git a/docs/core-data-structures/scope.i18n.yaml b/docs/core-data-structures/scope.i18n.yaml new file mode 100644 index 0000000000..b565e11461 --- /dev/null +++ b/docs/core-data-structures/scope.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +scope.md: 73a697f2843293daffff85dabf4656346f7dcd04 +scope.zh.md: f3c591da2befdcff69d89ad0667653392111fb8e diff --git a/docs/core-data-structures/scope.md b/docs/core-data-structures/scope.md index e9869f3152..73a697f284 100644 --- a/docs/core-data-structures/scope.md +++ b/docs/core-data-structures/scope.md @@ -1,5 +1,7 @@ # Scoped Registration +English | [中文](scope.zh.md) + The [scope package](../../packages/core/scope) supplies the identity, carrier, and scoped-layer vocabulary that makes one registration context mean both per-agent visibility and shared lifetime ownership. It is a library primitive rather than a Cordis service; the [agent-scope runtime-design Agent Note](../../.agents/notes/implemented/architecture/2026-07-12-agent-scope-runtime-design.md#scope-routing-one-opaque-key-selects-one-layer) owns the lifecycle rationale, the [shared-storage Agent Note](../../.agents/notes/implemented/architecture/2026-07-12-scoped-layers-store.md) owns the registry-layer decision, and the package [README](../../packages/core/scope/README.md) owns the callable API and filtering semantics. Sources: [`packages/core/scope/src/index.ts`](../../packages/core/scope/src/index.ts) and [`packages/core/scope/src/store.ts`](../../packages/core/scope/src/store.ts). diff --git a/docs/core-data-structures/scope.zh.md b/docs/core-data-structures/scope.zh.md new file mode 100644 index 0000000000..f3c591da2b --- /dev/null +++ b/docs/core-data-structures/scope.zh.md @@ -0,0 +1,59 @@ +# 作用域注册 + +[English](scope.md) | 中文 + +[scope 包(package)](../../packages/core/scope)提供 identity、carrier 与 scoped-layer 词汇,使同一个注册上下文同时代表逐 agent(智能体)可见性和共享生命周期所有权。它是库原语,而不是 Cordis 服务;生命周期设计理由由 [agent-scope 运行时设计 Agent Note(agent 决策记录)](../../.agents/notes/implemented/architecture/2026-07-12-agent-scope-runtime-design.md#scope-routing-one-opaque-key-selects-one-layer)规定,注册表层决策由[共享存储 Agent Note](../../.agents/notes/implemented/architecture/2026-07-12-scoped-layers-store.md)规定,可调用 API 与过滤语义则由包 [README](../../packages/core/scope/README.md)规定。 + +源码:[`packages/core/scope/src/index.ts`](../../packages/core/scope/src/index.ts) 与 [`packages/core/scope/src/store.ts`](../../packages/core/scope/src/store.ts)。 + +## 身份标识与分发载体 + +`ScopeKey` 是一个不透明的对象身份标识。已交付的 agent loop(智能体循环)使用活跃的 `Agent` 对象作为自身的 key,但该原语从不检视该对象。 + +```ts type-equiv +/** An opaque, identity-compared scope key. */ +type ScopeKey = object +``` + +`Scoped<T>` 是编译期品牌标记,标注在 `scopeTarget(base, key)` 返回的不透明路由接收器上。作用域过滤的事件声明要求以此载体作为 `this` 类型,而真正的事件主体仍作为显式参数传入。 + +```ts type-equiv +/** + * A routing-only event receiver built by {@link scopeTarget}. The type + * parameter records the subject type for dispatch checking; the carrier does + * not expose the subject's properties. Event payloads carry the real subject. + */ +type Scoped<T extends object> = object & { readonly [ScopedBrand]: T } +``` + +## 拥有所有权的注册上下文 + +`Scope` 将带标签的注册上下文与两个拆卸接口配对。`rawDispose` 保留有序复合 effect 所需的精确 Cordis disposer 身份;`dispose()` 是面向直接调用方和竞态调用方的公共停稳边界。 + +```ts type-equiv +/** A minted registration scope and its quiescent disposal boundaries. */ +interface Scope { + /** Context through which scope-owned registrations are made. */ + ctx: Context + /** Exact Cordis disposer, used when nesting this scope in an ordered composite effect. */ + rawDispose: () => Promise<void> | void + /** Dispose every scope-owned registration; racing calls await the same completion. */ + dispose(): Promise<void> +} +``` + +## 带作用域的注册表层 + +`ScopeLayer` 表示一个注册表在全局或确切作用域层级的完整贡献。具体 layer 可以聚合多个具名与匿名 table;整个 layer 为空时,`ScopedLayers` 可以回收带作用域状态,而不会丢弃兄弟 table。 + +```ts type-equiv +/** One scope's aggregate contribution to a registry. */ +interface ScopeLayer { + /** Whether every table in this layer is empty. */ + isEmpty(): boolean +} +``` + +`ScopedLayers<L>` 拥有立即创建的全局 layer,以及惰性创建的确切作用域 layer。读取不会创建 layer:`peek(undefined)` 表示没有 overlay,而 `merge()` 会物化按插入顺序排列的全局具名 entry,随后是带作用域的 shadow。注册使用同一个上下文表示可见性与 Cordis effect 所有权,在可选通知前收集一个同步 undo,返回 Cordis 的确切 disposer,并且只在带作用域 layer 的完整 `ScopeLayer` 为空时回收它。 + +`NamedEntries<V>` 提供按插入顺序的查找与 live iteration,重复错误由调用方所有。`AnonymousEntries<V>` 为每次 append 分配唯一标识,使相等的值仍相互独立。迭代在同一非空 table generation 内保持 live;排空 table 会让现有 iterator 与后续插入脱离。两者都返回幂等的确切 entry undo;共享的 `EntryValues` 实现接口不公开。 diff --git a/docs/core-data-structures/session-query.i18n.yaml b/docs/core-data-structures/session-query.i18n.yaml new file mode 100644 index 0000000000..2cba0f9b42 --- /dev/null +++ b/docs/core-data-structures/session-query.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +session-query.md: c6dde8714a0875d46cf7b49cc181daab8f44afe0 +session-query.zh.md: 44be8b7f89e1576e54c8dc3cb60619d6728c6895 diff --git a/docs/core-data-structures/session-query.md b/docs/core-data-structures/session-query.md index 25315e3166..c6dde8714a 100644 --- a/docs/core-data-structures/session-query.md +++ b/docs/core-data-structures/session-query.md @@ -1,5 +1,7 @@ # Session Query +English | [中文](session-query.zh.md) + Query vocabulary over the live-preferred logical session corpus. The [interface package](../../packages/session-query/session-query) owns exact reads, source precedence, relationship tracing, semantic extraction, and provider-independent filters, while the [SQLite package](../../packages/session-query/session-query-sqlite) owns the concrete full-text index lifecycle. Source: [`packages/session-query/session-query/src/types.ts`](../../packages/session-query/session-query/src/types.ts) diff --git a/docs/core-data-structures/session-query.zh.md b/docs/core-data-structures/session-query.zh.md new file mode 100644 index 0000000000..44be8b7f89 --- /dev/null +++ b/docs/core-data-structures/session-query.zh.md @@ -0,0 +1,304 @@ +# 会话查询 + +[English](session-query.md) | 中文 + +本文定义面向优先使用 live 数据的逻辑会话语料库的查询词汇。[接口包(package)](../../packages/session-query/session-query)负责精确读取、来源优先级、关系追踪、语义提取,以及与提供方无关的过滤器;[SQLite 包](../../packages/session-query/session-query-sqlite)负责具体全文索引的生命周期。 + +源码:[`packages/session-query/session-query/src/types.ts`](../../packages/session-query/session-query/src/types.ts) + +## 逻辑记录 + +`SessionRecord` 由跨语料库列表返回。它独立于克隆后的实时优先 header 暴露源可用性。`SessionEventRecord` 是轻量的原始日志投影;分类使用与 model-history 推导相同的 `foldSurface()` 状态转换。 + +```ts type-equiv +/** Whether an event is current model context, replaced context, or raw-log-only. */ +type SessionEventSurface = 'current' | 'shadowed' | 'log-only' +``` + +```ts type-equiv +/** Lightweight identity and source availability for one logical session. */ +interface SessionRecord { + /** Cloned session header selected from the live-preferred corpus. */ + header: SessionHeader + /** Whether the id currently exists in `ctx.sessions`. */ + live: boolean + /** Whether the active persistence backend currently materializes the id. */ + persisted: boolean +} +``` + +`SessionLogSnapshot` 是供恢复预检使用的完整原始日志:它脱离运行时,并经过回放验证。`SessionSurfaceSnapshot` 表示一次精确读取的 surface 观测结果,而不是持续保留的订阅。 + +```ts type-equiv +/** One validated detached observation of a logical session's complete raw log. */ +interface SessionLogSnapshot { + /** Cloned session header selected from the same observation as `events`. */ + session: SessionHeader + /** Cloned contiguous raw events after persistence repair and replay validation. */ + events: SessionEvent[] +} +``` + +```ts type-equiv +/** One atomic live-preferred observation of a session's current model surface. */ +interface SessionSurfaceSnapshot { + /** Cloned session header selected from the same corpus observation as `events`. */ + session: SessionHeader + /** Highest raw-log seq included in the observation, or `null` for an empty log. */ + capturedThroughSeq: number | null + /** Cloned current surface events in model-history order. */ + events: SurfaceEvent[] +} +``` + +```ts type-equiv +/** Lightweight metadata for one event within a logical session. */ +interface SessionEventRecord { + /** Session that owns the event. */ + sessionId: SessionId + /** Monotonic event seq within the session. */ + seq: number + /** Discriminant of the session event. */ + type: SessionEventType + /** Event timestamp in Unix epoch milliseconds. */ + time: number + /** Event placement in the folded session surface. */ + surface: SessionEventSurface +} +``` + +## 与提供方无关的过滤器和文档 + +会话和事件过滤器数组内的各项按逻辑与(AND)组合;单个列表子句中的各值按逻辑或(OR)组合。范围包含两端。事件的 `text` 子句会对提取出的语义文本执行正则表达式扫描:搜索文本按字面量处理,Unicode 字符不区分大小写,空白字符可灵活匹配;该过程与全文搜索提供方无关。 + +```ts type-equiv +/** + * One logical-session predicate. A filter array is ANDed; `values` within a + * clause are ORed. + */ +type SessionResultFilter = + | { kind: 'id'; values: readonly SessionId[] } + | { kind: 'cwd'; values: readonly (string | null)[] } + | ({ kind: 'created-at' } & SessionResultRange) + | { kind: 'parent'; values: readonly (SessionId | null)[] } + | { kind: 'availability'; values: readonly SessionAvailability[] } +``` + +```ts type-equiv +/** + * One event predicate. A filter array is ANDed; list-valued clauses are ORed. + * Text is a literal, case-insensitive, whitespace-flexible semantic-text scan. + */ +type SessionEventResultFilter = + | ({ kind: 'seq' } & SessionResultRange) + | ({ kind: 'time' } & SessionResultRange) + | { kind: 'type'; values: readonly SessionEventType[] } + | { kind: 'surface'; values: readonly SessionEventSurface[] } + | { kind: 'text'; text: string } +``` + +```ts type-equiv +/** Searchable semantic document derived from one session event. */ +interface SessionEventSearchDocument extends SessionEventRecord { + /** First-party semantic text used by scan filters and full-text indexes. */ + text: string +} +``` + +`ctx.sessionQuery.filterSessions(filters)` 会对完整的逻辑会话语料库应用 `SessionResultFilter`;`ctx.sessionQuery.filterEvents(sessionId, filters)` 按 seq 升序返回匹配的文档。消息、推理(reasoning)、工具调用和工具结果、被阻止的提示词、待办事项,以及失败和状态详情会纳入语义文本;结构事件和流分片则不会。 + +## 全文搜索结果页 + +整合后的 `ctx.sessionQuery` seam 提供两个全文搜索范围。`searchSessions()` 按匹配度最强的事件对语料库分组;`searchEvents()` 搜索单个会话。请求将不透明游标与规范化后的查询、元数据过滤器和结果数量上限绑定。提供方的元数据过滤器有意不包含事件文本扫描。 + +```ts type-equiv +/** Provider-owned opaque continuation token returned by session search. */ +type SessionSearchCursor = Branded<'SessionSearchCursor'> +``` + +```ts type-equiv +/** Cross-session full-text search request. */ +interface SessionSearchRequest { + /** Full-text query interpreted as data, never executable FTS syntax. */ + query: string + /** Logical-session predicates applied before event ranking. */ + sessionFilters?: readonly SessionResultFilter[] + /** Event predicates applied before event ranking. */ + eventFilters?: readonly SessionEventMetadataFilter[] + /** Maximum sessions in this page. */ + limit?: number + /** Opaque cursor returned for the identical normalized request. */ + cursor?: SessionSearchCursor +} +``` + +```ts type-equiv +/** Within-session full-text search request. */ +interface SessionEventSearchRequest { + /** Session whose live-preferred logical log is searched. */ + sessionId: SessionId + /** Full-text query interpreted as data, never executable FTS syntax. */ + query: string + /** Event predicates applied before ranking. */ + filters?: readonly SessionEventMetadataFilter[] + /** Maximum events in this page. */ + limit?: number + /** Opaque cursor returned for the identical normalized request. */ + cursor?: SessionSearchCursor +} +``` + +```ts type-equiv +/** One cursor-paginated result page. */ +interface SessionSearchPage<T> { + /** Results for this page in contract-defined order. */ + items: readonly T[] + /** Opaque continuation cursor, absent on the final page. */ + nextCursor?: SessionSearchCursor +} +``` + +```ts type-equiv +/** One event full-text search hit with a bounded plain-text excerpt. */ +interface SessionEventSearchHit extends SessionEventRecord { + /** Plain text excerpt selected around the match. */ + snippet: string +} +``` + +```ts type-equiv +/** One grouped cross-session hit, ranked by its strongest matching event. */ +interface SessionSearchHit extends SessionRecord { + /** Strongest matching event for this session. */ + bestMatch: SessionEventSearchHit +} +``` + +## 会话谱系 + +`SessionLineageTrace` 按由近及远的顺序携带已知 parent,并携带一片由直接 descendant 递归嵌套而成的森林。完整性判别字段使已知 root 与缺失 parent 互斥。 + +```ts type-equiv +/** Recursive descendant node in a session-lineage trace. */ +interface SessionLineageNode { + /** Detached logical-corpus record for this descendant. */ + session: SessionRecord + /** Direct children, each carrying its own recursive descendants. */ + descendants: SessionLineageNode[] +} +``` + +```ts type-equiv +/** Known ancestry and descendants for one logical session. */ +type SessionLineageTrace = { + /** Detached record for the session that was traced. */ + target: SessionRecord + /** Known parents from the immediate parent outward. */ + ancestors: SessionRecord[] + /** Complete known descendant trees rooted at the target's direct children. */ + descendants: SessionLineageNode[] +} & ( + | { + /** The complete parent chain is present in the logical corpus. */ + complete: true + /** Detached record at the top of the complete lineage. */ + root: SessionRecord + } + | { + /** The parent chain leaves the visible logical corpus. */ + complete: false + /** First parent id that is not present in the logical corpus. */ + unresolvedParentId: SessionId + } +) +``` + +## 有界事件读取 + +请求指定一个原始 seq 及可选的邻近数量。结果携带 `SessionHeader` 而非可用性标志,使已知的实时目标可以独立于持久化健康状态。 + +```ts type-equiv +/** Request for one event plus raw neighboring log context. */ +interface SessionEventReadRequest { + /** Session that owns the target event. */ + sessionId: SessionId + /** Target event seq. */ + seq: number + /** Number of preceding raw events to include. */ + before?: number + /** Number of following raw events to include. */ + after?: number +} +``` + +```ts type-equiv +/** Full target event and a bounded raw-log window. */ +interface SessionEventWindow { + /** Cloned header for the live-preferred source read. */ + session: SessionHeader + /** Full cloned target event. */ + target: SessionEvent + /** Full cloned events from `startSeq` through `endSeq`. */ + events: SessionEvent[] + /** First seq included in `events`. */ + startSeq: number + /** Last seq included in `events`. */ + endSeq: number +} +``` + +## 事件关系 + +事件追踪会区分位置性的 surface 替换与已记录 provenance。除 `replacementChain` 外,每个 seq 列表都包含直接链接;该链从目标沿直接 replacer 追踪到最终的位置替换。 + +```ts type-equiv +/** Request for direct surface and provenance relationships around one event. */ +interface SessionEventTraceRequest { + /** Session that owns the target event. */ + sessionId: SessionId + /** Target event seq. */ + seq: number +} +``` + +```ts type-equiv +/** Direct surface and provenance relationships for one event. */ +interface SessionEventTrace { + /** Lightweight target record. */ + target: SessionEventRecord + /** Immediate positional replacement event, when the target was shadowed. */ + replacedBy?: number + /** Positional replacers from the immediate replacement to the final replacement. */ + replacementChain: number[] + /** Surface nodes directly removed when the target itself performed a replacement. */ + replacedEventSeqs: number[] + /** Direct logged provenance sources in their recorded order. */ + sourceEventSeqs: number[] + /** Later events that directly name the target as a provenance source, in log order. */ + derivedEventSeqs: number[] +} +``` + +## 错误 + +封闭的 code 联合类型区分请求校验、目标缺失、surface 日志格式错误、可选后端故障与矛盾的源元数据。 + +```ts type-equiv +/** Stable machine-routable failure taxonomy for session reads, traces, and search. */ +type SessionQueryErrorCode = + | 'SESSION_QUERY_ABORTED' + | 'SESSION_QUERY_EVENT_NOT_FOUND' + | 'SESSION_QUERY_INDEX_FAILED' + | 'SESSION_QUERY_INVALID_CONFIG' + | 'SESSION_QUERY_INVALID_CURSOR' + | 'SESSION_QUERY_INVALID_FILTER' + | 'SESSION_QUERY_INVALID_LIMIT' + | 'SESSION_QUERY_INVALID_QUERY' + | 'SESSION_QUERY_INVALID_LINEAGE' + | 'SESSION_QUERY_INVALID_SURFACE' + | 'SESSION_QUERY_INVALID_WINDOW' + | 'SESSION_QUERY_PERSISTENCE_FAILED' + | 'SESSION_QUERY_SESSION_NOT_FOUND' + | 'SESSION_QUERY_STALE_CURSOR' + | 'SESSION_QUERY_SOURCE_CONFLICT' +``` diff --git a/docs/core-data-structures/session-reference.md b/docs/core-data-structures/session-reference.md index dbe3c43d35..d9a73c08c6 100644 --- a/docs/core-data-structures/session-reference.md +++ b/docs/core-data-structures/session-reference.md @@ -36,7 +36,7 @@ interface SessionReferenceCandidate { ## Prepared messages -Preparation preserves readable current-message content and returns at most one aggregated context. The host binds `contexts` to that exact `send()` or `steer()` call. +Preparation preserves readable current-message content and returns at most one aggregated context. The host binds `contexts` to that exact `followup()` or `steer()` call. ```ts type-equiv /** Message payload and the zero-or-one durable snapshot contexts bound to it. */ diff --git a/docs/core-data-structures/session.i18n.yaml b/docs/core-data-structures/session.i18n.yaml new file mode 100644 index 0000000000..f215956acf --- /dev/null +++ b/docs/core-data-structures/session.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +session.md: 7a9ae919fecef7db19f3ca67feb128bcba1db4f0 +session.zh.md: 9e1e9a4f39ed6919416ff5cebf345b43bbc450ea diff --git a/docs/core-data-structures/session.md b/docs/core-data-structures/session.md index ba1dcb98ba..7a9ae919fe 100644 --- a/docs/core-data-structures/session.md +++ b/docs/core-data-structures/session.md @@ -1,5 +1,7 @@ # Sessions +English | [中文](session.zh.md) + The in-memory, event-sourced model of [dsh-session](../../packages/core/session). A `Session` is an **append-only log** of typed `SessionEvent`s — the single source of truth for an agent's whole interaction history. The LLM message history is *derived* from the log, never stored separately; replay is re-derivation from the same events. How the log is made **durable** (the persistence seam, backends, crash recovery) is the sibling concern on [persistence.md](persistence.md). Source: [`packages/core/session/src/types.ts`](../../packages/core/session/src/types.ts) @@ -9,7 +11,13 @@ Source: [`packages/core/session/src/types.ts`](../../packages/core/session/src/t The append-only event types. Merge-extensible: a plugin declares extra event types via declaration merging — e.g. the [compaction seam](compaction.md) adds `compact/start` / `compact/summary` / `compact/end`, and `@deepseek-ai/dsh-hook-protocol` adds log-only `hook/invoked` / `hook/result` provenance for a hook bridge. Like `compact/*`, these are NOT `SurfaceEventType`s (no `surfaceOp`). The generated [persistence log event catalog](../persistence-catalog.md) enumerates every member — core and merged — with its payload, surface badge, and declaration site. ```ts type-equiv -/** Shared payload for ordinary and steering prompt messages. */ +/** + * Shared payload for user, injected-context, and steering prompt messages. A + * direct human prompt, a synthetic `agent.inject()` context, and mid-turn + * steering all project into the model transcript as verbatim user-role content; + * they are told apart by `source` (a non-`user` kind marks injected context), + * not by event type. `meta` carries durable model-hidden producer state. + */ interface PromptMessageData { /** Exact model-facing blocks, including any baked prompt-prefix contexts. */ content: ContentBlock[] @@ -17,6 +25,15 @@ interface PromptMessageData { source: MessageSource /** Present only when prompt-prefix contexts were baked into `content`. */ envelope?: PromptMessageEnvelope + /** + * Opaque durable JSON state retained on the event but hidden from the model + * projection. It is the intended channel for a future framing directive (a + * producer declares the frame, a dedicated renderer applies it — see the + * deferred note in + * ../../../../.agents/notes/implemented/simplification/2026-07-20-unwrap-injected-content-envelopes.md), + * so the surface keeps projecting `content` verbatim rather than wrapping it. + */ + meta?: JsonValue } ``` @@ -46,29 +63,21 @@ interface SessionEventMap { 'step/start': { turn: number; step: number } /** Closes step `step` of turn `turn`. */ 'step/end': { turn: number; step: number } - /** A user-visible prompt (the queued message claimed for this turn). */ + /** + * A user-role message on the model-visible surface: a direct human prompt + * (the queued message claimed for this turn), a synthetic `agent.inject()` + * context (file-change notices, subdir AGENTS.md, skill content, cron + * notifications, …), or an admitted goal continuation round. All three + * project their `content` verbatim; `source` (with a non-`user` kind marking + * injected context) is the only channel that tells them apart. An idle + * injection wraps this event in a one-shot turn so the log stays turn-enclosed. + */ 'user/message': PromptMessageData /** * Durable record of a prompt veto and its reason. It is log-only: the blocked * prompt never enters the model-visible surface, and its turn runs zero steps. */ 'prompt/blocked': { content: ContentBlock[]; source: MessageSource; reason: string } - /** - * In-session context injection (file-change notices, subdir AGENTS.md, - * skill content, cron notifications, …). Rendered into the derived history - * as a synthetic user-role message carrying `content` verbatim — NOT a - * user prompt. `meta` is durable JSON state omitted from the model - * projection; it is also the intended channel for any future framing - * directive (a producer declares the frame, a dedicated renderer applies it — - * see the deferred note in - * ../../../../.agents/notes/implemented/simplification/2026-07-20-unwrap-injected-content-envelopes.md), - * so the surface keeps projecting `content` verbatim rather than wrapping it. - */ - 'context/message': { - content: ContentBlock[] - source: MessageSource - meta?: JsonValue - } /** Raw stream chunk — token-level replay fidelity. */ 'assistant/chunk': { turn: number; step: number; chunk: StreamChunk } /** @@ -199,7 +208,7 @@ A proper discriminated union over `type` (not independent `type`/`data` unions), * * The {@link sourceEventSeqs} and {@link surfaceOp} fields are conditional: * they only exist on {@link SurfaceEventType} variants (`user/message`, - * `assistant/message`, `tool/result`, `context/message`, `steering/message`). + * `assistant/message`, `tool/result`, `steering/message`). * Non-surface events (boundary markers, chunks, usage, errors) never carry * surface metadata — the compiler enforces this at `Session.append()` * call sites. @@ -233,7 +242,7 @@ For `assistant/message`, a present `sourceEventSeqs: []` is a complete known-emp ## Surface types -The five message-producing types (`SurfaceEventType` — `user/message`, `assistant/message`, `tool/result`, `context/message`, `steering/message`) carry surface metadata declaring how they join the ordered derived surface. See the [session surface Agent Note](../../.agents/notes/implemented/architecture/2026-06-18-session-surface.md). +The four message-producing types (`SurfaceEventType` — `user/message`, `assistant/message`, `tool/result`, `steering/message`) carry surface metadata declaring how they join the ordered derived surface. See the [session surface Agent Note](../../.agents/notes/implemented/architecture/2026-06-18-session-surface.md). ### `SurfaceEventType` — the message-producing subset of event types @@ -247,7 +256,6 @@ type SurfaceEventType = | 'user/message' | 'assistant/message' | 'tool/result' - | 'context/message' | 'steering/message' ``` @@ -258,7 +266,7 @@ type SurfaceEventType = * How a session event entered the ordered surface. Only valid on * {@link SurfaceEventType} events. * - * - `'append'`: added to the tail — normal path for user/assistant/tool/context + * - `'append'`: added to the tail — normal path for user/assistant/tool/steering * messages. * - `{ op: 'replace', start, end }`: replaces surface nodes from `start` * (inclusive) through `end` (inclusive) with this node. Both must exist as @@ -465,7 +473,7 @@ declare class Session { - `user/message` → a user message carrying exact `content`; an optional envelope remains log-only display metadata. - `assistant/message` → an assistant message with the event's provider/model provenance and optional adapter-private replay state. Raw `assistant/chunk` events are replay/UI data and are **skipped** in derivation (the assembled message is authoritative). An **empty-content** `assistant/message` is also skipped — a max-tokens step cut off with no content still records an `assistant/message` to host its usage/provenance, but a content-less assistant turn must not enter the provider transcript. - `tool/result` → a user message carrying a `tool-result` block. -- `context/message` → a user-role message carrying its `content` verbatim at its chronological position. Optional JSON `meta` remains in the event log and is never rendered. +- `user/message` (injected context, i.e. non-`user` source) → a user-role message carrying its `content` verbatim at its chronological position. Optional JSON `meta` remains in the event log and is never rendered. - `steering/message` → a user-role message carrying exact `content` at its chronological position; an optional envelope remains log-only display metadata. Everything else (`turn/*`, `step/*`, plugin-owned `llm/retry`) is structural and does not project into a message. Token accounting reads per-step `assistant/chunk { type: 'usage' }` records and treats `assistant/message.usage` as the committed-step fallback when no usage chunk exists; failed model-request attempts have no assistant message, so their usage chunk is the durable accounting record. An operational error's step number is on `turn/end.reason` for `kind: 'error'`, with normalized `LlmFailure` facts for a final model-request failure and message/code for other live errors. Because this unreleased format intentionally has no compatibility promise, seed/load validation rejects request headers without provider+model and assistant messages without provider/model provenance instead of guessing a route for historical data. @@ -489,11 +497,12 @@ interface TurnTriggerMap { message: { kind: 'message'; source: MessageSource } /** * An out-of-band context injection (`agent.inject()`) made while the agent - * was idle. The loop wraps the injected `context/message` in a one-shot turn - * (`turn/start` → `context/message` → `turn/end`) so every event in the log - * stays turn-enclosed — the durability/replay boundary is the turn, and a - * bare event between turns would otherwise be indistinguishable from a crash - * tail on reload. + * was idle. The loop wraps the injected `user/message` (a non-`user` source, + * plugin by default) in a one-shot turn (`turn/start` → `user/message` → + * `turn/end`) so every event in the log stays turn-enclosed — the + * durability/replay boundary is the turn, and a bare event between turns would + * otherwise be indistinguishable from a crash tail on reload. The trigger's + * `source` mirrors that message's producer. */ injection: { kind: 'injection'; source: MessageSource } } @@ -542,13 +551,13 @@ interface TurnEndReasonMap { ## The turn-enclosure invariant -Every session event lives **inside** a turn (between a `turn/start` and its `turn/end`). The loop appends queued `user/message` events *after* `turn/start`, an idle `agent.inject()` wraps its `context/message` in a one-shot `injection` turn, and `appendOutOfBand()` similarly wraps an eligible log-only event when no turn is open. This makes the turn the single durability/replay boundary: a backend can treat anything after the last `turn/end` as an interrupted-crash tail without risking the loss of legitimately-recorded between-turn context. The optional `dsh-session/invariant` companion enforces it in dev through `ctx.invariants` (a message event outside an open turn throws). See [the turn-enclosure invariant Agent Note](../../.agents/notes/implemented/architecture/2026-06-15-turn-enclosure-invariant.md). +Every session event lives **inside** a turn (between a `turn/start` and its `turn/end`). The loop appends queued `user/message` events *after* `turn/start`, an idle `agent.inject()` wraps its `user/message` in a one-shot `injection` turn, and `appendOutOfBand()` similarly wraps an eligible log-only event when no turn is open. This makes the turn the single durability/replay boundary: a backend can treat anything after the last `turn/end` as an interrupted-crash tail without risking the loss of legitimately-recorded between-turn context. The optional `dsh-session/invariant` companion enforces it in dev through `ctx.invariants` (a message event outside an open turn throws). See [the turn-enclosure invariant Agent Note](../../.agents/notes/implemented/architecture/2026-06-15-turn-enclosure-invariant.md). ## Plugin-contributed log-only events A plugin may declaration-merge extra `SessionEventMap` types. These are **log-only**: NOT `SurfaceEventType`s (they carry no `surfaceOp` and contribute nothing to derived history), but, like every event, they must sit inside an open turn. The full per-event enumeration — core and plugin-contributed alike, with payloads and provenance — is the generated [persistence log event catalog](../persistence-catalog.md); the compaction seam's `compact/*` semantics are discussed on [compaction.md](compaction.md). -The hook bridges' `hook/invoked` / `hook/result` provenance pairs (from `@deepseek-ai/dsh-hook-protocol`) correlate by `handlerId`. The mid-turn hook points (`PreToolUse`/`PostToolUse`/`UserPromptSubmit`/`Stop`) fire inside the loop's open turn, so their `hook/*` records are turn-enclosed by construction. `SessionStart` gets no `hook/*` record — its injected `context/message` is the durable evidence — because it has no open turn to enclose one (see [the hook-bridges Agent Note](../../.agents/notes/implemented/feature/2026-06-30-hook-bridges.md)). +The hook bridges' `hook/invoked` / `hook/result` provenance pairs (from `@deepseek-ai/dsh-hook-protocol`) correlate by `handlerId`. The mid-turn hook points (`PreToolUse`/`PostToolUse`/`UserPromptSubmit`/`Stop`) fire inside the loop's open turn, so their `hook/*` records are turn-enclosed by construction. `SessionStart` gets no `hook/*` record — its injected `user/message` is the durable evidence — because it has no open turn to enclose one (see [the hook-bridges Agent Note](../../.agents/notes/implemented/feature/2026-06-30-hook-bridges.md)). ## Durability contract diff --git a/docs/core-data-structures/session.zh.md b/docs/core-data-structures/session.zh.md new file mode 100644 index 0000000000..9e1e9a4f39 --- /dev/null +++ b/docs/core-data-structures/session.zh.md @@ -0,0 +1,570 @@ +# 会话 + +[English](session.md) | 中文 + +[dsh-session](../../packages/core/session) 的内存事件溯源模型。`Session` 是一份由类型化 `SessionEvent` 组成的**仅追加日志**,是 agent(智能体)完整交互历史的唯一真源。LLM(大语言模型)消息历史从日志*派生*而来,从不单独存储;回放即从同一组事件重新派生。日志如何实现**持久化**(持久化 seam、后端、崩溃恢复)是兄弟文档 [persistence.md](persistence.md) 的关注点。 + +源码:[`packages/core/session/src/types.ts`](../../packages/core/session/src/types.ts) + +## `SessionEventMap`:事件词汇 + +仅追加的事件类型。可通过声明合并扩展:插件通过 declaration merging 声明额外的事件类型。例如[压缩(compaction) seam](compaction.md) 添加了 `compact/start` / `compact/summary` / `compact/end`,`@deepseek-ai/dsh-hook-protocol` 添加了仅记录日志的 `hook/invoked` / `hook/result` 溯源事件,用于钩子桥接。与 `compact/*` 一样,这些都不是 `SurfaceEventType`(没有 `surfaceOp`)。生成的[持久化日志事件目录](../persistence-catalog.md)列举了所有成员(核心与合并扩展的),包含其 payload、surface 标记与声明位置。 + +```ts type-equiv +/** + * Shared payload for user, injected-context, and steering prompt messages. A + * direct human prompt, a synthetic `agent.inject()` context, and mid-turn + * steering all project into the model transcript as verbatim user-role content; + * they are told apart by `source` (a non-`user` kind marks injected context), + * not by event type. `meta` carries durable model-hidden producer state. + */ +interface PromptMessageData { + /** Exact model-facing blocks, including any baked prompt-prefix contexts. */ + content: ContentBlock[] + /** Producer provenance for the direct prompt. */ + source: MessageSource + /** Present only when prompt-prefix contexts were baked into `content`. */ + envelope?: PromptMessageEnvelope + /** + * Opaque durable JSON state retained on the event but hidden from the model + * projection. It is the intended channel for a future framing directive (a + * producer declares the frame, a dedicated renderer applies it — see the + * deferred note in + * ../../../../.agents/notes/implemented/simplification/2026-07-20-unwrap-injected-content-envelopes.md), + * so the surface keeps projecting `content` verbatim rather than wrapping it. + */ + meta?: JsonValue +} +``` + +```ts type-equiv +/** + * The merge-extensible, append-only source of truth for an agent interaction. + * Message history is derived from this log. Every event is lossless JSON and + * sequence numbers stay contiguous, including raw chunks, so persistence can + * store the canonical log verbatim. + */ +interface SessionEventMap { + /** + * Opens turn `turn`. `trigger` records what started it — one claimed queued + * message or an idle-time injection. The turn is the durability/replay + * boundary: every event sits between a `turn/start` and its matching + * `turn/end` (the turn-enclosure invariant). + */ + 'turn/start': { turn: number; trigger: TurnTrigger } + /** + * Closes turn `turn` with the {@link TurnEndReason} that ended it. The loop + * awaits `session/flush` after an ordinary turn ends before claiming the next + * queued item. Success commits the turn; rejection is reported live and does + * not prevent later work. + */ + 'turn/end': { turn: number; reason: TurnEndReason } + /** Opens step `step` of turn `turn` — one model call plus the tool executions it requested. */ + 'step/start': { turn: number; step: number } + /** Closes step `step` of turn `turn`. */ + 'step/end': { turn: number; step: number } + /** + * A user-role message on the model-visible surface: a direct human prompt + * (the queued message claimed for this turn), a synthetic `agent.inject()` + * context (file-change notices, subdir AGENTS.md, skill content, cron + * notifications, …), or an admitted goal continuation round. All three + * project their `content` verbatim; `source` (with a non-`user` kind marking + * injected context) is the only channel that tells them apart. An idle + * injection wraps this event in a one-shot turn so the log stays turn-enclosed. + */ + 'user/message': PromptMessageData + /** + * Durable record of a prompt veto and its reason. It is log-only: the blocked + * prompt never enters the model-visible surface, and its turn runs zero steps. + */ + 'prompt/blocked': { content: ContentBlock[]; source: MessageSource; reason: string } + /** Raw stream chunk — token-level replay fidelity. */ + 'assistant/chunk': { turn: number; step: number; chunk: StreamChunk } + /** + * Assembled assistant message for one step (derived history uses this). + * Carries the step's `usage` when the adapter reported token accounting, so + * the model output and its accounting travel together (there is no separate + * usage record). `usage` is absent when the adapter reported none. + */ + 'assistant/message': { turn: number; step: number; content: ContentBlock[]; provenance: AssistantProvenance; usage?: TokenUsage } + /** + * The model requested one tool invocation: `name` with the raw `arguments` + * JSON string exactly as the model produced it (unparsed). `callId` pairs the + * call with its `tool/result`. + */ + 'tool/call': { turn: number; step: number; callId: CallId; name: string; arguments: string } + /** + * A completed tool call's model-facing result, optional internal failure + * identity, and optional tool-private `meta` presentation payload. `meta` is + * opaque to the core (the producing tool owns its shape and reads it back in + * `presentResult`) but MUST be JSON-serializable: `Session.append` + * runtime-validates all event data with `isJsonValue`, so a non-serializable + * `meta` is rejected at the source, and the durable log reproduces the + * identical card on replay. Absent + * unless the tool attaches one (e.g. `dsh-tool-fs` carries its result-time + * contextual diff here). + */ + 'tool/result': { + turn: number + step: number + callId: CallId + content: ContentBlock[] + isError: boolean + error?: { name: string; code: string } + meta?: JsonValue + } + /** Steering content injected between steps of a running turn. */ + 'steering/message': PromptMessageData & { turn: number } + /** Whole-list snapshot; latest write wins on replay. Log-only UI state; never derived history. */ + 'todo/write': { todos: TodoItem[] } + /** + * Full header for the next request, appended inside its step before dispatch. + * It is log-only; the latest snapshot reconstructs the request header. + */ + 'request/header': { header: EpochHeader; reason: RequestHeaderReason } +} +``` + +`PromptMessageData.content` 始终是确切的模型可见内容。当附加上下文声明 `prompt-prefix` 放置方式时,AgentLoop 会依次把它的块、一个 `## My request:` 分隔符以及最终生效的直接提示词拼接进该数组。可选且对模型隐藏的 `envelope` 会保留 `displayContent`,以及按顺序排列的前缀上下文来源/元数据描述信息,使 transcript(文本记录)、标题与重新引用消费方无需改变可重建历史,就能呈现人类提示词。`displayPromptContent()` 负责该选择,并为普通事件和较早的事件回退到 `content`。 + +### `OutOfBandSessionEventMap`:受限的带外追加显式准入 + +仅属于 `SessionEventMap` 并不表示事件可以脱离 agent loop(智能体循环)的常规生命周期追加。事件所有方必须通过声明合并将同一键加入这个空标记映射,`ctx.sessions.appendOutOfBand()` 才会接受该事件;派生类型还会排除所有 surface 事件。被接受的更新会并入已打开的轮次;如果没有打开的轮次,系统则为它创建一个边界配平且已刷新完成的零步骤轮次。 + +```ts type-equiv +/** + * Marker map for plugin-owned log-only events accepted by + * `SessionStore.appendOutOfBand()`. A plugin extends this map with the same key + * it adds to {@link SessionEventMap}; surface and lifecycle events stay + * ineligible unless their owner explicitly opts them into this narrow seam. + */ +interface OutOfBandSessionEventMap {} +``` + +### `TodoItem`:一条待办项 + +这是 `todo/write` 事件全量列表快照中的单元。它有意保持精简:一行 `content` 加一个三态 `status`(没有 id、优先级或 `activeForm`);列表在每次写入时整体替换,因此条目无需稳定标识,而这三个状态值恰好对应 ACP 的 `PlanEntryStatus`,所以 UI 桥接层可以将待办列表一一映射为 ACP `plan`(并合成 ACP 额外要求的优先级)。见 [todo_write Agent Note(agent 决策记录)](../../.agents/notes/implemented/feature/2026-06-29-todo-write-tool.md)。 + +```ts type-equiv +/** + * One entry in an agent's todo list — the unit of the `todo/write` + * {@link SessionEventMap} event's whole-list snapshot. + * + * Deliberately minimal: a human-readable `content` line and a three-state + * `status`. No id, priority, or `activeForm` — the list is replaced wholesale + * on every write (last-write-wins), so entries need no stable identity, and the + * status triple is exactly the ACP `PlanEntryStatus`, so a UI bridge can map a + * todo list onto an ACP `plan` 1:1 (synthesizing the priority ACP additionally + * requires). + */ +interface TodoItem { + /** What this task is — a short imperative line shown in the UI. */ + content: string + /** Lifecycle state. `in_progress` marks the single task being worked now. */ + status: 'pending' | 'in_progress' | 'completed' +} +``` + +<a id="the-request-header-event-requestheader"></a> + +### 请求头事件:`request/header` + +请求信封(即 `EpochHeader`:调用配置 + 渲染后的系统提示词 + 已组装的工具 schema + 会话前缀)会作为会话状态写入日志,因此每个对话请求都是日志的纯函数(见可重建性 Agent Note)。带有 reason `'initial'` 或 `'resume'` 的完整 `request/header` 快照记录每个 agent loop 实例的边界;之后请求发生变化时,系统会以 reason `'change'` 记录另一份完整快照。`foldRequestHeader(events)` 通过选择最新快照重建请求头。该事件不是 `SurfaceEventType`,不产生 LLM 消息。 + +```ts type-equiv +/** + * Logged request state outside derived history: call config, system prompt, + * tools, and prefix. The latest full `request/header` snapshot reconstructs it; + * canonical empty optional fields are absent. + */ +interface EpochHeader { + /** The conversation's call configuration (provider, model, and sampling scalars). */ + config: LlmCallConfig + /** Rendered system prompt text; absent for a system-less request. */ + system?: string + /** Assembled tool schemas; absent for a tool-less request. */ + tools?: ToolSchema[] + /** + * The session prefix: request-only messages sent BEFORE the entire derived + * history (the `agent/session-prefix` waterfall's product, composed once + * per loop instance and reused for every request it sends). Not session + * history — `deriveMessages()` never returns it — so the header is its + * only durable record; absent when the instance composed none. + */ + messagePrefix?: Message[] +} +``` + +规范形式:空系统提示词、空工具列表和空会话前缀都表示为字段缺失,与请求构建方式一致。`messagePrefix` 是 `agent/session-prefix` waterfall(瀑布式事件)产物的持久记录(请求 = `messagePrefix + derived history`);每个 agent loop 实例只组合一次,并包含在该实例记录的每份完整快照中。包含已移除的 `request/header-delta` 事件或完整快照原因为 `fallback` 的旧版 v0 日志,会在 seed、append 和持久化加载边界被拒绝,而不会以不完整方式回放。 + +## `SessionEvent<T>`:一条日志条目 + +基于 `type` 的真正可辨识联合(而非独立的 `type`/`data` 联合),因此 `switch (event.type)` 能直接收窄 `event.data`,无需类型断言。`seq` 是日志中的单调递增位置(`seq = log.length`);`time` 为 epoch 毫秒。 + +```ts type-equiv +/** + * One immutable entry in the session log. + * + * A proper discriminated union over `type` (not independent `type`/`data` + * unions), so `switch (event.type)` narrows `event.data` without casts. + * + * The {@link sourceEventSeqs} and {@link surfaceOp} fields are conditional: + * they only exist on {@link SurfaceEventType} variants (`user/message`, + * `assistant/message`, `tool/result`, `steering/message`). + * Non-surface events (boundary markers, chunks, usage, errors) never carry + * surface metadata — the compiler enforces this at `Session.append()` + * call sites. + */ +type SessionEvent<T extends SessionEventType = SessionEventType> = { + [K in SessionEventType]: { + type: K + /** Monotonic sequence number within the session. */ + seq: number + /** Unix epoch milliseconds. */ + time: number + data: SessionEventMap[K] + } & (K extends SurfaceEventType ? { + /** + * Seq numbers of events that are provenance sources of this event + * (e.g. the `assistant/chunk` seqs that built an `assistant/message`, + * or the surface nodes shadowed by a compaction replace node). An + * `assistant/message` may carry a present empty array for a known empty + * provider stream; omission means unrecorded provenance. + */ + sourceEventSeqs?: number[] + /** How this event entered the surface; absent for non-surface events. */ + surfaceOp?: SurfaceOp + } : object) +}[T] +``` + +`SessionEventType = keyof SessionEventMap`。由于 `SessionEventMap` 可通过合并扩展,对 `SessionEvent` 的 switch 语句禁止使用 `assertNever`:插件添加的变体是合法的未知值;处理已知 case 后在 `default` 中放行。 + +对于 `assistant/message`,存在的 `sourceEventSeqs: []` 表示提供方流已知且完整地为空;字段缺失则表示旧格式或其他未记录溯源信息的情况。agent loop 会为每次成功的模型调用写入该字段;其他 surface 事件只要包含该字段,其列表就必须非空。 + +## Surface 类型 + +四种产生消息的类型(`SurfaceEventType`:`user/message`、`assistant/message`、`tool/result`、`steering/message`)携带 surface 元数据,用来声明它们如何加入有序的派生 surface。见 [session surface Agent Note](../../.agents/notes/implemented/architecture/2026-06-18-session-surface.md)。 + +### `SurfaceEventType`:事件类型中产生消息的子集 + +```ts type-equiv +/** + * The subset of {@link SessionEventType} values whose events produce LLM + * messages and are eligible to appear on the ordered surface. Only these + * event types may carry {@link SurfaceOp} and {@link SessionEvent.sourceEventSeqs}. + */ +type SurfaceEventType = + | 'user/message' + | 'assistant/message' + | 'tool/result' + | 'steering/message' +``` + +### `SurfaceOp`:事件如何进入 surface + +```ts type-equiv +/** + * How a session event entered the ordered surface. Only valid on + * {@link SurfaceEventType} events. + * + * - `'append'`: added to the tail — normal path for user/assistant/tool/steering + * messages. + * - `{ op: 'replace', start, end }`: replaces surface nodes from `start` + * (inclusive) through `end` (inclusive) with this node. Both must exist as + * surface nodes in the current surface. `start === end` replaces a single + * node. The node's {@link SessionEvent.sourceEventSeqs} must include every + * shadowed surface node. Used by compaction and possible other manipulations. + */ +type SurfaceOp = + | 'append' + | { op: 'replace'; start: number; end: number } +``` + +`'append'` 是常规的尾部追加路径。`replace` 会遮蔽从 `start` 到 `end`(含两端)的 surface 条目(两者都必须是有效的 surface seq;`start === end` 时仅替换单个条目),并在原位置插入新事件。 + +### `SurfaceIntent`:`session.append()` 的参数 + +```ts type-equiv +/** + * Surface placement and provenance for {@link Session.append}. Required on + * message-producing events and forbidden on log-only events. + */ +interface SurfaceIntent { + surfaceOp: SurfaceOp + /** + * Complete known provenance source set. `assistant/message` may use a + * present empty array for a known empty provider stream; omission means its + * provenance was not recorded. Other surface events require a non-empty set + * when this field is present. + */ + sourceEventSeqs?: number[] +} +``` + +对 `SurfaceEventType` 事件必填:每个产生消息的事件都必须声明它如何加入 surface(派生历史的唯一来源)。非 surface 类型在编译期拒绝此参数。 + +此处适用相同的溯源区分:只有 `assistant/message` 可以携带存在但为空的 `sourceEventSeqs`;省略该字段并不表示其源流为空。 + +### `SessionSurface`:实时只读 surface 投影 + +`Session.surface` 返回会话稳定的 `SessionSurface` 视图。同一个增量管理器在提交前校验追加候选事件,并根据已提交事件推进该投影;调用方可以观察成员关系和替换代次,但不能调用校验。 + +```ts type-equiv +/** Readonly live projection of the message-producing session events. */ +interface SessionSurface { + /** Current surface event sequences in model-visible order. */ + readonly nodes: readonly number[] + /** Monotonic count of committed positional replacements. */ + readonly replaceGeneration: number +} +``` + +### `SurfaceFoldReplacement` 与 `SurfaceFoldResult`:完整的 surface 回放 + +`foldSurface(events)` 返回一份独立的当前事件 seq 列表,以及每个声明的替换范围实际遮蔽的 seq。实时管理器复用同一套状态转换,但不保留替换历史。每提交一次替换,其 `replaceGeneration` 就递增一次,使增量消费方能够区分纯尾部增长与重写。 + +```ts type-equiv +/** One replacement operation observed while folding a session surface. */ +interface SurfaceFoldReplacement { + /** Seq of the event that replaced the prior surface range. */ + seq: number + /** Declared inclusive start seq of the replaced surface range. */ + start: number + /** Declared inclusive end seq of the replaced surface range. */ + end: number + /** Actual surface entries removed by the operation, in surface order. */ + shadowedSeqs: number[] +} +``` + +```ts type-equiv +/** Complete result of replaying the surface operations in a session log. */ +interface SurfaceFoldResult { + /** Current surface event sequences in model-visible order. */ + nodes: number[] + /** Replacement operations in event order. */ + replacements: SurfaceFoldReplacement[] +} +``` + +## `Session` public API + +去除方法体的声明与源码中的普通类保持同步,覆盖其公共构造函数、状态访问器、追加边界和历史投影。存储操作仍由生成的 [`ctx.sessions` 服务目录](../cordis-catalog/services.md#ctxsessions--sessionstore)记录。 + +```ts public-api +/** + * An event-sourced session: an append-only log of {@link SessionEvent}s. + * + * Plain class (not a Service) — create instances via `ctx.sessions.create()`. + * Seeding with an existing event log replays/forks a session. + */ +declare class Session { + /** The ordered surface over this session's event log. */ + get surface(): SessionSurface; + /** + * Detached, deep-frozen creation metadata (format version, cwd, lineage, + * seed boundary). Supplied by the store via `ctx.sessions.create()`. When a + * `Session` is constructed bare (tests, ad-hoc replay), a minimal header is + * synthesized (stamped with the current {@link SESSION_FORMAT_VERSION}) so + * `session.header` is always present. Kept out of the event log — it is a + * storage concern, not replayable conversation state. + */ + readonly header: SessionHeader; + /** The session identity, derived from its durable header's single copy. */ + get id(): SessionId; + constructor(id: SessionId, seed?: readonly SessionEvent[], header?: SessionHeader); + /** + * An immutable snapshot of the append-only event log. The snapshot is reused + * until the next append; a previously returned array does not grow later. + * Events and their nested data are deep-frozen at acceptance, so neither a + * cast nor ordinary JavaScript can rewrite durable history. + */ + get events(): readonly SessionEvent[]; + /** The next event's sequence number — always the log length (the `seq = log.length` contiguity contract). */ + get seq(): number; + /** + * Append one typed event to the log and synchronously notify observers via + * the store-owned, module-private publication hooks. The hot path never blocks + * on I/O — persistence plugins buffer asynchronously. Once the event enters + * the log, the append is committed: observer failures are logged and + * contained per listener, so they do not change the return value or prevent + * later listeners from observing the same accepted event. + * + * @param type - The event type (key of {@link SessionEventMap}). + * @param data - The event payload; must be JSON-serializable. + * @param opts - Surface metadata: `surfaceOp` controls how the event enters + * the ordered surface; `sourceEventSeqs` records provenance (the seq + * numbers of events this one derives from). REQUIRED for + * {@link SurfaceEventType} events (every message-producing event must + * declare how it joins the surface, the sole source of derived history) and + * rejected by the compiler for non-surface types like `turn/start` or + * `assistant/chunk`. + * @returns the logged event — its assigned `seq`/`time` plus the SNAPSHOT of + * `data` that entered the log, so reading `event.data` back sees the logged + * value, never the caller's still-mutable input. + * @throws if `data` or surface metadata is not losslessly JSON-serializable + * (BigInt, function, symbol, undefined, negative zero, non-finite number, + * circular reference, sparse array, or an exotic object such as + * Map/Set/Date/class instance), or when the candidate violates the + * canonical surface contract (marker shape and eligibility, unique + * earlier provenance, positional replacement validity, and complete + * shadowed-node coverage). One recursive pass reads, validates, and + * copies each nested value once, so a stateful getter cannot supply one value + * to validation and another to storage. The event log is the durable source + * of truth, so a bad event fails at the append site rather than later during + * a backend flush. A synchronous internal dispatch validation failure or an + * append reentered while this acceptance/publication boundary is open also + * rejects before the log changes. + */ + append<T extends SessionEventType>( + type: T, + data: SessionEventMap[T], + ...opts: T extends SurfaceEventType ? [opts: SurfaceIntent] : [] + ): SessionEvent<T>; + /** + * The {@link EpochHeader} in force after the log's last header event — the + * header the NEXT request will be compared against — or undefined before + * the first `request/header` snapshot. The live, incrementally-maintained + * form of `foldRequestHeader(session.events)`: each header event is folded + * once, when first seen, so a per-step read costs O(new events). + * @returns the folded header, or undefined when no header event exists yet. + */ + requestHeader(): EpochHeader | undefined; + /** + * Derive the LLM message history by walking the ordered sequences of + * message-producing events maintained by `surfaceOp` markers. The + * surface is the single source of derived history: every message-producing + * append records its `surfaceOp`, so a raw event with no marker (a chunk, a + * turn boundary) is correctly absent, and a compaction `replace` deletes the + * shadowed nodes from the derivation. The projection rules are + * {@link deriveEventMessage}, folded per node. + * + * CACHED: each surface node is projected exactly once, when first seen — a + * call costs O(new nodes), and a surface rewrite (a `replace`; + * {@link SessionSurface.replaceGeneration}) rebuilds. The returned array is + * a fresh snapshot per call (later appends never grow an array a caller + * already holds); the `Message` objects in it are SHARED and **deep-frozen**. + * Their content reuses the already frozen durable event data, so the cache + * needs no second deep clone and consumers still cannot mutate the log. + * @returns a fresh array of the shared, frozen derived history. + */ + deriveMessages(): Message[]; + /** + * Project a single event into the LLM message it derives to, or null when + * it produces none — a non-surface event (chunk, boundary, log-only record) + * or an empty-content assistant/message (which exists only to host usage). + * The per-node pure function {@link deriveMessages} folds over the surface; + * an external reconstructor (or the dev invariant) folds the same function + * over a log prefix's surface to rebuild the exact messages any request was + * built from (the reconstructability Agent Note). The returned message wrapper is + * fresh; its content reuses the logged event's already deep-frozen durable + * data, so changing the wrapper cannot rewrite the log and changing content + * throws. + * @param event - the event to project. + * @returns the derived message, or null when the event produces none. + */ + deriveEventMessage(event: SessionEvent): Message | null; +} +``` + +## 派生历史:`deriveMessages()` 与 `deriveEventMessage()` + +`Session.deriveMessages()` 将事件日志投影为模型看到的 `Message[]`。它是缓存的(每个 surface 节点在首次出现时投影一次;surface 重写触发重建)且冻结的(每次调用返回一个新数组,引用共享的深冻结消息,因此通过投影修改已记录的历史在类型上不可表达)。`deriveEventMessage(event)` 是折叠所应用的逐节点纯函数,公开暴露以便外部重建器和开发不变式检查能以完全相同的规则投影日志前缀,不会与缓存产生分歧。投影规则: + +- `user/message` → 一条携带确切 `content` 的 user 消息;可选 envelope 仅作为日志中的展示元数据保留。 +- `assistant/message` → 一条 assistant 消息,包含事件的提供方/模型溯源信息和可选的适配器私有回放状态。原始 `assistant/chunk` 事件属于回放/UI 数据,在派生时会被**跳过**(组装后的消息才是权威)。**内容为空的** `assistant/message` 也会跳过:因 max-tokens 而截断且无内容的步骤仍会记录一条 `assistant/message` 以承载用量和溯源信息,但无内容的 assistant 轮次不得进入提供方 transcript。 +- `tool/result` → 一条携带 `tool-result` 块的 user 消息。 +- `user/message`(注入上下文,即非 `user` 来源)→ 按时间顺序在相应位置生成一条 user-role 消息,并原样承载其 `content`。可选的 JSON `meta` 保留在事件日志中,绝不渲染。 +- `steering/message` → 按时间顺序在相应位置生成一条携带确切 `content` 的 user-role 消息;可选 envelope 仅作为日志中的展示元数据保留。 + +其余所有事件(`turn/*`、`step/*`、插件所有的 `llm/retry`)均为结构信息,不会投影为消息。token 记账读取每个步骤的 `assistant/chunk { type: 'usage' }` 记录;如果没有用量分片,则将 `assistant/message.usage` 作为已提交步骤的后备。失败的模型请求尝试没有 assistant 消息,因此其用量分片是持久化的记账记录。操作错误的步骤号记录在 `turn/end.reason`(`kind: 'error'`)中;如果是最终模型请求失败,其中包含规范化的 `LlmFailure` 事实,其他实时错误则包含消息/代码。由于这一尚未发布的格式有意不提供兼容性承诺,seed/load 校验会拒绝缺少提供方和模型的请求头,以及缺少提供方/模型溯源信息的 assistant 消息,而不会猜测历史数据应走的提供方路由。 + +## 活跃会话 fork API + +`ctx.sessions.create(id, { seed, meta })` 是底层的回放/fork 原语。对于普通的活跃会话 fork,`SessionStore` 暴露一个策略 API: + +- `fork(source, boundary?, childSessionId?)` 接受一个活跃的 `Session` 对象或活跃的 `SessionId`,选取到 `boundary` seq(含)为止的源事件(默认为当前最后一个事件),要求 boundary 事件必须是 `turn/end`,然后创建一个活跃的子会话,包含深克隆的种子事件和子会话元数据(`parentSession`、`seedLength` 及继承的 `cwd`)。 + +显式 `boundary` 允许调用者从之前完成的轮次 fork,即使源会话有更新的事件或正在进行的轮次。API 拒绝非 `turn/end` 的 boundary,而不是静默截断。更广泛的轮次封闭性检查留在既有的 `dsh-invariants` 插件和持久化修复路径中,不在 `fork()` 中重复。`dsh-subagent-fork` 保留其已完成前缀截断逻辑,因为工具时委托通常在父轮次仍然打开时启动;普通的会话分支应显式指定请求的 boundary。 + +## 轮次的触发原因:`TurnTriggerMap` + +```ts type-equiv +/** + * What started a turn. + * Merge-extensible sum type (same pattern as MessageSourceMap). + */ +interface TurnTriggerMap { + message: { kind: 'message'; source: MessageSource } + /** + * An out-of-band context injection (`agent.inject()`) made while the agent + * was idle. The loop wraps the injected `user/message` (a non-`user` source, + * plugin by default) in a one-shot turn (`turn/start` → `user/message` → + * `turn/end`) so every event in the log stays turn-enclosed — the + * durability/replay boundary is the turn, and a bare event between turns would + * otherwise be indistinguishable from a crash tail on reload. The trigger's + * `source` mirrors that message's producer. + */ + injection: { kind: 'injection'; source: MessageSource } +} +``` + +<a id="why-a-turn-ended-turnendreasonmap"></a> + +## 轮次的结束原因:`TurnEndReasonMap` + +`aborted` 有意作为一种粗粒度的持久结果:它只记录取消中断了实时轮次,不记录是哪个运行时调用方发起取消。仅属于运行时的调用方词汇由 [`AgentCancelCause`](core.md#the-agent-handle) 定义;未来若有审计需求,应新增独立的控制请求事件,而非让终止结果承载这一信息。 + +```ts type-equiv +/** + * Why a turn ended. Merge-extensible sum type. + */ +interface TurnEndReasonMap { + completed: { kind: 'completed' } + /** A cancellation request interrupted the live turn. */ + aborted: { kind: 'aborted' } + /** + * The turn failed: a step threw or the model reported a failure. `step` is the + * step number the failure occurred on (the operational error's location — the + * single durable record of an in-turn failure; live diagnostics also fire via + * `agent/error`). Final model-request failures retain their normalized facts + * as one `failure`; other turn failures retain their live Error message/code. + */ + error: { kind: 'error'; step: number } & ( + | { failure: LlmFailure; message?: never; code?: never } + | { message: string; code?: string; failure?: never } + ) + disposed: { kind: 'disposed' } + /** At least one step reached its output-token ceiling, even if a plugin continued the turn. */ + 'max-tokens': { kind: 'max-tokens' } + /** + * Policy blocked the turn's claimed prompt before the first step. The + * zero-step turn still records a balanced durable boundary and veto reason. + */ + rejected: { kind: 'rejected'; reason: string } + /** + * A persistence backend closed a crash-orphaned turn on reload. The loop never + * emits this marker, and the events recorded before the crash remain intact. + */ + interrupted: { kind: 'interrupted' } +} +``` + +`max-tokens` 与模型调用中同名的 `FinishReason` 对应:只要轮次内有任何步骤以 `max-tokens` 结束,整个轮次就以 `max-tokens` 而不是 `completed` 结束(即使之后继续执行,截断事实仍优先),让消费方能够区分正常停止和截断停止;但它只优先于 `completed`,`disposed`/`aborted`/`error` 结果的优先级更高。`rejected` 表示一个零步骤轮次,其已认领的提示词被 `agent/prompt-submit` 钩子阻止(ACP(Agent Client Protocol)桥接层将其映射为 `cancelled`)。`interrupted` 是唯一不会由任何 loop 发出的原因:它由崩溃恢复合成(见 [persistence.md](persistence.md))。两个 map 均可通过合并扩展。 + +## 轮次封闭不变式 + +每个会话事件都位于一个轮次**之内**(在 `turn/start` 和对应的 `turn/end` 之间)。loop 在 `turn/start` *之后*追加已排队的 `user/message` 事件;空闲时的 `agent.inject()` 会用一次性的 `injection` 轮次包住其 `user/message`;没有打开的轮次时,`appendOutOfBand()` 同样会用一个轮次包住符合条件的仅日志事件。这使轮次成为唯一的持久性/回放边界:后端可以将最后一个 `turn/end` 之后的任何内容视为崩溃中断尾部,而不会丢失合法记录在轮次之间的上下文。可选的 `dsh-session/invariant` 配套插件通过 `ctx.invariants` 在开发环境中强制此不变式(消息事件若位于打开的轮次之外便会抛出)。见[轮次封闭不变式 Agent Note](../../.agents/notes/implemented/architecture/2026-06-15-turn-enclosure-invariant.md)。 + +## 插件贡献的仅日志事件 + +插件可以通过 declaration merging 添加额外的 `SessionEventMap` 类型。这些是**仅日志**事件:不是 `SurfaceEventType`(不携带 `surfaceOp`,不参与派生历史),但与所有事件一样,必须位于一个打开的轮次内。完整的逐事件枚举(核心与插件贡献的,含 payload 与溯源信息)见生成的[持久化日志事件目录](../persistence-catalog.md);压缩 seam 的 `compact/*` 语义在 [compaction.md](compaction.md) 中讨论。 + +钩子桥接层的 `hook/invoked` / `hook/result` 溯源对(来自 `@deepseek-ai/dsh-hook-protocol`)通过 `handlerId` 关联。轮次中间的钩子点(`PreToolUse`/`PostToolUse`/`UserPromptSubmit`/`Stop`)在 loop 已打开的轮次内触发,因此其 `hook/*` 记录天然位于轮次之内。`SessionStart` 不生成 `hook/*` 记录:它注入的 `user/message` 已是持久证据,而且当时没有已打开的轮次可容纳该记录(见[钩子桥接 Agent Note](../../.agents/notes/implemented/feature/2026-06-30-hook-bridges.md))。 + +## 持久性契约 + +持久化后端依赖的契约如下:持久日志无损保存每个事件,**包括** `assistant/chunk`;`seq` 必须连续,因此不能从规范日志中过滤分片。后端可以为事件批次选择自己的存储编码,只要 `load` 返回与追加时完全一致的事件即可(JSONL 后端可选启用的打包分片行就是此类编码;见 [persistence.md](persistence.md))。所有 `event.data` 都必须可序列化为 JSON;`Session.append` 会从源头强制这一要求(遇到不可序列化数据时抛出),因此错误事件绝不会进入日志,`session.events` 始终与后端可持久化的内容一致。新增携带不可序列化数据的事件类型,或破坏会话不变式配套插件所检查的轮次/步骤嵌套,会构成磁盘格式的破坏性变更。 + +消费此契约的后端见 [persistence.md](persistence.md)。 diff --git a/docs/core-data-structures/skills.i18n.yaml b/docs/core-data-structures/skills.i18n.yaml new file mode 100644 index 0000000000..2f67387224 --- /dev/null +++ b/docs/core-data-structures/skills.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +skills.md: fc9599713dcfddec9719ed746b66ea0217b86cf5 +skills.zh.md: 0eb4c0aa69ed56117c7508358c0d47e3b3e95fcb diff --git a/docs/core-data-structures/skills.md b/docs/core-data-structures/skills.md index e367adf006..fc9599713d 100644 --- a/docs/core-data-structures/skills.md +++ b/docs/core-data-structures/skills.md @@ -1,5 +1,7 @@ # Skills +English | [中文](skills.zh.md) + The [skill capability family](../../packages/skill) is split across three packages: the registry ([dsh-skill](../../packages/skill/skill), `ctx.skills`) merges provider catalogs; the local provider ([dsh-skill-local](../../packages/skill/skill-local)) scans project/custom/user directories; the consumer ([dsh-tool-skill](../../packages/skill/tool-skill)) owns the session-prefix catalog and model-facing `skill` tool. Skills are optional instructions, not session events, so their vocabulary lives here rather than in [core.md](core.md). Source: [`packages/skill/skill/src/index.ts`](../../packages/skill/skill/src/index.ts), [`packages/skill/skill-local/src/index.ts`](../../packages/skill/skill-local/src/index.ts), and [`packages/skill/tool-skill/src/index.ts`](../../packages/skill/tool-skill/src/index.ts). diff --git a/docs/core-data-structures/skills.zh.md b/docs/core-data-structures/skills.zh.md new file mode 100644 index 0000000000..0eb4c0aa69 --- /dev/null +++ b/docs/core-data-structures/skills.zh.md @@ -0,0 +1,159 @@ +# Skills + +[English](skills.md) | 中文 + +[skill(技能)能力族](../../packages/skill)拆分为三个包(package):注册表([dsh-skill](../../packages/skill/skill),`ctx.skills`)合并各提供方的目录;本地提供方([dsh-skill-local](../../packages/skill/skill-local))扫描项目/自定义/用户目录;消费方([dsh-tool-skill](../../packages/skill/tool-skill))拥有会话前缀目录和面向模型的 `skill` 工具。skill 是可选的指令而非会话事件,因此其词汇定义在此处而非 [core.md](core.md)。 + +源码:[`packages/skill/skill/src/index.ts`](../../packages/skill/skill/src/index.ts)、[`packages/skill/skill-local/src/index.ts`](../../packages/skill/skill-local/src/index.ts) 与 [`packages/skill/tool-skill/src/index.ts`](../../packages/skill/tool-skill/src/index.ts)。 + +## 提供方注册表 + +`ctx.skills` 组合本地、内嵌、远程或其他提供方。注册是同步的;远程初始化与发现属于 `list()` 的 await 阶段。提供方对象、选项与候选项以只读方式借用,语义字段会被校验。 + +重名按 rank、提供方顺序、本地顺序依次解决;摘要按名称排序。`list()` 拒绝时记录日志并跳过,不缓存降级后的目录;格式错误的候选项快速失败。 + +```ts type-equiv +/** Provider interface for one source of skills, such as local directories or a remote registry. */ +interface SkillProvider { + /** Unique provider name in the `ctx.skills` registry. */ + readonly name: string + /** + * List available skill candidates for the current lookup context. Provider + * plugins register synchronously during `apply()`; remote initialization, + * authentication, and discovery are awaited inside this method. Implementations + * should settle promptly when `options.signal` aborts. + * @param options - lookup options; `cwd` selects workspace-sensitive skills and `signal` cancels work. + * @returns provider candidates with precedence ranks and opaque locators. + */ + readonly list: (options: SkillLookupOptions) => Promise<readonly SkillCandidate[]> + /** + * Load a complete skill body for a previously listed candidate. + * @param candidate - the winning candidate originally returned by this provider. + * @param options - lookup options; `cwd` selects workspace-sensitive skills and `signal` cancels work. + * @returns the full skill body, or `undefined` if it is no longer loadable. + */ + readonly get: (candidate: SkillCandidate, options: SkillLookupOptions) => Promise<SkillDefinition | undefined> +} +``` + +## 本地发现优先级 + +内置的本地提供方按 rank 顺序扫描各根目录: + +| Rank | Source | Root | +|---|---|---| +| 100 | `project-dsh` | `<projectRoot>/.dsh/skills` | +| 200 | `project-agents` | `<projectRoot>/.agents/skills` | +| 300 | `custom` | `Config.customSkillDirs` | +| 400 | `user-dsh` | `<dshHome>/skills` | +| 500 | `user-agents` | `<agentsHome>/skills` | + +项目根目录为包含 `.git` 的最近祖先目录;找不到时使用当前 cwd。当 `ctx.fs` 可用时,git-root 向上查找通过文件系统服务探测 `.git`,使远程或沙箱工作区不会回退到宿主文件系统边界。用户 DSH 根目录会跳过其 `.system` 子目录。本地提供方不附带内置系统 skill;部署方通过另一个提供方提供内置 skill。 + +## Skill 身份 + +skill 名称为 kebab-case(`^[a-z0-9]+(?:-[a-z0-9]+)*$`)。本地提供方接受目录包(`<name>/SKILL.md`)和扁平 Markdown 文件(`<name>.md`)。嵌套递归的 `**/SKILL.md` 发现有意不在 v1 范围内。 + +```ts type-equiv +/** Origin bucket for a skill contribution. The value is prompt-visible metadata, not precedence by itself. */ +type SkillSource = 'project-dsh' | 'project-agents' | 'runtime' | 'user-dsh' | 'user-agents' | 'custom' | (string & {}) +``` + +## 摘要、候选项与完整定义 + +`SkillSummary` 是注册表中可供模型调用的摘要形状。消费方自行选择渲染哪些字段;会话目录仅使用 `name` 和 `description`,从不使用 body 或绝对文件路径。`disableModelInvocation` 将 skill 从模型列表中隐藏,但允许受信代码按名称加载。 + +```ts type-equiv +/** Model-visible skill metadata returned by `ctx.skills.list()` and rendered into request guidance. */ +interface SkillSummary { + /** Kebab-case identifier used with the `skill` tool. */ + readonly name: string + /** Short routing description shown to the model. */ + readonly description: string + /** Optional extra routing guidance shown to the model. */ + readonly whenToUse?: string + /** Whether the skill is hidden from model listings while remaining loadable by trusted callers. */ + readonly disableModelInvocation?: boolean + /** Discovery source that produced this winning skill. */ + readonly source: SkillSource + /** Provider that owns this skill body. */ + readonly provider: string + /** Provider-specific base for relative resources. */ + readonly resourceBase?: SkillResourceBase +} +``` + +`SkillCandidate` 是提供方到注册表的形状。`locator` 是提供方的不透明状态;注册表只存储它并在调用获胜提供方的 `get()` 时传回。 + +```ts type-equiv +/** Provider catalog entry used by the registry to merge and later load skills. */ +interface SkillCandidate extends SkillSummary { + /** Lower ranks win duplicate skill names before provider registration order is considered. */ + readonly rank: number + /** Opaque provider-owned handle passed back to `provider.get()`. */ + readonly locator: unknown + /** Absolute file path when the provider has one. */ + readonly path?: string + /** Parsed optional metadata object from provider-specific skill frontmatter. */ + readonly metadata?: Readonly<Record<string, unknown>> +} +``` + +`SkillDefinition` 是 `ctx.skills.get()` 返回的完整解析结果,供 `skill` 工具使用。`resourceBase` 告知工具如何为本地、URL 或提供方管理的 skill 渲染相对资源引导。 + +```ts type-equiv +/** Optional provider-specific base used by loaded skill bodies to resolve relative resources. */ +type SkillResourceBase = + | { readonly kind: 'directory'; readonly path: string } + | { readonly kind: 'url'; readonly url: string } + | { readonly kind: 'opaque'; readonly description: string } +``` + +```ts type-equiv +/** Complete parsed skill definition, including the body loaded by `ctx.skills.get()`. */ +interface SkillDefinition extends SkillSummary { + /** Markdown instruction body after any provider-specific metadata removal. */ + readonly content: string + /** Absolute file path when the skill came from disk. */ + readonly path?: string + /** Parsed optional metadata object from frontmatter. */ + readonly metadata?: Readonly<Record<string, unknown>> +} +``` + +运行时 skill 使用相同的完整形状,参与相同的先到先得收集顺序。返回的 disposer 移除该贡献并使发现缓存失效。 + +```ts type-equiv +/** Runtime skill contribution accepted by `ctx.skills.register()`. */ +type SkillRegistration = Omit<SkillDefinition, 'provider'> & { readonly provider?: string } +``` + +## 查找与配置 + +skill 查找对 cwd 敏感,因为提供方可能暴露工作区本地的 skill;可选的 signal 为调用方取消提供方的工作。提供方接收与缓存标识和加载相同的只读选项对象。取消在目录选择前后(包括缓存命中时)都会检查,并与发现和完整定义加载竞争。如果找不到 git root,本地提供方将所提供的 cwd 本身视为项目根目录。 + +```ts type-equiv +/** Caller context used for cwd-sensitive and abortable provider work. */ +interface SkillLookupOptions { + /** Workspace selector for the current lookup. */ + readonly cwd?: string | undefined + /** Abort discovery or loading work for the current caller. */ + readonly signal?: AbortSignal | undefined +} +``` + +注册表只拥有其发现缓存上限。本地提供方拥有文件系统根目录(`dshHome`、`agentsHome` 与 `customSkillDirs`)。消费方拥有其目录描述上限。 + +```ts type-equiv +/** Skill registry configuration. */ +interface Config { + /** Maximum number of completed cwd/provider catalogs kept in memory. */ + readonly collectCacheMaxEntries?: number +} +``` + +## 会话目录与工具契约 + +`dsh-tool-skill` 通过 `agent/session-prefix` 贡献一条 user-role `<system-reminder>`。目录只包含已排序的 skill `name` 和规范化、经 XML 转义的 `description`;不包含正文、路径、来源、提供方或路由提示。Prefix 发现通过 `SkillLookupOptions` 转发调用方的 abort signal。`catalogDescriptionMaxLength` 是消费方用于 description 上限的配置,默认值为 `500`,整数最小值为 `3`。其仅用于请求、记录在 header 中的生命周期由 [session-prefix Agent Note(agent 决策记录)](../../.agents/notes/implemented/feature/2026-07-07-session-prefix.md)定义。 + +面向模型的 `skill({ name })` 工具校验 kebab-case 名称,为调用方 agent 的 cwd 加载完整定义,将未解析的 skill 报告为 unknown 或 no longer available,拒绝 `disableModelInvocation` 的 skill,并返回包含 `<skill_content name="...">`、`<skill_resources>` 和 `<skill_instructions>` 的工具结果。`resourceBase` 仅按需解析显式引用的脚本、参考资料和资产;加载结果不枚举 skill 目录。工具结果是模型获取完整指令的可见路径。 diff --git a/docs/core-data-structures/subagent.i18n.yaml b/docs/core-data-structures/subagent.i18n.yaml new file mode 100644 index 0000000000..d8d6a493d7 --- /dev/null +++ b/docs/core-data-structures/subagent.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +subagent.md: 0335a3f0780ae17b57ae730f5a49a269261c8073 +subagent.zh.md: dac48b624f6e0cfc28737e3e1a2774ba2d97e85b diff --git a/docs/core-data-structures/subagent.md b/docs/core-data-structures/subagent.md index 4f9cbdae61..0335a3f078 100644 --- a/docs/core-data-structures/subagent.md +++ b/docs/core-data-structures/subagent.md @@ -1,5 +1,7 @@ # Subagent +English | [中文](subagent.zh.md) + The subagent seam — an agent delegating work to a child agent. Like [bash](bash.md) it is **one optional capability**, not part of the agent-loop spine, so its vocabulary lives here rather than in [core.md](core.md). But it differs from every other seam on one axis: **multiple provider implementations coexist** in one context, registered by name (`ctx.subagents`), where bash allows only one executor. The registry shape mirrors the [LLM adapter registry](llm-streaming.md), not the single-service bash executor. Interface: [dsh-subagent](../../packages/subagent/subagent) (`ctx.subagents` + the vocabulary below). Implementations are sibling packages (`dsh-subagent-spawn`, `-fork`, `-acp`); the model-facing consumer is [dsh-tool-subagent](../../packages/subagent/tool-subagent). The proposal and rationale: [the subagent Agent Note](../../.agents/notes/implemented/feature/2026-06-21-subagent-capability-seam.md). diff --git a/docs/core-data-structures/subagent.zh.md b/docs/core-data-structures/subagent.zh.md new file mode 100644 index 0000000000..dac48b624f --- /dev/null +++ b/docs/core-data-structures/subagent.zh.md @@ -0,0 +1,248 @@ +# Subagent + +[English](subagent.md) | 中文 + +subagent seam:一个 agent(智能体)将工作委派给子 agent。与 [bash](bash.md) 一样,它是**一项可选能力**,不属于 agent loop(智能体循环)主干,因此其词汇定义在此而非 [core.md](core.md) 中。但它在一个维度上与其他所有 seam 不同:**同一上下文中可共存多个提供方实现**,按名称注册(`ctx.subagents`),而 bash 只允许一个执行器。注册表的形状参照 [LLM(大语言模型)适配器注册表](llm-streaming.md),而非单服务的 bash 执行器。 + +接口:[dsh-subagent](../../packages/subagent/subagent)(`ctx.subagents` + 下文词汇)。实现为三个兄弟包(package):`dsh-subagent-spawn`、`-fork`、`-acp`;面向模型的消费方是 [dsh-tool-subagent](../../packages/subagent/tool-subagent)。提案与设计理由见 [subagent Agent Note(agent 决策记录)](../../.agents/notes/implemented/feature/2026-06-21-subagent-capability-seam.md)。 + +源码:[`packages/subagent/subagent/src/types.ts`](../../packages/subagent/subagent/src/types.ts) + +## 两类能力,两种发现方式 + +提供方通过一个静态描述符公布其**启动时**特性,服务在 run 存在之前即行检查;如果请求依赖提供方不具备的特性,会被大声拒绝(`SubagentError('UNSUPPORTED_CAPABILITY')`),绝不会被接受后静默忽略。**运行时**特性(steering(中途引导)、恢复)则是 [`SubagentRun`](#a-live-run-subagentrun) 上的可选方法——方法的存在即为能力,TypeScript 的类型收窄即为发现机制。 + +```ts type-equiv +/** + * Which START-TIME features a provider supports. Checked by the service before delegating to + * {@link SubagentProvider.start}: a request that needs a capability the chosen provider lacks + * is rejected with a typed error rather than accepted-then-ignored (the "fail loud, no silent + * degradation" rule). These static flags cover features needed before a run exists; runtime + * capabilities such as steering and resume are optional {@link SubagentRun} methods whose presence + * is the capability. + */ +interface SubagentCapabilities { + /** Honor {@link SubagentStartRequest.outputSchema} (structured final output). */ + readonly outputSchema: boolean + /** Enforce {@link SubagentStartRequest.maxDepth} (recursion cap). */ + readonly depthLimit: boolean + /** Enforce {@link SubagentStartRequest.toolFilter} (child tool scoping). */ + readonly toolFilter: boolean + /** Honor {@link SubagentStartRequest.persona} (a per-child persona). */ + readonly persona: boolean +} +``` + +## 启动请求 + +工具层根据模型输入和自身配置构建此请求;服务在 `start` 之前针对指定提供方进行校验。必填的 `parent` 提供会话 cwd、谱系与委派深度。可选的 output schema、depth、工具过滤器和 persona 需要对应的能力 flag 匹配。不支持的 schema 在启动时即失败;进程内后端将 filter 和 persona 的作用域限定在子 agent 创建阶段,并通过强制 capture 工具实现所支持的 object-rooted schema。 + +```ts type-equiv +/** + * What a caller asks for when starting a subagent. The tool layer builds this + * from the model's `{ description, prompt }` plus its own config; the service + * validates {@link SubagentCapabilities} against the named provider, then + * passes it to {@link SubagentProvider.start}. + */ +interface SubagentStartRequest { + /** The task/prompt for the child agent (a user message in the child session). */ + readonly prompt: ContentBlock[] + /** + * The spawning ("parent") agent — the one whose tool call started this + * subagent. REQUIRED: in-process backends read `parent.session.header` for + * the working directory, the `parentSession` lineage to stamp on the child, + * and the parent's delegation depth. The out-of-process backend (ACP) reads + * exactly one field — the session header's cwd, the child's workspace when + * no deployment `cwd` override is configured; nothing else crosses the + * process boundary. + */ + readonly parent: Agent + /** + * Cancellation signal from the spawning context (the tool's `exec.signal`). + * This is the canonical cancellation channel both before and after startup: + * a provider rejects `start()` after cleaning partial resources when it + * fires before publication, and cancels a published child when it fires + * afterward. + */ + readonly signal: AbortSignal + /** Per-child agent options (model and plugin-defined extension fields). */ + readonly agentOptions?: AgentOptions + /** + * Object-rooted JSON Schema within `assertObjectJsonSchema`'s enforced subset. Start rejects + * unsupported schemas or providers without the capability. Data must be plain host-realm JSON; + * a successful child returns the matching value as {@link SubagentResult.structured}. + */ + readonly outputSchema?: ObjectJsonSchema + /** + * Optional absolute delegation-depth cap for the child being started: its + * computed depth must be less than or equal to this non-negative safe + * integer. Requires {@link SubagentCapabilities.depthLimit}; rejected at + * start otherwise. + */ + readonly maxDepth?: number + /** + * Optional child tool scoping. Requires {@link SubagentCapabilities.toolFilter}; + * rejected at start otherwise. In-process backends apply it as a scoped + * `tools.restrict()` in the child's creation window: the named tools vanish + * from the child's prompt AND refuse to execute (one visibility), with loud + * unknown-name validation. + */ + readonly toolFilter?: ToolRestriction + /** + * Optional per-child persona. Requires {@link SubagentCapabilities.persona}; + * rejected at start otherwise. In-process backends register it as a scoped + * `deployment:persona` section on the child, SHADOWING the deployment's + * persona for this child alone — same template semantics as the deployment + * persona (strict `{{…}}` interpolation against the registered variables). + */ + readonly persona?: string +} +``` + +`signal` 是就绪前后唯一的取消通道。[subagent 组合控制 Agent Note](../../.agents/notes/implemented/feature/2026-07-12-subagent-persona-tool-filter-and-depth.md)规定 persona、live 全局工具过滤、绝对深度以及「可见性而非权限」的设计理由。 + +## 终态结果:`SubagentResult` + +一次 run 的最终产出,由 `SubagentRun.result` resolve。`structured` 仅在请求了 `outputSchema` 且成功满足时才存在;请求 schema 不保证一定能得到它,当子 agent 失败或结束时未产出有效 capture 时,提供方可能返回 `stopReason: 'error'`。非 `completed` 的 `stopReason` 意味着 `output` 可能不完整——消费方将其映射为 `isError` 的工具结果,而非将部分输出报告为成功。 + +```ts type-equiv +/** + * The terminal outcome of a subagent run, resolved by {@link SubagentRun.result}. + */ +interface SubagentResult { + /** The child's final assistant output (the last assistant message's content). */ + readonly output: ContentBlock[] + /** + * The structured result after a requested `outputSchema` was successfully + * satisfied. Requesting a schema does not guarantee presence: a provider can + * end with `stopReason: 'error'` when the child fails or finishes without a + * valid capture. Shape is validated against the request schema by the + * provider; `unknown` here because the seam is schema-agnostic. + */ + readonly structured?: unknown + /** Why the run ended. A non-`completed` reason means `output` may be partial. */ + readonly stopReason: SubagentStopReason +} +``` + +`SubagentStopReason` 是一个[可合并扩展的派生联合类型](core.md#the-map--derived-union-pattern)——后端可以添加变体,因此消费方应对已知 case 分支处理,将未知的终态原因视为失败: + +```ts type-equiv +/** + * Why a subagent run ended. Merge-extensible (a backend may add variants); + * consumers branch on the known cases and fall through `default`. The known + * cases mirror the harness turn-end vocabulary so the tool layer can map a + * non-`completed` result to an `isError` tool result. + */ +interface SubagentStopReasonMap { + /** The child finished its turn normally. */ + completed: 'completed' + /** The run was cancelled by its request signal or by disposal. */ + aborted: 'aborted' + /** The child failed (model error, transport error). */ + error: 'error' + /** The child hit its token ceiling before finishing. */ + 'max-tokens': 'max-tokens' + /** The child declined the task. */ + refusal: 'refusal' +} +``` + +<a id="a-live-run-subagentrun"></a> + +## 活跃 run:`SubagentRun` + +`SubagentRun` 是消费方持有的、指向一个就绪子 agent 的句柄。消费方 await `result` 并始终 dispose(资源释放)该 run,直至其完全停稳。子 agent 失败时以非 completed 的 stop reason resolve;只有不可表示的基础设施故障才会 reject。可选的 `sendMessage` 和 `resume` 方法通过自身的存在来公布运行时能力。 + +```ts type-equiv +/** + * Child handle returned only after readiness. Consumers await {@link result} and must always + * {@link dispose} to cancel remaining work and reach quiescence. Optional methods are runtime + * capability discovery; narrow their presence before calling. + */ +interface SubagentRun { + /** + * Parent-scoped run id. For a local run, this MUST equal the published child + * session id, whose `parentSession` records `request.parent.session.id`; a + * remote provider mints an id unique in the parent namespace. + */ + readonly id: SessionId + /** + * The exact published in-process child, or `undefined` for a remote run. + * When present, its id is {@link id}; the provider retains no ownership + * implication beyond the run's ordinary {@link dispose} contract. + */ + readonly localAgent: Agent | undefined + /** + * Resolves with the child's terminal {@link SubagentResult} when the run + * settles. Does NOT reject on a child-level failure — a model/transport + * failure resolves with `stopReason: 'error'` so the consumer maps it to an + * `isError` tool result. Rejects only on an infrastructure fault the seam + * cannot represent as a stop reason. + */ + readonly result: Promise<SubagentResult> + /** + * Cancel remaining work, reach child quiescence, and release the run's + * resources (in-process: dispose the owned agent and remove its session; + * ACP: kill and reap the subprocess). Idempotent. + */ + dispose(): Promise<void> + /** + * OPTIONAL (steering capability): send additional content to the running + * child between steps. Present only on providers that support live steering. + */ + sendMessage?(content: ContentBlock[]): void + /** + * OPTIONAL (resume capability): send a follow-up task to a settled child, + * continuing its session, and return a fresh run for the continuation. + */ + resume?(content: ContentBlock[]): Promise<SubagentRun> +} +``` + +本地 run 必须在 `start()` fulfill 前发布一个普通子 agent/会话,将该子会话 id 作为 `SubagentRun.id` 返回,以 `localAgent` 暴露确切子 agent,并在子 agent 的 `parentSession` header 中记录 `request.parent.session.id`。运行时所有权可以把子 agent 放在 parent、提供方或 root 作用域下。远程提供方则返回 parent 作用域的生命周期 id 与 `localAgent: undefined`。 + +## 提供方 seam:`SubagentProvider` + +每个提供方是一个具名的子 agent 传输层,多个提供方可以共存。服务在 `start()` 之前校验请求的启动时能力。`inheritsParentContext` 仅描述对话种子注入(`fork`:true;`spawn` 和 `acp`:false),使消费方能生成准确的面向模型的措辞,而不暗示继承了工具、服务或权限。 + +```ts type-equiv +/** + * A subagent backend: one transport for running a child agent (in-process + * spawn/fork, ACP to another process, …). Implementations register under a + * unique name via {@link SubagentService.registerProvider}; multiple providers + * coexist in one context (unlike the single-implementation bash seam). The + * Providers are trusted same-process implementations; callers treat their + * descriptors and returned values as borrowed immutable data. + */ +interface SubagentProvider { + /** Unique registry name (e.g. `spawn`, `fork`, `acp`). */ + readonly name: string + /** The start-time features this provider supports (see {@link SubagentCapabilities}). */ + readonly capabilities: SubagentCapabilities + /** + * Whether the child sees the parent's completed-turn prefix. This is descriptive, not a + * service-validated start capability: the model-facing tool derives truthful wording from it. + * It says nothing about tool registration, injected services, or authority inheritance. + */ + readonly inheritsParentContext: boolean + /** + * Establish a child and return its handle only after publication. The + * service has already validated that every requested start-time capability + * is supported, so an implementation may assume e.g. `request.maxDepth` is + * honorable when present. If setup fails or `request.signal` aborts before + * fulfillment, the provider owns and cleans all partial resources before this + * promise rejects. Ownership transfers to the caller only on fulfillment. + */ + start(request: SubagentStartRequest): Promise<SubagentRun> +} +``` + +`start()` 仅在 run 就绪时 fulfill。服务铸造唯一 `runId`,从提供方的确切 `localAgent` 快照 `local`,观察结果,emit `subagent/start`,并返回同一个 run;rejection 意味着提供方已清理,且不会 emit 生命周期事件对。配对的 `subagent/end` 携带相同标识与最终输出或基础设施失败。两个事件都仅用于观察,每个 listener 异常都会被独立隔离。 + +## 进程内后端:深度与种子 + +spawn 和 fork 后端通过 `parent.ctx` 创建一个普通 agent,将取消信号传入核心创建流程,并通过 `AgentHandle` 进行 dispose。移除提供方会阻止新的 start,但不会撤销已接受的 run。每个子 agent 获得一个新的扁平作用域,而非继承父级注册。深度与 fork 种子注入复用既有的 agent 和会话词汇: + +- **委派深度**由持久 `SessionHeader.delegationDepth` 与可合并扩展的运行时字段 `AgentOptions.subagentDepth` 共同表示;缺失表示顶层深度为零,存在的较大值具有权威性。两个字段都归该 seam 所有——循环既不设置也不读取它们——因此进程内子 agent 会持久保存 parent 深度 + 1,恢复无法降低深度,而且每次 start 都会拒绝超出安全整数域、或高于已定义绝对 `request.maxDepth` 上限的派生深度。 +- **Fork 种子注入**使用 `CreateAgentOptions.seed`(一个 `SessionEvent[]` 前缀,经由 `AgentLoop.createAgent` → `ctx.sessions.prepare({ seed })` 传递,与 `resume` 使用的原语相同)。fork 后端传入父级日志的一段*平衡的已完成轮次前缀*——父级事件直到并包括其最后一个 `turn/end`——因此种子从 0 连续,[invariants](../../packages/support/invariants) 回放可以接受它(进行中的、未平衡的轮次被排除在外)。 diff --git a/docs/core-data-structures/system-prompt.i18n.yaml b/docs/core-data-structures/system-prompt.i18n.yaml new file mode 100644 index 0000000000..e697ec6bcd --- /dev/null +++ b/docs/core-data-structures/system-prompt.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +system-prompt.md: 63a750c74300b4353f132d3dae9da52a10631f23 +system-prompt.zh.md: 3f7ab9aee5743616f00e95e81fb9a3a4af2c6e8a diff --git a/docs/core-data-structures/system-prompt.md b/docs/core-data-structures/system-prompt.md index 85a974e6df..63a750c743 100644 --- a/docs/core-data-structures/system-prompt.md +++ b/docs/core-data-structures/system-prompt.md @@ -1,5 +1,7 @@ # System Prompt Assembly +English | [中文](system-prompt.zh.md) + The [system-prompt package](../../packages/core/system-prompt) owns the data exchanged between prompt contributors and one assembly call. The package [README](../../packages/core/system-prompt/README.md) documents registration, ordering, scoping, and rendering behavior; this page pins the literal cross-package shapes that plugins implement or pass. Source: [`packages/core/system-prompt/src/index.ts`](../../packages/core/system-prompt/src/index.ts). diff --git a/docs/core-data-structures/system-prompt.zh.md b/docs/core-data-structures/system-prompt.zh.md new file mode 100644 index 0000000000..3f7ab9aee5 --- /dev/null +++ b/docs/core-data-structures/system-prompt.zh.md @@ -0,0 +1,62 @@ +# 系统提示词组装 + +[English](system-prompt.md) | 中文 + +[system-prompt 包(package)](../../packages/core/system-prompt)负责管理提示词贡献者与一次组装调用之间交换的数据。该包的 [README](../../packages/core/system-prompt/README.md) 记录了注册、排序、作用域与渲染行为;本页固定各插件实现或传递的跨包字面形状。 + +源码:[`packages/core/system-prompt/src/index.ts`](../../packages/core/system-prompt/src/index.ts)。 + +## 组装上下文 + +`AssembleContext` 标识一次组装所解析的作用域 layer,并可携带该请求的显式控制 signal。它可合并扩展:`dsh-agent` 添加可选的 live `agent` 字段,`assembleContextFor(agent, signal)` 则一起设置这些显式字段。裸组装既没有 scope,也没有 signal。 + +```ts type-equiv +/** Merge-extensible context for one prompt assembly. */ +interface AssembleContext { + /** + * Scope whose providers and waterfall listeners participate. When absent, + * only global providers and subject-less listeners participate. + */ + scope?: ScopeKey + /** Explicit control signal for the turn that requested this assembly, when any. */ + signal?: AbortSignal +} +``` + +## 工具提供方结果 + +`ToolProviderResult.schemas` 是当前组装中对模型可见的工具集合。`knownNames` 是提供方在限制前的名称全集,用于区分「配置名拼写错误」与「已知工具在此作用域中被有意隐藏」。 + +```ts type-equiv +/** Tool schemas visible in one assembly and their pre-restriction name set. */ +interface ToolProviderResult { + /** The schemas this provider contributes to THIS assembly. */ + readonly schemas: readonly ToolSchema[] + /** The pre-restriction name universe for config validation (defaults to `schemas`' names). */ + readonly knownNames?: readonly string[] +} +``` + +## 提示词段落 + +`PromptSection` 是一份只读的同进程注册契约。其文本可以是静态的,也可以从当前组装上下文动态解析。 + +```ts type-equiv +/** One contributed section of the system prompt (registry input). */ +interface PromptSection { + /** Unique name — a duplicate registration throws (see {@link SystemPrompt.section}). */ + readonly name: string + /** + * Sections are concatenated in ascending order. Convention: `-100` is the + * harness identity, `0` the deployment persona, tool guidance uses 100–199; + * other negative orders also render before the persona. + */ + readonly order: number + /** + * Static text or a provider evaluated at each assembly with that assembly's + * {@link AssembleContext}. The text may reference `{{variable}}`s — they are + * interpolated later, by {@link renderPrompt}. + */ + readonly text: string | ((context: AssembleContext) => string) +} +``` diff --git a/docs/core-data-structures/tools.i18n.yaml b/docs/core-data-structures/tools.i18n.yaml new file mode 100644 index 0000000000..d22f80c910 --- /dev/null +++ b/docs/core-data-structures/tools.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +tools.md: 43d91e72d83dce0bec99417ca90f9394f4c2169e +tools.zh.md: b92f6d3d99fda7dc28d10556adcceee3946a9571 diff --git a/docs/core-data-structures/tools.md b/docs/core-data-structures/tools.md index d68e280b24..43d91e72d8 100644 --- a/docs/core-data-structures/tools.md +++ b/docs/core-data-structures/tools.md @@ -1,5 +1,7 @@ # Tools +English | [中文](tools.zh.md) + The tool pipeline of [dsh-tools](../../packages/core/tools). [core.md](core.md) introduces `ToolDefinition` as the one pipeline-authoring type promoted to the spine and `ToolSchema` as the model-facing wire shape. This page owns the full `ToolDefinition`, the typed schema DSL that builds it, the guarded execution shapes, and the UI-presentation vocabulary. Source: [`packages/core/tools/src/index.ts`](../../packages/core/tools/src/index.ts) · [`packages/core/tools/src/schema.ts`](../../packages/core/tools/src/schema.ts) · [`packages/core/tools/src/presentation.ts`](../../packages/core/tools/src/presentation.ts) diff --git a/docs/core-data-structures/tools.zh.md b/docs/core-data-structures/tools.zh.md new file mode 100644 index 0000000000..b92f6d3d99 --- /dev/null +++ b/docs/core-data-structures/tools.zh.md @@ -0,0 +1,414 @@ +# 工具 + +[English](tools.md) | 中文 + +[dsh-tools](../../packages/core/tools) 的工具流水线。[core.md](core.md) 介绍了 `ToolDefinition`(唯一被提升到主干的流水线编写类型)和 `ToolSchema`(面向模型的协议格式(wire format)形状)。本页拥有完整的 `ToolDefinition`、用于构建它的类型化 schema DSL、受保护的执行形状,以及 UI 展示词汇。 + +源码:[`packages/core/tools/src/index.ts`](../../packages/core/tools/src/index.ts) · [`packages/core/tools/src/schema.ts`](../../packages/core/tools/src/schema.ts) · [`packages/core/tools/src/presentation.ts`](../../packages/core/tools/src/presentation.ts) + +## `ToolDefinition` — 一个已注册的工具 + +由一个 `ToolSchema`(面向模型的字段)、必需的规范输出声明、`execute` 函数、仅供宿主使用的调度器元数据、可选的最终内容回调和可选 UI 展示函数组成。注册表持有这些定义,循环通过它们分派调用。注册表的 `schemas()` 通过显式允许列表构建面向模型的 `ToolSchema[]`;`output`/`execute`/`finalizeContent`/`timeoutMs`/`isConcurrencySafe`/`presentCall`/`presentResult` 绝不能泄漏到模型请求中。 + +```ts type-equiv +/** Tool-owned canonical output contract used after the body returns a JSON value. */ +interface ToolOutputDefinition { + /** Raw supported JSON Schema enforced against every successful canonical value. */ + readonly schema: JsonSchemaNode + /** Pure projection from validated arguments and value to Native/model content. */ + render(args: unknown, value: JsonValue): ContentBlock[] + /** Pure replayable presentation projection, computed only for surface calls. */ + presentationMeta?(args: unknown, value: JsonValue): JsonValue +} +``` + +```ts type-equiv +/** A registered tool: its schema plus the execution function. */ +interface ToolDefinition extends ToolSchema { + /** Mandatory canonical output declaration. */ + readonly output: ToolOutputDefinition + /** + * Run one accepted call and return only its canonical lossless-JSON value. + * Async work must observe or forward `exec.signal` and settle only after its + * owned work reaches quiescence. The registry preserves caller cancellation + * through around-dispatch signal replacement and does not abandon this + * promise, but it cannot hard-kill same-process code. + * @param args - losslessly snapshotted, frozen model arguments. + * @param exec - execution identity, cancellation signal, and context deferral. + * @returns the canonical value declared by `output.schema`. + */ + execute(args: unknown, exec: ToolRunContext): Promise<unknown> + /** + * Synchronous last-mile transform for model-facing content. The registry + * snapshots this callback when execution starts and invokes it exactly once + * for every normalized outcome, including pipeline failures that bypass + * `tools/post-execute`, immediately before lossless materialization. + * Returning `undefined` preserves the content; every other result field + * remains registry-owned. The callback must be total and must not throw. + * @param exec - immutable execution identity and arguments. + * @param result - complete normalized outcome before materialization. + * @returns replacement content, or `undefined` to preserve it. + */ + finalizeContent?(exec: Readonly<ToolExecution>, result: Readonly<ToolExecutionResult>): ContentBlock[] | undefined + /** + * Cooperative tool-call timeout budget in milliseconds. Omit for no deadline. + * Enforced by `@deepseek-ai/dsh-timeout-policy` (a `tools/execute` wrapper); it + * is NEVER sent to the model — `schemas()` whitelists only name/description/ + * parameters. Declaring it asserts this tool forwards `exec.signal` to a + * cooperative implementation that can reach quiescence when the signal aborts. + */ + timeoutMs?: number + /** + * Pure synchronous classifier for overlap with sibling tool calls. Only + * `true` opts in; omission, exceptions, non-`true` returns, and invalid + * `defineTool` arguments are exclusive. This metadata is never model-visible. + * + * Opted-in executions must not mutate parent-owned state. Shared state must + * tolerate concurrent dispatch; recorder races are permitted only when they + * commute or fail closed. See the + * [parallel-tool-call Agent Note](../../../../.agents/notes/implemented/feature/2026-07-10-parallel-tool-call-execution.md) + * for the full contract. + * @param args - parsed arguments; `defineTool` validates before calling. + * @returns Whether this call may join a parallel group. + */ + isConcurrencySafe?(args: unknown): boolean + /** + * Optional: how to present the PENDING state of one call in a UI, derived from + * the call's `args` (parsed arguments, `unknown` — the tool validates/narrows + * its own input). Returns a {@link ToolCallView} (a `card`-tagged render intent), + * or `undefined` (or omit the method) to fall back to a generic presentation + * (title = tool name, raw args as input). Pure and side-effect-free: a UI may + * call it during live streaming AND a session-log replay, so it must depend + * only on `args`. + */ + presentCall?(args: unknown): ToolCallView | undefined + /** + * Optional: how to present the COMPLETED state, given the same `args` and the + * durable result projection (`content`, failure state, and optional `meta`). Returns a + * {@link ToolResultView}, or `undefined` (or omit the method) to keep the + * pending title and render the raw result content. Pure and side-effect-free + * for the same replay reason. + */ + presentResult?(args: unknown, result: ToolResult): ToolResultView | undefined +} +``` + +`execute` 接收 `args: unknown`——原始的 `ToolDefinition` 自行校验输入。第一方工具不需要手写校验;它们使用 `defineTool`,由后者代为校验并收窄参数类型、根据 `output.schema` 推导函数体返回类型,并为两个输出投影器提供类型约束。`finalizeContent` 特意接收不可变的执行对象而非类型化参数,因为无效输入和外层流水线失败也会到达该回调;它可以施加工具自有的内容限制,同时保留 `isError`、规范值、结构化错误身份、延迟上下文与展示元数据。 + +## 统一的 JSON 值 schema DSL + +插件作者使用同一套词汇描述类型化参数和类型化输出值。`ValueSchemaSpec` 支持 `string`、`number`、`integer`、`boolean`、`null`、`array`、`object`、仅作者侧可用的 `json`,以及要求恰好命中一个分支的 `oneOf`;标量 `enum` 和 `const` 值必须与节点类型匹配。显式对象节点始终声明 `additionalProperties: true | false`。参数定义仍是隐式的开放对象属性映射,每个必填属性都附带 `required: true`。 + +源码:[`packages/core/tools/src/schema.ts`](../../packages/core/tools/src/schema.ts) + +```ts type-equiv +/** One author-facing schema for any lossless JSON value root. */ +type ValueSchemaSpec = + | StringValueSchemaSpec + | NumberValueSchemaSpec + | IntegerValueSchemaSpec + | BooleanValueSchemaSpec + | NullValueSchemaSpec + | ArrayValueSchemaSpec + | ObjectValueSchemaSpec + | JsonValueSchemaSpec + | OneOfValueSchemaSpec +``` + +```ts type-equiv +/** One implicit parameter-root property, optionally required. */ +type ParameterPropertySpec = ValueSchemaSpec & { required?: true } +``` + +```ts type-equiv +/** + * Tool parameter schema. The map itself is an implicit open object root; + * requiredness remains a per-property `required: true` annotation. + */ +type ParameterSchemaSpec = { + [key: string]: ParameterPropertySpec + [key: symbol]: never +} +``` + +`{ type: 'json' }` 推导为 `JsonValue`,并编译成仅含注解、不施加约束的原始 schema。输出根可以是对象、数组、标量或 null。`InferValue<S>` 在 16 层容器内保留字面量约束与对象开放性,之后回退为 `JsonValue`,避免耗尽 TypeScript 的类型实例化栈。`InferArgs<P>` 依据逐属性的必填标记生成必填和可选的字符串键: + +```ts type-equiv +/** + * Infer the TypeScript value accepted by an author-facing value schema. Exact + * inference is bounded to 16 container levels, then falls back to `JsonValue`. + */ +type InferValue<S> = InferValueAt<S, []> +``` + +```ts type-equiv +/** Infer the TypeScript argument object for an implicit parameter schema. */ +type InferArgs<S> = InferProperties<S, []> +``` + +`defineTool({ name, description, parameters, output, execute, … })` 将参数推导与 `parameterSchemaSpecToJsonSchema()` 和 `validateArgs()` 绑定,并将 `execute`/`render`/`presentationMeta` 与 `InferValue<OutputSchema>` 绑定。Schema 记录只包含自有且可枚举的字符串键,schema 数组是稠密的内建数组,因此推导、编译与校验观察到的是同一份声明。精确推导保持到 16 层容器,之后放宽为 `JsonValue`;运行时校验仍会继续遍历完整 schema。`valueSchemaSpecToJsonSchema()` 通过同一套已强制执行的原始子集编译输出声明。参数不匹配时抛出 `ToolArgsError`(`INVALID_ARGS`);函数体或后置策略产生的值无效时抛出 `ToolOutputError`(`INVALID_TOOL_OUTPUT`)。两者都经由常规工具错误路径处理。原始 JSON Schema 默认保持开放;不支持的关键字会被拒绝,而不会在未强制执行的情况下获准进入。 + +注册是一个受信任的同进程契约。注册表以 readonly 输入借用类型化定义,要求它声明 `output`,校验其原始 schema,并检查 `timeoutMs` 必须为正有限值等语义要求;`schemas()` 在模型边界处物化显式的面向模型投影,使执行和展示共享同一份已解析定义,而不会将回调泄漏到协议上。 + +## `ToolRestriction` — 单个作用域的实时全局过滤器 + +`ToolRestriction` 仅作用于实时的部署全局工具层。注册表将 readonly 名称编译为私有集合,对多个限制取交集,再叠加作用域本地工具。仅 deny 的过滤器允许后续未列出的全局工具通过,而 allow 列表则排除它们。 + +```ts type-equiv +/** + * Per-scope filter over global tools. Restrictions intersect and do not affect + * scoped registrations or the reserved Code Mode transport. + */ +interface ToolRestriction { + /** Global tool names that stay visible; everything else is removed. */ + readonly allow?: readonly string[] + /** Global tool names removed from visibility. */ + readonly deny?: readonly string[] +} +``` + +## 执行:可扩展的 waterfall(瀑布式事件)加单调策略 + +`ctx.tools.execute()` 接受由调用方拥有且包含必需 readonly `signal` 的 `ToolExecutionInput`,将其解析后的 JSON 参数一次性物化为流水线拥有的 `ToolExecution`,然后让调用依次经过 `tools/pre-execute`(可重排的 allow/deny/ask waterfall)→ 已注册的单调 guard → `tools/execute`(环绕分派包装层)→ `tools/post-execute`(检查/替换结果)→ 可选且由定义拥有的 `finalizeContent` → `tools/result`(不可变的权威结果)。只有 `tools/execute` 视图可以替换必需的 signal。最终产出为 `ToolExecutionResult`。 + +```ts type-equiv +/** Opaque call identity that permits correlation without exposing mutable execution state. */ +type ToolExecutionToken = symbol & { readonly [toolExecutionTokenBrand]: true } +``` + +```ts type-equiv +/** + * Caller-supplied description of one tool call. {@link ToolRegistry.execute} + * adds the registry-owned token to form a pipeline {@link ToolExecution}; + * callers do not choose that token. + */ +interface ToolExecutionInput { + readonly callId: CallId + readonly name: string + /** Losslessly JSON-serializable parsed arguments (tools validate their own schema). */ + readonly arguments: unknown + /** The agent on whose behalf the call runs (set by the agent loop). */ + readonly agent?: Agent + /** + * Opaque token of the enclosing transport execution, when one exists. Code + * Mode sets this on SDK sub-dispatches so commit-style observers can wait for + * the outer `run_code` outcome without receiving its live mutable execution. + */ + readonly parent?: ToolExecutionToken + /** Required caller-owned cancellation for this invocation. */ + readonly signal: AbortSignal +} +``` + +工具函数体接收运行时扩展。`deferContext()` 是组合工具的通道:它记录嵌套分派产生的上下文,而不会在外层调用尚未结束时注入这些上下文。 + +```ts type-equiv +/** + * Runtime context handed to a tool implementation after the registry has + * accepted a {@link ToolExecution}. A composite tool uses + * {@link deferContext} to ferry context produced by nested dispatches back to + * the outer result; the loop appends it only after the outer `tool/result`. + */ +interface ToolRunContext extends ToolExecution { + /** + * Defer one nested-dispatch context until this tool's final result reaches + * the agent loop. Contexts retain their individual source and metadata and + * are emitted in call order. + */ + deferContext(context: HookContext): void +} +``` + +agent loop(智能体循环)向注册表查询每个待处理调用的执行模式,并据此形成独占屏障和滚动池并行执行: + +```ts type-equiv +/** + * Scheduling mode for one pending call. `parallel` may overlap with siblings; + * `exclusive` runs alone and forms an ordering barrier. + */ +type ToolExecutionMode = + | { kind: 'parallel' } + | { kind: 'exclusive' } +``` + +```ts type-equiv +/** + * One pending tool call inside the registry pipeline. Parsed arguments cross + * one lossless-JSON materialization boundary before policy and are deep-frozen; + * call identity, the caller signal, and the registry-assigned {@link token} are + * readonly. The registry freezes the complete object before `tools/result` + * observers run. + */ +interface ToolExecution extends ToolExecutionInput { + /** Registry-assigned identity shared with nested calls only as their opaque `parent` token. */ + readonly token: ToolExecutionToken +} +``` + +```ts type-equiv +/** + * Around-dispatch view of a {@link ToolExecution}. A `tools/execute` wrapper + * may replace the signal for its delegated lifetime, but it cannot remove it. + * The registry fuses every replacement with the captured caller signal. + */ +interface ToolDispatchExecution extends Omit<ToolExecution, 'signal'> { + /** Cancellation signal visible to the next wrapper or tool body. */ + signal: AbortSignal +} +``` + +`ToolExecutionToken` 是不透明的运行时 `Symbol`,仅用于身份比较。策略执行前,`execute()` 会物化并冻结参数、拒绝非 JSON 输入并分配 token。身份字段、调用方必需的 signal 和可选的 parent token 均保持 readonly。`ToolDispatchExecution` 包装层可以替换 signal 但不能移除;注册表会在调用工具函数体前重新融合调用方的 signal。最终观察者接收冻结的执行身份。 + +`ToolGuard` 是感知作用域的最终预分派策略。其形状有意不包含 allow 结果:`undefined` 保留 waterfall 的决策,而返回的 reason 只能缩减权限,因此后续监听器无法撤销它。 + +```ts type-equiv +/** + * A monotonic execution guard evaluated after every `tools/pre-execute` + * listener and before the tool body. Returning a reason denies the call; + * returning `undefined` leaves it unchanged. Because guards have no allow + * result, listener ordering cannot turn a denial back into permission. + * @param execution - the identity-protected call after extensible pre-execute policy completed. + * @returns a final denial reason, or `undefined` to leave the call allowed. + */ +type ToolGuard = (execution: Readonly<ToolExecution>) => string | undefined +``` + +```ts type-equiv +/** Canonical failure detail; internal routing information remains optional. */ +interface ToolFailure { + /** Human-readable failure message without the Native `Error: ` envelope. */ + message: string + /** Internal error class/code used by policy and durable diagnostics. */ + info?: ToolErrorInfo +} +``` + +```ts type-equiv +/** Successful canonical tool execution, including its Native/model projection. */ +interface ToolExecutionSuccess { + readonly isError: false + /** Execution-local canonical value; deliberately omitted from durable events. */ + readonly value: JsonValue + readonly content: ContentBlock[] + readonly error?: never + readonly meta?: JsonValue + readonly additionalContexts?: HookContext[] +} +``` + +```ts type-equiv +/** Failed canonical tool execution; failures never carry a successful value. */ +interface ToolExecutionFailure { + readonly isError: true + readonly error: ToolFailure + readonly value?: never + readonly content: ContentBlock[] + readonly meta?: JsonValue + readonly additionalContexts?: HookContext[] +} +``` + +```ts type-equiv +/** The discriminated, execution-local outcome of one tool call. */ +type ToolExecutionResult = ToolExecutionSuccess | ToolExecutionFailure +``` + +结果仅承载产出。调用身份保留在不可变的 `ToolExecution` 上,后者伴随结果经过每个钩子,并出现在持久化的 `tool/call` / `tool/result` 会话事件上,因此包装层无法创建第二个相互矛盾的身份。规范的 `value` 仅存在于执行期间:循环只持久化 `content`、`error` 和 `meta`,`tool/code-dispatch` 则存储有界摘要。回放可以重现展示,却无法重建中间值。 + +成功时,注册表会快照并校验函数体返回值,将其冻结,然后调用纯渲染器;对于直接的外层调用,还会调用可选的元数据投影器。注册表会在 `tools/result` 之前另行物化持久展示字段;无效值、渲染器/投影器失败或非 JSON 展示都会转为 JSON 安全的 `isError`。因此,最终实时观察者能看到精确的执行期值,以及可安全用于后续持久追加的字段。 + +在得到最终内容之前,注册表会物化候选结果;若内容、结构化错误、附加上下文或展示元数据无法物化,则会转为仍可到达 `finalizeContent` 的 JSON 安全 `isError` 结果。注册表恰好调用该回调一次,随后在 `tools/result` 之前立即物化并冻结已接受的结果,因此实时观察到的产出可安全用于后续持久化的 `tool/result` 追加。 + +每个拦截 waterfall 返回一个类型化的 **Decision**(与 `agent/*` seam 共享的惯用模式)。`tools/pre-execute` 监听器接收 `(exec, next)` 并返回 `PreToolDecision`;`tools/execute` 包装层返回 `ToolExecutionResult`;`tools/post-execute` 监听器接收 `(exec, result, next)` 并返回 `PostToolDecision`: + +```ts type-equiv +/** + * Pre-dispatch decision. `allow` runs the call; `deny` materializes an error; + * `ask` runs only after an approval service returns `allowed-once` and otherwise + * denies. Input rewriting is excluded because arguments are already logged and + * presented. + */ +type PreToolDecision = + | { kind: 'allow' } + | { kind: 'deny'; reason: string } + | { kind: 'ask'; reason?: string } +``` + +```ts type-equiv +/** + * Post-dispatch decision: accept, replace one projection, attach context for the + * next request, or block by turning corrective feedback into an error result. + */ +type PostToolDecision = + | { kind: 'accept'; content?: ContentBlock[]; value?: never; additionalContexts?: HookContext[] } + | { kind: 'accept'; value: JsonValue; content?: never; additionalContexts?: HookContext[] } + | { kind: 'block'; feedback: ContentBlock[]; additionalContexts?: HookContext[] } +``` + +调用 `next()` 获取默认决策,或直接返回一个决策以短路。前置策略可以 deny 或 ask;只有 `allowed-once` 才继续执行,而未授权、缺少审批通道或服务、或无 agent 的请求都会变为拒绝。Guard 仍可施加最终拒绝。参数不可被改写,因为历史记录、审计、UI 和执行必须保持一致。 + +后置策略可以替换内容或值,但不能同时替换两者。替换内容会保留规范值和现有元数据;替换值会重新校验并重新计算内容/元数据;阻止会移除值,并转为包含纠正反馈的 `isError`。内容替换是展示策略,而非保密策略;需要隐藏程序化值的监听器必须阻止或替换该值。`tools/result` 在归一化后接收冻结的执行和结果;观察者无法对其进行变换,观察者的失败也会被隔离。未知工具和抛出异常的工具都会变为结构化错误(`ToolNotFoundError` 映射为 `UNKNOWN_TOOL`),调用失败但不终止当前轮次。 + +## 已强制执行的原始 JSON Schema 子集 + +subagent、工作流、MCP 和动态注册提供的原始 schema 使用作者侧 DSL 在协议层的对应表示。`assertSupportedJsonSchema()` 接受任意 JSON 根,`validateJsonSchemaValue()` 强制执行该 schema,`JsonSchemaError` 则报告每条不受支持或格式错误的 schema 路径。仅含注解的空节点表示不受约束的无损 JSON。`oneOf` 至少要求两个分支,且一个值必须恰好匹配其中一个。仍要求对象根的消费方调用 `assertObjectJsonSchema()` 并携带 `ObjectJsonSchema`;这样,subagent/工作流中由调用方定义的结构化输出可以继续以对象为根,而不会限制共享词汇。 + +```ts type-equiv +/** Scalar JSON values supported by `enum` and `const`. */ +type JsonSchemaScalar = string | number | boolean | null +``` + +```ts type-equiv +/** Single-type keywords accepted by the enforced subset. */ +type JsonSchemaType = 'object' | 'array' | 'string' | 'number' | 'integer' | 'boolean' | 'null' +``` + +```ts type-equiv +/** + * One raw JSON Schema node in the enforced subset. The optional fields express + * the external wire shape; {@link assertSupportedJsonSchema} rejects invalid + * combinations before a caller treats the node as trusted. + */ +interface JsonSchemaNode { + /** Omit with no constraints for any JSON value, or use `oneOf`. */ + type?: JsonSchemaType + /** Exactly one branch must validate; at least two branches are required. */ + oneOf?: JsonSchemaNode[] + /** Nested property schemas (`type: 'object'` only). */ + properties?: Record<string, JsonSchemaNode> + /** Required property names; each must appear in `properties`. */ + required?: string[] + /** `false` rejects undeclared keys; absent/`true` follows JSON Schema's open default. */ + additionalProperties?: boolean + /** Item schema (`type: 'array'` only); absent accepts any JSON item. */ + items?: JsonSchemaNode + /** Allowed values for a scalar node. */ + enum?: JsonSchemaScalar[] + /** The single allowed value for a scalar node. */ + const?: JsonSchemaScalar + /** Annotation, ignored for validation. */ + description?: string + /** Annotation, ignored for validation. */ + title?: string + /** Annotation, ignored for validation but required to be lossless JSON. */ + default?: JsonValue + /** Annotation, ignored for validation but required to be lossless JSON. */ + examples?: JsonValue +} +``` + +```ts type-equiv +/** A consumer-constrained object-rooted schema. */ +type ObjectJsonSchema = JsonSchemaNode & { type: 'object' } +``` + +## 工具展示 UI 词汇 + +工具希望其调用在 UI 中如何呈现(编辑器工具调用卡片、CLI(命令行界面)日志行),提供方无关,使工具在不依赖任何客户端协议的情况下描述自身。`presentCall`/`presentResult` 返回一个 **`card` 标签的渲染意图**——一个可辨识联合类型,UI 桥接层据此分发: + +- `ToolCallView`(待执行):`{ card: 'generic', title, kind?, rawInput?, content?, locations? }`(默认卡片;`locations` 是 `{ path, line? }[]`,表示调用读取/修改的文件,供编辑器跟随)、`{ card: 'terminal', title, description?, cwd? }`(shell 命令→终端卡片)、或 `{ card: 'diff', title, diffs, locations? }`(文件创建/修改→行内 diff 卡片;`diffs` 是 `{ path, oldText, newText }[]`,新文件时 `oldText: null`)。 +- `ToolResultView`(已完成):`{ card: 'generic', title?, content? }`、`{ card: 'terminal', title?, output?, exitCode?, signal? }`(捕获的运行输出 + 退出状态;有能力的 UI 显示退出状态标签,无能力的 UI 获得桥接层从 `output` 派生的围栏 ` ```console ` 回退)、或 `{ card: 'diff', title?, diffs }`(已完成的文件变更→要展示的变更,通常是从变更前后内容计算出带上下文行的已应用 hunk,或在没有前像时的整文件 diff——例如文件创建。`tool_call_update` 的内容会替换调用的内容,因此变更工具即使与调用时的片段重复也要返回此卡片,以防结果文本覆盖 diff)。 + +`ToolCallKind`(`'read' | 'edit' | 'delete' | 'move' | 'search' | 'execute' | 'fetch' | 'other'`)用于为通用卡片选择图标。`FileLocation`(`{ path, line? }`)与 `FileDiff`(`{ path, oldText, newText }`)是共享的文件卡片词汇。该设计由[渲染意图联合类型 Agent Note(agent 决策记录)](../../.agents/notes/implemented/architecture/2026-07-02-tool-render-intent-union.md)固定;ACP(Agent Client Protocol)桥接层将 `diff` 卡片映射为 `{ type: 'diff' }` 内容块,将 `terminal` 卡片映射为 `_meta` 终端约定,并根据会话 cwd 将文件卡片标题转换为相对路径。 + +完整的展示字段文档见 [`packages/core/tools/src/presentation.ts`](../../packages/core/tools/src/presentation.ts)。`bash` schema 与执行器见 [bash.md](bash.md);通用后台控制见 [tasks.md](tasks.md)。 diff --git a/docs/core-data-structures/user-interaction.i18n.yaml b/docs/core-data-structures/user-interaction.i18n.yaml new file mode 100644 index 0000000000..126f18729e --- /dev/null +++ b/docs/core-data-structures/user-interaction.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +user-interaction.md: 7ddc2f46bdbbe25f2a8979b029d0c6b958f85b09 +user-interaction.zh.md: 75b9b7795a36e0706672f0d17ba0b399c20cc644 diff --git a/docs/core-data-structures/user-interaction.md b/docs/core-data-structures/user-interaction.md index e010b48987..7ddc2f46bd 100644 --- a/docs/core-data-structures/user-interaction.md +++ b/docs/core-data-structures/user-interaction.md @@ -1,5 +1,7 @@ # User Interaction +English | [中文](user-interaction.zh.md) + The user-interaction seam of [dsh-user-interaction](../../packages/ui/user-interaction). It is the provider-neutral vocabulary a tool or permission plugin uses when it needs the human to answer before the agent can continue. UI surfaces provide the active `UserInteractionProvider`: `dsh-tui` uses keyboard-driven overlays, and `dsh-acp` maps questions to ACP form elicitations. Source: [`packages/ui/user-interaction/src/index.ts`](../../packages/ui/user-interaction/src/index.ts) diff --git a/docs/core-data-structures/user-interaction.zh.md b/docs/core-data-structures/user-interaction.zh.md new file mode 100644 index 0000000000..75b9b7795a --- /dev/null +++ b/docs/core-data-structures/user-interaction.zh.md @@ -0,0 +1,108 @@ +# 用户交互 + +[English](user-interaction.md) | 中文 + +[dsh-user-interaction](../../packages/ui/user-interaction) 的用户交互 seam。它是工具或权限插件需要人类回答后 agent(智能体)才能继续时所使用的、提供方无关的词汇。UI surface 提供活跃的 `UserInteractionProvider`:`dsh-tui` 使用键盘驱动的 overlay,`dsh-acp` 则把问题映射为 ACP(Agent Client Protocol)表单 elicitation。 + +源码:[`packages/ui/user-interaction/src/index.ts`](../../packages/ui/user-interaction/src/index.ts) + +## 问题选项 + +`AskUserQuestionOption` 是可选择项的形状。`label` 是面向用户的选项文字,同时也是面向模型的选中值;`description` 是可选的 UI 帮助文本。 + +```ts type-equiv +/** One selectable answer offered to the user. */ +interface AskUserQuestionOption { + /** User-facing label. */ + label: string + /** Optional extra context rendered by capable UIs. */ + description?: string +} +``` + +## 问题条目 + +`AskUserQuestionItem` 是请求中的一个问题。调用方提供稳定的 `id`,它会随答案原样返回,使批量问题仍可路由。可选的 `detail` 携带辅助文本;提供方会将其随问题渲染,但不会放入可选 option label。 + +```ts type-equiv +/** One question in a user-interaction request. */ +interface AskUserQuestionItem { + /** Stable caller-provided question id, echoed in the answer. */ + id: string + /** The question to display. */ + question: string + /** Optional supporting detail rendered with the question but kept out of option labels. */ + detail?: string + /** Optional short heading/group label. */ + header?: string + /** Optional choices the UI can render as a menu. */ + options?: AskUserQuestionOption[] + /** Whether more than one option may be selected. Defaults to single-select. */ + multiSelect?: boolean +} +``` + +## 提问请求 + +`AskUserQuestionRequest` 是跨包(package)的请求。`questions` 是数组,这样 UI 可以在一个流程中呈现相关提示,同时保持每个回答有稳定的 id。 + +```ts type-equiv +/** Request for a human answer. */ +interface AskUserQuestionRequest { + /** Questions to display. */ + questions: AskUserQuestionItem[] + /** Calling agent, when the request came from an agent tool call. */ + agent?: Agent + /** Abort signal for the owning tool/step. */ + signal?: AbortSignal +} +``` + +## 回答 + +提供方为每个问题 id 返回一个回答项。`selected` 包含选中的选项标签,`custom` 在用户输入自由文本时携带「其他」回答。当 `custom` 存在时,`selected` 为空;自定义文本是对选中项的覆盖,而非补充。UI 也可以使用 `selected` 为空且不含 `custom` 的回答项,在其余问题均已完成的批次中保留被跳过的问题。 + +```ts type-equiv +/** Answer to one question. */ +interface AskUserQuestionAnswerItem { + /** The answered question id. */ + id: string + /** Selected option labels. Empty for custom or unanswered choices. */ + selected: string[] + /** Optional free-text "Other" answer. */ + custom?: string +} +``` + +```ts type-equiv +/** The human's answer. */ +interface AskUserQuestionAnswer { + /** Structured answers keyed by question id. */ + answers: AskUserQuestionAnswerItem[] +} +``` + +## 提供方 + +同一上下文中只能有一个活跃的提供方。提供方注册绑定到 effect,因此 HMR(热模块替换)或 dispose(资源释放)会移除当前活跃的 UI。 + +```ts type-equiv +/** UI-side provider for user questions. */ +interface UserInteractionProvider { + ask(request: AskUserQuestionRequest): Promise<AskUserQuestionAnswer> +} +``` + +## 错误 + +`UserInteractionError` 继承 `HarnessError`,因此 `ctx.tools.execute()` 会保留 `{ name, code }`,用于面向模型的工具失败,如 `EMPTY_QUESTIONS`、`NO_PROVIDER`、`ASK_ABORTED` 或 ACP 侧取消。 + +```ts type-equiv +/** Stable error taxonomy for user-interaction failures. */ +class UserInteractionError extends HarnessError { + constructor(message: string, code: string, options?: ErrorOptions) { + super(message, code, options) + this.name = 'UserInteractionError' + } +} +``` diff --git a/docs/core-data-structures/web.i18n.yaml b/docs/core-data-structures/web.i18n.yaml new file mode 100644 index 0000000000..912c1decbe --- /dev/null +++ b/docs/core-data-structures/web.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +web.md: 20d07240c9d9fea2f1f5abbac810f349a3e81f9b +web.zh.md: 68ceed04bb0b80f32ed704118f1fc25f48a0da70 diff --git a/docs/core-data-structures/web.md b/docs/core-data-structures/web.md index 22909b8dfb..20d07240c9 100644 --- a/docs/core-data-structures/web.md +++ b/docs/core-data-structures/web.md @@ -1,5 +1,7 @@ # Web Access +English | [中文](web.zh.md) + The web access seam — a [capability seam](../../.agents/notes/implemented/architecture/2026-06-24-web-capability-seam.md) that spans **two capabilities** (search and fetch) on one `ctx.web` service, split across packages: interface ([dsh-web](../../packages/web/web), `ctx.web` + the provider registries), implementations ([dsh-web-search-exa](../../packages/web/web-search-exa), [dsh-web-search-perplexity](../../packages/web/web-search-perplexity), [dsh-web-search-deepseek](../../packages/web/web-search-deepseek), [dsh-web-fetch-local](../../packages/web/web-fetch-local)), and consumer ([dsh-tool-web](../../packages/web/tool-web), the `web_search`/`web_fetch` tool schemas). Web is **one optional capability**, not part of the agent-loop spine — so its vocabulary lives here, not in [core.md](core.md). A search-provider swap does not change how the model asks for a query, and a fetch-implementation swap does not change how the model asks for a URL. Source: [`packages/web/web/src/types.ts`](../../packages/web/web/src/types.ts) diff --git a/docs/core-data-structures/web.zh.md b/docs/core-data-structures/web.zh.md new file mode 100644 index 0000000000..68ceed04bb --- /dev/null +++ b/docs/core-data-structures/web.zh.md @@ -0,0 +1,135 @@ +# Web 访问 + +[English](web.md) | 中文 + +Web 访问 seam 是一个[能力 seam](../../.agents/notes/implemented/architecture/2026-06-24-web-capability-seam.md),在同一个 `ctx.web` 服务上横跨**两项能力**(search 与 fetch),并拆分到多个包(package):接口([dsh-web](../../packages/web/web),`ctx.web` + 提供方注册表)、实现([dsh-web-search-exa](../../packages/web/web-search-exa)、[dsh-web-search-perplexity](../../packages/web/web-search-perplexity)、[dsh-web-search-deepseek](../../packages/web/web-search-deepseek)、[dsh-web-fetch-local](../../packages/web/web-fetch-local))与消费方([dsh-tool-web](../../packages/web/tool-web),即 `web_search`/`web_fetch` 工具 schema)。Web 是**一项可选能力**,不属于 agent loop(智能体循环)主干,因此其词汇定义在此而非 [core.md](core.md) 中。更换 search 提供方不会改变模型请求 query 的方式,更换 fetch 实现也不会改变模型请求 URL 的方式。 + +源码:[`packages/web/web/src/types.ts`](../../packages/web/web/src/types.ts) + +## 为什么两项能力合为一个 seam + +搜索与抓取既不共享请求 schema,也不共享业务逻辑,但它们被有意设计为同一个 `ctx.web` 中间层:一个提供方选择策略的所有者、一套 abort/error 词汇、一个面向产品的「此 harness 如何访问 Web」配置界面。代价是服务上并行的 `searchX`/`fetchX` 方法对;这种并行是有意为之,而非遗漏的提取。提供方注册的是**能力**(`WebSearchProvider` 或 `WebFetchProvider`),而非工具;面向模型的名称、schema、提示词引导与展示全部集中在唯一的消费方 `dsh-tool-web` 中。 + +## 搜索请求与结果 + +面向模型的工具参数仅为一个 `query`;`maxResults` 是消费方自有的上限(`dsh-tool-web` 的 `searchMaxResults` 配置,默认 `8`),通过 seam 传递并在返回时强制执行——如果提供方返回超量,seam 截断 `sources[]` 并设置 `truncated`。 + +```ts type-equiv +/** + * What one search-capable backend can return. The model-facing argument is just + * a query; `maxResults` is a `dsh-tool-web`-layer bound passed through unchanged + * and enforced on the way back by the seam (see {@link WebSearchResult}). + */ +interface WebSearchRequest { + readonly query: string + /** + * Upper bound on returned sources; the seam truncates to it. Omitted = no + * bound. `dsh-tool-web` always sets it. A provider whose API supports a + * result-count control (Exa's `numResults`) should apply it at the request + * layer as a cost/latency optimization; the seam enforces the bound + * regardless. + */ + readonly maxResults?: number +} +``` + +```ts type-equiv +/** + * Normalized search outcome. `content` is optional provider-generated answer + * text or summary (Exa returns none; Perplexity returns a generated answer). + * `sources[]` is the portable citation surface. `truncated` is set by the seam + * when it cut `sources[]` down to `maxResults`. + */ +interface WebSearchResult { + /** Optional provider-generated answer text, search context, or summary. */ + readonly content?: string + /** Citeable sources, already truncated to the request's `maxResults`. */ + readonly sources: readonly WebSearchSource[] + /** True when the seam dropped sources to honor `maxResults`. */ + readonly truncated: boolean +} +``` + +`content` 是提供方可选生成的回答文本(Exa 和 DeepSeek 不返回;Perplexity 返回生成式回答)。`sources[]` 是一套可跨提供方使用的引用数据结构。一个 source 必有 `url`;`title`/`snippet`/`publishedAt` 可选,因为并非每个提供方都返回它们——Perplexity 的引用可能只有 URL,强迫适配器编造其余字段会让 seam 说谎。`dsh-tool-web` 渲染时使用 `title ?? hostname(url)`。 + +```ts type-equiv +/** + * One citeable source. A source always has a URL; `title`, `snippet`, and + * `publishedAt` are optional because not every provider returns them — forcing + * adapters to invent them would make the seam lie (Perplexity citations may be + * URL-only). `dsh-tool-web` renders `title ?? hostname(url)` for display. + */ +interface WebSearchSource { + readonly url: string + readonly title?: string + readonly snippet?: string + /** Publication/crawl timestamp as a provider-supplied ISO-8601 string. */ + readonly publishedAt?: string +} +``` + +## 抓取请求与结果 + +```ts type-equiv +/** + * What one fetch-capable backend is asked to retrieve. The request deliberately + * omits timeout, format, prompt, and extraction controls: cancellation is a + * direct execution argument, while presentation and higher-level LLM concerns + * belong outside safe retrieval. + */ +interface WebFetchRequest { + readonly url: string +} +``` + +HTTP 状态码是被抓取资源状态的一部分,不自动视为失败:成功的网络抓取返回 `404`/`500` 时,仍产出一个带状态码和有界解码 body 的 `WebFetchResult`。`url` 是经过允许的重定向后的最终 URL。`WebError` 仅用于无法安全获取或表示资源的情况。 + +```ts type-equiv +/** + * Normalized fetch outcome. A successful network fetch of a non-2xx response is + * a result, not an error: the status code is part of the fetched resource + * state. {@link WebError} is reserved for failures to safely retrieve or + * represent the resource. + */ +interface WebFetchResult { + /** The final URL after allowed redirects (the request URL is in the request). */ + readonly url: string + /** HTTP status code of the fetched response. */ + readonly statusCode: number + /** Decoded body, classified by content kind. */ + readonly body: WebFetchBody + /** True when the provider capped the decoded body. */ + readonly truncated: boolean +} +``` + +`WebFetchBody` 是 `dsh-web` 拥有的**封闭**可辨识联合类型(不是可合并扩展的 map):提供方解码 kind,`dsh-tool-web` 渲染它,因此新增一个 kind 是已知包之间的协调变更,而非插件扩展。消费方对 `kind` 做 `switch` 并以 `default: assertNever(...)` 结尾,所以新增 kind 会在每个消费方处编译失败,直到被处理。即使各分支当前字段一致,每个分支仍保持独立的对象字面量,为将来分支特有字段留出空间(例如未来 `pdf` body 的 `pageCount`)。 + +```ts type-equiv +/** + * The decoded body of a fetched resource. A CLOSED discriminated union owned by + * `dsh-web`: the provider decodes the kind and `dsh-tool-web` renders it, so a + * new kind is a coordinated change across known packages, not a plugin + * extension. Consumers `switch` on `kind` ending in `default: assertNever(...)` + * so adding a kind breaks compilation at every consumer until handled. Each arm + * stays its own object literal even where fields coincide today, leaving room + * for arm-specific fields later (a `pdf` body's `pageCount`). + */ +type WebFetchBody = + | { readonly kind: 'html'; readonly content: string } + | { readonly kind: 'text'; readonly content: string } +``` + +## 提供方可用性 + +提供方的 `available(): boolean` 是一个廉价的本地检查(凭证是否存在、配置是否可解析),**禁止发起网络调用**。它是执行时选择的输入,而非健康检查系统:`search()`/`fetch()` 读取它以选出可用的提供方,选择失败以结构化的 `WebError` 呈现给调用方路由——其 code 和 message 携带可分支的细节(缺失的 id 或有歧义的候选集)。 + +选择从不依赖注册顺序、配置顺序或 HMR(热模块替换)顺序:一项能力要么有显式的提供方 id(配置 `searchProvider`/`fetchProvider`,或填充同一字段的对应环境变量),要么在恰好只有一个可用提供方注册时自动选择;多个可用提供方且未配置 id 时为 `WEB_PROVIDER_AMBIGUOUS`,而非先注册先赢。 + +## 错误 + +`WebError extends HarnessError`([core.md](core.md) 错误分类体系),带有 `code: string`(开放式,与其他 seam 的错误一致——`LlmError`、`SubagentError`),而非封闭联合类型:提供方可以在不修改 `dsh-web` 的情况下抛出自己的 code,消费方必须容忍未知 code。code 按所有者划分。seam 中立的 code 由 `WebService` 选择逻辑和共享契约抛出:`WEB_PROVIDER_UNAVAILABLE`、`WEB_PROVIDER_CONFIGURED_MISSING`、`WEB_PROVIDER_CONFIGURED_UNAVAILABLE`、`WEB_PROVIDER_AMBIGUOUS`、`WEB_DUPLICATE_PROVIDER`(注册时的编程错误,类似 `LlmService` 的 `DUPLICATE_ADAPTER`)、`WEB_ABORTED`,以及 `WEB_PROVIDER_ERROR`(提供方自身故障通过 seam 暴露的兜底 code,包括网络/传输失败——DNS、连接被拒、TLS)。抓取传输层 code 由 `dsh-web-fetch-local` 实现拥有,不同的抓取后端无需抛出它们:`WEB_INVALID_URL`、`WEB_BLOCKED_URL`、`WEB_REDIRECT_BLOCKED`、`WEB_FETCH_TOO_LARGE`、`WEB_FETCH_TIMEOUT`、`WEB_UNSUPPORTED_CONTENT_TYPE`。 + +## 服务 + +`WebService` 注册搜索与抓取提供方,以 `WEB_DUPLICATE_PROVIDER` 拒绝重复 id,并在执行时以结构化的选择错误解析提供方。本地抓取后端仅接受 HTTP(S)、拒绝凭证、限制重定向次数、字节数、字符数和时间、对每一跳同源重定向重新校验,并解码 body;展示由工具负责。私有网络阻断尚未实现,因此请勿在可触及敏感内部目标的环境中启用 `web_fetch`。 diff --git a/docs/core-data-structures/workflow.i18n.yaml b/docs/core-data-structures/workflow.i18n.yaml new file mode 100644 index 0000000000..492a9bea08 --- /dev/null +++ b/docs/core-data-structures/workflow.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +workflow.md: 8d271b89e71de6f6bef548aa8da61402ef9ada6e +workflow.zh.md: b8ed699eb52d9f0cef23c513f625de7e82c46c45 diff --git a/docs/core-data-structures/workflow.md b/docs/core-data-structures/workflow.md index 8d8e47fc79..8d271b89e7 100644 --- a/docs/core-data-structures/workflow.md +++ b/docs/core-data-structures/workflow.md @@ -1,5 +1,7 @@ # Workflow +English | [中文](workflow.zh.md) + The workflow seam — an agent running a model-written orchestration SCRIPT that fans out subagents. Like [subagent](subagent.md) it is **one optional capability**, not part of the agent-loop spine, so its vocabulary lives here rather than in [core.md](core.md). Unlike the subagent registry it takes the bash shape: ONE engine implementation per context provides `ctx.workflows`; there is no named-provider registry (a second engine is a plugin swap, not a co-resident). Interface: [dsh-workflow](../../packages/workflow/workflow) (`ctx.workflows` + the vocabulary below). The implementation is [dsh-workflow-workerthread](../../packages/workflow/workflow-workerthread) (a `node:worker_threads` engine — one worker per run, the script's vm context inside it); the model-facing consumer is [dsh-tool-workflow](../../packages/workflow/tool-workflow). The proposal and rationale: [the dynamic-workflows Agent Note](../../.agents/notes/implemented/feature/2026-07-05-dynamic-workflows.md). diff --git a/docs/core-data-structures/workflow.zh.md b/docs/core-data-structures/workflow.zh.md new file mode 100644 index 0000000000..b8ed699eb5 --- /dev/null +++ b/docs/core-data-structures/workflow.zh.md @@ -0,0 +1,132 @@ +# 工作流 + +[English](workflow.md) | 中文 + +工作流 seam:一个 agent(智能体)运行由模型编写的编排脚本(SCRIPT),扇出 subagent。与 [subagent](subagent.md) 一样,它是**一项可选能力**,不属于 agent loop(智能体循环)主干,因此其词汇定义在此处而非 [core.md](core.md)。与 subagent 注册表不同,它采用 bash 形态:每个上下文只有一个引擎实现提供 `ctx.workflows`;没有命名提供方注册表(第二个引擎是插件替换,而非共存)。 + +接口:[dsh-workflow](../../packages/workflow/workflow)(`ctx.workflows` + 下文词汇)。实现是 [dsh-workflow-workerthread](../../packages/workflow/workflow-workerthread)(一个 `node:worker_threads` 引擎——每个 run 一个 worker,脚本的 vm 上下文位于其中);面向模型的消费方是 [dsh-tool-workflow](../../packages/workflow/tool-workflow)。提案与设计理由见 [dynamic-workflows Agent Note(agent 决策记录)](../../.agents/notes/implemented/feature/2026-07-05-dynamic-workflows.md)。 + +源码:[`packages/workflow/workflow/src/types.ts`](../../packages/workflow/workflow/src/types.ts) + +## 启动请求 + +调用方启动 run 时提出的请求。普通工作流工具根据模型的 `{ script, meta, args }` 调用与发起调用的 agent 构建它;专用消费方还可以为该 run 选择一个引擎级 `subagentProvider` 并调低 `maxTotalAgents`,但脚本无法观察或替换这两项策略。`meta` 与 `args` 是普通 JSON 数据(引擎会对 `meta` 做形状校验,并在任何内容运行前大声拒绝——绝不会通过求值脚本文本来获取它)。`parent` 是必填字段——脚本生成的每个子 agent 都归属于它(cwd、谱系与深度通过 [subagent seam](subagent.md) 流转)。 + +```ts type-equiv +/** + * What a caller asks for when starting a workflow run. `meta` and `args` are + * plain JSON DATA by the seam contract (the tool builds both from the model's + * schema-validated call; the engine validates `meta`'s shape and rejects loud + * before anything runs) — an engine never evaluates script text to obtain + * them. `parent` is REQUIRED — every `agent()` the script spawns is + * attributed to it (cwd, lineage, depth flow through the subagent seam). + */ +interface WorkflowStartRequest { + /** The plain-JS script body (top-level await allowed; ends with `return <json-value>`). */ + script: string + /** The workflow's identity block, as plain JSON data (shape-validated by the engine). */ + meta: WorkflowMeta + /** Optional input exposed verbatim to the script as the `args` global. */ + args?: unknown + /** + * Optional engine-wide child-provider override for this run. The workflow + * script cannot observe or replace it; omission uses the engine's configured + * provider. + */ + subagentProvider?: string + /** + * Optional per-run total-child ceiling. Implementations reject values above + * their deployment ceiling before publishing the run. + */ + maxTotalAgents?: number + /** The agent on whose behalf the run executes (parent of every child). */ + parent: Agent + /** Cancels the run when aborted (the tool's `exec.signal`). */ + signal?: AbortSignal +} +``` + +## 工作流的身份标识:`WorkflowMeta` + +作为数据附在启动请求上的身份块(工具的 `meta` 参数;字段词汇与 Claude Code 动态工作流的 meta 块一致)。`phases` 仅用于进度展示:`phase()` 调用与标题匹配,供观察者使用;不暗示任何执行结构。 + +```ts type-equiv +/** + * The script's identity block, provided as plain JSON data alongside the + * script body (the model-facing tool carries it as its `meta` parameter) and + * validated by the engine before the body runs. `name`/`description` are + * required; the rest is optional annotation. The field vocabulary matches the + * Claude Code dynamic-workflows meta block. + */ +interface WorkflowMeta { + /** Short kebab-case workflow name (display + persistence key). */ + name: string + /** One-line description of what the workflow does. */ + description: string + /** Optional guidance on when this workflow applies (shown in listings). */ + whenToUse?: string + /** Optional phase declarations matched by `phase()` calls. */ + phases?: WorkflowPhase[] +} +``` + +## 终态结果:`WorkflowResult` + +一次运行的结果,由 `WorkflowRun.result` resolve。`value` 是脚本的物化返回值——纯宿主域 JSON 数据(脚本无返回值时为 `null`)——仅在 `completed` 时有意义。`stopReason` 是封闭联合类型(引擎所有;消费方可穷举):`completed` | `cancelled` | `error`。非 `completed` 的原因在 `error` 中携带失败信息,消费方将其映射为 `isError` 工具结果,而非把部分输出当作成功上报。 + +```ts type-equiv +/** + * The outcome of one run, resolved by {@link WorkflowRun.result}. `value` is + * the script's materialized return value (plain host-realm JSON data; `null` + * when the script returned `undefined`) — meaningful only for `completed`. + * A non-`completed` reason carries the failure in `error`; the consumer maps + * it to an `isError` tool result rather than reporting partial output. + */ +interface WorkflowResult { + /** The script's return value (host JSON data; `null` for no return). */ + value: unknown + /** Why the run settled. */ + stopReason: WorkflowStopReason + /** The failure message (present iff `stopReason` is not `completed`). */ + error?: string + /** + * How many `agent()` calls the run accepted over its whole lifetime. On a + * graceful settlement this is the script-side count (calls still queued for + * a concurrency slot included); on a termination path (grace force-settle, + * worker death) it degrades to the host-observed count — calls queued + * inside a terminated script are unknowable then. + */ + agentsStarted: number +} +``` + +## 活跃运行:`WorkflowRun` + +脚本执行期间消费方持有的句柄。消费方 await `result`,可中途 `cancel`,且必须在每条路径上 `dispose`(资源释放)。`result` 不会 reject:脚本失败以 `stopReason: 'error'` resolve;一旦运行被取消,即使脚本本身永不 settle,它也会在引擎的有界宽限期内 settle(引擎强制以 `cancelled` settle;worker-thread 引擎随后终止脚本的 worker),因此消费方 await `result` 不会在取消后卡死。`dispose()` = cancel + 有界 settle + 等待子 agent 停稳;它不会因脚本卡死而挂起。 + +```ts type-equiv +/** + * Holder-owned live workflow. `result` never rejects and settles within the + * engine's cancellation grace; failures resolve through `stopReason`. Consumers + * may cancel and must call idempotent `dispose()` on every path to await bounded + * script settlement and child quiescence. + */ +interface WorkflowRun { + readonly id: WorkflowRunId + /** The validated meta block (available before the body runs). */ + readonly meta: WorkflowMeta + readonly result: Promise<WorkflowResult> + /** Cancel the run: children abort, pending hooks reject, the script dies at its next await (or is force-settled at the grace). */ + cancel(reason?: string): void + /** Cancel + bounded-grace settle; safe to call on every path (idempotent). */ + dispose(): Promise<void> +} +``` + +## 失败纪律:`WorkflowError.fatal` + +脚本内部的钩子误用:错误参数、未知或延迟的 `agent()` 选项、超出[结构化输出子集](../../packages/core/tools/README.md)的 schema、触发的上限、seam 启动失败、取消,都会抛出 `fatal: true` 的 `WorkflowError`。`parallel()`/`pipeline()` 组合器对 fatal 错误直接重新抛出,而非将该项映射为 `null`:一个拼写错误的选项必须让脚本大声失败,绝不能消融为看似普通子 agent 失败的结果。逐项的 `null` 保留给子运行失败(非 `completed` 的 stop reason)和阶段内的普通脚本错误。 + +## 事件 + +`workflow/*` 事件(`workflow/start`、`workflow/phase`、`workflow/log`、`workflow/agent-start`、`workflow/agent-end`、`workflow/end`,见[事件目录](../cordis-catalog/events.md))是**仅供观察**的 emit,携带数据快照:每个 payload 以 `WorkflowRunInfo`(id + meta)开头,而非活跃的 `WorkflowRun`,因此订阅者无法获得 `cancel`/`dispose`;`workflow/end` 刻意省略 result value(观察结果的监听器不得收到调用方 result 的可变别名)。每次 emit 对每个监听器隔离:抛出异常的订阅者被记录日志但不传播,不会饿死在它之后注册的监听器;每个监听器收到自己的 payload 克隆,因此修改它既不会损坏引擎也不会影响其他监听器。这种隔离方式与 `subagent/start`/`subagent/end` 一致。 diff --git a/docs/defensive-patterns.i18n.yaml b/docs/defensive-patterns.i18n.yaml new file mode 100644 index 0000000000..96c938a74f --- /dev/null +++ b/docs/defensive-patterns.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +defensive-patterns.md: c69094db461048f5dbca5f8bdd1fb5581b08a962 +defensive-patterns.zh.md: eb57f035ad0bd67e62e285d451502d41e4efc2bc diff --git a/docs/defensive-patterns.md b/docs/defensive-patterns.md index fe74a9d19f..c69094db46 100644 --- a/docs/defensive-patterns.md +++ b/docs/defensive-patterns.md @@ -1,5 +1,7 @@ # Defensive patterns +English | [中文](defensive-patterns.zh.md) + Hard-won bug-class rules: each pattern below is a class of defect that actually shipped or nearly shipped here, stated as the rule that prevents its recurrence. Read this before writing lifecycle, concurrency, subprocess, or teardown code. Test-tier counterparts (real entry path, world-verification, resource ownership) are in [testing.md](testing.md). ## Report orthogonal outcomes independently @@ -12,7 +14,7 @@ When an interface documents two valid ways to signal something — an adapter ma ## Async state is not synchronous state -`agent.send()` does not flip status before returning; a background task's completion races turn boundaries; `reader.close()` fires for both EOF and disposal. Never gate control flow on a status you only just requested — drive lifecycle off the events/promises that actually fire (`agent/status`, `task.done`), and observe the transition (saw `running` THEN `idle`) instead of treating status as a per-send result: several queued sends run as consecutive turns under one `running` interval, while cancellation or disposal can discard unstarted items. The guard cuts both ways: if the awaited transition can never occur (EOF with no work submitted → never `running`), the wait hangs — handle the "nothing to wait for" branch explicitly. +`agent.followup()` does not flip status before returning; a background task's completion races turn boundaries; `reader.close()` fires for both EOF and disposal. Never gate control flow on a status you only just requested — drive lifecycle off the events/promises that actually fire (`agent/status`, `task.done`), and observe the transition (saw `running` THEN `idle`) instead of treating status as a per-follow-up result: several queued follow-ups run as consecutive turns under one `running` interval, while cancellation or disposal can discard unstarted items. The guard cuts both ways: if the awaited transition can never occur (EOF with no work submitted → never `running`), the wait hangs — handle the "nothing to wait for" branch explicitly. ## Dispose must reach quiescence, not just request it diff --git a/docs/defensive-patterns.zh.md b/docs/defensive-patterns.zh.md new file mode 100644 index 0000000000..eb57f035ad --- /dev/null +++ b/docs/defensive-patterns.zh.md @@ -0,0 +1,29 @@ +# 防御性模式 + +[English](defensive-patterns.md) | 中文 + +来之不易的缺陷类别规则:下面每条模式都是本项目实际发布或差点发布的一类缺陷,以防止其复发的规则形式陈述。在编写生命周期、并发、子进程或清理代码之前请先阅读本文。测试层面的对应规则(真实入口路径、world 验证、资源归属)见 [testing.md](testing.md)。 + +## 正交结果独立上报 + +一个结果可以同时具有多重性质:进程可能既超时又以 exit 0 退出,因为它捕获了信号。每个独立事实(`timedOut`、`signal`、`exitCode`)都应独立暴露;切勿将某个 flag 的上报嵌套在另一个 flag 的分支内,否则调用方会把一次被截断的运行误读为正常成功。 + +## 跨 seam 契约两侧都要遵守 + +当一个接口文档记录了两种合法的信号方式时——例如适配器可以通过从 `stream()` 抛出异常来报告失败,也可以通过以 `finish {kind:'error'|'aborted'}` 分片结束流来报告——消费方必须同时处理两种路径,而不是只处理第一个实现恰好使用的那种。依赖库的适配器可能无法在流中途抛出异常,只能走带内路径;如果 agent loop(智能体循环)只捕获抛出的异常,就会把提供方的 401 错误变成一个正常完成的轮次。请在类型定义处记录契约;通过真实消费方测试每个分支。 + +## 异步状态不是同步状态 + +`agent.followup()` 不会在返回前翻转状态;后台任务的完成与轮次边界存在竞争;`reader.close()` 在 EOF 和 dispose(资源释放)两种情况下都会触发。切勿基于一个刚刚请求的状态来控制流程——应以实际触发的事件/promise(`agent/status`、`task.done`)驱动生命周期,并观察状态转换(先看到 `running` 再看到 `idle`),而不是把状态当作逐次 `followup()` 的结果:多次排队的 `followup()` 会在同一个 `running` 区间内连续运行多个轮次,而取消或资源释放可能丢弃尚未启动的项。这条守则是双向的:如果等待的转换永远不会发生(EOF 时没有提交过任何工作 → 永远不会进入 `running`),等待就会挂起——请显式处理「无需等待」的分支。 + +## Dispose 必须达到完全停稳,而不仅仅是请求停止 + +一个清理流程如果发出 kill/abort 后就返回、而不等待工作实际停止,就会留下孤儿进程。请让清理逻辑异步化并 await 子进程退出(kill → await `done`),并在 kill 之前关闭监听器/通知注册表,使迟到的完成事件保持静默。测试应证明 dispose 确实等待了(`await fiber.dispose()` 之后 pid 已不存在),而不仅仅是进程最终会死。 + +## 在边界处包容回调异常 + +用户提供的监听器如果抛出异常,不得导致它所在的 promise 被 reject,也不得饿死排在它后面的监听器。请用 try/catch 包裹分发循环并记录日志;一个行为不当的订阅者绝不能破坏核心生命周期。 + +## 绝不将环境变量或可预测路径暴露给不可信输出 + +spawn 的命令应获得一份经过清洗的 env(去除 `*KEY*`/`*SECRET*`/`*TOKEN*`),使 harness 凭证无法泄漏到输出、`env` 或溢出文件中。临时/溢出文件应使用私有(0700)目录、随机文件名和排他的仅所有者可访问打开方式(`'wx'`、`0o600`)——可预测的全局可读路径会招致符号链接竞争和信息泄露。 diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index 179ad0dcee..b36d390f55 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -8,22 +8,24 @@ This matrix shows which packages dispatch each harness-owned event and which pac | Event | Mode | Declared in | Dispatchers | Listeners | | --- | --- | --- | --- | --- | | `agent-loop/config-start-failed` | `emit` | [`packages/core/agent-loop/src/index.ts:353`](../packages/core/agent-loop/src/index.ts) | [`agent-loop`](../packages/core/agent-loop) (`events.dispatch`) | [`tui`](../packages/ui/tui) | -| `agent/cancel-requested` | `emit` | [`packages/core/agent/src/types.ts:217`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`goal-session`](../packages/goal/goal-session) | -| `agent/created` | `emit` | [`packages/core/agent/src/types.ts:179`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`goal-session`](../packages/goal/goal-session), [`tui`](../packages/ui/tui) | -| `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:188`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`agent-loop`](../packages/core/agent-loop), [`goal-session`](../packages/goal/goal-session), [`tui`](../packages/ui/tui) | -| `agent/error` | `emit` | [`packages/core/agent/src/types.ts:365`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`goal-session`](../packages/goal/goal-session), `runtime`, [`tui`](../packages/ui/tui) | -| `agent/post-step` | `serial` | [`packages/core/agent/src/types.ts:315`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`compact-basic`](../packages/compact/compact-basic), [`session-checkpoint-policy`](../packages/session-persistence/session-checkpoint-policy) | -| `agent/pre-step` | `serial` | [`packages/core/agent/src/types.ts:246`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`time-context`](../packages/context/time-context), [`user-approval`](../packages/ui/user-approval) | -| `agent/prompt-submit` | `waterfall` | [`packages/core/agent/src/types.ts:262`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`acp`](../packages/ui/acp), [`goal-session`](../packages/goal/goal-session), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`plan-mode`](../packages/plan/plan-mode), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) | -| `agent/queued` | `emit` | [`packages/core/agent/src/types.ts:207`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`goal-session`](../packages/goal/goal-session), [`tui`](../packages/ui/tui) | -| `agent/request` | `waterfall` | [`packages/core/agent/src/types.ts:276`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`agent`](../packages/core/agent) | -| `agent/request-error` | `waterfall` | [`packages/core/agent/src/types.ts:330`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`compact-basic`](../packages/compact/compact-basic), [`llm-retry`](../packages/llm/llm-retry), [`plan-mode`](../packages/plan/plan-mode) | -| `agent/session-prefix` | `waterfall` | [`packages/core/agent/src/types.ts:291`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`tool-skill`](../packages/skill/tool-skill), [`workspace-context`](../packages/context/workspace-context) | -| `agent/session-start` | `emit` | [`packages/core/agent/src/types.ts:230`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`goal`](../packages/goal/goal), [`goal-session`](../packages/goal/goal-session), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | -| `agent/status` | `emit` | [`packages/core/agent/src/types.ts:197`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`agent`](../packages/core/agent), [`goal-session`](../packages/goal/goal-session), `runtime`, [`tui`](../packages/ui/tui) | -| `agent/step-result` | `waterfall` | [`packages/core/agent/src/types.ts:303`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | -| `agent/turn-continuation` | `waterfall` | [`packages/core/agent/src/types.ts:341`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`plan-mode`](../packages/plan/plan-mode) | -| `agent/turn-stop` | `serial` | [`packages/core/agent/src/types.ts:352`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`subagent-inprocess`](../packages/subagent/subagent-inprocess), [`tool-goal`](../packages/goal/tool-goal) | +| `agent/cancel-requested` | `emit` | [`packages/core/agent/src/types.ts:350`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`goal-session`](../packages/goal/goal-session) | +| `agent/created` | `emit` | [`packages/core/agent/src/types.ts:285`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`goal-session`](../packages/goal/goal-session), [`tui`](../packages/ui/tui) | +| `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:294`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`agent-loop`](../packages/core/agent-loop), [`goal-session`](../packages/goal/goal-session), [`tui`](../packages/ui/tui) | +| `agent/error` | `emit` | [`packages/core/agent/src/types.ts:498`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`goal-session`](../packages/goal/goal-session), `runtime`, [`tui`](../packages/ui/tui) | +| `agent/inbox/dequeue` | `emit` | [`packages/core/agent/src/types.ts:326`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`agent`](../packages/core/agent) | +| `agent/inbox/discard` | `emit` | [`packages/core/agent/src/types.ts:340`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`agent`](../packages/core/agent) | +| `agent/inbox/enqueue` | `emit` | [`packages/core/agent/src/types.ts:316`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`agent`](../packages/core/agent), [`goal-session`](../packages/goal/goal-session), [`tui`](../packages/ui/tui) | +| `agent/post-step` | `serial` | [`packages/core/agent/src/types.ts:448`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`compact-basic`](../packages/compact/compact-basic), [`session-checkpoint-policy`](../packages/session-persistence/session-checkpoint-policy) | +| `agent/pre-step` | `serial` | [`packages/core/agent/src/types.ts:379`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`time-context`](../packages/context/time-context), [`user-approval`](../packages/ui/user-approval) | +| `agent/prompt-submit` | `waterfall` | [`packages/core/agent/src/types.ts:395`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`acp`](../packages/ui/acp), [`goal-session`](../packages/goal/goal-session), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`plan-mode`](../packages/plan/plan-mode), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) | +| `agent/request` | `waterfall` | [`packages/core/agent/src/types.ts:409`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`agent`](../packages/core/agent) | +| `agent/request-error` | `waterfall` | [`packages/core/agent/src/types.ts:463`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`compact-basic`](../packages/compact/compact-basic), [`llm-retry`](../packages/llm/llm-retry), [`plan-mode`](../packages/plan/plan-mode) | +| `agent/session-prefix` | `waterfall` | [`packages/core/agent/src/types.ts:424`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`tool-skill`](../packages/skill/tool-skill), [`workspace-context`](../packages/context/workspace-context) | +| `agent/session-start` | `emit` | [`packages/core/agent/src/types.ts:363`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`goal`](../packages/goal/goal), [`goal-session`](../packages/goal/goal-session), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | +| `agent/status` | `emit` | [`packages/core/agent/src/types.ts:303`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`agent`](../packages/core/agent), [`goal-session`](../packages/goal/goal-session), `runtime`, [`tui`](../packages/ui/tui) | +| `agent/step-result` | `waterfall` | [`packages/core/agent/src/types.ts:436`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | +| `agent/turn-continuation` | `waterfall` | [`packages/core/agent/src/types.ts:474`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`plan-mode`](../packages/plan/plan-mode) | +| `agent/turn-stop` | `serial` | [`packages/core/agent/src/types.ts:485`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`subagent-inprocess`](../packages/subagent/subagent-inprocess), [`tool-goal`](../packages/goal/tool-goal) | | `approval/request` | `waterfall` | [`packages/ui/user-approval/src/index.ts:30`](../packages/ui/user-approval/src/index.ts) | [`user-approval`](../packages/ui/user-approval) (`waterfall`) | [`acp`](../packages/ui/acp) | | `commands/change` | `emit` | [`packages/ui/commands/src/index.ts:103`](../packages/ui/commands/src/index.ts) | [`commands`](../packages/ui/commands) (`events.dispatch`) | [`acp`](../packages/ui/acp), [`tui`](../packages/ui/tui) | | `fs/edit-intent` | `waterfall` | [`packages/fs/fs/src/index.ts:62`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`waterfall`) | [`fs-policy`](../packages/fs/fs-policy) | diff --git a/docs/glossary.i18n.yaml b/docs/glossary.i18n.yaml new file mode 100644 index 0000000000..b63e41b87b --- /dev/null +++ b/docs/glossary.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +glossary.md: 0270a2d0dba558483e8e458a932a27b0151f2c93 +glossary.zh.md: ed3009a054815f1c7165fc322e44cc9521527643 diff --git a/docs/glossary.md b/docs/glossary.md index e290543d2c..0270a2d0db 100644 --- a/docs/glossary.md +++ b/docs/glossary.md @@ -1,5 +1,7 @@ # Glossary +English | [中文](glossary.zh.md) + Domain vocabulary for the DeepSeek Harness SDK uses one canonical term per concept. Terms link to their entries with standard Markdown anchors; implementation detail stays in package READMEs and Agent Notes. FIXME(glossary-completeness): Expand this glossary before the first release so it covers the SDK's other core and capability subsystems, not only agent scope. @@ -19,7 +21,7 @@ FIXME(glossary-completeness): Expand this glossary before the first release so i ## goal - **goal** — one durable completion objective attached to an existing session, with a revisioned `active` / `paused` / `blocked` / `complete` phase and a goal-round cap; `blocked` retains a policy code and explanation. A goal is state, not a scheduler or a separate conversation; the session log remains its source of truth. -- **goal round** — one continuation cycle admitted for the current goal. The same-session driver materializes a goal round as one goal-sourced [turn](#turn), which can contain multiple steps; unrelated human turns in the same session do not consume the goal-round cap. <a id="goal-round"></a> +- **goal round** — one continuation cycle admitted for the current goal. The same-session driver materializes a goal round as one goal-sourced [turn](#turn), which can contain zero or more steps; unrelated human turns in the same session do not consume the goal-round cap. <a id="goal-round"></a> - **goal activation** — process-local permission for a continuation consumer to admit another goal round. Activation is either `armed` or `disarmed`; it is deliberately absent from durable replay, so resume and fork require a later human-authorized resume mutation through `/goal` or the model tool before automatic work. ## human command @@ -31,7 +33,7 @@ FIXME(glossary-completeness): Expand this glossary before the first release so i ## loop hierarchy - **turn** — one drain of admitted input in a session, ending after the model and its tools stop or a terminal policy intervenes. <a id="turn"></a> -- **step** — one model request plus the tool executions caused by its response; a turn contains one or more steps. <a id="step"></a> +- **step** — one model request plus the tool executions caused by its response; a turn contains zero or more steps. <a id="step"></a> - **round** — an outer policy iteration containing a turn, such as a [goal round](#goal-round) or one fresh-agent Ralph attempt. Round counters belong to that policy and do not count every turn in a session. <a id="round"></a> ## Ralph diff --git a/docs/glossary.zh.md b/docs/glossary.zh.md new file mode 100644 index 0000000000..ed3009a054 --- /dev/null +++ b/docs/glossary.zh.md @@ -0,0 +1,43 @@ +# 术语表 + +[English](glossary.md) | 中文 + +DeepSeek Harness SDK 的领域词汇为每个概念规定一个规范术语。各术语通过标准 Markdown 锚点链接到相应条目;实现细节留在各包(package)的 README 与 Agent Note(agent 决策记录)中。 + +FIXME(glossary-completeness): 首次发布前扩充本术语表,使其覆盖 SDK 的其他核心与能力子系统,而非仅限于 agent scope。 + +## agent-scope + +- **scope**:按 agent(智能体)划分的注册单位。一项贡献(工具、提示词片段、变量、限制、监听器)要么是*全局的*(对所有 agent 可见),要么是*有范围的*(归属于恰好一个 [scope key](#scope-key))。只有两层,扁平结构:有范围的注册不会向下继承给 subagent;子树行为通过 [lineage](#lineage) 数据表达,从不通过 scope 结构。 +- **scope key**:scope 的不透明标识,按对象同一性比较。harness 约定:一个活跃的 agent 就是其自身 scope 的 key。<a id="scope-key"></a> +- **agent 上下文(`agent.ctx`)**:agent 的有范围上下文;通过它进行的注册既是 scope 可见的,也是 scope 生命周期的(同一事实决定两者),其上的监听器参与该 agent 的 scope 过滤分发。注册表主体事件可以在各自的事件契约下保持故意不过滤。 +- **scope carrier**:scope 过滤分发所携带的 `thisArg`(由 `scopeTarget` 构建);其过滤器放行无标签监听器加上主体自身的监听器。*无主体*的 carrier(没有 key)只放行无标签监听器。 +- **scoped dispatch**:规则是:关于某个 agent 活动的事件以该 agent 的 carrier 进行分发。关于注册表本身的事件(如「一个工具被添加了」)属于*注册表主体*事件,保持不过滤。 +- **shadowing**:最具体者胜出的名称解析:一个有范围的工具/片段/变量仅在该 scope 内替换同名的全局对应项。这是按 agent 定制 persona 和按 agent 定制工具变体的机制。 +- **restriction / scope-local 注册**:restriction(`tools.restrict`)为单个 scope 过滤全局工具表面(多个 restriction 取交集组合);scope-local 注册在过滤之后合并。被过滤掉的全局工具既不出现在提示词中,也拒绝执行,与不存在的工具无法区分。 +- **setup window**:创建者组装 agent 有范围世界的创建时隙(`CreateAgentOptions.setup`):在 scope 和 agent 对象已存在、但 agent 或会话尚未发布、`agent/session-start` 尚未触发、首次提示词尚未组装之前。setup 只做注册,从不驱动 agent。 +- **lineage**:以数据形式携带的父子关系事实(`parentSession`、持久的 `delegationDepth`、运行时 `subagentDepth`);从不影响可见性。<a id="lineage"></a> + +## 目标 + +- **目标**:附着在现有会话上的单个持久完成目标,带有按修订号演进的 `active` / `paused` / `blocked` / `complete` 阶段和 Goal Round 上限;`blocked` 保留策略代码与说明。目标是一种状态,不是调度器,也不是一段独立对话;会话日志仍是其真源。 +- **Goal Round**:为当前目标接纳的一次续行周期。同会话驱动器将 Goal Round 具体化为一个来源为目标的[轮次](#turn),其中可包含零个或多个步骤;同一会话中无关的人类轮次不消耗 Goal Round 上限。<a id="goal-round"></a> +- **目标激活**:续行消费方接纳下一个 Goal Round 的进程本地权限。激活态为 `armed` 或 `disarmed`;它有意不参与持久回放,因此恢复和 fork 后,必须由人类随后通过 `/goal` 或模型工具授权恢复变更,自动工作才可开始。 + +## 人类命令 + +- **人类命令**:以斜杠开头的指令,由面向人类的适配器通过 `ctx.commands` 解释并执行,不会成为模型消息。它既不同于面向模型的工具,也不同于通过 `ctx.bash` 执行 shell 命令。 +- **命令平面**:由 UI 适配器与命令插件拥有的发现、解析、分发、取消和结果渲染。除非处理器另行改变持久领域,否则命令输出属于 UI 状态。 +- **目标命令**:`/goal` 是由 `dsh-command-goal` 提供的人类命令;它直接观察或更改当前目标,而目标领域拥有每条持久且模型可见的记录。 + +## 循环层级 + +- **轮次**:会话中一次对已接纳输入的排空过程,在模型及其工具停止工作或终止策略介入后结束。<a id="turn"></a> +- **步骤**:一次模型请求,以及由模型响应引发的工具执行;一个轮次包含零个或多个步骤。<a id="step"></a> +- **Round**:承载一个轮次的外层策略迭代,例如一个 [Goal Round](#goal-round) 或一次使用全新 agent 的 Ralph 尝试。Round 计数器归该策略所有,并不统计会话中的每个轮次。<a id="round"></a> + +## Ralph + +- **Ralph 循环**:一次面向不可变目标的前台全新 agent 工作流运行。它是由工作流和 subagent 原语组合而成的面向模型的工具策略,不是同会话目标、agent loop(智能体循环)模式、调度器或通用工作流脚本功能。<a id="ralph-loop"></a> +- **Ralph Round**:[Ralph 循环](#ralph-loop)中的一个全新子会话。子会话不接收父会话或此前子会话的对话种子;共享工作区和一份有界的 [Ralph 交接](#ralph-handoff)承载跨 Round 的状态。<a id="ralph-round"></a> +- **Ralph 交接**:从一个仍需继续的 Ralph Round 传给下一个 Ralph Round 的规范化、有界结构化报告,包含状态、摘要、证据、后续步骤和阻塞说明。它补充共享工作区,而不取代工作区的权威地位。<a id="ralph-handoff"></a> diff --git a/docs/i18n/README.i18n.yaml b/docs/i18n/README.i18n.yaml index d48ab803ee..602699a178 100644 --- a/docs/i18n/README.i18n.yaml +++ b/docs/i18n/README.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 -README.md: 430c499afbbfb786928276f6348cc0cedf14f94d -README.zh.md: 7ac7f4a2a8983c753def61df6f6d86a26405a3a0 +README.md: 77d7b3210216c7c12d7d06b1ed16396d02ef1d16 +README.zh.md: de15fc3b5f30c1280ce6b38c1afd2475be7f9671 diff --git a/docs/i18n/README.md b/docs/i18n/README.md index 430c499afb..77d7b32102 100644 --- a/docs/i18n/README.md +++ b/docs/i18n/README.md @@ -40,7 +40,7 @@ The gate's limit, stated plainly: **a green gate means the pair was confirmed co **Excluded** (never paired, and the gate rejects a `.zh.md` or `.i18n.yaml` for them): -- `docs/cordis-catalog/`, `docs/tool-catalog/`, `docs/config-catalog.md`, `docs/persistence-catalog.md`, and `docs/module-graph.md` — generated files; their generators emit English only today, so a hand-written translation would go stale on every regeneration. The planned follow-up is to teach the generators to emit Chinese alongside English, at which point these leave the exclusion list. +- `docs/cordis-catalog/`, `docs/tool-catalog/`, `docs/config-catalog.md`, `docs/persistence-catalog.md`, `docs/module-graph.md`, `docs/agent-lifecycle.md`, `docs/capability-seams.md`, `docs/event-producer-consumer.md`, `docs/graph-atlas.md`, and `docs/tool-execution-pipeline.md` — generated files; their generators emit English only today, so a hand-written translation would go stale on every regeneration. The planned follow-up is to teach the generators to emit Chinese alongside English, at which point these leave the exclusion list. - `docs/AGENTS.md` and `.agents/notes/**/AGENTS.md` — agent instructions, maintained in English only like the root `AGENTS.md`. - `docs/i18n/terminology.md` and [style-samples.md](style-samples.md) — both are bilingual by construction. - [translation-prompt.md](translation-prompt.md) — the automated pipeline's prompt template; its body is machine-consumed verbatim, so a paired translation would change pipeline behavior. diff --git a/docs/i18n/README.zh.md b/docs/i18n/README.zh.md index 7ac7f4a2a8..de15fc3b5f 100644 --- a/docs/i18n/README.zh.md +++ b/docs/i18n/README.zh.md @@ -40,7 +40,7 @@ **排除**(永不配对,门禁拒绝为它们建 `.zh.md` 或 `.i18n.yaml`): -- `docs/cordis-catalog/`、`docs/tool-catalog/`、`docs/config-catalog.md`、`docs/persistence-catalog.md` 与 `docs/module-graph.md`:生成文件;生成器目前只输出英文,手写译文在每次重新生成时必然陈旧。计划中的后续工作是让生成器同时输出中文,届时这些文件移出排除清单。 +- `docs/cordis-catalog/`、`docs/tool-catalog/`、`docs/config-catalog.md`、`docs/persistence-catalog.md`、`docs/module-graph.md`、`docs/agent-lifecycle.md`、`docs/capability-seams.md`、`docs/event-producer-consumer.md`、`docs/graph-atlas.md` 与 `docs/tool-execution-pipeline.md`:生成文件;生成器目前只输出英文,手写译文在每次重新生成时必然陈旧。计划中的后续工作是让生成器同时输出中文,届时这些文件移出排除清单。 - `docs/AGENTS.md` 与 `.agents/notes/**/AGENTS.md`:agent 指令,与根 `AGENTS.md` 一样只以英文维护。 - `docs/i18n/terminology.md` 与 [style-samples.md](style-samples.md):二者本身即为中英对照文档。 - [translation-prompt.md](translation-prompt.md):自动翻译流水线的提示词模板;正文逐字进入模型请求,配对翻译会改变流水线行为。 diff --git a/docs/i18n/style-samples.md b/docs/i18n/style-samples.md index dd970b7c12..b20b2a4c90 100644 --- a/docs/i18n/style-samples.md +++ b/docs/i18n/style-samples.md @@ -28,9 +28,9 @@ **dispose(资源释放)必须等待所有任务完全停稳,不能仅下发终止指令就返回**:如果清理过程只发出终止或中断信号,却不等任务停止就返回,就会留下孤儿进程。清理应采用异步方式,等待所有子任务彻底退出(先发出终止信号,再等待退出);发出信号前应先关闭监听器与通知注册表,使延迟到达的完成事件不再触发通知。测试要证明 dispose 的确等到清理完成:执行完 `await fiber.dispose()` 后进程 PID 立即消失,不能只检查进程最终会自行消亡。 -> **Async state is not synchronous state** — `agent.send()` does not flip status before returning; a background task's completion races turn boundaries; `reader.close()` fires for both EOF and disposal. Never gate control flow on a status you only just requested — drive lifecycle off the events/promises that actually fire (`agent/status`, `task.done`), and observe the transition (saw `running` THEN `idle`) instead of treating status as a per-send result: several queued sends run as consecutive turns under one `running` interval, while cancellation or disposal can discard unstarted items. +> **Async state is not synchronous state** — `agent.followup()` does not flip status before returning; a background task's completion races turn boundaries; `reader.close()` fires for both EOF and disposal. Never gate control flow on a status you only just requested — drive lifecycle off the events/promises that actually fire (`agent/status`, `task.done`), and observe the transition (saw `running` THEN `idle`) instead of treating status as a per-follow-up result: several queued follow-ups run as consecutive turns under one `running` interval, while cancellation or disposal can discard unstarted items. -**异步状态不等同于同步瞬时状态**:调用 `agent.send()` 不会在返回前同步更新状态;后台任务的完成时间与轮次边界存在竞态;`reader.close()` 既会在读到文件末尾时触发,也会在资源释放时触发。切勿把刚刚发起的状态变更当成已经生效,据此控制流程;生命周期逻辑应以实际触发的事件和已完成的 promise(`agent/status`、`task.done`)为准,并观察完整的状态变化(先 `running`,再 `idle`),不要把状态当作逐次 `send()` 的结果:多次排队的 `send()` 会作为连续轮次运行,但可能共用一个 `running` 区间;取消或资源释放还可能丢弃尚未启动的队列项。 +**异步状态不等同于同步瞬时状态**:调用 `agent.followup()` 不会在返回前同步更新状态;后台任务的完成时间与轮次边界存在竞态;`reader.close()` 既会在读到文件末尾时触发,也会在资源释放时触发。切勿把刚刚发起的状态变更当成已经生效,据此控制流程;生命周期逻辑应以实际触发的事件和已完成的 promise(`agent/status`、`task.done`)为准,并观察完整的状态变化(先 `running`,再 `idle`),不要把状态当作逐次 `followup()` 的结果:多次排队的 `followup()` 会作为连续轮次运行,但可能共用一个 `running` 区间;取消或资源释放还可能丢弃尚未启动的队列项。 ## ③ 测试政策清单 diff --git a/docs/i18n/terminology.md b/docs/i18n/terminology.md index 74ce7ad969..ae28258b9b 100644 --- a/docs/i18n/terminology.md +++ b/docs/i18n/terminology.md @@ -52,6 +52,7 @@ | loader | loader | | | | | manifest | manifest | manifest(元数据清单) | | | | monorepo | monorepo | | | | +| Round | Round | | 回合、目标回合、Ralph 回合 | 外层策略使用 Round 时,领域层级为 Session > Round > Turn(轮次) > Step(步骤);Round 是可选的外层策略迭代,并非每个会话轮次都具有的通用层级。Goal Round 与 Ralph Round 均保留英文。一个 Round 承载一个轮次,步骤隶属于该轮次;明确的零步骤轮次仍保持原义。 | | schema | schema | | | | | schema DSL | schema DSL | | | | | seam | seam | | | 与 `extension point` 是不同概念;根据具体语境,可译为`服务边界`或`可替换点` | @@ -103,10 +104,12 @@ | durability | 持久性 | | | | | feature requirement | 功能依赖 | | | 功能或功能选项通过 `requires` 声明的关系 | | enforcement frontier | 执行红线 | | 强制边界 | i18n 配对机制用语:manifest `required` 清单所划的门禁生效范围;与金标样例(style-samples ⑦)一致 | +| ergonomics | 易用性 / 开发体验 | | 人体工学 | API 或面向模型的接口用「易用性」;工具链或开发者工作流用「开发体验」 | | event | 事件 | | | | | event log | 事件日志 | | | | | event stream | 事件流 | | | | | event-sourced | 事件溯源 | | | 沿用 DDD 社区通行译法 | +| Executive summary | 摘要 | | | 事故复盘标题用语 | | executor | 执行器 | | | | | expected output | 预期输出 | | 金标 | 指 snapshot 比较产物;翻译语料的人工校准样例不在此列 | | extension | 扩展 | | | | @@ -131,11 +134,14 @@ | mod | 模组 | | | | | model provider | 模型提供方 | | | | | module | 模块 | | | | +| non-escalation | 非升权 | | 非升级、不可升级 | 仅用于安全与权限语境,指主体不得获得超出既有授权的权限;普通升级不适用此行 | | npm dependency | NPM 依赖 | | | `package.json` 中的包关系;`dependencies`、`devDependencies` 等字段保持原样 | +| opt-out ratio | opt-out 比例 | | 退出检查比例 | | | orphan | 遗留 | | 孤儿、孤立 | 指英文源已不存在的 `.zh.md`(如「遗留译文」);进程语境按 OS 惯用语译「孤儿进程」 | | orphan branch | 孤立分支 | | 孤儿分支 | 沿用 git 官方中文翻译 | | package | 包 | 包(package) | | 指 npm 包(`@deepseek-ai/dsh-*`);`package.json` 等代码标识保持原样 | | pairing | 配对 | | | | +| parent-subset grants | 父级子集授权 | | 父集合授权 | 指授权范围仅限于父级所持授权的子集 | | peer dependency | 对等依赖 | 对等依赖(peer dependency) | | | | permission | 权限 | | | | | persistence | 持久化 | | | | @@ -145,12 +151,14 @@ | provider | 提供方 | | | | | provider-neutral | 提供方无关 | | | | | quality gate | 质量门禁 | | | | +| quiescence | 完全停稳 | | 静默、静止状态 | 指生命周期工作全部结算后的状态 | | reasoning | 推理 | 推理(reasoning) | | 需要和 `inference` 区分时保留英文括注 | | reasoning_content | 思考内容 | | | | | registry | 注册表 | | | | | replay | 回放 | | | | | resume | 恢复 | | | | | runtime | 运行时 | | | | +| same-world subprocess | 与宿主共享文件系统和内核的子进程 | | 同世界子进程 | | | sandbox | 沙箱 | | | | | service | 服务 | | | | | serving surface | 对外服务接口 | | | | @@ -167,6 +175,7 @@ | stream | 流 | | | | | streaming | 流式输出 | | | | | structural signature | 结构签名 | | | i18n 配对机制用语:门禁比对两侧文件时提取的有序结构序列(标题层级、代码块、列表等) | +| Summary | 概述 | | | 事故复盘标题用语 | | system prompt | 系统提示词 | | | | | taxonomy | 分类体系 | | | | | token usage | token 用量 | | | | diff --git a/docs/persistence-catalog.md b/docs/persistence-catalog.md index 8c1d815bc0..973238d905 100644 --- a/docs/persistence-catalog.md +++ b/docs/persistence-catalog.md @@ -24,14 +24,13 @@ export type SurfaceEventType = | 'user/message' | 'assistant/message' | 'tool/result' - | 'context/message' | 'steering/message' /** * How a session event entered the ordered surface. Only valid on * {@link SurfaceEventType} events. * - * - `'append'`: added to the tail — normal path for user/assistant/tool/context + * - `'append'`: added to the tail — normal path for user/assistant/tool/steering * messages. * - `{ op: 'replace', start, end }`: replaces surface nodes from `start` * (inclusive) through `end` (inclusive) with this node. Both must exist as @@ -51,7 +50,7 @@ export type SurfaceOp = * * The {@link sourceEventSeqs} and {@link surfaceOp} fields are conditional: * they only exist on {@link SurfaceEventType} variants (`user/message`, - * `assistant/message`, `tool/result`, `context/message`, `steering/message`). + * `assistant/message`, `tool/result`, `steering/message`). * Non-surface events (boundary markers, chunks, usage, errors) never carry * surface metadata — the compiler enforces this at `Session.append()` * call sites. @@ -79,7 +78,7 @@ export type SessionEvent<T extends SessionEventType = SessionEventType> = { }[T] ``` -Sources: [`packages/core/session/src/types.ts:317`](../packages/core/session/src/types.ts) · [`packages/core/session/src/types.ts:330`](../packages/core/session/src/types.ts) · [`packages/core/session/src/types.ts:360`](../packages/core/session/src/types.ts) · [`packages/core/session/src/types.ts:392`](../packages/core/session/src/types.ts) +Sources: [`packages/core/session/src/types.ts:325`](../packages/core/session/src/types.ts) · [`packages/core/session/src/types.ts:338`](../packages/core/session/src/types.ts) · [`packages/core/session/src/types.ts:367`](../packages/core/session/src/types.ts) · [`packages/core/session/src/types.ts:399`](../packages/core/session/src/types.ts) ## Events @@ -151,7 +150,7 @@ Source: [`packages/ui/user-approval/src/index.ts:67`](../packages/ui/user-approv Types: [StreamChunk](core-data-structures/llm-streaming.md) -Source: [`packages/core/session/src/types.ts:263`](../packages/core/session/src/types.ts) +Source: [`packages/core/session/src/types.ts:271`](../packages/core/session/src/types.ts) #### `assistant/message` — surface @@ -167,7 +166,7 @@ Source: [`packages/core/session/src/types.ts:263`](../packages/core/session/src/ Types: [ContentBlock](core-data-structures/core.md) · [TokenUsage](core-data-structures/llm-streaming.md) -Source: [`packages/core/session/src/types.ts:270`](../packages/core/session/src/types.ts) +Source: [`packages/core/session/src/types.ts:278`](../packages/core/session/src/types.ts) ### `compact/*` @@ -221,33 +220,6 @@ Types: [ContentBlock](core-data-structures/core.md) Source: [`packages/compact/compact/src/types.ts:22`](../packages/compact/compact/src/types.ts) -### `context/*` - -#### `context/message` — surface - -```ts persistence-catalog -/** - * In-session context injection (file-change notices, subdir AGENTS.md, - * skill content, cron notifications, …). Rendered into the derived history - * as a synthetic user-role message carrying `content` verbatim — NOT a - * user prompt. `meta` is durable JSON state omitted from the model - * projection; it is also the intended channel for any future framing - * directive (a producer declares the frame, a dedicated renderer applies it — - * see the deferred note in - * ../../../../.agents/notes/implemented/simplification/2026-07-20-unwrap-injected-content-envelopes.md), - * so the surface keeps projecting `content` verbatim rather than wrapping it. - */ -'context/message': { - content: ContentBlock[] - source: MessageSource - meta?: JsonValue -} -``` - -Types: [ContentBlock](core-data-structures/core.md) · [MessageSource](core-data-structures/core.md) - -Source: [`packages/core/session/src/types.ts:257`](../packages/core/session/src/types.ts) - ### `hook/*` #### `hook/invoked` — log-only @@ -357,7 +329,7 @@ Source: [`packages/plan/plan-mode/src/index.ts:41`](../packages/plan/plan-mode/s Types: [ContentBlock](core-data-structures/core.md) · [MessageSource](core-data-structures/core.md) -Source: [`packages/core/session/src/types.ts:245`](../packages/core/session/src/types.ts) +Source: [`packages/core/session/src/types.ts:269`](../packages/core/session/src/types.ts) ### `request/*` @@ -371,7 +343,7 @@ Source: [`packages/core/session/src/types.ts:245`](../packages/core/session/src/ 'request/header': { header: EpochHeader; reason: RequestHeaderReason } ``` -Source: [`packages/core/session/src/types.ts:305`](../packages/core/session/src/types.ts) +Source: [`packages/core/session/src/types.ts:313`](../packages/core/session/src/types.ts) ### `sandbox/*` @@ -427,7 +399,7 @@ Source: [`packages/session-title/session-title-llm/src/index.ts:44`](../packages 'steering/message': PromptMessageData & { turn: number } ``` -Source: [`packages/core/session/src/types.ts:298`](../packages/core/session/src/types.ts) +Source: [`packages/core/session/src/types.ts:306`](../packages/core/session/src/types.ts) ### `step/*` @@ -438,7 +410,7 @@ Source: [`packages/core/session/src/types.ts:298`](../packages/core/session/src/ 'step/end': { turn: number; step: number } ``` -Source: [`packages/core/session/src/types.ts:238`](../packages/core/session/src/types.ts) +Source: [`packages/core/session/src/types.ts:254`](../packages/core/session/src/types.ts) #### `step/start` — log-only @@ -447,7 +419,7 @@ Source: [`packages/core/session/src/types.ts:238`](../packages/core/session/src/ 'step/start': { turn: number; step: number } ``` -Source: [`packages/core/session/src/types.ts:236`](../packages/core/session/src/types.ts) +Source: [`packages/core/session/src/types.ts:252`](../packages/core/session/src/types.ts) ### `todo/*` @@ -460,7 +432,7 @@ Source: [`packages/core/session/src/types.ts:236`](../packages/core/session/src/ Types: [TodoItem](core-data-structures/session.md) -Source: [`packages/core/session/src/types.ts:300`](../packages/core/session/src/types.ts) +Source: [`packages/core/session/src/types.ts:308`](../packages/core/session/src/types.ts) ### `tool/*` @@ -477,7 +449,7 @@ Source: [`packages/core/session/src/types.ts:300`](../packages/core/session/src/ Types: [CallId](core-data-structures/core.md) -Source: [`packages/core/session/src/types.ts:276`](../packages/core/session/src/types.ts) +Source: [`packages/core/session/src/types.ts:284`](../packages/core/session/src/types.ts) #### `tool/code-dispatch` — log-only @@ -531,7 +503,7 @@ Source: [`packages/core/tools/src/code-mode.ts:34`](../packages/core/tools/src/c Types: [CallId](core-data-structures/core.md) · [ContentBlock](core-data-structures/core.md) -Source: [`packages/core/session/src/types.ts:288`](../packages/core/session/src/types.ts) +Source: [`packages/core/session/src/types.ts:296`](../packages/core/session/src/types.ts) ### `turn/*` @@ -549,7 +521,7 @@ Source: [`packages/core/session/src/types.ts:288`](../packages/core/session/src/ Types: [TurnEndReason](core-data-structures/session.md) -Source: [`packages/core/session/src/types.ts:234`](../packages/core/session/src/types.ts) +Source: [`packages/core/session/src/types.ts:250`](../packages/core/session/src/types.ts) #### `turn/start` — log-only @@ -565,15 +537,23 @@ Source: [`packages/core/session/src/types.ts:234`](../packages/core/session/src/ Types: [TurnTrigger](core-data-structures/session.md) -Source: [`packages/core/session/src/types.ts:227`](../packages/core/session/src/types.ts) +Source: [`packages/core/session/src/types.ts:243`](../packages/core/session/src/types.ts) ### `user/*` #### `user/message` — surface ```ts persistence-catalog -/** A user-visible prompt (the queued message claimed for this turn). */ +/** + * A user-role message on the model-visible surface: a direct human prompt + * (the queued message claimed for this turn), a synthetic `agent.inject()` + * context (file-change notices, subdir AGENTS.md, skill content, cron + * notifications, …), or an admitted goal continuation round. All three + * project their `content` verbatim; `source` (with a non-`user` kind marking + * injected context) is the only channel that tells them apart. An idle + * injection wraps this event in a one-shot turn so the log stays turn-enclosed. + */ 'user/message': PromptMessageData ``` -Source: [`packages/core/session/src/types.ts:240`](../packages/core/session/src/types.ts) +Source: [`packages/core/session/src/types.ts:264`](../packages/core/session/src/types.ts) diff --git a/docs/postmortem/0001-acp-default-export-drops-inject.i18n.yaml b/docs/postmortem/0001-acp-default-export-drops-inject.i18n.yaml new file mode 100644 index 0000000000..d48af64198 --- /dev/null +++ b/docs/postmortem/0001-acp-default-export-drops-inject.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +0001-acp-default-export-drops-inject.md: ab3efc880cb5290dc149b6bacb276ccf581968c1 +0001-acp-default-export-drops-inject.zh.md: 763b2e6230cf42dcd6985df3d7e2da8766176fd5 diff --git a/docs/postmortem/0001-acp-default-export-drops-inject.md b/docs/postmortem/0001-acp-default-export-drops-inject.md index 10e88c390c..ab3efc880c 100644 --- a/docs/postmortem/0001-acp-default-export-drops-inject.md +++ b/docs/postmortem/0001-acp-default-export-drops-inject.md @@ -1,5 +1,7 @@ # Post-mortem 0001: ACP server crashed on connect — `export default` dropped the plugin's `inject` +English | [中文](0001-acp-default-export-drops-inject.zh.md) + Status: resolved (fix in PR #41 `feat/acp-2-bridge`) ## Executive summary diff --git a/docs/postmortem/0001-acp-default-export-drops-inject.zh.md b/docs/postmortem/0001-acp-default-export-drops-inject.zh.md new file mode 100644 index 0000000000..763b2e6230 --- /dev/null +++ b/docs/postmortem/0001-acp-default-export-drops-inject.zh.md @@ -0,0 +1,113 @@ +# 事故复盘(postmortem) 0001:ACP(Agent Client Protocol)服务器在连接时崩溃——`export default` 丢弃了插件的 `inject` + +[English](0001-acp-default-export-drops-inject.md) | 中文 + +Status: resolved (fix in PR(Pull Request) #41 `feat/acp-2-bridge`) + +## 摘要 + +两个集成错误在单元测试全覆盖的情况下仍然导致 ACP 崩溃:一个 default export 使 Loader 丢弃了 `inject`,一个经 traceable 代理的可选服务查找在 shadow 边界上失败。手动挂载的测试绕过了这两条路径。修复方案增加了无需 API key 的真实 Loader 覆盖率,并为插件导出和可选服务访问制定了包(package)级规则。 + +## 概述 + +ACP 服务器(`examples/acp-agent`、`@deepseek-ai/dsh-acp`)在真实编辑器(Zed)连接的瞬间崩溃:第一个 `session/new` 请求返回 `Internal error: cannot get property "agents" without inject`,`session/load` 对 `sessionPersistence` 返回同样的错误。尽管有 178 个绿色单元测试和 100% 行覆盖率,bridge 在生产环境中完全无法工作。两个独立的 bug 隐藏在同一个错误字符串背后,测试套件之所以两个都没捕获,原因也相同:所有测试都通过一条不会触及插件真实加载方式和服务真实解析方式的路径来挂载插件。 + +## 影响 + +ACP 服务器无法创建或加载任何一个会话——而这正是编辑器最先调用的两个 RPC。任何将 agent(智能体)接入 Zed 的人都会立即遭遇硬性失败。无数据丢失(崩溃前没有任何内容被持久化);代价完全是「功能不可用」加上两次定位原因的调试时间。 + +## 时间线 + +- bridge(RFC 010)落地时附带完整的单元测试套件(codec、内存传输、基于属性的协议形状测试、失败路径、HMR(热模块替换))、一个需要 key 的真实 API e2e 测试,以及一个无需 key 的 stdout 纯净性 e2e 测试。全部绿色,100% 覆盖率。 +- 真实 Zed 会话在 `session/new` 上立即失败,报错 `cannot get property "agents" without inject`。 +- 调查最初追踪了一个 Cordis「traceable/shadow」理论(看似合理,且该机制确实存在——见 Bug #2),随后在 vendor 的 `reflect.ts` 中对实际 fiber 遍历做了插桩,并运行了真实子进程。trace 显示 throw 发生在 `apply()` 第 179 行、*插件加载时*,位于 ROOT fiber 且没有 shadow——推翻了 shadow 理论对 `session/new` 的解释。 +- 找到根因 #1:一行多余的 `export default apply`。删除后 `session/new` 修复。 +- 删除后暴露了 Bug #2:`session/load` 仍然在 `sessionPersistence` 上抛错——这是一个真正不同的机制(shadow 遍历),通过隔离修复并重新运行真实子进程得到确认。 + +## 根因 #1——`export default apply` 丢弃了插件的 `inject`(导致 `session/new` 崩溃) + +`packages/ui/acp/src/index.ts` 是一个*命名空间插件*:它将 `name`、`inject`、`Config` 和 `apply` 作为独立的命名导出——与仓库中其他所有插件(`invariants`、`llm-deepseek`、`tool-bash`、`tui` 等)形状相同。但它*还*多了一行其他插件都没有的代码: + +```ts ignore-check +export const name = 'acp' +export const inject = ['agents', 'sessions', 'sessionPersistence'] +export function apply(ctx: Context, config: AcpConfig): void { /* … */ } +// … +export default apply // ← the bug +``` + +当插件从 `cordis.yml` 加载时,Cordis Loader 通过 `Loader.unwrapExports`(`vendor/loader/src/index.ts`)对导入的模块进行规范化: + +```ts ignore-check +unwrapExports(exports: any) { + if (isNullable(exports)) return exports + exports = exports.default ?? exports // ← prefers `.default` + if (!exports.__esModule) return exports + return exports.default ?? exports +} +``` + +存在 default export 时,`exports.default ?? exports` 解析为**裸 `apply` 函数**。裸函数没有 `inject`、没有 `name`、没有 `Config` 属性——这些作为*兄弟*命名导出存在于模块命名空间上,而 unwrap 到 `.default` 把整个命名空间丢弃了。Loader 随后基于空的 `inject` 构建了插件的 fiber。 + +因此 `apply` 在一个**没有注入任何服务**的 fiber 中运行。第一行 `const agents = ctx.agents` 遍历 fiber 树(ROOT → Include → Loader → ROOT),在所有 fiber 的 store 中都找不到 `agents`,到达根 fiber(`runtime === null`)后抛出 `cannot get property "agents" without inject`。崩溃发生在*加载时*,而非后续的请求处理器中——请求只是恰好触发了加载。 + +**修复:** 删除 `export default apply`。Loader 随后使用模块命名空间,正确识别 `inject`/`name`/`Config`,`apply` 在一个真正授予了声明服务的 fiber 中运行。 + +## 根因 #2——可选服务读取通过 traceable shadow 触发 inject 守卫(导致 `session/load` 崩溃) + +修复 #1 后,`session/new` 正常工作,但 `session/load` 仍然抛出 `cannot get property "sessionPersistence" without inject`。这个问题*确实*是 Cordis 的 traceable/shadow 机制,值得精确理解。 + +`session/load` 调用 `agents.resume(...)`,后者委托给 `AgentLoop.resume()`,其中读取了 `this.ctx.sessionPersistence`。`AgentLoop` 的 `static inject` 故意不包含 `sessionPersistence`——注入它会导致非持久化的演示永远挂起,等待一个永远不会加载的后端。该服务由一个独立的兄弟插件/fiber 提供,以机会性方式读取。 + +Cordis 中的服务访问通过上下文代理(`vendor/cordis/src/reflect.ts`)进行。当通过从外部 fiber 获取的 *traceable 代理*调用服务方法时(此处:bridge fiber 调用 `ctx.agents.resume`,注册表返回 `this.factory`——即 `AgentLoop`——重新包装为绑定到调用方的新 traceable 代理),`createShadowMethod`(`vendor/cordis/src/utils.ts`)将 `this` 重新绑定到一个 *shadow* 对象,其 `ctx` 携带 `[symbols.shadow]` 指向 `AgentLoop` 自身的构造上下文。在 `resume` 内部,`this.ctx.sessionPersistence` 的解析从 shadow 的 fiber 开始遍历: + +```ts ignore-check +// reflect.ts get handler +let fiber = (ctx[symbols.shadow] as Context ?? ctx).fiber // ← starts at AgentLoop's fiber +while (true) { + const impl = fiber.store?.[prop] + if (impl) return getTraceable(ctx, impl.value) + if (prop in fiber.inject) { /* inactive-context error */ } + if (!fiber.runtime) throw error // ← reached root, throw + if (fiber.parent[symbols.isolate][prop] !== key) throw error + fiber = fiber.parent.fiber // ← ancestor-only +} +``` + +遍历**仅向祖先方向**进行。`sessionPersistence` 既不在 `AgentLoop` 的 fiber store 中(不在其 `static inject` 中),也不在通往 root 的任何祖先上(它位于一个*兄弟*分支),因此遍历到达根 fiber 后抛错。 + +为什么内存中的 `AgentLoop` 恢复测试没有捕获这个问题?因为它们从测试代码直接调用 `ctx.agents.resume(...)`——*在任何插件 fiber 之外*。此时 `ctx.fiber.runtime` 为 `null`,代理处理器走了一条提前绕过的路径: + +```ts ignore-check +if (!ctx.fiber.runtime) return ctx.reflect.get(prop, false) // ← direct global-store lookup, no fiber walk +``` + +`ctx.reflect.get(name, false)` 是基于 isolate symbol 的全局服务 store 直接查找——完全忽略 fiber 拓扑,能找到服务。因此从顶层测试读取可以成功;而从真实插件 fiber 内部、经由 shadow 到达时则抛错。bridge 恰好是后者。 + +**修复:** 使用 `ctx.get('sessionPersistence')` 读取可选服务,该方法使用全局 isolate-keyed store 同时保留活跃状态检查。对于插件声明注入集中的服务,直接属性读取仍然适用。 + +## 为什么所有测试都没有捕获(真正的失败) + +两个 bug 共享同一个流程缺口:**没有任何测试通过插件的真实加载路径或真实调用拓扑来驱动它。** + +- 内存 harness 通过手动构建插件对象来挂载 bridge:`ctx.plugin({ name, inject, apply })`。这手动提供了 `inject`,因此永远无法复现 Bug #1——`unwrapExports` 只被 *Loader* 调用,`ctx.plugin` 从不调用它。即使 `ctx.plugin(NamespaceImport)` 也无法捕获。 +- 同一个 harness 将所有内容平铺挂载在一个根上下文上,因此从中触达的 `AgentLoop` 恢复要么运行在顶层(`!runtime` 绕过),要么通过一个 origin 仍然解析在 root 上的 shadow——掩盖了 Bug #2 的祖先遍历失败。 +- 唯一的无 key e2e 发送 `initialize` 并检查 stdout 纯净性。`initialize` 从不触达 factory,因此两个 bug 都安然通过。 +- 唯一驱动 `session/new`/`session/load` 的测试需要 key 才能运行,因此 CI(无 key)跳过了它——而本地它之所以「通过」,只是因为一个陈旧的已构建 `lib/`(包含旧代码)恰好满足了模块解析。 + +100% 行覆盖率始终满足。覆盖率证明代码行*被执行过*;它不能说明功能是否*按交付方式正常工作*。 + +## 新增的防护措施 + +- **删除 `export default apply`**(`packages/ui/acp/src/index.ts`)——Bug #1 的修复。 +- **`AgentLoop.resume` 使用 `this.ctx.get('sessionPersistence')`**(`packages/core/agent-loop/src/index.ts`)——Bug #2 的修复,附注释说明 shadow 遍历陷阱。 +- **无需 key 的 `session/new` e2e,通过真实 stdio 运行**(`examples/acp-agent/tests/acp.e2e.ts`):以子进程方式通过真实 Loader 启动示例,并断言 `session/new` 正常返回。无需 API key 即可在 Bug #1 上大声失败。已验证恢复 `export default apply` 时测试失败。 +- **e2e spawn 中设置 `TSX_TSCONFIG_PATH`**:子进程从临时 cwd 运行,tsx 无法通过向上搜索找到仓库根的 tsconfig `paths` 映射——因此 dsh-* 的 import 静默回退到已构建的 `lib/`。将 tsx 指向仓库 tsconfig 使解析不依赖 cwd,确保测试运行的是*源码*而非可能陈旧的构建产物。 +- **[docs/testing.md](../testing.md) 规则**:「测试真实入口路径」,行覆盖率不等于行为覆盖率——将这一教训编纂为所有未来插件的规则。 + +## 经验教训 + +- 命名空间插件与 default export 在 Cordis Loader 下互斥。选择命名空间形式(`name`/`inject`/`Config`/`apply`),不要添加 `export default`——`unwrapExports` 会丢弃命名空间。 +- 对于插件机会性读取但未在 `static inject` 中声明的服务,使用 `ctx.get(name)`,绝不使用 `ctx.<name>`。属性代理通过仅向祖先方向的 fiber 遍历解析,经由外部 shadow 时会失败;`ctx.get(name)` 是拓扑无关的查找(且默认严格——非活跃后端读取为 `undefined`,而非在 teardown 过程中被交出)。 +- 手动构建插件的测试无法验证插件的加载方式。至少一个测试必须端到端地驱动真实的 Loader/export 路径。当核心操作不调用模型时,该测试无需 API key——因此它属于 CI,而非 key 门控之后。 +- 相信 trace,不要相信理论。优雅的 shadow 解释是真实的,但它是*第二个* bug;*第一个*是一行导出错误,在数小时看似合理但实际错误的推理之后,一个 fiber 遍历的 `console.error` 在几分钟内就找到了它。 diff --git a/docs/postmortem/0002-js-expression-disabled-filesystem-tools.i18n.yaml b/docs/postmortem/0002-js-expression-disabled-filesystem-tools.i18n.yaml new file mode 100644 index 0000000000..2aad7141c5 --- /dev/null +++ b/docs/postmortem/0002-js-expression-disabled-filesystem-tools.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +0002-js-expression-disabled-filesystem-tools.md: 30ff9d920821a8d55c4bea5f120f1aeeca6634b3 +0002-js-expression-disabled-filesystem-tools.zh.md: b103ec6de5d6d6406ba48ec34f6ebb479e472352 diff --git a/docs/postmortem/0002-js-expression-disabled-filesystem-tools.md b/docs/postmortem/0002-js-expression-disabled-filesystem-tools.md index ccdb725bfb..30ff9d9208 100644 --- a/docs/postmortem/0002-js-expression-disabled-filesystem-tools.md +++ b/docs/postmortem/0002-js-expression-disabled-filesystem-tools.md @@ -1,5 +1,7 @@ # Post-mortem 0002: Filesystem snapshot tools were permanently disabled +English | [中文](0002-js-expression-disabled-filesystem-tools.zh.md) + Status: resolved ## Executive summary diff --git a/docs/postmortem/0002-js-expression-disabled-filesystem-tools.zh.md b/docs/postmortem/0002-js-expression-disabled-filesystem-tools.zh.md new file mode 100644 index 0000000000..b103ec6de5 --- /dev/null +++ b/docs/postmortem/0002-js-expression-disabled-filesystem-tools.zh.md @@ -0,0 +1,47 @@ +# 事故复盘(postmortem) 0002:文件系统快照工具被永久禁用 + +[English](0002-js-expression-disabled-filesystem-tools.md) | 中文 + +Status: resolved + +## 摘要 + +ACP(Agent Client Protocol)示例试图通过 `disabled: !!js ...` 有条件地启用文件系统插件,但 Cordis 仅在插件 `config` 内部对 JavaScript 表达式求值。原始的表达式对象为 truthy,因此文件系统栈始终处于禁用状态。快照刷新随后将 `UNKNOWN_TOOL` 结果接受为新的预期输出。修复方案改用显式的文件系统 overlay,并增加了静态配置守卫和快照结果守卫。 + +## 概述 + +默认的 ACP 组合有意只启用 bash,因为其沙箱无法约束进程内的文件系统提供方。文件系统快照场景仍然需要 `read`、`write` 和 `edit`,因此这些插件被放在默认的 `cordis.yml` 中,并附带一个 `disabled` 表达式,意图仅在全权限启动和快照模式下启用它们。 + +Cordis Include 将每个 `!!js` 标量解析为一个表达式对象。Loader 递归地对插件的 `config` 进行插值,但直接消费 `disabled` 等入口元数据。因此每个文件系统入口看到的都是一个 truthy 对象,在所有模式下均保持禁用。 + +## 影响 + +七个文件系统场景和一个混合工作区编辑场景调用了注册表中不存在的工具。其结构化会话日志携带 `ToolNotFoundError`(code 为 `UNKNOWN_TOOL`),stdout 渲染出通用的失败工具卡片。快照套件通过了,因为结构化会话日志和 stdout 渲染出的通用失败工具卡片均与刷新后的 fixture(测试前置数据)匹配;它证明的是回归的确定性回放,而非文件系统行为的正确性。 + +实际运行的受限默认模式并未获得意外的文件系统访问权限。一个简单的插值修复反而会制造该风险:权限预设在运行时更新 bash 沙箱和审批状态,但无法挂载、卸载或约束文件系统栈。 + +## 时间线 + +- PR(Pull Request) #261 整合了 ACP 组合并刷新了文件系统快照,同时引入了条件式文件系统入口。 +- 所有单元测试、覆盖率、快照、文档、构建和 hygiene 检查均通过。 +- 对刷新后的文件系统预期输出的评审发现了通用的失败卡片和结构化的 `UNKNOWN_TOOL` 结果。 +- 一次真实的 Loader 启动确认:每个 `disabled` 值仍为表达式对象,每个文件系统 fiber 均未创建。 + +## 根因 + +实现时假设 `!!js` 适用于整个 Loader 入口。其实际边界更窄:`Entry._resolveConfig()` 仅对 `entry.options.config` 进行插值;`Entry.disabled` 直接测试 `entry.options.disabled`,不经过插值。YAML 标签在语法上合法,因此加载过程不产生任何诊断信息。 + +快照框架将任何确定性的 transcript(文本记录)视为有效行为。Header pin 验证了组合后的工具 schema,但文件系统场景共享来自默认组合的 pin,因此未独立证明其所需工具已注册。刷新在任何语义断言拒绝缺失工具之前,就已重写了预期的 stdout 和会话日志。 + +## 已添加的防护措施 + +- 文件系统场景启动 `fs.cordis.yml`:一个显式的固定全权限 overlay,配有对应的回放配置和独立的 request-header 类。 +- [`AGENTS.md`](../../AGENTS.md) 与 [Cordis 入门](../cordis-primer.md#loader-configuration)明确说明 `!!js` 仅在插件 `config` 内有效,条件式组合应使用 overlay。 +- `verify-cordis-config` 解析仓库中的 Cordis YAML,拒绝 Loader 入口元数据中的表达式节点(包括 include patch 和插入的入口)。 +- `dsh-acp-snapshot` 在新鲜运行和已提交的会话 fixture 中拒绝结构化的 `UNKNOWN_TOOL` 结果,防止其被提交为预期输出。 + +## 教训 + +- 语法上被接受的配置值不一定在该位置被求值;应记录并验证插值边界。 +- 快照刷新是 fixture 的生产过程,不是正确性审查。诸如已注册工具缺失这类语义上不可能的结果,需要独立于预期输出的断言。 +- 权限控制只应描述其实际管辖的能力。组合时的文件系统访问无法安全地跟随运行时的 bash-only 预设。 diff --git a/docs/postmortem/README.i18n.yaml b/docs/postmortem/README.i18n.yaml new file mode 100644 index 0000000000..e68d3a1a07 --- /dev/null +++ b/docs/postmortem/README.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +README.md: df0e2fcb8540aeed005153dbecc451d781ca5ff1 +README.zh.md: 2ce6de475c705b02cd9dabfb2181929d81478e2c diff --git a/docs/postmortem/README.md b/docs/postmortem/README.md index 7114f65916..df0e2fcb85 100644 --- a/docs/postmortem/README.md +++ b/docs/postmortem/README.md @@ -1,5 +1,7 @@ # Post-mortems +English | [中文](README.zh.md) + Incident write-ups: a bug reached a place it shouldn't have (a real user, a merged PR, a release), and the interesting part is *why our process let it through*, not just the one-line fix. A post-mortem is NOT an [Agent Note](../../.agents/notes/README.md) (which records a deliberate design decision and its rejected alternatives, or proposes future work). It is a backward-looking record of a failure: what broke, the mechanism, why every safety net missed it, and the concrete guardrails added so the same class of bug fails loudly next time. diff --git a/docs/postmortem/README.zh.md b/docs/postmortem/README.zh.md new file mode 100644 index 0000000000..2ce6de475c --- /dev/null +++ b/docs/postmortem/README.zh.md @@ -0,0 +1,16 @@ +# 事故复盘(postmortem) + +[English](README.md) | 中文 + +事故复盘:一个 bug 到达了它不该到达的地方(真实用户、已合并的 PR(Pull Request)、已发布的版本),值得关注的是*为什么我们的流程放过了它*,而不仅仅是那一行修复。 + +事故复盘不是 [Agent Note(agent 决策记录)](../../.agents/notes/README.md)(Agent Note 记录一个经过深思熟虑的设计决策及其被否决的替代方案,或提出未来工作)。它是一份回顾性的失败记录:什么坏了、机制是什么、为什么每道安全网都没拦住、以及加了哪些具体的防护措施使同类 bug 下次能被显式暴露。 + +当一个 bug 满足以下条件时,请撰写事故复盘:**隐蔽**(机制不显而易见,即使是细心的工程师也得费力重新推导)、**系统性**(逃逸的原因是测试/工具/约定的缺口,而非一次性的笔误)、**重新发现的代价高**(它消耗了真实的调试时间,且下次还会如此)。请链接该事故复盘所推动建立的防护措施(测试、AGENTS.md 规则、ADR)。 + +每篇事故复盘以一段**摘要**开头:一个简短段落,让忙碌的读者在三十秒内吸收要点——什么坏了、用直白的话说根因是什么、为什么逃逸了、持久的教训是什么——然后才是后续的详细「概述 / 时间线 / 根因 / 防护措施」各节。 + +| # | 标题 | +|---|---| +| [0001](0001-acp-default-export-drops-inject.md) | ACP(Agent Client Protocol)服务器在连接时崩溃:`export default` 丢失了插件的 `inject` | +| [0002](0002-js-expression-disabled-filesystem-tools.md) | 文件系统快照工具被一个字面量 `!!js` 对象永久禁用 | diff --git a/docs/testing.i18n.yaml b/docs/testing.i18n.yaml new file mode 100644 index 0000000000..8ebdff8c55 --- /dev/null +++ b/docs/testing.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +testing.md: fd38fb7b20d76ef48c81c86badcf501f7c0dbd4e +testing.zh.md: 4584492350aefd5d72692093b08c0dcd4910a8af diff --git a/docs/testing.md b/docs/testing.md index 78ce3c2856..bf202c2357 100644 --- a/docs/testing.md +++ b/docs/testing.md @@ -1,22 +1,24 @@ # Testing policy +English | [中文](testing.zh.md) + How this repo tests, tier by tier, and the rules that keep a green suite meaningful. Commands live in root [AGENTS.md](../AGENTS.md); linked Agent Notes carry the rationale. ## Tiers -- **Unit** (`pnpm run test`): vitest over `packages|examples/*/tests/**/*.spec.ts`, colocated with what they test. Every registry gets an HMR-safety test (dispose the contributing fiber, assert cleanup). Prefer edge cases, error paths, event ordering, concurrency races, and permanent contract regressions (see `packages/core/agent-loop/tests/contract-regressions.spec.ts`). +- **Unit** (`pnpm run test`): vitest over package and example specs under their `tests/**` directories plus repository script specs under `scripts/**/*.spec.ts`; tests stay with the code area they exercise. Every registry gets an HMR-safety test (dispose the contributing fiber, assert cleanup). Prefer edge cases, error paths, event ordering, concurrency races, and permanent contract regressions (see `packages/core/agent-loop/tests/contract-regressions.spec.ts`). - **Coverage gate** (`pnpm run test:coverage`): the gating run, per-file 100% on `packages/*/*/src`. An uncovered line is often dead code the gate is correctly flagging for deletion, not a missing test to bolt on. Line coverage is necessary, never sufficient — it proves lines ran, not that the feature works as shipped. - **Real-API e2e** (`pnpm run test:e2e`): with-key tests against live provider APIs — the DeepSeek model plus provider-specific smokes that gate on their own keys (`EXA_API_KEY`, `PERPLEXITY_API_KEY`, …); each suite self-skips without its key so keyless CI stays green ([real-API e2e Agent Note](../.agents/notes/implemented/testing/2026-06-19-real-api-e2e-ci.md)). -- **Snapshot** (`pnpm run test:snapshot`): transport-specific keyless expected outputs cover external presentation. ACP suites boot the real example subprocess, replay a recorded session, and diff normalized JSON-RPC plus the re-persisted log ([ACP snapshot Agent Note](../.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.md)); the headless suite independently pins `stream-json` through its real one-shot subprocess. TUI completed journeys replay recorded primary/child JSONL through the real agent loop and tools before projecting ANSI into semantic terminal-state expected outputs; package-local snapshots retain transient renderer states, and a real PTY conversation covers the process boundary ([TUI snapshot Agent Note](../.agents/notes/implemented/testing/2026-07-18-tui-terminal-state-snapshots.md)). Use `pnpm run test:snapshot:record` when a model transcript must change and `pnpm run test:snapshot:refresh` when committed replay input remains correct; review every JSONL and expected-output diff. System-prompt/tool-schema content is pinned by one ACP scenario (`text-turn`) and tokenized in every other fixture, so a prompt or schema edit churns one committed line ([pinned-header Agent Note](../.agents/notes/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md)). +- **Snapshot** (`pnpm run test:snapshot`): keyless expected outputs cover external presentation. ACP boots the real example, replays a recorded session, and diffs normalized JSON-RPC plus the re-persisted log ([ACP snapshot Agent Note](../.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.md)); headless pins `stream-json` through its real one-shot process. TUI journeys replay primary/child JSONL through the real loop and tools, then project ANSI into semantic terminal-state outputs; package snapshots retain transient states and a real PTY covers the process boundary ([TUI snapshot Agent Note](../.agents/notes/implemented/testing/2026-07-18-tui-terminal-state-snapshots.md)). Use `pnpm run test:snapshot:record` when a model transcript changes and `pnpm run test:snapshot:refresh` when replay input remains valid; review every JSONL and expected-output diff. One ACP scenario (`text-turn`) pins full system-prompt/tool-schema content; other fixtures tokenize it so an edit churns one line ([pinned-header Agent Note](../.agents/notes/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md)). - **Web browser snapshot** (gate-exempt `pnpm run test:web`): real chromium over the in-process web assembly replays recorded fixtures against conversation aria goldens (`apps/web/tests/snapshots/`); `DSH_SNAPSHOT=record`/`refresh` semantics and the deferred CI browser decision live in the [web e2e lane Agent Note](../.agents/notes/implemented/testing/2026-07-24-web-gui-browser-e2e-lane.md). ## The with-key policy: inference is cheap here -We are DeepSeek — do not ration real-API tests. A no-key test proves plumbing; only a with-key run proves the agent works against a real model. Write many: file-writing prompts, multi-turn conversations, tool use, cancellation mid-stream. Highest-value are **smoke tests** that boot the real example, send one real prompt, and check the world — they catch the "green unit tests, broken product" class that mocks structurally cannot ([postmortem 0001](postmortem/0001-acp-default-export-drops-inject.md)). The self-skip exists only so secretless CI and keyless contributors aren't blocked; it is not a cost signal. Every example ships both a keyless smoke and a with-key smoke ([examples/AGENTS.md](../examples/AGENTS.md)). +We are DeepSeek — do not ration real-API tests. A no-key test proves plumbing; only a with-key run proves the agent works against a real model. Cover file-writing prompts, multi-turn conversations, tool use, and mid-stream cancellation. Highest-value are **smoke tests** that boot the real example, send one prompt, and check the world — they catch the "green unit tests, broken product" class that mocks cannot ([postmortem 0001](postmortem/0001-acp-default-export-drops-inject.md)). Self-skip keeps secretless CI and keyless contributors unblocked; it is not a cost signal. Every example ships keyless and with-key smokes ([examples/AGENTS.md](../examples/AGENTS.md)). ## Prefer the real implementation over a mock -Mock only the genuinely expensive or non-deterministic boundary (the LLM adapter, the network, the clock); keep everything downstream real. A hand-rolled stand-in proves the bridge moves bytes, not that the shipping tool behaves as asserted — the two drift while the test stays green. Example: bridge tool-call tests run the scripted mock MODEL but the real tool + real executor (`makeBridgeHarness({ withBash: true })` plugs `dsh-bash-local` + `dsh-tool-bash` and runs an actual `echo`). +Mock only the expensive or non-deterministic boundary (LLM adapter, network, clock); keep everything downstream real. A hand-rolled stand-in proves the bridge moves bytes, not that the shipping tool behaves as asserted. Bridge tool-call tests use the scripted mock model with the real tool and executor: `makeBridgeHarness({ withBash: true })` plugs in `dsh-bash-local` and `dsh-tool-bash`, then runs `echo`. Recovery tests separate pre/post-chunk failures by step and prove failed chunks derive no message or tool side effect. Cover exhaustion, cancellation, policy composition, persistence, status, wire counts, transport-closing idle timeouts, and shipping Loader composition. diff --git a/docs/testing.zh.md b/docs/testing.zh.md new file mode 100644 index 0000000000..8b98f17c95 --- /dev/null +++ b/docs/testing.zh.md @@ -0,0 +1,47 @@ +# 测试策略 + +[English](testing.md) | 中文 + +本文说明本仓库的分层测试方式,以及保持绿色测试套件有意义的规则。命令见根目录 [AGENTS.md](../AGENTS.md);相关 Agent Note(agent 决策记录)承载设计动机。 + +## 层级 + +- **单元测试**(`pnpm run test`):vitest 运行包(package)和示例各自的 `tests/**` 目录下的测试,以及匹配 `scripts/**/*.spec.ts` 的仓库脚本测试;测试文件与其所覆盖的代码区域放在一起。每个注册表都有一个 HMR(热模块替换)安全测试(dispose(资源释放)贡献的 fiber,断言清理完成)。优先覆盖边界情况、错误路径、事件顺序、并发竞态,以及永久性契约回归(见 `packages/core/agent-loop/tests/contract-regressions.spec.ts`)。 +- **覆盖率门禁**(`pnpm run test:coverage`):门禁级运行,对 `packages/*/*/src` 按文件 100% 覆盖。未覆盖的行往往是门禁正确标记出的死代码(应删除),而非需要补写的测试。行覆盖率是必要条件,但永远不是充分条件:它证明行被执行过,不证明功能按交付预期工作。 +- **真实 API e2e**(`pnpm run test:e2e`):带密钥测试调用真实提供方 API,包括 DeepSeek 模型以及各提供方特有的冒烟测试;这些测试各自由自己的密钥控制(`EXA_API_KEY`、`PERPLEXITY_API_KEY` 等),缺少密钥时套件会自动跳过,使 keyless CI 保持绿色([真实 API e2e Agent Note](../.agents/notes/implemented/testing/2026-06-19-real-api-e2e-ci.md))。 +- **快照**(`pnpm run test:snapshot`):无密钥预期输出覆盖对外呈现。ACP 启动真实示例、回放录制会话,并对归一化 JSON-RPC 与重新持久化的日志执行 diff([ACP 快照 Agent Note](../.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.md));headless 通过真实单次运行进程固定 `stream-json`。TUI 旅程通过真实循环与工具回放主会话与子会话 JSONL,再将 ANSI 投影为语义化终端状态输出;包级快照保留瞬态状态,真实 PTY 覆盖进程边界([TUI 快照 Agent Note](../.agents/notes/implemented/testing/2026-07-18-tui-terminal-state-snapshots.md))。当模型 transcript(文本记录)发生变化时使用 `pnpm run test:snapshot:record`,回放输入仍然有效时使用 `pnpm run test:snapshot:refresh`;请审查每一处 JSONL 与预期输出差异。一个 ACP 场景(`text-turn`)固定完整的系统提示词与工具 schema 内容;其他 fixture(测试前置数据)将其 token 化,因此修改只会扰动一行([pinned-header Agent Note](../.agents/notes/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md))。 +- **Web 浏览器快照**(豁免门禁的 `pnpm run test:web`):真实 chromium 在进程内 web 组装之上回放已录制 fixture,与会话区 aria 预期输出比对(`apps/web/tests/snapshots/`);`DSH_SNAPSHOT=record`/`refresh` 的语义与暂缓的 CI 浏览器决策见 [web e2e 车道 Agent Note](../.agents/notes/implemented/testing/2026-07-24-web-gui-browser-e2e-lane.md)。 + +## 带密钥策略:推理在这里很便宜 + +我们是 DeepSeek,不要吝惜真实 API 测试。无密钥测试只能证明底层通路;只有带密钥运行才能证明 agent(智能体)能对接真实模型正常工作。覆盖文件写入提示词、包含多个轮次的对话、工具使用和流中取消。价值最高的是**冒烟测试**:启动真实示例、发送一条提示词,并检查外部世界;它们能捕获「单元测试全绿、产品却坏了」这一类 mock 无法发现的问题([事故复盘 0001](postmortem/0001-acp-default-export-drops-inject.md))。自动跳过让无密钥 CI 和无密钥贡献者不受阻塞;它不是成本信号。每个示例都提供无密钥和带密钥冒烟测试([examples/AGENTS.md](../examples/AGENTS.md))。 + +## 优先使用真实实现而非 mock + +只 mock 开销高或不确定的边界(LLM(大语言模型)适配器、网络、时钟);下游一切保持真实。手写替身只能证明桥接层在搬运字节,不能证明交付的工具行为符合断言。桥接工具调用测试将脚本化 mock 模型与真实工具和执行器配合使用:`makeBridgeHarness({ withBash: true })` 接入 `dsh-bash-local` 与 `dsh-tool-bash`,然后运行 `echo`。 + +恢复测试按步骤区分分片前与分片后的失败,并证明失败分片不会派生出消息或工具副作用。覆盖耗尽、取消、策略组合、持久化、状态、协议计数、会关闭传输的空闲超时,以及交付的 Loader 组合。 + +## 验证外部世界,而非自我报告 + +e2e 断言应重新运行命令或从外部重新读取文件;对 agent 自身输出做关键词探测会让作弊的 agent 通过。断言未修改的文件逐字节一致。e2e 测试自行管理资源:在测试中创建 harness,在 `afterEach` 中 dispose(即使失败/重试/超时也要释放);共享 fixture 放在普通的 `tests/harness.ts` 中,绝不放在另一个 `*.e2e.ts` 中(导入一个 spec 会重新注册其 `describe`,导致真实 API 调用重复执行)。 + +## 测试真实入口路径 + +- 产品可见的插件必须有一个非单元的真实组合测试。手动构建的 `ctx.plugin(...)` 套件不够:通过 Loader 和 app/process 启动仅用于测试的 `cordis.yml`,只 mock 外部/不确定边界,断言模型可见的请求/日志、持久状态或用户可见输出。不要把 opt-in 选项混入交付默认值。 +- 一个守卫只有在回归真的能让它失败时才有效。对于没有 `inject` 的插件(bundle/组合插件),Loader 冒烟测试在导出形状损坏时仍然绿着——需要添加显式的 `expect('default' in mod).toBe(false)` 加 `unwrapExports` 往返断言,并证明它有效:引入回归、观察变红、回退。 +- 「真实入口路径」指已发布的产物:包的 `bin` 所运行的是构建后的 `lib/bin.js`,并由普通 `node` 执行,从而暴露 tsx 会掩盖的失败(等待稳定时的竞态、模块解析、被吞掉的加载失败)。同样的规则适用于非 index 运行时入口(worker-thread 的同级文件 `lib/worker.cjs`),也适用于多个 bundle 共享的单例模块(`packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts`)。保持构建产物冒烟测试绿色(`packages/ui/*/tests/built-bin.e2e.ts`、`packages/code-runtime/code-runtime-worker/tests/built-lib.e2e.ts`),并断言真正缺失的配置以非零状态退出。 + +## 测试解析:仅限源码 + +- 每个 vitest 配置都将 vite-tsconfig-paths 指向 `tsconfig.base.json`;工作区包的裸导入解析到 `src`([布局](development.md#typescript-project-layout)),绝不会经由包的 `exports` 解析到构建后的 `lib/`,因为其中的陈旧产物会加载第二份模块单例。构建产物只在显式指定时使用:以 `lib` 模式运行的子进程,以及下文的构建产物冒烟测试。 + +## 测试子进程启动模式 + +- CI 与已有构建产物的测试通道通过共享双模式启动器,从构建后的 `lib/` 运行每个示例或 Cordis 配置子进程。不要为这些子进程手写 `--import tsx`。 +- 不加载 Cordis 的协议与操作系统 fixture 直接通过 Node 运行使用可擦除语法的 `.ts` 文件,不经过 tsx 或根路径映射。 +- 只有测试对象本身是源码路径解析时,才可以选择 `src`;在测试中写明这一契约。 + +## 何时需要快照测试 + +每项非平凡的模型可见或人类可见变更,都必须在同一 PR 中,通过可运行示例所属的快照套件添加或更新无密钥场景。包测试、e2e 断言、mock 与仅测试组合、PR 理由都不能取代组装后的 transcript;必要时应扩展 harness。ACP 接口使用 `examples/<name>/tests/snapshots/`,即基于 [`dsh-acp-snapshot`](../packages/support/acp-snapshot/README.md) 套件工厂的场景表(`examples/acp-agent` 为主套件);`examples/headless-agent` 拥有 `stream-json` 快照与回放 fixture。已完成的交互式终端旅程使用 `examples/tui-agent/tests/snapshots/` 下由 JSONL 驱动的场景;瞬态呈现使用包内语义矩阵,输入、Loader 选择或终端清理发生变化时还要添加 PTY 用例。新的能力 seam、生命周期形态或 transcript 呈现接口在计划阶段就要列出每个覆盖层级,并在实现前验证 harness 能够表达它们。 diff --git a/docs/tool-catalog.md b/docs/tool-catalog.md index 4f9de3644f..c10b0c90a7 100644 --- a/docs/tool-catalog.md +++ b/docs/tool-catalog.md @@ -23,12 +23,12 @@ This table connects model-visible tool names to the plugin package and service s | `@deepseek-ai/dsh-tool-fs` | `edit`, `read`, `write` | `ctx.tools`, `ctx.fs`, `ctx.systemPrompt` | `tool/call`, `fs/write-intent or fs/edit-intent for mutations`, `fs/observed after successful file operations`, `tool/result` | - | The read-before-write/edit policy is added by `@deepseek-ai/dsh-fs-policy` (an `fs/*` event-gate plugin, no schema change); a deployment that loads these tools is expected to also load it. The tool schemas above are identical with or without the policy plugin. | | `@deepseek-ai/dsh-tool-fs-search` | `glob`, `grep` | `ctx.tools`, `ctx.bash`, `ctx.systemPrompt` | `tool/call`, `tool/result` | - | glob and grep are conditional bash-backed discovery tools: they register only when ctx.bash can find `rg`, then run fixed ripgrep commands through ctx.bash as ordinary foreground calls (never background tasks). Capped results save the complete formatted list through the optional ctx.spillStore backend; returned locators are follow-up-readable/searchable when the backend exposes local paths in co-located deployments. | | `@deepseek-ai/dsh-tool-pty` | `terminal_close`, `terminal_list`, `terminal_open`, `terminal_read`, `terminal_send`, `terminal_signal` | `ctx.tools`, `ctx.pty`, `ctx.systemPrompt`, `ctx.tasks at call time for run_in_background` | `tool/call`, `tool/result` | - | The six terminal tools are opt-in and complement one-shot bash/filesystem tools. `terminal_send(run_in_background: true)` registers with `ctx.tasks`; TUI, named key sequences, BEL, resize, auto-start, and cross-agent sharing are absent from the schema. | -| `@deepseek-ai/dsh-tool-goal` | `create_goal`, `get_goal`, `update_goal` | `ctx.tools`, `ctx.agents`, `ctx.goals`, `ctx.systemPrompt`, `a calling Agent in an authorized open turn` | `tool/call`, `context/message goal snapshot for mutations`, `tool/result` | - | create, edit, pause, and resume require direct-human root authority; complete and blocked also accept the exact current goal round. The default blocked lower bound is three admitted rounds. | +| `@deepseek-ai/dsh-tool-goal` | `create_goal`, `get_goal`, `update_goal` | `ctx.tools`, `ctx.agents`, `ctx.goals`, `ctx.systemPrompt`, `a calling Agent in an authorized open turn` | `tool/call`, `user/message goal snapshot for mutations`, `tool/result` | - | create, edit, pause, and resume require direct-human root authority; complete and blocked also accept the exact current goal round. The default blocked lower bound is three admitted rounds. | | `@deepseek-ai/dsh-tool-lsp` | `lsp` | `ctx.tools`, `ctx.lsp`, `ctx.systemPrompt` | `tool/call`, `tool/result` | - | The lsp tool keeps provider selection and language-server subprocesses behind ctx.lsp, so its model-visible schema stays stable across providers. Requires a registered provider (e.g. `@deepseek-ai/dsh-lsp-local`) at runtime; without one, a query returns the structured `LSP_UNAVAILABLE` error rather than changing the schema. | | `@deepseek-ai/dsh-tool-ralph` | `ralph` | `ctx.tools`, `ctx.workflows`, `ctx.subagents`, `ctx.systemPrompt`, `a calling Agent (exec.agent parents every fresh round)` | `tool/call`, `tool/result`, `workflow and child session events during execution` | - | A fixed foreground workflow starts one fresh structured child per round; the model selects only the immutable objective and an optional round cap. | | `@deepseek-ai/dsh-tool-skill` | `skill` | `ctx.tools`, `ctx.skills` | `tool/call`, `tool/result` | - | - | | `@deepseek-ai/dsh-tool-subagent` | `subagent` | `ctx.tools`, `ctx.subagents` | `tool/call`, `tool/result`, `child session events through the chosen provider` | `subagent`, `subagent_fork` | The registered tool name is the load-time `toolName` config (default `subagent`); the schema above is that default. The shipped example agents load this package once per subagent backend, so the model additionally sees `subagent_fork` (bound to the fork backend) with an identical schema — see `examples/tui-agent/cordis.yml` and `examples/acp-agent/cordis.yml`. | -| `@deepseek-ai/dsh-tool-tasks` | `task_kill`, `task_list`, `task_output` | `ctx.tools`, `ctx.tasks`, `ctx.systemPrompt` | `tool/call`, `tool/result`, `context/message via agent.inject() for background completion notices` | - | The kind-agnostic background-task control surface: background bash commands, PTY sends, and subagents are read, listed, and killed through the same three tools. Loading the plugin attaches the control surface that arms producers' `ctx.tasks.start()`. | +| `@deepseek-ai/dsh-tool-tasks` | `task_kill`, `task_list`, `task_output` | `ctx.tools`, `ctx.tasks`, `ctx.systemPrompt` | `tool/call`, `tool/result`, `user/message via agent.inject() for background completion notices` | - | The kind-agnostic background-task control surface: background bash commands, PTY sends, and subagents are read, listed, and killed through the same three tools. Loading the plugin attaches the control surface that arms producers' `ctx.tasks.start()`. | | `@deepseek-ai/dsh-tool-todo` | `todo_write` | `ctx.tools`, `owning Agent session` | `tool/call`, `todo/write`, `tool/result` | - | todo_write is session-owned state; UIs render the latest todo/write event as a checklist or ACP plan. | | `@deepseek-ai/dsh-tool-workflow` | `workflow` | `ctx.tools`, `ctx.workflows`, `ctx.systemPrompt`, `a calling Agent (exec.agent parents the script children)` | `tool/call`, `tool/result` | - | - | | `@deepseek-ai/dsh-tool-web` | `web_fetch`, `web_search` | `ctx.tools`, `ctx.web`, `ctx.systemPrompt` | `tool/call`, `tool/result` | - | web_search and web_fetch keep provider selection behind ctx.web so model-visible schemas stay stable across backend swaps. | diff --git a/docs/tool-execution-pipeline.md b/docs/tool-execution-pipeline.md index 6904c31dd2..16a4461b6c 100644 --- a/docs/tool-execution-pipeline.md +++ b/docs/tool-execution-pipeline.md @@ -22,7 +22,7 @@ flowchart TD normalized["Registry outer normalization<br/>pipeline/result snapshot throws become isError"] finalize["ToolDefinition.finalizeContent<br/>last content-only invariant"] final["<code>tools/result</code> synchronous notification<br/>frozen authoritative outcome"] - context["Active-batch additionalContexts FIFO<br/>context/message after recorded tool results"] + context["Active-batch additionalContexts FIFO<br/>injected user/message after recorded tool results"] toolResult["Session event: <code>tool/result</code><br/>single model-facing outcome"] allResults["Tool batch settled<br/>recorded tool/result events complete"] presentResult["UI completed card<br/>presentResult(args, result)"] diff --git a/examples/acp-agent/tests/acp.snapshot.ts b/examples/acp-agent/tests/acp.snapshot.ts index e35d47cea0..7d014991ed 100644 --- a/examples/acp-agent/tests/acp.snapshot.ts +++ b/examples/acp-agent/tests/acp.snapshot.ts @@ -140,11 +140,11 @@ const SCENARIOS: Scenario[] = [ // Keyless, authored (like error-finish/cancel): deterministically forcing a // LIVE model to repeat one call three times is not a stable recording, so // the fixture scripts five identical todo_write calls and pins BOTH reminder - // tiers (gentle at 3, detailed at 5) as context/message in transcript and log. + // tiers (gentle at 3, detailed at 5) as injected user/message in transcript and log. { name: 'repeat-tool-guard', hasModelTurn: true, recorded: false }, // Authored replay: a root AGENTS.md pins the session prefix, then a read in // nested/ discovers its narrower AGENTS.md as a raw, metadata-bearing - // context/message. Both AGENTS.md fixtures are symlinks to a sibling + // injected user/message. Both AGENTS.md fixtures are symlinks to a sibling // AGENTS.canonical.md, so this scenario also guards that discovery follows a // symlinked instruction file to its target's content. The scenario-specific // config keeps home/root discovery hermetic, and the resulting prefix needs @@ -220,7 +220,7 @@ const SCENARIOS: Scenario[] = [ // tool/code-dispatch events. Each overlay composes and pins its own header class. { name: 'code-mode-turn', hasModelTurn: true, recorded: true, pinsHeader: true, headerClass: 'code', configPath: CODE_MODE_CONFIG }, // A nested fs dispatch inside run_code discovers workspace instructions. The - // context/message must follow the outer result while retaining workspace + // injected user/message must follow the outer result while retaining workspace // provenance, which proves Code Mode carries deferred tool context end to end. { name: 'code-mode-workspace-context', diff --git a/examples/acp-agent/tests/fixtures/live-mode-switching-2026-07-07.session.jsonl b/examples/acp-agent/tests/fixtures/live-mode-switching-2026-07-07.session.jsonl index 10ffb8c507..cb28e3c646 100644 --- a/examples/acp-agent/tests/fixtures/live-mode-switching-2026-07-07.session.jsonl +++ b/examples/acp-agent/tests/fixtures/live-mode-switching-2026-07-07.session.jsonl @@ -688,7 +688,7 @@ {"type":"turn/start","seq":686,"time":1783421455801,"data":{"turn":4,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"approval/policy","seq":687,"time":1783421455801,"data":{"policy":"never"}} {"type":"user/message","seq":688,"time":1783421455801,"data":{"content":[{"type":"text","text":"帮我创建一个 c.md"}],"source":{"kind":"user"}},"surfaceOp":"append"} -{"type":"context/message","seq":689,"time":1783421455802,"data":{"content":[{"type":"text","text":"The approval policy changed from \"ask\" to \"never\" (changed by the user)."}],"source":{"kind":"plugin","plugin":"approval"}},"surfaceOp":"append"} +{"type":"user/message","seq":689,"time":1783421455802,"data":{"content":[{"type":"text","text":"The approval policy changed from \"ask\" to \"never\" (changed by the user)."}],"source":{"kind":"plugin","plugin":"approval"}},"surfaceOp":"append"} {"type":"step/start","seq":690,"time":1783421455802,"data":{"turn":4,"step":1}} {"type":"request/header-delta","seq":691,"time":1783421455802,"data":{"system":{"keepStart":13,"keepEnd":0,"insert":["","Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation."]}}} {"type":"assistant/chunk","seq":692,"time":1783421456825,"data":{"turn":4,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} @@ -830,7 +830,7 @@ {"type":"turn/start","seq":828,"time":1783421478599,"data":{"turn":5,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"bash/sandbox-mode","seq":829,"time":1783421478599,"data":{"mode":"workspace-write"}} {"type":"user/message","seq":830,"time":1783421478599,"data":{"content":[{"type":"text","text":"帮我创建一个 d.md"}],"source":{"kind":"user"}},"surfaceOp":"append"} -{"type":"context/message","seq":831,"time":1783421478600,"data":{"content":[{"type":"text","text":"The bash sandbox mode changed from \"read-only\" to \"workspace-write\" (changed by the user)."}],"source":{"kind":"plugin","plugin":"tool-bash"}},"surfaceOp":"append"} +{"type":"user/message","seq":831,"time":1783421478600,"data":{"content":[{"type":"text","text":"The bash sandbox mode changed from \"read-only\" to \"workspace-write\" (changed by the user)."}],"source":{"kind":"plugin","plugin":"tool-bash"}},"surfaceOp":"append"} {"type":"step/start","seq":832,"time":1783421478600,"data":{"turn":5,"step":1}} {"type":"request/header-delta","seq":833,"time":1783421478600,"data":{"system":{"keepStart":12,"keepEnd":2,"insert":["Bash commands run under the \"workspace-write\" file sandbox."]}}} {"type":"assistant/chunk","seq":834,"time":1783421479489,"data":{"turn":5,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} @@ -1482,7 +1482,7 @@ {"type":"turn/start","seq":1480,"time":1783421524030,"data":{"turn":7,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"approval/policy","seq":1481,"time":1783421524030,"data":{"policy":"ask"}} {"type":"user/message","seq":1482,"time":1783421524030,"data":{"content":[{"type":"text","text":"帮我在 ~ 创建一个 f.md"}],"source":{"kind":"user"}},"surfaceOp":"append"} -{"type":"context/message","seq":1483,"time":1783421524030,"data":{"content":[{"type":"text","text":"The approval policy changed from \"never\" to \"ask\" (changed by the user)."}],"source":{"kind":"plugin","plugin":"approval"}},"surfaceOp":"append"} +{"type":"user/message","seq":1483,"time":1783421524030,"data":{"content":[{"type":"text","text":"The approval policy changed from \"never\" to \"ask\" (changed by the user)."}],"source":{"kind":"plugin","plugin":"approval"}},"surfaceOp":"append"} {"type":"step/start","seq":1484,"time":1783421524030,"data":{"turn":7,"step":1}} {"type":"request/header-delta","seq":1485,"time":1783421524030,"data":{"system":{"keepStart":13,"keepEnd":0,"insert":[]}}} {"type":"assistant/chunk","seq":1486,"time":1783421524940,"data":{"turn":7,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} @@ -1946,7 +1946,7 @@ {"type":"turn/start","seq":1944,"time":1783421552564,"data":{"turn":9,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"bash/sandbox-mode","seq":1945,"time":1783421552564,"data":{"mode":"danger-full-access"}} {"type":"user/message","seq":1946,"time":1783421552564,"data":{"content":[{"type":"text","text":"创建一个 h.md"}],"source":{"kind":"user"}},"surfaceOp":"append"} -{"type":"context/message","seq":1947,"time":1783421552564,"data":{"content":[{"type":"text","text":"The bash sandbox mode changed from \"workspace-write\" to \"danger-full-access\" (changed by the user)."}],"source":{"kind":"plugin","plugin":"tool-bash"}},"surfaceOp":"append"} +{"type":"user/message","seq":1947,"time":1783421552564,"data":{"content":[{"type":"text","text":"The bash sandbox mode changed from \"workspace-write\" to \"danger-full-access\" (changed by the user)."}],"source":{"kind":"plugin","plugin":"tool-bash"}},"surfaceOp":"append"} {"type":"step/start","seq":1948,"time":1783421552564,"data":{"turn":9,"step":1}} {"type":"request/header-delta","seq":1949,"time":1783421552564,"data":{"system":{"keepStart":12,"keepEnd":0,"insert":["Bash commands run under the \"danger-full-access\" file sandbox."]}}} {"type":"assistant/chunk","seq":1950,"time":1783421553289,"data":{"turn":9,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} diff --git a/examples/acp-agent/tests/goal-snapshots/goal-session/session.expected.jsonl b/examples/acp-agent/tests/goal-snapshots/goal-session/session.expected.jsonl index 8954fd6bad..d598b34e37 100644 --- a/examples/acp-agent/tests/goal-snapshots/goal-session/session.expected.jsonl +++ b/examples/acp-agent/tests/goal-snapshots/goal-session/session.expected.jsonl @@ -12,7 +12,7 @@ {"type":"assistant/message","seq":10,"time":0,"data":{"turn":1,"step":1,"content":[{"type":"tool-call","id":"call_goal_create","name":"create_goal","arguments":"{\"objective\":\"Finish the ACP goal-session snapshot proof\",\"max_goal_rounds\":2}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":20,"outputTokens":8}},"sourceEventSeqs":[5,6,7,8,9],"surfaceOp":"append"} {"type":"tool/call","seq":11,"time":0,"data":{"turn":1,"step":1,"callId":"call_goal_create","name":"create_goal","arguments":"{\"objective\":\"Finish the ACP goal-session snapshot proof\",\"max_goal_rounds\":2}"}} {"type":"tool/result","seq":12,"time":0,"data":{"turn":1,"step":1,"callId":"call_goal_create","content":[{"type":"text","text":"{\"goal\":{\"id\":\"goal-{{sessionId}}\",\"revision\":1,\"objective\":\"Finish the ACP goal-session snapshot proof\",\"phase\":\"active\",\"roundsStarted\":0,\"maxGoalRounds\":2},\"activation\":\"armed\"}"}],"isError":false},"sourceEventSeqs":[11],"surfaceOp":"append"} -{"type":"context/message","seq":13,"time":0,"data":{"content":[{"type":"text","text":"<goal_state>{\"goal\":{\"id\":\"goal-{{sessionId}}\",\"revision\":1,\"objective\":\"Finish the ACP goal-session snapshot proof\",\"phase\":\"active\",\"maxGoalRounds\":2},\"roundsStarted\":0,\"createdAt\":0,\"updatedAt\":0}</goal_state>"}],"source":{"kind":"goal","goalId":"goal-{{sessionId}}","revision":1,"round":0},"meta":{"kind":"goal/change","version":1,"operation":"create","goal":{"id":"goal-{{sessionId}}","revision":1,"objective":"Finish the ACP goal-session snapshot proof","phase":"active","maxGoalRounds":2},"roundsStarted":0,"createdAt":0,"updatedAt":0}},"surfaceOp":"append"} +{"type":"user/message","seq":13,"time":0,"data":{"content":[{"type":"text","text":"<goal_state>{\"goal\":{\"id\":\"goal-{{sessionId}}\",\"revision\":1,\"objective\":\"Finish the ACP goal-session snapshot proof\",\"phase\":\"active\",\"maxGoalRounds\":2},\"roundsStarted\":0,\"createdAt\":0,\"updatedAt\":0}</goal_state>"}],"source":{"kind":"goal","goalId":"goal-{{sessionId}}","revision":1,"round":0},"meta":{"kind":"goal/change","version":1,"operation":"create","goal":{"id":"goal-{{sessionId}}","revision":1,"objective":"Finish the ACP goal-session snapshot proof","phase":"active","maxGoalRounds":2},"roundsStarted":0,"createdAt":0,"updatedAt":0}},"surfaceOp":"append"} {"type":"step/end","seq":14,"time":0,"data":{"turn":1,"step":1}} {"type":"step/start","seq":15,"time":0,"data":{"turn":1,"step":2}} {"type":"assistant/chunk","seq":16,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}} @@ -49,6 +49,6 @@ {"type":"step/start","seq":47,"time":0,"data":{"turn":3,"step":1}} {"type":"assistant/chunk","seq":48,"time":0,"data":{"turn":3,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}} {"type":"assistant/chunk","seq":49,"time":0,"data":{"turn":3,"step":1,"chunk":{"type":"text-delta","index":0,"text":"partial"}}} -{"type":"context/message","seq":50,"time":0,"data":{"content":[{"type":"text","text":"<goal_state>{\"goal\":{\"id\":\"goal-{{sessionId}}\",\"revision\":2,\"objective\":\"Finish the ACP goal-session snapshot proof\",\"phase\":\"paused\",\"maxGoalRounds\":2},\"roundsStarted\":2,\"createdAt\":0,\"updatedAt\":0}</goal_state>"}],"source":{"kind":"goal","goalId":"goal-{{sessionId}}","revision":2,"round":0},"meta":{"kind":"goal/change","version":1,"operation":"pause","goal":{"id":"goal-{{sessionId}}","revision":2,"objective":"Finish the ACP goal-session snapshot proof","phase":"paused","maxGoalRounds":2},"roundsStarted":2,"createdAt":0,"updatedAt":0}},"surfaceOp":"append"} +{"type":"user/message","seq":50,"time":0,"data":{"content":[{"type":"text","text":"<goal_state>{\"goal\":{\"id\":\"goal-{{sessionId}}\",\"revision\":2,\"objective\":\"Finish the ACP goal-session snapshot proof\",\"phase\":\"paused\",\"maxGoalRounds\":2},\"roundsStarted\":2,\"createdAt\":0,\"updatedAt\":0}</goal_state>"}],"source":{"kind":"goal","goalId":"goal-{{sessionId}}","revision":2,"round":0},"meta":{"kind":"goal/change","version":1,"operation":"pause","goal":{"id":"goal-{{sessionId}}","revision":2,"objective":"Finish the ACP goal-session snapshot proof","phase":"paused","maxGoalRounds":2},"roundsStarted":2,"createdAt":0,"updatedAt":0}},"surfaceOp":"append"} {"type":"step/end","seq":51,"time":0,"data":{"turn":3,"step":1}} {"type":"turn/end","seq":52,"time":0,"data":{"turn":3,"reason":{"kind":"aborted"}}} diff --git a/examples/acp-agent/tests/goal.snapshot.ts b/examples/acp-agent/tests/goal.snapshot.ts index 4bb01acd16..23359f9982 100644 --- a/examples/acp-agent/tests/goal.snapshot.ts +++ b/examples/acp-agent/tests/goal.snapshot.ts @@ -83,6 +83,7 @@ describe('ACP same-session goal snapshot', () => { const calls = events.filter(event => event.type === 'tool/call').map(event => event.data.name) expect(calls).toEqual(['create_goal', 'get_goal']) const rounds = events.flatMap(event => event.type === 'user/message' && event.data.source.kind === 'goal' + && event.data.source.round > 0 ? [event.data.source.round] : []) expect(rounds).toEqual([1, 2]) diff --git a/examples/acp-agent/tests/snapshots/code-mode-workspace-context/session.jsonl b/examples/acp-agent/tests/snapshots/code-mode-workspace-context/session.jsonl index 88152d69cd..3f664e8e09 100644 --- a/examples/acp-agent/tests/snapshots/code-mode-workspace-context/session.jsonl +++ b/examples/acp-agent/tests/snapshots/code-mode-workspace-context/session.jsonl @@ -87,7 +87,7 @@ {"type":"tool/call","seq":85,"time":1783921767208,"data":{"turn":1,"step":1,"callId":"call_00_6APApmaKLRDlXKMdIcWL5139","name":"run_code","arguments":"{\"code\": \"const content = await tools.read({ file_path: \\\"nested/task.txt\\\" });\\nreturn content.lines.map(line => line.text).join(String.fromCharCode(10));\"}"}} {"type":"tool/code-dispatch","seq":86,"time":1783921767270,"data":{"parentCallId":"call_00_6APApmaKLRDlXKMdIcWL5139","subCallId":"call_00_6APApmaKLRDlXKMdIcWL5139:code:1","name":"read","arguments":{"file_path":"nested/task.txt"},"isError":false,"resultSummary":"<path>./nested/task.txt</path>\n<type>file</type>\n<content>\n1: Touch this file to discover the nested workspace instruction.\n\n(End of file - total 1 lines)\n</content>"}} {"type":"tool/result","seq":87,"time":1783921767271,"data":{"turn":1,"step":1,"callId":"call_00_6APApmaKLRDlXKMdIcWL5139","content":[{"type":"text","text":"Touch this file to discover the nested workspace instruction."}],"isError":false},"sourceEventSeqs":[85],"surfaceOp":"append"} -{"type":"context/message","seq":88,"time":1783921767272,"data":{"content":[{"type":"text","text":"<system-reminder>\nAdditional instructions from: nested/AGENTS.md\n\nThese instructions apply to work under `nested`. Use them as guidance when relevant; more specific instructions take precedence. They do not override system, developer, or direct user instructions.\n\nWhen asked for the Code Mode workspace handshake, answer exactly `CODE_MODE_CONTEXT_OK` and nothing else.\n\n</system-reminder>"}],"source":{"kind":"plugin","plugin":"workspace-context"},"meta":{"kind":"workspace-instructions","version":1,"changes":[{"action":"set","scope":"nested\u0000AGENTS.md","path":"nested/AGENTS.md","digest":"ae22936ed26dc76b7107005ed6d5e2482a88668a"}]}},"surfaceOp":"append"} +{"type":"user/message","seq":88,"time":1784811336862,"data":{"content":[{"type":"text","text":"<system-reminder>\nAdditional instructions from: nested/AGENTS.md\n\nThese instructions apply to work under `nested`. Use them as guidance when relevant; more specific instructions take precedence. They do not override system, developer, or direct user instructions.\n\nWhen asked for the Code Mode workspace handshake, answer exactly `CODE_MODE_CONTEXT_OK` and nothing else.\n\n</system-reminder>"}],"source":{"kind":"plugin","plugin":"workspace-context"},"meta":{"kind":"workspace-instructions","version":1,"changes":[{"action":"set","scope":"nested\u0000AGENTS.md","path":"nested/AGENTS.md","digest":"ae22936ed26dc76b7107005ed6d5e2482a88668a"}]}},"surfaceOp":"append"} {"type":"step/end","seq":89,"time":1783921767272,"data":{"turn":1,"step":1}} {"type":"step/start","seq":90,"time":1783921767272,"data":{"turn":1,"step":2}} {"type":"assistant/chunk","seq":91,"time":1783921768339,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} diff --git a/examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/session.jsonl b/examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/session.jsonl index de23b34e4b..487f0517b1 100644 --- a/examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/session.jsonl +++ b/examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/session.jsonl @@ -11,7 +11,7 @@ {"type":"assistant/chunk","seq":9,"time":1783951000009,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} {"type":"assistant/message","seq":10,"time":1784449176722,"data":{"turn":1,"step":1,"content":[{"type":"tool-call","id":"inspect-tools-api","name":"cordis_inspect","arguments":"{\"what\":\"api\",\"name\":\"tools\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[5,6,7,8,9],"surfaceOp":"append"} {"type":"tool/call","seq":11,"time":1784449176722,"data":{"turn":1,"step":1,"callId":"inspect-tools-api","name":"cordis_inspect","arguments":"{\"what\":\"api\",\"name\":\"tools\"}"}} -{"type":"tool/result","seq":12,"time":1784449176732,"data":{"turn":1,"step":1,"callId":"inspect-tools-api","content":[{"type":"text","text":"## api\n- tools — Tool registry and execution pipeline.\n /**\n * Register globally or in the calling agent scope. Scoped tools shadow\n * globals; duplicates within one layer and the reserved `run_code` name fail.\n * @param definition - tool schema, execution, and optional finalization/presentation callbacks.\n * @returns the exact disposer that unregisters the tool.\n */\n register(definition: ToolDefinition): () => void\n /**\n * Restrict global tools for the calling agent scope. Empty filters, unknown\n * names, scope-local names, and reserved transport names fail. Restrictions\n * intersect; scoped registrations remain visible.\n * @param filter - global-surface mask: `allow` (keep only) and/or `deny` (remove).\n * @returns the exact disposer that lifts this restriction.\n */\n restrict(filter: ToolRestriction): () => void\n /**\n * Register a monotonic guard after the extensible `tools/pre-execute`\n * waterfall. A plain-context guard applies globally; one registered through\n * `agent.ctx` applies only to that agent. Any matching guard may deny by\n * returning a reason, while no guard can force-allow a call another guard\n * denied. The exact effect disposer is returned for ordered ownership and\n * HMR cleanup.\n * @param guard - synchronous check; a returned string denies the execution.\n * @returns the exact disposer that unregisters the guard.\n */\n guard(guard: ToolGuard): () => void\n /**\n * Look up a tool as one scope sees it (scoped\n * shadows global; a restricted-away global reads as absent). Presenters pass\n * the calling agent so the rendered card matches the definition that\n * actually executed.\n * @param name - the tool name as registered.\n * @param scope - the viewing scope (the agent); omitted = the global view.\n * @returns the definition the scope resolves, or undefined when none is visible.\n */\n get(name: string, scope?: ScopeKey): ToolDefinition | undefined\n /**\n * Project visible definitions onto the allowlisted model-facing schema fields,\n * excluding execution and presentation callbacks.\n * @param scope - the viewing scope (the agent); omitted = the global view.\n * @returns one deep-cloned schema per visible tool.\n */\n schemas(scope?: ScopeKey): ToolSchema[]\n /**\n * Classify a pending call through the caller's visible tool definition. Only\n * an exact `true` is parallel; unknown, hidden, undeclared, invalid, or\n * throwing classifiers are exclusive.\n * @param exec - call name, parsed arguments, and optional agent scope.\n * @returns the fail-closed scheduling mode.\n */\n executionMode(exec: ToolExecutionInput): ToolExecutionMode\n /**\n * Execute through pre-policy, guards, around-dispatch, post-policy,\n * definition-owned content finalization, and final notification. Tool and\n * listener failures resolve as materialized error results; an invisible tool\n * reports `UNKNOWN_TOOL`. The returned outcome is the same lossless, frozen\n * snapshot final observers receive. Cancellation\n * arriving after entry and before final result materialization skips a\n * not-yet-started body with `ABORTED_BEFORE_DISPATCH` or replaces a\n * successful started outcome with `ABORTED`; already-started work is still\n * drained and may retain a tool-owned structured error.\n * @param exec - the typed same-process call input. The registry assigns its\n * correlation token before policy begins.\n * @returns the materialized final result.\n */\n async execute(exec: ToolExecutionInput): Promise<ToolExecutionResult>\ntype shapes (referenced by the signatures above — read these before assuming a field is a string):\n export interface Agent {\n readonly id: SessionId;\n readonly options: AgentOptions;\n readonly session: Session;\n readonly status: AgentStatus;\n readonly ctx: Context;\n send(content: ContentBlock[], options?: SendOptions): void;\n steer(content: ContentBlock[], options?: SendOptions): void;\n inject(content: ContentBlock[], options?: InjectOptions): void;\n cancel(cause?: AgentCancelCause): void;\n whenIdle(): Promise<void>;\n }\n export type AgentCancelCause = {\n readonly kind: 'user';\n } | {\n readonly kind: 'parent';\n };\n export interface AgentOptions {\n provider?: string;\n model?: string;\n }\n export type AgentStatus = 'idle' | 'running' | 'disposed';\n export type Branded<B extends string> = string & {\n readonly [BRAND]: B;\n };\n export type CallId = Branded<'CallId'>;\n export interface DiffCallView {\n card: 'diff';\n title: string;\n diffs: FileDiff[];\n locations?: FileLocation[];\n }\n export interface DiffResultView {\n card: 'diff';\n title?: string;\n diffs: FileDiff[];\n }\n export interface FileDiff {\n path: string;\n oldText: string | null;\n newText: string;\n }\n export interface FileLocation {\n path: string;\n line?: number;\n }\n export interface GenericCallView {\n card: 'generic';\n title: string;\n kind?: ToolCallKind;\n rawInput?: unknown;\n content?: ContentBlock[];\n locations?: FileLocation[];\n }\n export interface GenericResultView {\n card: 'generic';\n title?: string;\n content?: ContentBlock[];\n }\n export interface HookContext {\n content: ContentBlock[];\n source: MessageSource;\n placement?: 'separate' | 'prompt-prefix';\n meta?: JsonValue;\n }\n export interface InjectOptions extends Omit<SendOptions, 'contexts'> {\n meta?: JsonValue;\n }\n export interface JsonSchemaNode {\n type?: JsonSchemaType;\n oneOf?: JsonSchemaNode[];\n properties?: Record<string, JsonSchemaNode>;\n required?: string[];\n additionalProperties?: boolean;\n items?: JsonSchemaNode;\n enum?: JsonSchemaScalar[];\n const?: JsonSchemaScalar;\n description?: string;\n title?: string;\n default?: JsonValue;\n examples?: JsonValue;\n }\n export type JsonSchemaScalar = string | number | boolean | null;\n export type JsonSchemaType = 'object' | 'array' | 'string' | 'number' | 'integer' | 'boolean' | 'null';\n export type JsonValue = null | boolean | number | string | JsonValue[] | {\n [key: string]: JsonValue;\n };\n export type MessageSource = MessageSourceMap[keyof MessageSourceMap];\n export interface MessageSourceMap {\n user: {\n kind: 'user';\n };\n plugin: {\n kind: 'plugin';\n plugin: string;\n };\n }\n export type ScopeKey = object;\n export interface SendOptions {\n source?: MessageSource;\n contexts?: HookContext[];\n }\n export type SessionId = Branded<'SessionId'>;\n export interface TerminalCallView {\n card: 'terminal';\n title: string;\n description?: string;\n cwd?: string;\n }\n export interface TerminalResultView {\n card: 'terminal';\n title?: string;\n output?: string;\n exitCode?: number;\n signal?: string;\n }\n export type ToolCallKind = 'read' | 'edit' | 'delete' | 'move' | 'search' | 'execute' | 'fetch' | 'other';\n export type ToolCallView = GenericCallView | TerminalCallView | DiffCallView;\n export interface ToolDefinition extends ToolSchema {\n readonly output: ToolOutputDefinition;\n execute(args: unknown, exec: ToolRunContext): Promise<unknown>;\n finalizeContent?(exec: Readonly<ToolExecution>, result: Readonly<ToolExecutionResult>): ContentBlock[] | undefined;\n timeoutMs?: number;\n isConcurrencySafe?(args: unknown): boolean;\n presentCall?(args: unknown): ToolCallView | undefined;\n presentResult?(args: unknown, result: ToolResult): ToolResultView | undefined;\n }\n export interface ToolErrorInfo {\n name: string;\n code: string;\n }\n export interface ToolExecution extends ToolExecutionInput {\n readonly token: ToolExecutionToken;\n }\n export interface ToolExecutionFailure {\n readonly isError: true;\n readonly error: ToolFailure;\n readonly value?: never;\n readonly content: ContentBlock[];\n readonly meta?: JsonValue;\n readonly additionalContexts?: HookContext[];\n }\n export interface ToolExecutionInput {\n readonly callId: CallId;\n readonly name: string;\n readonly arguments: unknown;\n readonly agent?: Agent;\n readonly parent?: ToolExecutionToken;\n readonly signal: AbortSignal;\n }\n export type ToolExecutionMode = {\n kind: 'parallel';\n } | {\n kind: 'exclusive';\n };\n export type ToolExecutionResult = ToolExecutionSuccess | ToolExecutionFailure;\n export interface ToolExecutionSuccess {\n readonly isError: false;\n readonly value: JsonValue;\n readonly content: ContentBlock[];\n readonly error?: never;\n readonly meta?: JsonValue;\n readonly additionalContexts?: HookContext[];\n }\n export type ToolExecutionToken = symbol & {\n readonly [toolExecutionTokenBrand]: true;\n };\n export interface ToolFailure {\n message: string;\n info?: ToolErrorInfo;\n }\n export type ToolGuard = (execution: Readonly<ToolExecution>) => string | undefined;\n export interface ToolOutputDefinition {\n readonly schema: JsonSchemaNode;\n render(args: unknown, value: JsonValue): ContentBlock[];\n presentationMeta?(args: unknown, value: JsonValue): JsonValue;\n }\n export interface ToolRestriction {\n readonly allow?: readonly string[];\n readonly deny?: readonly string[];\n }\n export interface ToolResult {\n content: ContentBlock[];\n isError: boolean;\n meta?: JsonValue;\n }\n export type ToolResultView = GenericResultView | TerminalResultView | DiffResultView;\n export interface ToolRunContext extends ToolExecution {\n deferContext(context: HookContext): void;\n }\n export interface ToolSchema {\n name: string;\n description: string;\n parameters: Record<string, unknown>;\n }"}],"isError":false},"sourceEventSeqs":[11],"surfaceOp":"append"} +{"type":"tool/result","seq":12,"time":1784449176732,"data":{"turn":1,"step":1,"callId":"inspect-tools-api","content":[{"type":"text","text":"## api\n- tools — Tool registry and execution pipeline.\n /**\n * Register globally or in the calling agent scope. Scoped tools shadow\n * globals; duplicates within one layer and the reserved `run_code` name fail.\n * @param definition - tool schema, execution, and optional finalization/presentation callbacks.\n * @returns the exact disposer that unregisters the tool.\n */\n register(definition: ToolDefinition): () => void\n /**\n * Restrict global tools for the calling agent scope. Empty filters, unknown\n * names, scope-local names, and reserved transport names fail. Restrictions\n * intersect; scoped registrations remain visible.\n * @param filter - global-surface mask: `allow` (keep only) and/or `deny` (remove).\n * @returns the exact disposer that lifts this restriction.\n */\n restrict(filter: ToolRestriction): () => void\n /**\n * Register a monotonic guard after the extensible `tools/pre-execute`\n * waterfall. A plain-context guard applies globally; one registered through\n * `agent.ctx` applies only to that agent. Any matching guard may deny by\n * returning a reason, while no guard can force-allow a call another guard\n * denied. The exact effect disposer is returned for ordered ownership and\n * HMR cleanup.\n * @param guard - synchronous check; a returned string denies the execution.\n * @returns the exact disposer that unregisters the guard.\n */\n guard(guard: ToolGuard): () => void\n /**\n * Look up a tool as one scope sees it (scoped\n * shadows global; a restricted-away global reads as absent). Presenters pass\n * the calling agent so the rendered card matches the definition that\n * actually executed.\n * @param name - the tool name as registered.\n * @param scope - the viewing scope (the agent); omitted = the global view.\n * @returns the definition the scope resolves, or undefined when none is visible.\n */\n get(name: string, scope?: ScopeKey): ToolDefinition | undefined\n /**\n * Project visible definitions onto the allowlisted model-facing schema fields,\n * excluding execution and presentation callbacks.\n * @param scope - the viewing scope (the agent); omitted = the global view.\n * @returns one deep-cloned schema per visible tool.\n */\n schemas(scope?: ScopeKey): ToolSchema[]\n /**\n * Classify a pending call through the caller's visible tool definition. Only\n * an exact `true` is parallel; unknown, hidden, undeclared, invalid, or\n * throwing classifiers are exclusive.\n * @param exec - call name, parsed arguments, and optional agent scope.\n * @returns the fail-closed scheduling mode.\n */\n executionMode(exec: ToolExecutionInput): ToolExecutionMode\n /**\n * Execute through pre-policy, guards, around-dispatch, post-policy,\n * definition-owned content finalization, and final notification. Tool and\n * listener failures resolve as materialized error results; an invisible tool\n * reports `UNKNOWN_TOOL`. The returned outcome is the same lossless, frozen\n * snapshot final observers receive. Cancellation\n * arriving after entry and before final result materialization skips a\n * not-yet-started body with `ABORTED_BEFORE_DISPATCH` or replaces a\n * successful started outcome with `ABORTED`; already-started work is still\n * drained and may retain a tool-owned structured error.\n * @param exec - the typed same-process call input. The registry assigns its\n * correlation token before policy begins.\n * @returns the materialized final result.\n */\n async execute(exec: ToolExecutionInput): Promise<ToolExecutionResult>\ntype shapes (referenced by the signatures above — read these before assuming a field is a string):\n export interface Agent {\n readonly id: SessionId;\n readonly options: AgentOptions;\n readonly session: Session;\n readonly status: AgentStatus;\n readonly ctx: Context;\n followup(content: ContentBlock[], options?: SendOptions): AgentMessageId;\n queue(content: ContentBlock[], options?: SendOptions): AgentMessageId;\n steer(content: ContentBlock[], options?: SendOptions): AgentMessageId;\n inject(content: ContentBlock[], options?: InjectOptions): AgentMessageId;\n send(input: ResolvedAgentInput): AgentMessageId;\n cancel(cause?: AgentCancelCause, options?: CancelOptions): void;\n whenIdle(): Promise<void>;\n }\n export type AgentCancelCause = {\n readonly kind: 'user';\n } | {\n readonly kind: 'parent';\n };\n export type AgentMessageId = Branded<'AgentMessageId'>;\n export interface AgentOptions {\n provider?: string;\n model?: string;\n }\n export type AgentStatus = 'idle' | 'running' | 'disposed';\n export interface AssistantProvenance {\n provider: string;\n model: string;\n replayState?: unknown;\n }\n export type Branded<B extends string> = string & {\n readonly [BRAND]: B;\n };\n export type CallId = Branded<'CallId'>;\n export interface CancelOptions {\n keepInbox?: boolean;\n }\n export interface ContentBlockMap {\n 'text': TextBlock;\n 'reasoning': ReasoningBlock;\n 'tool-call': ToolCallBlock;\n 'tool-result': ToolResultBlock;\n }\n export type ContentBlockType = keyof ContentBlockMap;\n export interface DiffCallView {\n card: 'diff';\n title: string;\n diffs: FileDiff[];\n locations?: FileLocation[];\n }\n export interface DiffResultView {\n card: 'diff';\n title?: string;\n diffs: FileDiff[];\n }\n export interface EpochHeader {\n config: LlmCallConfig;\n system?: string;\n tools?: ToolSchema[];\n messagePrefix?: Message[];\n }\n export interface FileDiff {\n path: string;\n oldText: string | null;\n newText: string;\n }\n export interface FileLocation {\n path: string;\n line?: number;\n }\n export type FinishReason = FinishReasonMap[keyof FinishReasonMap];\n export interface FinishReasonMap {\n 'stop': {\n kind: 'stop';\n };\n 'tool-calls': {\n kind: 'tool-calls';\n };\n 'max-tokens': {\n kind: 'max-tokens';\n };\n 'aborted': {\n kind: 'aborted';\n failure: LlmFailure;\n };\n 'error': {\n kind: 'error';\n failure: LlmFailure;\n };\n }\n export interface GenericCallView {\n card: 'generic';\n title: string;\n kind?: ToolCallKind;\n rawInput?: unknown;\n content?: ContentBlock[];\n locations?: FileLocation[];\n }\n export interface GenericResultView {\n card: 'generic';\n title?: string;\n content?: ContentBlock[];\n }\n export interface HookContext {\n content: ContentBlock[];\n source: MessageSource;\n placement?: 'separate' | 'prompt-prefix';\n meta?: JsonValue;\n }\n export interface InjectOptions {\n source?: MessageSource;\n meta?: JsonValue;\n }\n export interface JsonSchemaNode {\n type?: JsonSchemaType;\n oneOf?: JsonSchemaNode[];\n properties?: Record<string, JsonSchemaNode>;\n required?: string[];\n additionalProperties?: boolean;\n items?: JsonSchemaNode;\n enum?: JsonSchemaScalar[];\n const?: JsonSchemaScalar;\n description?: string;\n title?: string;\n default?: JsonValue;\n examples?: JsonValue;\n }\n export type JsonSchemaScalar = string | number | boolean | null;\n export type JsonSchemaType = 'object' | 'array' | 'string' | 'number' | 'integer' | 'boolean' | 'null';\n export type JsonValue = null | boolean | number | string | JsonValue[] | {\n [key: string]: JsonValue;\n };\n export interface LlmCallConfig {\n provider: string;\n model: string;\n temperature?: number;\n maxTokens?: number;\n stop?: string[];\n }\n export interface LlmFailure {\n readonly message: string;\n readonly code: string;\n readonly status?: number;\n readonly providerRetryAfterMs?: number;\n readonly requestId?: ProviderRequestId;\n }\n export interface Message {\n role: 'system' | 'user' | 'assistant';\n content: ContentBlock[];\n provenance?: AssistantProvenance;\n }\n export type MessageSource = MessageSourceMap[keyof MessageSourceMap];\n export interface MessageSourceMap {\n user: {\n kind: 'user';\n };\n plugin: {\n kind: 'plugin';\n plugin: string;\n };\n }\n export interface PromptMessageData {\n content: ContentBlock[];\n source: MessageSource;\n envelope?: PromptMessageEnvelope;\n meta?: JsonValue;\n }\n export interface PromptMessageEnvelope {\n displayContent: ContentBlock[];\n prefixContexts: PromptPrefixContext[];\n }\n export interface PromptPrefixContext {\n source: MessageSource;\n meta?: JsonValue;\n }\n export type ProviderRequestId = Branded<'ProviderRequestId'>;\n export interface ReasoningBlock {\n type: 'reasoning';\n text: string;\n }\n export type RequestHeaderReason = 'initial' | 'resume' | 'change';\n export type ResolvedAgentInput = {\n content: ContentBlock[];\n source: MessageSource;\n meta: JsonValue | undefined;\n } & ({\n target: 'next-turn';\n wakeup: boolean;\n contexts: HookContext[];\n } | {\n target: 'next-step';\n wakeup: true;\n contexts: HookContext[];\n } | {\n target: 'next-step';\n wakeup: false;\n contexts: [\n ];\n });\n export type ScopeKey = object;\n export interface SendOptions {\n source?: MessageSource;\n contexts?: HookContext[];\n meta?: JsonValue;\n }\n export class Session {\n get surface(): SessionSurface;\n readonly header: SessionHeader;\n get id(): SessionId;\n constructor(id: SessionId, seed?: readonly SessionEvent[], header?: SessionHeader);\n get events(): readonly SessionEvent[];\n get seq(): number;\n append<T extends SessionEventType>(type: T, data: SessionEventMap[T], ...opts: T extends SurfaceEventType ? [\n opts: SurfaceIntent\n ] : [\n ]): SessionEvent<T>;\n requestHeader(): EpochHeader | undefined;\n deriveMessages(): Message[];\n deriveEventMessage(event: SessionEvent): Message | null;\n }\n export type SessionEvent<T extends SessionEventType = SessionEventType> = {\n [K in SessionEventType]: {\n type: K;\n seq: number;\n time: number;\n data: SessionEventMap[K];\n } & (K extends SurfaceEventType ? {\n sourceEventSeqs?: number[];\n surfaceOp?: SurfaceOp;\n } : object);\n }[T];\n export interface SessionEventMap {\n 'turn/start': {\n turn: number;\n trigger: TurnTrigger;\n };\n 'turn/end': {\n turn: number;\n reason: TurnEndReason;\n };\n 'step/start': {\n turn: number;\n step: number;\n };\n 'step/end': {\n turn: number;\n step: number;\n };\n 'user/message': PromptMessageData;\n 'prompt/blocked': {\n content: ContentBlock[];\n source: MessageSource;\n reason: string;\n };\n 'assistant/chunk': {\n turn: number;\n step: number;\n chunk: StreamChunk;\n };\n 'assistant/message': {\n turn: number;\n step: number;\n content: ContentBlock[];\n provenance: AssistantProvenance;\n usage?: TokenUsage;\n };\n 'tool/call': {\n turn: number;\n step: number;\n callId: CallId;\n name: string;\n arguments: string;\n };\n 'tool/result': {\n turn: number;\n step: number;\n callId: CallId;\n content: ContentBlock[];\n isError: boolean;\n error?: {\n name: string;\n code: string;\n };\n meta?: JsonValue;\n };\n 'steering/message': PromptMessageData & {\n turn: number;\n };\n 'todo/write': {\n todos: TodoItem[];\n };\n 'request/header': {\n header: EpochHeader;\n reason: RequestHeaderReason;\n };\n }\n export type SessionEventType = keyof SessionEventMap;\n export interface SessionHeader {\n readonly version: number;\n readonly id: SessionId;\n readonly createdAt: number;\n readonly cwd?: string;\n readonly parentSession?: SessionId;\n readonly seedLength?: number;\n readonly delegationDepth?: number;\n }\n export type SessionId = Branded<'SessionId'>;\n export interface SessionSurface {\n readonly nodes: readonly number[];\n readonly replaceGeneration: number;\n }\n export type StreamChunk = {\n type: 'block-start';\n index: number;\n blockType: ContentBlockType;\n } | {\n type: 'text-delta';\n index: number;\n text: string;\n } | {\n type: 'reasoning-delta';\n index: number;\n text: string;\n } | {\n type: 'tool-call-delta';\n index: number;\n id: CallId;\n name?: string;\n argumentsDelta: string;\n } | {\n type: 'block-end';\n index: number;\n block: ContentBlock;\n } | {\n type: 'usage';\n usage: TokenUsage;\n } | {\n type: 'finish';\n reason: FinishReason;\n replayState?: unknown;\n };\n export type SurfaceEventType = 'user/message' | 'assistant/message' | 'tool/result' | 'steering/message';\n export interface SurfaceIntent {\n surfaceOp: SurfaceOp;\n sourceEventSeqs?: number[];\n }\n export type SurfaceOp = 'append' | {\n op: 'replace';\n start: number;\n end: number;\n };\n export interface TerminalCallView {\n card: 'terminal';\n title: string;\n description?: string;\n cwd?: string;\n }\n export interface TerminalResultView {\n card: 'terminal';\n title?: string;\n output?: string;\n exitCode?: number;\n signal?: string;\n }\n export interface TodoItem {\n content: string;\n status: 'pending' | 'in_progress' | 'completed';\n }\n export interface TokenUsage {\n inputTokens: number;\n outputTokens: number;\n cacheReadTokens?: number;\n cacheWriteTokens?: number;\n reasoningTokens?: number;\n }\n export interface ToolCallBlock {\n type: 'tool-call';\n id: CallId;\n name: string;\n arguments: string;\n }\n export type ToolCallKind = 'read' | 'edit' | 'delete' | 'move' | 'search' | 'execute' | 'fetch' | 'other';\n export type ToolCallView = GenericCallView | TerminalCallView | DiffCallView;\n export interface ToolDefinition extends ToolSchema {\n readonly output: ToolOutputDefinition;\n execute(args: unknown, exec: ToolRunContext): Promise<unknown>;\n finalizeContent?(exec: Readonly<ToolExecution>, result: Readonly<ToolExecutionResult>): ContentBlock[] | undefined;\n timeoutMs?: number;\n isConcurrencySafe?(args: unknown): boolean;\n presentCall?(args: unknown): ToolCallView | undefined;\n presentResult?(args: unknown, result: ToolResult): ToolResultView | undefined;\n }\n export interface ToolErrorInfo {\n name: string;\n code: string;\n }\n export interface ToolExecution extends ToolExecutionInput {\n readonly token: ToolExecutionToken;\n }\n export interface ToolExecutionFailure {\n readonly isError: true;\n readonly error: ToolFailure;\n readonly value?: never;\n readonly content: ContentBlock[];\n readonly meta?: JsonValue;\n readonly additionalContexts?: HookContext[];\n }\n export interface ToolExecutionInput {\n readonly callId: CallId;\n readonly name: string;\n readonly arguments: unknown;\n readonly agent?: Agent;\n readonly parent?: ToolExecutionToken;\n readonly signal: AbortSignal;\n }\n export type ToolExecutionMode = {\n kind: 'parallel';\n } | {\n kind: 'exclusive';\n };\n export type ToolExecutionResult = ToolExecutionSuccess | ToolExecutionFailure;\n export interface ToolExecutionSuccess {\n readonly isError: false;\n readonly value: JsonValue;\n readonly content: ContentBlock[];\n readonly error?: never;\n readonly meta?: JsonValue;\n readonly additionalContexts?: HookContext[];\n }\n export type ToolExecutionToken = symbol & {\n readonly [toolExecutionTokenBrand]: true;\n };\n export interface ToolFailure {\n message: string;\n info?: ToolErrorInfo;\n }\n export type ToolGuard = (execution: Readonly<ToolExecution>) => string | undefined;\n export interface ToolOutputDefinition {\n readonly schema: JsonSchemaNode;\n render(args: unknown, value: JsonValue): ContentBlock[];\n presentationMeta?(args: unknown, value: JsonValue): JsonValue;\n }\n export interface ToolRestriction {\n readonly allow?: readonly string[];\n readonly deny?: readonly string[];\n }\n export interface ToolResult {\n content: ContentBlock[];\n isError: boolean;\n meta?: JsonValue;\n }\n export interface ToolResultBlock {\n type: 'tool-result';\n toolCallId: CallId;\n content: ContentBlock[];\n isError?: boolean;\n }\n export type ToolResultView = GenericResultView | TerminalResultView | DiffResultView;\n export interface ToolRunContext extends ToolExecution {\n deferContext(context: HookContext): void;\n }\n export interface ToolSchema {\n name: string;\n description: string;\n parameters: Record<string, unknown>;\n }\n export type TurnEndReason = TurnEndReasonMap[keyof TurnEndReasonMap];\n export interface TurnEndReasonMap {\n completed: {\n kind: 'completed';\n };\n aborted: {\n kind: 'aborted';\n };\n error: {\n kind: 'error';\n step: number;\n } & ({\n failure: LlmFailure;\n message?: never;\n code?: never;\n } | {\n message: string;\n code?: string;\n failure?: never;\n });\n disposed: {\n kind: 'disposed';\n };\n 'max-tokens': {\n kind: 'max-tokens';\n };\n rejected: {\n kind: 'rejected';\n reason: string;\n };\n interrupted: {\n kind: 'interrupted';\n };\n }\n export type TurnTrigger = TurnTriggerMap[keyof TurnTriggerMap];\n export interface TurnTriggerMap {\n message: {\n kind: 'message';\n source: MessageSource;\n };\n injection: {\n kind: 'injection';\n source: MessageSource;\n };\n }"}],"isError":false},"sourceEventSeqs":[11],"surfaceOp":"append"} {"type":"step/end","seq":13,"time":1784449176732,"data":{"turn":1,"step":1}} {"type":"step/start","seq":14,"time":1784449176733,"data":{"turn":1,"step":2}} {"type":"assistant/chunk","seq":15,"time":1783951000015,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}} diff --git a/examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/stdout.expected.jsonl index 723a7c077d..56cc640977 100644 --- a/examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/stdout.expected.jsonl +++ b/examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/stdout.expected.jsonl @@ -3,7 +3,7 @@ {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[{"name":"goal","description":"set or view the goal for a long-running task","input":{"hint":"[<objective>|clear|edit <objective>|pause|resume]"}},{"name":"plan","description":"Enter or leave plan mode","input":{"hint":"[off|message]"}}]}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"session_info_update","title":"Inspect the exact tools service","updatedAt":"{{updatedAt}}"}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"inspect-tools-api","title":"Inspect cordis runtime: api: tools","kind":"read","status":"in_progress"}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"inspect-tools-api","status":"completed","content":[{"type":"content","content":{"type":"text","text":"## api\n- tools — Tool registry and execution pipeline.\n /**\n * Register globally or in the calling agent scope. Scoped tools shadow\n * globals; duplicates within one layer and the reserved `run_code` name fail.\n * @param definition - tool schema, execution, and optional finalization/presentation callbacks.\n * @returns the exact disposer that unregisters the tool.\n */\n register(definition: ToolDefinition): () => void\n /**\n * Restrict global tools for the calling agent scope. Empty filters, unknown\n * names, scope-local names, and reserved transport names fail. Restrictions\n * intersect; scoped registrations remain visible.\n * @param filter - global-surface mask: `allow` (keep only) and/or `deny` (remove).\n * @returns the exact disposer that lifts this restriction.\n */\n restrict(filter: ToolRestriction): () => void\n /**\n * Register a monotonic guard after the extensible `tools/pre-execute`\n * waterfall. A plain-context guard applies globally; one registered through\n * `agent.ctx` applies only to that agent. Any matching guard may deny by\n * returning a reason, while no guard can force-allow a call another guard\n * denied. The exact effect disposer is returned for ordered ownership and\n * HMR cleanup.\n * @param guard - synchronous check; a returned string denies the execution.\n * @returns the exact disposer that unregisters the guard.\n */\n guard(guard: ToolGuard): () => void\n /**\n * Look up a tool as one scope sees it (scoped\n * shadows global; a restricted-away global reads as absent). Presenters pass\n * the calling agent so the rendered card matches the definition that\n * actually executed.\n * @param name - the tool name as registered.\n * @param scope - the viewing scope (the agent); omitted = the global view.\n * @returns the definition the scope resolves, or undefined when none is visible.\n */\n get(name: string, scope?: ScopeKey): ToolDefinition | undefined\n /**\n * Project visible definitions onto the allowlisted model-facing schema fields,\n * excluding execution and presentation callbacks.\n * @param scope - the viewing scope (the agent); omitted = the global view.\n * @returns one deep-cloned schema per visible tool.\n */\n schemas(scope?: ScopeKey): ToolSchema[]\n /**\n * Classify a pending call through the caller's visible tool definition. Only\n * an exact `true` is parallel; unknown, hidden, undeclared, invalid, or\n * throwing classifiers are exclusive.\n * @param exec - call name, parsed arguments, and optional agent scope.\n * @returns the fail-closed scheduling mode.\n */\n executionMode(exec: ToolExecutionInput): ToolExecutionMode\n /**\n * Execute through pre-policy, guards, around-dispatch, post-policy,\n * definition-owned content finalization, and final notification. Tool and\n * listener failures resolve as materialized error results; an invisible tool\n * reports `UNKNOWN_TOOL`. The returned outcome is the same lossless, frozen\n * snapshot final observers receive. Cancellation\n * arriving after entry and before final result materialization skips a\n * not-yet-started body with `ABORTED_BEFORE_DISPATCH` or replaces a\n * successful started outcome with `ABORTED`; already-started work is still\n * drained and may retain a tool-owned structured error.\n * @param exec - the typed same-process call input. The registry assigns its\n * correlation token before policy begins.\n * @returns the materialized final result.\n */\n async execute(exec: ToolExecutionInput): Promise<ToolExecutionResult>\ntype shapes (referenced by the signatures above — read these before assuming a field is a string):\n export interface Agent {\n readonly id: SessionId;\n readonly options: AgentOptions;\n readonly session: Session;\n readonly status: AgentStatus;\n readonly ctx: Context;\n send(content: ContentBlock[], options?: SendOptions): void;\n steer(content: ContentBlock[], options?: SendOptions): void;\n inject(content: ContentBlock[], options?: InjectOptions): void;\n cancel(cause?: AgentCancelCause): void;\n whenIdle(): Promise<void>;\n }\n export type AgentCancelCause = {\n readonly kind: 'user';\n } | {\n readonly kind: 'parent';\n };\n export interface AgentOptions {\n provider?: string;\n model?: string;\n }\n export type AgentStatus = 'idle' | 'running' | 'disposed';\n export type Branded<B extends string> = string & {\n readonly [BRAND]: B;\n };\n export type CallId = Branded<'CallId'>;\n export interface DiffCallView {\n card: 'diff';\n title: string;\n diffs: FileDiff[];\n locations?: FileLocation[];\n }\n export interface DiffResultView {\n card: 'diff';\n title?: string;\n diffs: FileDiff[];\n }\n export interface FileDiff {\n path: string;\n oldText: string | null;\n newText: string;\n }\n export interface FileLocation {\n path: string;\n line?: number;\n }\n export interface GenericCallView {\n card: 'generic';\n title: string;\n kind?: ToolCallKind;\n rawInput?: unknown;\n content?: ContentBlock[];\n locations?: FileLocation[];\n }\n export interface GenericResultView {\n card: 'generic';\n title?: string;\n content?: ContentBlock[];\n }\n export interface HookContext {\n content: ContentBlock[];\n source: MessageSource;\n placement?: 'separate' | 'prompt-prefix';\n meta?: JsonValue;\n }\n export interface InjectOptions extends Omit<SendOptions, 'contexts'> {\n meta?: JsonValue;\n }\n export interface JsonSchemaNode {\n type?: JsonSchemaType;\n oneOf?: JsonSchemaNode[];\n properties?: Record<string, JsonSchemaNode>;\n required?: string[];\n additionalProperties?: boolean;\n items?: JsonSchemaNode;\n enum?: JsonSchemaScalar[];\n const?: JsonSchemaScalar;\n description?: string;\n title?: string;\n default?: JsonValue;\n examples?: JsonValue;\n }\n export type JsonSchemaScalar = string | number | boolean | null;\n export type JsonSchemaType = 'object' | 'array' | 'string' | 'number' | 'integer' | 'boolean' | 'null';\n export type JsonValue = null | boolean | number | string | JsonValue[] | {\n [key: string]: JsonValue;\n };\n export type MessageSource = MessageSourceMap[keyof MessageSourceMap];\n export interface MessageSourceMap {\n user: {\n kind: 'user';\n };\n plugin: {\n kind: 'plugin';\n plugin: string;\n };\n }\n export type ScopeKey = object;\n export interface SendOptions {\n source?: MessageSource;\n contexts?: HookContext[];\n }\n export type SessionId = Branded<'SessionId'>;\n export interface TerminalCallView {\n card: 'terminal';\n title: string;\n description?: string;\n cwd?: string;\n }\n export interface TerminalResultView {\n card: 'terminal';\n title?: string;\n output?: string;\n exitCode?: number;\n signal?: string;\n }\n export type ToolCallKind = 'read' | 'edit' | 'delete' | 'move' | 'search' | 'execute' | 'fetch' | 'other';\n export type ToolCallView = GenericCallView | TerminalCallView | DiffCallView;\n export interface ToolDefinition extends ToolSchema {\n readonly output: ToolOutputDefinition;\n execute(args: unknown, exec: ToolRunContext): Promise<unknown>;\n finalizeContent?(exec: Readonly<ToolExecution>, result: Readonly<ToolExecutionResult>): ContentBlock[] | undefined;\n timeoutMs?: number;\n isConcurrencySafe?(args: unknown): boolean;\n presentCall?(args: unknown): ToolCallView | undefined;\n presentResult?(args: unknown, result: ToolResult): ToolResultView | undefined;\n }\n export interface ToolErrorInfo {\n name: string;\n code: string;\n }\n export interface ToolExecution extends ToolExecutionInput {\n readonly token: ToolExecutionToken;\n }\n export interface ToolExecutionFailure {\n readonly isError: true;\n readonly error: ToolFailure;\n readonly value?: never;\n readonly content: ContentBlock[];\n readonly meta?: JsonValue;\n readonly additionalContexts?: HookContext[];\n }\n export interface ToolExecutionInput {\n readonly callId: CallId;\n readonly name: string;\n readonly arguments: unknown;\n readonly agent?: Agent;\n readonly parent?: ToolExecutionToken;\n readonly signal: AbortSignal;\n }\n export type ToolExecutionMode = {\n kind: 'parallel';\n } | {\n kind: 'exclusive';\n };\n export type ToolExecutionResult = ToolExecutionSuccess | ToolExecutionFailure;\n export interface ToolExecutionSuccess {\n readonly isError: false;\n readonly value: JsonValue;\n readonly content: ContentBlock[];\n readonly error?: never;\n readonly meta?: JsonValue;\n readonly additionalContexts?: HookContext[];\n }\n export type ToolExecutionToken = symbol & {\n readonly [toolExecutionTokenBrand]: true;\n };\n export interface ToolFailure {\n message: string;\n info?: ToolErrorInfo;\n }\n export type ToolGuard = (execution: Readonly<ToolExecution>) => string | undefined;\n export interface ToolOutputDefinition {\n readonly schema: JsonSchemaNode;\n render(args: unknown, value: JsonValue): ContentBlock[];\n presentationMeta?(args: unknown, value: JsonValue): JsonValue;\n }\n export interface ToolRestriction {\n readonly allow?: readonly string[];\n readonly deny?: readonly string[];\n }\n export interface ToolResult {\n content: ContentBlock[];\n isError: boolean;\n meta?: JsonValue;\n }\n export type ToolResultView = GenericResultView | TerminalResultView | DiffResultView;\n export interface ToolRunContext extends ToolExecution {\n deferContext(context: HookContext): void;\n }\n export interface ToolSchema {\n name: string;\n description: string;\n parameters: Record<string, unknown>;\n }"}}]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"inspect-tools-api","status":"completed","content":[{"type":"content","content":{"type":"text","text":"## api\n- tools — Tool registry and execution pipeline.\n /**\n * Register globally or in the calling agent scope. Scoped tools shadow\n * globals; duplicates within one layer and the reserved `run_code` name fail.\n * @param definition - tool schema, execution, and optional finalization/presentation callbacks.\n * @returns the exact disposer that unregisters the tool.\n */\n register(definition: ToolDefinition): () => void\n /**\n * Restrict global tools for the calling agent scope. Empty filters, unknown\n * names, scope-local names, and reserved transport names fail. Restrictions\n * intersect; scoped registrations remain visible.\n * @param filter - global-surface mask: `allow` (keep only) and/or `deny` (remove).\n * @returns the exact disposer that lifts this restriction.\n */\n restrict(filter: ToolRestriction): () => void\n /**\n * Register a monotonic guard after the extensible `tools/pre-execute`\n * waterfall. A plain-context guard applies globally; one registered through\n * `agent.ctx` applies only to that agent. Any matching guard may deny by\n * returning a reason, while no guard can force-allow a call another guard\n * denied. The exact effect disposer is returned for ordered ownership and\n * HMR cleanup.\n * @param guard - synchronous check; a returned string denies the execution.\n * @returns the exact disposer that unregisters the guard.\n */\n guard(guard: ToolGuard): () => void\n /**\n * Look up a tool as one scope sees it (scoped\n * shadows global; a restricted-away global reads as absent). Presenters pass\n * the calling agent so the rendered card matches the definition that\n * actually executed.\n * @param name - the tool name as registered.\n * @param scope - the viewing scope (the agent); omitted = the global view.\n * @returns the definition the scope resolves, or undefined when none is visible.\n */\n get(name: string, scope?: ScopeKey): ToolDefinition | undefined\n /**\n * Project visible definitions onto the allowlisted model-facing schema fields,\n * excluding execution and presentation callbacks.\n * @param scope - the viewing scope (the agent); omitted = the global view.\n * @returns one deep-cloned schema per visible tool.\n */\n schemas(scope?: ScopeKey): ToolSchema[]\n /**\n * Classify a pending call through the caller's visible tool definition. Only\n * an exact `true` is parallel; unknown, hidden, undeclared, invalid, or\n * throwing classifiers are exclusive.\n * @param exec - call name, parsed arguments, and optional agent scope.\n * @returns the fail-closed scheduling mode.\n */\n executionMode(exec: ToolExecutionInput): ToolExecutionMode\n /**\n * Execute through pre-policy, guards, around-dispatch, post-policy,\n * definition-owned content finalization, and final notification. Tool and\n * listener failures resolve as materialized error results; an invisible tool\n * reports `UNKNOWN_TOOL`. The returned outcome is the same lossless, frozen\n * snapshot final observers receive. Cancellation\n * arriving after entry and before final result materialization skips a\n * not-yet-started body with `ABORTED_BEFORE_DISPATCH` or replaces a\n * successful started outcome with `ABORTED`; already-started work is still\n * drained and may retain a tool-owned structured error.\n * @param exec - the typed same-process call input. The registry assigns its\n * correlation token before policy begins.\n * @returns the materialized final result.\n */\n async execute(exec: ToolExecutionInput): Promise<ToolExecutionResult>\ntype shapes (referenced by the signatures above — read these before assuming a field is a string):\n export interface Agent {\n readonly id: SessionId;\n readonly options: AgentOptions;\n readonly session: Session;\n readonly status: AgentStatus;\n readonly ctx: Context;\n followup(content: ContentBlock[], options?: SendOptions): AgentMessageId;\n queue(content: ContentBlock[], options?: SendOptions): AgentMessageId;\n steer(content: ContentBlock[], options?: SendOptions): AgentMessageId;\n inject(content: ContentBlock[], options?: InjectOptions): AgentMessageId;\n send(input: ResolvedAgentInput): AgentMessageId;\n cancel(cause?: AgentCancelCause, options?: CancelOptions): void;\n whenIdle(): Promise<void>;\n }\n export type AgentCancelCause = {\n readonly kind: 'user';\n } | {\n readonly kind: 'parent';\n };\n export type AgentMessageId = Branded<'AgentMessageId'>;\n export interface AgentOptions {\n provider?: string;\n model?: string;\n }\n export type AgentStatus = 'idle' | 'running' | 'disposed';\n export interface AssistantProvenance {\n provider: string;\n model: string;\n replayState?: unknown;\n }\n export type Branded<B extends string> = string & {\n readonly [BRAND]: B;\n };\n export type CallId = Branded<'CallId'>;\n export interface CancelOptions {\n keepInbox?: boolean;\n }\n export interface ContentBlockMap {\n 'text': TextBlock;\n 'reasoning': ReasoningBlock;\n 'tool-call': ToolCallBlock;\n 'tool-result': ToolResultBlock;\n }\n export type ContentBlockType = keyof ContentBlockMap;\n export interface DiffCallView {\n card: 'diff';\n title: string;\n diffs: FileDiff[];\n locations?: FileLocation[];\n }\n export interface DiffResultView {\n card: 'diff';\n title?: string;\n diffs: FileDiff[];\n }\n export interface EpochHeader {\n config: LlmCallConfig;\n system?: string;\n tools?: ToolSchema[];\n messagePrefix?: Message[];\n }\n export interface FileDiff {\n path: string;\n oldText: string | null;\n newText: string;\n }\n export interface FileLocation {\n path: string;\n line?: number;\n }\n export type FinishReason = FinishReasonMap[keyof FinishReasonMap];\n export interface FinishReasonMap {\n 'stop': {\n kind: 'stop';\n };\n 'tool-calls': {\n kind: 'tool-calls';\n };\n 'max-tokens': {\n kind: 'max-tokens';\n };\n 'aborted': {\n kind: 'aborted';\n failure: LlmFailure;\n };\n 'error': {\n kind: 'error';\n failure: LlmFailure;\n };\n }\n export interface GenericCallView {\n card: 'generic';\n title: string;\n kind?: ToolCallKind;\n rawInput?: unknown;\n content?: ContentBlock[];\n locations?: FileLocation[];\n }\n export interface GenericResultView {\n card: 'generic';\n title?: string;\n content?: ContentBlock[];\n }\n export interface HookContext {\n content: ContentBlock[];\n source: MessageSource;\n placement?: 'separate' | 'prompt-prefix';\n meta?: JsonValue;\n }\n export interface InjectOptions {\n source?: MessageSource;\n meta?: JsonValue;\n }\n export interface JsonSchemaNode {\n type?: JsonSchemaType;\n oneOf?: JsonSchemaNode[];\n properties?: Record<string, JsonSchemaNode>;\n required?: string[];\n additionalProperties?: boolean;\n items?: JsonSchemaNode;\n enum?: JsonSchemaScalar[];\n const?: JsonSchemaScalar;\n description?: string;\n title?: string;\n default?: JsonValue;\n examples?: JsonValue;\n }\n export type JsonSchemaScalar = string | number | boolean | null;\n export type JsonSchemaType = 'object' | 'array' | 'string' | 'number' | 'integer' | 'boolean' | 'null';\n export type JsonValue = null | boolean | number | string | JsonValue[] | {\n [key: string]: JsonValue;\n };\n export interface LlmCallConfig {\n provider: string;\n model: string;\n temperature?: number;\n maxTokens?: number;\n stop?: string[];\n }\n export interface LlmFailure {\n readonly message: string;\n readonly code: string;\n readonly status?: number;\n readonly providerRetryAfterMs?: number;\n readonly requestId?: ProviderRequestId;\n }\n export interface Message {\n role: 'system' | 'user' | 'assistant';\n content: ContentBlock[];\n provenance?: AssistantProvenance;\n }\n export type MessageSource = MessageSourceMap[keyof MessageSourceMap];\n export interface MessageSourceMap {\n user: {\n kind: 'user';\n };\n plugin: {\n kind: 'plugin';\n plugin: string;\n };\n }\n export interface PromptMessageData {\n content: ContentBlock[];\n source: MessageSource;\n envelope?: PromptMessageEnvelope;\n meta?: JsonValue;\n }\n export interface PromptMessageEnvelope {\n displayContent: ContentBlock[];\n prefixContexts: PromptPrefixContext[];\n }\n export interface PromptPrefixContext {\n source: MessageSource;\n meta?: JsonValue;\n }\n export type ProviderRequestId = Branded<'ProviderRequestId'>;\n export interface ReasoningBlock {\n type: 'reasoning';\n text: string;\n }\n export type RequestHeaderReason = 'initial' | 'resume' | 'change';\n export type ResolvedAgentInput = {\n content: ContentBlock[];\n source: MessageSource;\n meta: JsonValue | undefined;\n } & ({\n target: 'next-turn';\n wakeup: boolean;\n contexts: HookContext[];\n } | {\n target: 'next-step';\n wakeup: true;\n contexts: HookContext[];\n } | {\n target: 'next-step';\n wakeup: false;\n contexts: [\n ];\n });\n export type ScopeKey = object;\n export interface SendOptions {\n source?: MessageSource;\n contexts?: HookContext[];\n meta?: JsonValue;\n }\n export class Session {\n get surface(): SessionSurface;\n readonly header: SessionHeader;\n get id(): SessionId;\n constructor(id: SessionId, seed?: readonly SessionEvent[], header?: SessionHeader);\n get events(): readonly SessionEvent[];\n get seq(): number;\n append<T extends SessionEventType>(type: T, data: SessionEventMap[T], ...opts: T extends SurfaceEventType ? [\n opts: SurfaceIntent\n ] : [\n ]): SessionEvent<T>;\n requestHeader(): EpochHeader | undefined;\n deriveMessages(): Message[];\n deriveEventMessage(event: SessionEvent): Message | null;\n }\n export type SessionEvent<T extends SessionEventType = SessionEventType> = {\n [K in SessionEventType]: {\n type: K;\n seq: number;\n time: number;\n data: SessionEventMap[K];\n } & (K extends SurfaceEventType ? {\n sourceEventSeqs?: number[];\n surfaceOp?: SurfaceOp;\n } : object);\n }[T];\n export interface SessionEventMap {\n 'turn/start': {\n turn: number;\n trigger: TurnTrigger;\n };\n 'turn/end': {\n turn: number;\n reason: TurnEndReason;\n };\n 'step/start': {\n turn: number;\n step: number;\n };\n 'step/end': {\n turn: number;\n step: number;\n };\n 'user/message': PromptMessageData;\n 'prompt/blocked': {\n content: ContentBlock[];\n source: MessageSource;\n reason: string;\n };\n 'assistant/chunk': {\n turn: number;\n step: number;\n chunk: StreamChunk;\n };\n 'assistant/message': {\n turn: number;\n step: number;\n content: ContentBlock[];\n provenance: AssistantProvenance;\n usage?: TokenUsage;\n };\n 'tool/call': {\n turn: number;\n step: number;\n callId: CallId;\n name: string;\n arguments: string;\n };\n 'tool/result': {\n turn: number;\n step: number;\n callId: CallId;\n content: ContentBlock[];\n isError: boolean;\n error?: {\n name: string;\n code: string;\n };\n meta?: JsonValue;\n };\n 'steering/message': PromptMessageData & {\n turn: number;\n };\n 'todo/write': {\n todos: TodoItem[];\n };\n 'request/header': {\n header: EpochHeader;\n reason: RequestHeaderReason;\n };\n }\n export type SessionEventType = keyof SessionEventMap;\n export interface SessionHeader {\n readonly version: number;\n readonly id: SessionId;\n readonly createdAt: number;\n readonly cwd?: string;\n readonly parentSession?: SessionId;\n readonly seedLength?: number;\n readonly delegationDepth?: number;\n }\n export type SessionId = Branded<'SessionId'>;\n export interface SessionSurface {\n readonly nodes: readonly number[];\n readonly replaceGeneration: number;\n }\n export type StreamChunk = {\n type: 'block-start';\n index: number;\n blockType: ContentBlockType;\n } | {\n type: 'text-delta';\n index: number;\n text: string;\n } | {\n type: 'reasoning-delta';\n index: number;\n text: string;\n } | {\n type: 'tool-call-delta';\n index: number;\n id: CallId;\n name?: string;\n argumentsDelta: string;\n } | {\n type: 'block-end';\n index: number;\n block: ContentBlock;\n } | {\n type: 'usage';\n usage: TokenUsage;\n } | {\n type: 'finish';\n reason: FinishReason;\n replayState?: unknown;\n };\n export type SurfaceEventType = 'user/message' | 'assistant/message' | 'tool/result' | 'steering/message';\n export interface SurfaceIntent {\n surfaceOp: SurfaceOp;\n sourceEventSeqs?: number[];\n }\n export type SurfaceOp = 'append' | {\n op: 'replace';\n start: number;\n end: number;\n };\n export interface TerminalCallView {\n card: 'terminal';\n title: string;\n description?: string;\n cwd?: string;\n }\n export interface TerminalResultView {\n card: 'terminal';\n title?: string;\n output?: string;\n exitCode?: number;\n signal?: string;\n }\n export interface TodoItem {\n content: string;\n status: 'pending' | 'in_progress' | 'completed';\n }\n export interface TokenUsage {\n inputTokens: number;\n outputTokens: number;\n cacheReadTokens?: number;\n cacheWriteTokens?: number;\n reasoningTokens?: number;\n }\n export interface ToolCallBlock {\n type: 'tool-call';\n id: CallId;\n name: string;\n arguments: string;\n }\n export type ToolCallKind = 'read' | 'edit' | 'delete' | 'move' | 'search' | 'execute' | 'fetch' | 'other';\n export type ToolCallView = GenericCallView | TerminalCallView | DiffCallView;\n export interface ToolDefinition extends ToolSchema {\n readonly output: ToolOutputDefinition;\n execute(args: unknown, exec: ToolRunContext): Promise<unknown>;\n finalizeContent?(exec: Readonly<ToolExecution>, result: Readonly<ToolExecutionResult>): ContentBlock[] | undefined;\n timeoutMs?: number;\n isConcurrencySafe?(args: unknown): boolean;\n presentCall?(args: unknown): ToolCallView | undefined;\n presentResult?(args: unknown, result: ToolResult): ToolResultView | undefined;\n }\n export interface ToolErrorInfo {\n name: string;\n code: string;\n }\n export interface ToolExecution extends ToolExecutionInput {\n readonly token: ToolExecutionToken;\n }\n export interface ToolExecutionFailure {\n readonly isError: true;\n readonly error: ToolFailure;\n readonly value?: never;\n readonly content: ContentBlock[];\n readonly meta?: JsonValue;\n readonly additionalContexts?: HookContext[];\n }\n export interface ToolExecutionInput {\n readonly callId: CallId;\n readonly name: string;\n readonly arguments: unknown;\n readonly agent?: Agent;\n readonly parent?: ToolExecutionToken;\n readonly signal: AbortSignal;\n }\n export type ToolExecutionMode = {\n kind: 'parallel';\n } | {\n kind: 'exclusive';\n };\n export type ToolExecutionResult = ToolExecutionSuccess | ToolExecutionFailure;\n export interface ToolExecutionSuccess {\n readonly isError: false;\n readonly value: JsonValue;\n readonly content: ContentBlock[];\n readonly error?: never;\n readonly meta?: JsonValue;\n readonly additionalContexts?: HookContext[];\n }\n export type ToolExecutionToken = symbol & {\n readonly [toolExecutionTokenBrand]: true;\n };\n export interface ToolFailure {\n message: string;\n info?: ToolErrorInfo;\n }\n export type ToolGuard = (execution: Readonly<ToolExecution>) => string | undefined;\n export interface ToolOutputDefinition {\n readonly schema: JsonSchemaNode;\n render(args: unknown, value: JsonValue): ContentBlock[];\n presentationMeta?(args: unknown, value: JsonValue): JsonValue;\n }\n export interface ToolRestriction {\n readonly allow?: readonly string[];\n readonly deny?: readonly string[];\n }\n export interface ToolResult {\n content: ContentBlock[];\n isError: boolean;\n meta?: JsonValue;\n }\n export interface ToolResultBlock {\n type: 'tool-result';\n toolCallId: CallId;\n content: ContentBlock[];\n isError?: boolean;\n }\n export type ToolResultView = GenericResultView | TerminalResultView | DiffResultView;\n export interface ToolRunContext extends ToolExecution {\n deferContext(context: HookContext): void;\n }\n export interface ToolSchema {\n name: string;\n description: string;\n parameters: Record<string, unknown>;\n }\n export type TurnEndReason = TurnEndReasonMap[keyof TurnEndReasonMap];\n export interface TurnEndReasonMap {\n completed: {\n kind: 'completed';\n };\n aborted: {\n kind: 'aborted';\n };\n error: {\n kind: 'error';\n step: number;\n } & ({\n failure: LlmFailure;\n message?: never;\n code?: never;\n } | {\n message: string;\n code?: string;\n failure?: never;\n });\n disposed: {\n kind: 'disposed';\n };\n 'max-tokens': {\n kind: 'max-tokens';\n };\n rejected: {\n kind: 'rejected';\n reason: string;\n };\n interrupted: {\n kind: 'interrupted';\n };\n }\n export type TurnTrigger = TurnTriggerMap[keyof TurnTriggerMap];\n export interface TurnTriggerMap {\n message: {\n kind: 'message';\n source: MessageSource;\n };\n injection: {\n kind: 'injection';\n source: MessageSource;\n };\n }"}}]}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"inspect-tools-event","title":"Inspect cordis runtime: events: tools/pre-execute","kind":"read","status":"in_progress"}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"inspect-tools-event","status":"completed","content":[{"type":"content","content":{"type":"text","text":"## events\n- tools/pre-execute [waterfall] — Allow, deny, or ask before dispatch.\n /**\n * Allow, deny, or ask before dispatch. `next()` delegates to allow; missing\n * approval support turns `ask` into denial. Async gates must observe\n * `exec.signal`; the registry rechecks cancellation after they settle but\n * never abandons their promise.\n * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent's calls.\n * @param exec - the pending call (name, parsed arguments, caller agent).\n * @mode waterfall\n */\n 'tools/pre-execute'(this: Scoped<ToolRegistry>, exec: ToolExecution, next: () => Promise<PreToolDecision>): Promise<PreToolDecision>\nwaterfall listeners receive a trailing next() and MUST call it to delegate — returning without next() vetoes the chain."}}]}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"CORDIS_INSPECT_JSDOC_OK"}}}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-posttool-context/session.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-posttool-context/session.jsonl index c638389319..910bdfca68 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-posttool-context/session.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-posttool-context/session.jsonl @@ -63,7 +63,7 @@ {"type":"hook/invoked","seq":61,"time":1783352197968,"data":{"turn":1,"point":"PostToolUse","dialect":"claude","handlerId":"claude:PostToolUse:1","matcher":"bash"}} {"type":"hook/result","seq":62,"time":1783352197976,"data":{"turn":1,"point":"PostToolUse","handlerId":"claude:PostToolUse:1","decision":"pass","exitCode":0,"durationMs":7.404540999999881}} {"type":"tool/result","seq":63,"time":1783352197976,"data":{"turn":1,"step":1,"callId":"call_00_HbCMzTslWBZTSphWN0z97382","content":[{"type":"text","text":"HELLO\n"}],"isError":false},"sourceEventSeqs":[60],"surfaceOp":"append"} -{"type":"context/message","seq":64,"time":1783352197976,"data":{"content":[{"type":"text","text":"Note: command output has been verified against the audit log."}],"source":{"kind":"plugin","plugin":"hooks-claude"}},"surfaceOp":"append"} +{"type":"user/message","seq":64,"time":1783352197976,"data":{"content":[{"type":"text","text":"Note: command output has been verified against the audit log."}],"source":{"kind":"plugin","plugin":"hooks-claude"}},"surfaceOp":"append"} {"type":"step/end","seq":65,"time":1783352197977,"data":{"turn":1,"step":1}} {"type":"step/start","seq":66,"time":1783352197977,"data":{"turn":1,"step":2}} {"type":"assistant/chunk","seq":67,"time":1783352198981,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-context/session.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-context/session.jsonl index 46561a4760..921bc270d9 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-context/session.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-context/session.jsonl @@ -3,7 +3,7 @@ {"type":"hook/invoked","seq":1,"time":1783352160546,"data":{"turn":1,"point":"UserPromptSubmit","dialect":"claude","handlerId":"claude:UserPromptSubmit:1"}} {"type":"hook/result","seq":2,"time":1783352160564,"data":{"turn":1,"point":"UserPromptSubmit","handlerId":"claude:UserPromptSubmit:1","decision":"pass","exitCode":0,"durationMs":17.45639600000004}} {"type":"user/message","seq":3,"time":1783352160564,"data":{"content":[{"type":"text","text":"What is my favorite color? Reply with just the color and stop. Do not use any tools."}],"source":{"kind":"user"}},"surfaceOp":"append"} -{"type":"context/message","seq":4,"time":1783352160564,"data":{"content":[{"type":"text","text":"The user has previously stated their favorite color is teal."}],"source":{"kind":"plugin","plugin":"hooks-claude"}},"surfaceOp":"append"} +{"type":"user/message","seq":4,"time":1783352160564,"data":{"content":[{"type":"text","text":"The user has previously stated their favorite color is teal."}],"source":{"kind":"plugin","plugin":"hooks-claude"}},"surfaceOp":"append"} {"type":"session/title","seq":5,"time":1783352160564,"data":{"title":"What is my favorite color?","messageSeqs":[3],"source":{"kind":"fallback"}}} {"type":"step/start","seq":6,"time":1783352160565,"data":{"turn":1,"step":1}} {"type":"request/header","seq":7,"time":1783352160566,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} diff --git a/examples/acp-agent/tests/snapshots/hook-codex-posttool-context/session.jsonl b/examples/acp-agent/tests/snapshots/hook-codex-posttool-context/session.jsonl index 9b58a769c5..deab3ab423 100644 --- a/examples/acp-agent/tests/snapshots/hook-codex-posttool-context/session.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-codex-posttool-context/session.jsonl @@ -63,7 +63,7 @@ {"type":"hook/invoked","seq":61,"time":1783352229622,"data":{"turn":1,"point":"PostToolUse","dialect":"codex","handlerId":"codex:PostToolUse:1","matcher":"bash"}} {"type":"hook/result","seq":62,"time":1783352229632,"data":{"turn":1,"point":"PostToolUse","handlerId":"codex:PostToolUse:1","decision":"pass","exitCode":0,"durationMs":9.27664199999981}} {"type":"tool/result","seq":63,"time":1783352229632,"data":{"turn":1,"step":1,"callId":"call_00_Q6wHtakaip2QNfIXaVJY5458","content":[{"type":"text","text":"HELLO\n"}],"isError":false},"sourceEventSeqs":[60],"surfaceOp":"append"} -{"type":"context/message","seq":64,"time":1783352229633,"data":{"content":[{"type":"text","text":"Note: command output has been verified against the audit log."}],"source":{"kind":"plugin","plugin":"hooks-codex"}},"surfaceOp":"append"} +{"type":"user/message","seq":64,"time":1783352229633,"data":{"content":[{"type":"text","text":"Note: command output has been verified against the audit log."}],"source":{"kind":"plugin","plugin":"hooks-codex"}},"surfaceOp":"append"} {"type":"step/end","seq":65,"time":1783352229633,"data":{"turn":1,"step":1}} {"type":"step/start","seq":66,"time":1783352229633,"data":{"turn":1,"step":2}} {"type":"assistant/chunk","seq":67,"time":1783352230757,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} diff --git a/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-context/session.jsonl b/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-context/session.jsonl index c1f23a6b5e..ac319964f3 100644 --- a/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-context/session.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-context/session.jsonl @@ -3,7 +3,7 @@ {"type":"hook/invoked","seq":1,"time":1783352209687,"data":{"turn":1,"point":"UserPromptSubmit","dialect":"codex","handlerId":"codex:UserPromptSubmit:1"}} {"type":"hook/result","seq":2,"time":1783352209706,"data":{"turn":1,"point":"UserPromptSubmit","handlerId":"codex:UserPromptSubmit:1","decision":"pass","exitCode":0,"durationMs":19.49695100000008}} {"type":"user/message","seq":3,"time":1783352209707,"data":{"content":[{"type":"text","text":"What is my favorite color? Reply with just the color and stop. Do not use any tools."}],"source":{"kind":"user"}},"surfaceOp":"append"} -{"type":"context/message","seq":4,"time":1783352209707,"data":{"content":[{"type":"text","text":"The user has previously stated their favorite color is teal."}],"source":{"kind":"plugin","plugin":"hooks-codex"}},"surfaceOp":"append"} +{"type":"user/message","seq":4,"time":1783352209707,"data":{"content":[{"type":"text","text":"The user has previously stated their favorite color is teal."}],"source":{"kind":"plugin","plugin":"hooks-codex"}},"surfaceOp":"append"} {"type":"session/title","seq":5,"time":1783352209707,"data":{"title":"What is my favorite color?","messageSeqs":[3],"source":{"kind":"fallback"}}} {"type":"step/start","seq":6,"time":1783352209709,"data":{"turn":1,"step":1}} {"type":"request/header","seq":7,"time":1783352209710,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} diff --git a/examples/acp-agent/tests/snapshots/permission-switching/session.jsonl b/examples/acp-agent/tests/snapshots/permission-switching/session.jsonl index cbb52c1b08..381458957c 100644 --- a/examples/acp-agent/tests/snapshots/permission-switching/session.jsonl +++ b/examples/acp-agent/tests/snapshots/permission-switching/session.jsonl @@ -106,7 +106,7 @@ {"type":"sandbox/mode","seq":104,"time":1784518115842,"data":{"mode":"danger-full-access"}} {"type":"approval/policy","seq":105,"time":1783962244624,"data":{"policy":"never"}} {"type":"user/message","seq":106,"time":1783962244624,"data":{"content":[{"type":"text","text":"Use the bash tool to run exactly: cat out.txt. Then reply with the single word DONE and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} -{"type":"context/message","seq":107,"time":1783962244624,"data":{"content":[{"type":"text","text":"The approval policy changed from \"ask\" to \"never\" (changed by the user)."}],"source":{"kind":"plugin","plugin":"user-approval"}},"surfaceOp":"append"} +{"type":"user/message","seq":107,"time":1783962244624,"data":{"content":[{"type":"text","text":"The approval policy changed from \"ask\" to \"never\" (changed by the user)."}],"source":{"kind":"plugin","plugin":"user-approval"}},"surfaceOp":"append"} {"type":"step/start","seq":108,"time":1783962244624,"data":{"turn":2,"step":1}} {"type":"request/header","seq":109,"time":1784000791271,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"change"}} {"type":"assistant/chunk","seq":110,"time":1783860671025,"data":{"turn":2,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} diff --git a/examples/acp-agent/tests/snapshots/repeat-tool-guard/session.jsonl b/examples/acp-agent/tests/snapshots/repeat-tool-guard/session.jsonl index a277f2e997..1f7345dc80 100644 --- a/examples/acp-agent/tests/snapshots/repeat-tool-guard/session.jsonl +++ b/examples/acp-agent/tests/snapshots/repeat-tool-guard/session.jsonl @@ -35,7 +35,7 @@ {"type":"tool/call","seq":33,"time":0,"data":{"turn":1,"step":3,"callId":"call_3","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"watch the kettle boil\", \"status\": \"in_progress\"}]}"}} {"type":"todo/write","seq":34,"time":0,"data":{"todos":[{"content":"watch the kettle boil","status":"in_progress"}]}} {"type":"tool/result","seq":35,"time":0,"data":{"turn":1,"step":3,"callId":"call_3","content":[{"type":"text","text":"Updated todo list: 0 pending, 1 in progress, 0 completed."}],"isError":false},"sourceEventSeqs":[33],"surfaceOp":"append"} -{"type":"context/message","seq":36,"time":0,"data":{"content":[{"type":"text","text":"You are repeating the exact same tool call with identical arguments. Carefully analyze the previous result before calling again: if the task is not complete, try a different approach or different arguments instead of repeating the call."}],"source":{"kind":"plugin","plugin":"repeat-tool-guard"}},"surfaceOp":"append"} +{"type":"user/message","seq":36,"time":0,"data":{"content":[{"type":"text","text":"You are repeating the exact same tool call with identical arguments. Carefully analyze the previous result before calling again: if the task is not complete, try a different approach or different arguments instead of repeating the call."}],"source":{"kind":"plugin","plugin":"repeat-tool-guard"}},"surfaceOp":"append"} {"type":"step/end","seq":37,"time":0,"data":{"turn":1,"step":3}} {"type":"step/start","seq":38,"time":0,"data":{"turn":1,"step":4}} {"type":"assistant/chunk","seq":39,"time":0,"data":{"turn":1,"step":4,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}} @@ -58,7 +58,7 @@ {"type":"tool/call","seq":56,"time":0,"data":{"turn":1,"step":5,"callId":"call_5","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"watch the kettle boil\", \"status\": \"in_progress\"}]}"}} {"type":"todo/write","seq":57,"time":0,"data":{"todos":[{"content":"watch the kettle boil","status":"in_progress"}]}} {"type":"tool/result","seq":58,"time":0,"data":{"turn":1,"step":5,"callId":"call_5","content":[{"type":"text","text":"Updated todo list: 0 pending, 1 in progress, 0 completed."}],"isError":false},"sourceEventSeqs":[56],"surfaceOp":"append"} -{"type":"context/message","seq":59,"time":0,"data":{"content":[{"type":"text","text":"Repeated tool call detected:\n- tool: todo_write\n- consecutive_calls: 5\n- arguments: {\"todos\":[{\"content\":\"watch the kettle boil\",\"status\":\"in_progress\"}]}\nThe repeated calls are not making progress. Do not call this tool with these exact arguments again. Inspect the latest result and choose a different action, different arguments, or finish the task if enough evidence has been gathered."}],"source":{"kind":"plugin","plugin":"repeat-tool-guard"}},"surfaceOp":"append"} +{"type":"user/message","seq":59,"time":0,"data":{"content":[{"type":"text","text":"Repeated tool call detected:\n- tool: todo_write\n- consecutive_calls: 5\n- arguments: {\"todos\":[{\"content\":\"watch the kettle boil\",\"status\":\"in_progress\"}]}\nThe repeated calls are not making progress. Do not call this tool with these exact arguments again. Inspect the latest result and choose a different action, different arguments, or finish the task if enough evidence has been gathered."}],"source":{"kind":"plugin","plugin":"repeat-tool-guard"}},"surfaceOp":"append"} {"type":"step/end","seq":60,"time":0,"data":{"turn":1,"step":5}} {"type":"step/start","seq":61,"time":0,"data":{"turn":1,"step":6}} {"type":"assistant/chunk","seq":62,"time":0,"data":{"turn":1,"step":6,"chunk":{"type":"block-start","index":0,"blockType":"text"}}} diff --git a/examples/acp-agent/tests/snapshots/workspace-context/session.jsonl b/examples/acp-agent/tests/snapshots/workspace-context/session.jsonl index 8293ea3abf..883e685a6d 100644 --- a/examples/acp-agent/tests/snapshots/workspace-context/session.jsonl +++ b/examples/acp-agent/tests/snapshots/workspace-context/session.jsonl @@ -12,7 +12,7 @@ {"type":"assistant/message","seq":10,"time":1783778297070,"data":{"turn":1,"step":1,"content":[{"type":"tool-call","id":"call_workspace_read","name":"read","arguments":"{\"file_path\":\"nested/task.txt\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[5,6,7,8,9],"surfaceOp":"append"} {"type":"tool/call","seq":11,"time":1783778297070,"data":{"turn":1,"step":1,"callId":"call_workspace_read","name":"read","arguments":"{\"file_path\":\"nested/task.txt\"}"}} {"type":"tool/result","seq":12,"time":1783778297072,"data":{"turn":1,"step":1,"callId":"call_workspace_read","content":[{"type":"text","text":"<path>{{cwd}}/nested/task.txt</path>\n<type>file</type>\n<content>\n1: snapshot task\n\n(End of file - total 1 lines)\n</content>"}],"isError":false},"sourceEventSeqs":[11],"surfaceOp":"append"} -{"type":"context/message","seq":13,"time":1783778297072,"data":{"content":[{"type":"text","text":"<system-reminder>\nAdditional instructions from: nested/AGENTS.md\n\nThese instructions apply to work under `nested`. Use them as guidance when relevant; more specific instructions take precedence. They do not override system, developer, or direct user instructions.\n\nNested snapshot instruction.\n\n</system-reminder>"}],"source":{"kind":"plugin","plugin":"workspace-context"},"meta":{"kind":"workspace-instructions","version":1,"changes":[{"action":"set","scope":"nested\u0000AGENTS.md","path":"nested/AGENTS.md","digest":"c446df9a85c7e73a3055f394a4822a19ac9ead5a"}]}},"surfaceOp":"append"} +{"type":"user/message","seq":13,"time":1783778297072,"data":{"content":[{"type":"text","text":"<system-reminder>\nAdditional instructions from: nested/AGENTS.md\n\nThese instructions apply to work under `nested`. Use them as guidance when relevant; more specific instructions take precedence. They do not override system, developer, or direct user instructions.\n\nNested snapshot instruction.\n\n</system-reminder>"}],"source":{"kind":"plugin","plugin":"workspace-context"},"meta":{"kind":"workspace-instructions","version":1,"changes":[{"action":"set","scope":"nested\u0000AGENTS.md","path":"nested/AGENTS.md","digest":"c446df9a85c7e73a3055f394a4822a19ac9ead5a"}]}},"surfaceOp":"append"} {"type":"step/end","seq":14,"time":1783778297072,"data":{"turn":1,"step":1}} {"type":"step/start","seq":15,"time":1783778297072,"data":{"turn":1,"step":2}} {"type":"assistant/chunk","seq":16,"time":1783778297073,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"text"}}} diff --git a/examples/cordis-agent/tests/cordis-tools.e2e.ts b/examples/cordis-agent/tests/cordis-tools.e2e.ts index ae3651fdaf..b5f8e27564 100644 --- a/examples/cordis-agent/tests/cordis-tools.e2e.ts +++ b/examples/cordis-agent/tests/cordis-tools.e2e.ts @@ -42,7 +42,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('cordis tools: a real model modif const log = vi.spyOn(console, 'log').mockImplementation(() => {}) const agent = ctx.agentLoop.create(SessionId('cordis-e2e-listener'), { provider: 'deepseek', model: 'deepseek-v4-flash' }) - agent.send([{ + agent.followup([{ type: 'text', text: 'Use cordis_mount to mount a plugin that listens to the \'agent/status\' ' + 'cordis event and logs every change with console.log. Reply "mounted" once done.', @@ -58,7 +58,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('cordis tools: a real model modif }) expect(resultText(mid)).toContain('dyn-') - agent.send([{ type: 'text', text: 'Now unmount the plugin you just mounted.' }]) + agent.followup([{ type: 'text', text: 'Now unmount the plugin you just mounted.' }]) await waitForIdle(ctx, agent) const after = await ctx.tools.execute({ @@ -72,7 +72,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('cordis tools: a real model modif ctx = await cordisHarness() const agent = ctx.agentLoop.create(SessionId('cordis-e2e-selftool'), { provider: 'deepseek', model: 'deepseek-v4-flash' }) - agent.send([{ + agent.followup([{ type: 'text', text: 'Give yourself a new tool: use cordis_mount to mount a plugin with ' + 'inject ["tools"] that calls harness.registerTool(ctx, harness.defineTool({...})) ' @@ -119,7 +119,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('cordis tools: a real model modif ctx = await cordisHarness() const agent = ctx.agentLoop.create(SessionId('cordis-e2e-compose'), { provider: 'deepseek', model: 'deepseek-v4-flash' }) - agent.send([{ + agent.followup([{ type: 'text', text: 'Mount TWO separate plugins with cordis_mount. First a provider: apply calls ' + 'ctx.provide(\'shouter\', { shout: (s) => s.toUpperCase() }). Second a consumer with ' @@ -144,7 +144,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('cordis tools: a real model modif .flatMap(event => event.data.content.filter(block => block.type === 'text').map(block => block.text)) expect(shoutResults.some(text => text.includes('QUIET'))).toBe(true) - agent.send([{ type: 'text', text: 'Now unmount ONLY the provider plugin (the one that provided shouter).' }]) + agent.followup([{ type: 'text', text: 'Now unmount ONLY the provider plugin (the one that provided shouter).' }]) await waitForIdle(ctx, agent) // The consumer must have been parked by cordis itself: service gone, diff --git a/examples/headless-agent/tests/code-mode.e2e.ts b/examples/headless-agent/tests/code-mode.e2e.ts index 071d91d55b..86c1559b83 100644 --- a/examples/headless-agent/tests/code-mode.e2e.ts +++ b/examples/headless-agent/tests/code-mode.e2e.ts @@ -311,7 +311,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('Code Mode: real model writes a p ctx = await codeModeHarness(workdir) const agent = ctx.agentLoop.create(SessionId('e2e-code-mode'), { provider: 'deepseek', model: 'deepseek-v4-flash' }) - agent.send([{ + agent.followup([{ type: 'text', text: 'Using one run_code program: run `echo alpha-7` with the bash tool, run `echo beta-9` with the bash tool, ' + 'then write both outputs joined by a plus sign into combined.txt (bash heredoc or redirect), ' @@ -363,7 +363,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('Code Mode: real model writes a p agentOptions: { provider: 'deepseek', model: 'deepseek-v4-flash' }, }) - handle.agent.send([{ + handle.agent.followup([{ type: 'text', text: 'Use one run_code program to call tools.read on pkg/deep/task.txt. After it finishes, answer: Code Mode workspace handshake?', }]) @@ -372,7 +372,8 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('Code Mode: real model writes a p const events: SessionEvent[] = [...handle.agent.session.events] const dispatch = events.find(event => event.type === 'tool/code-dispatch' && event.data.name === 'read') const outerResult = events.find(event => event.type === 'tool/result') - const workspaceContext = events.find(event => event.type === 'context/message' + const workspaceContext = events.find(event => event.type === 'user/message' + && event.data.source.kind === 'plugin' && typeof event.data.meta === 'object' && event.data.meta !== null && !Array.isArray(event.data.meta) diff --git a/examples/headless-agent/tests/coding-task.e2e.ts b/examples/headless-agent/tests/coding-task.e2e.ts index a5f525e5c3..4a827858bb 100644 --- a/examples/headless-agent/tests/coding-task.e2e.ts +++ b/examples/headless-agent/tests/coding-task.e2e.ts @@ -56,7 +56,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('coding task: fix a failing test ctx = await codingHarness(workdir, { persona: SYSTEM_PROMPT }) const agent = ctx.agentLoop.create(SessionId('e2e-task'), { provider: 'deepseek', model: 'deepseek-v4-flash' }) - agent.send([{ + agent.followup([{ type: 'text', text: 'In the current directory, `node add.test.js` fails because add.js has a bug. ' + 'Fix add.js so the test passes, run `node add.test.js` to verify, and report the result. ' diff --git a/examples/headless-agent/tests/compaction.e2e.ts b/examples/headless-agent/tests/compaction.e2e.ts index fcebddb863..a96b7f3611 100644 --- a/examples/headless-agent/tests/compaction.e2e.ts +++ b/examples/headless-agent/tests/compaction.e2e.ts @@ -46,7 +46,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('compaction: a long session compa }) const agent = ctx.agentLoop.create(SessionId('e2e-compaction'), { provider: 'deepseek', model: 'deepseek-v4-flash' }) - agent.send([{ + agent.followup([{ type: 'text', text: 'Read file1.txt, file2.txt, file3.txt, and file4.txt one at a ' + 'time using cat (a separate bash command for each). After reading all four, tell me how ' diff --git a/examples/headless-agent/tests/full-loop.e2e.ts b/examples/headless-agent/tests/full-loop.e2e.ts index db2eec63fc..4f61ec3fa3 100644 --- a/examples/headless-agent/tests/full-loop.e2e.ts +++ b/examples/headless-agent/tests/full-loop.e2e.ts @@ -30,7 +30,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('full loop: real model + real bas ctx = await codingHarness(workdir, { persona: SYSTEM_PROMPT }) const agent = ctx.agentLoop.create(SessionId('e2e-loop'), { provider: 'deepseek', model: 'deepseek-v4-flash' }) - agent.send([{ type: 'text', text: 'Run `echo e2e-ok` with the bash tool and tell me its exact output.' }]) + agent.followup([{ type: 'text', text: 'Run `echo e2e-ok` with the bash tool and tell me its exact output.' }]) await waitForIdle(ctx, agent) const events = [...agent.session.events] diff --git a/examples/headless-agent/tests/headless.snapshot.ts b/examples/headless-agent/tests/headless.snapshot.ts index 1626489bf5..6852fed20b 100644 --- a/examples/headless-agent/tests/headless.snapshot.ts +++ b/examples/headless-agent/tests/headless.snapshot.ts @@ -222,9 +222,14 @@ describe('headless stream-json snapshots', () => { const records = parseJsonl(logs[0]?.content ?? '') const calls = records.filter(record => record.type === 'tool/call') .map(record => (record.data as JsonObject | undefined)?.name) - expect(calls).toEqual(['create_goal', 'get_goal']) + expect(calls).toEqual(['update_goal', 'create_goal', 'get_goal']) + const probeResult = records.find(record => record.type === 'tool/result' + && (record.data as JsonObject | undefined)?.callId === 'call_goal_probe') + const probeData = probeResult?.data as JsonObject | undefined + expect(probeData?.isError).toBe(true) + expect((probeData?.error as JsonObject | undefined)?.code).toBe('GOAL_NOT_FOUND') const goalChanges = records.filter((record) => { - if (record.type !== 'context/message') return false + if (record.type !== 'user/message') return false const data = record.data as JsonObject | undefined const meta = data?.meta as JsonObject | undefined return meta?.kind === 'goal/change' diff --git a/examples/headless-agent/tests/resume.e2e.ts b/examples/headless-agent/tests/resume.e2e.ts index 01c7d52393..a4ded767da 100644 --- a/examples/headless-agent/tests/resume.e2e.ts +++ b/examples/headless-agent/tests/resume.e2e.ts @@ -41,7 +41,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('resume: continue a persisted ses sessionId: SESSION_ID, agentOptions: { provider: 'deepseek', model: 'deepseek-v4-flash' }, })).agent - first.send([{ type: 'text', text: `Remember this code for later: ${SECRET}. Just acknowledge it.` }]) + first.followup([{ type: 'text', text: `Remember this code for later: ${SECRET}. Just acknowledge it.` }]) await waitForIdle(ctx, first) await ctx.fiber.dispose() ctx = undefined @@ -58,7 +58,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('resume: continue a persisted ses // The prior user turn is in the rehydrated log before the model is asked. expect(JSON.stringify(resumed.session.deriveMessages())).toContain(SECRET) - resumed.send([{ type: 'text', text: 'What was the code I asked you to remember? Reply with just the code.' }]) + resumed.followup([{ type: 'text', text: 'What was the code I asked you to remember? Reply with just the code.' }]) await waitForIdle(ctx, resumed) // The model recalls it — only possible from the resumed history. diff --git a/examples/headless-agent/tests/snapshots/goal-tools/input.json b/examples/headless-agent/tests/snapshots/goal-tools/input.json index 5263ccd4e2..8449d44c4c 100644 --- a/examples/headless-agent/tests/snapshots/goal-tools/input.json +++ b/examples/headless-agent/tests/snapshots/goal-tools/input.json @@ -2,7 +2,7 @@ "steps": [ { "op": "prompt", - "text": "Create a durable goal to finish the snapshot proof, then inspect it." + "text": "Probe strict-schema fillers against missing-goal revision 1, then create a durable goal to finish the snapshot proof and inspect it." } ] } diff --git a/examples/headless-agent/tests/snapshots/goal-tools/replay.override.json b/examples/headless-agent/tests/snapshots/goal-tools/replay.override.json index aec5204c7d..c4716ba7b0 100644 --- a/examples/headless-agent/tests/snapshots/goal-tools/replay.override.json +++ b/examples/headless-agent/tests/snapshots/goal-tools/replay.override.json @@ -1,4 +1,14 @@ [ + { + "kind": "chunks", + "chunks": [ + { "type": "block-start", "index": 0, "blockType": "tool-call" }, + { "type": "tool-call-delta", "index": 0, "id": "call_goal_probe", "name": "update_goal", "argumentsDelta": "{\"goal_id\":\"missing-goal\",\"revision\":1,\"action\":\"pause\",\"objective\":\"\",\"max_goal_rounds\":0,\"blocked_reason\":\"\"}" }, + { "type": "block-end", "index": 0, "block": { "type": "tool-call", "id": "call_goal_probe", "name": "update_goal", "arguments": "{\"goal_id\":\"missing-goal\",\"revision\":1,\"action\":\"pause\",\"objective\":\"\",\"max_goal_rounds\":0,\"blocked_reason\":\"\"}" } }, + { "type": "usage", "usage": { "inputTokens": 15, "outputTokens": 6 } }, + { "type": "finish", "reason": { "kind": "tool-calls" } } + ] + }, { "kind": "chunks", "chunks": [ diff --git a/examples/headless-agent/tests/snapshots/goal-tools/stream-json.expected.jsonl b/examples/headless-agent/tests/snapshots/goal-tools/stream-json.expected.jsonl index 05a1282a6f..16518b2d03 100644 --- a/examples/headless-agent/tests/snapshots/goal-tools/stream-json.expected.jsonl +++ b/examples/headless-agent/tests/snapshots/goal-tools/stream-json.expected.jsonl @@ -1,35 +1,45 @@ {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"turn/start","seq":0,"time":0,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}}} -{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"user/message","seq":1,"time":0,"data":{"content":[{"type":"text","text":"Create a durable goal to finish the snapshot proof, then inspect it."}],"source":{"kind":"user"}},"surfaceOp":"append"}} -{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"session/title","seq":2,"time":0,"data":{"title":"Create a durable goal to","messageSeqs":[1],"source":{"kind":"fallback"}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"user/message","seq":1,"time":0,"data":{"content":[{"type":"text","text":"Probe strict-schema fillers against missing-goal revision 1, then create a durable goal to finish the snapshot proof and inspect it."}],"source":{"kind":"user"}},"surfaceOp":"append"}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"session/title","seq":2,"time":0,"data":{"title":"Probe strict-schema fillers against miss","messageSeqs":[1],"source":{"kind":"fallback"}}}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/start","seq":3,"time":0,"data":{"turn":1,"step":1}}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"request/header","seq":4,"time":0,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":5,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}} -{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":6,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"call_goal_create","name":"create_goal","argumentsDelta":"{\"objective\":\"Finish the headless goal-tool snapshot proof\",\"max_goal_rounds\":7}"}}}} -{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":7,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_goal_create","name":"create_goal","arguments":"{\"objective\":\"Finish the headless goal-tool snapshot proof\",\"max_goal_rounds\":7}"}}}}} -{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":8,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":20,"outputTokens":8}}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":6,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"call_goal_probe","name":"update_goal","argumentsDelta":"{\"goal_id\":\"missing-goal\",\"revision\":1,\"action\":\"pause\",\"objective\":\"\",\"max_goal_rounds\":0,\"blocked_reason\":\"\"}"}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":7,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_goal_probe","name":"update_goal","arguments":"{\"goal_id\":\"missing-goal\",\"revision\":1,\"action\":\"pause\",\"objective\":\"\",\"max_goal_rounds\":0,\"blocked_reason\":\"\"}"}}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":8,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":15,"outputTokens":6}}}}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":9,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}} -{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":10,"time":0,"data":{"turn":1,"step":1,"content":[{"type":"tool-call","id":"call_goal_create","name":"create_goal","arguments":"{\"objective\":\"Finish the headless goal-tool snapshot proof\",\"max_goal_rounds\":7}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":20,"outputTokens":8}},"sourceEventSeqs":[5,6,7,8,9],"surfaceOp":"append"}} -{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/call","seq":11,"time":0,"data":{"turn":1,"step":1,"callId":"call_goal_create","name":"create_goal","arguments":"{\"objective\":\"Finish the headless goal-tool snapshot proof\",\"max_goal_rounds\":7}"}}} -{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/result","seq":12,"time":0,"data":{"turn":1,"step":1,"callId":"call_goal_create","content":[{"type":"text","text":"{\"goal\":{\"id\":\"goal-{{sessionId}}\",\"revision\":1,\"objective\":\"Finish the headless goal-tool snapshot proof\",\"phase\":\"active\",\"roundsStarted\":0,\"maxGoalRounds\":7},\"activation\":\"armed\"}"}],"isError":false},"sourceEventSeqs":[11],"surfaceOp":"append"}} -{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"context/message","seq":13,"time":0,"data":{"content":[{"type":"text","text":"<goal_state>{\"goal\":{\"id\":\"goal-{{sessionId}}\",\"revision\":1,\"objective\":\"Finish the headless goal-tool snapshot proof\",\"phase\":\"active\",\"maxGoalRounds\":7},\"roundsStarted\":0,\"createdAt\":0,\"updatedAt\":0}</goal_state>"}],"source":{"kind":"goal","goalId":"goal-{{sessionId}}","revision":1,"round":0},"meta":{"kind":"goal/change","version":1,"operation":"create","goal":{"id":"goal-{{sessionId}}","revision":1,"objective":"Finish the headless goal-tool snapshot proof","phase":"active","maxGoalRounds":7},"roundsStarted":0,"createdAt":0,"updatedAt":0}},"surfaceOp":"append"}} -{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/end","seq":14,"time":0,"data":{"turn":1,"step":1}}} -{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/start","seq":15,"time":0,"data":{"turn":1,"step":2}}} -{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":16,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}} -{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":17,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":0,"id":"call_goal_get","name":"get_goal","argumentsDelta":"{}"}}}} -{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":18,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_goal_get","name":"get_goal","arguments":"{}"}}}}} -{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":19,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":30,"outputTokens":4}}}}} -{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":20,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}} -{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":21,"time":0,"data":{"turn":1,"step":2,"content":[{"type":"tool-call","id":"call_goal_get","name":"get_goal","arguments":"{}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":30,"outputTokens":4}},"sourceEventSeqs":[16,17,18,19,20],"surfaceOp":"append"}} -{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/call","seq":22,"time":0,"data":{"turn":1,"step":2,"callId":"call_goal_get","name":"get_goal","arguments":"{}"}}} -{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/result","seq":23,"time":0,"data":{"turn":1,"step":2,"callId":"call_goal_get","content":[{"type":"text","text":"{\"goal\":{\"id\":\"goal-{{sessionId}}\",\"revision\":1,\"objective\":\"Finish the headless goal-tool snapshot proof\",\"phase\":\"active\",\"roundsStarted\":0,\"maxGoalRounds\":7},\"activation\":\"armed\"}"}],"isError":false},"sourceEventSeqs":[22],"surfaceOp":"append"}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":10,"time":0,"data":{"turn":1,"step":1,"content":[{"type":"tool-call","id":"call_goal_probe","name":"update_goal","arguments":"{\"goal_id\":\"missing-goal\",\"revision\":1,\"action\":\"pause\",\"objective\":\"\",\"max_goal_rounds\":0,\"blocked_reason\":\"\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":15,"outputTokens":6}},"sourceEventSeqs":[5,6,7,8,9],"surfaceOp":"append"}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/call","seq":11,"time":0,"data":{"turn":1,"step":1,"callId":"call_goal_probe","name":"update_goal","arguments":"{\"goal_id\":\"missing-goal\",\"revision\":1,\"action\":\"pause\",\"objective\":\"\",\"max_goal_rounds\":0,\"blocked_reason\":\"\"}"}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/result","seq":12,"time":0,"data":{"turn":1,"step":1,"callId":"call_goal_probe","content":[{"type":"text","text":"Error: no current goal"}],"isError":true,"error":{"name":"GoalError","code":"GOAL_NOT_FOUND"}},"sourceEventSeqs":[11],"surfaceOp":"append"}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/end","seq":13,"time":0,"data":{"turn":1,"step":1}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/start","seq":14,"time":0,"data":{"turn":1,"step":2}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":15,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":16,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":0,"id":"call_goal_create","name":"create_goal","argumentsDelta":"{\"objective\":\"Finish the headless goal-tool snapshot proof\",\"max_goal_rounds\":7}"}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":17,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_goal_create","name":"create_goal","arguments":"{\"objective\":\"Finish the headless goal-tool snapshot proof\",\"max_goal_rounds\":7}"}}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":18,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":20,"outputTokens":8}}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":19,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":20,"time":0,"data":{"turn":1,"step":2,"content":[{"type":"tool-call","id":"call_goal_create","name":"create_goal","arguments":"{\"objective\":\"Finish the headless goal-tool snapshot proof\",\"max_goal_rounds\":7}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":20,"outputTokens":8}},"sourceEventSeqs":[15,16,17,18,19],"surfaceOp":"append"}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/call","seq":21,"time":0,"data":{"turn":1,"step":2,"callId":"call_goal_create","name":"create_goal","arguments":"{\"objective\":\"Finish the headless goal-tool snapshot proof\",\"max_goal_rounds\":7}"}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/result","seq":22,"time":0,"data":{"turn":1,"step":2,"callId":"call_goal_create","content":[{"type":"text","text":"{\"goal\":{\"id\":\"goal-{{sessionId}}\",\"revision\":1,\"objective\":\"Finish the headless goal-tool snapshot proof\",\"phase\":\"active\",\"roundsStarted\":0,\"maxGoalRounds\":7},\"activation\":\"armed\"}"}],"isError":false},"sourceEventSeqs":[21],"surfaceOp":"append"}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"user/message","seq":23,"time":0,"data":{"content":[{"type":"text","text":"<goal_state>{\"goal\":{\"id\":\"goal-{{sessionId}}\",\"revision\":1,\"objective\":\"Finish the headless goal-tool snapshot proof\",\"phase\":\"active\",\"maxGoalRounds\":7},\"roundsStarted\":0,\"createdAt\":0,\"updatedAt\":0}</goal_state>"}],"source":{"kind":"goal","goalId":"goal-{{sessionId}}","revision":1,"round":0},"meta":{"kind":"goal/change","version":1,"operation":"create","goal":{"id":"goal-{{sessionId}}","revision":1,"objective":"Finish the headless goal-tool snapshot proof","phase":"active","maxGoalRounds":7},"roundsStarted":0,"createdAt":0,"updatedAt":0}},"surfaceOp":"append"}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/end","seq":24,"time":0,"data":{"turn":1,"step":2}}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/start","seq":25,"time":0,"data":{"turn":1,"step":3}}} -{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":26,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}} -{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":27,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"text-delta","index":0,"text":"GOAL READY"}}}} -{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":28,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"GOAL READY"}}}}} -{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":29,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"usage","usage":{"inputTokens":35,"outputTokens":2}}}}} -{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":30,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}} -{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":31,"time":0,"data":{"turn":1,"step":3,"content":[{"type":"text","text":"GOAL READY"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":35,"outputTokens":2}},"sourceEventSeqs":[26,27,28,29,30],"surfaceOp":"append"}} -{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/end","seq":32,"time":0,"data":{"turn":1,"step":3}}} -{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"turn/end","seq":33,"time":0,"data":{"turn":1,"reason":{"kind":"completed"}}}} -{"type":"result","success":true,"sessionId":"{{sessionId}}","turn":1,"result":"GOAL READY","reason":{"kind":"completed"},"usage":{"inputTokens":85,"outputTokens":14}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":26,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":27,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"tool-call-delta","index":0,"id":"call_goal_get","name":"get_goal","argumentsDelta":"{}"}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":28,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_goal_get","name":"get_goal","arguments":"{}"}}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":29,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"usage","usage":{"inputTokens":30,"outputTokens":4}}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":30,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":31,"time":0,"data":{"turn":1,"step":3,"content":[{"type":"tool-call","id":"call_goal_get","name":"get_goal","arguments":"{}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":30,"outputTokens":4}},"sourceEventSeqs":[26,27,28,29,30],"surfaceOp":"append"}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/call","seq":32,"time":0,"data":{"turn":1,"step":3,"callId":"call_goal_get","name":"get_goal","arguments":"{}"}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/result","seq":33,"time":0,"data":{"turn":1,"step":3,"callId":"call_goal_get","content":[{"type":"text","text":"{\"goal\":{\"id\":\"goal-{{sessionId}}\",\"revision\":1,\"objective\":\"Finish the headless goal-tool snapshot proof\",\"phase\":\"active\",\"roundsStarted\":0,\"maxGoalRounds\":7},\"activation\":\"armed\"}"}],"isError":false},"sourceEventSeqs":[32],"surfaceOp":"append"}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/end","seq":34,"time":0,"data":{"turn":1,"step":3}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/start","seq":35,"time":0,"data":{"turn":1,"step":4}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":36,"time":0,"data":{"turn":1,"step":4,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":37,"time":0,"data":{"turn":1,"step":4,"chunk":{"type":"text-delta","index":0,"text":"GOAL READY"}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":38,"time":0,"data":{"turn":1,"step":4,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"GOAL READY"}}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":39,"time":0,"data":{"turn":1,"step":4,"chunk":{"type":"usage","usage":{"inputTokens":35,"outputTokens":2}}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":40,"time":0,"data":{"turn":1,"step":4,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":41,"time":0,"data":{"turn":1,"step":4,"content":[{"type":"text","text":"GOAL READY"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":35,"outputTokens":2}},"sourceEventSeqs":[36,37,38,39,40],"surfaceOp":"append"}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/end","seq":42,"time":0,"data":{"turn":1,"step":4}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"turn/end","seq":43,"time":0,"data":{"turn":1,"reason":{"kind":"completed"}}}} +{"type":"result","success":true,"sessionId":"{{sessionId}}","turn":1,"result":"GOAL READY","reason":{"kind":"completed"},"usage":{"inputTokens":100,"outputTokens":20}} diff --git a/examples/headless-agent/tests/todo-write.e2e.ts b/examples/headless-agent/tests/todo-write.e2e.ts index daf5c018b1..c3053572d9 100644 --- a/examples/headless-agent/tests/todo-write.e2e.ts +++ b/examples/headless-agent/tests/todo-write.e2e.ts @@ -28,7 +28,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('todo_write: real model records a ctx = await codingHarness(workdir, { persona: TODO_SYSTEM_PROMPT }) const agent = ctx.agentLoop.create(SessionId('e2e-todo'), { provider: 'deepseek', model: 'deepseek-v4-flash' }) - agent.send([{ type: 'text', text: + agent.followup([{ type: 'text', text: 'Use the todo_write tool to record a plan of exactly two steps: first ' + '"inspect the failing test" (in_progress), then "apply the fix" (pending). ' + 'Send both in one todo_write call, then reply with the single word DONE.' }]) diff --git a/examples/package.json b/examples/package.json index 1b4e28c4fd..bd87263340 100644 --- a/examples/package.json +++ b/examples/package.json @@ -26,6 +26,7 @@ "@deepseek-ai/dsh-jsonrpc": "workspace:*", "@deepseek-ai/dsh-llm": "workspace:*", "@deepseek-ai/dsh-llm-deepseek": "workspace:*", + "@deepseek-ai/dsh-llm-pi-ai": "workspace:*", "@deepseek-ai/dsh-llm-replay": "workspace:*", "@deepseek-ai/dsh-lsp": "workspace:*", "@deepseek-ai/dsh-lsp-local": "workspace:*", diff --git a/examples/tui-agent/tests/tui.snapshot.ts b/examples/tui-agent/tests/tui.snapshot.ts index 0dee21988b..26ba64f23b 100644 --- a/examples/tui-agent/tests/tui.snapshot.ts +++ b/examples/tui-agent/tests/tui.snapshot.ts @@ -341,7 +341,7 @@ async function runScenario(scenario: Scenario): Promise<ScenarioResult> { } expect(exit.seq).toBeLessThan(afterExit.seq) expect(afterExit.data.header.system).not.toContain('Snapshot plan mode instructions.') - expect(events.filter(event => event.type === 'context/message').map(event => event.data.content)) + expect(events.filter(event => event.type === 'user/message' && event.data.source.kind === 'plugin').map(event => (event.data as { content: unknown }).content)) .toContainEqual([{ type: 'text', text: 'The user switched this session back to the default mode.' }]) } expect(events.filter(event => event.type === 'tool/result').every(event => !event.data.isError)).toBe(true) diff --git a/packages/bash/tool-bash/tests/integration.spec.ts b/packages/bash/tool-bash/tests/integration.spec.ts index 7d04dfe952..8adf2165e0 100644 --- a/packages/bash/tool-bash/tests/integration.spec.ts +++ b/packages/bash/tool-bash/tests/integration.spec.ts @@ -109,7 +109,7 @@ describe('bash tool through the agent loop', () => { const location = ctx.sessionPersistence.locate(agent.session.header) expect(location?.kind).toBe('jsonl') - agent.send([{ type: 'text', text: 'inspect the current session' }]) + agent.followup([{ type: 'text', text: 'inspect the current session' }]) await waitForIdle(ctx, agent) const result = findEvent(events(agent), 'tool/result') @@ -128,7 +128,7 @@ describe('bash tool through the agent loop', () => { const ctx = await harness(adapter) const agent = ctx.agentLoop.create(SessionId('it-fg'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'run echo integration-ok' }]) + agent.followup([{ type: 'text', text: 'run echo integration-ok' }]) await waitForIdle(ctx, agent) const log = events(agent) @@ -160,7 +160,7 @@ describe('bash tool through the agent loop', () => { const ctx = await harness(adapter) const agent = ctx.agentLoop.create(SessionId('it-exit'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'run exit 9' }]) + agent.followup([{ type: 'text', text: 'run exit 9' }]) await waitForIdle(ctx, agent) const toolResult = findEvent(events(agent), 'tool/result') @@ -168,7 +168,7 @@ describe('bash tool through the agent loop', () => { expect(resultText(toolResult)).toContain('[exit code: 9]') }) - it('background: start ack → completion notice as context/message → task_output collects it', async () => { + it('background: start ack → completion notice as user/message → task_output collects it', async () => { // The task id is deterministic (a fresh TaskService counts per kind from 1), // so the script can name `bash-1` without threading a generated id. const adapter = new MockAdapter([ @@ -180,7 +180,7 @@ describe('bash tool through the agent loop', () => { const ctx = await harness(adapter) const agent = ctx.agentLoop.create(SessionId('it-bg'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'run echo bg-ok in the background' }]) + agent.followup([{ type: 'text', text: 'run echo bg-ok in the background' }]) await waitForIdle(ctx, agent) const firstResult = findEvent(events(agent), 'tool/result') @@ -188,17 +188,19 @@ describe('bash tool through the agent loop', () => { expect(resultText(firstResult)).toBe('started background task bash-1') // The task settles on its own; the tool-tasks notice listener injects a - // durable context/message into the owning agent's session (settlement may - // race turn end, so poll for it). - await pollUntil(() => events(agent).some(event => event.type === 'context/message')) - const notice = findEvent(events(agent), 'context/message') + // durable plugin-sourced user/message into the owning agent's session + // (settlement may race turn end, so poll for it). + const isNotice = (e: SessionEvent): e is SessionEvent<'user/message'> => + e.type === 'user/message' && e.data.source.kind === 'plugin' + await pollUntil(() => events(agent).some(isNotice)) + const notice = events(agent).find(isNotice)! expect(notice.data.content.some( block => block.type === 'text' && block.text.includes('background task bash-1 (bash: echo bg-ok) finished'), )).toBe(true) expect(notice.data.source).toEqual({ kind: 'plugin', plugin: 'tool-tasks' }) // The next turn collects the output through the generic task tool. - agent.send([{ type: 'text', text: 'collect it' }]) + agent.followup([{ type: 'text', text: 'collect it' }]) await waitForIdle(ctx, agent) const readResult = findEvent(events(agent), 'tool/result', 'last') expect(readResult.data.isError).toBe(false) diff --git a/packages/client/connection/src/client/fixture.ts b/packages/client/connection/src/client/fixture.ts index 7585ca9fba..e1e21dfd78 100644 --- a/packages/client/connection/src/client/fixture.ts +++ b/packages/client/connection/src/client/fixture.ts @@ -76,7 +76,7 @@ function buildAlphaLog(): SessionEvent[] { }) } if (turn % 9 === 4) { - push({ type: 'context/message', surfaceOp: 'append', data: { content: text(`[fixture] 上下文注入(turn ${turn})`), source: { kind: 'plugin', plugin: 'fixture' } } }) + push({ type: 'user/message', surfaceOp: 'append', data: { content: text(`[fixture] 上下文注入(turn ${turn})`), source: { kind: 'plugin', plugin: 'fixture' } } }) } push({ type: 'step/start', data: { turn, step: 0 } }) const withTool = turn % 5 === 2 diff --git a/packages/client/runtime/src/client/sessions/fold-adapter.ts b/packages/client/runtime/src/client/sessions/fold-adapter.ts index 0342bc3c85..23b35f86bf 100644 --- a/packages/client/runtime/src/client/sessions/fold-adapter.ts +++ b/packages/client/runtime/src/client/sessions/fold-adapter.ts @@ -40,6 +40,15 @@ function materializeNode( ): ConversationNode { switch (event.type) { case 'user/message': + // Injected context (plugin/goal source) folds to a context node, not a + // user message; only a direct human prompt is a user node. + if (event.data.source.kind !== 'user') { + return { + kind: 'context', seq: event.seq, time: event.time, + content: event.data.content, source: event.data.source, + meta: event.data.meta, + } + } return { kind: 'user', seq: event.seq, time: event.time, content: event.data.content, source: event.data.source, @@ -55,12 +64,6 @@ function materializeNode( kind: 'steering', seq: event.seq, time: event.time, turn: event.data.turn, content: event.data.content, source: event.data.source, } - case 'context/message': - return { - kind: 'context', seq: event.seq, time: event.time, - content: event.data.content, source: event.data.source, - meta: event.data.meta, - } case 'tool/result': { const call = callIndex.get(String(event.data.callId)) return { @@ -75,7 +78,7 @@ function materializeNode( resultView, } } - /* v8 ignore next 2 -- defensive arm: fold output only carries the five + /* v8 ignore next 2 -- defensive arm: fold output only carries the four surface-eligible types, and each has a case above; reachable only if core adds an eligible type. */ default: diff --git a/packages/client/runtime/tests/fold-adapter.spec.ts b/packages/client/runtime/tests/fold-adapter.spec.ts index 3214c44ee9..bb360e2a67 100644 --- a/packages/client/runtime/tests/fold-adapter.spec.ts +++ b/packages/client/runtime/tests/fold-adapter.spec.ts @@ -40,7 +40,7 @@ describe('FoldAdapter', () => { ev.user(0, '用户'), ev.assistant(1, 0, '助手'), at(2, { type: 'steering/message', surfaceOp: 'append', data: { turn: 0, content: [{ type: 'text', text: '插话' }], source: { kind: 'user' } } }), - at(3, { type: 'context/message', surfaceOp: 'append', data: { content: [{ type: 'text', text: '上下文' }], source: { kind: 'plugin', plugin: 'p' } } }), + at(3, { type: 'user/message', surfaceOp: 'append', data: { content: [{ type: 'text', text: '上下文' }], source: { kind: 'plugin', plugin: 'p' } } }), ev.toolCall(4, 0, 'c1', 'echo', '{"x":1}'), ev.toolResult(5, 0, 'c1', '结果'), ] diff --git a/packages/compact/compact-basic/tests/compact-basic.spec.ts b/packages/compact/compact-basic/tests/compact-basic.spec.ts index 3ea658b64d..1db86d38e4 100644 --- a/packages/compact/compact-basic/tests/compact-basic.spec.ts +++ b/packages/compact/compact-basic/tests/compact-basic.spec.ts @@ -563,7 +563,10 @@ describe('pressure measurement and retention', () => { const result = await compactIfNeeded(compact, session) expect(result).not.toBeNull() expect(prefix).toHaveLength(1) - expect(session.events.some(event => event.type === 'context/message')).toBe(false) + // The routed request prefix must not reach the surface as its own message + // (the compaction summary itself is an expected plugin-sourced checkpoint). + expect(session.events.some(event => event.type === 'user/message' + && event.data.content.some(block => block.type === 'text' && block.text.includes('p'.repeat(600))))).toBe(false) }) it('uses the latest logged request envelope without an AgentOptions override', async () => { @@ -959,7 +962,7 @@ describe('compaction region transaction', () => { const compact = service() const session = conversation(2) compact.mutateDuringSummary = () => { - session.append('context/message', { + session.append('user/message', { content: [{ type: 'text', text: 'concurrent surface mutation' }], source: { kind: 'plugin', plugin: 'test' }, }, { surfaceOp: 'append' }) diff --git a/packages/compact/compact-basic/tests/compact-loop-repro.spec.ts b/packages/compact/compact-basic/tests/compact-loop-repro.spec.ts index f9f61e4096..83c18f78b4 100644 --- a/packages/compact/compact-basic/tests/compact-loop-repro.spec.ts +++ b/packages/compact/compact-basic/tests/compact-loop-repro.spec.ts @@ -197,7 +197,7 @@ describe('CBR-001: a real-loop checkpoint is a valid boundary on both sides', () provider: 'unconfigured-agent-fallback', model: 'unconfigured-agent-fallback', }) - agent.send([{ type: 'text', text: 'do a routed multi-step task' }]) + agent.followup([{ type: 'text', text: 'do a routed multi-step task' }]) await waitForIdle(ctx, agent) expect(agent.session.requestHeader()?.config.model).toBe('mock') @@ -215,7 +215,7 @@ describe('CBR-001: a real-loop checkpoint is a valid boundary on both sides', () const { ctx } = await harness(8) try { const agent = ctx.agentLoop.create(SessionId('post-step-order'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'do tool work' }]) + agent.followup([{ type: 'text', text: 'do tool work' }]) await waitForIdle(ctx, agent) const events = [...agent.session.events] @@ -241,7 +241,7 @@ describe('CBR-001: a real-loop checkpoint is a valid boundary on both sides', () const { ctx } = await harness(8) try { const agent = ctx.agentLoop.create(SessionId('repro'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'do a long multi-step task' }]) + agent.followup([{ type: 'text', text: 'do a long multi-step task' }]) await waitForIdle(ctx, agent) const events = [...agent.session.events] @@ -297,7 +297,7 @@ describe('context-overflow recovery across the real loop and compact-basic', () }) seedOverflowHistory(agent) - agent.send([{ type: 'text', text: 'continue from history' }]) + agent.followup([{ type: 'text', text: 'continue from history' }]) await agent.whenIdle() expect(adapter.conversationRequests).toHaveLength(2) @@ -360,7 +360,7 @@ describe('context-overflow recovery across the real loop and compact-basic', () try { const agent = ctx.agentLoop.create(SessionId('alternating-recovery'), { provider: 'mock', model: 'mock' }) seedOverflowHistory(agent) - agent.send([{ type: 'text', text: 'continue from history' }]) + agent.followup([{ type: 'text', text: 'continue from history' }]) await agent.whenIdle() expect(adapter.conversationRequests).toHaveLength(3) diff --git a/packages/compact/compact/README.md b/packages/compact/compact/README.md index 03b91d653e..ff47ef3b19 100644 --- a/packages/compact/compact/README.md +++ b/packages/compact/compact/README.md @@ -33,7 +33,7 @@ The private per-session cache is keyed by `session.surface.replaceGeneration` an ## Surface contract -`SurfaceEventType` is a closed union — only `user/message`, `assistant/message`, `tool/result`, `context/message`, and `steering/message` may carry `surfaceOp`. A `compact/*` event therefore **cannot** appear on the surface. A successful compaction instead: +`SurfaceEventType` is a closed union — only `user/message`, `assistant/message`, `tool/result`, and `steering/message` may carry `surfaceOp`. A `compact/*` event therefore **cannot** appear on the surface. A successful compaction instead: 1. appends `compact/start` (log-only) — acquires the lock, 2. summarizes the range, diff --git a/packages/compact/compact/tests/tool-pairing.spec.ts b/packages/compact/compact/tests/tool-pairing.spec.ts index 5f48e7f99f..3de0473d57 100644 --- a/packages/compact/compact/tests/tool-pairing.spec.ts +++ b/packages/compact/compact/tests/tool-pairing.spec.ts @@ -96,23 +96,23 @@ describe('tool-pairing boundaries', () => { content: [{ type: 'tool-call', id: CallId('c1'), name: 'bash', arguments: '{}' }], provenance: { provider: 'mock', model: 'mock' }, }, SURFACE) - midStep.append('context/message', { + midStep.append('user/message', { content: [{ type: 'text', text: 'background update' }], source: { kind: 'plugin', plugin: 'test' }, }, SURFACE) midStep.append('tool/result', { turn: 1, step: 1, callId: CallId('c1'), content: [], isError: false, }, SURFACE) - expect(before(midStep, 'context/message')).toBe(false) - expect(after(midStep, 'context/message')).toBe(false) + expect(before(midStep, 'user/message')).toBe(false) + expect(after(midStep, 'user/message')).toBe(false) const free = new Session(SessionId('neutral-free')) - free.append('context/message', { + free.append('user/message', { content: [{ type: 'text', text: 'idle injection' }], source: { kind: 'user' }, }, SURFACE) - expect(before(free, 'context/message')).toBe(true) - expect(after(free, 'context/message')).toBe(true) + expect(before(free, 'user/message')).toBe(true) + expect(after(free, 'user/message')).toBe(true) }) }) diff --git a/packages/context/session-reference/README.md b/packages/context/session-reference/README.md index b3a4b2013d..4fca9a9977 100644 --- a/packages/context/session-reference/README.md +++ b/packages/context/session-reference/README.md @@ -5,7 +5,7 @@ ## Public API - `listCandidates(agent, query?, limit?)` lists sessions other than `agent.id`, filters case-insensitively by id or cwd, and ranks same-cwd, cwd-less, then other-cwd records while preserving `listSessions()` creation order within each group. Each selected candidate uses its latest log-backed title as the mention label and falls back to the session id; titles and message bodies are not searched. -- `prepare(agent, content, references, signal?)` preserves first-mention order, deduplicates ids, rejects self-reference and more than the configured distinct-source limit, reads every source in parallel, and returns detached content plus zero or one aggregated `HookContext`. Any invalid reference, failed read, cancellation, or budget failure rejects before the host calls `send()` or `steer()`. +- `prepare(agent, content, references, signal?)` preserves first-mention order, deduplicates ids, rejects self-reference and more than the configured distinct-source limit, reads every source in parallel, and returns detached content plus zero or one aggregated `HookContext`. Any invalid reference, failed read, cancellation, or budget failure rejects before the host calls `followup()` or `steer()`. - `encodeSessionReferenceUri()` and `decodeSessionReferenceUri()` implement `dsh-session:<base64url(JSON.stringify(sessionId))>` so every JavaScript string id round-trips exactly. `formatSessionReferenceMention()` emits `@[label](uri)`, and `parseSessionReferenceText()` replaces Markdown mentions or bare canonical URIs with readable `@label` text while returning structured references. Explicit Markdown mentions reject every malformed URI; bare text is considered a reference only when a non-empty base64url-shaped payload follows the scheme, and a matching noncanonical candidate still fails. Empty or punctuation-only scheme mentions remain ordinary discussion text. ## Snapshot semantics diff --git a/packages/context/session-reference/src/projection.ts b/packages/context/session-reference/src/projection.ts index bbb2a2c739..dea29b38ee 100644 --- a/packages/context/session-reference/src/projection.ts +++ b/packages/context/session-reference/src/projection.ts @@ -57,7 +57,6 @@ function projectSessionConversation(snapshot: SessionSurfaceSnapshot): Projected break } case 'tool/result': - case 'context/message': break /* v8 ignore next 2 -- SurfaceEventType is closed and every variant is handled above. */ default: diff --git a/packages/context/session-reference/tests/session-reference.spec.ts b/packages/context/session-reference/tests/session-reference.spec.ts index 2470ae8d93..937535b042 100644 --- a/packages/context/session-reference/tests/session-reference.spec.ts +++ b/packages/context/session-reference/tests/session-reference.spec.ts @@ -75,7 +75,7 @@ function appendConversation(session: Session): void { { surfaceOp: 'append' }, ) session.append( - 'context/message', + 'user/message', { content: [{ type: 'text', text: 'workspace secret' }], source: { kind: 'plugin', plugin: 'workspace' } }, { surfaceOp: 'append' }, ) diff --git a/packages/context/time-context/README.md b/packages/context/time-context/README.md index 2327da81b2..f4938982a1 100644 --- a/packages/context/time-context/README.md +++ b/packages/context/time-context/README.md @@ -18,9 +18,9 @@ When `timeZone` is omitted, the plugin resolves the Node process's system zone o ## Timing semantics -The plugin prepends an `agent/pre-step` listener. When an injection is due, it appends one `context/message` through `agent.inject()` before `step/start` and ordinary automatic compaction, with source `{ kind: 'plugin', plugin: 'time-context' }`. A suppressed attempt appends nothing. +The plugin prepends an `agent/pre-step` listener. When an injection is due, it appends one injected `user/message` through `agent.inject()` before `step/start` and ordinary automatic compaction, with source `{ kind: 'plugin', plugin: 'time-context' }`. A suppressed attempt appends nothing. -Positive-interval scheduling scans the raw durable session events for the latest `context/message` with that source, including a reading shadowed by compaction. The schedule therefore applies across turns and resumed processes without process-local cache state. It reduces append frequency and history growth but never removes an existing reading, and sessions schedule independently. +Positive-interval scheduling scans the raw durable session events for the latest `user/message` with that source, including a reading shadowed by compaction. The schedule therefore applies across turns and resumed processes without process-local cache state. It reduces append frequency and history growth but never removes an existing reading, and sessions schedule independently. Step 1 measures from the latest preceding model-visible message, including the prompt that opened the turn. Later steps measure from the preceding time-context event in the same turn. Both baselines use durable session-event timestamps; backward wall-clock movement clamps elapsed time to zero. A missing first-step baseline, or a later step with no earlier same-turn reading because interval suppression skipped it, reports `unavailable`. diff --git a/packages/context/time-context/src/index.ts b/packages/context/time-context/src/index.ts index 96ea7165af..fcf9e36efc 100644 --- a/packages/context/time-context/src/index.ts +++ b/packages/context/time-context/src/index.ts @@ -64,7 +64,6 @@ function precedingMessageTime(agent: Agent): number | undefined { case 'user/message': case 'assistant/message': case 'tool/result': - case 'context/message': case 'steering/message': return event.time default: @@ -79,7 +78,7 @@ function precedingMessageTime(agent: Agent): number | undefined { function precedingStepContextTime(agent: Agent, turn: number): number | undefined { for (const event of [...agent.session.events].reverse()) { if (event.type === 'turn/start' && event.data.turn === turn) return undefined - if (event.type === 'context/message' + if (event.type === 'user/message' && event.data.source.kind === 'plugin' && event.data.source.plugin === name) { return event.time @@ -91,7 +90,7 @@ function precedingStepContextTime(agent: Agent, turn: number): number | undefine /** Find this plugin's latest durable injection, including a shadowed surface event. */ function latestInjectionTime(agent: Agent): number | undefined { for (const event of [...agent.session.events].reverse()) { - if (event.type === 'context/message' + if (event.type === 'user/message' && event.data.source.kind === 'plugin' && event.data.source.plugin === name) { return event.time diff --git a/packages/context/time-context/src/invariant.ts b/packages/context/time-context/src/invariant.ts index 45fdb48cba..aa8f0418dd 100644 --- a/packages/context/time-context/src/invariant.ts +++ b/packages/context/time-context/src/invariant.ts @@ -48,7 +48,7 @@ function preparationPosition(history: readonly SessionEvent[], fail: InvariantFa /** Validate one plugin-attributed time reading against its session position and timestamp. */ function validateReading( history: readonly SessionEvent[], - event: SessionEvent<'context/message'>, + event: SessionEvent<'user/message'>, fail: InvariantFailure, ): void { const [block] = event.data.content @@ -84,7 +84,7 @@ function validateReading( /** Validate all package-owned readings already present in one session. */ function validateSession(session: Session, fail: InvariantFailure): void { for (const [index, event] of session.events.entries()) { - if (event.type !== 'context/message' + if (event.type !== 'user/message' || event.data.source.kind !== 'plugin' || event.data.source.plugin !== SOURCE_NAME) continue validateReading(session.events.slice(0, index), event, fail) @@ -97,7 +97,7 @@ const install: InvariantInstaller = Object.assign((ctx: Context, fail: Invariant ctx.on('internal/dispatch', (_mode, eventName, args) => { if (eventName !== 'session/event') return const [session, event] = args as [Session, SessionEvent] - if (event.type !== 'context/message' + if (event.type !== 'user/message' || event.data.source.kind !== 'plugin' || event.data.source.plugin !== SOURCE_NAME) return validateReading(session.events, event, fail) diff --git a/packages/context/time-context/tests/invariant.spec.ts b/packages/context/time-context/tests/invariant.spec.ts index cd65f1aa3d..855303b295 100644 --- a/packages/context/time-context/tests/invariant.spec.ts +++ b/packages/context/time-context/tests/invariant.spec.ts @@ -17,7 +17,7 @@ async function setup(): Promise<Context> { function event(text: string, time = SECOND + 456, content?: unknown[]): SessionEvent { return { - type: 'context/message', + type: 'user/message', seq: 0, time, data: { @@ -56,7 +56,7 @@ function preparing(turn: number, step: number): Session { } function appendReading(session: Session, text: string): void { - session.append('context/message', { + session.append('user/message', { content: [{ type: 'text', text }], source: { kind: 'plugin', plugin: 'time-context' }, }, { surfaceOp: 'append' }) @@ -162,7 +162,7 @@ describe('time-context invariants', () => { it('ignores context messages owned by another package', async () => { const ctx = await setup() - const other = event('unrelated') as SessionEvent<'context/message'> + const other = event('unrelated') as SessionEvent<'user/message'> other.data.source = { kind: 'plugin', plugin: 'other' } expect(() => { ctx.emit('session/event', preparing(1, 1), other) }).not.toThrow() other.data.source = { kind: 'user' } diff --git a/packages/context/time-context/tests/time-context.e2e.ts b/packages/context/time-context/tests/time-context.e2e.ts index 2a0c06fe51..02704d3eba 100644 --- a/packages/context/time-context/tests/time-context.e2e.ts +++ b/packages/context/time-context/tests/time-context.e2e.ts @@ -48,7 +48,8 @@ describe('time-context through a real headless cordis.yml', () => { expect(stderr).not.toContain('UNHANDLED') expect(events.filter(event => event.type === 'turn/end')).toHaveLength(2) - const contexts = events.filter(event => event.type === 'context/message') + const contexts = events.filter( + (event): event is SessionEvent<'user/message'> => event.type === 'user/message' && event.data.source.kind === 'plugin') const starts = events.filter(event => event.type === 'step/start') expect(contexts).toHaveLength(2) expect(starts).toHaveLength(2) diff --git a/packages/context/time-context/tests/time-context.spec.ts b/packages/context/time-context/tests/time-context.spec.ts index a42ed71454..424363d4b1 100644 --- a/packages/context/time-context/tests/time-context.spec.ts +++ b/packages/context/time-context/tests/time-context.spec.ts @@ -3,8 +3,8 @@ import { Context } from 'cordis' import Loader from '@cordisjs/plugin-loader' import { CallId, LlmAdapter } from '@deepseek-ai/dsh-llm' import type { GenerateOptions, StreamChunk } from '@deepseek-ai/dsh-llm' -import { Session, SessionId } from '@deepseek-ai/dsh-session' -import AgentRegistry, { agentEvents, type Agent } from '@deepseek-ai/dsh-agent' +import { Session, SessionId, type SessionEvent } from '@deepseek-ai/dsh-session' +import AgentRegistry, { agentEvents, AgentMessageId, type Agent } from '@deepseek-ai/dsh-agent' import { defineContentToolFixture } from '@deepseek-ai/dsh-tools' import AgentLoop from '@deepseek-ai/dsh-agent-loop' import { mountAgentLoopTestDependencies } from '@deepseek-ai/dsh-agent-loop-testkit' @@ -42,14 +42,17 @@ function sessionAgent(session: Session, id = 'agent'): Agent { session, status: 'running', ctx: new Context(), - send() {}, - steer() {}, + followup: () => AgentMessageId('stub'), + queue: () => AgentMessageId('stub'), + steer: () => AgentMessageId('stub'), inject(content, options) { - session.append('context/message', { + session.append('user/message', { content, source: options?.source ?? { kind: 'user' }, }, { surfaceOp: 'append' }) + return AgentMessageId('stub') }, + send: () => AgentMessageId('stub'), cancel() {}, whenIdle: () => Promise.resolve(), } @@ -66,7 +69,7 @@ function openMessageTurn(session: Session, turn: number): void { function contextTexts(session: Session): string[] { const texts: string[] = [] for (const event of session.events) { - if (event.type === 'context/message' + if (event.type === 'user/message' && event.data.source.kind === 'plugin' && event.data.source.plugin === 'time-context') { texts.push(event.data.content.find(block => block.type === 'text')?.text ?? '') @@ -151,8 +154,8 @@ describe('durable step context', () => { + 'Elapsed since the preceding model-visible message: 1d 1h 1m 1s.', ]) const event = session.events.at(-1) - expect(event?.type).toBe('context/message') - if (event?.type !== 'context/message') throw new Error('missing time context') + expect(event?.type).toBe('user/message') + if (event?.type !== 'user/message') throw new Error('missing time context') expect(event.data.source).toEqual({ kind: 'plugin', plugin: 'time-context' }) expect(event.surfaceOp).toBe('append') }) @@ -230,10 +233,10 @@ describe('durable step context', () => { const original = new Session(SessionId('seed-source')) openMessageTurn(original, 1) await fire(ctx, sessionAgent(original), 1, 1) - const user = original.events.find(event => event.type === 'user/message') - const reading = original.events.find(event => event.type === 'context/message') + const user = original.events.find(event => event.type === 'user/message' && event.data.source.kind === 'user') + const reading = original.events.find(event => event.type === 'user/message' && event.data.source.kind === 'plugin') if (user === undefined || reading === undefined) throw new Error('missing source surface events') - original.append('context/message', { + original.append('user/message', { content: [{ type: 'text', text: 'compacted history' }], source: { kind: 'plugin', plugin: 'compact-basic' }, }, { @@ -292,7 +295,7 @@ describe('durable step context', () => { openMessageTurn(session, 1) let ordinarySawContext = false ctx.on('agent/pre-step', (subject) => { - ordinarySawContext = subject.session.events.some(event => event.type === 'context/message') + ordinarySawContext = subject.session.events.some(event => event.type === 'user/message') }) await fire(ctx, agent, 1, 1) @@ -371,7 +374,7 @@ describe('real agent-loop request history', () => { }) const agent = ctx.agentLoop.create(SessionId(`late-${mode}`), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'start' }]) + agent.followup([{ type: 'text', text: 'start' }]) await agent.whenIdle() expect(laterSawReading).toBe(true) @@ -397,11 +400,12 @@ describe('real agent-loop request history', () => { })) const agent = ctx.agentLoop.create(SessionId('loop'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'start' }]) + agent.followup([{ type: 'text', text: 'start' }]) await agent.whenIdle() expect(adapter.requests).toHaveLength(2) - const contexts = agent.session.events.filter(event => event.type === 'context/message') + const contexts = agent.session.events.filter( + (event): event is SessionEvent<'user/message'> => event.type === 'user/message' && event.data.source.kind === 'plugin') const starts = agent.session.events.filter(event => event.type === 'step/start') expect(contexts).toHaveLength(adapter.requests.length) expect(starts).toHaveLength(adapter.requests.length) diff --git a/packages/context/workspace-context/README.md b/packages/context/workspace-context/README.md index a7245df91f..67ab9b4245 100644 --- a/packages/context/workspace-context/README.md +++ b/packages/context/workspace-context/README.md @@ -28,7 +28,7 @@ Instructions from: AGENTS.md </system-reminder> ``` -Newly reached scopes use a durable raw `context/message`: +Newly reached scopes use a durable injected `user/message` (plugin source): ```md <system-reminder> @@ -42,11 +42,11 @@ These instructions apply to work under `packages/app`. Use them as guidance when A same-file edit starts with `Updated instructions from: <path>` and says to use the new content instead of the previously loaded content. When a candidate disappears or becomes a per-directory duplicate of an earlier candidate, the message is `Instructions removed: <path>` followed by `The previously loaded instructions from this file no longer apply.` Literal `</system-reminder>` text inside an instruction file is escaped so file content cannot close the plugin-owned frame. -The plugin owns the complete `<system-reminder>` framing, and every `context/message` (from this plugin or any other) reaches the model verbatim as a user-role message with no wrapping. +The plugin owns the complete `<system-reminder>` framing, and every injected `user/message` (from this plugin or any other) reaches the model verbatim as a user-role message with no wrapping. ## State And Refresh -Model-visible text contains no hidden state markers. Each dynamic context event instead carries JSON metadata with a versioned list of `{ action, scope, path, digest? }` changes. On every relevant tool touch, the plugin reconstructs loaded state from its visible session events and overlays a short in-memory pending window for context present on the immutable top-level `tools/result` but not yet appended by the loop. A matching durable `context/message` confirms the pending transition. If the owning `step/end` arrives before a matching context reaches the log, the plugin clears the pending transition and its version fast path so the next successful touch can load it again. Nested Code Mode results stage pending changes under the outer execution token for same-run duplicate suppression; the outer result rolls that state back and recommits only contexts that survived outer policy. +Model-visible text contains no hidden state markers. Each dynamic context event instead carries JSON metadata with a versioned list of `{ action, scope, path, digest? }` changes. On every relevant tool touch, the plugin reconstructs loaded state from its visible session events and overlays a short in-memory pending window for context present on the immutable top-level `tools/result` but not yet appended by the loop. A matching durable `user/message` confirms the pending transition. If the owning `step/end` arrives before a matching context reaches the log, the plugin clears the pending transition and its version fast path so the next successful touch can load it again. Nested Code Mode results stage pending changes under the outer execution token for same-run duplicate suppression; the outer result rolls that state back and recommits only contexts that survived outer policy. An unchanged path and SHA-1 content digest is not injected again. A per-session, per-scope metadata cache stores only `{ path, version, digest, trimmedDigest }`: when the provider's opaque `FsVersion` and the effective visible state both match, reconciliation skips the content read; a changed version triggers a bounded read and SHA-1 confirmation before any model-visible update. The `trimmedDigest` — SHA-1 over the whitespace-trimmed content — is the per-directory duplicate key, so an unchanged file can still be removed when an earlier candidate converges on its content. Resume works because SHA-1 state is persisted in the session log, while an empty in-memory version cache merely causes one confirming read. Compaction re-arms a scope after its context event leaves the visible surface even when the cached version is unchanged. A removal is a tombstone, so a later candidate reappearance is loaded again. Only model-visible changes actually rendered within the byte budget enter metadata, pending state, and the version cache; an omitted change remains eligible for a later touch, while a same-digest version refresh updates metadata only. @@ -111,7 +111,7 @@ Prefix-stable within one loop instance because the baseline is frozen. A new or #### What the model sees -After a successful first-party filesystem call reaches a deeper directory, the next request includes one retained raw `context/message` with the newly applicable instruction file. +After a successful first-party filesystem call reaches a deeper directory, the next request includes one retained injected `user/message` with the newly applicable instruction file. ##### Additional instruction template diff --git a/packages/context/workspace-context/src/state.ts b/packages/context/workspace-context/src/state.ts index 66b70f639d..61db3f527b 100644 --- a/packages/context/workspace-context/src/state.ts +++ b/packages/context/workspace-context/src/state.ts @@ -145,7 +145,7 @@ function visibleInstructionChanges( const visibleSeqs = new Set(agent.session.surface.nodes) const visible = new Map<string, WorkspaceInstructionChange>() for (const [seq, event] of agent.session.events.entries()) { - if (event.type !== 'context/message' || !isWorkspaceContextSource(event.data.source)) continue + if (event.type !== 'user/message' || !isWorkspaceContextSource(event.data.source)) continue const changes = workspaceInstructionChanges(event.data.meta) for (const change of changes) { const waiting = pending.get(change.scope) @@ -281,7 +281,7 @@ export function observeInstructionSessionEvent( if (pending === undefined) return switch (event.type) { - case 'context/message': { + case 'user/message': { if (!isWorkspaceContextSource(event.data.source)) return for (const change of workspaceInstructionChanges(event.data.meta)) { const waiting = pending.get(change.scope) diff --git a/packages/context/workspace-context/tests/workspace-context.e2e.ts b/packages/context/workspace-context/tests/workspace-context.e2e.ts index 9341eb33d0..fbeacb5496 100644 --- a/packages/context/workspace-context/tests/workspace-context.e2e.ts +++ b/packages/context/workspace-context/tests/workspace-context.e2e.ts @@ -78,7 +78,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('workspace context e2e: real mode it('obeys a probe instruction loaded from the workspace', async () => { const live = await harness() - live.agent.send([{ type: 'text', text: 'Workspace context handshake?' }]) + live.agent.followup([{ type: 'text', text: 'Workspace context handshake?' }]) await waitForIdle(live.ctx, live.agent) expect(finalText([...live.agent.session.events])).toContain(PROBE) @@ -90,7 +90,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('workspace context e2e: real mode await writeFile(join(workdir!, 'pkg/AGENTS.md'), `If the user asks for the nested instruction handshake, reply with exactly this string and nothing else: ${NESTED_PROBE}.\n`) await writeFile(join(workdir!, 'pkg/deep/file.txt'), 'This file exists only to trigger nested workspace instructions.\n') - live.agent.send([{ type: 'text', text: 'Use the read tool to inspect pkg/deep/file.txt. After reading it, answer: nested instruction handshake?' }]) + live.agent.followup([{ type: 'text', text: 'Use the read tool to inspect pkg/deep/file.txt. After reading it, answer: nested instruction handshake?' }]) await waitForIdle(live.ctx, live.agent) expect(finalText([...live.agent.session.events])).toContain(NESTED_PROBE) @@ -99,23 +99,23 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('workspace context e2e: real mode it('appends changed baseline instructions after a real file-tool touch without rewriting the frozen prefix', async () => { const live = await harness() await writeFile(join(workdir!, 'trigger.txt'), 'This file triggers workspace instruction reconciliation.\n') - live.agent.send([{ type: 'text', text: 'Workspace context handshake?' }]) + live.agent.followup([{ type: 'text', text: 'Workspace context handshake?' }]) await waitForIdle(live.ctx, live.agent) await writeFile(join(workdir!, 'AGENTS.md'), `The old workspace handshake no longer applies. If the user asks for the updated workspace context handshake, reply with exactly this string and nothing else: ${UPDATED_PROBE}.\n`) - live.agent.send([{ type: 'text', text: 'You must use the read tool to inspect trigger.txt. After reading it, answer: updated workspace context handshake?' }]) + live.agent.followup([{ type: 'text', text: 'You must use the read tool to inspect trigger.txt. After reading it, answer: updated workspace context handshake?' }]) await waitForIdle(live.ctx, live.agent) const events = [...live.agent.session.events] - const update = events.find(event => event.type === 'context/message' + const update = events.find(event => event.type === 'user/message' && typeof event.data.meta === 'object' && event.data.meta !== null && !Array.isArray(event.data.meta) && event.data.meta.kind === 'workspace-instructions') - expect(update?.type === 'context/message' && update.data.meta).toMatchObject({ + expect(update?.type === 'user/message' && update.data.meta).toMatchObject({ changes: [{ action: 'replace', scope: candidateScopeKey('.', 'AGENTS.md'), path: 'AGENTS.md' }], }) - const updateText = update?.type === 'context/message' + const updateText = update?.type === 'user/message' ? update.data.content.filter(block => block.type === 'text').map(block => block.text).join('') : '' expect(updateText).toContain('Updated instructions from: AGENTS.md') diff --git a/packages/context/workspace-context/tests/workspace-context.spec.ts b/packages/context/workspace-context/tests/workspace-context.spec.ts index 475db4b479..c8c33f3a4b 100644 --- a/packages/context/workspace-context/tests/workspace-context.spec.ts +++ b/packages/context/workspace-context/tests/workspace-context.spec.ts @@ -7,7 +7,7 @@ import Loader from '@cordisjs/plugin-loader' import * as workspaceContext from '@deepseek-ai/dsh-workspace-context' import LlmService, { CallId, type Message, type StreamChunk } from '@deepseek-ai/dsh-llm' import SessionStore, { Session, SessionId, SESSION_FORMAT_VERSION, type SessionEvent } from '@deepseek-ai/dsh-session' -import AgentRegistry, { type Agent, type HookContext } from '@deepseek-ai/dsh-agent' +import AgentRegistry, { AgentMessageId, type Agent, type HookContext } from '@deepseek-ai/dsh-agent' import AgentLoop from '@deepseek-ai/dsh-agent-loop' import { FileSystem, FsTargetKey, FsVersion } from '@deepseek-ai/dsh-fs' import type { @@ -177,15 +177,18 @@ function stubAgent(cwd?: string, seed: SessionEvent[] = []): Agent { options: {}, session, status: 'idle', - send() {}, - steer() {}, + followup: () => AgentMessageId('stub'), + queue: () => AgentMessageId('stub'), + steer: () => AgentMessageId('stub'), inject(content, options) { - session.append('context/message', { + session.append('user/message', { content, source: options?.source ?? { kind: 'user' }, ...options?.meta !== undefined ? { meta: options.meta } : {}, }, { surfaceOp: 'append' }) + return AgentMessageId('stub') }, + send: () => AgentMessageId('stub'), cancel() {}, whenIdle: () => Promise.resolve(), } @@ -222,7 +225,7 @@ function workspaceChangeContext(scope: string, digest: string): HookContext { function appendAdditionalContexts(agent: Agent, result: { additionalContexts?: HookContext[] }): number | undefined { let lastSeq: number | undefined for (const context of result.additionalContexts ?? []) { - lastSeq = agent.session.append('context/message', { + lastSeq = agent.session.append('user/message', { content: context.content, source: context.source, ...context.meta !== undefined ? { meta: context.meta } : {}, @@ -976,7 +979,7 @@ describe('workspace context request injection', () => { const second = await composeBaselinePrefix(ctx, agent) expect(second).toEqual(first) - expect(agent.session.events.filter(event => event.type === 'context/message')).toHaveLength(0) + expect(agent.session.events.filter(event => event.type === 'user/message' && event.data.source.kind !== 'user')).toHaveLength(0) expect(derivedText(agent)).toContain('repo rule') } finally { await rm(root, { recursive: true, force: true }) @@ -1148,7 +1151,7 @@ describe('workspace context request injection', () => { await composeBaselinePrefix(ctx, agent) - expect(agent.session.events.filter(event => event.type === 'context/message')).toHaveLength(0) + expect(agent.session.events.filter(event => event.type === 'user/message' && event.data.source.kind !== 'user')).toHaveLength(0) expect(derivedText(agent)).not.toContain('workspace-context:') } finally { await rm(root, { recursive: true, force: true }) @@ -1714,14 +1717,14 @@ describe('dynamic nested workspace context injection', () => { }, })) - agent.send([{ type: 'text', text: 'read and abort' }]) + agent.followup([{ type: 'text', text: 'read and abort' }]) await agent.whenIdle() - expect(agent.session.events.filter(event => event.type === 'context/message')).toHaveLength(1) + expect(agent.session.events.filter(event => event.type === 'user/message' && event.data.source.kind !== 'user')).toHaveLength(1) - agent.send([{ type: 'text', text: 'retry the read' }]) + agent.followup([{ type: 'text', text: 'retry the read' }]) await agent.whenIdle() - const contexts = agent.session.events.filter(event => event.type === 'context/message') + const contexts = agent.session.events.filter(event => event.type === 'user/message' && event.data.source.kind !== 'user') // The aborted batch drained its accepted context before step close, so the // retry sees durable history without producing a duplicate instruction. expect(contexts).toHaveLength(1) @@ -2496,10 +2499,7 @@ describe('dynamic nested workspace context injection', () => { agent, }) appendAdditionalContexts(agent, first) - const resumed = { - ...agent, - session: new Session(agent.session.id, [...agent.session.events], agent.session.header), - } + const resumed = stubAgent(root, [...agent.session.events]) const afterResume = await ctx.tools.execute({ signal: testToolSignal, @@ -2537,11 +2537,11 @@ describe('dynamic nested workspace context injection', () => { await composeBaselinePrefix(ctx, resumed) - const update = resumed.session.events.findLast(event => event.type === 'context/message') - expect(update?.type === 'context/message' && update.data.meta).toMatchObject({ + const update = resumed.session.events.findLast(event => event.type === 'user/message' && event.data.source.kind !== 'user') + expect(update?.type === 'user/message' && update.data.meta).toMatchObject({ changes: [{ action: 'replace', scope: sk('pkg', 'AGENTS.md'), path: join('pkg', 'AGENTS.md') }], }) - expect(update?.type === 'context/message' && blocksText(update.data.content)).toContain('new nested rule after resume') + expect(update?.type === 'user/message' && blocksText(update.data.content)).toContain('new nested rule after resume') } finally { await rm(root, { recursive: true, force: true }) await rm(home, { recursive: true, force: true }) @@ -2687,7 +2687,7 @@ describe('dynamic nested workspace context injection', () => { const ctx = new Context() await mountFileToolsAndWorkspaceContext(ctx, { dshHome: home, maxBytes: 65536 }) const agent = stubAgent(root) - agent.session.append('context/message', { + agent.session.append('user/message', { content: [ { type: 'reasoning', text: 'Additional instructions from: pkg/AGENTS.md' }, { type: 'text', text: 'Updated instructions from: pkg/AGENTS.md' }, @@ -2704,12 +2704,12 @@ describe('dynamic nested workspace context injection', () => { ], }, }, { surfaceOp: 'append' }) - agent.session.append('context/message', { + agent.session.append('user/message', { content: [{ type: 'text', text: 'stale metadata version' }], source: { kind: 'plugin', plugin: 'workspace-context' }, meta: { kind: 'workspace-instructions', version: 0, changes: [] }, }, { surfaceOp: 'append' }) - agent.session.append('context/message', { + agent.session.append('user/message', { content: [{ type: 'text', text: 'foreign plugin context' }], source: { kind: 'plugin', plugin: 'other' }, meta: { @@ -3237,14 +3237,14 @@ describe('workspace context pending state', () => { path: join('pkg', 'AGENTS.md'), version: FsVersion('v1'), digest: 'one', trimmedDigest: 'one', }]])) - const unrelated = agent.session.append('context/message', { + const unrelated = agent.session.append('user/message', { content: [], source: { kind: 'plugin', plugin: 'other' }, }, { surfaceOp: 'append' }) observeInstructionSessionEvent(agent.session, unrelated, pending, versions) expect(pending.get(agent.session)?.has('pkg')).toBe(true) const otherContext = workspaceChangeContext('other', 'other') - const otherWorkspaceEvent = agent.session.append('context/message', { + const otherWorkspaceEvent = agent.session.append('user/message', { content: otherContext.content, source: otherContext.source, ...otherContext.meta !== undefined ? { meta: otherContext.meta } : {}, @@ -3253,7 +3253,7 @@ describe('workspace context pending state', () => { expect(pending.get(agent.session)?.has('pkg')).toBe(true) const context = workspaceChangeContext('pkg', 'one') - const confirmed = agent.session.append('context/message', { + const confirmed = agent.session.append('user/message', { content: context.content, source: context.source, ...context.meta !== undefined ? { meta: context.meta } : {}, diff --git a/packages/cordis/tool-cordis/src/api-catalog.ts b/packages/cordis/tool-cordis/src/api-catalog.ts index 6939ec9927..c3e4e1858b 100644 --- a/packages/cordis/tool-cordis/src/api-catalog.ts +++ b/packages/cordis/tool-cordis/src/api-catalog.ts @@ -885,6 +885,27 @@ export const EVENT_API: readonly EventApiEntry[] = [ jsDoc: '/**\n * A step or turn errored. The loop reports a failure here (plus the logger)\n * even when the error has no in-turn position for a session `error` event.\n * @param agent - the agent whose turn errored.\n * @param turn - the turn in which the failure surfaced.\n * @param step - the step at which the failure surfaced.\n * @param error - the failure, verbatim.\n * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent.\n * @mode emit\n */', summary: 'A step or turn errored.', }, + { + name: 'agent/inbox/dequeue', + mode: 'emit', + signature: '\'agent/inbox/dequeue\'(this: Scoped<Agent>, agent: Agent, message: AgentMessage): void', + jsDoc: '/**\n * The driver claimed one item out of the inbox: a queued item at a turn\n * boundary, or steering drained between steps. Fires after the item leaves\n * its FIFO and before it becomes a durable message.\n * @param agent - the agent whose inbox item was claimed.\n * @param message - the claimed message (matching the `id` from its `agent/inbox/enqueue`).\n * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent.\n * @mode emit\n */', + summary: 'The driver claimed one item out of the inbox: a queued item at a turn boundary, or steering drained between steps.', + }, + { + name: 'agent/inbox/discard', + mode: 'emit', + signature: '\'agent/inbox/discard\'(this: Scoped<Agent>, agent: Agent, messages: AgentMessage[]): void', + jsDoc: '/**\n * Pending inbox items were dropped without delivering them, so every\n * enqueued id receives exactly one terminal `agent/inbox/dequeue` OR\n * `agent/inbox/discard`. Emitters: `cancel()` without `keepInbox` (after\n * `agent/cancel-requested`, before the abort); a terminal `agent/turn-stop`\n * dropping pending steering (in-turn and on the post-turn late-steering\n * drain); and disposal of any still-pending items (before\n * `agent/status(\'disposed\')`). Fires once per drop with every dropped item.\n * @param agent - the agent whose inbox items were dropped.\n * @param messages - the discarded messages in FIFO order (queued then steering); never empty.\n * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent.\n * @mode emit\n */', + summary: 'Pending inbox items were dropped without delivering them, so every enqueued id receives exactly one terminal `agent/inbox/dequeue` OR `agent/inbox/discard`.', + }, + { + name: 'agent/inbox/enqueue', + mode: 'emit', + signature: '\'agent/inbox/enqueue\'(this: Scoped<Agent>, agent: Agent, message: AgentMessage): void', + jsDoc: '/**\n * A detached, frozen item entered the agent\'s inbox (queued or steering\n * FIFO). Source defaults are already applied, so `message` holds the exact\n * accepted values. This is the enqueue-time live signal; the durable record\n * is the eventual `user/message`/`steering/message`. Injection through\n * `agent.inject()` or equivalent `send()` routing bypasses the FIFOs\n * and does not emit this.\n * @param agent - the agent whose inbox received the item.\n * @param message - the accepted message (its returned `id`, content, source, contexts, steering, and wakeup facts).\n * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent.\n * @mode emit\n */', + summary: 'A detached, frozen item entered the agent\'s inbox (queued or steering FIFO).', + }, { name: 'agent/post-step', mode: 'serial', @@ -906,13 +927,6 @@ export const EVENT_API: readonly EventApiEntry[] = [ jsDoc: '/**\n * Allow, rewrite, or block one claimed prompt before it becomes a user\n * message. Call `next()` for the unchanged default. A listener wrapping a\n * downstream `allow` must preserve its `content` and `additionalContexts`\n * unless it intentionally replaces them. The signal controls only this turn;\n * listeners may cooperate with it but must not retain it to control another\n * turn. Steering messages do not dispatch this event; they join an open turn\n * at a steering checkpoint.\n * @param agent - the agent whose turn claimed the message.\n * @param content - the claimed message\'s blocks, as queued.\n * @param source - the message\'s resolved source.\n * @param signal - the current turn\'s explicit abort signal.\n * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent.\n * @mode waterfall\n */', summary: 'Allow, rewrite, or block one claimed prompt before it becomes a user message.', }, - { - name: 'agent/queued', - mode: 'emit', - signature: '\'agent/queued\'(this: Scoped<Agent>, agent: Agent, content: ContentBlock[], info: { source: MessageSource; contexts: HookContext[]; steering: boolean }): void', - jsDoc: '/**\n * Detached, frozen content entered the agent\'s inbox. Source defaults have\n * already been applied, so these are the exact values retained for the log.\n * @param agent - the agent whose inbox received the message.\n * @param content - the accepted content blocks retained by the inbox.\n * @param info - the accepted source, contexts, and whether it entered as steering.\n * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent.\n * @mode emit\n */', - summary: 'Detached, frozen content entered the agent\'s inbox.', - }, { name: 'agent/request', mode: 'waterfall', @@ -945,7 +959,7 @@ export const EVENT_API: readonly EventApiEntry[] = [ name: 'agent/status', mode: 'emit', signature: '\'agent/status\'(this: Scoped<Agent>, agent: Agent, status: AgentStatus): void', - jsDoc: '/**\n * Agent status changed (`idle` ⇄ `running`, or → `disposed`). `send()` does\n * not enter `running` synchronously; drive lifecycle from this event.\n * @param agent - the agent whose status flipped.\n * @param status - the status just entered (the transition\'s destination).\n * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent.\n * @mode emit\n */', + jsDoc: '/**\n * Agent status changed (`idle` ⇄ `running`, or → `disposed`). A waking\n * delivery does not enter `running` synchronously; drive lifecycle from this event.\n * @param agent - the agent whose status flipped.\n * @param status - the status just entered (the transition\'s destination).\n * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent.\n * @mode emit\n */', summary: 'Agent status changed (`idle` ⇄ `running`, or → `disposed`).', }, { @@ -1171,7 +1185,7 @@ export const EVENT_API: readonly EventApiEntry[] = [ export const TYPE_API: readonly TypeApiEntry[] = [ { name: 'Agent', - declaration: 'export interface Agent {\n readonly id: SessionId;\n readonly options: AgentOptions;\n readonly session: Session;\n readonly status: AgentStatus;\n readonly ctx: Context;\n send(content: ContentBlock[], options?: SendOptions): void;\n steer(content: ContentBlock[], options?: SendOptions): void;\n inject(content: ContentBlock[], options?: InjectOptions): void;\n cancel(cause?: AgentCancelCause): void;\n whenIdle(): Promise<void>;\n}', + declaration: 'export interface Agent {\n readonly id: SessionId;\n readonly options: AgentOptions;\n readonly session: Session;\n readonly status: AgentStatus;\n readonly ctx: Context;\n followup(content: ContentBlock[], options?: SendOptions): AgentMessageId;\n queue(content: ContentBlock[], options?: SendOptions): AgentMessageId;\n steer(content: ContentBlock[], options?: SendOptions): AgentMessageId;\n inject(content: ContentBlock[], options?: InjectOptions): AgentMessageId;\n send(input: ResolvedAgentInput): AgentMessageId;\n cancel(cause?: AgentCancelCause, options?: CancelOptions): void;\n whenIdle(): Promise<void>;\n}', }, { name: 'AgentCancelCause', @@ -1185,6 +1199,10 @@ export const TYPE_API: readonly TypeApiEntry[] = [ name: 'AgentHandle', declaration: 'export interface AgentHandle {\n agent: Agent;\n dispose(): Promise<void>;\n}', }, + { + name: 'AgentMessageId', + declaration: 'export type AgentMessageId = Branded<\'AgentMessageId\'>;', + }, { name: 'AgentOptions', declaration: 'export interface AgentOptions {\n provider?: string;\n model?: string;\n}', @@ -1285,6 +1303,10 @@ export const TYPE_API: readonly TypeApiEntry[] = [ name: 'CallId', declaration: 'export type CallId = Branded<\'CallId\'>;', }, + { + name: 'CancelOptions', + declaration: 'export interface CancelOptions {\n keepInbox?: boolean;\n}', + }, { name: 'CodeBindingErrorClass', declaration: 'export interface CodeBindingErrorClass {\n name: string;\n memberNameProperty: string;\n}', @@ -1503,7 +1525,7 @@ export const TYPE_API: readonly TypeApiEntry[] = [ }, { name: 'InjectOptions', - declaration: 'export interface InjectOptions extends Omit<SendOptions, \'contexts\'> {\n meta?: JsonValue;\n}', + declaration: 'export interface InjectOptions {\n source?: MessageSource;\n meta?: JsonValue;\n}', }, { name: 'InvariantFailure', @@ -1529,6 +1551,10 @@ export const TYPE_API: readonly TypeApiEntry[] = [ name: 'JsonValue', declaration: 'export type JsonValue = null | boolean | number | string | JsonValue[] | {\n [key: string]: JsonValue;\n};', }, + { + name: 'LlmAdapter', + declaration: 'export abstract class LlmAdapter {\n providerInfo(provider: string): LlmProviderInfo;\n listModels(_provider: string): Promise<readonly LlmModelInfo[]>;\n resolveModelContext(_provider: string, _model: string): Promise<LlmModelContext | undefined>;\n abstract stream(options: GenerateOptions): AsyncIterable<StreamChunk>;\n}', + }, { name: 'LlmCallConfig', declaration: 'export interface LlmCallConfig {\n provider: string;\n model: string;\n temperature?: number;\n maxTokens?: number;\n stop?: string[];\n}', @@ -1591,7 +1617,7 @@ export const TYPE_API: readonly TypeApiEntry[] = [ }, { name: 'PromptMessageData', - declaration: 'export interface PromptMessageData {\n content: ContentBlock[];\n source: MessageSource;\n envelope?: PromptMessageEnvelope;\n}', + declaration: 'export interface PromptMessageData {\n content: ContentBlock[];\n source: MessageSource;\n envelope?: PromptMessageEnvelope;\n meta?: JsonValue;\n}', }, { name: 'PromptMessageEnvelope', @@ -1693,6 +1719,14 @@ export const TYPE_API: readonly TypeApiEntry[] = [ name: 'ReasoningBlock', declaration: 'export interface ReasoningBlock {\n type: \'reasoning\';\n text: string;\n}', }, + { + name: 'RequestHeaderReason', + declaration: 'export type RequestHeaderReason = \'initial\' | \'resume\' | \'change\';', + }, + { + name: 'ResolvedAgentInput', + declaration: 'export type ResolvedAgentInput = {\n content: ContentBlock[];\n source: MessageSource;\n meta: JsonValue | undefined;\n} & ({\n target: \'next-turn\';\n wakeup: boolean;\n contexts: HookContext[];\n} | {\n target: \'next-step\';\n wakeup: true;\n contexts: HookContext[];\n} | {\n target: \'next-step\';\n wakeup: false;\n contexts: [\n ];\n});', + }, { name: 'ResumeAgentOptions', declaration: 'export interface ResumeAgentOptions {\n readonly resumeSessionId: SessionId;\n readonly agentOptions?: AgentOptions;\n readonly signal?: AbortSignal;\n readonly setup?: (agentCtx: Context) => Promise<void> | void;\n}', @@ -1727,7 +1761,11 @@ export const TYPE_API: readonly TypeApiEntry[] = [ }, { name: 'SendOptions', - declaration: 'export interface SendOptions {\n source?: MessageSource;\n contexts?: HookContext[];\n}', + declaration: 'export interface SendOptions {\n source?: MessageSource;\n contexts?: HookContext[];\n meta?: JsonValue;\n}', + }, + { + name: 'Session', + declaration: 'export class Session {\n get surface(): SessionSurface;\n readonly header: SessionHeader;\n get id(): SessionId;\n constructor(id: SessionId, seed?: readonly SessionEvent[], header?: SessionHeader);\n get events(): readonly SessionEvent[];\n get seq(): number;\n append<T extends SessionEventType>(type: T, data: SessionEventMap[T], ...opts: T extends SurfaceEventType ? [\n opts: SurfaceIntent\n ] : [\n ]): SessionEvent<T>;\n requestHeader(): EpochHeader | undefined;\n deriveMessages(): Message[];\n deriveEventMessage(event: SessionEvent): Message | null;\n}', }, { name: 'SessionAvailability', @@ -1739,7 +1777,7 @@ export const TYPE_API: readonly TypeApiEntry[] = [ }, { name: 'SessionEventMap', - declaration: 'export interface SessionEventMap {\n \'turn/start\': {\n turn: number;\n trigger: TurnTrigger;\n };\n \'turn/end\': {\n turn: number;\n reason: TurnEndReason;\n };\n \'step/start\': {\n turn: number;\n step: number;\n };\n \'step/end\': {\n turn: number;\n step: number;\n };\n \'user/message\': PromptMessageData;\n \'prompt/blocked\': {\n content: ContentBlock[];\n source: MessageSource;\n reason: string;\n };\n \'context/message\': {\n content: ContentBlock[];\n source: MessageSource;\n meta?: JsonValue;\n };\n \'assistant/chunk\': {\n turn: number;\n step: number;\n chunk: StreamChunk;\n };\n \'assistant/message\': {\n turn: number;\n step: number;\n content: ContentBlock[];\n provenance: AssistantProvenance;\n usage?: TokenUsage;\n };\n \'tool/call\': {\n turn: number;\n step: number;\n callId: CallId;\n name: string;\n arguments: string;\n };\n \'tool/result\': {\n turn: number;\n step: number;\n callId: CallId;\n content: ContentBlock[];\n isError: boolean;\n error?: {\n name: string;\n code: string;\n };\n meta?: JsonValue;\n };\n \'steering/message\': PromptMessageData & {\n turn: number;\n };\n \'todo/write\': {\n todos: TodoItem[];\n };\n \'request/header\': {\n header: EpochHeader;\n reason: R /* …truncated — full shape in source */', + declaration: 'export interface SessionEventMap {\n \'turn/start\': {\n turn: number;\n trigger: TurnTrigger;\n };\n \'turn/end\': {\n turn: number;\n reason: TurnEndReason;\n };\n \'step/start\': {\n turn: number;\n step: number;\n };\n \'step/end\': {\n turn: number;\n step: number;\n };\n \'user/message\': PromptMessageData;\n \'prompt/blocked\': {\n content: ContentBlock[];\n source: MessageSource;\n reason: string;\n };\n \'assistant/chunk\': {\n turn: number;\n step: number;\n chunk: StreamChunk;\n };\n \'assistant/message\': {\n turn: number;\n step: number;\n content: ContentBlock[];\n provenance: AssistantProvenance;\n usage?: TokenUsage;\n };\n \'tool/call\': {\n turn: number;\n step: number;\n callId: CallId;\n name: string;\n arguments: string;\n };\n \'tool/result\': {\n turn: number;\n step: number;\n callId: CallId;\n content: ContentBlock[];\n isError: boolean;\n error?: {\n name: string;\n code: string;\n };\n meta?: JsonValue;\n };\n \'steering/message\': PromptMessageData & {\n turn: number;\n };\n \'todo/write\': {\n todos: TodoItem[];\n };\n \'request/header\': {\n header: EpochHeader;\n reason: RequestHeaderReason;\n };\n}', }, { name: 'SessionEventMetadataFilter', @@ -1865,6 +1903,10 @@ export const TYPE_API: readonly TypeApiEntry[] = [ name: 'SessionSearchRequest', declaration: 'export interface SessionSearchRequest {\n query: string;\n sessionFilters?: readonly SessionResultFilter[];\n eventFilters?: readonly SessionEventMetadataFilter[];\n limit?: number;\n cursor?: SessionSearchCursor;\n}', }, + { + name: 'SessionSurface', + declaration: 'export interface SessionSurface {\n readonly nodes: readonly number[];\n readonly replaceGeneration: number;\n}', + }, { name: 'SessionSurfaceSnapshot', declaration: 'export interface SessionSurfaceSnapshot {\n session: SessionHeader;\n capturedThroughSeq: number | null;\n events: SurfaceEvent[];\n}', @@ -1995,7 +2037,11 @@ export const TYPE_API: readonly TypeApiEntry[] = [ }, { name: 'SurfaceEventType', - declaration: 'export type SurfaceEventType = \'user/message\' | \'assistant/message\' | \'tool/result\' | \'context/message\' | \'steering/message\';', + declaration: 'export type SurfaceEventType = \'user/message\' | \'assistant/message\' | \'tool/result\' | \'steering/message\';', + }, + { + name: 'SurfaceIntent', + declaration: 'export interface SurfaceIntent {\n surfaceOp: SurfaceOp;\n sourceEventSeqs?: number[];\n}', }, { name: 'SurfaceOp', diff --git a/packages/cordis/tool-cordis/tests/inspect.spec.ts b/packages/cordis/tool-cordis/tests/inspect.spec.ts index 3085cfd057..18b4d04df7 100644 --- a/packages/cordis/tool-cordis/tests/inspect.spec.ts +++ b/packages/cordis/tool-cordis/tests/inspect.spec.ts @@ -61,6 +61,8 @@ describe('cordis_inspect', () => { // generated TYPE_API — a consumer can see field types, not just names). expect(report).toContain('type shapes (referenced by the signatures above') expect(report).toContain('export interface ToolExecution') + expect(report).toContain('export class Session') + expect(report).toContain('export interface SessionSurface') // A type only reachable through a NOT-live service (e.g. bash) is scoped out. expect(report).not.toContain('export interface BashRunResult') // The inherited ctx surface closes the section. diff --git a/packages/cordis/tool-cordis/tests/integration.spec.ts b/packages/cordis/tool-cordis/tests/integration.spec.ts index d68f6be349..7f917e5b3c 100644 --- a/packages/cordis/tool-cordis/tests/integration.spec.ts +++ b/packages/cordis/tool-cordis/tests/integration.spec.ts @@ -47,7 +47,7 @@ describe('cordis tools through the agent loop', () => { const ctx = await harness(adapter) const agent = ctx.agentLoop.create(SessionId('it-cordis'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'give yourself reverse_text, use it, clean up' }]) + agent.followup([{ type: 'text', text: 'give yourself reverse_text, use it, clean up' }]) await waitForIdle(ctx, agent) const log = agent.session.events diff --git a/packages/core/agent-loop/README.md b/packages/core/agent-loop/README.md index 79fbbd7824..47250c354f 100644 --- a/packages/core/agent-loop/README.md +++ b/packages/core/agent-loop/README.md @@ -50,9 +50,9 @@ Configured agents start automatically. A model call requires both `provider` and ### Internal concrete driver -The concrete `Agent` class, its `Inbox`, `runLoop`, and instance-bound publication/start controls are package-internal. The package root exports only the plugin/service/config contract, and the package exports map exposes no `./src/*` escape hatch; lifecycle owners create agents through `ctx.agents` rather than naming, constructing, or starting driver internals. One prepared session can be claimed by only one concrete driver, and everything observable happens through session events and the `agent/*` event taxonomy. +The concrete `ReactLoopAgent` adapter, its `Inbox`, `runLoop`, and instance-bound publication/start controls are package-internal. The package root exports only the plugin/service/config contract, and the package exports map exposes no `./src/*` escape hatch; lifecycle owners create agents through `ctx.agents` rather than naming, constructing, or starting driver internals. One prepared session can be claimed by only one concrete driver, and everything observable happens through session events and the `agent/*` event taxonomy. -Each concrete `send()` materializes content, resolved source, and attached contexts once as a detached, deeply frozen lossless-JSON FIFO item. If claimed, it is the sole ordinary message in its turn; its contexts are the prompt waterfall's default additional contexts and therefore materialize only after admission. Absent or `separate` placement appends an independent `context/message`; `prompt-prefix` placement bakes the context, the stable `## My request:` delimiter, and effective request into one `user/message`, whose model-hidden envelope retains display content and context descriptors. The waterfall's returned allow is authoritative, so a listener wrapping `next()` preserves downstream `content` and `additionalContexts` unless it intentionally replaces them. A successor waits for the preceding ordinary turn's checkpoint to settle, while cancellation, disposal, a prompt block, or a pre-start failure may drop its contexts with the message. Running `steer()` enters the same record shape in the steering FIFO without dispatching `agent/prompt-submit`; its next checkpoint applies the same separate-or-prefix placement to `steering/message`, while policy can still stop before another step. Steering left after turn close and its checkpoint becomes later queued input with contexts intact unless terminal turn policy, cancellation, or disposal discards it. Open-turn `inject()` uses the same accepted-value boundary but defers in a FIFO while the current step executes assistant tool calls; successful batches place it after all results, and interrupted batches drain it before turn close. Malformed data throws before enqueue or append. +`ReactLoopAgent.send()` implements the public fully resolved acceptance path. The `followup()`/`queue()`/`steer()`/`inject()` helpers resolve every optional field before delegating to it; direct callers provide mandatory content, source, contexts, metadata, target, and wakeup facts through `ResolvedAgentInput`. `followup()` and `queue()` join the ordinary FIFO, respectively waking or leaving an idle driver parked. If claimed, an ordinary item is the sole message in its turn, and its contexts are the prompt waterfall's default additional contexts that materialize only after admission. Absent or `separate` placement appends an independent injected `user/message`; `prompt-prefix` placement bakes the context, the stable `## My request:` delimiter, and effective request into one `user/message`, whose model-hidden envelope retains display content and context descriptors. The waterfall's returned allow is authoritative, so a listener wrapping `next()` preserves downstream `content` and `additionalContexts` unless it intentionally replaces them. A successor waits for the preceding ordinary turn's checkpoint to settle, while cancellation, disposal, a prompt block, or a pre-start failure may drop its contexts with the message. Running `steer()` or equivalent `send()` routing enters the same record shape in the steering FIFO without dispatching `agent/prompt-submit`; its next checkpoint applies the same separate-or-prefix placement to `steering/message`, while policy can still stop before another step. Steering left after turn close and its checkpoint becomes later queued input with contexts intact unless terminal turn policy, cancellation, or disposal discards it. `inject()` and non-waking next-step acceptance require an empty context tuple, bypass both FIFOs, and append durable context directly: an open-turn injection defers in a FIFO while the current step executes assistant tool calls (successful batches place it after all results, interrupted batches drain it before turn close), and an idle injection wraps a one-shot `injection` turn. Every FIFO enqueue publishes `agent/inbox/enqueue`; the driver's claims publish `agent/inbox/dequeue`, and `cancel()` without `keepInbox` publishes `agent/inbox/discard`. Malformed data throws before enqueue or append. ### Loop lifecycle (`loop.ts`) diff --git a/packages/core/agent-loop/src/agent.ts b/packages/core/agent-loop/src/agent.ts index 91efbf7782..e09acfff40 100644 --- a/packages/core/agent-loop/src/agent.ts +++ b/packages/core/agent-loop/src/agent.ts @@ -6,15 +6,25 @@ * @module dsh-agent-loop/agent */ +import { randomUUID } from 'node:crypto' import type { Context } from 'cordis' -import { agentEvents } from '@deepseek-ai/dsh-agent' -import type { AgentCancelCause, AgentOptions, AgentStatus, HookContext, InjectOptions, SendOptions } from '@deepseek-ai/dsh-agent' -import type { Agent } from '@deepseek-ai/dsh-agent' +import { agentEvents, AgentMessageId } from '@deepseek-ai/dsh-agent' +import type { + Agent, + AgentCancelCause, + AgentOptions, + AgentStatus, + CancelOptions, + HookContext, + InjectOptions, + ResolvedAgentInput, + SendOptions, +} from '@deepseek-ai/dsh-agent' import { deepFreeze, errorChain } from '@deepseek-ai/dsh-llm' -import type { ContentBlock, MessageSource } from '@deepseek-ai/dsh-llm' +import type { ContentBlock } from '@deepseek-ai/dsh-llm' import { snapshotJsonValue, type Session, type SessionId } from '@deepseek-ai/dsh-session' import { DISPOSED_INTERRUPT_REASON, TurnCancellation } from './cancellation.ts' -import { Inbox, type InboxMessage } from './inbox.ts' +import { Inbox, agentMessage, type InboxMessage } from './inbox.ts' import { isTurnOpen, lastTurnNumber, runLoop } from './loop.ts' /** Sessions already claimed by a concrete driver construction. */ @@ -190,19 +200,17 @@ export class ReactLoopAgent implements Agent { for (const resolve of waiters) resolve() } - private resolveSource(options?: SendOptions): MessageSource { - return options?.source ?? { kind: 'user' } - } - /** * Accept one public message payload as a detached record. Lossless-JSON * materialization reads every nested field once; deep freeze prevents later * caller mutation before an inbox or deferred-injection queue drains it. */ - private acceptMessage(content: ContentBlock[], options?: SendOptions): InboxMessage { - const source = this.resolveSource(options) - const contexts = options?.contexts ?? [] - const accepted = snapshotJsonValue({ content, source, contexts }) + private snapshotMessage(id: AgentMessageId, input: ResolvedAgentInput): InboxMessage { + const { content, source, contexts, wakeup, meta } = input + const accepted = snapshotJsonValue({ + id, content, source, contexts, wakeup, + ...meta !== undefined ? { meta } : {}, + }) if (accepted === undefined) { throw new TypeError('agent message content, source, and contexts must be losslessly JSON-serializable') } @@ -223,33 +231,81 @@ export class ReactLoopAgent implements Agent { if (this._status === 'disposed') throw new Error(`agent "${this.id}" is disposed`) } - send(content: ContentBlock[], options?: SendOptions): void { + /** Accept one fully resolved agent input through the concrete driver's routing matrix. */ + send(input: ResolvedAgentInput): AgentMessageId { this.assertNotDisposed() - const accepted = this.acceptMessage(content, options) - this.#inbox.enqueue(accepted) - const info = { source: accepted.source, contexts: accepted.contexts, steering: false } as const - agentEvents(this.loopCtx, this).emit('agent/queued', accepted.content, info) + const id = AgentMessageId(randomUUID()) + const { target, wakeup } = input + // next-step/no-wakeup is injection: durable context without running the model. + if (target === 'next-step' && !wakeup) { this.injectContext(input); return id } + // next-step/wakeup is steering into the running turn; idle falls back to a + // waking ordinary turn (there is no active turn to attach to). + const steering = target === 'next-step' && this._status === 'running' + const accepted = this.snapshotMessage(id, input) + if (steering) { + this.#inbox.steer(accepted) + } else { + this.#inbox.enqueue(accepted, wakeup) + } + agentEvents(this.loopCtx, this).emit('agent/inbox/enqueue', agentMessage(accepted, steering)) + return id } - steer(content: ContentBlock[], options?: SendOptions): void { - this.assertNotDisposed() - if (this._status !== 'running') { this.send(content, options); return } - const accepted = this.acceptMessage(content, options) - this.#inbox.steer(accepted) - const info = { source: accepted.source, contexts: accepted.contexts, steering: true } as const - agentEvents(this.loopCtx, this).emit('agent/queued', accepted.content, info) + followup(content: ContentBlock[], options?: SendOptions): AgentMessageId { + return this.send({ + content, + target: 'next-turn', + wakeup: true, + source: options?.source ?? { kind: 'user' }, + contexts: options?.contexts ?? [], + meta: options?.meta, + }) } - inject(content: ContentBlock[], options?: InjectOptions): void { - this.assertNotDisposed() - const source = this.resolveSource(options) - const context = { + queue(content: ContentBlock[], options?: SendOptions): AgentMessageId { + return this.send({ + content, + target: 'next-turn', + wakeup: false, + source: options?.source ?? { kind: 'user' }, + contexts: options?.contexts ?? [], + meta: options?.meta, + }) + } + + steer(content: ContentBlock[], options?: SendOptions): AgentMessageId { + return this.send({ + content, + target: 'next-step', + wakeup: true, + source: options?.source ?? { kind: 'user' }, + contexts: options?.contexts ?? [], + meta: options?.meta, + }) + } + + inject(content: ContentBlock[], options?: InjectOptions): AgentMessageId { + return this.send({ + content, + target: 'next-step', + wakeup: false, + source: options?.source ?? { kind: 'plugin', plugin: '' }, + contexts: [], + meta: options?.meta, + }) + } + + /** The `next-step`/no-wakeup injection path: durable context, no FIFO, no run. */ + private injectContext(input: Extract<ResolvedAgentInput, { target: 'next-step'; wakeup: false }>): void { + const { content, source, meta } = input + // Detach and validate the payload before any append, so malformed input + // cannot open a one-shot turn or otherwise mutate the session. + const accepted = this.acceptContext({ content, source, - ...options?.meta !== undefined ? { meta: options.meta } : {}, - } + ...meta !== undefined ? { meta } : {}, + }) if (isTurnOpen(this.session)) { - const accepted = this.acceptContext(context) // Provider protocols require every assistant tool-call batch to be // followed only by its tool results. Historical interrupted batches do // not own new context; only the currently executing batch may defer it. @@ -257,27 +313,29 @@ export class ReactLoopAgent implements Agent { this.deferredInjections.push(accepted) return } - this.session.append('context/message', accepted, { surfaceOp: 'append' }) + this.session.append('user/message', accepted, { surfaceOp: 'append' }) return } // No turn open: wrap the injection in a one-shot turn so every event stays - // turn-enclosed (the durability/replay boundary is the turn). + // turn-enclosed (the durability/replay boundary is the turn). The payload is + // validated above, but `Session.append` can still reject a turn/start + // pre-commit (append re-entrancy from a session/event listener, or an + // internal-dispatch veto), so the finally owes a turn/end only when + // turn/start actually committed. const turn = lastTurnNumber(this.session) + 1 - // Once turn/start enters the log, a turn/end is owed even if the message - // append fails acceptance or pre-commit validation. The finally re-checks - // the log and closes only a turn that actually opened; post-commit observers - // are contained by Session and cannot create a false append failure. try { this.session.append('turn/start', { turn, trigger: { kind: 'injection', source } }) - this.session.append('context/message', context, { surfaceOp: 'append' }) + this.session.append('user/message', accepted, { surfaceOp: 'append' }) } finally { // Close the turn if turn/start made it into the log. A pre-commit veto // must escape rather than being mistaken for a committed turn/end. if (isTurnOpen(this.session)) { this.session.append('turn/end', { turn, reason: { kind: 'completed' } }) } - // Decide the durability checkpoint from the log: an accepted one-shot - // turn must be flushed even when its message append was the failing step. + // Checkpoint only an accepted one-shot turn: a turn/start rejected + // pre-commit recorded nothing, so it owes no flush (and a spurious flush + // would emit a phantom-turn agent/error). The payload is validated up + // front, so a committed turn/start is always followed by its user/message. const turnRecorded = this.session.events.some(e => e.type === 'turn/start' && e.data.turn === turn) // Keep inject() synchronous: report checkpoint failures live instead of // rejecting the caller, and track the task so disposal still drains it. @@ -301,7 +359,7 @@ export class ReactLoopAgent implements Agent { private drainDeferredInjections(): void { const pending = this.deferredInjections.splice(0) for (const accepted of pending) { - this.session.append('context/message', accepted, { surfaceOp: 'append' }) + this.session.append('user/message', accepted, { surfaceOp: 'append' }) } } @@ -325,10 +383,14 @@ export class ReactLoopAgent implements Agent { } } - cancel(cause?: AgentCancelCause): void { + cancel(cause?: AgentCancelCause, options?: CancelOptions): void { const resolvedCause = cause ?? { kind: 'user' } + const keepInbox = options?.keepInbox ?? false const cancellation = this.turnCancellation - const preRun = cancellation === undefined && (this.#inbox.hasQueued || this.#inbox.hasSteering) + // keepInbox preserves pending work, so un-started items must not arm the + // pre-run cancel path that would otherwise drop the next queued turn. + const preRun = !keepInbox && cancellation === undefined + && (this.#inbox.hasQueued || this.#inbox.hasSteering) if (cancellation !== undefined || preRun) { if (preRun) this.preRunCancelled = true // Coordination consumers must update their own state before this call @@ -336,9 +398,24 @@ export class ReactLoopAgent implements Agent { // contained by the fused dispatcher and cannot veto cancellation. agentEvents(this.loopCtx, this).emit('agent/cancel-requested', resolvedCause) } - // Clear work already present before abort observers run. A replacement - // synchronously enqueued by an observer belongs to the next turn. - this.#inbox.clear() + if (!keepInbox) { + // Snapshot before clearing so the discard notification carries the exact + // dropped items; a replacement synchronously enqueued by an + // `agent/cancel-requested` observer belongs to the next turn, not here. + const discarded = this.#inbox.pending() + // Clear work already present before abort observers run. + this.#inbox.clear() + if (discarded.length > 0) { + const items = discarded.map(({ message, steering }) => agentMessage(message, steering)) + agentEvents(this.loopCtx, this).emit('agent/inbox/discard', items) + } + // No idle-waiter settle here: a `whenIdle` waiter exists only while the + // agent is `running` or a waking item is queued, and neither is left + // quiescent by clearing the inbox — a lone quiet item takes `whenIdle`'s + // fast path (no waiter), a waking item keeps the woken driver running, + // and a running agent owns its own idle transition (including the + // post-turn flush window). + } cancellation?.request(resolvedCause) } @@ -349,7 +426,9 @@ export class ReactLoopAgent implements Agent { */ whenIdle(): Promise<void> { if (this._status === 'disposed') return this.done - if (this._status !== 'running' && !this.#inbox.hasQueued) return Promise.resolve() + // A lone quiet (`wakeup:false`) queued item leaves the agent quiescent — the + // driver stays parked — so gate on hasWakingQueued, not hasQueued. + if (this._status !== 'running' && !this.#inbox.hasWakingQueued) return Promise.resolve() // Agent-owned waiters survive concurrent fiber disposal. return new Promise<void>((resolve) => { this.idleWaiters.push(() => { @@ -407,8 +486,21 @@ export class ReactLoopAgent implements Agent { */ private [stopDriver](): Promise<void> | void { if (this._status !== 'disposed') { + // Snapshot any still-pending inbox items, then CLEAR and mark disposed + // BEFORE emitting the discard — mirroring cancel()'s snapshot→clear→emit + // order so a re-entrant followup()/cancel() from a discard listener throws + // `disposed` (or finds an empty inbox) instead of leaking or double- + // discarding an id. `followup()` emits enqueue unconditionally, so the discard + // is unconditional too (even on an unpublished rollback) to keep every + // enqueued id matched. + const discarded = this.#inbox.pending() + this.#inbox.clear() this._status = 'disposed' this.resolveDisposed() + if (discarded.length > 0) { + const items = discarded.map(({ message, steering }) => agentMessage(message, steering)) + agentEvents(this.loopCtx, this).emit('agent/inbox/discard', items) + } // Release whenIdle waiters BEFORE the (guarded) event emit — they are // internal state that must settle even if a listener throws below. Each // waiter chains `done`, so it resolves only once the loop actually exits. diff --git a/packages/core/agent-loop/src/inbox.ts b/packages/core/agent-loop/src/inbox.ts index 6c8a20e3d1..0f93884515 100644 --- a/packages/core/agent-loop/src/inbox.ts +++ b/packages/core/agent-loop/src/inbox.ts @@ -1,54 +1,91 @@ /** * Per-agent message inbox: queued and steering FIFOs. Purely an in-memory - * mechanism of the loop driver — the public surface is `Agent.send()` and - * `Agent.steer()`. + * mechanism of the loop driver — callers use `Agent`'s intent-named delivery + * methods instead. * * @module dsh-agent-loop/inbox */ import type { ContentBlock, MessageSource } from '@deepseek-ai/dsh-llm' -import type { HookContext } from '@deepseek-ai/dsh-agent' +import type { JsonValue } from '@deepseek-ai/dsh-session' +import type { AgentMessage, AgentMessageId, HookContext } from '@deepseek-ai/dsh-agent' -/** One message waiting in an agent's inbox. */ +/** One message waiting in an agent's inbox; `id` is the value its accepting delivery method returned. */ export interface InboxMessage { + id: AgentMessageId content: ContentBlock[] source: MessageSource contexts: HookContext[] + /** Whether the item is marked to wake the driver or force a continuation. */ + wakeup: boolean + /** Opaque durable JSON state retained on the durable message but hidden from the model. */ + meta?: JsonValue +} + +/** + * Build the `agent/inbox/*` event payload for one inbox item. + * @param message - the accepted inbox record. + * @param steering - whether the item is in the steering FIFO (`next-step`). + * @returns the live-event message for enqueue/dequeue/discard. + */ +export function agentMessage(message: InboxMessage, steering: boolean): AgentMessage { + // Frozen: the fused emitter passes this exact object to every listener in + // turn, so one listener must not be able to mutate a field (`id`, `steering`, + // `content`, …) a later listener then observes. `message` is already a frozen + // inbox record, so its nested fields need no re-clone. + return Object.freeze({ + id: message.id, content: message.content, source: message.source, + contexts: message.contexts, steering, wakeup: message.wakeup, + }) } /** * Per-agent inbox: a queued FIFO (dequeued once per turn start) and a steering FIFO * (drained between steps of a running turn). Purely an in-memory mechanism of - * the loop — the public surface is `Agent.send()` / `Agent.steer()`. + * the loop — the public surface is `Agent`'s intent-named delivery methods. */ export class Inbox { private queuedMessages: InboxMessage[] = [] private steeringMessages: InboxMessage[] = [] private wakeup: (() => void) | undefined - /** True while queued messages are pending — read by the idle wait's fast path and the loop's turn-start checks. */ + /** True while any queued message is pending — read by cancellation's discard snapshot and the turn-start dequeue guard. */ get hasQueued(): boolean { return this.queuedMessages.length > 0 } + /** + * True while a queued message wants to wake the driver — the "should the loop + * run" signal read by the idle wait's fast path, the loop's idle-publish + * check, and `whenIdle`. A `wakeup:false` (quiet) item alone leaves this + * false, so the driver stays parked until a waking follow-up (or a waking item + * ahead of it in FIFO order) drives the loop; the quiet item then rides along. + */ + get hasWakingQueued(): boolean { + return this.queuedMessages.some(message => message.wakeup) + } + /** True while steering messages are pending — read by cancellation and the loop's stop-override check. */ get hasSteering(): boolean { return this.steeringMessages.length > 0 } /** - * Add a message to the queued FIFO and wake a parked {@link waitForQueued}. + * Add a message to the queued FIFO, waking a parked {@link waitForQueued} + * unless the item opted out. A non-waking item still runs once any woken + * item or later wakeup drives the parked loop. * @param message - the message to queue for the next turn start. + * @param wake - whether to wake a parked idle wait (default true). */ - enqueue(message: InboxMessage): void { + enqueue(message: InboxMessage, wake = true): void { this.queuedMessages.push(message) - this.wakeup?.() + if (wake) this.wakeup?.() } /** * Add a message to the steering FIFO. Deliberately no wakeup: steering is * drained between steps of a running turn, never by the idle wait — - * `Agent.steer()` on an idle agent falls back to `send()` instead. + * `Agent.steer()` on an idle agent falls back to a waking ordinary turn instead. * @param message - the message to inject between steps of the running turn. */ steer(message: InboxMessage): void { @@ -71,6 +108,18 @@ export class Inbox { return this.steeringMessages.splice(0) } + /** + * Snapshot the pending items (queued then steering, FIFO order) without + * removing them — the discard notification's payload source. + * @returns the pending items paired with whether each is steering. + */ + pending(): { message: InboxMessage; steering: boolean }[] { + return [ + ...this.queuedMessages.map(message => ({ message, steering: false })), + ...this.steeringMessages.map(message => ({ message, steering: true })), + ] + } + /** * Discard all pending messages (queued + steering) without delivering them — * used by `cancel()`, which drops un-started work rather than draining it into @@ -88,7 +137,7 @@ export class Inbox { * loop can exit). */ waitForQueued(cancel: Promise<void>): Promise<void> { - if (this.hasQueued) return Promise.resolve() + if (this.hasWakingQueued) return Promise.resolve() const { promise, resolve } = Promise.withResolvers<void>() this.wakeup = resolve void cancel.then(resolve) diff --git a/packages/core/agent-loop/src/loop.ts b/packages/core/agent-loop/src/loop.ts index 1cfd913b77..4324deca8d 100644 --- a/packages/core/agent-loop/src/loop.ts +++ b/packages/core/agent-loop/src/loop.ts @@ -5,11 +5,12 @@ * @module dsh-agent-loop/loop */ +import { randomUUID } from 'node:crypto' import type { Context } from 'cordis' import type { ContentBlock, FinishReason, GenerateOptions, LlmCallConfig, LlmFailure, Message } from '@deepseek-ai/dsh-llm' import { isDeepStrictEqual } from 'node:util' import { BlockAssembler, HarnessError, LlmError, assertNever, deepFreeze, errorChain, llmFailureOf, markAgentLoopRequest } from '@deepseek-ai/dsh-llm' -import { agentEvents, agentInterruptReasonOf, assembleContextFor } from '@deepseek-ai/dsh-agent' +import { agentEvents, agentInterruptReasonOf, assembleContextFor, AgentMessageId } from '@deepseek-ai/dsh-agent' import type { AgentEventDispatch, ContinuationDecision, HookContext, PromptDecision, RequestError, RequestErrorDecision } from '@deepseek-ai/dsh-agent' import { canonicalHeader } from '@deepseek-ai/dsh-session' import type { PromptMessageData, Session, TurnEndReason, TurnTrigger } from '@deepseek-ai/dsh-session' @@ -19,7 +20,7 @@ import { renderPrompt } from '@deepseek-ai/dsh-system-prompt' import type { PromptAssembly } from '@deepseek-ai/dsh-system-prompt' import type {} from '@deepseek-ai/dsh-tools' import { executeToolCalls } from './tool-calls.ts' -import type { Inbox } from './inbox.ts' +import { agentMessage, type Inbox, type InboxMessage } from './inbox.ts' import type { TurnCancellation } from './cancellation.ts' /** Normalize thrown values while preserving an existing error code. */ @@ -201,9 +202,11 @@ export async function runLoop(ctx: Context, handle: LoopHandle): Promise<void> { while (!handle.isDisposed()) { // An idle listener can enqueue and cancel replacement work before the next // wait is installed. Consume that empty marker before parking the driver. + // A quiet (`wakeup:false`) item alone must not un-park the loop, so gate on + // hasWakingQueued, not hasQueued. if (handle.isPreRunCancelled()) { handle.clearPreRunCancel() - if (!handle.inbox.hasQueued) { + if (!handle.inbox.hasWakingQueued) { handle.settleIdle() handle.setStatus('idle') continue @@ -217,7 +220,7 @@ export async function runLoop(ctx: Context, handle: LoopHandle): Promise<void> { // a replacement prompt still runs before the eventual idle transition. if (handle.isPreRunCancelled()) { handle.clearPreRunCancel() - if (!handle.inbox.hasQueued) { + if (!handle.inbox.hasWakingQueued) { // Settle before publishing idle: the already-idle path has no status // transition, while an idle listener can register waiters for new work. handle.settleIdle() @@ -234,10 +237,11 @@ export async function runLoop(ctx: Context, handle: LoopHandle): Promise<void> { } // A synchronous `running` listener can cancel before `runTurn`; balance the - // status only when no replacement prompt was queued by that listener. + // status only when no waking replacement prompt was queued by that listener + // (a lone quiet item parks at idle rather than driving a turn). if (cancellation.signal.aborted) { handle.clearTurnCancellation(cancellation) - if (!handle.inbox.hasQueued) { + if (!handle.inbox.hasWakingQueued) { handle.setStatus('idle') continue } @@ -260,12 +264,22 @@ export async function runLoop(ctx: Context, handle: LoopHandle): Promise<void> { handle.clearTurnCancellation(cancellation) } - // Late steering becomes queued input unless terminal policy stopped the turn. - for (const message of handle.inbox.drainSteering()) { - if (!terminalStopped) handle.inbox.enqueue(message) + // Late steering (arriving after runTurn returns, e.g. during the post-turn + // flush) becomes queued input — unless terminal policy stopped the turn, in + // which case it is dropped and must publish a discard so its enqueue is + // still matched (the invariant only catches a NEGATIVE count, not a leak). + const lateSteering = handle.inbox.drainSteering() + if (terminalStopped) { + if (lateSteering.length > 0) { + events.emit('agent/inbox/discard', lateSteering.map(message => agentMessage(message, true))) + } + } else { + for (const message of lateSteering) handle.inbox.enqueue(message) } - if (!handle.inbox.hasQueued) handle.setStatus('idle') + // Park at idle unless a waking item still wants the model to run; a lone + // quiet (`wakeup:false`) item stays queued but does not keep the loop busy. + if (!handle.inbox.hasWakingQueued) handle.setStatus('idle') } } @@ -279,10 +293,14 @@ async function runTurn( const drainSteering = (): boolean => { const messages = handle.inbox.drainSteering() for (const message of messages) { + events.emit('agent/inbox/dequeue', agentMessage(message, true)) const prepared = preparePromptMessage(message.content, message.source, message.contexts) - session.append('steering/message', { turn, ...prepared.data }, { surfaceOp: 'append' }) + session.append('steering/message', { + turn, ...prepared.data, + ...message.meta === undefined ? {} : { meta: message.meta }, + }, { surfaceOp: 'append' }) for (const context of prepared.separateContexts) { - session.append('context/message', { + session.append('user/message', { content: context.content, source: context.source, ...context.meta === undefined ? {} : { meta: context.meta }, @@ -296,6 +314,7 @@ async function runTurn( const message = handle.inbox.dequeueQueued() /* v8 ignore next 3 -- invariant guard: runLoop only calls runTurn when hasQueued */ if (!message) throw new Error('runTurn invariant violated: no queued message at turn start') + events.emit('agent/inbox/dequeue', agentMessage(message, false)) const trigger: TurnTrigger = { kind: 'message', source: message.source } let reason: TurnEndReason = { kind: 'completed' } @@ -361,7 +380,10 @@ async function runTurn( // `allow.content` REPLACES the prompt bytes (a rewrite); absent keeps them. const content = promptDecision.content ?? message.content const prepared = preparePromptMessage(content, message.source, promptDecision.additionalContexts ?? []) - session.append('user/message', prepared.data, { surfaceOp: 'append' }) + session.append('user/message', { + ...prepared.data, + ...message.meta === undefined ? {} : { meta: message.meta }, + }, { surfaceOp: 'append' }) // Separate contexts still enter THIS turn through inject(). Prefix // contexts are already baked into the user/message with their durable // display envelope, so appending them again would duplicate model input. @@ -536,9 +558,21 @@ async function runTurn( break } - // A continuation reason becomes next-step steering. + // A continuation reason becomes next-step steering. Publish the same + // enqueue event a public steer would, so the inbox ledger stays balanced + // (every FIFO entry has a matching enqueue before its dequeue/discard). if (decision.action === 'continue' && decision.reason) { - handle.inbox.steer({ content: decision.reason.content, source: decision.reason.source, contexts: [] }) + // Detach and freeze the listener-owned reason like a public steer, so an + // enqueue listener or the producer cannot mutate the durable/model-visible + // steering message before it drains. + const item: InboxMessage = deepFreeze({ + id: AgentMessageId(randomUUID()), + content: structuredClone(decision.reason.content), + source: structuredClone(decision.reason.source), + contexts: [], wakeup: true, + }) + handle.inbox.steer(item) + events.emit('agent/inbox/enqueue', agentMessage(item, true)) } let shouldContinue = decision.action === 'continue' @@ -562,7 +596,13 @@ async function runTurn( if (terminalStop) { terminalStopped = true // Terminal stop discards steering but preserves ordinary queued prompts. - handle.inbox.drainSteering() + // Publish a discard for every dropped steering item so the enqueue ⇒ + // dequeue-or-discard ledger stays balanced (the outstanding-count + // invariant and correlation consumers must not be left with dangling ids). + const dropped = handle.inbox.drainSteering() + if (dropped.length > 0) { + events.emit('agent/inbox/discard', dropped.map(item => agentMessage(item, true))) + } shouldContinue = false } diff --git a/packages/core/agent-loop/tests/agent-initiator.spec.ts b/packages/core/agent-loop/tests/agent-initiator.spec.ts index c6c767d422..a2359562a8 100644 --- a/packages/core/agent-loop/tests/agent-initiator.spec.ts +++ b/packages/core/agent-loop/tests/agent-initiator.spec.ts @@ -41,7 +41,7 @@ function waitForIdle(ctx: Context, agent: Agent): Promise<void> { } function send(agent: Agent, text: string): void { - agent.send([{ type: 'text', text }]) + agent.followup([{ type: 'text', text }]) } /** Adapter that holds both drivers at the same awaited continuation. */ diff --git a/packages/core/agent-loop/tests/agent.spec.ts b/packages/core/agent-loop/tests/agent.spec.ts index 2cb3191f83..08b77711f9 100644 --- a/packages/core/agent-loop/tests/agent.spec.ts +++ b/packages/core/agent-loop/tests/agent.spec.ts @@ -48,7 +48,7 @@ function waitForStatus(ctx: Context, agent: Agent, expected: Agent['status']): P } function send(agent: Agent, text: string) { - agent.send([{ type: 'text', text }]) + agent.followup([{ type: 'text', text }]) } describe('Agent', () => { @@ -83,7 +83,41 @@ describe('Agent', () => { await ctx.fiber.dispose() }) - it('send() throws after disposal', async () => { + it('send exposes the fully resolved delivery path without applying helper defaults', async () => { + const adapter = new MockAdapter([textResponse('accepted')]) + const ctx = await harness(adapter) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) + const enqueued = Promise.withResolvers<{ id: string; source: unknown; wakeup: boolean }>() + ctx.on('agent/inbox/enqueue', (subject, message) => { + if (subject === agent) enqueued.resolve(message) + }) + + const id = agent.send({ + content: [{ type: 'text', text: 'advanced input' }], + source: { kind: 'plugin', plugin: 'advanced-caller' }, + contexts: [], + meta: { caller: 'advanced' }, + target: 'next-turn', + wakeup: true, + }) + await waitForIdle(ctx, agent) + + expect(await enqueued.promise).toMatchObject({ + id, + source: { kind: 'plugin', plugin: 'advanced-caller' }, + wakeup: true, + }) + expect(agent.session.events.find(event => event.type === 'user/message')) + .toMatchObject({ + data: { + source: { kind: 'plugin', plugin: 'advanced-caller' }, + meta: { caller: 'advanced' }, + }, + }) + await ctx.fiber.dispose() + }) + + it('followup() throws after disposal', async () => { const adapter = new MockAdapter(['hang']) const ctx = await harness(adapter) let agent!: Agent @@ -95,7 +129,28 @@ describe('Agent', () => { await fiber.dispose() await driverDone(agent) - expect(() => { agent.send([{ type: 'text', text: 'too late' }]) }).toThrow('disposed') + expect(() => { agent.followup([{ type: 'text', text: 'too late' }]) }).toThrow('disposed') + }) + + it('disposal discards still-pending inbox items so every id gets a terminal event', async () => { + const adapter = new MockAdapter(['hang']) + const ctx = await harness(adapter) + let agent!: Agent + const discarded: string[] = [] + ctx.on('agent/inbox/discard', (subject, messages) => { + if (subject === agent) discarded.push(...messages.map(m => m.id)) + }) + const fiber = await ctx.plugin(Object.assign((inner: Context) => { + agent = inner.agentLoop.create(SessionId('scoped'), { provider: 'mock', model: 'mock' }) + }, { inject: ['agentLoop'] })) + + // A quiet (non-waking) item stays parked in the inbox; disposal must drop it + // WITH a discard so its enqueued id is not left dangling forever. + const id = agent.queue([{ type: 'text', text: 'never runs' }]) + await fiber.dispose() + await driverDone(agent) + + expect(discarded).toEqual([id]) }) it('steer() throws after disposal', async () => { @@ -139,7 +194,7 @@ describe('Agent', () => { agent.session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) agent.inject([{ type: 'text', text: 'mid' }], { source: { kind: 'plugin', plugin: 'p' } }) expect(agent.session.events.filter(e => e.type === 'turn/start')).toHaveLength(1) - expect(agent.session.events.at(-1)!.type).toBe('context/message') + expect(agent.session.events.at(-1)!.type).toBe('user/message') // Close the turn; now inject must wrap its own one-shot injection turn. agent.session.append('turn/end', { turn: 1, reason: { kind: 'completed' } }) @@ -151,6 +206,16 @@ describe('Agent', () => { expect(agent.session.events.at(-1)!.type).toBe('turn/end') // turn-enclosed }) + it('inject() defaults its source to an empty plugin, never user', async () => { + const adapter = new MockAdapter([textResponse('ok')]) + const ctx = await harness(adapter) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) + agent.session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) + agent.inject([{ type: 'text', text: 'no explicit source' }]) + const injected = agent.session.events.at(-1)! + expect(injected.type === 'user/message' && injected.data.source).toEqual({ kind: 'plugin', plugin: '' }) + }) + it('idle inject() contains a failing flush (logs, does not throw into the caller)', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) @@ -167,24 +232,54 @@ describe('Agent', () => { warn.mockRestore() }) - it('idle inject() closes its one-shot turn AND still checkpoints even if the append throws', async () => { + it('idle inject() validates its payload BEFORE opening a turn, so invalid input appends nothing', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) let flushes = 0 ctx.on('session/flush', () => { flushes += 1 }) - // Non-serializable injected content makes Session.append throw AFTER - // turn/start was recorded. The turn/end must still be appended (finally), - // AND the durability checkpoint must still fire — the balanced turn is in - // memory and a crash before the next turn/dispose would otherwise lose it. + // Non-serializable injected content is rejected by the up-front snapshot + // BEFORE any append (the unified send contract: invalid input throws before + // mutating the log). No one-shot turn opens and no durability checkpoint fires. expect(() => { agent.inject([{ type: 'text', text: 'x', bad: 1n } as never], { source: { kind: 'plugin', plugin: 'p' } }) - }).toThrow(/non-JSON-serializable/) - const types = agent.session.events.map(e => e.type) - expect(types).toEqual(['turn/start', 'turn/end']) // balanced, no open turn - await new Promise(r => setTimeout(r, 10)) // let the fire-and-forget flush run - expect(flushes).toBe(1) // checkpoint fired despite the throw + }).toThrow(/losslessly JSON-serializable/) + expect(agent.session.events).toHaveLength(0) + await new Promise(r => setTimeout(r, 10)) // give any (erroneous) flush a chance + expect(flushes).toBe(0) // nothing was appended, so no checkpoint + }) + + it('idle inject() re-entered from a session/event listener is rejected pre-commit and opens no turn', async () => { + const adapter = new MockAdapter([textResponse('ok')]) + const ctx = await harness(adapter) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) + let flushes = 0 + ctx.on('session/flush', () => { flushes += 1 }) + // Injecting from inside a session/event listener re-enters Session.append, + // which rejects pre-commit — so turn/start never commits. The finally sees + // no open turn (closes nothing) and no recorded turn (no checkpoint), and + // the reentrant throw is contained by Session's post-commit dispatch. + // Fire on turn/end: at that instant the outer one-shot turn is closed (no + // turn open), so the reentrant inject takes the idle one-shot-turn path and + // its turn/start append re-enters Session and is rejected pre-commit. + let reentered = false + ctx.on('session/event', (_s, event) => { + if (!reentered && event.type === 'turn/end') { + reentered = true + agent.inject([{ type: 'text', text: 'reentrant' }], { source: { kind: 'plugin', plugin: 'p' } }) + } + }) + + agent.inject([{ type: 'text', text: 'outer' }], { source: { kind: 'plugin', plugin: 'p' } }) + // The outer injection's own one-shot turn is balanced; the reentrant one + // opened no turn (its turn/start was rejected pre-commit). + const turnStarts = agent.session.events.filter(e => e.type === 'turn/start') + expect(turnStarts).toHaveLength(1) + const injected = agent.session.events.filter(e => e.type === 'user/message') + expect(injected).toHaveLength(1) // the reentrant user/message never committed + await new Promise(r => setTimeout(r, 10)) + expect(flushes).toBe(1) // only the outer accepted turn checkpointed }) it('idle inject() still checkpoints when a listener throws on the synthetic turn/end', async () => { @@ -202,7 +297,7 @@ describe('Agent', () => { expect(() => { agent.inject([{ type: 'text', text: 'notice' }], { source: { kind: 'plugin', plugin: 'p' } }) }).not.toThrow() const types = agent.session.events.map(e => e.type) - expect(types).toEqual(['turn/start', 'context/message', 'turn/end']) // balanced + expect(types).toEqual(['turn/start', 'user/message', 'turn/end']) // balanced await new Promise(r => setTimeout(r, 10)) expect(flushes).toBe(1) // checkpoint fired despite the throwing turn/end listener }) @@ -234,13 +329,11 @@ describe('Agent', () => { const ctx = await harness(adapter) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - // A non-serializable source makes the turn/start append throw BEFORE the - // event is pushed (Session.append validates before push), so NO turn opens. - // The finally's isTurnOpen() guard sees no open turn and appends nothing — - // the log stays empty, not left with a dangling turn/start. + // A non-serializable source is rejected by the up-front snapshot BEFORE any + // append, so NO turn opens and the log stays empty. expect(() => { agent.inject([{ type: 'text', text: 'x' }], { source: { kind: 'plugin', plugin: 'p', bad: 1n } as never }) - }).toThrow(/non-JSON-serializable/) + }).toThrow(/losslessly JSON-serializable/) expect(agent.session.events).toHaveLength(0) }) @@ -397,7 +490,7 @@ describe('Agent', () => { const { agent } = prepared prepared.markPublished() const dispose = prepared.startDriver() - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await new Promise(r => setTimeout(r, 30)) expect(agent.status).toBe('running') diff --git a/packages/core/agent-loop/tests/cancel.spec.ts b/packages/core/agent-loop/tests/cancel.spec.ts index cbf2c70564..32418fe112 100644 --- a/packages/core/agent-loop/tests/cancel.spec.ts +++ b/packages/core/agent-loop/tests/cancel.spec.ts @@ -33,7 +33,7 @@ async function harness(adapter: MockAdapter) { } function send(agent: Agent, text: string) { - agent.send([{ type: 'text', text }]) + agent.followup([{ type: 'text', text }]) } /** Resolve on the agent's next idle transition (event-based, not status poll). */ @@ -63,7 +63,7 @@ describe('Agent.cancel()', () => { ctx.on('agent/cancel-requested', (subject, cause) => { if (subject !== agent) return seen.push(`first:${cause.kind}`) - subject.send([{ type: 'text', text: 'queued by cancel observer' }]) + subject.followup([{ type: 'text', text: 'queued by cancel observer' }]) throw new Error('observer failed') }) ctx.on('agent/cancel-requested', (subject, cause) => { @@ -98,6 +98,57 @@ describe('Agent.cancel()', () => { expect(agent.session.events.some(e => e.type === 'turn/end')).toBe(true) }) + it('cancel({ keepInbox: true }) preserves queued work and emits no discard', async () => { + const adapter = new MockAdapter([textResponse('reply')]) + const ctx = await harness(adapter) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) + const discards: unknown[] = [] + ctx.on('agent/inbox/discard', (subject, items) => { if (subject === agent) discards.push(items) }) + + // Queue a turn WITHOUT waking the driver, so it sits in the inbox. + agent.queue([{ type: 'text', text: 'preserved' }]) + // keepInbox cancel: no active turn, work preserved, no discard event. + agent.cancel({ kind: 'user' }, { keepInbox: true }) + expect(discards).toEqual([]) + + // The preserved item still runs once the driver is woken by a later send. + send(agent, 'wake it') + await waitForIdle(ctx, agent) + expect(userTexts(agent)).toEqual(['preserved', 'wake it']) + }) + + it('a lone queued message leaves the agent parked at idle', async () => { + const adapter = new MockAdapter([textResponse('reply')]) + const ctx = await harness(adapter) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) + + // A quiet item alone must NOT wake the driver: no turn runs and whenIdle + // resolves (the agent is quiescent), leaving the item queued. + agent.queue([{ type: 'text', text: 'quiet' }]) + await agent.whenIdle() + expect(agent.status).toBe('idle') + expect(agent.session.events.some(e => e.type === 'turn/start')).toBe(false) + + // A later waking send drives the loop, and the quiet item rides along first. + send(agent, 'wake') + await waitForIdle(ctx, agent) + expect(userTexts(agent)).toEqual(['quiet', 'wake']) + }) + + it('cancelling a parked quiet item settles a pending whenIdle() without a later send', async () => { + const adapter = new MockAdapter([textResponse('reply')]) + const ctx = await harness(adapter) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) + + agent.queue([{ type: 'text', text: 'quiet' }]) + const idle = agent.whenIdle() + // Cancel reaches quiescence with no status transition and no waking send; + // whenIdle must still resolve (previously it hung until the next send). + agent.cancel({ kind: 'user' }) + await idle + expect(agent.session.events.some(e => e.type === 'turn/start')).toBe(false) + }) + it('pre-step cancel drops the about-to-start turn (no turn is opened)', async () => { const adapter = new MockAdapter([textResponse('should not run')]) const ctx = await harness(adapter) diff --git a/packages/core/agent-loop/tests/config-session-id.spec.ts b/packages/core/agent-loop/tests/config-session-id.spec.ts index 2103dd6831..d144127498 100644 --- a/packages/core/agent-loop/tests/config-session-id.spec.ts +++ b/packages/core/agent-loop/tests/config-session-id.spec.ts @@ -98,7 +98,7 @@ describe('config-driven session id', () => { first = ctx.agents.get(SessionId('config-exact-reload')) } expect(first).toBeDefined() - first!.send([{ type: 'text', text: 'remember me' }], { source: { kind: 'user' } }) + first!.followup([{ type: 'text', text: 'remember me' }], { source: { kind: 'user' } }) await waitForIdle(ctx, first!) await firstLoop.dispose() @@ -110,7 +110,7 @@ describe('config-driven session id', () => { } expect(second).toBeDefined() expect(JSON.stringify(second!.session.deriveMessages())).toContain('remember me') - second!.send([{ type: 'text', text: 'continue' }], { source: { kind: 'user' } }) + second!.followup([{ type: 'text', text: 'continue' }], { source: { kind: 'user' } }) await waitForIdle(ctx, second!) await ctx.sessions.flush(second!.session) const loaded = await ctx.sessionPersistence.load(SessionId('config-exact-reload')) @@ -335,7 +335,7 @@ describe('config-driven session id', () => { expect(a1.id).toBe(a1.session.id) expect(a1.session.id).toMatch(idPattern) expect(ctx1.agents.get(SessionId('cfg'))).toBeUndefined() - a1.send([{ type: 'text', text: 'q' }], { source: { kind: 'user' } }) + a1.followup([{ type: 'text', text: 'q' }], { source: { kind: 'user' } }) await waitForIdle(ctx1, a1) await ctx1.fiber.dispose() @@ -354,7 +354,7 @@ describe('config-driven session id', () => { expect(a2.id).toBe(a2.session.id) expect(a2.session.id).toMatch(idPattern) expect(a2.session.id).not.toBe(a1.session.id) - a2.send([{ type: 'text', text: 'q2' }], { source: { kind: 'user' } }) + a2.followup([{ type: 'text', text: 'q2' }], { source: { kind: 'user' } }) await waitForIdle(ctx2, a2) await ctx2.fiber.dispose() }) @@ -375,7 +375,7 @@ describe('config-driven session id', () => { await ctx1.plugin(SessionPersistenceJsonl, { root }) ctx1.llm.registerAdapter(['mock'], new MockAdapter([textResponse('first')])) const a1 = (await ctx1.agents.create({ sessionId: SessionId('sticky-1') })).agent - a1.send([{ type: 'text', text: 'remember me' }], { source: { kind: 'user' } }) + a1.followup([{ type: 'text', text: 'remember me' }], { source: { kind: 'user' } }) await waitForIdle(ctx1, a1) await ctx1.fiber.dispose() diff --git a/packages/core/agent-loop/tests/contract-regressions.spec.ts b/packages/core/agent-loop/tests/contract-regressions.spec.ts index 07cf87f57d..2b85691151 100644 --- a/packages/core/agent-loop/tests/contract-regressions.spec.ts +++ b/packages/core/agent-loop/tests/contract-regressions.spec.ts @@ -50,7 +50,7 @@ function waitForIdle(ctx: Context, agent: Agent): Promise<void> { } function send(agent: Agent, text: string) { - agent.send([{ type: 'text', text }]) + agent.followup([{ type: 'text', text }]) } describe('session log records what agent/step-result actually produced', () => { @@ -275,7 +275,9 @@ describe('abort during tool execution ends the turn', () => { order.push(`tool/result:${event.data.callId}:${outcome}`) break } - case 'context/message': order.push('context/message'); break + // Injected context is a plugin-sourced user/message; the direct human + // prompt (user source) is not tracked in this ordering. + case 'user/message': if (event.data.source.kind !== 'user') order.push('context/message'); break case 'steering/message': order.push('steering/message'); break case 'step/end': order.push('step/end'); break case 'turn/end': { @@ -354,13 +356,14 @@ describe('abort during tool execution ends the turn', () => { await waitForIdle(ctx, agent) const events = [...agent.session.events] + const isInjected = (e: SessionEvent): e is SessionEvent<'user/message'> => e.type === 'user/message' && e.data.source.kind !== 'user' expect(events - .filter(event => event.type === 'tool/result' || event.type === 'context/message' + .filter(event => event.type === 'tool/result' || isInjected(event) || event.type === 'step/end' || event.type === 'turn/end') - .map(event => event.type)) + .map(event => isInjected(event) ? 'context/message' : event.type)) .toEqual(['tool/result', 'context/message', 'context/message', 'step/end', 'turn/end']) expect(events - .filter(event => event.type === 'context/message') + .filter(isInjected) .map(event => event.data.content)) .toEqual([ [{ type: 'text', text: 'accepted before abort' }], @@ -410,12 +413,13 @@ describe('abort during tool execution ends the turn', () => { await waitForIdle(ctx, agent) const events = [...agent.session.events] + const isInjected = (e: SessionEvent): e is SessionEvent<'user/message'> => e.type === 'user/message' && e.data.source.kind !== 'user' expect(events - .filter(event => event.type === 'tool/result' || event.type === 'context/message' + .filter(event => event.type === 'tool/result' || isInjected(event) || event.type === 'step/end' || event.type === 'turn/end') - .map(event => event.type)) + .map(event => isInjected(event) ? 'context/message' : event.type)) .toEqual(['tool/result', 'tool/result', 'context/message', 'step/end', 'turn/end']) - expect(events.find(event => event.type === 'context/message')?.data.content) + expect(events.find(isInjected)?.data.content) .toEqual([{ type: 'text', text: 'accepted after first result' }]) }) @@ -456,7 +460,7 @@ describe('abort during tool execution ends the turn', () => { await fiber.dispose() expect(agent.session.events - .filter(event => event.type === 'context/message') + .filter((event): event is SessionEvent<'user/message'> => event.type === 'user/message' && event.data.source.kind !== 'user') .map(event => event.data.content)) .toEqual([ [{ type: 'text', text: 'accepted before disposal' }], @@ -507,7 +511,7 @@ describe('abort during tool execution ends the turn', () => { send(agent, 'start a text-only turn') await waitForIdle(ctx, agent) - expect(agent.session.events.find(event => event.type === 'context/message')?.data.content) + expect(agent.session.events.find((event): event is SessionEvent<'user/message'> => event.type === 'user/message' && event.data.source.kind !== 'user')?.data.content) .toEqual([{ type: 'text', text: 'new turn context' }]) expect(JSON.stringify(adapter.requests[1]?.messages)).toContain('new turn context') }) @@ -763,7 +767,7 @@ describe('adapter registration, routing, and accepted-input ownership', () => { expect(agent.session.deriveMessages().at(-1)?.content).toEqual([{ type: 'text', text: 'routed' }]) }) - it('agent/queued carries the resolved source; steering/message records its source', async () => { + it('agent/inbox/enqueue carries the resolved source; steering/message records its source', async () => { const adapter = new MockAdapter([toolCallResponse('c1', 'noop', {}), textResponse('done')]) const ctx = await harness(adapter) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) @@ -778,7 +782,7 @@ describe('adapter registration, routing, and accepted-input ownership', () => { })) const queuedSources: { source: MessageSource; contexts: HookContext[]; steering: boolean }[] = [] - ctx.on('agent/queued', (_agent, _content, info) => void queuedSources.push(info)) + ctx.on('agent/inbox/enqueue', (_agent, info) => void queuedSources.push({ source: info.source, contexts: info.contexts, steering: info.steering })) send(agent, 'go') // no explicit source → default {kind:'user'} must be visible await waitForIdle(ctx, agent) @@ -800,11 +804,11 @@ describe('adapter registration, routing, and accepted-input ownership', () => { let notifiedContent: ContentBlock[] | undefined let notifiedSource: MessageSource | undefined let notifiedContexts: HookContext[] | undefined - ctx.on('agent/queued', (subject, acceptedContent, info) => { + ctx.on('agent/inbox/enqueue', (subject, info) => { if (subject !== agent || info.steering) return // Retain the exact notification references: cloning here would test the // listener's copy rather than the event/inbox ownership boundary. - notifiedContent = acceptedContent + notifiedContent = info.content notifiedSource = info.source notifiedContexts = info.contexts }) @@ -814,7 +818,7 @@ describe('adapter registration, routing, and accepted-input ownership', () => { source: { kind: 'plugin', plugin: 'context-source' }, meta: { version: 1 }, }] - agent.send(content, { source, contexts }) + agent.followup(content, { source, contexts }) content[0]!.text = 'caller-mutated-send' source.plugin = 'caller-mutated-source' contexts[0]!.content[0] = { type: 'text', text: 'caller-mutated-context' } @@ -863,14 +867,14 @@ describe('adapter registration, routing, and accepted-input ownership', () => { let notifiedContent: ContentBlock[] | undefined let notifiedSource: MessageSource | undefined let notifiedContexts: HookContext[] | undefined - ctx.on('agent/queued', (subject, acceptedContent, info) => { + ctx.on('agent/inbox/enqueue', (subject, info) => { if (subject !== agent || !info.steering) return - notifiedContent = acceptedContent + notifiedContent = info.content notifiedSource = info.source notifiedContexts = info.contexts }) - agent.send([{ type: 'text', text: 'start' }]) + agent.followup([{ type: 'text', text: 'start' }]) await entered.promise expect(agent.status).toBe('running') const content = [{ type: 'text' as const, text: 'accepted-steer' }] @@ -951,7 +955,7 @@ describe('adapter registration, routing, and accepted-input ownership', () => { expect(request).not.toContain('caller-mutated-steering-context-without-meta') const steeringIndex = agent.session.events.findIndex(event => event.type === 'steering/message') - const contextIndex = agent.session.events.findIndex(event => event.type === 'context/message' + const contextIndex = agent.session.events.findIndex(event => event.type === 'user/message' && event.data.source.kind === 'plugin' && event.data.source.plugin === 'steering-context') expect(steeringIndex).toBeGreaterThanOrEqual(0) expect(contextIndex).toBe(steeringIndex + 1) @@ -987,7 +991,7 @@ describe('turn numbering continues across seeded sessions', () => { const turns: number[] = [] ctx2.on('session/event', (_s, event) => { if (event.type === 'turn/start') turns.push(event.data.turn) }) - forked.send([{ type: 'text', text: 'continue' }]) + forked.followup([{ type: 'text', text: 'continue' }]) await new Promise<void>((resolve) => { ctx2.on('agent/status', (subject, status) => { if (subject === forked && status === 'idle') resolve() diff --git a/packages/core/agent-loop/tests/coverage-edges.spec.ts b/packages/core/agent-loop/tests/coverage-edges.spec.ts index 38ea3d103e..f8ff5a74b9 100644 --- a/packages/core/agent-loop/tests/coverage-edges.spec.ts +++ b/packages/core/agent-loop/tests/coverage-edges.spec.ts @@ -38,7 +38,7 @@ function waitForIdle(ctx: Context, agent: Agent): Promise<void> { } function send(agent: Agent, text: string) { - agent.send([{ type: 'text', text }]) + agent.followup([{ type: 'text', text }]) } describe('inbox acceptance', () => { @@ -47,13 +47,13 @@ describe('inbox acceptance', () => { const ctx = await harness(adapter) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) let queued = 0 - ctx.on('agent/queued', () => { queued += 1 }) + ctx.on('agent/inbox/enqueue', () => { queued += 1 }) expect(() => { - agent.send([{ type: 'text', text: 'first', bad: 1n } as never]) + agent.followup([{ type: 'text', text: 'first', bad: 1n } as never]) }).toThrow(/losslessly JSON-serializable/) expect(() => { - agent.send([{ type: 'text', text: 'first' }], { source: { kind: 'plugin', plugin: 'p', bad: 1n } as never }) + agent.followup([{ type: 'text', text: 'first' }], { source: { kind: 'plugin', plugin: 'p', bad: 1n } as never }) }).toThrow(/losslessly JSON-serializable/) expect(queued).toBe(0) expect(agent.session.events).toHaveLength(0) diff --git a/packages/core/agent-loop/tests/inbox-invariant.spec.ts b/packages/core/agent-loop/tests/inbox-invariant.spec.ts new file mode 100644 index 0000000000..0d907f26d7 --- /dev/null +++ b/packages/core/agent-loop/tests/inbox-invariant.spec.ts @@ -0,0 +1,155 @@ +/** + * Regression: the dsh-agent FIFO-conservation invariant must stay balanced on + * the loop-authored continuation-reason steering path. A continue-with-reason + * decision enters the steering FIFO and later drains (or is discarded by + * cancel); both must be matched by an enqueue event so the invariant's + * outstanding count never goes negative. + * @module dsh-agent-loop/tests/inbox-invariant + */ + +import { describe, expect, it, vi } from 'vitest' +import { Context } from 'cordis' +import LlmService from '@deepseek-ai/dsh-llm' +import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' +import SystemPrompt from '@deepseek-ai/dsh-system-prompt' +import ToolRegistry from '@deepseek-ai/dsh-tools' +import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' +import * as AgentInvariant from '@deepseek-ai/dsh-agent/invariant' +import InvariantService from '@deepseek-ai/dsh-invariants' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' +import { MockAdapter, textResponse } from './mock-adapter.ts' + +async function harness(adapter: MockAdapter) { + const ctx = new Context() + await ctx.plugin(LlmService) + await ctx.plugin(SessionStore) + await ctx.plugin(SystemPrompt) + await ctx.plugin(ToolRegistry) + await ctx.plugin(AgentRegistry) + await ctx.plugin(InvariantService) + await ctx.plugin(AgentInvariant) + await ctx.plugin(AgentLoop, { agents: [] }) + ctx.llm.registerAdapter(['mock'], adapter) + return ctx +} + +function waitForIdle(ctx: Context, agent: Agent): Promise<void> { + return new Promise((resolve) => { + const dispose = ctx.on('agent/status', (subject, status) => { + if (subject === agent && status === 'idle') { dispose(); resolve() } + }) + }) +} + +describe('inbox FIFO-conservation invariant', () => { + it('stays balanced when a continuation reason enters and drains the steering FIFO', async () => { + const adapter = new MockAdapter([textResponse('step 1'), textResponse('step 2')]) + const ctx = await harness(adapter) + const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) + + let forced = false + ctx.on('agent/turn-continuation', async (_agent, _turn, _default, _signal, next) => { + if (forced) return next() + forced = true + return { action: 'continue' as const, reason: { content: [{ type: 'text', text: 'keep going' }], source: { kind: 'plugin', plugin: 'loop' } } } + }) + + agent.followup([{ type: 'text', text: 'go' }]) + await waitForIdle(ctx, agent) + + expect(adapter.requests).toHaveLength(2) + // The continuation reason drained as a steering/message on the second step. + expect(agent.session.events.some(e => e.type === 'steering/message')).toBe(true) + // No invariant violation was logged. + expect(warn.mock.calls.flat().some(arg => String(arg).includes('agent/inbox'))).toBe(false) + expect(warn.mock.calls.flat().some(arg => String(arg).includes('INVARIANT'))).toBe(false) + }) + + it('stays balanced when cancel discards a pending continuation reason', async () => { + const adapter = new MockAdapter([textResponse('only step')]) + const ctx = await harness(adapter) + const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) + + // Force a continuation reason, then cancel from the same checkpoint so the + // reason sits in the steering FIFO when the inbox is discarded. + ctx.on('agent/turn-continuation', async (subject, _turn, _default, _signal, next) => { + if (subject !== agent) return next() + queueMicrotask(() => { agent.cancel({ kind: 'user' }) }) + return { action: 'continue' as const, reason: { content: [{ type: 'text', text: 'keep going' }], source: { kind: 'plugin', plugin: 'loop' } } } + }) + + agent.followup([{ type: 'text', text: 'go' }]) + await waitForIdle(ctx, agent) + + expect(warn.mock.calls.flat().some(arg => String(arg).includes('agent/inbox'))).toBe(false) + expect(warn.mock.calls.flat().some(arg => String(arg).includes('INVARIANT'))).toBe(false) + }) + + it('stays balanced when a terminal stop discards pending steering', async () => { + const adapter = new MockAdapter([textResponse('done')]) + const ctx = await harness(adapter) + const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) + + const discards: number[] = [] + ctx.on('agent/inbox/discard', (subject, messages) => { if (subject === agent) discards.push(messages.length) }) + + // A continuation reason enqueues a steering item; a terminal stop then drops + // it. The drop must emit a discard so the enqueue ⇒ dequeue-or-discard + // ledger stays balanced (no dangling outstanding id). + ctx.on('agent/turn-continuation', async (subject, _turn, _default, _signal, next) => { + if (subject !== agent) return next() + return { action: 'continue' as const, reason: { content: [{ type: 'text', text: 'keep going' }], source: { kind: 'plugin', plugin: 'loop' } } } + }) + let stopped = false + ctx.on('agent/turn-stop', (subject) => { + if (subject !== agent || stopped) return undefined + stopped = true + return { action: 'stop' as const } + }) + + agent.followup([{ type: 'text', text: 'go' }]) + await waitForIdle(ctx, agent) + + expect(discards).toEqual([1]) // the dropped steering item was reported + expect(warn.mock.calls.flat().some(arg => String(arg).includes('agent/inbox'))).toBe(false) + expect(warn.mock.calls.flat().some(arg => String(arg).includes('INVARIANT'))).toBe(false) + }) + + it('stays balanced when late steering lands after a terminal stop (post-turn flush window)', async () => { + const adapter = new MockAdapter([textResponse('done')]) + const ctx = await harness(adapter) + const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) + + let enqueues = 0 + const discards: number[] = [] + ctx.on('agent/inbox/enqueue', (subject) => { if (subject === agent) enqueues += 1 }) + ctx.on('agent/inbox/discard', (subject, messages) => { if (subject === agent) discards.push(messages.length) }) + + // Terminal-stop the turn, then steer during the post-turn flush window + // (status is still running). That late steer is drained by runLoop and + // dropped because the turn terminally stopped; it must still be discarded so + // its enqueue is matched (the drain sits on a different code path than the + // in-turn terminal-stop drop). + ctx.on('agent/turn-stop', subject => (subject === agent ? { action: 'stop' as const } : undefined)) + let steered = false + ctx.on('session/flush', (session) => { + if (session !== agent.session || steered) return + steered = true + agent.steer([{ type: 'text', text: 'late' }], { source: { kind: 'plugin', plugin: 'late' } }) + }) + + agent.followup([{ type: 'text', text: 'go' }]) + await waitForIdle(ctx, agent) + + // The prompt plus the late steer both enqueued; both are matched (the prompt + // dequeued, the late steer discarded) so no id is left outstanding. + expect(enqueues).toBe(2) + expect(discards).toEqual([1]) + expect(warn.mock.calls.flat().some(arg => String(arg).includes('agent/inbox'))).toBe(false) + expect(warn.mock.calls.flat().some(arg => String(arg).includes('INVARIANT'))).toBe(false) + }) +}) diff --git a/packages/core/agent-loop/tests/inbox.spec.ts b/packages/core/agent-loop/tests/inbox.spec.ts index 99cae1ae77..289cd2f6d5 100644 --- a/packages/core/agent-loop/tests/inbox.spec.ts +++ b/packages/core/agent-loop/tests/inbox.spec.ts @@ -1,10 +1,20 @@ import { describe, expect, it } from 'vitest' -import { Inbox } from '../src/inbox.ts' +import { AgentMessageId } from '@deepseek-ai/dsh-agent' +import { Inbox, agentMessage } from '../src/inbox.ts' function message(text: string) { - return { content: [{ type: 'text' as const, text }], source: { kind: 'user' as const }, contexts: [] } + return { id: AgentMessageId(text), content: [{ type: 'text' as const, text }], source: { kind: 'user' as const }, contexts: [], wakeup: true } } +describe('agentMessage', () => { + it('returns a frozen payload so a listener cannot mutate it for later listeners', () => { + const payload = agentMessage(message('m'), false) + expect(Object.isFrozen(payload)).toBe(true) + expect(() => { (payload as { id: string }).id = 'mutated' }).toThrow() + expect(payload.id).toBe(AgentMessageId('m')) + }) +}) + function resolverPair() { let r!: () => void const p = new Promise<void>((resolve) => { r = resolve }) @@ -25,6 +35,32 @@ describe('Inbox', () => { expect(inbox.dequeueQueued()).toBeUndefined() }) + it('enqueue(msg, false) queues without waking a parked waiter', async () => { + const inbox = new Inbox() + let woke = false + const waiter = inbox.waitForQueued(new Promise(() => {})).then(() => { woke = true }) + inbox.enqueue(message('quiet'), false) + // The item is queued, but the parked waiter was not resolved by it. + expect(inbox.hasQueued).toBe(true) + await Promise.resolve() + expect(woke).toBe(false) + // A later waking enqueue resolves the same waiter. + inbox.enqueue(message('loud')) + await waiter + expect(woke).toBe(true) + }) + + it('pending() snapshots queued then steering without removing them', () => { + const inbox = new Inbox() + inbox.enqueue(message('q')) + inbox.steer(message('s')) + const pending = inbox.pending() + expect(pending.map(p => p.steering)).toEqual([false, true]) + // Snapshot does not drain the FIFOs. + expect(inbox.hasQueued).toBe(true) + expect(inbox.hasSteering).toBe(true) + }) + it('pushes and drains steering messages separately from queued', () => { const inbox = new Inbox() inbox.steer(message('steer')) diff --git a/packages/core/agent-loop/tests/interception.spec.ts b/packages/core/agent-loop/tests/interception.spec.ts index 9e1663dcfe..de721b1653 100644 --- a/packages/core/agent-loop/tests/interception.spec.ts +++ b/packages/core/agent-loop/tests/interception.spec.ts @@ -42,7 +42,7 @@ function waitForIdle(ctx: Context, agent: Agent): Promise<void> { } function send(agent: Agent, text: string) { - agent.send([{ type: 'text', text }]) + agent.followup([{ type: 'text', text }]) } function events(agent: Agent): SessionEvent[] { @@ -87,7 +87,7 @@ describe('agent/prompt-submit', () => { expect(JSON.stringify(adapter.requests[0]!.messages)).not.toContain('original') }) - it('allow with additionalContexts injects separate context/message events into the turn', async () => { + it('allow with additionalContexts injects separate injected-context user messages into the turn', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) @@ -107,12 +107,12 @@ describe('agent/prompt-submit', () => { await waitForIdle(ctx, agent) const log = events(agent) - const userMsg = log.find(e => e.type === 'user/message') - const ctxMsg = log.find(e => e.type === 'context/message') + const userMsg = log.find(e => e.type === 'user/message' && e.data.source.kind === 'user') + const ctxMsg = log.find(e => e.type === 'user/message' && e.data.source.kind === 'plugin') expect(userMsg).toBeDefined() - expect(ctxMsg?.type === 'context/message' && ctxMsg.data.content).toEqual([{ type: 'text', text: '<system-reminder>extra ctx</system-reminder>' }]) - expect(ctxMsg?.type === 'context/message' && ctxMsg.data.source).toEqual({ kind: 'plugin', plugin: 'test' }) - expect(ctxMsg?.type === 'context/message' && ctxMsg.data.meta).toEqual(meta) + expect(ctxMsg?.type === 'user/message' && ctxMsg.data.content).toEqual([{ type: 'text', text: '<system-reminder>extra ctx</system-reminder>' }]) + expect(ctxMsg?.type === 'user/message' && ctxMsg.data.source).toEqual({ kind: 'plugin', plugin: 'test' }) + expect(ctxMsg?.type === 'user/message' && ctxMsg.data.meta).toEqual(meta) const sent = JSON.stringify(adapter.requests[0]!.messages) expect(sent).toContain('extra ctx') }) @@ -128,7 +128,7 @@ describe('agent/prompt-submit', () => { ? downstream : { ...downstream, content: [{ type: 'text', text: 'rewritten request' }] } }) - agent.send([{ type: 'text', text: 'original request' }], { + agent.followup([{ type: 'text', text: 'original request' }], { contexts: [{ content: [{ type: 'text', text: 'untrusted prefix' }], source: { kind: 'plugin', plugin: 'prefix' }, @@ -155,7 +155,7 @@ describe('agent/prompt-submit', () => { }], }, }) - expect(log.some(event => event.type === 'context/message')).toBe(false) + expect(log.some(event => event.type === 'user/message' && event.data.source.kind === 'plugin')).toBe(false) expect(adapter.requests[0]?.messages.at(-1)).toEqual({ role: 'user', content: [ @@ -203,7 +203,7 @@ describe('agent/prompt-submit', () => { const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event: SessionEvent) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) - agent.send([{ type: 'text', text: 'do something' }], { + agent.followup([{ type: 'text', text: 'do something' }], { contexts: [{ content: [{ type: 'text', text: 'must be dropped' }], source: { kind: 'plugin', plugin: 'test' } }], }) await waitForIdle(ctx, agent) @@ -215,7 +215,6 @@ describe('agent/prompt-submit', () => { expect(log.some(e => e.type === 'turn/start')).toBe(true) expect(log.some(e => e.type === 'turn/end')).toBe(true) expect(log.some(e => e.type === 'user/message')).toBe(false) - expect(log.some(e => e.type === 'context/message')).toBe(false) expect(log.some(e => e.type === 'step/start')).toBe(false) // the veto is recorded durably as a prompt/blocked in the open turn const blocked = log.find(e => e.type === 'prompt/blocked') @@ -340,8 +339,8 @@ describe('agent/session-start', () => { // the injected context reached the model on the first (only) request expect(JSON.stringify(adapter.requests[0]!.messages)).toContain('session preamble') // and is recorded with the plugin source, never mislabeled as a user prompt - const ctxMsg = events(agent).find(e => e.type === 'context/message') - expect(ctxMsg?.type === 'context/message' && ctxMsg.data.source).toEqual({ kind: 'plugin', plugin: 'test' }) + const ctxMsg = events(agent).find(e => e.type === 'user/message' && e.data.source.kind === 'plugin') + expect(ctxMsg?.type === 'user/message' && ctxMsg.data.source).toEqual({ kind: 'plugin', plugin: 'test' }) }) it('a throwing session-start listener does not abort agent construction', async () => { @@ -624,23 +623,22 @@ describe('tool additionalContexts buffering across a step', () => { send(agent, 'go') await waitForIdle(ctx, agent) - // Event order in the log: both tool/results, THEN both context/messages — + // Event order in the log: both tool/results, THEN both injected contexts — // never interleaved (which would break tool-call/result adjacency). - const types = events(agent).map(e => e.type) - const firstResult = types.indexOf('tool/result') - const lastResult = types.lastIndexOf('tool/result') - const firstCtx = types.indexOf('context/message') + const injected = events(agent).filter(e => e.type === 'user/message' && e.data.source.kind === 'plugin') + const seqs = events(agent) + const firstResult = seqs.findIndex(e => e.type === 'tool/result') + const lastResult = seqs.map(e => e.type).lastIndexOf('tool/result') + const firstCtx = seqs.findIndex(e => e === injected[0]) expect(firstResult).toBeGreaterThanOrEqual(0) expect(lastResult).toBeGreaterThan(firstResult) // two results expect(firstCtx).toBeGreaterThan(lastResult) // context only after ALL results // both contexts present - const ctxTexts = events(agent) - .filter(e => e.type === 'context/message') - .flatMap(e => (e.type === 'context/message' ? e.data.content : [])) + const ctxTexts = injected + .flatMap(e => (e.type === 'user/message' ? e.data.content : [])) .map(b => (b.type === 'text' ? b.text : '')) expect(ctxTexts).toEqual(['ctx-c1', 'ctx-c2']) - const contextEvents = events(agent).filter(e => e.type === 'context/message') - expect(contextEvents.map(e => e.type === 'context/message' && e.data.meta)).toEqual([{ callId: 'c1' }, { callId: 'c2' }]) + expect(injected.map(e => e.type === 'user/message' && e.data.meta)).toEqual([{ callId: 'c1' }, { callId: 'c2' }]) }) it('appends multiple contexts deferred by one composite tool after its outer result', async () => { @@ -661,14 +659,14 @@ describe('tool additionalContexts buffering across a step', () => { const log = events(agent) const resultIndex = log.findIndex(event => event.type === 'tool/result') - const contextEvents = log.filter(event => event.type === 'context/message') + const contextEvents = log.filter(event => event.type === 'user/message' && event.data.source.kind === 'plugin') expect(resultIndex).toBeGreaterThanOrEqual(0) expect(log.findIndex(event => event === contextEvents[0])).toBeGreaterThan(resultIndex) - expect(contextEvents.map(event => event.type === 'context/message' && event.data.source)).toEqual([ + expect(contextEvents.map(event => event.type === 'user/message' && event.data.source)).toEqual([ { kind: 'plugin', plugin: 'a' }, { kind: 'plugin', plugin: 'b' }, ]) - expect(contextEvents.map(event => event.type === 'context/message' && event.data.meta)).toEqual([{ order: 1 }, { order: 2 }]) + expect(contextEvents.map(event => event.type === 'user/message' && event.data.meta)).toEqual([{ order: 1 }, { order: 2 }]) }) }) @@ -750,13 +748,13 @@ describe('worked example: a native hook plugin is just a cordis plugin on the se const log = events(agent) // session-start preamble injected - expect(log.some(e => e.type === 'context/message' + expect(log.some(e => e.type === 'user/message' && e.data.source.kind === 'plugin' && e.data.content.some(b => b.type === 'text' && b.text.includes('policy active (started: startup)')))).toBe(true) - // prompt allowed → user/message recorded - expect(log.some(e => e.type === 'user/message')).toBe(true) + // prompt allowed → user-sourced user/message recorded + expect(log.some(e => e.type === 'user/message' && e.data.source.kind === 'user')).toBe(true) // tool ran (echo allowed) and post-execute attached "audited" context expect(log.some(e => e.type === 'tool/result' && !e.data.isError)).toBe(true) - expect(log.some(e => e.type === 'context/message' + expect(log.some(e => e.type === 'user/message' && e.data.source.kind === 'plugin' && e.data.content.some(b => b.type === 'text' && b.text === 'audited'))).toBe(true) // NO hook/* events — a native plugin needs none expect(log.some(e => e.type.startsWith('hook/'))).toBe(false) diff --git a/packages/core/agent-loop/tests/invariant.spec.ts b/packages/core/agent-loop/tests/invariant.spec.ts index aa8bd5d6d5..cb0dcd2384 100644 --- a/packages/core/agent-loop/tests/invariant.spec.ts +++ b/packages/core/agent-loop/tests/invariant.spec.ts @@ -42,7 +42,7 @@ describe('request-reconstruction invariant', () => { it('uses the step boundary rather than content appended afterward', async () => { const { ctx, session, boundary } = await requestSetup() - session.append('context/message', { content: [{ type: 'text', text: '[late]' }], source: { kind: 'plugin', plugin: 'x' } }, { surfaceOp: 'append' }) + session.append('user/message', { content: [{ type: 'text', text: '[late]' }], source: { kind: 'plugin', plugin: 'x' } }, { surfaceOp: 'append' }) const options = loopRequest({ model: 'm', messages: Object.freeze(boundary), sessionId: session.id }) expect(() => { dispatch(ctx, options) }).not.toThrow() }) diff --git a/packages/core/agent-loop/tests/loop.spec.ts b/packages/core/agent-loop/tests/loop.spec.ts index f8f1901a20..8875b51d67 100644 --- a/packages/core/agent-loop/tests/loop.spec.ts +++ b/packages/core/agent-loop/tests/loop.spec.ts @@ -42,7 +42,7 @@ function waitForIdle(ctx: Context, agent: Agent): Promise<void> { } function send(agent: Agent, text: string) { - agent.send([{ type: 'text', text }]) + agent.followup([{ type: 'text', text }]) } describe('agent loop', () => { @@ -391,7 +391,7 @@ describe('agent loop', () => { const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) agent.inject([{ type: 'text', text: 'file changed: a.ts' }], { source: { kind: 'plugin', plugin: 'watcher' } }) - // The idle inject records a self-contained turn (turn/start → context/message + // The idle inject records a self-contained turn (turn/start → user/message // → turn/end) so the event stays turn-enclosed, but does NOT run the model. await new Promise(r => setTimeout(r, 20)) expect(agent.status).toBe('idle') @@ -427,8 +427,8 @@ describe('agent loop', () => { send(agent, 'go') await waitForIdle(ctx, agent) - const contextEvent = agent.session.events.find(event => event.type === 'context/message') - expect(contextEvent?.type === 'context/message' && contextEvent.data).toMatchObject({ meta }) + const contextEvent = agent.session.events.find(event => event.type === 'user/message' && event.data.source.kind === 'plugin') + expect(contextEvent?.type === 'user/message' && contextEvent.data).toMatchObject({ meta }) const requestText = JSON.stringify(adapter.requests[0]!.messages) expect(requestText).toContain('Additional instructions from: pkg/AGENTS.md') expect(requestText).not.toContain('<context source=') @@ -456,7 +456,7 @@ describe('agent loop', () => { }) first.text = 'mutated after inject' agent.inject([{ type: 'text', text: 'second notice' }], { source: { kind: 'plugin', plugin: 'x' } }) - visibleDuringTool = agent.session.events.some(e => e.type === 'context/message') + visibleDuringTool = agent.session.events.some(e => e.type === 'user/message' && e.data.source.kind === 'plugin') return [{ type: 'text', text: 'ok' }] }, })) @@ -473,13 +473,13 @@ describe('agent loop', () => { const ts0 = turnStarts[0]! expect(ts0.type === 'turn/start' && ts0.data.trigger.kind).toBe('message') const result = agent.session.events.find(e => e.type === 'tool/result')! - const contexts = agent.session.events.filter(e => e.type === 'context/message') + const contexts = agent.session.events.filter(e => e.type === 'user/message' && e.data.source.kind === 'plugin') expect(contexts).toHaveLength(2) expect(result.seq).toBeLessThan(contexts[0]!.seq) - expect(contexts[0]?.type === 'context/message' && contexts[0].data).toMatchObject({ + expect(contexts[0]?.type === 'user/message' && contexts[0].data).toMatchObject({ meta, }) - expect(contexts.flatMap(event => event.type === 'context/message' ? event.data.content : [])) + expect(contexts.flatMap(event => event.type === 'user/message' ? event.data.content : [])) .toEqual([ { type: 'text', text: 'mid-turn notice' }, { type: 'text', text: 'second notice' }, @@ -523,7 +523,29 @@ describe('agent loop', () => { send(agent, 'go') await waitForIdle(ctx, agent) - expect(agent.session.events.some(event => event.type === 'context/message')).toBe(false) + expect(agent.session.events.some(event => event.type === 'user/message' && event.data.source.kind === 'plugin')).toBe(false) + }) + + it('preserves SendOptions.meta on the durable user/message and steering/message', async () => { + const adapter = new MockAdapter([toolCallResponse('c1', 'noop', {}), textResponse('done')]) + const ctx = await harness(adapter) + ctx.tools.register(defineContentToolFixture({ + name: 'noop', description: '', parameters: {}, + async execute() { + // Running steer carries its own meta onto the durable steering/message. + agent.steer([{ type: 'text', text: 's' }], { source: { kind: 'plugin', plugin: 'p' }, meta: { steer: 1 } }) + return [] + }, + })) + const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) + + agent.followup([{ type: 'text', text: 'go' }], { meta: { prompt: 1 } }) + await waitForIdle(ctx, agent) + + const user = agent.session.events.find(e => e.type === 'user/message') + expect(user?.type === 'user/message' && user.data.meta).toEqual({ prompt: 1 }) + const steering = agent.session.events.find(e => e.type === 'steering/message') + expect(steering?.type === 'steering/message' && steering.data.meta).toEqual({ steer: 1 }) }) it('agent/turn-continuation can force-continue (/loop pattern) and force-stop', async () => { @@ -632,7 +654,7 @@ describe('agent loop', () => { ctx.on('agent/pre-step', (subject) => { if (subject === agent && !injected) { injected = true - subject.session.append('context/message', { + subject.session.append('user/message', { content: [{ type: 'text', text: 'INJECTED-IN-PRE-STEP' }], source: { kind: 'plugin', plugin: 'test' }, }, { surfaceOp: 'append' }) @@ -650,7 +672,7 @@ describe('agent loop', () => { // And the injected event sits BEFORE the first step/start in the log — // the seam fired outside the step. const events = agent.session.events - const injectedSeq = events.find(e => e.type === 'context/message')!.seq + const injectedSeq = events.find(e => e.type === 'user/message' && e.data.source.kind === 'plugin')!.seq const firstStepStartSeq = events.find(e => e.type === 'step/start')!.seq expect(injectedSeq).toBeLessThan(firstStepStartSeq) }) @@ -1028,13 +1050,13 @@ describe('agent loop', () => { expect(JSON.stringify(adapter.requests[1]!.messages)).toContain('turn-end listener message') }) - it('keeps a reentrant agent/queued send as the next independent turn', async () => { + it('keeps a reentrant agent/inbox/enqueue send as the next independent turn', async () => { const adapter = new MockAdapter([textResponse('first'), textResponse('second')]) const ctx = await harness(adapter) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) let nested = false - ctx.on('agent/queued', (subject) => { + ctx.on('agent/inbox/enqueue', (subject) => { if (subject !== agent || nested) return nested = true send(agent, 'queued listener message') @@ -1061,9 +1083,9 @@ describe('agent loop', () => { const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) const idle = waitForIdle(ctx, agent) - agent.send([{ type: 'text', text: 'user message' }]) + agent.followup([{ type: 'text', text: 'user message' }]) await Promise.resolve() - agent.send( + agent.followup( [{ type: 'text', text: 'plugin message' }], { source: { kind: 'plugin', plugin: 'test' } }, ) diff --git a/packages/core/agent-loop/tests/properties.spec.ts b/packages/core/agent-loop/tests/properties.spec.ts index 85efda0e4e..593b32ab38 100644 --- a/packages/core/agent-loop/tests/properties.spec.ts +++ b/packages/core/agent-loop/tests/properties.spec.ts @@ -115,7 +115,7 @@ describe('agent loop scheduling properties', () => { const { seen: trace } = recordStatus(ctx, agent) const idle = nextIdle(ctx, agent) // Send all in one synchronous tick: they queue before the loop wakes. - for (const text of texts) agent.send([{ type: 'text', text }]) + for (const text of texts) agent.followup([{ type: 'text', text }]) await idle // No message lost: every send appears as a user/message, in order. @@ -142,7 +142,7 @@ describe('agent loop scheduling properties', () => { const agent = ctx.agentLoop.create(SessionId('a'), { provider: 'mock', model: 'mock' }) for (const text of texts) { const idle = nextIdle(ctx, agent) - agent.send([{ type: 'text', text }]) + agent.followup([{ type: 'text', text }]) await idle } // Each send was drained at a separate turn start: N turns, 1..N. @@ -171,7 +171,7 @@ describe('agent loop scheduling properties', () => { for (const step of steps) { const idle = nextIdle(ctx, agent) lastIdle = idle - agent.send([{ type: 'text', text: step.text }]) + agent.followup([{ type: 'text', text: step.text }]) if (step.settle) await idle } await lastIdle diff --git a/packages/core/agent-loop/tests/request-cache.e2e.ts b/packages/core/agent-loop/tests/request-cache.e2e.ts index f1e1a1a367..37079b8565 100644 --- a/packages/core/agent-loop/tests/request-cache.e2e.ts +++ b/packages/core/agent-loop/tests/request-cache.e2e.ts @@ -73,10 +73,10 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('log-derived request cache hits ( const agent = ctx.agentLoop.create(SessionId('cache-e2e'), { provider: 'deepseek', model: 'deepseek-v4-flash' }) // Turn 1: forces a tool call → at least two steps (two model requests). - agent.send([{ type: 'text', text: 'Look up the key "deploy-color" with the lookup tool and tell me the value.' }]) + agent.followup([{ type: 'text', text: 'Look up the key "deploy-color" with the lookup tool and tell me the value.' }]) await waitForIdle(ctx, agent) // Turn 2: a follow-up over the same (longer) prefix. - agent.send([{ type: 'text', text: 'Thanks. Repeat that value one more time.' }]) + agent.followup([{ type: 'text', text: 'Thanks. Repeat that value one more time.' }]) await waitForIdle(ctx, agent) const usages = [...agent.session.events] diff --git a/packages/core/agent-loop/tests/request-reconstruction.spec.ts b/packages/core/agent-loop/tests/request-reconstruction.spec.ts index 63c59618e3..a73218f345 100644 --- a/packages/core/agent-loop/tests/request-reconstruction.spec.ts +++ b/packages/core/agent-loop/tests/request-reconstruction.spec.ts @@ -41,7 +41,7 @@ function waitForIdle(ctx: Context, agent: Agent): Promise<void> { } function send(agent: Agent, text: string) { - agent.send([{ type: 'text', text }]) + agent.followup([{ type: 'text', text }]) } /** Assert `previous` is a strict value-prefix of `current`. */ @@ -118,7 +118,7 @@ describe('request stability across the loop', () => { preStep() const session = agent.session const nodes = session.surface.nodes - session.append('context/message', { + session.append('user/message', { content: [{ type: 'text', text: '[summary of turn 1]' }], source: { kind: 'plugin', plugin: 'test-compact' }, }, { @@ -180,7 +180,7 @@ describe('request stability across the loop', () => { const first = adapter.requests[0]! // The inject landed in the log after the boundary: not in THIS request… expect(first.messages.some(m => m.content.some(b => b.type === 'text' && b.text.includes('[late context]')))).toBe(false) - expect(agent.session.events.some(e => e.type === 'context/message')).toBe(true) + expect(agent.session.events.some(e => e.type === 'user/message' && e.data.source.kind === 'plugin')).toBe(true) send(agent, 'second') await waitForIdle(ctx, agent) diff --git a/packages/core/agent-loop/tests/request-recovery.spec.ts b/packages/core/agent-loop/tests/request-recovery.spec.ts index 3bbfeba47f..1fc44e3431 100644 --- a/packages/core/agent-loop/tests/request-recovery.spec.ts +++ b/packages/core/agent-loop/tests/request-recovery.spec.ts @@ -114,7 +114,7 @@ function waitForIdle(ctx: Context, agent: Agent): Promise<void> { } function send(agent: Agent): void { - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) } function contextError(message = 'context too large'): LlmError { @@ -154,12 +154,15 @@ describe('agent post-step and request-error lifecycle', () => { const agent = ctx.agentLoop.create(SessionId('post-step-order'), { provider: 'mock', model: 'mock' }) const order: string[] = [] ctx.on('session/event', (_session, event) => { + // Injected context is a plugin-sourced user/message; the direct human + // prompt (user source) stays untracked as before. + const isInjected = event.type === 'user/message' && event.data.source.kind !== 'user' if ( event.type === 'assistant/message' || event.type === 'tool/call' - || event.type === 'tool/result' || event.type === 'context/message' + || event.type === 'tool/result' || isInjected || event.type === 'steering/message' || event.type === 'step/end' ) { - if (!('step' in event.data) || event.data.step === 1) order.push(event.type) + if (!('step' in event.data) || event.data.step === 1) order.push(isInjected ? 'context/message' : event.type) } }) ctx.on('agent/post-step', (subject, turn, step, signal) => { @@ -271,7 +274,7 @@ describe('agent post-step and request-error lifecycle', () => { expect({ turn, step, code: error.code }).toEqual({ turn: 1, step: 1, code: CONTEXT_WINDOW_EXCEEDED_CODE }) expect(facts.code).toBe(CONTEXT_WINDOW_EXCEEDED_CODE) attempts.push(history.length) - subject.session.append('context/message', { + subject.session.append('user/message', { content: [{ type: 'text', text: 'RECOVERY SURFACE MUTATION' }], source: { kind: 'plugin', plugin: 'test-recovery' }, }, { surfaceOp: 'append' }) @@ -288,7 +291,7 @@ describe('agent post-step and request-error lifecycle', () => { const ends = agent.session.events.filter(event => event.type === 'step/end') expect(starts.map(event => event.data.step)).toEqual([1, 2]) expect(ends.map(event => event.data.step)).toEqual([1, 2]) - const recovery = agent.session.events.find(event => event.type === 'context/message')! + const recovery = agent.session.events.find(event => event.type === 'user/message' && event.data.source.kind === 'plugin')! expect(ends[0]!.seq).toBeLessThan(recovery.seq) expect(recovery.seq).toBeLessThan(starts[1]!.seq) }) diff --git a/packages/core/agent-loop/tests/resume.spec.ts b/packages/core/agent-loop/tests/resume.spec.ts index fdf5c39514..a9bd0a0355 100644 --- a/packages/core/agent-loop/tests/resume.spec.ts +++ b/packages/core/agent-loop/tests/resume.spec.ts @@ -146,7 +146,7 @@ describe('the session-persistence Agent Note: AgentLoop factory create/resume', const adapter1 = new MockAdapter([textResponse('a')]) const { ctx: ctx1, root } = await persistentHarness(adapter1) const a1 = (await ctx1.agents.create({ sessionId: SessionId('nocwd-sess') })).agent - a1.send([{ type: 'text', text: 'q' }], { source: { kind: 'user' } }) + a1.followup([{ type: 'text', text: 'q' }], { source: { kind: 'user' } }) await waitForIdle(ctx1, a1) await ctx1.fiber.dispose() @@ -174,7 +174,7 @@ describe('the session-persistence Agent Note: AgentLoop factory create/resume', ctx1.on('agent/session-start', (_agent, source) => void sources1.push(source)) const a1 = (await ctx1.agents.create({ sessionId: SessionId('start-sess') })).agent expect(sources1).toEqual(['startup']) - a1.send([{ type: 'text', text: 'q' }], { source: { kind: 'user' } }) + a1.followup([{ type: 'text', text: 'q' }], { source: { kind: 'user' } }) await waitForIdle(ctx1, a1) await ctx1.fiber.dispose() @@ -480,7 +480,7 @@ describe('the session-persistence Agent Note: AgentLoop factory create/resume', const adapter1 = new MockAdapter([textResponse('answer')]) const { ctx: ctx1, root } = await persistentHarness(adapter1) const a1 = (await ctx1.agents.create({ sessionId: SessionId('inject-sess'), meta: { cwd: '/w' } })).agent - a1.send([{ type: 'text', text: 'q' }], { source: { kind: 'user' } }) + a1.followup([{ type: 'text', text: 'q' }], { source: { kind: 'user' } }) await waitForIdle(ctx1, a1) a1.inject([{ type: 'text', text: 'background task 42 finished' }], { source: { kind: 'plugin', plugin: 'tool-bash' } }) // Let inject()'s fire-and-forget flush settle (NO explicit flush/dispose). @@ -503,7 +503,7 @@ describe('the session-persistence Agent Note: AgentLoop factory create/resume', const adapter1 = new MockAdapter([textResponse('answer')]) const { ctx: ctx1, root } = await persistentHarness(adapter1) const a1 = (await ctx1.agents.create({ sessionId: SessionId('inject-sess'), meta: { cwd: '/w' } })).agent - a1.send([{ type: 'text', text: 'q' }], { source: { kind: 'user' } }) + a1.followup([{ type: 'text', text: 'q' }], { source: { kind: 'user' } }) await waitForIdle(ctx1, a1) a1.inject([{ type: 'text', text: 'background task 42 finished' }], { source: { kind: 'plugin', plugin: 'tool-bash' } }) await ctx1.sessions.flush(a1.session) @@ -531,7 +531,7 @@ describe('the session-persistence Agent Note: AgentLoop factory create/resume', const adapter1 = new MockAdapter([textResponse('first answer')]) const { ctx: ctx1, root } = await persistentHarness(adapter1) const a1 = (await ctx1.agents.create({ sessionId: SessionId('sess-resume'), meta: { cwd: '/w' } })).agent - a1.send([{ type: 'text', text: 'first question' }], { source: { kind: 'user' } }) + a1.followup([{ type: 'text', text: 'first question' }], { source: { kind: 'user' } }) await waitForIdle(ctx1, a1) const events1 = [...a1.session.events] const seqs1 = events1.map(e => e.seq) @@ -558,7 +558,7 @@ describe('the session-persistence Agent Note: AgentLoop factory create/resume', expect(a2.session.deriveMessages()).toEqual(replay.deriveMessages()) // …and a new turn continues numbering (turn 2) with contiguous seqs. - a2.send([{ type: 'text', text: 'second question' }], { source: { kind: 'user' } }) + a2.followup([{ type: 'text', text: 'second question' }], { source: { kind: 'user' } }) await waitForIdle(ctx2, a2) const allSeqs = a2.session.events.map(e => e.seq) expect(allSeqs).toEqual(allSeqs.map((_, i) => i)) // 0..N contiguous, no duplicates diff --git a/packages/core/agent-loop/tests/scope-lifecycle.spec.ts b/packages/core/agent-loop/tests/scope-lifecycle.spec.ts index 469a815d8b..8844e5c1a3 100644 --- a/packages/core/agent-loop/tests/scope-lifecycle.spec.ts +++ b/packages/core/agent-loop/tests/scope-lifecycle.spec.ts @@ -203,11 +203,11 @@ describe('agent scope lifecycle', () => { if (event.type === 'user/message') heard.push('a-sees:user-message') }) - b.send(text('for b')) + b.followup(text('for b')) await waitForIdle(ctx, b) expect(heard).toEqual([]) // nothing of b's leaked into a's scope - a.send(text('for a')) + a.followup(text('for a')) await waitForIdle(ctx, a) expect(heard).toContain('a-sees:a:running') expect(heard).toContain('a-sees:user-message') @@ -934,7 +934,7 @@ describe('agent scope lifecycle', () => { if (event.type === 'turn/start') { off(); resolve() } }) }) - agent.send(text('work')) + agent.followup(text('work')) await turnOpen await owner.dispose() expect(order).toEqual(['turn-end', 'disposed(listed=false)', 'session-still-stored=true']) diff --git a/packages/core/agent-loop/tests/tool-calls.spec.ts b/packages/core/agent-loop/tests/tool-calls.spec.ts index 93378142b3..0e7f1313cb 100644 --- a/packages/core/agent-loop/tests/tool-calls.spec.ts +++ b/packages/core/agent-loop/tests/tool-calls.spec.ts @@ -105,7 +105,7 @@ describe('tool-call scheduler: grouping and barriers', () => { ctx.tools.register(gated.tool) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await until(() => gated.started.length === 3) expect(gated.started).toEqual(['1', '2', '3']) gated.release('1'); gated.release('2'); gated.release('3') @@ -133,7 +133,7 @@ describe('tool-call scheduler: grouping and barriers', () => { async execute(args) { order.push(`w-${args.id}`); return [{ type: 'text', text: 'w' }] }, })) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(order).toEqual(['r-start-A1', 'r-end-A1', 'w-A2', 'r-start-A3', 'r-end-A3']) @@ -169,7 +169,7 @@ describe('tool-call scheduler: grouping and barriers', () => { })) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await until(() => replacement.started.length === 1) await new Promise(r => setTimeout(r, 5)) expect(replacement.started).toEqual(['1']) @@ -200,7 +200,7 @@ describe('tool-call scheduler: grouping and barriers', () => { }) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await until(() => initial.started.length === 2) initial.release('1') await until(() => events(agent).some(event => @@ -226,7 +226,7 @@ describe('tool-call scheduler: model-order results despite out-of-order settleme ctx.tools.register(gated.tool) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await until(() => gated.started.length === 2) gated.release('2') await new Promise(r => setTimeout(r, 5)) @@ -248,7 +248,7 @@ describe('tool-call scheduler: model-order results despite out-of-order settleme const gated = gatedParallelTool('p') ctx.tools.register(gated.tool) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await until(() => gated.started.length === 2) gated.release('2'); gated.release('1') await waitForIdle(ctx, agent) @@ -294,7 +294,7 @@ describe('tool-call scheduler: rolling pool honors maxParallelToolCalls', () => ctx.tools.register(gated.tool) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await until(() => gated.started.length === 2) await new Promise(r => setTimeout(r, 5)) expect(gated.started).toEqual(['1', '2']) @@ -323,7 +323,7 @@ describe('tool-call scheduler: rolling pool honors maxParallelToolCalls', () => const gated = gatedParallelTool('p') ctx.tools.register(gated.tool) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await until(() => gated.started.length === 1) await new Promise(r => setTimeout(r, 5)) expect(gated.started).toEqual(['1']) @@ -349,7 +349,7 @@ describe('tool-call scheduler: rolling pool honors maxParallelToolCalls', () => const gated = gatedParallelTool('p') ctx.tools.register(gated.tool) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await until(() => gated.started.length === 1) await new Promise(r => setTimeout(r, 5)) expect(gated.started).toEqual(['1']) @@ -376,7 +376,7 @@ describe('tool-call scheduler: ordered middleware and additional contexts', () = ctx.on('tools/post-execute', async (exec, _result, next): Promise<PostToolDecision> => { post.push(String(exec.callId)); return next() }) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await until(() => gated.started.length === 3) gated.release('3'); gated.release('2'); gated.release('1') await waitForIdle(ctx, agent) @@ -397,17 +397,17 @@ describe('tool-call scheduler: ordered middleware and additional contexts', () = ({ kind: 'accept', additionalContexts: [{ content: [{ type: 'text', text: `ctx-${exec.callId}` }], source: { kind: 'plugin', plugin: 'p' } }] })) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await until(() => gated.started.length === 2) gated.release('2'); gated.release('1') await waitForIdle(ctx, agent) const log = events(agent) - const contextTexts = log.filter(e => e.type === 'context/message') - .map(e => (e.data.content[0] as { text: string }).text) + const contextTexts = log.filter(e => e.type === 'user/message' && e.data.source.kind === 'plugin') + .map(e => ((e.data as { content: { text: string }[] }).content[0]!).text) expect(contextTexts).toEqual(['ctx-c1', 'ctx-c2']) const lastResult = log.findLastIndex(e => e.type === 'tool/result') - const firstContext = log.findIndex(e => e.type === 'context/message') + const firstContext = log.findIndex(e => e.type === 'user/message' && e.data.source.kind === 'plugin') expect(lastResult).toBeLessThan(firstContext) }) @@ -435,7 +435,7 @@ describe('tool-call scheduler: ordered middleware and additional contexts', () = }) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await until(() => gated.started.length === 1) gated.release('1') await waitForIdle(ctx, agent) @@ -465,7 +465,7 @@ describe('tool-call scheduler: abort handling', () => { } }) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(gated.started).toEqual([]) @@ -497,7 +497,7 @@ describe('tool-call scheduler: abort handling', () => { return next() }) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(gated.started).toEqual([]) @@ -527,7 +527,7 @@ describe('tool-call scheduler: abort handling', () => { })) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await until(() => gated.started.length === 2) agent.cancel({ kind: 'user' }) gated.release('1') @@ -548,10 +548,11 @@ describe('tool-call scheduler: abort handling', () => { { callId: CallId('c3'), isError: true, errorInfo: { name: 'AbortError', code: TOOL_ABORTED_BEFORE_DISPATCH } }, { callId: CallId('c4'), isError: true, errorInfo: { name: 'AbortError', code: TOOL_ABORTED_BEFORE_DISPATCH } }, ]) - const settled = events(agent).filter(e => e.type === 'tool/result' || e.type === 'context/message') + const settled = events(agent).filter(e => e.type === 'tool/result' + || (e.type === 'user/message' && e.data.source.kind === 'plugin')) expect(settled.map(e => e.type)) - .toEqual(['tool/result', 'tool/result', 'tool/result', 'tool/result', 'context/message', 'context/message']) - expect(settled.filter(e => e.type === 'context/message') + .toEqual(['tool/result', 'tool/result', 'tool/result', 'tool/result', 'user/message', 'user/message']) + expect(settled.filter(e => e.type === 'user/message') .map(e => (e.data.content[0] as { text: string }).text)) .toEqual(['ctx-c1', 'ctx-c2']) }) @@ -577,7 +578,7 @@ describe('tool-call scheduler: abort handling', () => { })) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await until(() => gated.started.length === 2) agent.cancel({ kind: 'user' }) gated.release('1') diff --git a/packages/core/agent-loop/tests/tool-order.spec.ts b/packages/core/agent-loop/tests/tool-order.spec.ts index 76b14e92c2..a39961bfbf 100644 --- a/packages/core/agent-loop/tests/tool-order.spec.ts +++ b/packages/core/agent-loop/tests/tool-order.spec.ts @@ -58,7 +58,7 @@ async function runTurn(registrationOrder: string[], toolOrder?: SystemPromptConf const ctx = await harness(adapter, toolOrder) for (const name of registrationOrder) registerNamed(ctx, name) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) return { ctx, agent, adapter } } @@ -100,7 +100,7 @@ describe('loop-level canonical tool order', () => { const errors: Error[] = [] ctx.on('agent/error', (_agent, _turn, _step, error) => void errors.push(error)) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(adapter.requests).toHaveLength(0) expect(errors.map(e => e.message)).toEqual(['toolOrder lists unregistered tool "ghost"; known tools: alpha']) diff --git a/packages/core/agent-loop/tests/turn-stop.spec.ts b/packages/core/agent-loop/tests/turn-stop.spec.ts index eb6e6b4da5..44e1fd8a7b 100644 --- a/packages/core/agent-loop/tests/turn-stop.spec.ts +++ b/packages/core/agent-loop/tests/turn-stop.spec.ts @@ -34,7 +34,7 @@ async function harness(adapter: MockAdapter): Promise<Context> { } function send(agent: Agent, text = 'go'): Promise<void> { - agent.send([{ type: 'text', text }]) + agent.followup([{ type: 'text', text }]) return agent.whenIdle() } @@ -116,7 +116,7 @@ describe('agent/turn-stop', () => { ctx.on('session/flush', (session) => { if (session !== agent.session || queued) return queued = true - agent.send([{ type: 'text', text: 'ordinary queued follow-up' }]) + agent.followup([{ type: 'text', text: 'ordinary queued follow-up' }]) }) await send(agent) diff --git a/packages/core/agent/README.md b/packages/core/agent/README.md index b040d8cbdc..511ce32235 100644 --- a/packages/core/agent/README.md +++ b/packages/core/agent/README.md @@ -48,18 +48,20 @@ The lifecycle edges have two important local caveats. `agent/created` runs after Most interception points are cooperative waterfalls returning seam-specific decisions. Turn-scoped asynchronous seams receive one explicit `AbortSignal`, with `signal` immediately before a waterfall's final `next`; listeners may cooperate but must not retain it as authority over another turn. The signal remains authoritative through terminal policy and is retired immediately before `turn/end` publication, so terminal observers and the following durability flush cannot cancel completed turn work. `agent/pre-step` and `agent/post-step` are serial checkpoints around a step's durable work, while `agent/request-error` is the failed-model-request recovery waterfall: it receives the exact error, normalized failure facts, immutable prior-retried facts, and signal after the failed step closes; a retry opens a new numbered step. `agent/turn-stop` is the terminal serial fold: it runs after ordinary continuation and steering folding, and a returned stop remains in force through turn close and flush so later steering cannot create an extra step or turn. Ordinary queued prompts remain intact. Effective broad cancellation first emits the observe-only `agent/cancel-requested` with its resolved typed cause, then clears queues and aborts; notification failures are contained and cannot veto the stop. The [explicit-cancellation decision](../../../.agents/notes/implemented/architecture/2026-07-16-explicit-turn-cancellation.md) owns signal lifetime; the [agent-scope runtime-design Agent Note](../../../.agents/notes/implemented/architecture/2026-07-12-agent-scope-runtime-design.md#three-execution-boundaries-are-deliberately-one-way) owns scoped dispatch and terminal settlement. -`PromptDecision.additionalContexts` is an array so every context keeps its own source, metadata, and placement. `SendOptions.contexts` binds the same shape to one queued message before prompt interception: the default allow decision carries it forward, while a blocked prompt records no context. Absent or `separate` placement writes an independent `context/message`; `prompt-prefix` writes the context, `## My request:` delimiter, and effective prompt into one `user/message` or `steering/message`, whose model-hidden envelope retains the direct prompt and context descriptors for human replay. A listener that wraps a downstream allow preserves its `content` and `additionalContexts` unless it intentionally replaces either field; the returned allow is authoritative. A `ContinuationDecision` reason is narrower: it becomes a `steering/message` without attached context metadata. +`PromptDecision.additionalContexts` is an array so every context keeps its own source, metadata, and placement. `SendOptions.contexts` binds the same shape to one queued message before prompt interception: the default allow decision carries it forward, while a blocked prompt records no context. Absent or `separate` placement writes an independent injected `user/message` (plugin/goal source); `prompt-prefix` writes the context, `## My request:` delimiter, and effective prompt into one `user/message` or `steering/message`, whose model-hidden envelope retains the direct prompt and context descriptors for human replay. A listener that wraps a downstream allow preserves its `content` and `additionalContexts` unless it intentionally replaces either field; the returned allow is authoritative. A `ContinuationDecision` reason is narrower: it becomes a `steering/message` without attached context metadata. Turn and step boundaries and the model token stream are durable `session/event` facts rather than mirrored `agent/*` notifications. Consumers read `turn/*`, `step/*`, and `assistant/chunk` from the session feed; tool policy and outcome observation belong to the complete pipeline documented by [`dsh-tools`](../tools/README.md). ### Agent interface (`types.ts`) -The handle every plugin programs against: +`Agent` is a structural interface. `followup()`, `queue()`, `steer()`, and `inject()` name common caller intents; `send(ResolvedAgentInput)` exposes the same acceptance path when a caller already has exact routing facts ([decision](../../../.agents/notes/implemented/architecture/2026-07-24-intent-named-agent-delivery.md)). Every `ResolvedAgentInput` field is mandatory, and its discriminated union excludes attached contexts from non-waking next-step injection. FIFO acceptance returns an opaque `AgentMessageId` carried by that item's `agent/inbox/enqueue`/`dequeue`/`discard` events. The driver snapshots content, resolved source, attached contexts, and model-hidden metadata as one detached, deeply frozen lossless-JSON record before notification and enqueue; invalid data throws synchronously. The helpers apply defaults: omitting `options.source` on `followup()`, `queue()`, or `steer()` attests direct human input as `{ kind: 'user' }`, so every non-human producer labels its content. -- `agent.send(content, options?)` — queue one independent FIFO item. If claimed, that item becomes the sole ordinary message in its turn; a claimed FIFO successor waits for that turn's checkpoint to settle. Broad cancellation, disposal, or a pre-start failure may instead drop it without a turn. Omitting `options.source` attests direct human input as `{ kind: 'user' }` and may authorize policy consumers, so plugins, schedulers, and other non-human producers provide their own source. Content, resolved source, and `options.contexts` become one detached, deeply frozen lossless-JSON record before `agent/queued` and enqueue; invalid data throws synchronously, and caller or notification-listener in-place mutation cannot change the log or model input. After admission, separate contexts become `context/message` events, while prompt-prefix contexts are baked before the effective request in the same `user/message`; a block or replacement of the default additional-context decision can discard them. The [one-send-one-turn Agent Note](../../../.agents/notes/implemented/simplification/2026-07-17-one-send-one-turn.md) owns the turn rationale. -- `agent.steer(content, options?)` — while running, queue steering for the next checkpoint without dispatching `agent/prompt-submit`; when idle, delegate to `send()`. Attached contexts remain in the same frozen record; separate contexts append immediately after the steering event, while prompt-prefix contexts are baked into that steering event. Both survive late-steering conversion to queued input and disappear with their message on cancellation or terminal discard. Policy can still stop before another step; after turn close and its checkpoint, remaining steering becomes later queued input unless terminal turn policy, cancellation, or disposal discards it. -- `agent.inject(content, options?)` — accept detached in-session context without running the model; the next request sees its `context/message` with `content` rendered verbatim as a user-role message. `options.meta` persists opaque JSON state without rendering it. While a turn is open it joins that turn, deferring FIFO while the current tool batch executes and draining before turn close if execution is interrupted; while idle it is wrapped in a one-shot `injection` turn and durability checkpoint ([the turn-enclosure invariant](../../../.agents/notes/implemented/architecture/2026-06-15-turn-enclosure-invariant.md)). -- `agent.cancel(cause?)` — cancel ALL pending work: an omitted cause means `{ kind: 'user' }`; TypeScript restricts callers to the `user | parent` union, and an active holder copies its discriminant into a detached frozen signal reason before aborting. An effective call emits `agent/cancel-requested` with the cause before clearing queued and steering work; observers may synchronize state but cannot veto cancellation. The same-process typed seam adds no runtime validation or compatibility fallback for untyped callers. Repeated active-turn cancellation is first-wins for the signal, and idle cancellation is a safe no-op with no notification. ACP maps to `user`, while in-process parent propagation maps to `parent`. The cause is runtime-only; durable `turn/end` stays coarse `aborted`. +- `agent.followup(content, options?)` — queue one independent FIFO message as its own turn and wake the driver. After admission, separate contexts become injected `user/message` events, while prompt-prefix contexts are baked before the effective request in the same `user/message`; a block or replacement of the default additional-context decision can discard them. The [one-send-one-turn Agent Note](../../../.agents/notes/implemented/simplification/2026-07-17-one-send-one-turn.md) owns the turn rationale. +- `agent.queue(content, options?)` — queue the same ordinary message without waking an idle driver. A lone queued item leaves `whenIdle()` resolved and rides along before the next waking message. +- `agent.steer(content, options?)` — while running, queue steering for the next checkpoint without dispatching `agent/prompt-submit`; while idle, create a waking ordinary turn. Attached contexts remain in the same frozen record; separate contexts append immediately after the steering event, while prompt-prefix contexts are baked into that event. Both survive late-steering conversion to queued input and disappear with their message on cancellation or terminal discard. Policy can still stop before another step; after turn close and its checkpoint, remaining steering becomes later queued input unless terminal turn policy, cancellation, or disposal discards it. +- `agent.inject(content, options?)` — accept detached in-session context without running the model; the next request sees its `user/message` (default plugin source) with `content` rendered verbatim as a user-role message. `InjectOptions` deliberately has no attached contexts. `options.meta` persists opaque JSON state without rendering it. While a turn is open the injection joins that turn, deferring FIFO while the current tool batch executes and draining before turn close if execution is interrupted; while idle it is wrapped in a one-shot `injection` turn and durability checkpoint ([the turn-enclosure invariant](../../../.agents/notes/implemented/architecture/2026-06-15-turn-enclosure-invariant.md)). Injection bypasses the FIFOs and emits no `agent/inbox/*` event. +- `agent.send(input)` — accept a fully specified route without helper defaults. `next-turn` targets the ordinary FIFO; `next-step` with wakeup targets steering and falls back to a waking ordinary turn while idle; `next-step` without wakeup is injection and requires `contexts: []`. Callers provide `meta: undefined` explicitly when they have no metadata. +- `agent.cancel(cause?, options?)` — cancel the active turn and, unless `options.keepInbox`, ALL pending work: an omitted cause means `{ kind: 'user' }`; TypeScript restricts callers to the `user | parent` union, and an active holder copies its discriminant into a detached frozen signal reason before aborting. An effective call emits `agent/cancel-requested` with the cause before clearing queued and steering work; dropped items are reported on `agent/inbox/discard`, and observers may synchronize state but cannot veto cancellation. `keepInbox: true` aborts the turn but preserves queued and steering items (no discard, and un-started work is not dropped). The same-process typed seam adds no runtime validation or compatibility fallback for untyped callers. Repeated active-turn cancellation is first-wins for the signal, and idle cancellation is a safe no-op with no notification. ACP maps to `user`, while in-process parent propagation maps to `parent`. The cause is runtime-only; durable `turn/end` stays coarse `aborted`. - `agent.whenIdle()` — resolve once the agent reaches quiescence after settling out of `running` (idle → immediately; disposed → awaits the loop exit). A non-owner's quiescence-observation hook: it observes the work settling WITHOUT tearing the agent down. Teardown is separate — a lifecycle owner stops and unregisters via `AgentHandle.dispose()`, which awaits the loop exit directly. - `agent.session`, `agent.status`, `agent.options`, `agent.id` @@ -77,7 +79,7 @@ The handle every plugin programs against: #### What the model sees -`send`, `steer`, and `inject` feed the owning session. `agent/prompt-submit`, `agent/session-prefix`, and other declared events let plugins block a prompt or add request material; this interface contributes no fixed prose itself. +The four intent helpers and fully resolved `send` path feed the owning session. `agent/prompt-submit`, `agent/session-prefix`, and other declared events let plugins block a prompt or add request material; this interface contributes no fixed prose itself. #### Token effect @@ -107,6 +109,6 @@ Prefix-stable while an agent's scoped registrations are unchanged. Setup or relo - **Ambient identity may outlive liveness** — consumers still check `agent.status`, cancellation, and the owning capability contract before lifecycle-sensitive work. - **Inter-agent channels beyond delegation** — shared state, streaming child output, and background/poll semantics remain outside the current synchronous `ctx.subagents` seam. - **`agent/session-start` cannot gate startup** — it remains a synchronous, veto-less notification; async composition that must finish before publication belongs in the factory's `setup(agentCtx)` transaction instead. -- **No public step-only abort** — `cancel()` clears ALL pending work (queued + steering + in-flight); an abort that preserves queued prompts returns only with a named consumer ([stop-surface Agent Note](../../../.agents/notes/implemented/simplification/2026-06-20-public-agent-stop-surface.md)). +- **`cancel()` clears the inbox by default** — it aborts the in-flight turn plus queued and steering work; `cancel(cause, { keepInbox: true })` aborts only the turn and preserves pending items. There is still no step-only abort that keeps the in-flight turn running ([stop-surface Agent Note](../../../.agents/notes/implemented/simplification/2026-06-20-public-agent-stop-surface.md)). - **`HookContext` carries exactly one `MessageSource`** — contributions from several plugins merged onto one tool call collapse under one source; mixed provenance is unrepresentable. - **`SessionStartSource` reserves `'clear'`/`'compact'` with no emitter yet** — only `'startup'`/`'resume'` occur until the driving subsystems land (`TODO(compaction)`). diff --git a/packages/core/agent/src/invariant.ts b/packages/core/agent/src/invariant.ts index 1902f3e746..a5a7725707 100644 --- a/packages/core/agent/src/invariant.ts +++ b/packages/core/agent/src/invariant.ts @@ -24,6 +24,27 @@ const install: InvariantInstaller = (ctx, fail) => { } lastStatus.set(agent, status) }, { global: true }) + + // Inbox FIFO conservation: an item leaves the inbox (dequeue) or is dropped + // (discard) only after it entered (enqueue), so the live outstanding count + // per agent can never go negative. Injection bypasses the FIFOs entirely and + // never appears on these events. + const outstanding = new WeakMap<Agent, number>() + ctx.on('agent/inbox/enqueue', (agent) => { + outstanding.set(agent, (outstanding.get(agent) ?? 0) + 1) + }, { global: true }) + ctx.on('agent/inbox/dequeue', (agent) => { + const count = outstanding.get(agent) ?? 0 + if (count <= 0) fail('agent/inbox/dequeue without a matching prior enqueue') + outstanding.set(agent, count - 1) + }, { global: true }) + ctx.on('agent/inbox/discard', (agent, items) => { + const count = outstanding.get(agent) ?? 0 + if (items.length > count) { + fail(`agent/inbox/discard dropped ${items.length} items but only ${count} were outstanding`) + } + outstanding.set(agent, count - items.length) + }, { global: true }) } /** diff --git a/packages/core/agent/src/types.ts b/packages/core/agent/src/types.ts index dc78d76ef5..0f442e3f88 100644 --- a/packages/core/agent/src/types.ts +++ b/packages/core/agent/src/types.ts @@ -6,6 +6,7 @@ */ import type { Context } from 'cordis' +import type { Branded } from '@deepseek-ai/dsh-brand' import type { Scoped } from '@deepseek-ai/dsh-scope' import type { ContentBlock, LlmCallConfig, LlmFailure, Message, MessageSource } from '@deepseek-ai/dsh-llm' import type { JsonValue, Session, SessionId } from '@deepseek-ai/dsh-session' @@ -26,8 +27,9 @@ export interface AgentOptions { } /** - * Message options. An omitted source attests direct human input as `{ kind: 'user' }` - * and may authorize policy consumers, so non-human producers must label their content. + * Options for {@link Agent.followup}, {@link Agent.queue}, and {@link Agent.steer}. + * An omitted source attests direct human input as `{ kind: 'user' }` and may + * authorize policy consumers, so non-human producers must label their content. */ export interface SendOptions { source?: MessageSource @@ -37,19 +39,71 @@ export interface SendOptions { * records them directly at its next checkpoint. */ contexts?: HookContext[] + /** Opaque JSON state retained on the durable message but hidden from the model. */ + meta?: JsonValue } /** Options specific to durable synthetic context injection. */ -export interface InjectOptions extends Omit<SendOptions, 'contexts'> { - /** Opaque JSON state retained in the session event but hidden from the model. */ +export interface InjectOptions { + /** Defaults to `{ kind: 'plugin', plugin: '' }`; non-human producers should identify themselves. */ + source?: MessageSource + /** Opaque JSON state retained on the durable message but hidden from the model. */ meta?: JsonValue } +/** + * Opaque id assigned to one accepted agent input. FIFO inputs carry the same id + * on their `agent/inbox/*` events; injection bypasses those events. + */ +export type AgentMessageId = Branded<'AgentMessageId'> + +/** + * Brand a string as an {@link AgentMessageId}. + * @param id - the generated message id. + * @returns the same string, branded; no validation is performed. + */ +export function AgentMessageId(id: string): AgentMessageId { + return id as AgentMessageId +} + +/** + * One accepted FIFO message, carried by the `agent/inbox/*` live events. `id` + * is the value returned by the accepting helper or {@link Agent.send}, + * stable across this message's enqueue, dequeue, and discard events. Source + * defaults, when applicable, are already applied, so these are the exact values + * the item was accepted with. + * `steering` is true for an item drained between steps; otherwise it is claimed + * at a turn boundary. `SendOptions.meta` is intentionally omitted: it is durable + * model-hidden state that lands on the eventual `user/message`/ + * `steering/message`, not live-event routing data. + */ +export interface AgentMessage { + /** The id returned by the accepting helper or {@link Agent.send}. */ + id: AgentMessageId + content: ContentBlock[] + source: MessageSource + contexts: HookContext[] + /** Whether the item joined the steering FIFO rather than the queued FIFO. */ + steering: boolean + /** Whether the item wakes the driver or requests another step. */ + wakeup: boolean +} + +/** Options for {@link Agent.cancel}. */ +export interface CancelOptions { + /** + * Preserve queued and steering inbox items instead of discarding them. The + * active turn is still aborted, but un-started and pending work survives for a + * later turn and no `agent/inbox/discard` fires. + */ + keepInbox?: boolean +} + /** * An agent's lifecycle state, emitted on every transition as `agent/status`: * `idle` (parked, waiting for queued work), `running` (the driver is draining * work and may be closing or checkpointing a turn), `disposed` (terminal — no - * transition leaves it, and `send`/`steer`/`inject` throw). + * transition leaves it, and every delivery method throws). */ export type AgentStatus = 'idle' | 'running' | 'disposed' @@ -58,8 +112,8 @@ export interface HookContext { content: ContentBlock[] source: MessageSource /** - * Model placement. Absent or `separate` records an independent - * `context/message`; `prompt-prefix` prepends this context and a stable + * Model placement. Absent or `separate` records an independent injected + * `user/message`; `prompt-prefix` prepends this context and a stable * request delimiter to the same user-role message as its attached prompt. */ placement?: 'separate' | 'prompt-prefix' @@ -67,6 +121,22 @@ export interface HookContext { meta?: JsonValue } +/** + * Fully specified input for {@link Agent.send}. Unlike the intent-named + * helpers, this form applies no defaults: callers provide content, source, + * contexts, metadata (including explicit `undefined`), target, and wakeup. + * The union excludes attached contexts from non-waking next-step injection. + */ +export type ResolvedAgentInput = { + content: ContentBlock[] + source: MessageSource + meta: JsonValue | undefined +} & ( + | { target: 'next-turn'; wakeup: boolean; contexts: HookContext[] } + | { target: 'next-step'; wakeup: true; contexts: HookContext[] } + | { target: 'next-step'; wakeup: false; contexts: [] } +) + /** * Prompt interception result. `allow.content` replaces the prompt. Each * `additionalContexts` entry follows its declared placement: separate context @@ -113,54 +183,90 @@ export type AgentInterruptReason = AgentCancelCause | { readonly kind: 'disposed export interface Agent { /** The single identity shared with {@link session}. */ readonly id: SessionId + /** The provider route and model this agent's requests use. */ readonly options: AgentOptions + /** The live session this agent drives; its log is the durable source of truth. */ readonly session: Session + /** The current lifecycle state, mirrored on every `agent/status` transition. */ readonly status: AgentStatus /** Agent-scoped context; its contributions are agent-local, unwind on disposal, and reject registration afterward. */ readonly ctx: Context /** - * Queue one detached, frozen lossless-JSON item. If claimed, it is the sole - * ordinary message in its FIFO-ordered turn; the next claimed item waits for - * that turn's checkpoint. - * Attached contexts share the same snapshot and ownership boundary. Invalid - * input throws synchronously before notification or enqueue. + * Queue an ordinary message as its own FIFO-ordered turn and wake the driver. + * Content, resolved source, and attached contexts are detached, validated, + * and frozen together; invalid input throws synchronously before notification + * or enqueue. + * @param content - the prompt content blocks. + * @param options - source, attached contexts, and durable model-hidden meta. + * @returns the accepted message's {@link AgentMessageId}, stable across its `agent/inbox/*` events. */ - send(content: ContentBlock[], options?: SendOptions): void + followup(content: ContentBlock[], options?: SendOptions): AgentMessageId /** - * Submit steering while the agent is `running`. An open turn records it at - * the next steering checkpoint before a request or continuation decision; - * policy may stop before another step. After turn close and its checkpoint, - * any remainder is queued for a later turn; terminal `agent/turn-stop`, - * cancellation, or disposal may discard it. Uses the same synchronous - * snapshot-and-validation boundary as {@link send}; when idle, delegates to it. + * Queue an ordinary message without waking an idle driver. The item retains + * FIFO order and is claimed only after another input wakes the driver. A lone + * queued item leaves `whenIdle()` resolved. + * @param content - the prompt content blocks. + * @param options - source, attached contexts, and durable model-hidden meta. + * @returns the accepted message's {@link AgentMessageId}, stable across its `agent/inbox/*` events. */ - steer(content: ContentBlock[], options?: SendOptions): void + queue(content: ContentBlock[], options?: SendOptions): AgentMessageId + + /** + * Submit steering into the running turn and request another step. An open turn + * records it at the next steering checkpoint before a request or continuation + * decision; policy may stop before another step. After turn close and its + * checkpoint, any remainder is queued for a later turn; terminal + * `agent/turn-stop`, cancellation, or disposal may discard it. Idle steering + * becomes a waking ordinary turn. + * @param content - the steering content blocks. + * @param options - source, attached contexts, and durable model-hidden meta. + * @returns the accepted message's {@link AgentMessageId}, stable across its `agent/inbox/*` events. + */ + steer(content: ContentBlock[], options?: SendOptions): AgentMessageId /** * Append detached model-facing context without running the model. An open-turn * injection joins at the current log position unless the current tool batch is - * executing; then it waits FIFO until that batch settles and drains before turn - * close even when interrupted. Idle injection uses a one-shot turn and durability - * checkpoint. Disposal awaits idle checkpoints; flush failures report through `agent/error`. + * executing; then it waits FIFO until that batch settles and drains before + * turn close even when interrupted. Idle injection uses a one-shot turn and + * durability checkpoint. Disposal awaits idle checkpoints; flush failures + * report through `agent/error`. An omitted source defaults to + * `{ kind: 'plugin', plugin: '' }`. + * @param content - the injected context content blocks. + * @param options - source and durable model-hidden meta. + * @returns the accepted injection's {@link AgentMessageId}; injection emits no `agent/inbox/*` events. */ - inject(content: ContentBlock[], options?: InjectOptions): void + inject(content: ContentBlock[], options?: InjectOptions): AgentMessageId /** - * Clear all queued and steering work, including items waiting to start, and - * abort the active turn. An effective call first emits - * `agent/cancel-requested` with the resolved typed cause. The first cause wins - * for the active turn, and `whenIdle()` resolves after cancellation reaches - * quiescence. Omission means `{ kind: 'user' }`. Idle cancellation is a no-op - * and does not arm later work. The active turn snapshots and freezes the cause. - * @param cause - the stable caller intent carried by the current turn signal. + * Accept one fully specified input through the same snapshot and routing path + * as the four intent-named helpers. `next-turn` targets the ordinary FIFO; + * `next-step`/wakeup targets steering (falling back to an ordinary waking turn + * while idle); and `next-step` without wakeup injects durable context without + * running the model. Every field is mandatory and no source or routing default + * is applied. Invalid input throws synchronously before notification, enqueue, + * or append. + * @param input - the resolved content, attribution, context, metadata, and routing facts. + * @returns the accepted input's {@link AgentMessageId}, carried by FIFO lifecycle events when applicable. */ - cancel(cause?: AgentCancelCause): void + send(input: ResolvedAgentInput): AgentMessageId + + /** + * Clear queued and steering work — unless `keepInbox` — and abort the active + * turn. An effective call first emits `agent/cancel-requested` with the + * resolved typed cause. The first cause wins for the active turn, and + * `whenIdle()` resolves after cancellation reaches quiescence. Omitted cause + * means `{ kind: 'user' }`. Idle cancellation is a no-op and does not arm + * later work. The active turn snapshots and freezes the cause. + * @param cause - the stable caller intent carried by the current turn signal. + * @param options - cancellation options; `keepInbox` preserves pending work. + */ + cancel(cause?: AgentCancelCause, options?: CancelOptions): void /** Resolve at idle quiescence; disposal waits for driver exit rather than only the status transition. */ whenIdle(): Promise<void> - } declare module 'cordis' { @@ -187,8 +293,8 @@ declare module 'cordis' { */ 'agent/disposed'(this: Scoped<Agent>, agent: Agent): void /** - * Agent status changed (`idle` ⇄ `running`, or → `disposed`). `send()` does - * not enter `running` synchronously; drive lifecycle from this event. + * Agent status changed (`idle` ⇄ `running`, or → `disposed`). A waking + * delivery does not enter `running` synchronously; drive lifecycle from this event. * @param agent - the agent whose status flipped. * @param status - the status just entered (the transition's destination). * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. @@ -196,15 +302,42 @@ declare module 'cordis' { */ 'agent/status'(this: Scoped<Agent>, agent: Agent, status: AgentStatus): void /** - * Detached, frozen content entered the agent's inbox. Source defaults have - * already been applied, so these are the exact values retained for the log. - * @param agent - the agent whose inbox received the message. - * @param content - the accepted content blocks retained by the inbox. - * @param info - the accepted source, contexts, and whether it entered as steering. + * A detached, frozen item entered the agent's inbox (queued or steering + * FIFO). Source defaults are already applied, so `message` holds the exact + * accepted values. This is the enqueue-time live signal; the durable record + * is the eventual `user/message`/`steering/message`. Injection through + * `agent.inject()` or equivalent `send()` routing bypasses the FIFOs + * and does not emit this. + * @param agent - the agent whose inbox received the item. + * @param message - the accepted message (its returned `id`, content, source, contexts, steering, and wakeup facts). * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. * @mode emit */ - 'agent/queued'(this: Scoped<Agent>, agent: Agent, content: ContentBlock[], info: { source: MessageSource; contexts: HookContext[]; steering: boolean }): void + 'agent/inbox/enqueue'(this: Scoped<Agent>, agent: Agent, message: AgentMessage): void + /** + * The driver claimed one item out of the inbox: a queued item at a turn + * boundary, or steering drained between steps. Fires after the item leaves + * its FIFO and before it becomes a durable message. + * @param agent - the agent whose inbox item was claimed. + * @param message - the claimed message (matching the `id` from its `agent/inbox/enqueue`). + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. + * @mode emit + */ + 'agent/inbox/dequeue'(this: Scoped<Agent>, agent: Agent, message: AgentMessage): void + /** + * Pending inbox items were dropped without delivering them, so every + * enqueued id receives exactly one terminal `agent/inbox/dequeue` OR + * `agent/inbox/discard`. Emitters: `cancel()` without `keepInbox` (after + * `agent/cancel-requested`, before the abort); a terminal `agent/turn-stop` + * dropping pending steering (in-turn and on the post-turn late-steering + * drain); and disposal of any still-pending items (before + * `agent/status('disposed')`). Fires once per drop with every dropped item. + * @param agent - the agent whose inbox items were dropped. + * @param messages - the discarded messages in FIFO order (queued then steering); never empty. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. + * @mode emit + */ + 'agent/inbox/discard'(this: Scoped<Agent>, agent: Agent, messages: AgentMessage[]): void /** * Effective broad cancellation was requested, before queued/steering work * is cleared or the active turn is aborted. This observe-only notification diff --git a/packages/core/agent/tests/agent.spec.ts b/packages/core/agent/tests/agent.spec.ts index 509ad14a22..b5b0424957 100644 --- a/packages/core/agent/tests/agent.spec.ts +++ b/packages/core/agent/tests/agent.spec.ts @@ -3,13 +3,24 @@ import { Context, Service, symbols } from 'cordis' import type { Events } from 'cordis' import { Session, SessionId } from '@deepseek-ai/dsh-session' import AgentRegistry, { + AgentMessageId, agentEvents, agentInterruptReasonOf, } from '@deepseek-ai/dsh-agent' -import type { Agent, AgentCancelCause, AgentFactory, ContinuationStop, CreateAgentOptions, ResumeAgentOptions } from '@deepseek-ai/dsh-agent' +import type { + Agent, + AgentCancelCause, + AgentFactory, + ContinuationStop, + CreateAgentOptions, + InjectOptions, + ResolvedAgentInput, + ResumeAgentOptions, + SendOptions, +} from '@deepseek-ai/dsh-agent' -function stubAgent(rawId: string): Agent { +function stubAgent(rawId: string, overrides: Partial<Agent> = {}): Agent { const id = SessionId(rawId) return { id, @@ -17,15 +28,34 @@ function stubAgent(rawId: string): Agent { session: new Session(id), status: 'idle', ctx: new Context(), - send() {}, - steer() {}, - inject() {}, + followup: () => AgentMessageId('stub'), + queue: () => AgentMessageId('stub'), + steer: () => AgentMessageId('stub'), + inject: () => AgentMessageId('stub'), + send: () => AgentMessageId('stub'), cancel() {}, whenIdle() { return Promise.resolve() }, + ...overrides, } } describe('AgentRegistry', () => { + it('keeps helper options semantic and makes advanced input fully specified', () => { + type OptionalInputKey = { + [Key in keyof ResolvedAgentInput]-?: Record<never, never> extends Pick<ResolvedAgentInput, Key> + ? Key + : never + }[keyof ResolvedAgentInput] + + expectTypeOf<'target' extends keyof SendOptions ? true : false>().toEqualTypeOf<false>() + expectTypeOf<'wakeup' extends keyof SendOptions ? true : false>().toEqualTypeOf<false>() + expectTypeOf<'contexts' extends keyof InjectOptions ? true : false>().toEqualTypeOf<false>() + expectTypeOf<Parameters<Agent['send']>[0]>().toEqualTypeOf<ResolvedAgentInput>() + expectTypeOf<OptionalInputKey>().toEqualTypeOf<never>() + expectTypeOf<Extract<ResolvedAgentInput, { target: 'next-step'; wakeup: false }>['contexts']>() + .toEqualTypeOf<[]>() + }) + it('allows terminal stop policy to cooperate asynchronously with turn cancellation', () => { type TurnStopListener = Events['agent/turn-stop'] type AsyncTurnStopListener = () => Promise<ContinuationStop | undefined> @@ -56,7 +86,7 @@ describe('AgentRegistry', () => { it('rejects an agent whose registry and session identities differ', async () => { const ctx = new Context() await ctx.plugin(AgentRegistry) - const agent = { ...stubAgent('agent-id'), session: new Session(SessionId('session-id')) } + const agent = stubAgent('agent-id', { session: new Session(SessionId('session-id')) }) expect(() => ctx.agents.enter(agent, undefined)) .toThrow('agent id "agent-id" does not match session id "session-id"') diff --git a/packages/core/agent/tests/invariant.spec.ts b/packages/core/agent/tests/invariant.spec.ts index 3c0d147b9a..453752c402 100644 --- a/packages/core/agent/tests/invariant.spec.ts +++ b/packages/core/agent/tests/invariant.spec.ts @@ -1,6 +1,6 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' -import type { Agent } from '@deepseek-ai/dsh-agent' +import { AgentMessageId, type Agent } from '@deepseek-ai/dsh-agent' import * as AgentInvariant from '@deepseek-ai/dsh-agent/invariant' import { scopeTarget } from '@deepseek-ai/dsh-scope' import InvariantService from '@deepseek-ai/dsh-invariants' @@ -56,3 +56,41 @@ describe('agent status invariants', () => { expect(() => { ctx.emit(scopeTarget(b, b), 'agent/status', b, 'running') }).not.toThrow() }) }) + +describe('agent inbox invariants', () => { + const info = (steering: boolean) => ({ id: AgentMessageId('m'), content: [], source: { kind: 'user' as const }, contexts: [], steering, wakeup: true }) + + it('accepts a dequeue and a discard covered by prior enqueues', async () => { + const ctx = await setup() + const agent = mockAgent('i1') + const at = scopeTarget(agent, agent) + expect(() => { + ctx.emit(at, 'agent/inbox/enqueue', agent, info(false)) + ctx.emit(at, 'agent/inbox/enqueue', agent, info(true)) + ctx.emit(at, 'agent/inbox/dequeue', agent, info(false)) + ctx.emit(at, 'agent/inbox/discard', agent, [info(true)]) + }).not.toThrow() + }) + + it('rejects a dequeue with no outstanding item', async () => { + const ctx = await setup() + const agent = mockAgent('i2') + expect(() => { ctx.emit(scopeTarget(agent, agent), 'agent/inbox/dequeue', agent, info(false)) }) + .toThrow(/without a matching prior enqueue/) + }) + + it('rejects a discard larger than the outstanding count', async () => { + const ctx = await setup() + const agent = mockAgent('i3') + const at = scopeTarget(agent, agent) + ctx.emit(at, 'agent/inbox/enqueue', agent, info(false)) + expect(() => { ctx.emit(at, 'agent/inbox/discard', agent, [info(false), info(true)]) }) + .toThrow(/dropped 2 items but only 1 were outstanding/) + }) + + it('accepts an empty discard against a fresh agent', async () => { + const ctx = await setup() + const agent = mockAgent('i4') + expect(() => { ctx.emit(scopeTarget(agent, agent), 'agent/inbox/discard', agent, []) }).not.toThrow() + }) +}) diff --git a/packages/core/scope/src/scoped-events.generated.ts b/packages/core/scope/src/scoped-events.generated.ts index 5988b58145..a12b0a513e 100644 --- a/packages/core/scope/src/scoped-events.generated.ts +++ b/packages/core/scope/src/scoped-events.generated.ts @@ -12,10 +12,12 @@ const scopedSubjectResolvers: Readonly<Record<string, ScopedSubjectResolver | nu 'agent/created': args => args[0], 'agent/disposed': args => args[0], 'agent/error': args => args[0], + 'agent/inbox/dequeue': args => args[0], + 'agent/inbox/discard': args => args[0], + 'agent/inbox/enqueue': args => args[0], 'agent/post-step': args => args[0], 'agent/pre-step': args => args[0], 'agent/prompt-submit': args => args[0], - 'agent/queued': args => args[0], 'agent/request': args => args[0], 'agent/request-error': args => args[0], 'agent/session-prefix': args => args[0], diff --git a/packages/core/scope/tests/invariant.spec.ts b/packages/core/scope/tests/invariant.spec.ts index 2d93bcddc5..ca0841165b 100644 --- a/packages/core/scope/tests/invariant.spec.ts +++ b/packages/core/scope/tests/invariant.spec.ts @@ -1,7 +1,7 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' import type { Events } from 'cordis' -import type { Agent } from '@deepseek-ai/dsh-agent' +import { AgentMessageId, type Agent } from '@deepseek-ai/dsh-agent' import { scopeTarget } from '@deepseek-ai/dsh-scope' import * as ScopeInvariant from '@deepseek-ai/dsh-scope/invariant' import InvariantService from '@deepseek-ai/dsh-invariants' @@ -42,7 +42,9 @@ describe('scoped-dispatch invariants', () => { 'agent/created': [agent], 'agent/disposed': [agent], 'agent/status': [agent, 'idle'], - 'agent/queued': [agent, [], { source: { kind: 'user' }, contexts: [], steering: false }], + 'agent/inbox/enqueue': [agent, { id: AgentMessageId('m'), content: [], source: { kind: 'user' }, contexts: [], steering: false, wakeup: true }], + 'agent/inbox/dequeue': [agent, { id: AgentMessageId('m'), content: [], source: { kind: 'user' }, contexts: [], steering: false, wakeup: true }], + 'agent/inbox/discard': [agent, []], 'agent/cancel-requested': [agent, { kind: 'user' }], 'agent/session-start': [agent, 'startup'], 'agent/pre-step': [agent, 1, 1, signal], diff --git a/packages/core/session/README.md b/packages/core/session/README.md index 0bd0265f78..a01bb21cc0 100644 --- a/packages/core/session/README.md +++ b/packages/core/session/README.md @@ -64,7 +64,7 @@ Providers stream token-sized deltas, so a raw log stores hundreds of `assistant/ `request/header` records a full canonical snapshot of the non-history request envelope with reason `initial`, `resume`, or `change`. `foldRequestHeader()` selects the latest snapshot; legacy delta events and the removed `fallback` reason are rejected. `messagePrefix` remains separate from derived history. See the [reconstructable-requests Agent Note](../../../.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.md). -`context/message` renders its `content` verbatim as a user-role message, and may attach JSON `meta` for replayable plugin state; metadata remains durable but is excluded from `deriveMessages()`. A `user/message` or `steering/message` with prompt-prefix context keeps the exact combined model bytes in `content` and stores a model-hidden `envelope` containing the direct `displayContent` and prefix context source/metadata descriptors. `displayPromptContent()` selects the human-facing prompt without changing derived history. +A `user/message` renders its `content` verbatim as a user-role message whether it is a direct human prompt (`user` source), a synthetic injection (`plugin`/`goal` source), or an admitted goal round — `source` is the only channel that tells them apart. It may attach JSON `meta` for replayable plugin state; metadata remains durable but is excluded from `deriveMessages()`. A `user/message` or `steering/message` with prompt-prefix context keeps the exact combined model bytes in `content` and stores a model-hidden `envelope` containing the direct `displayContent` and prefix context source/metadata descriptors. `displayPromptContent()` selects the human-facing prompt without changing derived history. `tool/result` persists the model-facing content, optional internal failure identity, and optional presentation metadata. A tool's successful canonical `value` and human-readable canonical failure message remain execution-local; rendered error content is the replay-authoritative message. This preserves the existing event shape and does not change `SESSION_FORMAT_VERSION`. @@ -99,7 +99,7 @@ Every `SessionEvent` carries two optional top-level fields (structural metadata) #### What the model sees -The model receives projections of `user/message`, `assistant/message`, `tool/result`, `context/message`, and `steering/message` surface entries verbatim: each is a user- or assistant-role message carrying its content blocks unchanged. A prompt envelope changes only human presentation; its prefix context and request delimiter are already present in the event content. Tool calls live inside assistant messages. Chunks, boundaries, usage, hook records, todo records, and other log-only events add no message. +The model receives projections of `user/message`, `assistant/message`, `tool/result`, and `steering/message` surface entries verbatim: each is a user- or assistant-role message carrying its content blocks unchanged. A prompt envelope changes only human presentation; its prefix context and request delimiter are already present in the event content. Tool calls live inside assistant messages. Chunks, boundaries, usage, hook records, todo records, and other log-only events add no message. #### Token effect diff --git a/packages/core/session/src/index.ts b/packages/core/session/src/index.ts index 9c5831bb18..5a6b274b3e 100644 --- a/packages/core/session/src/index.ts +++ b/packages/core/session/src/index.ts @@ -129,8 +129,10 @@ function snapshotSessionHeader(id: SessionId, source?: SessionHeader): SessionHe if (record.id !== id) { throw new Error(`session header id "${String(record.id)}" does not match session id "${id}"`) } - if (typeof record.createdAt !== 'number' || !Number.isFinite(record.createdAt)) { - throw new Error('session header createdAt must be a finite number') + if (typeof record.createdAt !== 'number' + || !Number.isSafeInteger(record.createdAt) + || record.createdAt < 0) { + throw new Error('session header createdAt must be a non-negative safe integer') } if (record.cwd !== undefined) { if (typeof record.cwd !== 'string') throw new Error('session header cwd must be a string') @@ -532,10 +534,10 @@ export class Session { // trace/replay data. switch (event.type) { - // Injected context, ordinary prompts, and mid-turn steering project + // Ordinary prompts, injected context, and mid-turn steering project // identically in user role: the event's model-facing content stays // verbatim. A prompt envelope is model-hidden display metadata; its - // prefix bytes are already present in content. context's `source`/`meta` + // prefix bytes are already present in content. The message's `source`/`meta` // and steering's `turn` are also log-only. Do NOT // re-add per-type framing (e.g. `<context>`/`<steering>`) here: framing is // caller-owned — a producer bakes it into `content`, as workspace-context @@ -544,7 +546,6 @@ export class Session { // verbatim pass-through. See the deferred design note in // ../../../../.agents/notes/implemented/simplification/2026-07-20-unwrap-injected-content-envelopes.md case 'user/message': - case 'context/message': case 'steering/message': { return { role: 'user', content: event.data.content } } diff --git a/packages/core/session/src/surface.ts b/packages/core/session/src/surface.ts index 9095c8388b..fc275129f9 100644 --- a/packages/core/session/src/surface.ts +++ b/packages/core/session/src/surface.ts @@ -15,14 +15,13 @@ const SURFACE_EVENT_TYPES = new Set<string>([ 'user/message', 'assistant/message', 'tool/result', - 'context/message', 'steering/message', ]) /** * Whether an event type can join the model-visible surface. * @param type - event type to test. - * @returns true for one of the five message-producing event types. + * @returns true for one of the four message-producing event types. */ export function isSurfaceEligibleType(type: string): boolean { return SURFACE_EVENT_TYPES.has(type) diff --git a/packages/core/session/src/types.ts b/packages/core/session/src/types.ts index 8b3a1e8cb6..d909d51452 100644 --- a/packages/core/session/src/types.ts +++ b/packages/core/session/src/types.ts @@ -36,7 +36,7 @@ export interface SessionHeader { readonly version: number /** The session's id (mirrors the {@link Session}'s id). */ readonly id: SessionId - /** Unix epoch milliseconds when the session was created. */ + /** Non-negative safe-integer Unix epoch milliseconds when the session was created. */ readonly createdAt: number /** Absolute working directory the session was created in (if any). */ readonly cwd?: string @@ -84,11 +84,12 @@ export interface TurnTriggerMap { message: { kind: 'message'; source: MessageSource } /** * An out-of-band context injection (`agent.inject()`) made while the agent - * was idle. The loop wraps the injected `context/message` in a one-shot turn - * (`turn/start` → `context/message` → `turn/end`) so every event in the log - * stays turn-enclosed — the durability/replay boundary is the turn, and a - * bare event between turns would otherwise be indistinguishable from a crash - * tail on reload. + * was idle. The loop wraps the injected `user/message` (a non-`user` source, + * plugin by default) in a one-shot turn (`turn/start` → `user/message` → + * `turn/end`) so every event in the log stays turn-enclosed — the + * durability/replay boundary is the turn, and a bare event between turns would + * otherwise be indistinguishable from a crash tail on reload. The trigger's + * `source` mirrors that message's producer. */ injection: { kind: 'injection'; source: MessageSource } } @@ -201,7 +202,13 @@ export interface PromptMessageEnvelope { prefixContexts: PromptPrefixContext[] } -/** Shared payload for ordinary and steering prompt messages. */ +/** + * Shared payload for user, injected-context, and steering prompt messages. A + * direct human prompt, a synthetic `agent.inject()` context, and mid-turn + * steering all project into the model transcript as verbatim user-role content; + * they are told apart by `source` (a non-`user` kind marks injected context), + * not by event type. `meta` carries durable model-hidden producer state. + */ export interface PromptMessageData { /** Exact model-facing blocks, including any baked prompt-prefix contexts. */ content: ContentBlock[] @@ -209,6 +216,15 @@ export interface PromptMessageData { source: MessageSource /** Present only when prompt-prefix contexts were baked into `content`. */ envelope?: PromptMessageEnvelope + /** + * Opaque durable JSON state retained on the event but hidden from the model + * projection. It is the intended channel for a future framing directive (a + * producer declares the frame, a dedicated renderer applies it — see the + * deferred note in + * ../../../../.agents/notes/implemented/simplification/2026-07-20-unwrap-injected-content-envelopes.md), + * so the surface keeps projecting `content` verbatim rather than wrapping it. + */ + meta?: JsonValue } /** @@ -236,29 +252,21 @@ export interface SessionEventMap { 'step/start': { turn: number; step: number } /** Closes step `step` of turn `turn`. */ 'step/end': { turn: number; step: number } - /** A user-visible prompt (the queued message claimed for this turn). */ + /** + * A user-role message on the model-visible surface: a direct human prompt + * (the queued message claimed for this turn), a synthetic `agent.inject()` + * context (file-change notices, subdir AGENTS.md, skill content, cron + * notifications, …), or an admitted goal continuation round. All three + * project their `content` verbatim; `source` (with a non-`user` kind marking + * injected context) is the only channel that tells them apart. An idle + * injection wraps this event in a one-shot turn so the log stays turn-enclosed. + */ 'user/message': PromptMessageData /** * Durable record of a prompt veto and its reason. It is log-only: the blocked * prompt never enters the model-visible surface, and its turn runs zero steps. */ 'prompt/blocked': { content: ContentBlock[]; source: MessageSource; reason: string } - /** - * In-session context injection (file-change notices, subdir AGENTS.md, - * skill content, cron notifications, …). Rendered into the derived history - * as a synthetic user-role message carrying `content` verbatim — NOT a - * user prompt. `meta` is durable JSON state omitted from the model - * projection; it is also the intended channel for any future framing - * directive (a producer declares the frame, a dedicated renderer applies it — - * see the deferred note in - * ../../../../.agents/notes/implemented/simplification/2026-07-20-unwrap-injected-content-envelopes.md), - * so the surface keeps projecting `content` verbatim rather than wrapping it. - */ - 'context/message': { - content: ContentBlock[] - source: MessageSource - meta?: JsonValue - } /** Raw stream chunk — token-level replay fidelity. */ 'assistant/chunk': { turn: number; step: number; chunk: StreamChunk } /** @@ -331,7 +339,6 @@ export type SurfaceEventType = | 'user/message' | 'assistant/message' | 'tool/result' - | 'context/message' | 'steering/message' /** @@ -349,7 +356,7 @@ export type SurfaceEvent = SessionEvent<SurfaceEventType> & { surfaceOp: Surface * How a session event entered the ordered surface. Only valid on * {@link SurfaceEventType} events. * - * - `'append'`: added to the tail — normal path for user/assistant/tool/context + * - `'append'`: added to the tail — normal path for user/assistant/tool/steering * messages. * - `{ op: 'replace', start, end }`: replaces surface nodes from `start` * (inclusive) through `end` (inclusive) with this node. Both must exist as @@ -384,7 +391,7 @@ export interface SurfaceIntent { * * The {@link sourceEventSeqs} and {@link surfaceOp} fields are conditional: * they only exist on {@link SurfaceEventType} variants (`user/message`, - * `assistant/message`, `tool/result`, `context/message`, `steering/message`). + * `assistant/message`, `tool/result`, `steering/message`). * Non-surface events (boundary markers, chunks, usage, errors) never carry * surface metadata — the compiler enforces this at `Session.append()` * call sites. diff --git a/packages/core/session/tests/derived-cache.spec.ts b/packages/core/session/tests/derived-cache.spec.ts index 96d1f7048c..c2ff24936b 100644 --- a/packages/core/session/tests/derived-cache.spec.ts +++ b/packages/core/session/tests/derived-cache.spec.ts @@ -38,7 +38,7 @@ describe('derived-message cache', () => { expect(beforeReplace).toHaveLength(2) const nodes = session.surface.nodes - session.append('context/message', { + session.append('user/message', { content: [{ type: 'text', text: 'summary' }], source: { kind: 'plugin', plugin: 'compact' }, }, { surfaceOp: { op: 'replace', start: nodes[0]!, end: nodes[1]! }, sourceEventSeqs: [nodes[0]!, nodes[1]!] }) diff --git a/packages/core/session/tests/session.spec.ts b/packages/core/session/tests/session.spec.ts index d880153dd3..e649214a29 100644 --- a/packages/core/session/tests/session.spec.ts +++ b/packages/core/session/tests/session.spec.ts @@ -62,7 +62,7 @@ describe('Session', () => { turn: 1, trigger: { kind: 'injection', source: { kind: 'plugin', plugin: 'before' } }, }) - session.append('context/message', { + session.append('user/message', { content: [{ type: 'text', text: 'before' }], source: { kind: 'plugin', plugin: 'before' }, }, { surfaceOp: 'append' }) @@ -82,7 +82,7 @@ describe('Session', () => { turn: 3, trigger: { kind: 'injection', source: { kind: 'plugin', plugin: 'after' } }, }) - session.append('context/message', { + session.append('user/message', { content: [{ type: 'text', text: 'after' }], source: { kind: 'plugin', plugin: 'after' }, }, { surfaceOp: 'append' }) @@ -117,9 +117,9 @@ describe('Session', () => { .toThrow('seed turn/end at index 1 uses unsupported reason-bearing aborted format') }) - it('renders context and steering messages as plain user content', () => { + it('renders injected-context and steering messages as plain user content', () => { const session = new Session(SessionId('s2')) - session.append('context/message', { + session.append('user/message', { content: [{ type: 'text', text: 'file changed: a.ts' }], source: { kind: 'plugin', plugin: 'watcher' }, }, { surfaceOp: 'append' }) @@ -172,7 +172,7 @@ describe('Session', () => { version: 1, changes: [{ action: 'set', scope: 'pkg', path: 'pkg/AGENTS.md', digest: 'abc123' }], } - session.append('context/message', { + session.append('user/message', { content: [{ type: 'text', text: '<system-reminder>Additional instructions from: pkg/AGENTS.md</system-reminder>' }], source: { kind: 'plugin', plugin: 'workspace-context' }, meta, @@ -183,7 +183,7 @@ describe('Session', () => { content: [{ type: 'text', text: '<system-reminder>Additional instructions from: pkg/AGENTS.md</system-reminder>' }], }]) const event = session.events[0] - expect(event?.type === 'context/message' && event.data.meta).toEqual(meta) + expect(event?.type === 'user/message' && event.data.meta).toEqual(meta) }) it('replays identically from a seeded event log', () => { @@ -757,7 +757,7 @@ describe('Session', () => { { header: 1, error: /not a plain JSON record/ }, { header: null, error: /not a plain JSON record/ }, { header: { ...base, version: 1 }, error: /header version/ }, - { header: { ...base, createdAt: '123' }, error: /createdAt must be a finite number/ }, + { header: { ...base, createdAt: '123' }, error: /createdAt must be a non-negative safe integer/ }, { header: { ...base, cwd: 1 }, error: /header cwd must be a string/ }, { header: { ...base, cwd: 'relative' }, error: /header cwd must be an absolute path/ }, { header: { ...base, parentSession: 1 }, error: /header parentSession must be a string/ }, @@ -962,7 +962,7 @@ describe('SessionStore', () => { await ctx.plugin(SessionStore) const session = ctx.sessions.create(SessionId('plain')) expect(session.header).toMatchObject({ version: SESSION_FORMAT_VERSION, id: 'plain' }) - expect(typeof session.header.createdAt).toBe('number') + expect(Number.isSafeInteger(session.header.createdAt)).toBe(true) expect(session.header.cwd).toBeUndefined() expect(session.header.parentSession).toBeUndefined() }) @@ -1001,7 +1001,10 @@ describe('SessionStore', () => { { meta: { parentSession: 1n }, error: /header is not losslessly JSON-serializable/ }, { meta: { cwd: 1 }, error: /header cwd must be a string/ }, { meta: { parentSession: 1 }, error: /header parentSession must be a string/ }, - { meta: { createdAt: '123' }, error: /header createdAt must be a finite number/ }, + { meta: { createdAt: '123' }, error: /header createdAt must be a non-negative safe integer/ }, + { meta: { createdAt: 1.5 }, error: /header createdAt must be a non-negative safe integer/ }, + { meta: { createdAt: -1 }, error: /header createdAt must be a non-negative safe integer/ }, + { meta: { createdAt: Number.MAX_SAFE_INTEGER + 1 }, error: /header createdAt must be a non-negative safe integer/ }, { meta: { seedLength: '1' }, error: /seedLength must be a non-negative safe integer/ }, { meta: { seedLength: 0.5 }, error: /seedLength must be a non-negative safe integer/ }, { meta: { seedLength: -1 }, error: /seedLength must be a non-negative safe integer/ }, diff --git a/packages/core/session/tests/surface.spec.ts b/packages/core/session/tests/surface.spec.ts index b7cbe11b11..cfb84f4e18 100644 --- a/packages/core/session/tests/surface.spec.ts +++ b/packages/core/session/tests/surface.spec.ts @@ -444,9 +444,9 @@ describe('deriveMessages with surface', () => { expect(messages[0]!.content[0]).toMatchObject({ type: 'text', text: 'compacted' }) }) - it('context/message and steering/message appear on surface', () => { + it('injected-context and steering/message appear on surface', () => { const s = new Session(SessionId('ctx')) - s.append('context/message', { content: [{ type: 'text', text: 'file changed' }], source: { kind: 'plugin', plugin: 'watcher' } }, { surfaceOp: 'append' }) + s.append('user/message', { content: [{ type: 'text', text: 'file changed' }], source: { kind: 'plugin', plugin: 'watcher' } }, { surfaceOp: 'append' }) s.append('steering/message', { turn: 1, content: [{ type: 'text', text: 'focus' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) const messages = s.deriveMessages() expect(messages).toHaveLength(2) @@ -524,7 +524,6 @@ describe('surface type guards', () => { expect(isSurfaceEligibleType('user/message')).toBe(true) expect(isSurfaceEligibleType('assistant/message')).toBe(true) expect(isSurfaceEligibleType('tool/result')).toBe(true) - expect(isSurfaceEligibleType('context/message')).toBe(true) expect(isSurfaceEligibleType('steering/message')).toBe(true) expect(isSurfaceEligibleType('turn/start')).toBe(false) expect(isSurfaceEligibleType('assistant/chunk')).toBe(false) @@ -568,7 +567,7 @@ describe('SurfaceManager.replaceGeneration', () => { expect(s.surface.replaceGeneration).toBe(0) const nodes = s.surface.nodes - s.append('context/message', { + s.append('user/message', { content: [{ type: 'text', text: 'summary' }], source: { kind: 'plugin', plugin: 'compact' }, }, { surfaceOp: { op: 'replace', start: nodes[0]!, end: nodes[1]! }, sourceEventSeqs: [nodes[0]!, nodes[1]!] }) expect(s.surface.replaceGeneration).toBe(1) diff --git a/packages/examples/agent-spine-demo/tests/agent-core.spec.ts b/packages/examples/agent-spine-demo/tests/agent-core.spec.ts index 1ac506a098..e00bf2016d 100644 --- a/packages/examples/agent-spine-demo/tests/agent-core.spec.ts +++ b/packages/examples/agent-spine-demo/tests/agent-core.spec.ts @@ -235,7 +235,7 @@ describe('dsh-agent-spine-demo bundle', () => { agentOptions: { provider: 'mock', model: 'mock' }, }) - handle.agent.send([{ type: 'text', text: 'recover' }]) + handle.agent.followup([{ type: 'text', text: 'recover' }]) await waitForIdle(ctx, handle.agent) expect(adapter.requests).toBe(2) @@ -335,7 +335,7 @@ describe('dsh-agent-spine-demo bundle', () => { }) const agent = handle.agent - agent.send([{ type: 'text', text: 'hi' }]) + agent.followup([{ type: 'text', text: 'hi' }]) await waitForIdle(ctx, agent) const sentText = adapter.requests[0]?.messages.map(messageText).join('\n') @@ -364,7 +364,7 @@ describe('dsh-agent-spine-demo bundle', () => { agentOptions: { provider: 'mock', model: 'mock' }, }) - handle.agent.send([{ type: 'text', text: 'hi' }]) + handle.agent.followup([{ type: 'text', text: 'hi' }]) await waitForIdle(ctx, handle.agent) expect(adapter.requests[0]?.messages).toEqual([{ role: 'user', content: [{ type: 'text', text: 'hi' }] }]) @@ -454,7 +454,7 @@ describe('dsh-agent-spine-demo bundle', () => { agentOptions: { provider: 'mock', model: 'mock' }, }) - handle.agent.send([{ type: 'text', text: 'hi' }]) + handle.agent.followup([{ type: 'text', text: 'hi' }]) await waitForIdle(ctx, handle.agent) expect(messageText(adapter.requests[0]?.messages[0])).toContain('workspace rule before skills') diff --git a/packages/examples/cli-demo/src/cli.ts b/packages/examples/cli-demo/src/cli.ts index 66ce345520..e6672f91ad 100644 --- a/packages/examples/cli-demo/src/cli.ts +++ b/packages/examples/cli-demo/src/cli.ts @@ -290,7 +290,7 @@ export async function runOneShot(ctx: Context, options: OneShotOptions): Promise try { /* v8 ignore next -- skips send only when cancellation wins the listener-registration race above */ if (!settled) { // eslint-disable-line @typescript-eslint/no-unnecessary-condition - agent.send([{ type: 'text', text: options.task }]) + agent.followup([{ type: 'text', text: options.task }]) } await turnEnded } finally { diff --git a/packages/examples/cli-demo/tests/cli.spec.ts b/packages/examples/cli-demo/tests/cli.spec.ts index 65eafff1cc..c57dda5b00 100644 --- a/packages/examples/cli-demo/tests/cli.spec.ts +++ b/packages/examples/cli-demo/tests/cli.spec.ts @@ -369,7 +369,7 @@ describe('runOneShot and executeCli', () => { const { ctx, agent } = await harness([textResponse('streamed')]) const other = ctx.sessions.create(SessionId('unrelated')) let injected = false - ctx.on('agent/queued', (subject) => { + ctx.on('agent/inbox/enqueue', (subject) => { if (subject !== agent || injected) return injected = true agent.inject([{ type: 'text', text: 'startup injection' }], { source: { kind: 'plugin', plugin: 'test' } }) @@ -383,7 +383,7 @@ describe('runOneShot and executeCli', () => { expect(events[0]).toMatchObject({ type: 'turn/start', data: { turn: 2, trigger: { kind: 'message' } } }) expect(events.at(-1)).toMatchObject({ type: 'turn/end', data: { turn: 2 } }) expect(lines.slice(0, -1).every(line => line['sessionId'] === agent.session.id)).toBe(true) - expect(events.some(event => event.type === 'context/message')).toBe(false) + expect(events.some(event => event.type === 'user/message' && event.data.source.kind !== 'user')).toBe(false) }) it('emits partial data and a diagnostic for non-completed turns', async () => { @@ -471,7 +471,7 @@ describe('runOneShot and executeCli', () => { startup.ctx.on('session/event', (session, event) => { if (session === startup.agent.session && event.type === 'assistant/chunk') started() }) - startup.agent.send([{ type: 'text', text: 'first' }]) + startup.agent.followup([{ type: 'text', text: 'first' }]) await running const startupAbort = new AbortController() const waiting = runOneShot(startup.ctx, { task: 'second', signal: startupAbort.signal }) @@ -481,7 +481,7 @@ describe('runOneShot and executeCli', () => { const queued = await harness([textResponse('unused')]) const queuedAbort = new AbortController() - queued.ctx.on('agent/queued', (agent) => { + queued.ctx.on('agent/inbox/enqueue', (agent) => { if (agent === queued.agent) queuedAbort.abort('cancel queued') }) await expect(runOneShot(queued.ctx, { task: 'task', signal: queuedAbort.signal })).rejects.toThrow('cancel queued') diff --git a/packages/fs/tool-fs/tests/fs-tools.e2e.ts b/packages/fs/tool-fs/tests/fs-tools.e2e.ts index 472b32f47a..b768813b22 100644 --- a/packages/fs/tool-fs/tests/fs-tools.e2e.ts +++ b/packages/fs/tool-fs/tests/fs-tools.e2e.ts @@ -36,7 +36,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('fs tools with-key smoke', () => // (config.cwd = workdir) is the workspace. const agent = ctx.agentLoop.create(SessionId('fs-e2e'), { provider: 'deepseek', model: 'deepseek-v4-flash' }) - agent.send([{ type: 'text', text: + agent.followup([{ type: 'text', text: 'Create a file named note.txt containing exactly the line: status: draft. ' + 'Then read it back, then edit it to replace the literal word draft with final. ' + 'Tell me when done.' }]) @@ -68,7 +68,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('fs tools with-key smoke', () => meta: { cwd: sessionDir }, agentOptions: { provider: 'deepseek', model: 'deepseek-v4-flash' }, }) - handle.agent.send([{ type: 'text', text: + handle.agent.followup([{ type: 'text', text: 'Use the write tool to create a file named where.txt containing exactly the line: here. Tell me when done.' }]) await waitForIdle(ctx, handle.agent) diff --git a/packages/goal/command-goal/tests/command-goal.spec.ts b/packages/goal/command-goal/tests/command-goal.spec.ts index 35994ecb71..a958659eba 100644 --- a/packages/goal/command-goal/tests/command-goal.spec.ts +++ b/packages/goal/command-goal/tests/command-goal.spec.ts @@ -1,7 +1,7 @@ import { describe, expect, it, vi } from 'vitest' import { Context } from 'cordis' import Loader from '@cordisjs/plugin-loader' -import AgentRegistry from '@deepseek-ai/dsh-agent' +import AgentRegistry, { AgentMessageId } from '@deepseek-ai/dsh-agent' import type { Agent, AgentStatus, InjectOptions } from '@deepseek-ai/dsh-agent' import CommandService from '@deepseek-ai/dsh-commands' import GoalService from '@deepseek-ai/dsh-goal' @@ -27,10 +27,10 @@ function nextTurn(session: Session): number { /** Append one idle injection using the public Agent contract's balanced shape. */ function appendInjection(session: Session, content: ContentBlock[], options?: InjectOptions): void { - const source: MessageSource = options?.source ?? { kind: 'user' } + const source: MessageSource = options?.source ?? { kind: 'plugin', plugin: '' } const turn = nextTurn(session) session.append('turn/start', { turn, trigger: { kind: 'injection', source } }) - session.append('context/message', { + session.append('user/message', { content, source, ...options?.meta === undefined ? {} : { meta: options.meta }, @@ -48,9 +48,11 @@ function stubAgent(id: string): { agent: Agent; session: Session } { session, ctx: new Context(), get status() { return status }, - send() {}, - steer() {}, - inject(content, options) { appendInjection(session, content, options) }, + followup: () => AgentMessageId('stub'), + queue: () => AgentMessageId('stub'), + steer: () => AgentMessageId('stub'), + inject(content, options) { appendInjection(session, content, options); return AgentMessageId('stub') }, + send: () => AgentMessageId('stub'), cancel() { status = 'idle' }, whenIdle() { return Promise.resolve() }, } @@ -125,7 +127,7 @@ describe('/goal human command', () => { expect(created.text).toContain('Rounds: 0/256') expect(created.text).toContain('Activation: armed') expect(test.ctx.goals.get(test.agent)?.objective).toBe('finish the release') - expect(test.session.events.map(event => event.type)).toEqual(['turn/start', 'context/message', 'turn/end']) + expect(test.session.events.map(event => event.type)).toEqual(['turn/start', 'user/message', 'turn/end']) const count = test.session.events.length await expect(run(test, ' replacement')).resolves.toEqual({ diff --git a/packages/goal/goal-session/src/index.ts b/packages/goal/goal-session/src/index.ts index bcb3fc2a75..67cbd89d05 100644 --- a/packages/goal/goal-session/src/index.ts +++ b/packages/goal/goal-session/src/index.ts @@ -219,7 +219,7 @@ export function apply(ctx: Context): void { } state.attempt = reservation try { - agent.send(content, { + agent.followup(content, { source: { kind: 'goal', goalId: goal.id, revision: goal.revision, round }, }) } catch (error: unknown) { @@ -306,10 +306,10 @@ export function apply(ctx: Context): void { requestDrive(state) } }) - ctx.on('agent/queued', (agent, content, info) => { + ctx.on('agent/inbox/enqueue', (agent, info) => { const state = stateFor(agent) const attempt = state.attempt - if (attempt !== undefined && sameQueued(content, info.source, attempt)) return + if (attempt !== undefined && sameQueued(info.content, info.source, attempt)) return state.competingQueued = true if (attempt?.phase === 'queued') attempt.stale = true }) diff --git a/packages/goal/goal-session/src/prompt.ts b/packages/goal/goal-session/src/prompt.ts index 9a2f69fcd8..d98f0bb83a 100644 --- a/packages/goal/goal-session/src/prompt.ts +++ b/packages/goal/goal-session/src/prompt.ts @@ -7,7 +7,7 @@ import type { GoalView } from '@deepseek-ai/dsh-goal' * Render the complete goal-round instruction retained in session history. * @param goal - exact active goal revision being admitted. * @param round - next positive round number. - * @returns a fresh one-block prompt for `Agent.send()`. + * @returns a fresh one-block prompt for `Agent.followup()`. */ export function renderGoalRoundPrompt(goal: GoalView, round: number): ContentBlock[] { return [{ diff --git a/packages/goal/goal-session/tests/goal-session.spec.ts b/packages/goal/goal-session/tests/goal-session.spec.ts index f204893578..dc3d6723a7 100644 --- a/packages/goal/goal-session/tests/goal-session.spec.ts +++ b/packages/goal/goal-session/tests/goal-session.spec.ts @@ -207,7 +207,9 @@ describe('same-session goal driving', () => { expect(test.adapter.requests).toHaveLength(2) const rounds: number[] = [] for (const event of test.agent.session.events) { - if (event.type === 'user/message' && event.data.source.kind === 'goal') { + // Round zero is a durable goal state change; positive rounds are the + // admitted continuation prompts this test counts. + if (event.type === 'user/message' && event.data.source.kind === 'goal' && event.data.source.round > 0) { rounds.push(event.data.source.round) } } @@ -274,7 +276,7 @@ describe('same-session goal driving', () => { ? Promise.resolve({ kind: 'block', reason: 'stop this round' }) : next()) test.ctx.on('goal/changed', (agent, change) => { - if (change.operation === 'block') agent.send([{ type: 'text', text: 'inspect the blocker' }]) + if (change.operation === 'block') agent.followup([{ type: 'text', text: 'inspect the blocker' }]) }) test.ctx.goals.create(test.agent, { objective: 'stop and inspect' }) @@ -287,7 +289,7 @@ describe('same-session goal driving', () => { it('pauses and drops a reserved round when cancellation lands before admission', async () => { const test = await harness([]) - const cancel = test.ctx.on('agent/queued', (agent, _content, info) => { + const cancel = test.ctx.on('agent/inbox/enqueue', (agent, info) => { if (agent === test.agent && info.source.kind === 'goal') { cancel() agent.cancel({ kind: 'user' }) @@ -299,8 +301,10 @@ describe('same-session goal driving', () => { expect(goal).toMatchObject({ roundsStarted: 0, activation: 'disarmed' }) expect(test.adapter.requests).toHaveLength(0) + // No admitted continuation round (positive round); goal state changes + // (round zero) are expected in the log. expect(test.agent.session.events.some(event => event.type === 'user/message' - && event.data.source.kind === 'goal')).toBe(false) + && event.data.source.kind === 'goal' && event.data.source.round > 0)).toBe(false) }) it('pauses an admitted round when cancellation aborts an active step', async () => { @@ -319,7 +323,7 @@ describe('same-session goal driving', () => { it('lets already-queued human work finish before reserving the next round', async () => { const test = await harness([textResponse('human answer'), textResponse('goal answer')]) test.ctx.goals.create(test.agent, { objective: 'continue after the human', maxGoalRounds: 1 }) - test.agent.send([{ type: 'text', text: 'human goes first' }]) + test.agent.followup([{ type: 'text', text: 'human goes first' }]) await waitForGoal(test.ctx, test.agent, goal => goal?.phase === 'blocked') @@ -334,7 +338,7 @@ describe('same-session goal driving', () => { const warnings: string[] = [] test.ctx.logger.warn = ((message: unknown) => { warnings.push(String(message)) }) as typeof test.ctx.logger.warn let inserted = false - test.ctx.on('agent/queued', (agent, _content, info) => { + test.ctx.on('agent/inbox/enqueue', (agent, info) => { if (agent !== test.agent || info.source.kind !== 'goal' || inserted) return inserted = true const lastStart = agent.session.events.findLast(event => event.type === 'turn/start') @@ -357,10 +361,10 @@ describe('same-session goal driving', () => { it('makes a reserved round stale when a listener queues human work behind it', async () => { const test = await harness([textResponse('human batch'), textResponse('later goal')]) let inserted = false - test.ctx.on('agent/queued', (agent, _content, info) => { + test.ctx.on('agent/inbox/enqueue', (agent, info) => { if (agent !== test.agent || info.source.kind !== 'goal' || inserted) return inserted = true - agent.send([{ type: 'text', text: 'human joined the pending batch' }]) + agent.followup([{ type: 'text', text: 'human joined the pending batch' }]) }) test.ctx.goals.create(test.agent, { objective: 'yield to nested human input', maxGoalRounds: 1 }) @@ -375,7 +379,7 @@ describe('same-session goal driving', () => { it('blocks a queued reservation made stale by a goal edit and continues the new revision', async () => { const test = await harness([textResponse('new revision')]) let edited = false - test.ctx.on('agent/queued', (agent, _content, info) => { + test.ctx.on('agent/inbox/enqueue', (agent, info) => { if (agent !== test.agent || info.source.kind !== 'goal' || edited) return edited = true const current = test.ctx.goals.get(agent) @@ -391,7 +395,7 @@ describe('same-session goal driving', () => { expect(blocked?.type === 'prompt/blocked' ? blocked.data.reason : undefined) .toBe('stale goal-round reservation') const admitted = test.agent.session.events.find(event => event.type === 'user/message' - && event.data.source.kind === 'goal') + && event.data.source.kind === 'goal' && event.data.source.round > 0) expect(admitted?.type === 'user/message' && admitted.data.source.kind === 'goal' ? admitted.data.source.revision : undefined).toBe(2) @@ -475,10 +479,16 @@ describe('same-session goal driving', () => { expect(injectedTurn).toBeGreaterThan(goalTurn) }) - it('blocks the goal when a custom agent rejects the otherwise valid send', async () => { + it('blocks the goal when a custom agent rejects the otherwise valid follow-up', async () => { const test = await harness([]) - vi.spyOn(test.agent, 'send').mockImplementationOnce(() => { - throw new Error('queue rejected') + // Reject only the goal-sourced round follow-up, not the state-change injection + // that precedes it. + const realFollowup = test.agent.followup.bind(test.agent) + vi.spyOn(test.agent, 'followup').mockImplementation((content, options) => { + if (options?.source?.kind === 'goal') { + throw new Error('queue rejected') + } + return realFollowup(content, options) }) test.ctx.goals.create(test.agent, { objective: 'handle queue failure' }) @@ -492,11 +502,15 @@ describe('same-session goal driving', () => { expect(test.adapter.requests).toHaveLength(0) }) - it('preserves a custom agent side effect when send disarms before throwing', async () => { + it('preserves a custom agent side effect when followup disarms before throwing', async () => { const test = await harness([]) - vi.spyOn(test.agent, 'send').mockImplementationOnce(() => { - test.ctx.goals.disarm(test.agent) - throw new Error('queue rejected after disarm') + const realFollowup = test.agent.followup.bind(test.agent) + vi.spyOn(test.agent, 'followup').mockImplementation((content, options) => { + if (options?.source?.kind === 'goal') { + test.ctx.goals.disarm(test.agent) + throw new Error('queue rejected after disarm') + } + return realFollowup(content, options) }) test.ctx.goals.create(test.agent, { objective: 'preserve the newer activation state' }) @@ -554,7 +568,7 @@ describe('same-session goal driving', () => { it('fails a pre-admission read closed even when the first disarm attempt throws', async () => { const test = await harness([textResponse('retry after containment')]) let armed = true - test.ctx.on('agent/queued', (agent, _content, info) => { + test.ctx.on('agent/inbox/enqueue', (agent, info) => { if (agent !== test.agent || info.source.kind !== 'goal' || !armed) return armed = false vi.spyOn(test.ctx.goals, 'get').mockImplementationOnce(() => { @@ -595,7 +609,7 @@ describe('same-session goal driving', () => { it('blocks forged goal attribution without touching an absent reservation', async () => { const test = await harness([]) - test.agent.send([{ type: 'text', text: 'forged automatic work' }], { + test.agent.followup([{ type: 'text', text: 'forged automatic work' }], { source: { kind: 'goal', goalId: GoalId('forged-goal'), revision: 1, round: 1 }, }) await test.agent.whenIdle() @@ -607,7 +621,7 @@ describe('same-session goal driving', () => { it('does not invent goal state when ordinary queued work is cancelled', async () => { const test = await harness([]) - test.agent.send([{ type: 'text', text: 'cancel ordinary work' }]) + test.agent.followup([{ type: 'text', text: 'cancel ordinary work' }]) test.agent.cancel({ kind: 'user' }) await test.agent.whenIdle() @@ -617,7 +631,7 @@ describe('same-session goal driving', () => { it('disarms without durably pausing when cancellation belongs to unrelated human work', async () => { const test = await harness(['hang']) - test.agent.send([{ type: 'text', text: 'inspect something first' }]) + test.agent.followup([{ type: 'text', text: 'inspect something first' }]) await waitForRequests(test.adapter, 1) const created = test.ctx.goals.create(test.agent, { objective: 'continue after inspection' }) @@ -635,7 +649,7 @@ describe('same-session goal driving', () => { it('falls back to disarming when a cancelled reservation cannot be paused', async () => { const test = await harness([]) - const cancel = test.ctx.on('agent/queued', (agent, _content, info) => { + const cancel = test.ctx.on('agent/inbox/enqueue', (agent, info) => { if (agent !== test.agent || info.source.kind !== 'goal') return cancel() vi.spyOn(test.ctx.goals, 'pause').mockImplementationOnce(() => { @@ -689,7 +703,7 @@ describe('same-session goal driving', () => { it('cancels an accepted queued round and awaits its driver task during teardown', async () => { const test = await harness([]) let unloading: Promise<void> | undefined - test.ctx.on('agent/queued', (agent, _content, info) => { + test.ctx.on('agent/inbox/enqueue', (agent, info) => { if (agent === test.agent && info.source.kind === 'goal' && unloading === undefined) { unloading = Promise.resolve(test.driver.dispose()) } diff --git a/packages/goal/goal-session/tests/invariant.spec.ts b/packages/goal/goal-session/tests/invariant.spec.ts index 19200747e8..0427a41333 100644 --- a/packages/goal/goal-session/tests/invariant.spec.ts +++ b/packages/goal/goal-session/tests/invariant.spec.ts @@ -40,7 +40,7 @@ function view(roundsStarted: number): GoalView { function appendChange(session: Session): void { session.append('turn/start', { turn: 1, trigger: { kind: 'injection', source: changeSource } }) - session.append('context/message', { + session.append('user/message', { content: renderGoalChange(change), source: changeSource, meta: change as never, @@ -126,7 +126,7 @@ describe('goal-session prompt invariants', () => { it('attributes an invalid durable prefix during late loading', async () => { const { ctx, session } = await mount(true) session.append('turn/start', { turn: 1, trigger: { kind: 'injection', source: changeSource } }) - session.append('context/message', { + session.append('user/message', { content: [{ type: 'text', text: 'counterfeit goal state' }], source: changeSource, meta: change as never, diff --git a/packages/goal/goal/README.md b/packages/goal/goal/README.md index e50044d135..1df6d08f5c 100644 --- a/packages/goal/goal/README.md +++ b/packages/goal/goal/README.md @@ -19,7 +19,7 @@ Event-sourced same-session goal state. The service retains one current completio At most one goal is current. Creation produces an active revision-one goal and arms it. A non-complete goal must be edited, transitioned, or cleared; a completed goal may be replaced by a globally fresh id. Edits retain phase, blocker reason, and activation. Pause, completion, blocking, and clear disarm activation. A block records a policy-owned lower-kebab-case code plus a normalized free-form explanation; provider limits, configured budgets, execution errors, and requests for human input all use this one durable phase rather than multiplying lifecycle states. Resume accepts a stopped phase or a disarmed active goal only while the configured round cap has remaining capacity; it clears any former blocker reason. An active armed goal rejects the redundant operation. -Every non-clear mutation appends a complete versioned snapshot through `agent.inject()`; clear appends a revisioned tombstone. The `context/message` content projected verbatim to the model, its `{ kind: 'goal' }` source, and its metadata must agree exactly. Replay rejects malformed shapes, source/content drift, discontinuous revisions, illegal lifecycle transitions, non-monotonic per-goal timestamps, and non-sequential goal rounds. Mutation timestamps clamp against the preceding goal update when wall time moves backward. +Every non-clear mutation appends a complete versioned snapshot through `agent.inject()`; clear appends a revisioned tombstone. The round-zero `user/message` content projected verbatim to the model, its `{ kind: 'goal' }` source, and its metadata must agree exactly. Replay rejects malformed shapes, source/content drift, discontinuous revisions, illegal lifecycle transitions, non-monotonic per-goal timestamps, and non-sequential goal rounds. Mutation timestamps clamp against the preceding goal update when wall time moves backward. Injection may append immediately or wait in an active tool-batch FIFO. The service overlays accepted pending changes in memory and reconciles each exact payload when it enters the log, so consecutive model-tool mutations see their own latest revisions without treating an unlogged cache as durable state. Reentrant append observers see each accepted mutation exactly once, and incremental replay retains its cursor at the first corrupt event. `goal/changed` fires after the append or enqueue succeeds; listener failures are contained. diff --git a/packages/goal/goal/src/fold.ts b/packages/goal/goal/src/fold.ts index fe88ebcdba..2ff756249f 100644 --- a/packages/goal/goal/src/fold.ts +++ b/packages/goal/goal/src/fold.ts @@ -17,7 +17,7 @@ import type { GoalSnapshotChangeMeta, } from './types.ts' -type ContextMessageEvent = Extract<SessionEvent, { type: 'context/message' }> +type UserMessageEvent = Extract<SessionEvent, { type: 'user/message' }> const SNAPSHOT_OPERATIONS: ReadonlySet<Exclude<GoalOperation, 'clear'>> = new Set([ 'create', @@ -310,17 +310,18 @@ export function applyGoalChange(state: GoalFoldState, change: GoalChangeMeta): v } /** - * Decode and verify one model-visible goal context event without folding it. - * @param event - context event whose metadata and rendered content must agree. - * @returns validated change or `undefined` for an unrelated context event. + * Decode and verify one model-visible goal state change without folding it. A + * goal state change is a round-zero goal-sourced `user/message` carrying + * `goal/change` metadata; any other user message returns `undefined`. Goal + * metadata on a non-goal source, or a mismatched attribution or rendered body, + * fails replay loudly. + * @param event - user message whose metadata and rendered content must agree. + * @returns validated change, or `undefined` when the message is not a goal state change. */ -export function decodeGoalEvent(event: ContextMessageEvent): GoalChangeMeta | undefined { +export function decodeGoalEvent(event: UserMessageEvent): GoalChangeMeta | undefined { const change = decodeGoalChange(event.data.meta) + if (change === undefined) return undefined const source = goalSource(event.data.source) - if (change === undefined) { - if (source !== undefined) throw new Error(`goal source at session event ${event.seq} lacks goal change metadata`) - return undefined - } const ref = goalChangeRef(change) if (source === undefined || source.goalId !== ref.id || source.revision !== ref.revision || source.round !== 0) { throw new Error(`goal change at session event ${event.seq} has mismatched source attribution`) @@ -338,23 +339,27 @@ export function decodeGoalEvent(event: ContextMessageEvent): GoalChangeMeta | un * @returns decoded change for pending-overlay reconciliation. */ export function applyGoalEvent(state: GoalFoldState, event: SessionEvent): GoalChangeMeta | undefined { - if (event.type === 'context/message') { - const change = decodeGoalEvent(event) - if (change === undefined) return undefined - applyGoalChange(state, change) - return change - } if (event.type === 'user/message') { - const source = goalSource(event.data.source) - if (source !== undefined) { - const current = state.goal - if (current === undefined || current.phase !== 'active' || source.goalId !== current.id - || source.revision !== current.revision || source.round !== state.roundsStarted + 1 - || source.round > current.maxGoalRounds) { - throw new Error(`goal round at session event ${event.seq} is not the next admitted round of the active goal`) - } - state.roundsStarted = source.round + // A goal state change carries `goal/change` metadata (round zero). + const change = decodeGoalEvent(event) + if (change !== undefined) { + applyGoalChange(state, change) + return change } + const source = goalSource(event.data.source) + if (source === undefined) return undefined + // A goal-sourced message without change metadata must be a positive-round + // admitted continuation prompt; round zero owes durable change metadata. + if (source.round === 0) { + throw new Error(`goal source at session event ${event.seq} lacks goal change metadata`) + } + const current = state.goal + if (current === undefined || current.phase !== 'active' || source.goalId !== current.id + || source.revision !== current.revision || source.round !== state.roundsStarted + 1 + || source.round > current.maxGoalRounds) { + throw new Error(`goal round at session event ${event.seq} is not the next admitted round of the active goal`) + } + state.roundsStarted = source.round } return undefined } diff --git a/packages/goal/goal/src/index.ts b/packages/goal/goal/src/index.ts index 7391c69e93..e4700452fa 100644 --- a/packages/goal/goal/src/index.ts +++ b/packages/goal/goal/src/index.ts @@ -370,7 +370,9 @@ export class GoalService extends Service { /** Incrementally observe durable events without losing deferred mutations. */ private sync(session: Session, cache: GoalCache): void { for (const event of session.events.slice(cache.observedSeq)) { - if (event.type === 'context/message') { + // A goal state change is a round-zero goal-sourced user message; a + // positive round is a continuation prompt handled by applyGoalEvent. + if (event.type === 'user/message' && event.data.source.kind === 'goal' && event.data.source.round === 0) { const change = decodeGoalEvent(event) if (change !== undefined) { const pending = cache.pending[0] diff --git a/packages/goal/goal/src/runtime.ts b/packages/goal/goal/src/runtime.ts index 49184faa8c..5a97cceae0 100644 --- a/packages/goal/goal/src/runtime.ts +++ b/packages/goal/goal/src/runtime.ts @@ -3,7 +3,7 @@ import { HarnessError } from '@deepseek-ai/dsh-llm' import type { GoalErrorCode, GoalId as GoalIdType } from './types.ts' -/** Version of the goal change metadata embedded in `context/message`. */ +/** Version of the goal change metadata embedded in a round-zero `user/message`. */ export const GOAL_CHANGE_VERSION = 1 /** diff --git a/packages/goal/goal/src/types.ts b/packages/goal/goal/src/types.ts index 2c6798718d..7da3c525d7 100644 --- a/packages/goal/goal/src/types.ts +++ b/packages/goal/goal/src/types.ts @@ -89,7 +89,7 @@ export interface GoalClearChangeMeta { readonly clearedAt: number } -/** Durable metadata union carried by a goal-owned `context/message`. */ +/** Durable metadata union carried by a goal-owned round-zero `user/message`. */ export type GoalChangeMeta = GoalSnapshotChangeMeta | GoalClearChangeMeta /** Message attribution for durable goal state and continuation rounds. */ diff --git a/packages/goal/goal/tests/goal.e2e.ts b/packages/goal/goal/tests/goal.e2e.ts index 0c582645bc..756073083a 100644 --- a/packages/goal/goal/tests/goal.e2e.ts +++ b/packages/goal/goal/tests/goal.e2e.ts @@ -50,11 +50,11 @@ describe('goal domain through a real cordis.yml and headless process', () => { expect(result['result']).toContain('CLI tool round trip complete') expect(events.filter(event => event.type === 'turn/end')).toHaveLength(1) - const contexts = events.filter(event => event.type === 'context/message' + const contexts = events.filter(event => event.type === 'user/message' && event.data.source.kind === 'goal') expect(contexts).toHaveLength(1) const context = contexts[0] - if (context?.type !== 'context/message') throw new Error('expected goal context event') + if (context?.type !== 'user/message') throw new Error('expected goal context event') const change = decodeGoalChange(context.data.meta) if (change === undefined) throw new Error('expected durable goal change') expect(change).toMatchObject({ @@ -69,7 +69,9 @@ describe('goal domain through a real cordis.yml and headless process', () => { }) expect(context.data.content).toEqual(renderGoalChange(change)) expect(JSON.stringify(context)).not.toContain('activation') + // No admitted continuation round ran (the snapshot mounts without starting + // a round); the round-zero state change from create is expected above. expect(events.filter(event => event.type === 'user/message' - && event.data.source.kind === 'goal')).toHaveLength(0) + && event.data.source.kind === 'goal' && event.data.source.round > 0)).toHaveLength(0) }, LOADER_SMOKE_TEST_TIMEOUT_MS) }) diff --git a/packages/goal/goal/tests/goal.spec.ts b/packages/goal/goal/tests/goal.spec.ts index ad2011fc62..264261d94b 100644 --- a/packages/goal/goal/tests/goal.spec.ts +++ b/packages/goal/goal/tests/goal.spec.ts @@ -1,6 +1,6 @@ import { describe, expect, it, vi } from 'vitest' import { Context } from 'cordis' -import AgentRegistry, { agentEvents } from '@deepseek-ai/dsh-agent' +import AgentRegistry, { agentEvents, AgentMessageId } from '@deepseek-ai/dsh-agent' import type { Agent, AgentStatus, InjectOptions } from '@deepseek-ai/dsh-agent' import { HarnessError, type ContentBlock, type MessageSource } from '@deepseek-ai/dsh-llm' import SessionStore, { Session, SessionId } from '@deepseek-ai/dsh-session' @@ -34,7 +34,7 @@ function nextTurn(session: Session): number { /** Mirror the public Agent.inject idle/open-turn contract for domain tests. */ function appendInjection(session: Session, content: ContentBlock[], options?: InjectOptions): void { - const source: MessageSource = options?.source ?? { kind: 'user' } + const source: MessageSource = options?.source ?? { kind: 'plugin', plugin: '' } const context = { content, source, @@ -43,12 +43,12 @@ function appendInjection(session: Session, content: ContentBlock[], options?: In const last = session.events.at(-1) const open = last !== undefined && last.type !== 'turn/end' if (open) { - session.append('context/message', context, { surfaceOp: 'append' }) + session.append('user/message', context, { surfaceOp: 'append' }) return } const turn = nextTurn(session) session.append('turn/start', { turn, trigger: { kind: 'injection', source } }) - session.append('context/message', context, { surfaceOp: 'append' }) + session.append('user/message', context, { surfaceOp: 'append' }) session.append('turn/end', { turn, reason: { kind: 'completed' } }) } @@ -64,12 +64,15 @@ function stubAgentForSession(session: Session): StubAgent { session, ctx: new Context(), get status() { return status }, - send() {}, - steer() {}, + followup: () => AgentMessageId('stub'), + queue: () => AgentMessageId('stub'), + steer: () => AgentMessageId('stub'), inject(content, options) { if (shouldDefer) deferred.push({ content, options }) else appendInjection(session, content, options) + return AgentMessageId('stub') }, + send: () => AgentMessageId('stub'), cancel() {}, whenIdle() { return Promise.resolve() }, } @@ -131,10 +134,10 @@ describe('GoalService creation and replay', () => { }) expect(goal.id).toMatch(/^goal-/) expect(seen).toEqual(['create']) - expect(session.events.map(event => event.type)).toEqual(['turn/start', 'context/message', 'turn/end']) + expect(session.events.map(event => event.type)).toEqual(['turn/start', 'user/message', 'turn/end']) const context = session.events[1] - expect(context?.type).toBe('context/message') - if (context?.type !== 'context/message') throw new Error('expected goal context') + expect(context?.type).toBe('user/message') + if (context?.type !== 'user/message') throw new Error('expected goal context') expect(context.data.source).toEqual({ kind: 'goal', goalId: goal.id, revision: 1, round: 0 }) const change = decodeGoalChange(context.data.meta) if (change === undefined) throw new Error('expected decoded goal change') @@ -266,7 +269,9 @@ describe('GoalService creation and replay', () => { it('requires the exact live registry instance for reads and mutations', async () => { const { ctx, agent } = await harness() - const impostor = { ...agent, session: new Session(agent.id) } + // A same-id agent backed by a different session object — the live-instance + // check must reject it even though the ids match. + const impostor = stubAgentForSession(new Session(agent.id)).agent expect(() => ctx.goals.get(impostor)).toThrow(expect.objectContaining({ code: 'GOAL_AGENT_NOT_LIVE' })) expect(() => ctx.goals.create(impostor, { objective: 'no' })).toThrow(expect.objectContaining({ code: 'GOAL_AGENT_NOT_LIVE', @@ -407,8 +412,8 @@ describe('GoalService mutations', () => { vi.setSystemTime(80) ctx.goals.clear(agent, goal) const clear = session.events - .filter(event => event.type === 'context/message') - .map(event => decodeGoalChange(event.data.meta)) + .filter(event => event.type === 'user/message' && event.data.source.kind === 'goal') + .map(event => event.type === 'user/message' ? decodeGoalChange(event.data.meta) : undefined) .at(-1) expect(clear).toMatchObject({ operation: 'clear', clearedAt: 100 }) expect(() => foldGoal(session.events)).not.toThrow() @@ -454,7 +459,7 @@ describe('GoalService mutations', () => { ctx.agents.register(stub.agent) let observed: ReturnType<GoalService['get']> ctx.on('session/event', (session, event) => { - if (session === stub.session && event.type === 'context/message') observed = ctx.goals.get(stub.agent) + if (session === stub.session && event.type === 'user/message' && event.data.source.kind === 'goal') observed = ctx.goals.get(stub.agent) }) const created = ctx.goals.create(stub.agent, { objective: 'publish once' }) @@ -473,7 +478,7 @@ describe('GoalService mutations', () => { let reject = true stub.agent.inject = (content, options) => { if (reject) throw new Error('injection rejected') - append(content, options) + return append(content, options) } ctx.agents.register(stub.agent) @@ -517,7 +522,7 @@ describe('GoalService mutations', () => { const source = { kind: 'goal', goalId: change.goal.id, revision: 1, round: 0 } as const const turn = nextTurn(session) session.append('turn/start', { turn, trigger: { kind: 'injection', source } }) - session.append('context/message', { + session.append('user/message', { content: renderGoalChange(change), source, meta: change as never, }, { surfaceOp: 'append' }) session.append('turn/end', { turn, reason: { kind: 'completed' } }) @@ -594,7 +599,7 @@ describe('goal replay validation', () => { } const turn = nextTurn(session) session.append('turn/start', { turn, trigger: { kind: 'injection', source } }) - session.append('context/message', { + session.append('user/message', { content: overrides.content ?? renderGoalChange(change), source, meta: change as never, @@ -791,7 +796,7 @@ describe('goal replay validation', () => { const source = { kind: 'goal', goalId: GoalId('goal-missing-meta'), revision: 1, round: 0 } as const const turn = nextTurn(session) session.append('turn/start', { turn, trigger: { kind: 'injection', source } }) - session.append('context/message', { + session.append('user/message', { content: [{ type: 'text', text: 'missing' }], source, }, { surfaceOp: 'append' }) session.append('turn/end', { turn, reason: { kind: 'completed' } }) @@ -853,7 +858,7 @@ describe('goal replay validation', () => { const source = { kind: 'goal', goalId: change.goal.id, revision: 2, round: 0 } as const const turn = nextTurn(session) session.append('turn/start', { turn, trigger: { kind: 'injection', source } }) - session.append('context/message', { + session.append('user/message', { content: renderGoalChange(clear), source, meta: clear as never, }, { surfaceOp: 'append' }) session.append('turn/end', { turn, reason: { kind: 'completed' } }) diff --git a/packages/goal/goal/tests/invariant.spec.ts b/packages/goal/goal/tests/invariant.spec.ts index 85f0b839d1..996743ceca 100644 --- a/packages/goal/goal/tests/invariant.spec.ts +++ b/packages/goal/goal/tests/invariant.spec.ts @@ -45,7 +45,7 @@ describe('goal stream invariants', () => { const ctx = await setup() const session = ctx.sessions.create(SessionId('goal-invariant-valid')) session.append('turn/start', { turn: 1, trigger: { kind: 'injection', source: changeSource } }) - session.append('context/message', { + session.append('user/message', { content: renderGoalChange(change), source: changeSource, meta: change as never, @@ -71,7 +71,7 @@ describe('goal stream invariants', () => { const session = ctx.sessions.create(SessionId('goal-invariant-invalid')) session.append('turn/start', { turn: 1, trigger: { kind: 'injection', source: changeSource } }) expect(() => { - session.append('context/message', { + session.append('user/message', { content: [{ type: 'text', text: 'counterfeit' }], source: changeSource, meta: change as never, @@ -82,7 +82,7 @@ describe('goal stream invariants', () => { })) expect(session.seq).toBe(1) expect(() => { - session.append('context/message', { + session.append('user/message', { content: renderGoalChange(change), source: changeSource, meta: change as never, @@ -95,7 +95,7 @@ describe('goal stream invariants', () => { await ctx.plugin(SessionStore) const session = ctx.sessions.create(SessionId('goal-invariant-late-load')) session.append('turn/start', { turn: 1, trigger: { kind: 'injection', source: changeSource } }) - session.append('context/message', { + session.append('user/message', { content: renderGoalChange(change), source: changeSource, meta: change as never, diff --git a/packages/goal/tool-goal/README.md b/packages/goal/tool-goal/README.md index 3f286f8ec3..346ac07dcc 100644 --- a/packages/goal/tool-goal/README.md +++ b/packages/goal/tool-goal/README.md @@ -6,9 +6,9 @@ The model-facing control surface for [`ctx.goals`](../goal/README.md): `get_goal - `get_goal()` returns the current goal or `null`, including the compare-and-set id/revision, durable phase, admitted/capped goal rounds, any blocker reason, and current process-local activation. - `create_goal(objective, max_goal_rounds?)` creates one goal from a direct top-level human turn. The model may infer long-running goal intent without an exact command phrase; non-human turns and subagents are rejected at execution. -- `update_goal(goal_id, revision, action, objective?, max_goal_rounds?, blocked_reason?)` supports `edit`, `pause`, `resume`, `complete`, and `blocked`. Replacements belong only to `edit`; `blocked_reason` is required only for `blocked` and is persisted with the stable code `model-reported`. +- `update_goal(goal_id, revision, action, objective?, max_goal_rounds?, blocked_reason?)` supports `edit`, `pause`, `resume`, `complete`, and `blocked`. Replacements belong only to `edit`; `blocked_reason` is required only for `blocked` and is persisted with the stable code `model-reported`. Strict-schema empty-string and zero fillers count as omitted, while meaningful values remain limited to their action. -All calls are exclusive, so a model-ordered batch observes earlier mutations and their new revisions. ACP and other clients receive pure generic cards: read for `get_goal`, other for mutations. +All calls are exclusive, so a model-ordered batch observes earlier mutations and their new revisions. ACP and other clients receive pure generic cards: read for `get_goal`, other for mutations. Mutation cards select the first meaningful action value and otherwise show the goal id, so accepted fillers never produce blank input. All three canonical values match the compact JSON already rendered to Native callers: `{ goal: null }` or `{ goal: { id, revision, objective, phase, roundsStarted, maxGoalRounds, blockedReason? }, activation }`. Programmatic consumers therefore receive the same domain structure without parsing the rendered JSON. @@ -18,7 +18,7 @@ An autonomous goal round that successfully reports `complete` or `blocked` contr Execution requires the exact live `exec.agent`, its inherited `AgentRegistry` initiator, running status, and an open turn. Create, edit, pause, and resume additionally require an accepted `{ kind: 'user' }` message or steering event in a runtime-root agent's current turn. Durable fork lineage does not demote a resumed root; live subagent ownership does. -`{ kind: 'user' }` is a host attestation. `Agent.send()` and `steer()` assign it when their caller omits a source, so plugins, schedulers, and other non-human producers must pass their own source rather than inheriting human authority. +`{ kind: 'user' }` is a host attestation. `Agent.followup()` and `steer()` assign it when their caller omits a source, so plugins, schedulers, and other non-human producers must pass their own source rather than inheriting human authority. Complete and blocked also accept the exact current goal round: a goal-sourced `user/message` whose id, revision, and round equal the folded current goal. A goal-round blocked call is mechanically rejected until `blockedAfterConsecutiveRounds`; the model judges whether the same condition actually persisted and must describe it in `blocked_reason`. Direct human authority may stop a goal immediately. diff --git a/packages/goal/tool-goal/src/authority.ts b/packages/goal/tool-goal/src/authority.ts index 41fe713dc6..f48c9cd098 100644 --- a/packages/goal/tool-goal/src/authority.ts +++ b/packages/goal/tool-goal/src/authority.ts @@ -64,7 +64,7 @@ export function goalToolExecution(ctx: Context, exec: ToolRunContext): GoalToolE /** * Whether host-attested human input appears in the current root-agent turn. - * An omitted `Agent.send()` / `steer()` source resolves to `user`, so non-human + * An omitted `Agent.followup()` / `steer()` source resolves to `user`, so non-human * producers must supply their own source rather than inheriting this authority. */ function hasDirectHumanInput(ctx: Context, execution: GoalToolExecution): boolean { diff --git a/packages/goal/tool-goal/src/index.ts b/packages/goal/tool-goal/src/index.ts index 009a00376f..09953041fa 100644 --- a/packages/goal/tool-goal/src/index.ts +++ b/packages/goal/tool-goal/src/index.ts @@ -132,6 +132,16 @@ function resolveConfig(config: Config): ResolvedConfig { return { blockedAfterConsecutiveRounds: blockedAfter } } +/** Whether optional text is meaningful rather than a strict-schema empty filler. */ +function hasText(value: string | undefined): value is string { + return value !== undefined && value !== '' +} + +/** Whether an optional round cap is meaningful rather than a strict-schema zero filler. */ +function hasRoundCap(value: number | undefined): value is number { + return value !== undefined && value !== 0 +} + /** Build the exact compare-and-set ref from model arguments. */ function goalRef(goalId: string, revision: number): GoalRef { if (goalId.length === 0 || goalId !== goalId.trim() @@ -271,12 +281,12 @@ export function apply(ctx: Context, config: Config): void { const execution = goalToolExecution(ctx, exec) const ref = goalRef(args.goal_id, args.revision) const replacements = { - ...args.objective === undefined ? {} : { objective: args.objective }, - ...args.max_goal_rounds === undefined ? {} : { maxGoalRounds: args.max_goal_rounds }, + ...hasText(args.objective) ? { objective: args.objective } : {}, + ...hasRoundCap(args.max_goal_rounds) ? { maxGoalRounds: args.max_goal_rounds } : {}, } if (args.action === 'edit') { requireDirectHuman(ctx, execution) - if (args.blocked_reason !== undefined) { + if (hasText(args.blocked_reason)) { throw new HarnessError('blocked_reason is valid only with action blocked', 'GOAL_TOOL_INVALID_UPDATE') } const goal = ctx.goals.edit(execution.agent, ref, replacements) @@ -285,7 +295,7 @@ export function apply(ctx: Context, config: Config): void { } if (args.action === 'pause' || args.action === 'resume') { requireDirectHuman(ctx, execution) - if (args.objective !== undefined || args.max_goal_rounds !== undefined || args.blocked_reason !== undefined) { + if (hasText(args.objective) || hasRoundCap(args.max_goal_rounds) || hasText(args.blocked_reason)) { throw new HarnessError( 'objective and max_goal_rounds are valid only with action edit; blocked_reason is valid only with action blocked', 'GOAL_TOOL_INVALID_UPDATE', @@ -298,13 +308,13 @@ export function apply(ctx: Context, config: Config): void { return Promise.resolve(goalValue(goal)) } const authority = completionAuthority(ctx, execution) - if (args.objective !== undefined || args.max_goal_rounds !== undefined) { + if (hasText(args.objective) || hasRoundCap(args.max_goal_rounds)) { throw new HarnessError( 'objective and max_goal_rounds are valid only with action edit', 'GOAL_TOOL_INVALID_UPDATE', ) } - if (args.action === 'complete' && args.blocked_reason !== undefined) { + if (args.action === 'complete' && hasText(args.blocked_reason)) { throw new HarnessError('blocked_reason is valid only with action blocked', 'GOAL_TOOL_INVALID_UPDATE') } if (args.action === 'blocked' @@ -331,7 +341,11 @@ export function apply(ctx: Context, config: Config): void { presentCall: args => present( `${args.action === 'blocked' ? 'Mark' : args.action.charAt(0).toUpperCase() + args.action.slice(1)} goal`, 'other', - args.blocked_reason ?? args.objective ?? args.goal_id, + hasText(args.blocked_reason) + ? args.blocked_reason + : hasText(args.objective) + ? args.objective + : hasRoundCap(args.max_goal_rounds) ? args.max_goal_rounds : args.goal_id, ), })) } diff --git a/packages/goal/tool-goal/tests/tool-goal.spec.ts b/packages/goal/tool-goal/tests/tool-goal.spec.ts index 7b2ccdc347..eaab21e202 100644 --- a/packages/goal/tool-goal/tests/tool-goal.spec.ts +++ b/packages/goal/tool-goal/tests/tool-goal.spec.ts @@ -1,7 +1,7 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' import Loader from '@cordisjs/plugin-loader' -import AgentRegistry, { agentEvents } from '@deepseek-ai/dsh-agent' +import AgentRegistry, { agentEvents, AgentMessageId } from '@deepseek-ai/dsh-agent' import type { Agent, AgentStatus, InjectOptions } from '@deepseek-ai/dsh-agent' import GoalService, { GoalId } from '@deepseek-ai/dsh-goal' import type { GoalRef } from '@deepseek-ai/dsh-goal' @@ -31,16 +31,19 @@ function stubAgent(rawId: string, supplied?: Session): StubAgent { session, get status() { return status }, ctx: new Context(), - send() {}, - steer() {}, + followup: () => AgentMessageId('stub'), + queue: () => AgentMessageId('stub'), + steer: () => AgentMessageId('stub'), inject(content: ContentBlock[], options?: InjectOptions) { - const source = options?.source ?? { kind: 'user' } - session.append('context/message', { + const source = options?.source ?? { kind: 'plugin', plugin: '' } + session.append('user/message', { content, source, ...options?.meta === undefined ? {} : { meta: options.meta }, }, { surfaceOp: 'append' }) + return AgentMessageId('stub') }, + send: () => AgentMessageId('stub'), cancel() {}, whenIdle() { return Promise.resolve() }, } @@ -142,8 +145,17 @@ describe('goal tool registration and presentation', () => { expect(ctx.tools.get('update_goal')?.presentCall?.({ goal_id: 'goal-1', revision: 2, action: 'blocked', blocked_reason: 'Waiting for a human choice.', })).toEqual({ card: 'generic', title: 'Mark goal', kind: 'other', rawInput: 'Waiting for a human choice.' }) + expect(ctx.tools.get('update_goal')?.presentCall?.({ + goal_id: 'goal-1', revision: 2, action: 'edit', + objective: 'ship', max_goal_rounds: 0, blocked_reason: '', + })).toEqual({ card: 'generic', title: 'Edit goal', kind: 'other', rawInput: 'ship' }) + expect(ctx.tools.get('update_goal')?.presentCall?.({ + goal_id: 'goal-1', revision: 2, action: 'edit', + objective: '', max_goal_rounds: 8, blocked_reason: '', + })).toEqual({ card: 'generic', title: 'Edit goal', kind: 'other', rawInput: 8 }) expect(ctx.tools.get('update_goal')?.presentCall?.({ goal_id: 'goal-1', revision: 2, action: 'resume', + objective: '', max_goal_rounds: 0, blocked_reason: '', })).toEqual({ card: 'generic', title: 'Resume goal', kind: 'other', rawInput: 'goal-1' }) expect(ctx.tools.get('update_goal')?.presentCall?.({ wrong: true })).toBeUndefined() }) @@ -228,7 +240,9 @@ describe('goal tool execution authority', () => { it('rejects stale agent objects and agents outside running status through the executor', async () => { const { ctx, root } = await harness() openTurn(root, { kind: 'user' }) - const stale = { ...root.agent } + // A distinct agent object over root's exact session: same id, not the live + // registered instance, so the executor must reject it. + const stale = stubAgent('goal-tool-stale', root.agent.session).agent const staleResult = await execute(ctx, 'get_goal', {}, stale, stale) expect(staleResult.error?.info?.code).toBe('GOAL_TOOL_DRIVER_REQUIRED') @@ -423,6 +437,77 @@ describe('goal tool state transitions', () => { expect(malformedRef.error?.info?.code).toBe('GOAL_TOOL_INVALID_UPDATE') }) + it('accepts only empty fillers in fields unused by the selected action', async () => { + const { ctx, root } = await harness() + openTurn(root, { kind: 'user' }) + let goal = ctx.goals.create(root.agent, { objective: 'valid' }) + + const edited = await execute(ctx, 'update_goal', { + goal_id: goal.id, + revision: goal.revision, + action: 'edit', + objective: 'edited', + max_goal_rounds: 0, + blocked_reason: '', + }, root.agent) + expect(resultGoal(edited)).toMatchObject({ objective: 'edited' }) + goal = ctx.goals.get(root.agent)! + + const capped = await execute(ctx, 'update_goal', { + goal_id: goal.id, + revision: goal.revision, + action: 'edit', + objective: '', + max_goal_rounds: 8, + blocked_reason: '', + }, root.agent) + expect(resultGoal(capped)).toMatchObject({ objective: 'edited', maxGoalRounds: 8 }) + goal = ctx.goals.get(root.agent)! + + const paused = await execute(ctx, 'update_goal', { + goal_id: goal.id, + revision: goal.revision, + action: 'pause', + objective: '', + max_goal_rounds: 0, + blocked_reason: '', + }, root.agent) + expect(resultGoal(paused)).toMatchObject({ phase: 'paused', objective: 'edited' }) + goal = ctx.goals.get(root.agent)! + + const resumed = await execute(ctx, 'update_goal', { + goal_id: goal.id, + revision: goal.revision, + action: 'resume', + objective: '', + max_goal_rounds: 0, + blocked_reason: '', + }, root.agent) + expect(resultGoal(resumed)).toMatchObject({ phase: 'active', objective: 'edited' }) + goal = ctx.goals.get(root.agent)! + + const blocked = await execute(ctx, 'update_goal', { + goal_id: goal.id, + revision: goal.revision, + action: 'blocked', + objective: '', + max_goal_rounds: 0, + blocked_reason: 'actual blocker', + }, root.agent) + expect(resultGoal(blocked)).toMatchObject({ phase: 'blocked' }) + goal = ctx.goals.resume(root.agent, { id: goal.id, revision: goal.revision + 1 }) + + const complete = await execute(ctx, 'update_goal', { + goal_id: goal.id, + revision: goal.revision, + action: 'complete', + objective: '', + max_goal_rounds: 0, + blocked_reason: '', + }, root.agent) + expect(resultGoal(complete)).toMatchObject({ phase: 'complete', objective: 'edited' }) + }) + it('allows exact goal rounds to complete but not edit or pause', async () => { const { ctx, root } = await harness() const humanTurn = openTurn(root, { kind: 'user' }) diff --git a/packages/guard/README.md b/packages/guard/README.md index 05c9625cb0..e7066ba434 100644 --- a/packages/guard/README.md +++ b/packages/guard/README.md @@ -6,4 +6,4 @@ Behavioral guard plugins that watch the agent loop for unproductive patterns and |---|---|---| | `repeat-tool-guard/` | Advisory reminders when an agent loops on identical tool calls | (listens on `ctx.tools`' waterfalls) | -Reminders travel as `additionalContexts` on the `tools/post-execute` decision; the agent loop appends them as logged `context/message` events after the step's tool results (see [the tools package](../core/tools)), so everything a guard says to the model is reconstructable from the session log. +Reminders travel as `additionalContexts` on the `tools/post-execute` decision; the agent loop appends them as logged plugin-sourced `user/message` events after the step's tool results (see [the tools package](../core/tools)), so everything a guard says to the model is reconstructable from the session log. diff --git a/packages/guard/repeat-tool-guard/README.md b/packages/guard/repeat-tool-guard/README.md index ef5e4e5846..e7bd79732e 100644 --- a/packages/guard/repeat-tool-guard/README.md +++ b/packages/guard/repeat-tool-guard/README.md @@ -30,11 +30,11 @@ The chain key is `(tool name, canonical arguments)` — canonicalization is a de ## Reminder delivery -Reminders ride the post-execute decision's `additionalContexts` (source `{kind: 'plugin', plugin: 'repeat-tool-guard'}`), never a `content` replacement: the `tool/result` event stays the tool's own output for audit. The loop buffers the context and appends it as a `context/message` after the step's tool results, which the session renders as a plain synthetic user message — so the reminder is model-visible, source-attributed, and reconstructable from the session log with no new session event. The guard always delegates via `next()` and prepends its reminder to the downstream decision's context array (both variants — a blocked call still gets the nudge); every entry retains its own source and metadata. +Reminders ride the post-execute decision's `additionalContexts` (source `{kind: 'plugin', plugin: 'repeat-tool-guard'}`), never a `content` replacement: the `tool/result` event stays the tool's own output for audit. The loop buffers the context and appends it as an injected `user/message` after the step's tool results, which the session renders as a plain synthetic user message — so the reminder is model-visible, source-attributed, and reconstructable from the session log with no new session event. The guard always delegates via `next()` and prepends its reminder to the downstream decision's context array (both variants — a blocked call still gets the nudge); every entry retains its own source and metadata. ## Testing -Unit suites drive a real agent loop against a mock adapter (no network) and cover the chain semantics above to per-file 100%. The snapshot tier owns the transcript surface: a scripted-replay scenario repeats a call five times and pins both reminder tiers (gentle at 3, detailed at 5) as `context/message`s in the ACP transcript. +Unit suites drive a real agent loop against a mock adapter (no network) and cover the chain semantics above to per-file 100%. The snapshot tier owns the transcript surface: a scripted-replay scenario repeats a call five times and pins both reminder tiers (gentle at 3, detailed at 5) as injected `user/message`s in the ACP transcript. ## Model Experience diff --git a/packages/guard/repeat-tool-guard/tests/repeat-tool-guard.spec.ts b/packages/guard/repeat-tool-guard/tests/repeat-tool-guard.spec.ts index 2049d416fb..d0a3214518 100644 --- a/packages/guard/repeat-tool-guard/tests/repeat-tool-guard.spec.ts +++ b/packages/guard/repeat-tool-guard/tests/repeat-tool-guard.spec.ts @@ -35,10 +35,10 @@ function waitForIdle(ctx: Context, agent: Agent): Promise<void> { return new Promise((resolve) => { const d = ctx.on('agent/status', (s, st) => { if (s === agent && st === 'idle') { d(); resolve() } }) }) } -/** Every `context/message` in the agent's log, flattened to joined text + source for terse assertions. */ +/** Every injected-context user message in the agent's log, flattened to joined text + source for terse assertions. */ function reminders(agent: Agent): { text: string; source: unknown }[] { return [...agent.session.events] - .filter((e): e is SessionEvent<'context/message'> => e.type === 'context/message') + .filter((e): e is SessionEvent<'user/message'> => e.type === 'user/message' && e.data.source.kind !== 'user') .map(e => ({ text: e.data.content.map(block => block.type === 'text' ? block.text : '').join('|'), source: e.data.source, @@ -56,7 +56,7 @@ describe('threshold escalation', () => { ]) ctx.llm.registerAdapter(['mock'], adapter) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const found = reminders(agent) @@ -77,7 +77,7 @@ describe('threshold escalation', () => { ]) ctx.llm.registerAdapter(['mock'], adapter) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const found = reminders(agent) @@ -99,7 +99,7 @@ describe('chain semantics', () => { ]) ctx.llm.registerAdapter(['mock'], adapter) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const found = reminders(agent) @@ -123,7 +123,7 @@ describe('chain semantics', () => { ]) ctx.llm.registerAdapter(['mock'], adapter) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(reminders(agent)).toHaveLength(1) @@ -141,7 +141,7 @@ describe('chain semantics', () => { ]) ctx.llm.registerAdapter(['mock'], adapter) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const found = reminders(agent) @@ -162,7 +162,7 @@ describe('chain semantics', () => { ]) ctx.llm.registerAdapter(['mock'], adapter) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const found = reminders(agent) @@ -178,7 +178,7 @@ describe('chain semantics', () => { ]) ctx.llm.registerAdapter(['mock'], adapter) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(reminders(agent)).toHaveLength(1) // probe was NOT excluded @@ -194,7 +194,7 @@ describe('chain semantics', () => { ]) ctx.llm.registerAdapter(['mock'], adapter) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(reminders(agent)).toHaveLength(1) // all three canonicalize identically @@ -215,8 +215,8 @@ describe('chain semantics', () => { ])) const agentA = ctx.agentLoop.create(SessionId('a'), { provider: 'mock-a', model: 'model-a' }) const agentB = ctx.agentLoop.create(SessionId('b'), { provider: 'mock-b', model: 'model-b' }) - agentA.send([{ type: 'text', text: 'go' }]) - agentB.send([{ type: 'text', text: 'go' }]) + agentA.followup([{ type: 'text', text: 'go' }]) + agentB.followup([{ type: 'text', text: 'go' }]) await Promise.all([waitForIdle(ctx, agentA), waitForIdle(ctx, agentB)]) expect(reminders(agentA)).toHaveLength(0) // 2 repeats < 3, despite B's 3 in the same registry @@ -234,9 +234,9 @@ describe('chain semantics', () => { ]) ctx.llm.registerAdapter(['mock'], adapter) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) - agent.send([{ type: 'text', text: 'again' }]) + agent.followup([{ type: 'text', text: 'again' }]) await waitForIdle(ctx, agent) expect(reminders(agent)).toHaveLength(0) @@ -256,13 +256,13 @@ describe('chain semantics', () => { const fiber = await ctx.plugin(Object.assign((inner: Context) => { first = inner.agentLoop.create(SessionId('reused'), { provider: 'mock', model: 'mock' }) }, { inject: ['agentLoop'] })) - first.send([{ type: 'text', text: 'go' }]) + first.followup([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, first) await fiber.dispose() await first.whenIdle() const second = ctx.agentLoop.create(SessionId('reused'), { provider: 'mock', model: 'mock' }) - second.send([{ type: 'text', text: 'go' }]) + second.followup([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, second) expect(reminders(second)).toHaveLength(0) @@ -278,7 +278,7 @@ describe('chain semantics', () => { ]) ctx.llm.registerAdapter(['mock'], adapter) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(reminders(agent)).toHaveLength(1) @@ -294,7 +294,7 @@ describe('chain semantics', () => { textResponse('done'), ])) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(reminders(agent)).toHaveLength(0) @@ -316,7 +316,7 @@ describe('fold onto the downstream decision', () => { ]) ctx.llm.registerAdapter(['mock'], adapter) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const found = reminders(agent) @@ -347,7 +347,7 @@ describe('fold onto the downstream decision', () => { ]) ctx.llm.registerAdapter(['mock'], adapter) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const found = reminders(agent) diff --git a/packages/hooks/hook-protocol/README.md b/packages/hooks/hook-protocol/README.md index 42a642caf0..3a84807285 100644 --- a/packages/hooks/hook-protocol/README.md +++ b/packages/hooks/hook-protocol/README.md @@ -27,7 +27,7 @@ Why a shared lib at all: Codex deliberately reimplements a *subset* of the Claud Declaration-merged into `SessionEventMap` (log-only, like `compact/*` — NOT a `SurfaceEventType`, no `surfaceOp`): `hook/invoked` (a hook command ran) and `hook/result` (its outcome, paired by `handlerId`, with `appendHookResult` owning the decision rule). Payloads and per-event JSDoc are in the generated [persistence log event catalog](../../../docs/persistence-catalog.md); `stderrSummary` is truncated to the record's `stderrSummaryMaxChars` (the bridge's config, reference default `DEFAULT_STDERR_SUMMARY_MAX_CHARS` = 500; omitted when empty). -Like every event they must sit inside an open turn. The mid-turn points (`PreToolUse`/`PostToolUse`/`UserPromptSubmit`/`Stop`) fire inside the loop's open turn by construction; `SessionStart` gets no `hook/*` record (its injected `context/message` is the durable evidence) — see the hooks Agent Note. +Like every event they must sit inside an open turn. The mid-turn points (`PreToolUse`/`PostToolUse`/`UserPromptSubmit`/`Stop`) fire inside the loop's open turn by construction; `SessionStart` gets no `hook/*` record (its injected `user/message` is the durable evidence) — see the hooks Agent Note. ## Model Experience diff --git a/packages/hooks/hooks-claude/tests/bridge.spec.ts b/packages/hooks/hooks-claude/tests/bridge.spec.ts index e59ae24e31..f5fd5702d5 100644 --- a/packages/hooks/hooks-claude/tests/bridge.spec.ts +++ b/packages/hooks/hooks-claude/tests/bridge.spec.ts @@ -97,7 +97,7 @@ describe('hooks-claude bridge — UserPromptSubmit', () => { const adapter = new MockAdapter([textResponse('should not run')]) const ctx = await harness(dir, adapter) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'do something' }]) + agent.followup([{ type: 'text', text: 'do something' }]) await waitForIdle(ctx, agent) // The prompt was blocked: model never called, turn ended rejected. @@ -120,13 +120,13 @@ describe('hooks-claude bridge — UserPromptSubmit', () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(dir, adapter) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) // The injected context reached the model and is recorded with the plugin source. expect(JSON.stringify(adapter.requests[0]!.messages)).toContain('remember: be brief') - const ctxMsg = events(agent).find(e => e.type === 'context/message') - expect(ctxMsg?.type === 'context/message' && ctxMsg.data.source).toEqual({ kind: 'plugin', plugin: 'hooks-claude' }) + const ctxMsg = events(agent).find(e => e.type === 'user/message' && e.data.source.kind !== 'user') + expect(ctxMsg?.type === 'user/message' && ctxMsg.data.source).toEqual({ kind: 'plugin', plugin: 'hooks-claude' }) }) }) @@ -145,7 +145,7 @@ describe('hooks-claude bridge — PreToolUse', () => { let ran = false ctx.tools.register(defineContentToolFixture({ name: 'danger', description: 'd', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'should not run' }] } })) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'use danger' }]) + agent.followup([{ type: 'text', text: 'use danger' }]) await waitForIdle(ctx, agent) expect(ran).toBe(false) @@ -168,7 +168,7 @@ describe('hooks-claude bridge — PreToolUse', () => { let ran = false ctx.tools.register(defineContentToolFixture({ name: 'safe', description: 's', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'ran ok' }] } })) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'use safe' }]) + agent.followup([{ type: 'text', text: 'use safe' }]) await waitForIdle(ctx, agent) expect(ran).toBe(true) @@ -190,7 +190,7 @@ describe('hooks-claude bridge — PostToolUse', () => { const ctx = await harness(dir, adapter) ctx.tools.register(defineContentToolFixture({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'raw output' }] } })) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const result = events(agent).find(e => e.type === 'tool/result') @@ -211,15 +211,15 @@ describe('hooks-claude bridge — PostToolUse', () => { const ctx = await harness(dir, adapter) ctx.tools.register(defineContentToolFixture({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const log = events(agent) const resultIdx = log.findIndex(e => e.type === 'tool/result') - const ctxIdx = log.findIndex(e => e.type === 'context/message') + const ctxIdx = log.findIndex(e => e.type === 'user/message' && e.data.source.kind !== 'user') expect(ctxIdx).toBeGreaterThan(resultIdx) // context appended AFTER the tool result const ctxMsg = log[ctxIdx] - expect(ctxMsg?.type === 'context/message' && ctxMsg.data.content.some(b => b.type === 'text' && b.text.includes('tool was slow'))).toBe(true) + expect(ctxMsg?.type === 'user/message' && ctxMsg.data.content.some(b => b.type === 'text' && b.text.includes('tool was slow'))).toBe(true) }) it('a PreToolUse permissionDecision:ask degrades to ask (the tool is gated, not run)', async () => { @@ -235,7 +235,7 @@ describe('hooks-claude bridge — PostToolUse', () => { let ran = false ctx.tools.register(defineContentToolFixture({ name: 'echo', description: 'e', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'x' }] } })) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) // `ask` degrades to deny today (FIXME permissions): the tool does not run and the result is isError. @@ -262,9 +262,9 @@ describe('hooks-claude bridge — SessionStart', () => { // session-start fires async (detached .then → agent.inject); wait for the // injected context/message to actually land before sending, rather than a // fixed sleep that flakes under load. - await waitFor(() => events(agent).some(e => e.type === 'context/message' + await waitFor(() => events(agent).some(e => e.type === 'user/message' && e.data.content.some(b => b.type === 'text' && b.text.includes('project uses tabs')))) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(JSON.stringify(adapter.requests[0]!.messages)).toContain('project uses tabs') @@ -357,7 +357,7 @@ describe('hooks-claude bridge — load resilience', () => { await ctx.plugin(HooksClaude, { configPath: '/nonexistent/hooks.json' }) ctx.llm.registerAdapter(['mock'], adapter) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) // The turn ran normally — no hooks, no crash. expect(adapter.requests).toHaveLength(1) @@ -379,7 +379,7 @@ describe('hooks-claude bridge — load resilience', () => { await fiber.dispose() ctx.llm.registerAdapter(['mock'], adapter) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(adapter.requests).toHaveLength(1) // not blocked → the listener is gone expect(events(agent).some(e => e.type === 'hook/invoked')).toBe(false) // no hook ran diff --git a/packages/hooks/hooks-claude/tests/coverage-cases.ts b/packages/hooks/hooks-claude/tests/coverage-cases.ts index 4a894e6c2f..ab770479ed 100644 --- a/packages/hooks/hooks-claude/tests/coverage-cases.ts +++ b/packages/hooks/hooks-claude/tests/coverage-cases.ts @@ -74,7 +74,7 @@ export function defineCoverageCases(group: CoverageGroup): void { const ctx = await harness(path, adapter, { ...sessionRoot !== undefined ? { sessionRoot } : {} }) ctx.tools.register(defineContentToolFixture({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) const agent = ctx.agentLoop.create(SessionId('transcript'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) return { payload: JSON.parse(readFileSync(cap, 'utf8')) as { transcript_path: string }, @@ -104,7 +104,7 @@ export function defineCoverageCases(group: CoverageGroup): void { ctx.logger.warn = warn as never ctx.tools.register(defineContentToolFixture({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(existsSync(marker)).toBe(true) // substituted command ran }) @@ -120,7 +120,7 @@ export function defineCoverageCases(group: CoverageGroup): void { let sawArgs: unknown ctx.tools.register(defineContentToolFixture({ name: 'echo', description: 'e', parameters: { command: { type: 'string' } }, async execute(args) { sawArgs = args; return [{ type: 'text', text: 'ok' }] } })) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) // updatedInput is NOT honored — the tool ran with the ORIGINAL args. expect((sawArgs as { command?: string }).command).toBe('original') @@ -136,11 +136,11 @@ export function defineCoverageCases(group: CoverageGroup): void { const adapter = new MockAdapter([textResponse('ran')]) const ctx = await harness(path, adapter) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) - // The prompt proceeded unchanged; no context/message injected. + // The prompt proceeded unchanged; no injected context. expect(adapter.requests).toHaveLength(1) - expect(events(agent).some(e => e.type === 'context/message')).toBe(false) + expect(events(agent).some(e => e.type === 'user/message' && e.data.source.kind !== 'user')).toBe(false) }) it('a PreToolUse hook fires for a no-agent direct tool call (no session/turn to record into)', async () => { @@ -166,7 +166,7 @@ export function defineCoverageCases(group: CoverageGroup): void { const ctx = await harness(path, adapter) ctx.tools.register(defineContentToolFixture({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const res = events(agent).find(e => e.type === 'hook/result') expect(res?.type === 'hook/result' && res.data.stderrSummary?.endsWith('…')).toBe(true) @@ -191,7 +191,7 @@ export function defineCoverageCases(group: CoverageGroup): void { const ctx = await harness(path, adapter, { stderrSummaryMaxChars: 40 }) ctx.tools.register(defineContentToolFixture({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const res = events(agent).find(e => e.type === 'hook/result') expect(res?.type === 'hook/result' && res.data.stderrSummary).toBe('x'.repeat(40) + '…') @@ -207,7 +207,7 @@ export function defineCoverageCases(group: CoverageGroup): void { const adapter = new MockAdapter([textResponse('one'), textResponse('two')]) const ctx = await harness(path, adapter) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(adapter.requests).toHaveLength(2) expect(JSON.stringify(adapter.requests[1]!.messages)).toContain('continue please') @@ -223,7 +223,7 @@ export function defineCoverageCases(group: CoverageGroup): void { const adapter = new MockAdapter([textResponse('one'), textResponse('two')]) const ctx = await harness(path, adapter) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) // A second model request ran → the empty-reason block forced continuation. expect(adapter.requests).toHaveLength(2) @@ -271,7 +271,7 @@ export function defineCoverageCases(group: CoverageGroup): void { const ctx = await harness(path, adapter) ctx.tools.register(defineContentToolFixture({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'x' }] } })) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const result = events(agent).find(e => e.type === 'tool/result') expect(result?.type === 'tool/result' && result.data.content.some(b => b.type === 'text' && b.text.includes('blocked by PreToolUse hook'))).toBe(true) @@ -285,7 +285,7 @@ export function defineCoverageCases(group: CoverageGroup): void { const ctx = await harness(path, adapter) ctx.tools.register(defineContentToolFixture({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const result = events(agent).find(e => e.type === 'tool/result') expect(result?.type === 'tool/result' && result.data.content.some(b => b.type === 'text' && b.text.includes('blocked by PostToolUse hook'))).toBe(true) @@ -314,7 +314,7 @@ export function defineCoverageCases(group: CoverageGroup): void { const adapter = new MockAdapter([textResponse('no')]) const ctx = await harness(path, adapter) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const turnEnd = events(agent).findLast(e => e.type === 'turn/end') expect(turnEnd?.type === 'turn/end' && turnEnd.data.reason.kind === 'rejected' && turnEnd.data.reason.reason).toContain('blocked by UserPromptSubmit hook') @@ -329,7 +329,7 @@ export function defineCoverageCases(group: CoverageGroup): void { let ran = false ctx.tools.register(defineContentToolFixture({ name: 'echo', description: 'e', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'x' }] } })) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) // ask (no reason) → degrades to deny with the registry's generic message. expect(ran).toBe(false) @@ -344,7 +344,7 @@ export function defineCoverageCases(group: CoverageGroup): void { const ctx = await harness(path, adapter) ctx.tools.register(defineContentToolFixture({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const res = events(agent).find(e => e.type === 'hook/result') expect(res?.type === 'hook/result' && res.data.exitCode).toBe(0) @@ -369,7 +369,7 @@ export function defineCoverageCases(group: CoverageGroup): void { HooksClaude.apply(ctx, { configPath: join(d, 'hooks.json') }) ctx.llm.registerAdapter(['mock'], adapter) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(existsSync(marker)).toBe(true) }) @@ -384,7 +384,7 @@ export function defineCoverageCases(group: CoverageGroup): void { let ran = false ctx.tools.register(defineContentToolFixture({ name: 'echo', description: 'e', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(ran).toBe(true) const res = events(agent).find(e => e.type === 'hook/result') @@ -399,7 +399,7 @@ export function defineCoverageCases(group: CoverageGroup): void { const ctx = await harness(path, adapter) ctx.tools.register(defineContentToolFixture({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const result = events(agent).find(e => e.type === 'tool/result') expect(result?.type === 'tool/result' && result.data.isError).toBe(true) @@ -418,7 +418,7 @@ export function defineCoverageCases(group: CoverageGroup): void { let ran = false ctx.tools.register(defineContentToolFixture({ name: 'echo', description: 'e', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const res = events(agent).find(e => e.type === 'hook/result') expect(res?.type === 'hook/result' && res.data.decision).toBe('stop') // recorded @@ -435,13 +435,13 @@ export function defineCoverageCases(group: CoverageGroup): void { const ctx = await harness(path, adapter) ctx.tools.register(defineContentToolFixture({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const result = events(agent).find(e => e.type === 'tool/result') expect(result?.type === 'tool/result' && result.data.isError).toBe(true) expect(result?.type === 'tool/result' && result.data.content.some(b => b.type === 'text' && b.text.includes('bad'))).toBe(true) // additionalContext also injected (the block + context arm). - expect(events(agent).some(e => e.type === 'context/message' && e.data.content.some(b => b.type === 'text' && b.text.includes('context too')))).toBe(true) + expect(events(agent).some(e => e.type === 'user/message' && e.data.source.kind !== 'user' && e.data.content.some(b => b.type === 'text' && b.text.includes('context too')))).toBe(true) }) it('a PreToolUse hook whose hookSpecificOutput names a DIFFERENT event does NOT deny the tool', async () => { @@ -455,7 +455,7 @@ export function defineCoverageCases(group: CoverageGroup): void { let ran = false ctx.tools.register(defineContentToolFixture({ name: 'echo', description: 'e', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(ran).toBe(true) // the mismatched deny was discarded → the tool ran }) @@ -473,9 +473,9 @@ export function defineCoverageCases(group: CoverageGroup): void { // The factory create() path honors meta.cwd (the plain agentLoop.create() does not). const { SessionId } = await import('@deepseek-ai/dsh-session') const handle = await ctx.agents.create({ sessionId: SessionId('s1'), meta: { cwd: workspace }, agentOptions: { provider: 'mock', model: 'mock' } }) - handle.agent.send([{ type: 'text', text: 'go' }]) + handle.agent.followup([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, handle.agent) - expect(events(handle.agent).some(e => e.type === 'context/message' + expect(events(handle.agent).some(e => e.type === 'user/message' && e.data.content.some(b => b.type === 'text' && b.text.includes(`dir=${workspace}`)))).toBe(true) await handle.dispose() }) @@ -491,12 +491,12 @@ export function defineCoverageCases(group: CoverageGroup): void { // A later listener that blocks every prompt (registered AFTER the bridge). ctx.on('agent/prompt-submit', async () => ({ kind: 'block' as const, reason: 'policy veto' })) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) // the downstream block won: the model was never called, no user/message was // recorded, and the (sole, fully-blocked) prompt closed the turn `rejected` expect(adapter.requests).toHaveLength(0) - expect(events(agent).some(e => e.type === 'user/message')).toBe(false) + expect(events(agent).some(e => e.type === 'user/message' && e.data.source.kind !== 'user')).toBe(false) const turnEnd = events(agent).findLast(e => e.type === 'turn/end') expect(turnEnd?.type === 'turn/end' && turnEnd.data.reason).toMatchObject({ kind: 'rejected', reason: 'policy veto' }) }) @@ -519,7 +519,7 @@ export function defineCoverageCases(group: CoverageGroup): void { }], })) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const req = JSON.stringify(adapter.requests[0]!.messages) expect(req).toContain('from-bridge') @@ -528,12 +528,12 @@ export function defineCoverageCases(group: CoverageGroup): void { // the original prompt was replaced by the downstream rewrite const userMsg = events(agent).find(e => e.type === 'user/message') expect(userMsg?.type === 'user/message' && userMsg.data.content.some(b => b.type === 'text' && b.text === 'rewritten-prompt')).toBe(true) - const contexts = events(agent).filter(event => event.type === 'context/message') - expect(contexts.map(event => event.type === 'context/message' && event.data.source)).toEqual([ + const contexts = events(agent).filter(event => event.type === 'user/message' && event.data.source.kind !== 'user') + expect(contexts.map(event => event.type === 'user/message' && event.data.source)).toEqual([ { kind: 'plugin', plugin: 'hooks-claude' }, { kind: 'plugin', plugin: 'policy' }, ]) - expect(contexts[1]?.type === 'context/message' && contexts[1].data.meta).toEqual({ owner: 'policy' }) + expect(contexts[1]?.type === 'user/message' && contexts[1].data.meta).toEqual({ owner: 'policy' }) }) it('folds the bridge PostToolUse context onto a downstream canonical value replacement', async () => { @@ -547,11 +547,11 @@ export function defineCoverageCases(group: CoverageGroup): void { ctx.tools.register(defineContentToolFixture({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) ctx.on('tools/post-execute', async () => ({ kind: 'accept' as const, value: [{ type: 'text' as const, text: 'rewritten-result' }] })) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const result = events(agent).find(e => e.type === 'tool/result') expect(result?.type === 'tool/result' && result.data.content.some(b => b.type === 'text' && b.text === 'rewritten-result')).toBe(true) - expect(events(agent).some(e => e.type === 'context/message' && e.data.content.some(b => b.type === 'text' && b.text.includes('bridge-note')))).toBe(true) + expect(events(agent).some(e => e.type === 'user/message' && e.data.source.kind !== 'user' && e.data.content.some(b => b.type === 'text' && b.text.includes('bridge-note')))).toBe(true) }) it('keeps bridge and downstream PostToolUse contexts as separate sourced events', async () => { @@ -570,15 +570,15 @@ export function defineCoverageCases(group: CoverageGroup): void { }], })) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) - const contexts = events(agent).filter(event => event.type === 'context/message') - expect(contexts.map(event => event.type === 'context/message' && event.data.source)).toEqual([ + const contexts = events(agent).filter(event => event.type === 'user/message' && event.data.source.kind !== 'user') + expect(contexts.map(event => event.type === 'user/message' && event.data.source)).toEqual([ { kind: 'plugin', plugin: 'hooks-claude' }, { kind: 'plugin', plugin: 'policy' }, ]) - expect(contexts[1]?.type === 'context/message' && contexts[1].data.meta).toEqual({ owner: 'policy' }) + expect(contexts[1]?.type === 'user/message' && contexts[1].data.meta).toEqual({ owner: 'policy' }) }) it('folds the bridge PostToolUse context onto a downstream listener BLOCK', async () => { @@ -593,13 +593,13 @@ export function defineCoverageCases(group: CoverageGroup): void { ctx.tools.register(defineContentToolFixture({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) ctx.on('tools/post-execute', async () => ({ kind: 'block' as const, feedback: [{ type: 'text' as const, text: 'downstream-block' }] })) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const result = events(agent).find(e => e.type === 'tool/result') expect(result?.type === 'tool/result' && result.data.isError).toBe(true) expect(result?.type === 'tool/result' && result.data.content.some(b => b.type === 'text' && b.text.includes('downstream-block'))).toBe(true) // the bridge's context still landed (folded onto the block) - expect(events(agent).some(e => e.type === 'context/message' && e.data.content.some(b => b.type === 'text' && b.text.includes('bridge-note')))).toBe(true) + expect(events(agent).some(e => e.type === 'user/message' && e.data.source.kind !== 'user' && e.data.content.some(b => b.type === 'text' && b.text.includes('bridge-note')))).toBe(true) }) }) @@ -617,7 +617,7 @@ export function defineCoverageCases(group: CoverageGroup): void { bash.run = (() => Promise.reject(new Error('executor down'))) ctx.tools.register(defineContentToolFixture({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const res = events(agent).find(e => e.type === 'hook/result') expect(res?.type === 'hook/result' && 'exitCode' in res.data).toBe(false) @@ -640,7 +640,7 @@ export function defineCoverageCases(group: CoverageGroup): void { await waitFor(() => threw) expect(threw).toBe(true) agent.inject = original - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(adapter.requests).toHaveLength(1) // loop survived the thrown inject }) @@ -667,7 +667,7 @@ export function defineCoverageCases(group: CoverageGroup): void { const { SessionId } = await import('@deepseek-ai/dsh-session') const handle = await ctx.agents.create({ sessionId: SessionId('s1'), meta: { cwd: sessionDir }, agentOptions: { provider: 'mock', model: 'mock' } }) - handle.agent.send([{ type: 'text', text: 'go' }]) + handle.agent.followup([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, handle.agent) expect(existsSync(marker)).toBe(true) // the marker landed in the SESSION dir @@ -717,7 +717,7 @@ export function defineCoverageCases(group: CoverageGroup): void { const ctx = await harness(path, adapter) const warn = vi.fn(); ctx.logger.warn = warn as never const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(warn).toHaveBeenCalledWith(expect.stringContaining('systemMessage')) // Not surfaced: the systemMessage text never reaches the model request. @@ -736,7 +736,7 @@ export function defineCoverageCases(group: CoverageGroup): void { const ctx = await harness(path, adapter) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) // Send immediately — do NOT wait for the session-start inject. - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(adapter.requests).toHaveLength(1) // the turn ran regardless of hook timing }) diff --git a/packages/hooks/hooks-codex/tests/bridge.spec.ts b/packages/hooks/hooks-codex/tests/bridge.spec.ts index 00c0e6c14d..923a4bf8b5 100644 --- a/packages/hooks/hooks-codex/tests/bridge.spec.ts +++ b/packages/hooks/hooks-codex/tests/bridge.spec.ts @@ -77,7 +77,7 @@ describe('hooks-codex bridge', () => { let ran = false ctx.tools.register(defineContentToolFixture({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { ran = true; return [{ type: 'text', text: 'no' }] } })) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'run ls' }]) + agent.followup([{ type: 'text', text: 'run ls' }]) await waitForIdle(ctx, agent) expect(ran).toBe(false) @@ -98,7 +98,7 @@ describe('hooks-codex bridge', () => { const adapter = new MockAdapter([textResponse('first answer'), textResponse('second answer after goal')]) const ctx = await harness(dir, adapter) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(adapter.requests).toHaveLength(2) @@ -115,7 +115,7 @@ describe('hooks-codex bridge', () => { const adapter = new MockAdapter([textResponse('must not run')]) const ctx = await harness(dir, adapter) const agent = ctx.agentLoop.create(SessionId('cancel-prompt-hook'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'cancel the hook' }]) + agent.followup([{ type: 'text', text: 'cancel the hook' }]) await waitFor(() => existsSync(marker)) const pid = Number(readFileSync(pidFile, 'utf8').trim()) @@ -139,7 +139,7 @@ describe('hooks-codex bridge', () => { const adapter = new MockAdapter([textResponse('fine')]) const ctx = await harness(dir, adapter) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(adapter.requests).toHaveLength(1) }) @@ -149,7 +149,7 @@ describe('hooks-codex bridge', () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(dir, adapter) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(adapter.requests).toHaveLength(1) }) @@ -169,7 +169,7 @@ describe('hooks-codex bridge', () => { await fiber.dispose() ctx.llm.registerAdapter(['mock'], adapter) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(adapter.requests).toHaveLength(1) // not blocked → the listener is gone expect(events(agent).some(e => e.type === 'hook/invoked')).toBe(false) // no hook ran diff --git a/packages/hooks/hooks-codex/tests/coverage-cases.ts b/packages/hooks/hooks-codex/tests/coverage-cases.ts index 0c46ddea7a..ebb2164902 100644 --- a/packages/hooks/hooks-codex/tests/coverage-cases.ts +++ b/packages/hooks/hooks-codex/tests/coverage-cases.ts @@ -65,7 +65,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro const ctx = await harness(path, adapter, { ...sessionRoot !== undefined ? { sessionRoot } : {} }) ctx.tools.register(defineContentToolFixture({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) const agent = ctx.agentLoop.create(SessionId('transcript'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) return { payload: JSON.parse(readFileSync(cap, 'utf8')) as { transcript_path: string | null }, @@ -84,7 +84,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro const adapter = new MockAdapter([textResponse('no')]) const ctx = await harness(join(d, 'hooks.json'), adapter) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) + agent.followup([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(adapter.requests).toHaveLength(0) const te = events(agent).findLast(e => e.type === 'turn/end') expect(te?.type === 'turn/end' && te.data.reason.kind).toBe('rejected') @@ -96,7 +96,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(join(d, 'hooks.json'), adapter) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) + agent.followup([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(JSON.stringify(adapter.requests[0]!.messages)).toContain('ctx-x') }) @@ -109,7 +109,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.on('agent/prompt-submit', async () => ({ kind: 'block' as const, reason: 'policy veto' })) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) + agent.followup([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(adapter.requests).toHaveLength(0) expect(events(agent).some(e => e.type === 'user/message')).toBe(false) const te = events(agent).findLast(e => e.type === 'turn/end') @@ -131,17 +131,17 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro }], })) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) + agent.followup([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const req = JSON.stringify(adapter.requests[0]!.messages) expect(req).toContain('from-bridge') expect(req).toContain('from-downstream') expect(req).toContain('rewritten-prompt') - const contexts = events(agent).filter(event => event.type === 'context/message') - expect(contexts.map(event => event.type === 'context/message' && event.data.source)).toEqual([ + const contexts = events(agent).filter(event => event.type === 'user/message' && event.data.source.kind !== 'user') + expect(contexts.map(event => event.type === 'user/message' && event.data.source)).toEqual([ { kind: 'plugin', plugin: 'hooks-codex' }, { kind: 'plugin', plugin: 'policy' }, ]) - expect(contexts[1]?.type === 'context/message' && contexts[1].data.meta).toEqual({ owner: 'policy' }) + expect(contexts[1]?.type === 'user/message' && contexts[1].data.meta).toEqual({ owner: 'policy' }) }) }) @@ -154,10 +154,10 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro ctx.tools.register(defineContentToolFixture({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) ctx.on('tools/post-execute', async () => ({ kind: 'accept' as const, value: [{ type: 'text' as const, text: 'rewritten-result' }] })) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) + agent.followup([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const result = events(agent).find(e => e.type === 'tool/result') expect(result?.type === 'tool/result' && result.data.content.some(b => b.type === 'text' && b.text === 'rewritten-result')).toBe(true) - expect(events(agent).some(e => e.type === 'context/message' && e.data.content.some(b => b.type === 'text' && b.text.includes('bridge-note')))).toBe(true) + expect(events(agent).some(e => e.type === 'user/message' && e.data.source.kind !== 'user' && e.data.content.some(b => b.type === 'text' && b.text.includes('bridge-note')))).toBe(true) }) it('keeps bridge and downstream PostToolUse contexts as separate sourced events', async () => { @@ -175,14 +175,14 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro }], })) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) + agent.followup([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) - const contexts = events(agent).filter(event => event.type === 'context/message') - expect(contexts.map(event => event.type === 'context/message' && event.data.source)).toEqual([ + const contexts = events(agent).filter(event => event.type === 'user/message' && event.data.source.kind !== 'user') + expect(contexts.map(event => event.type === 'user/message' && event.data.source)).toEqual([ { kind: 'plugin', plugin: 'hooks-codex' }, { kind: 'plugin', plugin: 'policy' }, ]) - expect(contexts[1]?.type === 'context/message' && contexts[1].data.meta).toEqual({ owner: 'policy' }) + expect(contexts[1]?.type === 'user/message' && contexts[1].data.meta).toEqual({ owner: 'policy' }) }) it('folds the bridge PostToolUse context onto a downstream listener BLOCK', async () => { @@ -193,11 +193,11 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro ctx.tools.register(defineContentToolFixture({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) ctx.on('tools/post-execute', async () => ({ kind: 'block' as const, feedback: [{ type: 'text' as const, text: 'downstream-block' }] })) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) + agent.followup([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const result = events(agent).find(e => e.type === 'tool/result') expect(result?.type === 'tool/result' && result.data.isError).toBe(true) expect(result?.type === 'tool/result' && result.data.content.some(b => b.type === 'text' && b.text.includes('downstream-block'))).toBe(true) - expect(events(agent).some(e => e.type === 'context/message' && e.data.content.some(b => b.type === 'text' && b.text.includes('bridge-note')))).toBe(true) + expect(events(agent).some(e => e.type === 'user/message' && e.data.source.kind !== 'user' && e.data.content.some(b => b.type === 'text' && b.text.includes('bridge-note')))).toBe(true) }) it('SessionStart additionalContext is injected for the first request', async () => { @@ -206,9 +206,9 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(join(d, 'hooks.json'), adapter) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - await waitFor(() => events(agent).some(e => e.type === 'context/message' + await waitFor(() => events(agent).some(e => e.type === 'user/message' && e.data.content.some(b => b.type === 'text' && b.text.includes('start-ctx')))) - agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) + agent.followup([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(JSON.stringify(adapter.requests[0]!.messages)).toContain('start-ctx') }) @@ -219,7 +219,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.tools.register(defineContentToolFixture({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) + agent.followup([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const r = events(agent).find(e => e.type === 'tool/result') expect(r?.type === 'tool/result' && r.data.isError).toBe(true) expect(r?.type === 'tool/result' && r.data.content.some(b => b.type === 'text' && b.text.includes('blocked by PostToolUse hook'))).toBe(true) @@ -232,8 +232,8 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.tools.register(defineContentToolFixture({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) - expect(events(agent).some(e => e.type === 'context/message' && e.data.content.some(b => b.type === 'text' && b.text.includes('post-ctx')))).toBe(true) + agent.followup([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) + expect(events(agent).some(e => e.type === 'user/message' && e.data.source.kind !== 'user' && e.data.content.some(b => b.type === 'text' && b.text.includes('post-ctx')))).toBe(true) }) }) @@ -246,7 +246,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro let ran = false ctx.tools.register(defineContentToolFixture({ name: 'Bash', description: 'b', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) + agent.followup([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(ran).toBe(true) // clean-exit hook allows; commandOf returned '' }) @@ -257,7 +257,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.tools.register(defineContentToolFixture({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) + agent.followup([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const res = events(agent).find(e => e.type === 'hook/result') expect(res?.type === 'hook/result' && res.data.exitCode).toBe(0) expect(res?.type === 'hook/result' && 'stderrSummary' in res.data).toBe(false) @@ -270,7 +270,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.tools.register(defineContentToolFixture({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) + agent.followup([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const res = events(agent).find(e => e.type === 'hook/result') expect(res?.type === 'hook/result' && res.data.stderrSummary?.endsWith('…')).toBe(true) expect(res?.type === 'hook/result' && res.data.stderrSummary?.length).toBe(501) // default 500-char cap + ellipsis @@ -293,7 +293,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro const ctx = await harness(join(d, 'hooks.json'), adapter, { stderrSummaryMaxChars: 40 }) ctx.tools.register(defineContentToolFixture({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) + agent.followup([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const res = events(agent).find(e => e.type === 'hook/result') expect(res?.type === 'hook/result' && res.data.stderrSummary).toBe('x'.repeat(40) + '…') }) @@ -316,7 +316,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro HooksCodex.apply(ctx, { configPath: join(d, 'hooks.json') }) ctx.llm.registerAdapter(['mock'], adapter) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) + agent.followup([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(existsSync(marker)).toBe(true) expect(warn).toHaveBeenCalledWith(expect.stringContaining('async hook')) }) @@ -329,7 +329,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro let ran = false ctx.tools.register(defineContentToolFixture({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) + agent.followup([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(ran).toBe(true) }) @@ -344,8 +344,8 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro const ctx = await harness(join(d, 'hooks.json'), adapter) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) await waitFor(() => existsSync(marker)) // the clean no-output hook has finished - agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) - expect(events(agent).some(e => e.type === 'context/message')).toBe(false) + agent.followup([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) + expect(events(agent).some(e => e.type === 'user/message' && e.data.source.kind !== 'user')).toBe(false) }) it('a throwing SessionStart inject is contained (logged)', async () => { @@ -370,7 +370,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro let ran = false ctx.tools.register(defineContentToolFixture({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) + agent.followup([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(ran).toBe(true) }) @@ -383,7 +383,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro let ran = false ctx.tools.register(defineContentToolFixture({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) + agent.followup([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(ran).toBe(true) // matcher didn't match → no hook ran → tool proceeded expect(events(agent).some(e => e.type === 'hook/invoked')).toBe(false) }) @@ -399,7 +399,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro let ran = false ctx.tools.register(defineContentToolFixture({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) + agent.followup([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const res = events(agent).find(e => e.type === 'hook/result') expect(res?.type === 'hook/result' && res.data.decision).toBe('stop') // recorded expect(ran).toBe(true) // NOT honored: the tool still ran (halt is deferred) @@ -412,7 +412,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.tools.register(defineContentToolFixture({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) + agent.followup([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const r = events(agent).find(e => e.type === 'tool/result') expect(r?.type === 'tool/result' && r.data.content.some(b => b.type === 'text' && b.text.includes('blocked by PreToolUse hook'))).toBe(true) }) @@ -424,11 +424,11 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.tools.register(defineContentToolFixture({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) + agent.followup([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const r = events(agent).find(e => e.type === 'tool/result') expect(r?.type === 'tool/result' && r.data.isError).toBe(true) expect(r?.type === 'tool/result' && r.data.content.some(b => b.type === 'text' && b.text.includes('bad'))).toBe(true) - expect(events(agent).some(e => e.type === 'context/message' && e.data.content.some(b => b.type === 'text' && b.text.includes('ctx too')))).toBe(true) + expect(events(agent).some(e => e.type === 'user/message' && e.data.source.kind !== 'user' && e.data.content.some(b => b.type === 'text' && b.text.includes('ctx too')))).toBe(true) }) it('commandOf reads a non-string command arg as an empty command', async () => { @@ -441,7 +441,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.tools.register(defineContentToolFixture({ name: 'Bash', description: 'b', parameters: { command: { type: 'number' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) + agent.followup([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const payload = JSON.parse(readFileSync(cap, 'utf8')) as { tool_input: { command: string } } expect(payload.tool_input.command).toBe('') }) @@ -477,7 +477,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro ctx.bash.run = (() => Promise.reject(new Error('executor down'))) ctx.tools.register(defineContentToolFixture({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) + agent.followup([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const res = events(agent).find(e => e.type === 'hook/result') expect(res?.type === 'hook/result' && 'exitCode' in res.data).toBe(false) }) @@ -493,7 +493,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro const adapter = new MockAdapter([textResponse('one'), textResponse('two')]) const ctx = await harness(join(d, 'hooks.json'), adapter) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) + agent.followup([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(adapter.requests).toHaveLength(2) // empty-reason block forced continuation expect(JSON.stringify(adapter.requests[1]!.messages)).toContain('blocked by Stop hook') }) @@ -506,7 +506,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(join(d, 'hooks.json'), adapter) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) + agent.followup([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(JSON.stringify(adapter.requests[0]!.messages)).toContain('extra guidance from a plain hook') }) @@ -521,7 +521,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro const ctx = await harness(join(d, 'hooks.json'), adapter) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) await waitFor(() => existsSync(marker)) // the exit-2 hook has finished - expect(events(agent).some(e => e.type === 'context/message' + expect(events(agent).some(e => e.type === 'user/message' && e.data.content.some(b => b.type === 'text' && b.text.includes('stale')))).toBe(false) }) @@ -534,7 +534,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(join(d, 'hooks.json'), adapter) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) + agent.followup([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(adapter.requests).toHaveLength(1) // exit 1 is non-blocking → the turn ran expect(JSON.stringify(adapter.requests[0]!.messages)).not.toContain('stale') }) @@ -545,9 +545,9 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(join(d, 'hooks.json'), adapter) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - await waitFor(() => events(agent).some(e => e.type === 'context/message' + await waitFor(() => events(agent).some(e => e.type === 'user/message' && e.data.content.some(b => b.type === 'text' && b.text.includes('session preamble')))) - agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) + agent.followup([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(JSON.stringify(adapter.requests[0]!.messages)).toContain('session preamble') }) @@ -559,7 +559,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(join(d, 'hooks.json'), adapter) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) + agent.followup([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(JSON.stringify(adapter.requests[0]!.messages)).not.toContain('unrelated') }) @@ -574,7 +574,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.tools.register(defineContentToolFixture({ name: 'shell', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) + agent.followup([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const payload = JSON.parse(readFileSync(cap, 'utf8')) as { tool_name: string; tool_input: { command: string } } expect(payload.tool_name).toBe('shell') expect(payload.tool_input.command).toBe('ls') @@ -590,7 +590,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro let ran = false ctx.tools.register(defineContentToolFixture({ name: 'shell', description: 'b', parameters: { command: { type: 'string' } }, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) + agent.followup([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(ran).toBe(false) // the matcher fired → the hook denied the tool expect(events(agent).some(e => e.type === 'hook/invoked' && e.data.point === 'PreToolUse')).toBe(true) }) @@ -602,7 +602,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro const ctx = await harness(join(d, 'hooks.json'), adapter) const warn = vi.fn(); ctx.logger.warn = warn as never const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) + agent.followup([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(warn).toHaveBeenCalledWith(expect.stringContaining('systemMessage')) expect(JSON.stringify(adapter.requests[0]!.messages)).not.toContain('heads up') }) @@ -625,7 +625,7 @@ export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGro ctx.tools.register(defineContentToolFixture({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) const { SessionId } = await import('@deepseek-ai/dsh-session') const handle = await ctx.agents.create({ sessionId: SessionId('s1'), meta: { cwd: sessionDir }, agentOptions: { provider: 'mock', model: 'mock' } }) - handle.agent.send([{ type: 'text', text: 'go' }]) + handle.agent.followup([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, handle.agent) expect(existsSync(marker)).toBe(true) expect(readFileSync(marker, 'utf8').trim().endsWith(sessionDir.split('/').pop()!)).toBe(true) diff --git a/packages/host/runtime/src/api-proxy.ts b/packages/host/runtime/src/api-proxy.ts index 3792d17da3..acf77751af 100644 --- a/packages/host/runtime/src/api-proxy.ts +++ b/packages/host/runtime/src/api-proxy.ts @@ -447,7 +447,7 @@ export function createApiProxy(ctx: Context, defaults: ApiProxyDefaults): ApiPro const source: MessageSource = { kind: 'user', rpcId: request.rpcId } try { if (mode === 'steer') agent.steer(content, { source }) - else agent.send(content, { source }) + else agent.followup(content, { source }) } catch (error: unknown) { // A synchronous throw from send/steer means disposed or invalid input; surface as agent-busy with the reason attached. return err(request, { code: 'agent-busy', message: 'prompt rejected', details: { reason: String(error) } }) diff --git a/packages/host/runtime/tests/host-runtime.spec.ts b/packages/host/runtime/tests/host-runtime.spec.ts index 92d6534831..0a324abda3 100644 --- a/packages/host/runtime/tests/host-runtime.spec.ts +++ b/packages/host/runtime/tests/host-runtime.spec.ts @@ -431,7 +431,7 @@ describe('sessions.prompt / cancel', () => { const { api, ctx } = running const { sessionId } = expectOk(await api.sessions.create(request({}))) const agent = ctx.agents.get(sessionId) as Agent - agent.send([{ type: 'text', text: 'run forever' }]) + agent.followup([{ type: 'text', text: 'run forever' }]) expectOk(await api.sessions.cancel(request({ sessionId }))) const missing = await api.sessions.cancel(request({ sessionId: 'session-none' as SessionId })) @@ -450,7 +450,7 @@ describe('sessions.history', () => { const { sessionId } = expectOk(await first.api.sessions.create(request({}))) const agent = first.ctx.agents.get(sessionId) as Agent const idle = waitForIdle(first.ctx, agent) - agent.send([{ type: 'text', text: 'save me' }]) + agent.followup([{ type: 'text', text: 'save me' }]) await idle const titleEvent = await appendTitle(first.ctx, agent, 'Persisted title') await first.dispose() @@ -499,7 +499,7 @@ describe('sessions.history', () => { const agent = ctx.agents.get(sessionId) as Agent for (const text of ['q1', 'q2', 'q3']) { const idle = waitForIdle(ctx, agent) - agent.send([{ type: 'text', text }]) + agent.followup([{ type: 'text', text }]) await idle } @@ -570,7 +570,7 @@ describe('events streams', () => { const agent = ctx.agents.get(sessionId) as Agent const idle = waitForIdle(ctx, agent) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await idle const live = await stream.next() expect((live.value as RpcRequest<MuxFrame>).payload.type).toBe('session/event') @@ -633,7 +633,7 @@ describe('events streams', () => { const agent = ctx.agents.get(sessionId) as Agent const idle = waitForIdle(ctx, agent) - agent.send([{ type: 'text', text: 'run' }]) + agent.followup([{ type: 'text', text: 'run' }]) await idle const runningFrame = await stream.next() expect((runningFrame.value as RpcRequest<HostFrame>).payload).toMatchObject({ type: 'host/session-status', running: true }) diff --git a/packages/llm/llm-retry/tests/loader-composition.spec.ts b/packages/llm/llm-retry/tests/loader-composition.spec.ts index 1aafc91d92..bb08577d74 100644 --- a/packages/llm/llm-retry/tests/loader-composition.spec.ts +++ b/packages/llm/llm-retry/tests/loader-composition.spec.ts @@ -114,7 +114,7 @@ describe('real Loader composition', () => { loaded.llm.registerAdapter(['mock'], adapter) const agent = loaded.agentLoop.create(SessionId('loader-retry'), { provider: 'mock', model: 'mock' }) const idle = waitForIdle(loaded, agent) - agent.send([{ type: 'text', text: 'recover' }]) + agent.followup([{ type: 'text', text: 'recover' }]) await idle expect(adapter.requests).toBe(2) diff --git a/packages/llm/llm-retry/tests/retry.spec.ts b/packages/llm/llm-retry/tests/retry.spec.ts index 4dc1c06bd6..20e7862ebc 100644 --- a/packages/llm/llm-retry/tests/retry.spec.ts +++ b/packages/llm/llm-retry/tests/retry.spec.ts @@ -129,7 +129,7 @@ describe('bounded transient retry policy', () => { }) }) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) const event = await scheduled expect(event.data).toEqual({ @@ -178,7 +178,7 @@ describe('bounded transient retry policy', () => { const agent = context.agentLoop.create(SessionId('retry-partial'), { provider: 'mock', model: 'mock' }) const scheduled = waitForRetry(context, agent, 1) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await scheduled const idle = waitForIdle(context, agent) await vi.advanceTimersByTimeAsync(500) @@ -213,7 +213,7 @@ describe('bounded transient retry policy', () => { const agent = context.agentLoop.create(SessionId('retry-exhausted'), { provider: 'mock', model: 'mock' }) const first = waitForRetry(context, agent, 1) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) expect((await first).data.delayMs).toBe(450) const second = waitForRetry(context, agent, 2) @@ -246,7 +246,7 @@ describe('bounded transient retry policy', () => { const agent = context.agentLoop.create(SessionId('retry-zero-delay'), { provider: 'mock', model: 'mock' }) const scheduled = waitForRetry(context, agent, 1) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) expect((await scheduled).data.delayMs).toBe(0) const idle = waitForIdle(context, agent) @@ -264,7 +264,7 @@ describe('bounded transient retry policy', () => { ;({ ctx: context } = await harness(accepted, { jitterRatio: 1 })) const acceptedAgent = context.agentLoop.create(SessionId('retry-after-accepted'), { provider: 'mock', model: 'mock' }) const scheduled = waitForRetry(context, acceptedAgent, 1) - acceptedAgent.send([{ type: 'text', text: 'go' }]) + acceptedAgent.followup([{ type: 'text', text: 'go' }]) expect((await scheduled).data.delayMs).toBe(2_000) const acceptedIdle = waitForIdle(context, acceptedAgent) await vi.advanceTimersByTimeAsync(2_000) @@ -278,7 +278,7 @@ describe('bounded transient retry policy', () => { ;({ ctx: context } = await harness(rejected)) const rejectedAgent = context.agentLoop.create(SessionId('retry-after-rejected'), { provider: 'mock', model: 'mock' }) const rejectedIdle = waitForIdle(context, rejectedAgent) - rejectedAgent.send([{ type: 'text', text: 'go' }]) + rejectedAgent.followup([{ type: 'text', text: 'go' }]) await rejectedIdle expect(rejected.requests).toHaveLength(1) expect(rejectedAgent.session.events.some(event => event.type === 'llm/retry')).toBe(false) @@ -290,7 +290,7 @@ describe('bounded transient retry policy', () => { ;({ ctx: context } = await harness(adapter)) const agent = context.agentLoop.create(SessionId('retry-auth'), { provider: 'mock', model: 'mock' }) const idle = waitForIdle(context, agent) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await idle expect(adapter.requests).toHaveLength(1) expect(agent.session.events.some(event => event.type === 'llm/retry')).toBe(false) @@ -307,7 +307,7 @@ describe('bounded transient retry policy', () => { context = mounted.ctx const agent = context.agentLoop.create(SessionId('retry-hmr'), { provider: 'mock', model: 'mock' }) const scheduled = waitForRetry(context, agent, 1) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await scheduled const idle = waitForIdle(context, agent) @@ -335,7 +335,7 @@ describe('bounded transient retry policy', () => { model: 'mock', }) const idle = waitForIdle(context, agent) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await entered.promise const disposing = mounted.retryFiber.dispose() @@ -376,7 +376,7 @@ describe('bounded transient retry policy', () => { model: 'mock', }) const idle = waitForIdle(context, agent) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await captured.promise await mounted.retryFiber.dispose() @@ -397,7 +397,7 @@ describe('bounded transient retry policy', () => { ;({ ctx: context } = await harness(adapter)) const agent = context.agentLoop.create(SessionId('retry-cancel'), { provider: 'mock', model: 'mock' }) const scheduled = waitForRetry(context, agent, 1) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await scheduled const idle = waitForIdle(context, agent) agent.cancel({ kind: 'user' }) @@ -426,7 +426,7 @@ describe('bounded transient retry policy', () => { const agent = context.agentLoop.create(SessionId('retry-pre-cancel'), { provider: 'mock', model: 'mock' }) const idle = waitForIdle(context, agent) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await idle expect(adapter.requests).toHaveLength(1) @@ -450,7 +450,7 @@ describe('bounded transient retry policy', () => { }) const idle = waitForIdle(context, agent) - agent.send([{ type: 'text', text: 'go' }]) + agent.followup([{ type: 'text', text: 'go' }]) await idle expect(adapter.requests).toHaveLength(1) diff --git a/packages/plan/plan-mode/README.md b/packages/plan/plan-mode/README.md index 2725954185..0f24508d14 100644 --- a/packages/plan/plan-mode/README.md +++ b/packages/plan/plan-mode/README.md @@ -6,7 +6,7 @@ Logged, per-agent plan collaboration state with deployment-owned guidance, direc `plan/mode` (`{ active: boolean }`) is a log-only, whole-value-replace `SessionEventMap` member. `foldPlanMode(events)` returns the last logged value or `false`, so resume, fork, and compaction recover plan state directly from the session log. UIs observe committed flips through `session/event`. -`ctx.planMode.set(agent, active)` records a pending selection and flushes it inside the next turn boundary. `get(agent)` returns `{ active, pending? }`, separating the logged state shaping the current step from a user's optimistic selection. Prompt submission, ordinary continuation, and request-recovery retry are all covered; a changed user selection contributes one `context/message` notice when the last logged request header described the other state. +`ctx.planMode.set(agent, active)` records a pending selection and flushes it inside the next turn boundary. `get(agent)` returns `{ active, pending? }`, separating the logged state shaping the current step from a user's optimistic selection. Prompt submission, ordinary continuation, and request-recovery retry are all covered; a changed user selection contributes one plugin-sourced `user/message` notice when the last logged request header described the other state. ## Model and human surfaces diff --git a/packages/plan/plan-mode/src/index.ts b/packages/plan/plan-mode/src/index.ts index c1ece17958..26ad904d30 100644 --- a/packages/plan/plan-mode/src/index.ts +++ b/packages/plan/plan-mode/src/index.ts @@ -357,7 +357,7 @@ export class PlanModeService extends Service { const text = target ? 'The user switched this session to plan mode.' : 'The user switched this session back to the default mode.' - session.append('context/message', { + session.append('user/message', { content: [{ type: 'text', text }], source: { kind: 'plugin', plugin: 'plan-mode' }, }, { surfaceOp: 'append' }) diff --git a/packages/plan/plan-mode/tests/integration.spec.ts b/packages/plan/plan-mode/tests/integration.spec.ts index 940b78870a..e195ed54b2 100644 --- a/packages/plan/plan-mode/tests/integration.spec.ts +++ b/packages/plan/plan-mode/tests/integration.spec.ts @@ -75,7 +75,7 @@ describe('plan mode through the agent loop', () => { // the first prompt-submit, BEFORE the first assembly. ctx.planMode.set(agent, true) - agent.send([{ type: 'text', text: 'explore the repo' }]) + agent.followup([{ type: 'text', text: 'explore the repo' }]) await waitForIdle(ctx, agent) const log = agent.session.events @@ -92,7 +92,7 @@ describe('plan mode through the agent loop', () => { const result = findEvent(log, 'tool/result') expect(result.data.isError).toBe(false) expect(foldPlanMode(log)).toBe(true) - expect(log.some(event => event.type === 'context/message')).toBe(false) + expect(log.some(event => event.type === 'user/message' && event.data.source.kind === 'plugin')).toBe(false) }) it('a user flip between turns lands at the boundary: one notice and a changed header with stable tool schemas', async () => { @@ -103,21 +103,21 @@ describe('plan mode through the agent loop', () => { const ctx = await harness(adapter) const agent = ctx.agentLoop.create(SessionId('it-plan-flip'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'hello' }]) + agent.followup([{ type: 'text', text: 'hello' }]) await waitForIdle(ctx, agent) expect(foldPlanMode(agent.session.events)).toBe(false) const first = findEvent(agent.session.events, 'request/header') expect(first.data.header.tools?.map(tool => tool.name)).toEqual(['exit_plan_mode', 'read', 'write']) ctx.planMode.set(agent, true) - agent.send([{ type: 'text', text: 'now plan' }]) + agent.followup([{ type: 'text', text: 'now plan' }]) await waitForIdle(ctx, agent) const log = agent.session.events expect(foldPlanMode(log)).toBe(true) - const notices = log.filter(event => event.type === 'context/message') + const notices = log.filter(event => event.type === 'user/message' && event.data.source.kind === 'plugin') expect(notices).toHaveLength(1) - expect(findEvent(log, 'context/message').data.content).toEqual([ + expect(notices[0]?.type === 'user/message' && notices[0].data.content).toEqual([ { type: 'text', text: 'The user switched this session to plan mode.' }, ]) // The changed request is logged as a complete snapshot. @@ -146,7 +146,7 @@ describe('plan mode through the agent loop', () => { }) const idle = waitForIdle(ctx, agent) - agent.send([{ type: 'text', text: 'plan after the transient failure' }]) + agent.followup([{ type: 'text', text: 'plan after the transient failure' }]) await recoveryEntered.promise ctx.planMode.set(agent, true) releaseRecovery.resolve(true) @@ -163,7 +163,8 @@ describe('plan mode through the agent loop', () => { expect(firstEnd?.seq).toBeLessThan(planMode.seq) expect(planMode.seq).toBeLessThan(retryStart?.seq ?? 0) expect(findEvent(log, 'request/header', 'last').data.header.system).toContain(PLAN_CONFIG.section) - expect(findEvent(log, 'context/message').data.content).toEqual([ + const notice = log.find(event => event.type === 'user/message' && event.data.source.kind === 'plugin') + expect(notice?.type === 'user/message' && notice.data.content).toEqual([ { type: 'text', text: 'The user switched this session to plan mode.' }, ]) }) diff --git a/packages/plan/plan-mode/tests/plan-mode.spec.ts b/packages/plan/plan-mode/tests/plan-mode.spec.ts index f45ada4db0..a7f7743497 100644 --- a/packages/plan/plan-mode/tests/plan-mode.spec.ts +++ b/packages/plan/plan-mode/tests/plan-mode.spec.ts @@ -95,7 +95,7 @@ function header(session: Session): void { function noticeTexts(session: Session): string[] { return session.events - .filter(event => event.type === 'context/message') + .filter(event => event.type === 'user/message' && event.data.source.kind === 'plugin') .map(event => (event.data as { content: { type: string; text?: string }[] }).content.map(block => block.text ?? '').join('')) } diff --git a/packages/pty/pty-local/tests/index.spec.ts b/packages/pty/pty-local/tests/index.spec.ts index 31a8d99184..26f4ddcc11 100644 --- a/packages/pty/pty-local/tests/index.spec.ts +++ b/packages/pty/pty-local/tests/index.spec.ts @@ -3,8 +3,7 @@ import type { IPty, IPtyForkOptions } from 'node-pty' import { Context } from 'cordis' import Loader from '@cordisjs/plugin-loader' import SessionStore, { Session, SessionId } from '@deepseek-ai/dsh-session' -import AgentRegistry from '@deepseek-ai/dsh-agent' -import type { Agent } from '@deepseek-ai/dsh-agent' +import AgentRegistry, { AgentMessageId, type Agent } from '@deepseek-ai/dsh-agent' import SandboxProvider from '@deepseek-ai/dsh-sandbox' import type { ConfinedArgv, SandboxPolicy } from '@deepseek-ai/dsh-sandbox' import SandboxPolicyService, { setSandboxMode } from '@deepseek-ai/dsh-sandbox-policy' @@ -43,7 +42,7 @@ function agent(ctx: Context): Agent { const id = SessionId('agent') return { id, options: {}, session: new Session(id), status: 'idle', ctx, - send() {}, steer() {}, inject() {}, cancel() {}, whenIdle: () => Promise.resolve(), + followup: () => AgentMessageId('stub'), queue: () => AgentMessageId('stub'), steer: () => AgentMessageId('stub'), inject: () => AgentMessageId('stub'), send: () => AgentMessageId('stub'), cancel() {}, whenIdle: () => Promise.resolve(), } } @@ -245,7 +244,7 @@ describe('pty-local plugin shape', () => { const ownerFiber = await ctx.plugin(() => {}) const owner: Agent = { id: session.id, options: {}, session, status: 'idle', ctx: ownerFiber.ctx, - send() {}, steer() {}, inject() {}, cancel() {}, whenIdle: () => Promise.resolve(), + followup: () => AgentMessageId('stub'), queue: () => AgentMessageId('stub'), steer: () => AgentMessageId('stub'), inject: () => AgentMessageId('stub'), send: () => AgentMessageId('stub'), cancel() {}, whenIdle: () => Promise.resolve(), } ctx.agents.register(owner) const providerFiber = await registerStubLocalBackend(ctx, () => stubLocalSession()) @@ -288,7 +287,7 @@ describe('pty-local plugin shape', () => { const ownerFiber = await ctx.plugin(() => {}) const owner: Agent = { id: session.id, options: {}, session, status: 'idle', ctx: ownerFiber.ctx, - send() {}, steer() {}, inject() {}, cancel() {}, whenIdle: () => Promise.resolve(), + followup: () => AgentMessageId('stub'), queue: () => AgentMessageId('stub'), steer: () => AgentMessageId('stub'), inject: () => AgentMessageId('stub'), send: () => AgentMessageId('stub'), cancel() {}, whenIdle: () => Promise.resolve(), } ctx.agents.register(owner) const gate = Promise.withResolvers<undefined>() diff --git a/packages/pty/pty-local/tests/local.spec.ts b/packages/pty/pty-local/tests/local.spec.ts index 1b04dfea8c..763ab5c871 100644 --- a/packages/pty/pty-local/tests/local.spec.ts +++ b/packages/pty/pty-local/tests/local.spec.ts @@ -4,7 +4,7 @@ import { join } from 'node:path' import { afterEach, describe, expect, it } from 'vitest' import { Context } from 'cordis' import { Session, SessionId } from '@deepseek-ai/dsh-session' -import AgentRegistry from '@deepseek-ai/dsh-agent' +import AgentRegistry, { AgentMessageId } from '@deepseek-ai/dsh-agent' import type { Agent } from '@deepseek-ai/dsh-agent' import PtyService from '@deepseek-ai/dsh-pty' import type { PtySendOperation } from '@deepseek-ai/dsh-pty' @@ -35,7 +35,7 @@ function stubAgent(ctx: Context, rawId: string): Agent { const scope = ctx.plugin(() => {}) return { id, options: {}, session: new Session(id), status: 'idle', ctx: scope.ctx, - send() {}, steer() {}, inject() {}, cancel() {}, whenIdle: () => Promise.resolve(), + followup: () => AgentMessageId('stub'), queue: () => AgentMessageId('stub'), steer: () => AgentMessageId('stub'), inject: () => AgentMessageId('stub'), send: () => AgentMessageId('stub'), cancel() {}, whenIdle: () => Promise.resolve(), } } diff --git a/packages/pty/pty/tests/service.spec.ts b/packages/pty/pty/tests/service.spec.ts index cab879b1a9..42622f2712 100644 --- a/packages/pty/pty/tests/service.spec.ts +++ b/packages/pty/pty/tests/service.spec.ts @@ -1,7 +1,7 @@ import { describe, expect, expectTypeOf, it } from 'vitest' import { Context } from 'cordis' import { Session, SessionId } from '@deepseek-ai/dsh-session' -import AgentRegistry from '@deepseek-ai/dsh-agent' +import AgentRegistry, { AgentMessageId } from '@deepseek-ai/dsh-agent' import type { Agent } from '@deepseek-ai/dsh-agent' import PtyService, { PtyBackendCleanupError, PtyError, PtySessionId } from '@deepseek-ai/dsh-pty' import type { @@ -27,9 +27,11 @@ function stubAgent(ctx: Context, rawId: string): Agent { session: new Session(id), status: 'idle', ctx: scopeFiber.ctx, - send() {}, - steer() {}, - inject() {}, + followup: () => AgentMessageId('stub'), + queue: () => AgentMessageId('stub'), + steer: () => AgentMessageId('stub'), + inject: () => AgentMessageId('stub'), + send: () => AgentMessageId('stub'), cancel() {}, whenIdle: () => Promise.resolve(), } diff --git a/packages/pty/tool-pty/tests/loader-composition.spec.ts b/packages/pty/tool-pty/tests/loader-composition.spec.ts index 38a5cb4ed6..40477aeb7a 100644 --- a/packages/pty/tool-pty/tests/loader-composition.spec.ts +++ b/packages/pty/tool-pty/tests/loader-composition.spec.ts @@ -8,7 +8,7 @@ import Loader from '@cordisjs/plugin-loader' import Include from '@cordisjs/plugin-include' import { CallId } from '@deepseek-ai/dsh-llm' import { Session, SessionId } from '@deepseek-ai/dsh-session' -import AgentRegistry from '@deepseek-ai/dsh-agent' +import AgentRegistry, { AgentMessageId } from '@deepseek-ai/dsh-agent' import type { Agent } from '@deepseek-ai/dsh-agent' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' @@ -40,7 +40,7 @@ function agent(ctx: Context): Agent { const id = SessionId('pty-loader-agent') const value: Agent = { id, options: {}, session: new Session(id), status: 'idle', ctx: scope.ctx, - send() {}, steer() {}, inject() {}, cancel() {}, whenIdle: () => Promise.resolve(), + followup: () => AgentMessageId('stub'), queue: () => AgentMessageId('stub'), steer: () => AgentMessageId('stub'), inject: () => AgentMessageId('stub'), send: () => AgentMessageId('stub'), cancel() {}, whenIdle: () => Promise.resolve(), } ctx.agents.register(value) return value diff --git a/packages/pty/tool-pty/tests/tools.spec.ts b/packages/pty/tool-pty/tests/tools.spec.ts index 9235e93226..e0b854ee43 100644 --- a/packages/pty/tool-pty/tests/tools.spec.ts +++ b/packages/pty/tool-pty/tests/tools.spec.ts @@ -2,7 +2,7 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' import { CallId } from '@deepseek-ai/dsh-llm' import { Session, SessionId } from '@deepseek-ai/dsh-session' -import AgentRegistry from '@deepseek-ai/dsh-agent' +import AgentRegistry, { AgentMessageId } from '@deepseek-ai/dsh-agent' import type { Agent } from '@deepseek-ai/dsh-agent' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { renderToolsSdk } from '@deepseek-ai/dsh-tools' @@ -18,7 +18,7 @@ function fakeAgent(ctx: Context, rawId: string): Agent { const id = SessionId(rawId) const agent: Agent = { id, options: {}, session: new Session(id), status: 'idle', ctx: scope.ctx, - send() {}, steer() {}, inject() {}, cancel() {}, whenIdle: () => Promise.resolve(), + followup: () => AgentMessageId('stub'), queue: () => AgentMessageId('stub'), steer: () => AgentMessageId('stub'), inject: () => AgentMessageId('stub'), send: () => AgentMessageId('stub'), cancel() {}, whenIdle: () => Promise.resolve(), } ctx.agents.register(agent) return agent diff --git a/packages/session-persistence/session-checkpoint-policy/tests/fixtures/crash-child.ts b/packages/session-persistence/session-checkpoint-policy/tests/fixtures/crash-child.ts index 89cd254c8e..412ff8203d 100644 --- a/packages/session-persistence/session-checkpoint-policy/tests/fixtures/crash-child.ts +++ b/packages/session-persistence/session-checkpoint-policy/tests/fixtures/crash-child.ts @@ -56,5 +56,5 @@ const handle = await ctx.agents.create({ sessionId: SessionId('semantic-checkpoint-crash'), agentOptions: { provider: 'crash', model: 'crash' }, }) -handle.agent.send([{ type: 'text', text: 'exercise the crash boundary' }]) +handle.agent.followup([{ type: 'text', text: 'exercise the crash boundary' }]) await waitForCrash() diff --git a/packages/session-persistence/session-persistence-jsonl/src/format.ts b/packages/session-persistence/session-persistence-jsonl/src/format.ts index 2a34a1ce80..48f99e6610 100644 --- a/packages/session-persistence/session-persistence-jsonl/src/format.ts +++ b/packages/session-persistence/session-persistence-jsonl/src/format.ts @@ -84,6 +84,9 @@ function isHeaderLine(value: unknown): value is HeaderLine { && typeof (value as { version?: unknown }).version === 'number' && typeof (value as { id?: unknown }).id === 'string' && typeof (value as { createdAt?: unknown }).createdAt === 'number' + && Number.isSafeInteger((value as { createdAt: number }).createdAt) + && (value as { createdAt: number }).createdAt >= 0 + && !Object.is((value as { createdAt: number }).createdAt, -0) && typeof (value as { delegationDepth?: unknown }).delegationDepth === 'number' && Number.isSafeInteger((value as { delegationDepth: number }).delegationDepth) && (value as { delegationDepth: number }).delegationDepth >= 0 diff --git a/packages/session-persistence/session-persistence-jsonl/tests/jsonl.spec.ts b/packages/session-persistence/session-persistence-jsonl/tests/jsonl.spec.ts index 2b49b7d55b..5e9f446379 100644 --- a/packages/session-persistence/session-persistence-jsonl/tests/jsonl.spec.ts +++ b/packages/session-persistence/session-persistence-jsonl/tests/jsonl.spec.ts @@ -559,6 +559,26 @@ describe('SessionPersistenceJsonl: scanLog unit', () => { expect(() => scanLog(Buffer.from('{"type":"event"}\n'))).toThrow(/session header/) }) + it.each([ + ['fractional', 1.5], + ['negative', -1], + ['unsafe', Number.MAX_SAFE_INTEGER + 1], + ])('rejects a session header with a %s createdAt', (_label, createdAt) => { + const log = JSON.stringify({ + type: 'session', + version: 0, + id: 'invalid-created-at', + createdAt, + delegationDepth: 0, + }) + '\n' + expect(() => scanLog(Buffer.from(log))).toThrow(/session header/) + }) + + it('rejects a session header with negative-zero createdAt', () => { + const log = '{"type":"session","version":0,"id":"invalid-created-at","createdAt":-0,"delegationDepth":0}\n' + expect(() => scanLog(Buffer.from(log))).toThrow(/session header/) + }) + it.each([ ['missing', undefined], ['a string', '1'], diff --git a/packages/session-persistence/session-persistence-sqlite/README.md b/packages/session-persistence/session-persistence-sqlite/README.md index f1f4bc1f7b..011926d4b9 100644 --- a/packages/session-persistence/session-persistence-sqlite/README.md +++ b/packages/session-persistence/session-persistence-sqlite/README.md @@ -8,9 +8,9 @@ A SQLite durable session-persistence backend — a second `SessionPersistence` i ## Storage model -Each `SessionEvent` maps 1:1 onto a row in an `events` table `(session_id, seq, type, time, data, source_event_seqs, surface_op)` — `data` is the event payload as JSON text, so the row shape is the event verbatim (including `assistant/chunk`, keeping `seq` contiguous). The two `TEXT` columns `source_event_seqs` and `surface_op` are nullable; they store the event's optional surface-metadata fields (see [session surface](../../../.agents/notes/implemented/architecture/2026-06-18-session-surface.md)). Out-of-log metadata (`SessionHeader`), a per-materialization incarnation id, and a monotonic per-log revision live in a `sessions` row; a singleton state row carries the immutable store id. A `sessions` row is written only by the first `append` — its existence is the lazy-materialization signal (`list` reports exactly the sessions that have a row). +Each `SessionEvent` maps 1:1 onto a row in an `events` table `(session_id, seq, type, time, data, source_event_seqs, surface_op)` — `data` is the event payload as JSON text, so the row shape is the event verbatim (including `assistant/chunk`, keeping `seq` contiguous). The two `TEXT` columns `source_event_seqs` and `surface_op` are nullable; they store the event's optional surface-metadata fields (see [session surface](../../../.agents/notes/implemented/architecture/2026-06-18-session-surface.md)). Out-of-log metadata (`SessionHeader`), a per-materialization incarnation id, and a monotonic per-log revision live in a `sessions` row; `createdAt` is a non-negative safe integer stored in a strict `INTEGER` column. A singleton state row carries the immutable store id. A `sessions` row is written only by the first `append` — its existence is the lazy-materialization signal (`list` reports exactly the sessions that have a row). -The repository's Node range supports unflagged `node:sqlite`. The database enables foreign keys and uses the configured journal mode (`wal` by default; use a rollback mode where WAL shared-memory files are unsuitable). `PRAGMA user_version` stores the table-layout version; databases with any other version are rejected because this unreleased format has no migrations. +The repository's Node range supports unflagged `node:sqlite`. The database enables foreign keys and uses the configured journal mode (`wal` by default; use a rollback mode where WAL shared-memory files are unsuitable). `PRAGMA application_id` identifies the canonical persistence database, and `PRAGMA user_version` stores its layout version. A fresh database must have no application identity or user-defined schema objects; initialization creates every table and stamps both pragmas in one transaction. Non-pristine unversioned databases, foreign application identities, and every non-current version reject before journal-mode mutation because this unreleased format has no migrations. On filesystems with POSIX modes, the backend requests mode `0700` for missing directories and exclusively creates a missing database with mode `0600` before SQLite opens it; the process umask may further restrict both. New WAL, shared-memory, and persistent rollback-journal sidecars receive the database's resulting owner-only mode. Existing directories, database files, and sidecars keep their modes; filesystem setup errors other than an existing database fail initialization. These defaults prevent incidental exposure through a permissive process umask, but do not protect database confidentiality or integrity when another principal can replace the database entry in its parent directory. @@ -55,5 +55,5 @@ SQLite storage does not mutate live request prefixes. A resumed loop can reuse p - **`DatabaseSync` is synchronous** — every append transaction blocks the event loop for its duration; acceptable for local stores, a throughput ceiling for busy multi-session servers. - **Write contention has no wait or retry policy** — the backend sets no busy timeout and retries no locked-database error, so another connection holding a write transaction makes the operation reject immediately. -- **Only the current `SCHEMA_VERSION` opens** — a database with any other schema version is rejected rather than migrated (unreleased software; no persisted user data to preserve). +- **Only a pristine new database or the current owned `SCHEMA_VERSION` opens** — unversioned schema objects, foreign application identities, and every other schema version are rejected rather than migrated (unreleased software; no persisted user data to preserve). - **Nothing deletes stored sessions** — rows accumulate until removed externally (the seam has no deletion surface; `ON DELETE CASCADE` is wired for such out-of-band cleanup). diff --git a/packages/session-persistence/session-persistence-sqlite/src/schema.ts b/packages/session-persistence/session-persistence-sqlite/src/schema.ts index 8b8dcd78e0..754d9d7e63 100644 --- a/packages/session-persistence/session-persistence-sqlite/src/schema.ts +++ b/packages/session-persistence/session-persistence-sqlite/src/schema.ts @@ -17,7 +17,10 @@ import type { SessionEvent, SessionId, SessionHeader, SurfaceOp } from '@deepsee * layout; orthogonal to a session's own `version` (which versions the EVENT * vocabulary, stored per session in the `sessions` row). */ -export const SCHEMA_VERSION = 8 +export const SCHEMA_VERSION = 10 + +/** SQLite application id protecting unrelated databases from persistence writes. */ +export const SESSION_PERSISTENCE_SQLITE_APPLICATION_ID = 0x44534850 /** * A row of the `sessions` table — the out-of-log metadata ({@link SessionHeader}). @@ -63,9 +66,10 @@ export interface EventRow { export type JournalMode = 'wal' | 'delete' | 'truncate' | 'persist' /** - * Open the database and apply its schema and pragmas. A zero `user_version` is - * stamped with {@link SCHEMA_VERSION}; every other non-current version rejects - * rather than being migrated in place. + * Open the database and apply its schema and pragmas. An empty database with a + * zero `user_version` is initialized at {@link SCHEMA_VERSION}; a nonempty + * unversioned database and every other non-current version reject rather than + * being migrated in place. * @param path - the SQLite database file to open (created when absent). * @param journalMode - validated journal pragma. * @returns the open handle with pragmas applied and all three tables ensured. @@ -83,51 +87,81 @@ export function openDatabase(path: string, journalMode: JournalMode): DatabaseSy function configureDatabase(db: DatabaseSync, path: string, journalMode: JournalMode): void { db.exec('PRAGMA foreign_keys = ON') + let began = false + try { + db.exec('BEGIN IMMEDIATE') + began = true + // Validate while holding the write lock so no other connection can change + // schema ownership between inspection and initialization. + const { user_version: onDisk } = db.prepare('PRAGMA user_version').get() as { user_version: number } + const { application_id: applicationId } = db.prepare('PRAGMA application_id').get() as { application_id: number } + const { count: userObjectCount } = db.prepare( + "SELECT COUNT(*) AS count FROM sqlite_schema WHERE name NOT GLOB 'sqlite_*'", + ).get() as { count: number } + if (onDisk === 0 && (applicationId !== 0 || userObjectCount > 0)) { + throw new Error(`session database at "${path}" has an unversioned schema or application identity`) + } + if (onDisk !== 0 && onDisk !== SCHEMA_VERSION) { + throw new Error(`session database at "${path}" has schema version ${onDisk}, incompatible with this build (${SCHEMA_VERSION})`) + } + if (onDisk === SCHEMA_VERSION && applicationId !== SESSION_PERSISTENCE_SQLITE_APPLICATION_ID) { + throw new Error( + `session database at "${path}" has application id ${applicationId}, expected ${SESSION_PERSISTENCE_SQLITE_APPLICATION_ID}`, + ) + } + db.exec(` + CREATE TABLE IF NOT EXISTS persistence_state ( + singleton INTEGER PRIMARY KEY CHECK (singleton = 1), + store_id TEXT NOT NULL + ) STRICT; + + CREATE TABLE IF NOT EXISTS sessions ( + id TEXT PRIMARY KEY, + version INTEGER NOT NULL, + created_at INTEGER NOT NULL, + cwd TEXT, + parent_session TEXT, + seed_length INTEGER, + delegation_depth INTEGER, + incarnation TEXT NOT NULL, + revision INTEGER NOT NULL + ) STRICT; + + CREATE TABLE IF NOT EXISTS events ( + session_id TEXT NOT NULL REFERENCES sessions(id) ON DELETE CASCADE, + seq INTEGER NOT NULL, + type TEXT NOT NULL, + time INTEGER NOT NULL, + data TEXT NOT NULL, + source_event_seqs TEXT, + surface_op TEXT, + PRIMARY KEY (session_id, seq) + ) STRICT + `) + db.prepare( + 'INSERT OR IGNORE INTO persistence_state (singleton, store_id) VALUES (1, ?)', + ).run(randomUUID()) + if (onDisk === 0) { + db.exec(`PRAGMA application_id = ${SESSION_PERSISTENCE_SQLITE_APPLICATION_ID}`) + db.exec(`PRAGMA user_version = ${SCHEMA_VERSION}`) + } + db.exec('COMMIT') + began = false + } catch (error: unknown) { + /* v8 ignore next -- a BEGIN failure leaves no transaction to roll back. */ + if (began) { + /* v8 ignore next 5 -- preserve the original schema failure if SQLite also refuses rollback. */ + try { + db.exec('ROLLBACK') + } catch { + // The original SQLite failure remains the actionable cause. + } + } + throw error + } // The validated union is safe to interpolate into a non-bindable PRAGMA. + // Apply it only after ownership validation and initialization commit. db.exec(`PRAGMA journal_mode = ${journalMode.toUpperCase()}`) - // `PRAGMA user_version` always returns exactly one row { user_version }. - const { user_version: onDisk } = db.prepare('PRAGMA user_version').get() as { user_version: number } - if (onDisk !== 0 && onDisk !== SCHEMA_VERSION) { - throw new Error(`session database at "${path}" has schema version ${onDisk}, incompatible with this build (${SCHEMA_VERSION})`) - } - if (onDisk === 0) { - // Stamp fresh or pre-versioning databases. - db.exec(`PRAGMA user_version = ${SCHEMA_VERSION}`) - } - db.exec(` - CREATE TABLE IF NOT EXISTS persistence_state ( - singleton INTEGER PRIMARY KEY CHECK (singleton = 1), - store_id TEXT NOT NULL - ) STRICT - `) - db.prepare( - 'INSERT OR IGNORE INTO persistence_state (singleton, store_id) VALUES (1, ?)', - ).run(randomUUID()) - db.exec(` - CREATE TABLE IF NOT EXISTS sessions ( - id TEXT PRIMARY KEY, - version INTEGER NOT NULL, - created_at INTEGER NOT NULL, - cwd TEXT, - parent_session TEXT, - seed_length INTEGER, - delegation_depth INTEGER, - incarnation TEXT NOT NULL, - revision INTEGER NOT NULL - ) STRICT - `) - db.exec(` - CREATE TABLE IF NOT EXISTS events ( - session_id TEXT NOT NULL REFERENCES sessions(id) ON DELETE CASCADE, - seq INTEGER NOT NULL, - type TEXT NOT NULL, - time INTEGER NOT NULL, - data TEXT NOT NULL, - source_event_seqs TEXT, - surface_op TEXT, - PRIMARY KEY (session_id, seq) - ) STRICT - `) } /** @@ -136,6 +170,9 @@ function configureDatabase(db: DatabaseSync, path: string, journalMode: JournalM * @returns the header, `NULL` columns mapped to omitted optional fields. */ export function rowToMeta(row: SessionRow): SessionHeader { + if (!Number.isSafeInteger(row.created_at) || row.created_at < 0) { + throw new Error('stored session createdAt must be a non-negative safe integer') + } return { version: row.version, id: row.id as SessionId, diff --git a/packages/session-persistence/session-persistence-sqlite/tests/sqlite.spec.ts b/packages/session-persistence/session-persistence-sqlite/tests/sqlite.spec.ts index 3976e71549..8a47c7917f 100644 --- a/packages/session-persistence/session-persistence-sqlite/tests/sqlite.spec.ts +++ b/packages/session-persistence/session-persistence-sqlite/tests/sqlite.spec.ts @@ -4,10 +4,18 @@ import { existsSync } from 'node:fs' import { chmod, mkdtemp, rm, stat, symlink, writeFile } from 'node:fs/promises' import { tmpdir } from 'node:os' import { dirname, join } from 'node:path' +import { DatabaseSync } from 'node:sqlite' import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import type { Session, SessionEvent, SurfaceEvent, SurfaceEventType } from '@deepseek-ai/dsh-session' import SessionPersistenceSqlite, { SCHEMA_VERSION } from '@deepseek-ai/dsh-session-persistence-sqlite' -import { openDatabase, rowToEvent, scanRows, type EventRow } from '../src/schema.ts' +import { + openDatabase, + rowToEvent, + rowToMeta, + scanRows, + SESSION_PERSISTENCE_SQLITE_APPLICATION_ID, + type EventRow, +} from '../src/schema.ts' import { runPersistenceContract, meta, oneTurnLog, appendLog } from '../../session-persistence/tests/contract.ts' import { runCoordinatorContract, type CoordinatorFixture } from '../../session-persistence/tests/coordinator-contract.ts' @@ -150,6 +158,22 @@ describe('scanRows', () => { }) }) +describe('rowToMeta', () => { + it('rejects fractional stored creation metadata', () => { + expect(() => rowToMeta({ + id: 'fractional', + version: 0, + created_at: 1.5, + cwd: null, + parent_session: null, + seed_length: null, + incarnation: 'fractional', + revision: 1, + delegation_depth: null, + })).toThrow('stored session createdAt must be a non-negative safe integer') + }) +}) + describe('SessionPersistenceSqlite: durability and crash semantics', () => { it('rejects a stored v0 log containing a legacy request/header-delta event', async () => { const path = await freshDbPath() @@ -304,6 +328,121 @@ describe('SessionPersistenceSqlite: durability and crash semantics', () => { expect(() => openDatabase(olderPath, 'wal')).toThrow(/incompatible with this build/) }) + it('rejects a table-backed unversioned database before stamping or changing journal mode', async () => { + const path = await freshDbPath() + const legacy = new DatabaseSync(path) + legacy.exec('CREATE TABLE sessions (id TEXT PRIMARY KEY)') + legacy.close() + + expect(() => openDatabase(path, 'wal')).toThrow(/unversioned schema or application identity/) + + const unchanged = new DatabaseSync(path) + expect(unchanged.prepare('PRAGMA user_version').get()).toEqual({ user_version: 0 }) + expect(unchanged.prepare('PRAGMA journal_mode').get()).toEqual({ journal_mode: 'delete' }) + expect(unchanged.prepare( + "SELECT name FROM sqlite_schema WHERE type = 'table' AND name = 'sessions'", + ).get()).toEqual({ name: 'sessions' }) + unchanged.close() + }) + + it('counts a sqliteX table as user-owned instead of mistaking it for SQLite metadata', async () => { + const path = await freshDbPath() + const unrelated = new DatabaseSync(path) + unrelated.exec('CREATE TABLE sqliteX (value TEXT)') + unrelated.exec("INSERT INTO sqliteX VALUES ('safe')") + unrelated.close() + + expect(() => openDatabase(path, 'wal')).toThrow(/unversioned schema or application identity/) + + const unchanged = new DatabaseSync(path) + expect(unchanged.prepare('SELECT value FROM sqliteX').get()).toEqual({ value: 'safe' }) + expect(unchanged.prepare('PRAGMA application_id').get()).toEqual({ application_id: 0 }) + expect(unchanged.prepare('PRAGMA user_version').get()).toEqual({ user_version: 0 }) + expect(unchanged.prepare('PRAGMA journal_mode').get()).toEqual({ journal_mode: 'delete' }) + unchanged.close() + }) + + it('rejects view-only and foreign-application unversioned databases without mutation', async () => { + const viewPath = await freshDbPath() + const viewOnly = new DatabaseSync(viewPath) + viewOnly.exec('CREATE VIEW foreign_view AS SELECT 1 AS value') + viewOnly.close() + + expect(() => openDatabase(viewPath, 'wal')).toThrow(/unversioned schema or application identity/) + const unchangedView = new DatabaseSync(viewPath) + expect(unchangedView.prepare('PRAGMA journal_mode').get()).toEqual({ journal_mode: 'delete' }) + expect(unchangedView.prepare( + "SELECT type FROM sqlite_schema WHERE name = 'foreign_view'", + ).get()).toEqual({ type: 'view' }) + unchangedView.close() + + const applicationPath = await freshDbPath() + const foreignApplication = new DatabaseSync(applicationPath) + foreignApplication.exec('PRAGMA application_id = 12345') + foreignApplication.close() + + expect(() => openDatabase(applicationPath, 'wal')).toThrow(/unversioned schema or application identity/) + const unchangedApplication = new DatabaseSync(applicationPath) + expect(unchangedApplication.prepare('PRAGMA application_id').get()).toEqual({ application_id: 12345 }) + expect(unchangedApplication.prepare('PRAGMA user_version').get()).toEqual({ user_version: 0 }) + expect(unchangedApplication.prepare('PRAGMA journal_mode').get()).toEqual({ journal_mode: 'delete' }) + unchangedApplication.close() + }) + + it('rejects a current-version database with a foreign application identity', async () => { + const path = await freshDbPath() + const foreign = new DatabaseSync(path) + foreign.exec('PRAGMA application_id = 12345') + foreign.exec(`PRAGMA user_version = ${SCHEMA_VERSION}`) + foreign.close() + + expect(() => openDatabase(path, 'wal')).toThrow(/has application id 12345/) + + const unchanged = new DatabaseSync(path) + expect(unchanged.prepare('PRAGMA application_id').get()).toEqual({ application_id: 12345 }) + expect(unchanged.prepare('PRAGMA user_version').get()).toEqual({ user_version: SCHEMA_VERSION }) + expect(unchanged.prepare('PRAGMA journal_mode').get()).toEqual({ journal_mode: 'delete' }) + unchanged.close() + }) + + it('rolls back schema objects and identity stamps when initialization fails', async () => { + const path = await freshDbPath() + const conflicting = new DatabaseSync(path) + conflicting.exec(`PRAGMA application_id = ${SESSION_PERSISTENCE_SQLITE_APPLICATION_ID}`) + conflicting.exec(`PRAGMA user_version = ${SCHEMA_VERSION}`) + conflicting.exec("CREATE VIEW persistence_state AS SELECT 1 AS singleton, 'foreign' AS store_id") + conflicting.close() + + expect(() => openDatabase(path, 'wal')).toThrow() + + const unchanged = new DatabaseSync(path) + expect(unchanged.prepare( + "SELECT type FROM sqlite_schema WHERE name = 'persistence_state'", + ).get()).toEqual({ type: 'view' }) + expect(unchanged.prepare( + "SELECT type FROM sqlite_schema WHERE name = 'sessions'", + ).get()).toBeUndefined() + expect(unchanged.prepare( + "SELECT type FROM sqlite_schema WHERE name = 'events'", + ).get()).toBeUndefined() + expect(unchanged.prepare('PRAGMA application_id').get()) + .toEqual({ application_id: SESSION_PERSISTENCE_SQLITE_APPLICATION_ID }) + expect(unchanged.prepare('PRAGMA user_version').get()).toEqual({ user_version: SCHEMA_VERSION }) + expect(unchanged.prepare('PRAGMA journal_mode').get()).toEqual({ journal_mode: 'delete' }) + unchanged.close() + }) + + it('stamps the persistence application identity with the schema version', async () => { + const path = await freshDbPath() + openDatabase(path, 'wal').close() + + const db = new DatabaseSync(path) + expect(db.prepare('PRAGMA application_id').get()) + .toEqual({ application_id: SESSION_PERSISTENCE_SQLITE_APPLICATION_ID }) + expect(db.prepare('PRAGMA user_version').get()).toEqual({ user_version: SCHEMA_VERSION }) + db.close() + }) + it('rejects a sibling v3 database (the merge-collided version) rather than opening it against missing columns', async () => { // Version 3 identified two incompatible sibling layouts, so it is always rejected. const path = await freshDbPath() @@ -442,7 +581,7 @@ describe('SessionPersistenceSqlite: durability and crash semantics', () => { }) it('exposes the schema version constant', () => { - expect(SCHEMA_VERSION).toBe(8) + expect(SCHEMA_VERSION).toBe(10) }) it('keeps the revision stable for an empty repair hook', async () => { diff --git a/packages/session-persistence/session-persistence/src/coordinator.ts b/packages/session-persistence/session-persistence/src/coordinator.ts index fb46aa4877..089a4f7d83 100644 --- a/packages/session-persistence/session-persistence/src/coordinator.ts +++ b/packages/session-persistence/session-persistence/src/coordinator.ts @@ -178,6 +178,9 @@ export class PersistenceCoordinator<TornMarker = unknown> { if (snapshot === undefined) { return Promise.reject(new TypeError('session metadata must be losslessly JSON-serializable')) } + if (!Number.isSafeInteger(snapshot.createdAt) || snapshot.createdAt < 0) { + return Promise.reject(new TypeError('session metadata createdAt must be a non-negative safe integer')) + } return this.serialize(snapshot.id, () => this.createCore(snapshot)) } diff --git a/packages/session-persistence/session-persistence/tests/contract.ts b/packages/session-persistence/session-persistence/tests/contract.ts index ae07bf77aa..cf72f4d028 100644 --- a/packages/session-persistence/session-persistence/tests/contract.ts +++ b/packages/session-persistence/session-persistence/tests/contract.ts @@ -84,6 +84,22 @@ export function runPersistenceContract(name: string, make: () => Promise<Contrac } }) + it('rejects a fractional creation timestamp without reserving its session id', async () => { + const { persistence, dispose } = await make() + try { + const m = { ...meta('fractional-created-at'), createdAt: 1.5 } + await expect(persistence.create(m)) + .rejects.toThrow('session metadata createdAt must be a non-negative safe integer') + + const valid = meta('fractional-created-at') + await persistence.create(valid) + await persistence.append(valid.id, oneTurnLog()) + expect((await persistence.load(valid.id)).meta.createdAt).toBe(valid.createdAt) + } finally { + await dispose() + } + }) + it('crash recovery: load preserves an interrupted (unclosed) turn and closes it with turn/end {interrupted}', async () => { const { persistence, dispose } = await make() try { diff --git a/packages/session-query/session-query-sqlite/src/schema.ts b/packages/session-query/session-query-sqlite/src/schema.ts index b88e04b536..47f6374ba6 100644 --- a/packages/session-query/session-query-sqlite/src/schema.ts +++ b/packages/session-query/session-query-sqlite/src/schema.ts @@ -5,7 +5,7 @@ import { mkdir, open } from 'node:fs/promises' import { dirname, resolve } from 'node:path' /** Current derived-index schema version. Incompatible versions reset in place. */ -export const SESSION_QUERY_SQLITE_SCHEMA_VERSION = 3 +export const SESSION_QUERY_SQLITE_SCHEMA_VERSION = 5 /** SQLite application id protecting unrelated databases from derived resets. */ export const SESSION_QUERY_SQLITE_APPLICATION_ID = 0x44534851 @@ -78,7 +78,7 @@ export async function openSearchDatabase(path: string, journalMode: JournalMode) function listUserTables(db: DatabaseSync): string[] { const rows = db.prepare( - "SELECT name FROM sqlite_master WHERE type = 'table' AND name NOT LIKE 'sqlite_%' ORDER BY name", + "SELECT name FROM sqlite_master WHERE type = 'table' AND name NOT GLOB 'sqlite_*' ORDER BY name", ).all() as Array<{ name: string }> return rows.map(row => row.name) } diff --git a/packages/session-query/session-query-sqlite/tests/sqlite.spec.ts b/packages/session-query/session-query-sqlite/tests/sqlite.spec.ts index 1923c6f3eb..1812a85428 100644 --- a/packages/session-query/session-query-sqlite/tests/sqlite.spec.ts +++ b/packages/session-query/session-query-sqlite/tests/sqlite.spec.ts @@ -1148,6 +1148,26 @@ describe('SQLite schema, cancellation, and real persistence integration', () => expect(stillForeign.prepare('PRAGMA journal_mode').get()).toEqual({ journal_mode: 'wal' }) stillForeign.close() + const wildcardPath = await temporaryPath('sqlite-wildcard.db') + const wildcard = new DatabaseSync(wildcardPath) + wildcard.exec('PRAGMA journal_mode = WAL') + wildcard.exec('CREATE TABLE sqliteX(value TEXT)') + wildcard.exec("INSERT INTO sqliteX VALUES ('safe')") + wildcard.close() + const wildcardCtx = new Context() + await wildcardCtx.plugin(SessionStore) + await expect(wildcardCtx.plugin(SessionQuerySqlite, { + path: wildcardPath, + journalMode: 'delete', + })).rejects.toThrow(expectCode('SESSION_QUERY_INDEX_FAILED')) + expect(wildcardCtx.sessionQuery).toBeUndefined() + const stillWildcard = new DatabaseSync(wildcardPath) + expect(stillWildcard.prepare('SELECT value FROM sqliteX').get()).toEqual({ value: 'safe' }) + expect(stillWildcard.prepare('PRAGMA application_id').get()).toEqual({ application_id: 0 }) + expect(stillWildcard.prepare('PRAGMA user_version').get()).toEqual({ user_version: 0 }) + expect(stillWildcard.prepare('PRAGMA journal_mode').get()).toEqual({ journal_mode: 'wal' }) + stillWildcard.close() + const otherAppPath = await temporaryPath('other-app.db') const otherApp = new DatabaseSync(otherAppPath) otherApp.exec('PRAGMA application_id = 123') diff --git a/packages/session-query/session-query/src/extraction.ts b/packages/session-query/session-query/src/extraction.ts index 5bf132a15e..4cbe850352 100644 --- a/packages/session-query/session-query/src/extraction.ts +++ b/packages/session-query/session-query/src/extraction.ts @@ -14,7 +14,6 @@ export function extractSessionEventText(event: SessionEvent): string { switch (event.type) { case 'user/message': case 'assistant/message': - case 'context/message': case 'steering/message': return contentText(event.data.content) case 'prompt/blocked': diff --git a/packages/session-query/session-query/tests/search-helpers.spec.ts b/packages/session-query/session-query/tests/search-helpers.spec.ts index 327048b8c1..fef9e25ad0 100644 --- a/packages/session-query/session-query/tests/search-helpers.spec.ts +++ b/packages/session-query/session-query/tests/search-helpers.spec.ts @@ -44,7 +44,7 @@ describe('session-query semantic extraction', () => { const events: SessionEvent[] = [ { type: 'user/message', seq: 0, time: 1, data: { content: messageContent, source: { kind: 'user' } }, surfaceOp: 'append' }, { type: 'assistant/message', seq: 1, time: 2, data: { turn: 1, step: 1, content: messageContent, provenance: { provider: 'mock', model: 'mock' } }, surfaceOp: 'append' }, - { type: 'context/message', seq: 2, time: 3, data: { content: messageContent, source: { kind: 'plugin', plugin: 'test' } }, surfaceOp: 'append' }, + { type: 'user/message', seq: 2, time: 3, data: { content: messageContent, source: { kind: 'plugin', plugin: 'test' } }, surfaceOp: 'append' }, { type: 'steering/message', seq: 3, time: 4, data: { turn: 1, content: messageContent, source: { kind: 'user' } }, surfaceOp: 'append' }, { type: 'prompt/blocked', seq: 4, time: 5, data: { content: [{ type: 'text', text: 'unsafe' }], source: { kind: 'user' }, reason: 'policy' } }, { type: 'tool/call', seq: 5, time: 6, data: { turn: 1, step: 1, callId, name: 'bash', arguments: '{"cmd":"pwd"}' } }, diff --git a/packages/session-query/session-query/tests/tracing.spec.ts b/packages/session-query/session-query/tests/tracing.spec.ts index 2f115d2dc9..b23292bc3d 100644 --- a/packages/session-query/session-query/tests/tracing.spec.ts +++ b/packages/session-query/session-query/tests/tracing.spec.ts @@ -116,7 +116,7 @@ function appendTraceEvents(session: Session): void { { surfaceOp: { op: 'replace', start: 3, end: 3 }, sourceEventSeqs: [3, 2] }, ) session.append( - 'context/message', + 'user/message', { content: [{ type: 'text', text: 'context' }], source: { kind: 'plugin', plugin: 'test' } }, { surfaceOp: 'append' }, ) @@ -318,14 +318,14 @@ describe('session event tracing', () => { const live = ctx.sessions.create(durable.id, { meta: { createdAt: 1, cwd: '/same' } }) live.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) live.append( - 'context/message', + 'user/message', { content: [{ type: 'text', text: 'live' }], source: { kind: 'plugin', plugin: 'test' } }, { surfaceOp: 'append' }, ) TracePersistence.listFailure = new Error('list unavailable') TracePersistence.inspectFailure = new Error('inspect unavailable') await expect(ctx.sessionQuery.traceEvent({ sessionId: durable.id, seq: 1 })) - .resolves.toMatchObject({ target: { type: 'context/message' } }) + .resolves.toMatchObject({ target: { type: 'user/message' } }) expect([TracePersistence.listCalls, TracePersistence.inspectCalls]).toEqual([1, 1]) TracePersistence.reset([{ meta: durable, events: [appendEvent(0)] }]) diff --git a/packages/subagent/subagent-fork/tests/multi-subagent.spec.ts b/packages/subagent/subagent-fork/tests/multi-subagent.spec.ts index 6f091c2bf6..6882d324fc 100644 --- a/packages/subagent/subagent-fork/tests/multi-subagent.spec.ts +++ b/packages/subagent/subagent-fork/tests/multi-subagent.spec.ts @@ -64,7 +64,7 @@ describe('multi-subagent coexistence (spawn + fork on one context)', () => { ]) // Parent does one real turn first, so the fork has a completed turn to seed. - parent.send([{ type: 'text', text: 'parent q1' }]) + parent.followup([{ type: 'text', text: 'parent q1' }]) await parent.whenIdle() const parentPrefixLen = parent.session.events.length @@ -93,7 +93,7 @@ describe('multi-subagent coexistence (spawn + fork on one context)', () => { await forkRun.dispose() // The parent is unaffected and keeps working after both delegations. - parent.send([{ type: 'text', text: 'parent q2' }]) + parent.followup([{ type: 'text', text: 'parent q2' }]) await parent.whenIdle() const lastParentMessage = parent.session.events.findLast(e => e.type === 'assistant/message') expect(lastParentMessage?.type === 'assistant/message' && text(lastParentMessage.data.content)).toBe('parent turn two') diff --git a/packages/subagent/subagent-fork/tests/subagent-fork.spec.ts b/packages/subagent/subagent-fork/tests/subagent-fork.spec.ts index 046c6ee8fe..cf5848e625 100644 --- a/packages/subagent/subagent-fork/tests/subagent-fork.spec.ts +++ b/packages/subagent/subagent-fork/tests/subagent-fork.spec.ts @@ -89,9 +89,9 @@ describe('dsh-subagent-fork', () => { it('seeds every completed parent turn through the last turn/end', async () => { const { ctx, parent } = await setup([textResponse('first'), textResponse('second'), textResponse('child')]) - parent.send([{ type: 'text', text: 'q1' }]) + parent.followup([{ type: 'text', text: 'q1' }]) await parent.whenIdle() - parent.send([{ type: 'text', text: 'q2' }]) + parent.followup([{ type: 'text', text: 'q2' }]) await parent.whenIdle() const parentPrefixLen = parent.session.events.length @@ -108,7 +108,7 @@ describe('dsh-subagent-fork', () => { // Parent runs one turn, then we fork. The child's seeded log should contain // the parent's first turn, and the child should run its own new turn on top. const { ctx, parent } = await setup([textResponse('parent answer'), textResponse('child answer')]) - parent.send([{ type: 'text', text: 'parent question' }]) + parent.followup([{ type: 'text', text: 'parent question' }]) await parent.whenIdle() const parentPrefixLen = parent.session.events.length @@ -137,10 +137,10 @@ describe('dsh-subagent-fork', () => { // open (a hanging model call), and fork while it's in flight. The seed must stop after the // balanced first turn; including the open turn would fail invariant replay during start. const { ctx, parent } = await setup([textResponse('done'), 'hang', textResponse('child')]) - parent.send([{ type: 'text', text: 'q1' }]) + parent.followup([{ type: 'text', text: 'q1' }]) await parent.whenIdle() // Start a second turn that hangs (open turn/start + open step, never ends). - parent.send([{ type: 'text', text: 'q2' }]) + parent.followup([{ type: 'text', text: 'q2' }]) await new Promise(r => setTimeout(r, 20)) // let the hanging turn open // Forking now must NOT throw (the open second turn is excluded from the seed). @@ -164,7 +164,7 @@ describe('dsh-subagent-fork', () => { textResponse('parent turn'), toolCallResponse('c1', STRUCTURED_OUTPUT_TOOL, { answer: 9 }), ]) - parent.send([{ type: 'text', text: 'warm up' }]) + parent.followup([{ type: 'text', text: 'warm up' }]) await parent.whenIdle() const run = await start(ctx, 'fork', { prompt: [{ type: 'text', text: 'report structured' }], @@ -183,7 +183,7 @@ describe('dsh-subagent-fork', () => { // `readResult` must scan only child-owned events after the seed. The child emits no assistant // message, so scanning the whole log would incorrectly return the parent's distinctive text. const { ctx, parent } = await setup([textResponse('parent stale'), emptyStop]) - parent.send([{ type: 'text', text: 'parent question' }]) + parent.followup([{ type: 'text', text: 'parent question' }]) await parent.whenIdle() const run = await start(ctx, 'fork', { prompt: [{ type: 'text', text: 'child question' }], parent }) diff --git a/packages/subagent/subagent-inprocess/README.md b/packages/subagent/subagent-inprocess/README.md index 7776b2af3f..48c72e9cf0 100644 --- a/packages/subagent/subagent-inprocess/README.md +++ b/packages/subagent/subagent-inprocess/README.md @@ -11,7 +11,7 @@ The driver follows this sequence: 1. Validate the parent depth and optional absolute `maxDepth`, then derive child depth as parent depth plus one and persist it in the child session header. 2. Call `parent.ctx.agents.create` directly, passing the required request signal into the factory's creation transaction. 3. During that transaction's unpublished setup window, install the requested persona, tool restriction, and structured-output runtime. -4. Publish the child, retain the returned `AgentHandle`, and drive one task with `child.send(prompt)` followed by `child.whenIdle()`. +4. Publish the child, retain the returned `AgentHandle`, and drive one task with `child.followup(prompt)` followed by `child.whenIdle()`. 5. Read the child's own last assistant message and latest message-triggered turn reason, excluding any fork seed and later plugin-owned zero-step turns. The child gets the parent's working-directory/session lineage and inherits the parent model unless `request.agentOptions` overrides it. It gets a fresh flat registration scope: parent ownership does not import parent tool restrictions or establish an authority subset. diff --git a/packages/subagent/subagent-inprocess/src/index.ts b/packages/subagent/subagent-inprocess/src/index.ts index e83b397bb5..71bc7e42a6 100644 --- a/packages/subagent/subagent-inprocess/src/index.ts +++ b/packages/subagent/subagent-inprocess/src/index.ts @@ -141,7 +141,7 @@ export async function startInProcessRun( const result: Promise<SubagentResult> = (async () => { try { - child.send(request.prompt) + child.followup(request.prompt) await child.whenIdle() return readResult( child, diff --git a/packages/subagent/subagent-inprocess/tests/structured.spec.ts b/packages/subagent/subagent-inprocess/tests/structured.spec.ts index 1c08488fc2..bb4cf32544 100644 --- a/packages/subagent/subagent-inprocess/tests/structured.spec.ts +++ b/packages/subagent/subagent-inprocess/tests/structured.spec.ts @@ -522,7 +522,7 @@ describe('in-process structured output', () => { textResponse('parent answer'), toolCallResponse('c1', STRUCTURED_OUTPUT_TOOL, { answer: 1 }), ]) - parent.send([{ type: 'text', text: 'hello' }]) + parent.followup([{ type: 'text', text: 'hello' }]) await parent.whenIdle() expect(adapter.requests[0]!.system ?? '').not.toContain(STRUCTURED_OUTPUT_INSTRUCTION) const run = await ctx.subagents.start('spawn', structuredRequest(parent)) @@ -538,7 +538,7 @@ describe('in-process structured output', () => { describe('scoped registration (each child owns its capture tool)', () => { it('a plain agent never sees the tool: nothing is registered globally at all', async () => { const { ctx, parent, adapter } = await setup([textResponse('parent answer')]) - parent.send([{ type: 'text', text: 'hello' }]) + parent.followup([{ type: 'text', text: 'hello' }]) await parent.whenIdle() // Scoped registration: the global view has no capture tool, ever. expect(ctx.tools.get(STRUCTURED_OUTPUT_TOOL)).toBeUndefined() @@ -552,7 +552,7 @@ describe('in-process structured output', () => { // Child turn: must see it, with the run's schema. toolCallResponse('c1', STRUCTURED_OUTPUT_TOOL, { answer: 42 }), ]) - parent.send([{ type: 'text', text: 'hello' }]) + parent.followup([{ type: 'text', text: 'hello' }]) await parent.whenIdle() expect(toolNames(adapter.requests[0]!)).not.toContain(STRUCTURED_OUTPUT_TOOL) @@ -630,7 +630,7 @@ describe('in-process structured output', () => { it('a non-structured agent request keeps tools ABSENT when it had none (no tools: [] materialized)', async () => { const { parent, adapter } = await setup([textResponse('plain')]) - parent.send([{ type: 'text', text: 'q' }]) + parent.followup([{ type: 'text', text: 'q' }]) await parent.whenIdle() const request = adapter.requests[0]! expect(request.tools).toBeUndefined() diff --git a/packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts b/packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts index 1cfb809601..ce91480ea8 100644 --- a/packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts +++ b/packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts @@ -68,7 +68,7 @@ describe('startInProcessRun', () => { turn, trigger: { kind: 'injection', source: { kind: 'plugin', plugin: 'late-metadata' } }, }) - session.append('context/message', { + session.append('user/message', { content: [{ type: 'text', text: 'late metadata' }], source: { kind: 'plugin', plugin: 'late-metadata' }, }, { surfaceOp: 'append' }) @@ -87,7 +87,7 @@ describe('startInProcessRun', () => { it('seeds a forked child but reads only the child-owned output', async () => { const { ctx, parent } = await setup([textResponse('parent answer'), textResponse('child answer')]) - parent.send([{ type: 'text', text: 'parent question' }]) + parent.followup([{ type: 'text', text: 'parent question' }]) await parent.whenIdle() const seed = parent.session.events.slice() const run = await startInProcessRun(request(parent), { seed }) diff --git a/packages/subagent/subagent-spawn/tests/spawn.e2e.ts b/packages/subagent/subagent-spawn/tests/spawn.e2e.ts index 89efb2b815..8fbecdc976 100644 --- a/packages/subagent/subagent-spawn/tests/spawn.e2e.ts +++ b/packages/subagent/subagent-spawn/tests/spawn.e2e.ts @@ -31,7 +31,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('spawn backend with-key smoke', ( ctx = await spawnHarness(workdir) const parent = ctx.agentLoop.create(SessionId('e2e-parent'), { provider: 'deepseek', model: 'deepseek-v4-flash' }) - parent.send([{ type: 'text', text: + parent.followup([{ type: 'text', text: 'Use the subagent tool to delegate this exact task: "Use the bash tool to write the text ' + 'SUBAGENT_WAS_HERE into a file named proof.txt in the current directory." ' + 'After the subagent finishes, tell me it is done.' }]) diff --git a/packages/subagent/subagent-spawn/tests/subagent-spawn.spec.ts b/packages/subagent/subagent-spawn/tests/subagent-spawn.spec.ts index 8952c29be7..c83eca75ab 100644 --- a/packages/subagent/subagent-spawn/tests/subagent-spawn.spec.ts +++ b/packages/subagent/subagent-spawn/tests/subagent-spawn.spec.ts @@ -95,7 +95,7 @@ describe('dsh-subagent-spawn', () => { it('a fresh child does NOT inherit the parent conversation (its log starts empty before the prompt)', async () => { // Drive the parent through one real turn so it has history, THEN spawn. const { ctx, parent } = await setup([textResponse('parent turn'), textResponse('child sees nothing')]) - parent.send([{ type: 'text', text: 'parent prompt' }]) + parent.followup([{ type: 'text', text: 'parent prompt' }]) await parent.whenIdle() const parentEventCount = parent.session.events.length expect(parentEventCount).toBeGreaterThan(0) @@ -188,10 +188,10 @@ describe('dsh-subagent-spawn', () => { expect(published).toEqual([]) }) - it('a cancel from agent/queued maps a no-turn child log to aborted', async () => { + it('a cancel from agent/inbox/enqueue maps a no-turn child log to aborted', async () => { const { ctx, parent } = await setup([]) const controller = new AbortController() - ctx.on('agent/queued', () => { controller.abort('queued-window') }) + ctx.on('agent/inbox/enqueue', () => { controller.abort('queued-window') }) const run = await start(ctx, 'spawn', { prompt: [{ type: 'text', text: 'p' }], parent, signal: controller.signal }) const result = await run.result expect(result).toMatchObject({ stopReason: 'aborted', output: [] }) @@ -372,7 +372,7 @@ describe('dsh-subagent-spawn', () => { textResponse('parent answer'), textResponse('child answer'), ]) - parent.send([{ type: 'text', text: 'hi' }]) + parent.followup([{ type: 'text', text: 'hi' }]) await parent.whenIdle() const run = await start(ctx, 'spawn', { diff --git a/packages/support/invariants/README.md b/packages/support/invariants/README.md index e4866212b6..2dd0cde142 100644 --- a/packages/support/invariants/README.md +++ b/packages/support/invariants/README.md @@ -34,7 +34,7 @@ The current executable companions protect these relationships: | Companion | Checks | |---|---| -| `dsh-session`, `dsh-agent`, `dsh-scope`, `dsh-agent-loop` | Session enclosure and call/result trace, agent-status transitions, scoped subjects, and model-request reconstruction. | +| `dsh-session`, `dsh-agent`, `dsh-scope`, `dsh-agent-loop` | Session enclosure and call/result trace, agent-status transitions, inbox FIFO conservation, scoped subjects, and model-request reconstruction. | | `dsh-llm`, `dsh-llm-retry`, `dsh-tools`, `dsh-system-prompt` | Stream grammar, durable retry position and bounds, tool-pipeline stages and frozen results, and authoritative prompt-assembly data. | | `dsh-compact`, `dsh-hook-protocol`, `dsh-sandbox-policy` | Durable compaction and hook pairing, compaction metadata, and sandbox-mode vocabulary. | | `dsh-fs`, `dsh-subagent`, `dsh-workflow` | Filesystem event identity, provider/child pairing, and workflow/agent lifecycle identity. | diff --git a/packages/tasks/tasks/tests/tasks.spec.ts b/packages/tasks/tasks/tests/tasks.spec.ts index 34506b3a47..015f1c4f2b 100644 --- a/packages/tasks/tasks/tests/tasks.spec.ts +++ b/packages/tasks/tasks/tests/tasks.spec.ts @@ -1,7 +1,7 @@ import { describe, expect, expectTypeOf, it, vi } from 'vitest' import { Context } from 'cordis' import { Session, SessionId } from '@deepseek-ai/dsh-session' -import AgentRegistry from '@deepseek-ai/dsh-agent' +import AgentRegistry, { AgentMessageId } from '@deepseek-ai/dsh-agent' import type { Agent } from '@deepseek-ai/dsh-agent' import TaskService, { TaskId } from '@deepseek-ai/dsh-tasks' import type { TaskHooks, TaskKind, TaskOutcome, TaskSnapshot, TaskStart } from '@deepseek-ai/dsh-tasks' @@ -23,9 +23,11 @@ function stubAgent(ctx: Context, rawId: string): Agent { session: new Session(id), status: 'idle' as const, ctx: scopeFiber.ctx, - send() {}, - steer() {}, - inject() {}, + followup: () => AgentMessageId('stub'), + queue: () => AgentMessageId('stub'), + steer: () => AgentMessageId('stub'), + inject: () => AgentMessageId('stub'), + send: () => AgentMessageId('stub'), cancel() {}, whenIdle() { return Promise.resolve() }, } diff --git a/packages/todo/tool-todo/tests/integration.spec.ts b/packages/todo/tool-todo/tests/integration.spec.ts index 869c1183f2..fe09af9730 100644 --- a/packages/todo/tool-todo/tests/integration.spec.ts +++ b/packages/todo/tool-todo/tests/integration.spec.ts @@ -59,7 +59,7 @@ describe('todo_write tool through the agent loop', () => { const ctx = await harness(adapter) const agent = ctx.agentLoop.create(SessionId('it-todo'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'plan a two-step task' }]) + agent.followup([{ type: 'text', text: 'plan a two-step task' }]) await waitForIdle(ctx, agent) const log = agent.session.events @@ -87,7 +87,7 @@ describe('todo_write tool through the agent loop', () => { const ctx = await harness(adapter) const agent = ctx.agentLoop.create(SessionId('it-todo-2'), { provider: 'mock', model: 'mock' }) - agent.send([{ type: 'text', text: 'plan then update' }]) + agent.followup([{ type: 'text', text: 'plan then update' }]) await waitForIdle(ctx, agent) const todoEvents = agent.session.events.filter(e => e.type === 'todo/write') diff --git a/packages/ui/acp/README.md b/packages/ui/acp/README.md index 3a8576df74..f135e42553 100644 --- a/packages/ui/acp/README.md +++ b/packages/ui/acp/README.md @@ -29,7 +29,7 @@ The `initialize` handshake reports a fixed server identity (`agentInfo: { name: | `session/new` | `ctx.agents.create({ sessionId, meta:{cwd} })` | creates a new session/agent; N concurrent sessions are allowed, keyed by id; advertises the effective command snapshot; `cwd` must be absolute (it becomes the session's workspace — see Per-session cwd); non-empty `additionalDirectories` and `mcpServers` rejected | | `session/load` | `ctx.agents.resume(...)` | reserves the id, verifies the persisted cwd, resumes, replays user, assistant, tool, and title events, and re-advertises commands | | `session/list` | `ctx.sessionQuery` | returns live-preferred newest-first sessions with absolute cwd and optional folded title; supports exact normalized cwd filtering, returns no cursor, and rejects supplied cursors | -| `session/prompt` | `ctx.commands.execute()` or `agent.send()` | a flattened prompt beginning with `/` stays in the direct command plane; ordinary prompts support ACP `text` and `resource_link`; `dsh-session:` links and inline mentions are snapshotted through optional `ctx.sessionReferences` before enqueue; unsupported content, unavailable reference capability, failed snapshots, and empty prompts are rejected; one request is in flight per session and settles on the owning turn's end, with an error turn rejecting the RPC | +| `session/prompt` | `ctx.commands.execute()` or `agent.followup()` | a flattened prompt beginning with `/` stays in the direct command plane; ordinary prompts support ACP `text` and `resource_link`; `dsh-session:` links and inline mentions are snapshotted through optional `ctx.sessionReferences` before enqueue; unsupported content, unavailable reference capability, failed snapshots, and empty prompts are rejected; one request is in flight per session and settles on the owning turn's end, with an error turn rejecting the RPC | | `session/cancel` | command `AbortSignal` or `agent.cancel()` | aborts the exact direct command, or applies the queue-aware agent cancel and settles its prompt `cancelled`; one session never cancels another | | `session/update` | `session/event` | streams user replay, assistant text/reasoning, retry/failure attempt markers, tool render intents, and `session_info_update` title revisions | | `elicitation/create` | `ctx.userInteraction.ask()` | maps `ask_user_question` questions to ACP form elicitations; option descriptions are shown in enum titles, `multi_select` uses ACP array enums, optionless requests use a required `custom` field, and a non-empty custom answer overrides any selected choice | diff --git a/packages/ui/acp/acp-feature-support.md b/packages/ui/acp/acp-feature-support.md index 55d44613c5..3292ee17c4 100644 --- a/packages/ui/acp/acp-feature-support.md +++ b/packages/ui/acp/acp-feature-support.md @@ -23,7 +23,7 @@ The bridge implements the **core prompt-turn loop** for N concurrent sessions: i | `session/load` | S | ✅ | ✅ | ✅ | Maps to `agents.resume` + full event-log replay; validates persisted `cwd` before constructing the agent. | | `session/resume` | S | ❌ | ✅ | ✅ | Reconnect WITHOUT replay; gated by `sessionCapabilities.resume`. Not advertised. | | `session/close` | S | ❌ | ✅ | ✅ | No `session/close` handler — the SDK dispatch returns `method_not_found`. The bridge tears sessions down on client disconnect / Cordis disposal (cross-cutting, see [§8](#8-cross-cutting)), but that is not the on-demand per-session method. | -| `session/prompt` | S | ✅ | ✅ | ✅ | A flattened prompt beginning with `/` dispatches through `ctx.commands` without a model request; ordinary input maps to `agent.send`. One request is in flight per session. | +| `session/prompt` | S | ✅ | ✅ | ✅ | A flattened prompt beginning with `/` dispatches through `ctx.commands` without a model request; ordinary input maps to `agent.followup`. One request is in flight per session. | | `session/cancel` | S | ✅ | ✅ | ✅ | Aborts the exact direct command, or applies queue-aware `agent.cancel` and settles its prompt `cancelled`, scoped to one session. | | `session/set_mode` | S | ✅ | ✅ | ✅ | Composed opportunistically: with `@deepseek-ai/dsh-plan-mode` mounted, `session/new`/`session/load` advertise the fixed `default` / `plan` projection and `session/set_mode` records the boolean pending intent (optimistic `current_mode_update`; logged `plan/mode` lands at the turn boundary). Without the plugin: no `modes` advertised, `set_mode` rejected (see [§6 Modes](#6-session-modes--config-options--models)). | | `session/set_config_option` | S | ✅ | ✅ | ✅ | A provider/model select is present for a complete registered target; one `permission` select is added when `ctx.permission` is composed. Every response carries the complete refreshed state. | diff --git a/packages/ui/acp/src/index.ts b/packages/ui/acp/src/index.ts index 8a731a1bf6..dcc32f1c6f 100644 --- a/packages/ui/acp/src/index.ts +++ b/packages/ui/acp/src/index.ts @@ -1056,7 +1056,7 @@ export function apply(ctx: Context, config: AcpConfig): void { } const { text } = referencedPrompt let preparedContent: ContentBlock[] = [{ type: 'text', text }] - let preparedContexts: NonNullable<Parameters<Agent['send']>[1]>['contexts'] = [] + let preparedContexts: NonNullable<Parameters<Agent['followup']>[1]>['contexts'] = [] if (referencedPrompt.references.length > 0) { const sessionReferences = ctx.get('sessionReferences') if (sessionReferences === undefined) { @@ -1081,14 +1081,14 @@ export function apply(ctx: Context, config: AcpConfig): void { } assertOpen() } - // Install the in-flight slot BEFORE send() (send does not synchronously + // Install the in-flight slot BEFORE followup() (followup does not synchronously // flip status to running; the session/event listener records the turn // number and settle/rejects it). Capture the log length now as the // A turn that ends in error rejects this promise (the codec never // produces an error stop reason). const stopReason = await new Promise<StopReason>((resolve, reject) => { rec.inflight = { resolve, reject, turn: undefined } - rec.agent.send(preparedContent, { contexts: preparedContexts }) + rec.agent.followup(preparedContent, { contexts: preparedContexts }) }) return { stopReason } }, @@ -1333,8 +1333,8 @@ function validateMcpServers(params: { mcpServers?: unknown[] }): void { * generic fallback (title = tool name, raw args as input) when no registry is * available (e.g. pure translator tests). * - * Other event types (turn/step boundaries, context/message, …) produce - * no client update. + * Other event types (turn/step boundaries, injected-context user messages, …) + * produce no client update. * @param sessionId - the ACP session id stamped on every emitted notification. * @param event - the harness session event to translate. * @param notify - sink for each produced `session/update` notification; called @@ -1374,6 +1374,9 @@ export function streamSessionEventUpdate( } case 'user/message': { if (!includeUserMessages) return + // Only a direct human prompt replays as a user message; injected context + // (plugin/goal source) is not the user's turn and produces no update. + if (event.data.source.kind !== 'user') return // Replay the user's prompt so a loaded session shows both sides of each // turn. Live prompt turns suppress this path to avoid duplicating what // the client just sent. @@ -1420,7 +1423,7 @@ export function streamSessionEventUpdate( notify({ sessionId, update: { sessionUpdate: 'agent_message_chunk', content: { type: 'text', text } } }) return } - // non-error turn/step boundaries, context/message, steering, + // non-error turn/step boundaries, injected-context user messages, steering, // assistant/message — no direct ACP client update. default: return diff --git a/packages/ui/acp/tests/bridge.spec.ts b/packages/ui/acp/tests/bridge.spec.ts index 1e15910ce7..6e24acce24 100644 --- a/packages/ui/acp/tests/bridge.spec.ts +++ b/packages/ui/acp/tests/bridge.spec.ts @@ -383,7 +383,7 @@ describe('acp bridge', () => { }, }], }) - expect(target.events.some(event => event.type === 'context/message')).toBe(false) + expect(target.events.some(event => event.type === 'user/message' && event.data.source.kind !== 'user')).toBe(false) const request = JSON.stringify(harness.adapter.requests[0]?.messages) expect(request).toContain('untrusted, read-only snapshot') expect(request).toContain('source background') diff --git a/packages/ui/acp/tests/dispose.spec.ts b/packages/ui/acp/tests/dispose.spec.ts index 8baf076d58..bcfb177b16 100644 --- a/packages/ui/acp/tests/dispose.spec.ts +++ b/packages/ui/acp/tests/dispose.spec.ts @@ -264,7 +264,7 @@ describe('acp bridge — disposal & HMR safety', () => { const handle = await harness.ctx.agents.create({ sessionId: SessionId('guard-a'), agentOptions: { provider: 'mock', model: 'mock' }, }) - handle.agent.send([{ type: 'text', text: 'go' }]) + handle.agent.followup([{ type: 'text', text: 'go' }]) await handle.agent.whenIdle() expect(harness.ctx.sessions.get(SessionId('guard-a'))).toBeDefined() @@ -288,7 +288,7 @@ describe('acp bridge — disposal & HMR safety', () => { // Drive a turn that hangs in the model stream, so the loop is mid-turn when // disposed — its exit runs a final session/flush we can gate to hold the // teardown observably in-flight. - handle.agent.send([{ type: 'text', text: 'go' }]) + handle.agent.followup([{ type: 'text', text: 'go' }]) await new Promise(r => setTimeout(r, 30)) expect(handle.agent.status).toBe('running') let releaseFlush!: () => void diff --git a/packages/ui/acp/tests/edges.spec.ts b/packages/ui/acp/tests/edges.spec.ts index fdbaf241e6..ac85fbd7e0 100644 --- a/packages/ui/acp/tests/edges.spec.ts +++ b/packages/ui/acp/tests/edges.spec.ts @@ -30,7 +30,7 @@ describe('acp bridge — demux & config edges', () => { const before = harness.updates.length const { agent: foreign } = await harness.ctx.agents.create({ sessionId: SessionId('foreign-session'), agentOptions: { provider: 'mock', model: 'mock' } }) - foreign.send([{ type: 'text', text: 'hi' }]) + foreign.followup([{ type: 'text', text: 'hi' }]) await foreign.whenIdle() await new Promise(r => setTimeout(r, 10)) diff --git a/packages/ui/acp/tests/turns.spec.ts b/packages/ui/acp/tests/turns.spec.ts index 2535102405..b3dcc22a55 100644 --- a/packages/ui/acp/tests/turns.spec.ts +++ b/packages/ui/acp/tests/turns.spec.ts @@ -285,10 +285,10 @@ describe('acp bridge — turn outcomes', () => { const sessionId = await newSession(harness) const agent = harness.ctx.agents.get(SessionId(sessionId))! // On the queued prompt, synchronously inject a one-shot context turn (idle - // inject writes turn/start{injection} → context/message → turn/end). Fire + // inject writes turn/start{injection} → user/message → turn/end). Fire // once so it lands between install and the prompt turn. let injected = false - harness.ctx.on('agent/queued', (subject) => { + harness.ctx.on('agent/inbox/enqueue', (subject) => { if (subject === agent && !injected) { injected = true agent.inject([{ type: 'text', text: 'ctx note' }], { source: { kind: 'plugin', plugin: 'test' } }) diff --git a/packages/ui/jsonrpc/src/server.ts b/packages/ui/jsonrpc/src/server.ts index 65ca3ed52c..5200a2de13 100644 --- a/packages/ui/jsonrpc/src/server.ts +++ b/packages/ui/jsonrpc/src/server.ts @@ -152,7 +152,7 @@ export class HarnessSdkServer { rec.activePrompt = true try { rec.lastTurnEnd = undefined - rec.handle.agent.send(params.contentBlocks) + rec.handle.agent.followup(params.contentBlocks) await rec.handle.agent.whenIdle() const status = this.finishedStatus(rec.lastTurnEnd) this.transport.notify('session.finished', { diff --git a/packages/ui/jsonrpc/tests/server.spec.ts b/packages/ui/jsonrpc/tests/server.spec.ts index 40dbc81acd..91d3503263 100644 --- a/packages/ui/jsonrpc/tests/server.spec.ts +++ b/packages/ui/jsonrpc/tests/server.spec.ts @@ -5,7 +5,7 @@ import { join } from 'node:path' import { tmpdir } from 'node:os' import { afterEach, describe, expect, it, vi } from 'vitest' import { Context } from 'cordis' -import { type Agent, type AgentHandle } from '@deepseek-ai/dsh-agent' +import { AgentMessageId, type Agent, type AgentHandle } from '@deepseek-ai/dsh-agent' import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import * as agentCore from '@deepseek-ai/dsh-agent-spine-demo' @@ -152,7 +152,7 @@ describe('HarnessSdkServer', () => { meta: { cwd: storageDir }, agentOptions: { provider: 'deepseek', model: 'dsagent-model' }, }) - orphanHandle.agent.send([{ type: 'text', text: 'outside the sdk session map' }]) + orphanHandle.agent.followup([{ type: 'text', text: 'outside the sdk session map' }]) await orphanHandle.agent.whenIdle() await orphanHandle.dispose() expect(llmServer.requests).toHaveLength(3) @@ -170,16 +170,16 @@ describe('HarnessSdkServer', () => { const mainWhenIdle = vi.fn<() => Promise<void>>() .mockReturnValueOnce(firstMainIdle) .mockResolvedValue(undefined) - const mainSend = vi.fn() - const mainAgent = { - send: mainSend, + const mainFollowup = vi.fn<Agent['followup']>().mockReturnValue(AgentMessageId('main-followup')) + const mainAgent = ({ + followup: mainFollowup, whenIdle: mainWhenIdle, - } as unknown as Agent - const otherSend = vi.fn() - const otherAgent = { - send: otherSend, + } satisfies Pick<Agent, 'followup' | 'whenIdle'>) as unknown as Agent + const otherFollowup = vi.fn<Agent['followup']>().mockReturnValue(AgentMessageId('other-followup')) + const otherAgent = ({ + followup: otherFollowup, whenIdle: vi.fn(() => Promise.resolve()), - } as unknown as Agent + } satisfies Pick<Agent, 'followup' | 'whenIdle'>) as unknown as Agent const mainHandle = { agent: mainAgent, dispose: vi.fn(() => Promise.resolve()) } const otherHandle = { agent: otherAgent, dispose: vi.fn(() => Promise.resolve()) } const create = vi.fn(async (options: { sessionId: SessionId }) => @@ -196,7 +196,7 @@ describe('HarnessSdkServer', () => { }) const first = prompt('main', 'first') - await vi.waitFor(() => { expect(mainSend).toHaveBeenCalledOnce() }) + await vi.waitFor(() => { expect(mainFollowup).toHaveBeenCalledOnce() }) await expect(prompt('main', 'overlap')).rejects.toThrow('session already has an active prompt: main') await expect(prompt('other', 'independent')).resolves.toEqual({ accepted: true }) @@ -208,8 +208,8 @@ describe('HarnessSdkServer', () => { await expect(prompt('main', 'failing')).rejects.toThrow('turn wait failed') await expect(prompt('main', 'after failure')).resolves.toEqual({ accepted: true }) - expect(mainSend).toHaveBeenCalledTimes(4) - expect(otherSend).toHaveBeenCalledOnce() + expect(mainFollowup).toHaveBeenCalledTimes(4) + expect(otherFollowup).toHaveBeenCalledOnce() await server.shutdown() expect(mainHandle.dispose).toHaveBeenCalledOnce() expect(otherHandle.dispose).toHaveBeenCalledOnce() @@ -225,9 +225,9 @@ describe('HarnessSdkServer', () => { shutdown(): Promise<Record<string, never>> } const session = ctx.sessions.create(SessionId('message-outcome')) - const agent = { + const agent = ({ session, - send(content: { type: 'text'; text: string }[]) { + followup(content: { type: 'text'; text: string }[]) { session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } }, @@ -241,14 +241,15 @@ describe('HarnessSdkServer', () => { turn: 2, trigger: { kind: 'injection', source: { kind: 'plugin', plugin: 'late-metadata' } }, }) - session.append('context/message', { + session.append('user/message', { content: [{ type: 'text', text: 'late metadata' }], source: { kind: 'plugin', plugin: 'late-metadata' }, }, { surfaceOp: 'append' }) session.append('turn/end', { turn: 2, reason: { kind: 'completed' } }) + return AgentMessageId('message-outcome') }, whenIdle: () => Promise.resolve(), - } as unknown as Agent + } satisfies Pick<Agent, 'session' | 'followup' | 'whenIdle'>) as unknown as Agent server.sessions.set('message-outcome', { handle: { agent, dispose: () => Promise.resolve() }, lastTurnEnd: undefined, diff --git a/packages/ui/tui/README.md b/packages/ui/tui/README.md index 3dae79bf73..616544779f 100644 --- a/packages/ui/tui/README.md +++ b/packages/ui/tui/README.md @@ -18,9 +18,9 @@ Before model output, session events, tool presenters, questions, configuration, Typing `@` at a token boundary searches files and directories under the session working directory. A bare fuzzy query uses a reusable bounded workspace index; a query containing `/` lists that directory directly, and selecting a folder keeps completion open for descent. Whitespace-bearing paths are inserted as `@"path with spaces"`. Selecting a file inserts only its path and a trailing space: the TUI does not read it, attach hidden context, or replace it with a reference object. When a model-facing `read` tool is registered, the TUI adds one fixed system-prompt instruction telling the model to read an explicit path when its contents are needed. -When optional `ctx.sessionReferences` is mounted, the same `@` menu also offers metadata-only session candidates, inserts `@[label](dsh-session:<payload>)`, and prepares the selected snapshots before dispatch. Session references remain structured because the model has no filesystem-like tool for retrieving session snapshots later. Preparation disables duplicate submission and restores the editor input on failure. The TUI chooses `agent.steer()` or `agent.send()` from the status after that asynchronous preparation, so idle sends still dispatch `agent/prompt-submit` while in-turn steering joins at a checkpoint without that hook. +When optional `ctx.sessionReferences` is mounted, the same `@` menu also offers metadata-only session candidates, inserts `@[label](dsh-session:<payload>)`, and prepares the selected snapshots before dispatch. Session references remain structured because the model has no filesystem-like tool for retrieving session snapshots later. Preparation disables duplicate submission and restores the editor input on failure. The TUI chooses `agent.steer()` or `agent.followup()` from the status after that asynchronous preparation, so idle follow-ups still dispatch `agent/prompt-submit` while in-turn steering joins at a checkpoint without that hook. -While the agent is running, ordinary editor submissions call `agent.steer()`; otherwise they call `agent.send()`. A slash at the start of the submitted line enters `ctx.commands` instead: known commands execute directly, unknown commands produce a warning, and neither path automatically reaches the model. A command producer may explicitly schedule agent work; [`dsh-plan-mode`](../../plan/plan-mode/README.md#model-and-human-surfaces) uses that contract for `/plan [message]`. The TUI registers `/help`, `/model`, `/clear`, `/reasoning`, `/tools`, `/redraw`, `/reload`, `/resume`, `/status`, and `/exit` as agent-scoped definitions; every other effective command joins autocomplete and `/help` dynamically, as do `/skill:` completions. A status line above the editor reports the turn phase the TUI derives from session events — waiting for the first token, thinking, responding, or executing tools — with the elapsed time in that phase and the running step total, refreshed each second, and ends with the `Enter sends steering, Esc cancels` hint; while steering messages wait to reach the model it inserts a `N queued ·` badge before the hint that clears as each drains. Ctrl+C or Escape cancels a running turn. Tool cards collapse long bodies into a configurable head/tail preview; Ctrl+O toggles every card between its preview and full output. Ctrl+R toggles reasoning, Ctrl+L redraws, and Ctrl+D exits while idle. +While the agent is running, ordinary editor submissions call `agent.steer()`; otherwise they call `agent.followup()`. A slash at the start of the submitted line enters `ctx.commands` instead: known commands execute directly, unknown commands produce a warning, and neither path automatically reaches the model. A command producer may explicitly schedule agent work; [`dsh-plan-mode`](../../plan/plan-mode/README.md#model-and-human-surfaces) uses that contract for `/plan [message]`. The TUI registers `/help`, `/model`, `/clear`, `/reasoning`, `/tools`, `/redraw`, `/reload`, `/resume`, `/status`, and `/exit` as agent-scoped definitions; every other effective command joins autocomplete and `/help` dynamically, as do `/skill:` completions. A status line above the editor reports the turn phase the TUI derives from session events — waiting for the first token, thinking, responding, or executing tools — with the elapsed time in that phase and the running step total, refreshed each second, and ends with the `Enter sends steering, Esc cancels` hint; while steering messages wait to reach the model it inserts a `N queued ·` badge before the hint that clears as each drains. Ctrl+C or Escape cancels a running turn. Tool cards collapse long bodies into a configurable head/tail preview; Ctrl+O toggles every card between its preview and full output. Ctrl+R toggles reasoning, Ctrl+L redraws, and Ctrl+D exits while idle. `/model` opens the advisory `ctx.llm` catalog as a keyboard selector: Up/Down moves, Enter selects, and Escape closes it. `/model <model>` still selects an unambiguous model id directly, while `/model <provider>/<model>` selects an exact target. The configured target or latest logged request header initializes the selector, and an unlisted current model remains visible because catalogs are advisory. Selection is local to this TUI session. Prompt assembly snapshots the target for one step, replaces `{{provider}}` and `{{model}}`, and applies the same pair through `agent/request`; a switch during assembly therefore starts with a later step. The request header durably records targets that reach the model, while an unused selection remains process-local. @@ -80,7 +80,7 @@ The palette uses the standard 16-color ANSI foregrounds and SGR attributes, whic #### What the model sees -Each non-empty ordinary editor submission becomes one text block, sent with `agent.send()` while the target agent is idle and `agent.steer()` while it is running. A session mention becomes readable `@label` text plus the durable untrusted context defined by [`dsh-session-reference`](../../context/session-reference/README.md); its full JSON is hidden behind a compact reference card. Slash commands and keybindings are TUI-only; command results remain terminal notices. A command producer may schedule a separate agent input, such as the optional message accepted by `/plan [message]`. +Each non-empty ordinary editor submission becomes one text block, sent with `agent.followup()` while the target agent is idle and `agent.steer()` while it is running. A session mention becomes readable `@label` text plus the durable untrusted context defined by [`dsh-session-reference`](../../context/session-reference/README.md); its full JSON is hidden behind a compact reference card. Slash commands and keybindings are TUI-only; command results remain terminal notices. A command producer may schedule a separate agent input, such as the optional message accepted by `/plan [message]`. #### Token effect @@ -128,7 +128,7 @@ Changing provider or model enters that target's cache domain; no cache reuse acr #### What the model sees -A `/skill:<name> [instructions]` submission loads the named skill and delivers one text block: a `<skill name="…">` element wrapping the skill's instructions — preceded, when the provider exposes a resource base, by a line locating the skill's relative resources — followed by any trailing instructions the user typed. Delivery follows the same send-while-idle / steer-while-running rule as ordinary input. The command, not the model, chooses the skill; model-disabled skills are omitted from autocomplete but stay loadable by exact name. +A `/skill:<name> [instructions]` submission loads the named skill and delivers one text block: a `<skill name="…">` element wrapping the skill's instructions — preceded, when the provider exposes a resource base, by a line locating the skill's relative resources — followed by any trailing instructions the user typed. Delivery follows the same followup-while-idle / steer-while-running rule as ordinary input. The command, not the model, chooses the skill; model-disabled skills are omitted from autocomplete but stay loadable by exact name. #### Token effect diff --git a/packages/ui/tui/src/index.ts b/packages/ui/tui/src/index.ts index 2ade1937e3..de0ef02f7e 100644 --- a/packages/ui/tui/src/index.ts +++ b/packages/ui/tui/src/index.ts @@ -1884,14 +1884,15 @@ export function createTuiChat( let toolsExpanded = false let streaming: StreamingAssistantComponent | undefined let runningStatus: RunningStatus | undefined - // Steering messages queued during the running turn (`agent/queued`) that the - // loop has not yet drained, shown as a badge on the status line. Each entry is - // the queued message's serialized source: a drain (`steering/message`) removes - // one MATCHING entry, so loop-authored steering — continuation reasons enter - // the inbox without an `agent/queued` event — cannot consume a pending user - // message's slot. Cleared on leaving `running`, which also absorbs a - // cancellation that discards the queue without logging drains; the status - // line exists only while running, so idle carries no badge to keep current. + // Steering messages queued during the running turn (`agent/inbox/enqueue` + // with `info.steering`) that the loop has not yet drained, shown as a badge on + // the status line. Each entry is the queued message's serialized source: a + // drain (`steering/message`) removes one MATCHING entry, so a loop-authored + // continuation reason (which enqueues and drains under its own source) pushes + // and pops its own slot and cannot consume a pending user message's slot. + // Cleared on leaving `running`, which also absorbs a cancellation that + // discards the queue without logging drains; the status line exists only + // while running, so idle carries no badge to keep current. const pendingSteering: string[] = [] let disposed = false let shuttingDown: Promise<void> | undefined @@ -2238,6 +2239,29 @@ export function createTuiChat( const renderEvent = (event: SessionEvent, options: { addHistory: boolean; renderChunks: boolean }): void => { switch (event.type) { case 'user/message': { + // Injected context (plugin/goal source) renders as a dim context card, + // not a human bubble; only a direct human prompt is a user message. The + // boolean avoids narrowing `source`, so the label keeps its full union. + const source = event.data.source + if (source.kind !== 'user') { + const references = sessionReferenceCard(event.data.meta) + if (references !== undefined) { + chat.addChild(new Spacer(1)) + chat.addChild(new Text(palette.dim(`Referenced sessions · ${references.map(displayText).join(', ')}`), 1, 0)) + break + } + const text = displayText(contentText(event.data.content).trim()) + if (text) { + // The tui type view lacks plugin-augmented source kinds (e.g. goal), + // so read the display label without narrowing on `kind`. + const labelled = source as { kind: string; plugin?: string } + const label = labelled.plugin ?? labelled.kind + chat.addChild(new Spacer(1)) + chat.addChild(new Text(palette.dim(`Context · ${displayText(label)}`), 1, 0)) + chat.addChild(new Text(palette.muted(text), 1, 0)) + } + break + } const text = displayText(contentText(displayPromptContent(event.data)).trim()) if (text) { chat.addChild(new Spacer(1)) @@ -2262,22 +2286,6 @@ export function createTuiChat( } break } - case 'context/message': { - const references = sessionReferenceCard(event.data.meta) - if (references !== undefined) { - chat.addChild(new Spacer(1)) - chat.addChild(new Text(palette.dim(`Referenced sessions · ${references.map(displayText).join(', ')}`), 1, 0)) - break - } - const text = displayText(contentText(event.data.content).trim()) - if (text) { - const source = event.data.source.kind === 'plugin' ? event.data.source.plugin : event.data.source.kind - chat.addChild(new Spacer(1)) - chat.addChild(new Text(palette.dim(`Context · ${displayText(source)}`), 1, 0)) - chat.addChild(new Text(palette.muted(text), 1, 0)) - } - break - } case 'prompt/blocked': appendNotice(`Prompt blocked: ${event.data.reason}`, 'warning') break @@ -2362,7 +2370,6 @@ export function createTuiChat( const isSurface = event.type === 'user/message' || event.type === 'assistant/message' || event.type === 'tool/result' - || event.type === 'context/message' || event.type === 'steering/message' if (isSurface && !active.has(event.seq)) continue if (event.type === 'tool/call' && !activeCalls.has(event.data.callId)) continue @@ -2804,7 +2811,7 @@ export function createTuiChat( } else if (agent.status === 'running') { agent.steer(content, { contexts }) } else { - agent.send(content, { contexts }) + agent.followup(content, { contexts }) } } @@ -3148,9 +3155,9 @@ export function createTuiChat( advanceTurnPhase(event) if (event.type === 'steering/message') { // A queued steering message reached the model as it drained; drop its - // entry from the badge. Matching by source keeps loop-authored steering - // (e.g. continuation reasons), which logs here without a matching - // `agent/queued` increment, from consuming a pending user slot. + // entry from the badge. Matching by source keeps a loop-authored + // continuation reason popping its own enqueued slot rather than a pending + // user message's slot. const drained = pendingSteering.indexOf(JSON.stringify(event.data.source)) if (drained >= 0) { pendingSteering.splice(drained, 1) @@ -3164,7 +3171,7 @@ export function createTuiChat( renderEvent(event, { addHistory: false, renderChunks: true }) requestRender() }) - const disposeQueued = ctx.on('agent/queued', (subject, _content, info) => { + const disposeQueued = ctx.on('agent/inbox/enqueue', (subject, info) => { if (subject !== agent || !info.steering) return pendingSteering.push(JSON.stringify(info.source)) refreshStatus() diff --git a/packages/ui/tui/tests/harness.ts b/packages/ui/tui/tests/harness.ts index 97d0947536..37eee99735 100644 --- a/packages/ui/tui/tests/harness.ts +++ b/packages/ui/tui/tests/harness.ts @@ -1,6 +1,7 @@ import { Context } from 'cordis' import type { Terminal } from '@earendil-works/pi-tui' import AgentRegistry, { + AgentMessageId, type Agent, type AgentCancelCause, type AgentOptions, @@ -171,15 +172,23 @@ export async function createTuiTestHarness<TerminalType extends Terminal, Exit e steered, steeredOptions, cancelled, - send(content, options) { + followup(content, options) { sent.push(content) sentOptions.push(options) + return AgentMessageId('stub') + }, + queue(content, options) { + sent.push(content) + sentOptions.push(options) + return AgentMessageId('stub') }, steer(content, options) { steered.push(content) steeredOptions.push(options) + return AgentMessageId('stub') }, - inject() {}, + inject: () => AgentMessageId('stub'), + send: () => AgentMessageId('stub'), cancel(cause = { kind: 'user' }) { cancelled.push(cause) }, diff --git a/packages/ui/tui/tests/session-reference.snapshot.ts b/packages/ui/tui/tests/session-reference.snapshot.ts index bfbc98b590..f0b5e0eb61 100644 --- a/packages/ui/tui/tests/session-reference.snapshot.ts +++ b/packages/ui/tui/tests/session-reference.snapshot.ts @@ -128,7 +128,7 @@ describe('TUI session-reference snapshot', () => { type: 'text', text: '\n\n## My request:\n', }) - expect(target.session.events.some(event => event.type === 'context/message')).toBe(false) + expect(target.session.events.some(event => event.type === 'user/message' && event.data.source.kind !== 'user')).toBe(false) const snapshot = await terminal.snapshot({ includeScrollback: true }) if (REFRESHING) { diff --git a/packages/ui/tui/tests/tui.snapshot.ts b/packages/ui/tui/tests/tui.snapshot.ts index 16d6794002..d837841286 100644 --- a/packages/ui/tui/tests/tui.snapshot.ts +++ b/packages/ui/tui/tests/tui.snapshot.ts @@ -471,7 +471,7 @@ describe('TUI terminal-state snapshots', () => { session.append('todo/write', { todos: [{ content: `Unsafe todo ${CONTROL_PROBE}`, status: 'in_progress' }], }) - session.append('context/message', { + session.append('user/message', { content: [{ type: 'text', text: `Unsafe context ${CONTROL_PROBE}` }], source: { kind: 'plugin', plugin: `unsafe-${CONTROL_PROBE}` }, }, { surfaceOp: 'append' }) @@ -587,7 +587,7 @@ describe('TUI terminal-state snapshots', () => { await checkpoint('surface-before-compaction', harness.terminal, { includeScrollback: true }) await renderAfter(harness, () => { - harness.session.append('context/message', { + harness.session.append('user/message', { content: [{ type: 'text', text: 'Compacted summary: the prior command completed and its details were retired from the active surface.' }], source: { kind: 'plugin', plugin: 'compact' }, }, { diff --git a/packages/ui/tui/tests/tui.spec.ts b/packages/ui/tui/tests/tui.spec.ts index 73be9abe76..2c4fd21650 100644 --- a/packages/ui/tui/tests/tui.spec.ts +++ b/packages/ui/tui/tests/tui.spec.ts @@ -4,7 +4,7 @@ import { join, resolve } from 'node:path' import { describe, expect, it, vi } from 'vitest' import { Context } from 'cordis' import { CombinedAutocompleteProvider, type Terminal } from '@earendil-works/pi-tui' -import AgentRegistry, { agentEvents, assembleContextFor, type Agent } from '@deepseek-ai/dsh-agent' +import AgentRegistry, { agentEvents, assembleContextFor, AgentMessageId, type Agent } from '@deepseek-ai/dsh-agent' import { type LlmCallConfig } from '@deepseek-ai/dsh-llm' import { GOAL_CHANGE_VERSION, GoalId, renderGoalChange, type GoalSnapshotChangeMeta } from '@deepseek-ai/dsh-goal' import CommandService, { type CommandInvocation } from '@deepseek-ai/dsh-commands' @@ -1073,7 +1073,7 @@ describe('pi-tui chat lifecycle and transcript', () => { } const result = await setup({ beforeMount(session) { - session.append('context/message', { + session.append('user/message', { content: renderGoalChange(change), source: { kind: 'goal', goalId: change.goal.id, revision: change.goal.revision, round: 0 }, meta: change as unknown as JsonValue, @@ -1172,8 +1172,11 @@ describe('pi-tui chat lifecycle and transcript', () => { result.session.append('user/message', { content: [{ type: 'text', text: ' ' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) result.session.append('steering/message', { turn: 2, content: [{ type: 'text', text: 'steering note' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) result.session.append('steering/message', { turn: 2, content: [{ type: 'text', text: '' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) - result.session.append('context/message', { content: [{ type: 'text', text: 'user context' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) - result.session.append('context/message', { content: [{ type: 'text', text: '' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) + result.session.append('user/message', { content: [{ type: 'text', text: 'user context' }], source: { kind: 'plugin', plugin: 'ctx' } }, { surfaceOp: 'append' }) + result.session.append('user/message', { content: [{ type: 'text', text: '' }], source: { kind: 'plugin', plugin: 'ctx' } }, { surfaceOp: 'append' }) + // A non-plugin injected source (goal) has no `plugin` field, so its context + // card label falls back to the source kind. + result.session.append('user/message', { content: [{ type: 'text', text: 'goal context' }], source: { kind: 'goal', goalId: 'g1', revision: 1, round: 0 } as never }, { surfaceOp: 'append' }) result.session.append('prompt/blocked', { content: [{ type: 'text', text: 'blocked' }], source: { kind: 'user' }, reason: 'test policy' }) appendAssistant(result.session, []) result.session.append('step/end', { turn: 1, step: 1 }) @@ -1254,6 +1257,7 @@ describe('pi-tui chat lifecycle and transcript', () => { expect(result.terminal.output).toContain('Enter sends steering, Esc cancels') expect(result.terminal.output).toContain('Steering') expect(result.terminal.output).toContain('user context') + expect(result.terminal.output).toContain('Context · goal') // goal-sourced injected context labels by kind expect(result.terminal.output).toContain('Prompt blocked') expect(result.terminal.output).toContain('Turn cancelled') expect(result.terminal.progress).toContain(true) @@ -1350,16 +1354,16 @@ describe('pi-tui chat lifecycle and transcript', () => { expect(result.terminal.output).not.toContain('queued') const queueSteering = (text: string): void => { - result.ctx.emit('agent/queued', result.agent, [{ type: 'text', text }], { source: { kind: 'user' }, contexts: [], steering: true }) + result.ctx.emit('agent/inbox/enqueue', result.agent, { id: AgentMessageId('stub'), content: [{ type: 'text', text }], source: { kind: 'user' }, contexts: [], steering: true, wakeup: true }) } const drainSteering = (text: string): void => { result.session.append('steering/message', { turn: 1, content: [{ type: 'text', text }], source: { kind: 'user' } }, { surfaceOp: 'append' }) } // A steering queue for a different agent never touches this status line. - const other = { ...result.agent, id: SessionId('other') } as Agent + const other = { ...result.agent, id: SessionId('other') } as unknown as Agent result.terminal.output = '' - result.ctx.emit('agent/queued', other, [{ type: 'text', text: 'elsewhere' }], { source: { kind: 'user' }, contexts: [], steering: true }) + result.ctx.emit('agent/inbox/enqueue', other, { id: AgentMessageId('stub'), content: [{ type: 'text', text: 'elsewhere' }], source: { kind: 'user' }, contexts: [], steering: true, wakeup: true }) await tick() expect(result.terminal.output).not.toContain('queued') @@ -1372,7 +1376,7 @@ describe('pi-tui chat lifecycle and transcript', () => { // A non-steering queue (an idle-style send) leaves the badge untouched. result.terminal.output = '' - result.ctx.emit('agent/queued', result.agent, [{ type: 'text', text: 'sent' }], { source: { kind: 'user' }, contexts: [], steering: false }) + result.ctx.emit('agent/inbox/enqueue', result.agent, { id: AgentMessageId('stub'), content: [{ type: 'text', text: 'sent' }], source: { kind: 'user' }, contexts: [], steering: false, wakeup: true }) drainSteering('first') await tick() expect(result.terminal.output).toContain('1 queued') @@ -1392,8 +1396,9 @@ describe('pi-tui chat lifecycle and transcript', () => { await tick() expect(result.terminal.output).toContain('1 queued') - // A loop-authored steering event (plugin source, no matching agent/queued) - // cannot consume a pending user slot, even when it drains first. + // A steering/message whose source matches no pending badge entry (here a + // plugin source with no tracked enqueue) pops nothing, so it cannot consume + // a pending user slot even when it drains first. result.terminal.output = '' result.session.append('steering/message', { turn: 1, @@ -1425,7 +1430,7 @@ describe('pi-tui chat lifecycle and transcript', () => { const idle = await setup() // A steering queue arriving while idle has no status line to badge, so the // refresh is a no-op beyond requesting a render. - idle.ctx.emit('agent/queued', idle.agent, [{ type: 'text', text: 'early' }], { source: { kind: 'user' }, contexts: [], steering: true }) + idle.ctx.emit('agent/inbox/enqueue', idle.agent, { id: AgentMessageId('stub'), content: [{ type: 'text', text: 'early' }], source: { kind: 'user' }, contexts: [], steering: true, wakeup: true }) idle.session.append('tool/call', { turn: 1, step: 0, callId: 'pre' as never, name: 'bash', arguments: '{}' }) await tick() expect(idle.terminal.output).not.toContain('Executing tools') @@ -1909,10 +1914,11 @@ describe('pi-tui chat lifecycle and transcript', () => { expect(result.terminal.output).toContain('Folder · docs/') }) result.terminal.send('\t') - await vi.waitFor(() => { - expect(result.terminal.output).toContain('File · design notes.md') - }) + result.terminal.output = '' result.terminal.send('\t') + await vi.waitFor(() => { + expect(result.terminal.output).toContain('@"docs/design notes.md"') + }) await tick() result.terminal.send('\r') await vi.waitFor(() => { expect(result.agent.sent).toHaveLength(2) }) @@ -2150,7 +2156,7 @@ describe('pi-tui chat lifecycle and transcript', () => { expect(result.terminal.output).toContain('Referenced sessions · Steering source (steering-source)') expect(result.terminal.output).not.toContain('hidden non-reference prefix') - result.session.append('context/message', { + result.session.append('user/message', { content: [{ type: 'text', text: 'secret full snapshot payload' }], source: { kind: 'plugin', plugin: 'session-reference' }, meta: { @@ -2169,13 +2175,13 @@ describe('pi-tui chat lifecycle and transcript', () => { [{ kind: 'session-reference', references: [{}] }, 'invalid-fields'], ] for (const [meta, text] of invalidCards) { - result.session.append('context/message', { + result.session.append('user/message', { content: [{ type: 'text', text }], source: { kind: 'plugin', plugin: 'session-reference' }, meta, }, { surfaceOp: 'append' }) } - result.session.append('context/message', { + result.session.append('user/message', { content: [{ type: 'text', text: 'same-label snapshot' }], source: { kind: 'plugin', plugin: 'session-reference' }, meta: { kind: 'session-reference', references: [{ sessionId: 'same', label: 'same' }] }, @@ -2609,7 +2615,7 @@ describe('pi-tui chat lifecycle and transcript', () => { const events = await setup() const unrelatedSession = events.ctx.sessions.create(SessionId('unrelated-session')) - const unrelatedAgent = { ...events.agent, id: unrelatedSession.id, session: unrelatedSession } + const unrelatedAgent = { ...events.agent, id: unrelatedSession.id, session: unrelatedSession } as unknown as Agent unrelatedSession.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) unrelatedSession.append('todo/write', { todos: [{ content: 'hidden', status: 'pending' }] }) agentEvents(events.ctx, unrelatedAgent).emit('agent/status', 'running') @@ -2972,7 +2978,7 @@ describe('tool cards and surface replay', () => { turn: 1, step: 1, callId: 'old-call' as never, content: [{ type: 'text', text: 'old output' }], isError: false, }, { surfaceOp: 'append' }) const start = result.session.surface.nodes[0] as number - result.session.append('context/message', { + result.session.append('user/message', { content: [{ type: 'text', text: 'summary replacement' }], source: { kind: 'plugin', plugin: 'compact' }, }, { @@ -3293,7 +3299,7 @@ describe('terminal mounting', () => { const session = ctx.sessions.create(SessionId('main')) ctx.agents.register({ id: session.id, options: {}, session, status: 'idle', ctx, - send() {}, steer() {}, inject() {}, cancel() {}, whenIdle: () => Promise.resolve(), + followup: () => AgentMessageId('stub'), queue: () => AgentMessageId('stub'), steer: () => AgentMessageId('stub'), inject: () => AgentMessageId('stub'), send: () => AgentMessageId('stub'), cancel() {}, whenIdle: () => Promise.resolve(), }) const terminal = new FakeTerminal() mountTui(ctx, { color: false }, { terminal, exit: vi.fn() }) @@ -3317,7 +3323,7 @@ describe('terminal mounting', () => { const session = ctx.sessions.create(SessionId('main')) ctx.agents.register({ id: session.id, options: {}, session, status: 'idle', ctx, - send() {}, steer() {}, inject() {}, cancel() {}, whenIdle: () => Promise.resolve(), + followup: () => AgentMessageId('stub'), queue: () => AgentMessageId('stub'), steer: () => AgentMessageId('stub'), inject: () => AgentMessageId('stub'), send: () => AgentMessageId('stub'), cancel() {}, whenIdle: () => Promise.resolve(), }) const terminal = new FakeTerminal() // Mirror dsh-tui's own inject (minus loader, the absence under test). @@ -3351,14 +3357,14 @@ describe('terminal mounting', () => { const otherSession = ctx.sessions.create(SessionId('other-session')) ctx.agents.register({ id: otherSession.id, options: {}, session: otherSession, status: 'idle', ctx, - send() {}, steer() {}, inject() {}, cancel() {}, whenIdle: () => Promise.resolve(), + followup: () => AgentMessageId('stub'), queue: () => AgentMessageId('stub'), steer: () => AgentMessageId('stub'), inject: () => AgentMessageId('stub'), send: () => AgentMessageId('stub'), cancel() {}, whenIdle: () => Promise.resolve(), }) expect(terminal.started).toBe(0) const session = ctx.sessions.create(SessionId('late-session')) const agent = { id: session.id, options: {}, session, status: 'idle', ctx, - send() {}, steer() {}, inject() {}, cancel() {}, whenIdle: () => Promise.resolve(), + followup: () => AgentMessageId('stub'), queue: () => AgentMessageId('stub'), steer: () => AgentMessageId('stub'), inject: () => AgentMessageId('stub'), send: () => AgentMessageId('stub'), cancel() {}, whenIdle: () => Promise.resolve(), } as Agent ctx.agents.register(agent) await tick() @@ -3388,7 +3394,7 @@ describe('terminal mounting', () => { const session = ctx.sessions.create(SessionId('main-session')) ctx.agents.register({ id: session.id, options: {}, session, status: 'idle', ctx, - send() {}, steer() {}, inject() {}, cancel() {}, whenIdle: () => Promise.resolve(), + followup: () => AgentMessageId('stub'), queue: () => AgentMessageId('stub'), steer: () => AgentMessageId('stub'), inject: () => AgentMessageId('stub'), send: () => AgentMessageId('stub'), cancel() {}, whenIdle: () => Promise.resolve(), }) await tick() expect(terminal.started).toBe(0) @@ -3430,7 +3436,7 @@ describe('terminal mounting', () => { session.append('step/start', { turn: 1, step: 1 }) ctx.agents.register({ id: session.id, options: {}, session, status: 'running', ctx, - send() {}, steer() {}, inject() {}, cancel() {}, whenIdle: () => Promise.resolve(), + followup: () => AgentMessageId('stub'), queue: () => AgentMessageId('stub'), steer: () => AgentMessageId('stub'), inject: () => AgentMessageId('stub'), send: () => AgentMessageId('stub'), cancel() {}, whenIdle: () => Promise.resolve(), }) const terminal = new FakeTerminal() terminal.start = () => { throw new Error('terminal startup failed') } diff --git a/packages/workflow/tool-ralph/tests/integration.spec.ts b/packages/workflow/tool-ralph/tests/integration.spec.ts index dcc3b947fb..c9492b9450 100644 --- a/packages/workflow/tool-ralph/tests/integration.spec.ts +++ b/packages/workflow/tool-ralph/tests/integration.spec.ts @@ -70,7 +70,7 @@ describe('dsh-tool-ralph over the real spawn and worker-thread stack', () => { agentOptions: { provider: 'mock', model: 'mock' }, }) const parent = parentHandle.agent - parent.send([{ type: 'text', text: 'PARENT_PROMPT_MARKER' }]) + parent.followup([{ type: 'text', text: 'PARENT_PROMPT_MARKER' }]) await parent.whenIdle() const children: Agent[] = [] diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml index 21eb750454..edd75466c5 100644 --- a/pnpm-lock.yaml +++ b/pnpm-lock.yaml @@ -273,6 +273,9 @@ importers: '@deepseek-ai/dsh-llm-deepseek': specifier: workspace:* version: link:../packages/llm/llm-deepseek + '@deepseek-ai/dsh-llm-pi-ai': + specifier: workspace:* + version: link:../packages/llm/llm-pi-ai '@deepseek-ai/dsh-llm-replay': specifier: workspace:* version: link:../packages/support/llm-replay diff --git a/python/sdk/README.i18n.yaml b/python/sdk/README.i18n.yaml index 956d6f8ff8..ed74d60087 100644 --- a/python/sdk/README.i18n.yaml +++ b/python/sdk/README.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 -README.md: 23d15d617b3d295a6cc2d8d20c6d03abc226834b -README.zh.md: 4f6aef13833af937babc2e5a92bfd14c12170534 +README.md: bfa31a712acd6fccf1458a0a80fc2ff80dfe114e +README.zh.md: 11ebcdd133b2fd839b73f50ef2be2e531e8bbc2a diff --git a/python/sdk/README.md b/python/sdk/README.md index 23d15d617b..bfa31a712a 100644 --- a/python/sdk/README.md +++ b/python/sdk/README.md @@ -34,9 +34,7 @@ with DeepSeekHarness( `provider` selects a provider route registered by the chosen Cordis composition; `model` is the model id resolved by that adapter. The bundled default composition registers `deepseek`. A custom composition can mount `llm-pi-ai`, configure provider-specific credentials/endpoints there, and select any provider/model present in pi-ai's installed catalog. -`TurnResult.final_response` is the text content from the last -`assistant/message` event in the turn. Use `TurnResult.events` for the complete -event stream, including intermediate assistant messages and tool activity. +`HarnessClient` retains discovered subagent ancestry for the lifetime of the runtime process. During each `Session.run()`, `TurnResult.notifications` and `on_notification` receive the root session and all known descendant notifications in wire order, including nested subagent lifecycle and session events. `TurnResult.events` remains the root session's complete event stream, and `TurnResult.final_response` is the text content from its last `assistant/message`; descendant messages therefore cannot replace the root response. The same behavior can be selected for the runtime subprocess with `DSH_CORDIS_CONFIG`. The injection lives in `HarnessClient.start()`, so the low-level client's default launch gets it too: when the launch resolves to the bundled runtime and neither `cordis` nor a non-empty `DSH_CORDIS_CONFIG` is set (the runtime treats an empty value as absent, and so does the injection check), the bundled default configuration is used; an explicit `runtime_bin`, `bridge_bin`, or `launch_args_override` disables the injection entirely. See the [sdk-runtime README](../sdk-runtime/README.md) for the runtime carriers (production exe vs dev-only node closure) and how to obtain them. diff --git a/python/sdk/README.zh.md b/python/sdk/README.zh.md index 4f6aef1383..11ebcdd133 100644 --- a/python/sdk/README.zh.md +++ b/python/sdk/README.zh.md @@ -30,7 +30,7 @@ with DeepSeekHarness( `provider` 用于选择当前 Cordis 组合已注册的提供方路由;`model` 是该适配器解析的模型 ID。内置默认组合注册 `deepseek`。自定义组合可以挂载 `llm-pi-ai`,在其中配置各提供方的凭据与端点,再选择 pi-ai 已安装目录中的任意提供方/模型组合。 -`TurnResult.final_response` 是本轮次最后一个 `assistant/message` 事件的文本内容。完整的事件流(包括中间的助手消息与工具活动)用 `TurnResult.events` 获取。 +`HarnessClient` 会在运行时进程的生命周期内保留已发现的 subagent(子 agent)祖先关系。每次执行 `Session.run()` 时,`TurnResult.notifications` 与 `on_notification` 会按线上的原始顺序收到根会话及所有已知后代的通知,其中包括嵌套 subagent 的生命周期与会话事件。`TurnResult.events` 仍只保存根会话的完整事件流,`TurnResult.final_response` 则取该会话最后一个 `assistant/message` 的文本内容,因此后代消息不会覆盖根会话回复。 同样的行为也可以通过 `DSH_CORDIS_CONFIG` 为运行时子进程选定。注入逻辑位于 `HarnessClient.start()`,因此底层客户端的默认启动也具有此行为:当启动解析到内置运行时,且 `cordis` 与非空的 `DSH_CORDIS_CONFIG` 均未设置时(运行时把空值视为缺省,注入检查与之一致),使用内置的默认配置;显式给出 `runtime_bin`、`bridge_bin` 或 `launch_args_override` 则完全禁用注入。运行时载体(生产用 exe 与仅限开发的 `node` 闭包)及其获取方式见 [sdk-runtime README](../sdk-runtime/README.md)。 diff --git a/python/sdk/src/deepseek_harness/api.py b/python/sdk/src/deepseek_harness/api.py index 2b44a50c64..d96e974bc3 100644 --- a/python/sdk/src/deepseek_harness/api.py +++ b/python/sdk/src/deepseek_harness/api.py @@ -143,7 +143,10 @@ class Session: notifications.append(notification) if on_notification is not None: on_notification(notification) - if notification.method == "session.event": + if ( + notification.method == "session.event" + and notification.payload.get("sessionId") == self.id + ): event = notification.payload.get("event") if isinstance(event, dict): events.append(event) diff --git a/python/sdk/src/deepseek_harness/client.py b/python/sdk/src/deepseek_harness/client.py index e552c8b685..8d4ec7f848 100644 --- a/python/sdk/src/deepseek_harness/client.py +++ b/python/sdk/src/deepseek_harness/client.py @@ -47,6 +47,7 @@ class HarnessClient: self._notification_subscribers: dict[ str, tuple[queue.Queue[Notification | BaseException], NotificationFilter | None] ] = {} + self._session_parents: dict[str, str] = {} self._requests: queue.Queue[IncomingRequest | BaseException] = queue.Queue() self._stderr_lines: deque[str] = deque(maxlen=400) self._reader_thread: threading.Thread | None = None @@ -62,6 +63,8 @@ class HarnessClient: def start(self) -> None: if self._proc is not None: return + with self._lock: + self._session_parents.clear() args = list(self.config.launch_args_override or self._default_launch_args()) env = os.environ.copy() if self.config.env: @@ -143,7 +146,7 @@ class HarnessClient: payload, response_model=_SessionPromptResponse, on_notification=on_notification, - notification_filter=_notification_belongs_to_session(session_id), + notification_filter=self._notification_belongs_to_session_tree(session_id), notification_subscription=notification_subscription, ) @@ -193,7 +196,8 @@ class HarnessClient: return NotificationSubscription(self, subscription_id, notifications) def subscribe_session_notifications(self, session_id: str) -> "NotificationSubscription": - return self.subscribe_notifications(_notification_belongs_to_session(session_id)) + """Subscribe to a session and descendants discovered from subagent lifecycle edges.""" + return self.subscribe_notifications(self._notification_belongs_to_session_tree(session_id)) def next_request(self) -> IncomingRequest: item = self._requests.get() @@ -352,6 +356,7 @@ class HarnessClient: params = message.get("params") notification = Notification(method=method, payload=params if isinstance(params, dict) else {}) with self._lock: + self._record_session_relationship_locked(notification) subscribers = list(self._notification_subscribers.items()) delivered = False for subscription_id, (subscriber, predicate) in subscribers: @@ -439,6 +444,52 @@ class HarnessClient: with self._lock: self._notification_subscribers.pop(subscription_id, None) + def _record_session_relationship_locked(self, notification: Notification) -> None: + if notification.method != "subagent.started": + return + parent_id = notification.payload.get("parentSessionId") + child_id = notification.payload.get("childSessionId") + if ( + isinstance(parent_id, str) + and parent_id + and isinstance(child_id, str) + and child_id + and parent_id != child_id + ): + self._session_parents[child_id] = parent_id + + def _notification_belongs_to_session_tree(self, session_id: str) -> NotificationFilter: + def belongs(notification: Notification) -> bool: + payload = notification.payload + if notification.method in {"subagent.started", "subagent.finished"}: + parent_id = payload.get("parentSessionId") + if ( + isinstance(parent_id, str) + and self._session_is_descendant_of(parent_id, session_id) + ): + return True + return payload.get("childSessionId") == session_id + related_id = payload.get("sessionId") + return ( + isinstance(related_id, str) + and self._session_is_descendant_of(related_id, session_id) + ) + + return belongs + + def _session_is_descendant_of(self, session_id: str, root_session_id: str) -> bool: + current = session_id + visited: set[str] = set() + while current not in visited: + if current == root_session_id: + return True + visited.add(current) + parent = self._session_parents.get(current) + if parent is None: + return False + current = parent + return False + class NotificationSubscription: def __init__( @@ -491,15 +542,3 @@ class _ShutdownResponse(BaseModel): def _int_or_none(value: object) -> int | None: return value if isinstance(value, int) else None - - -def _notification_belongs_to_session(session_id: str) -> NotificationFilter: - def belongs(notification: Notification) -> bool: - payload = notification.payload - return ( - payload.get("sessionId") == session_id - or payload.get("parentSessionId") == session_id - or payload.get("childSessionId") == session_id - ) - - return belongs diff --git a/python/sdk/tests/test_client.py b/python/sdk/tests/test_client.py index f66abf4b36..d5460b8683 100644 --- a/python/sdk/tests/test_client.py +++ b/python/sdk/tests/test_client.py @@ -9,7 +9,7 @@ from pathlib import Path import pytest -from deepseek_harness import DeepSeekHarness, HarnessClient, HarnessConfig +from deepseek_harness import DeepSeekHarness, HarnessClient, HarnessConfig, Notification def test_high_level_sdk_runs_turn_and_collects_final_response(tmp_path: Path) -> None: @@ -198,6 +198,65 @@ for line in sys.stdin: ] +def test_session_run_collects_nested_subagent_tree_without_polluting_root_events( + tmp_path: Path, +) -> None: + script = tmp_path / "fake_runtime.py" + script.write_text( + """ +import json +import sys + +for line in sys.stdin: + msg = json.loads(line) + method = msg.get("method") + if method == "initialize": + print(json.dumps({"jsonrpc": "2.0", "id": msg["id"], "result": {"serverInfo": {"name": "fake-runtime"}}}), flush=True) + elif method == "session/prompt": + root = (msg.get("params") or {})["sessionId"] + print(json.dumps({"jsonrpc": "2.0", "method": "subagent.started", "params": {"parentSessionId": root, "childSessionId": "child"}}), flush=True) + print(json.dumps({"jsonrpc": "2.0", "method": "session.event", "params": {"sessionId": "child", "event": {"type": "assistant/message", "data": {"content": [{"type": "text", "text": "child response"}]}}}}), flush=True) + print(json.dumps({"jsonrpc": "2.0", "method": "subagent.started", "params": {"parentSessionId": "child", "childSessionId": "grandchild"}}), flush=True) + print(json.dumps({"jsonrpc": "2.0", "method": "session.event", "params": {"sessionId": "grandchild", "event": {"type": "assistant/message", "data": {"content": [{"type": "text", "text": "grandchild response"}]}}}}), flush=True) + print(json.dumps({"jsonrpc": "2.0", "method": "subagent.finished", "params": {"parentSessionId": "child", "childSessionId": "grandchild", "status": "ok"}}), flush=True) + print(json.dumps({"jsonrpc": "2.0", "method": "subagent.finished", "params": {"parentSessionId": root, "childSessionId": "child", "status": "ok"}}), flush=True) + print(json.dumps({"jsonrpc": "2.0", "method": "session.event", "params": {"sessionId": root, "event": {"type": "assistant/message", "data": {"content": [{"type": "text", "text": "root response"}]}}}}), flush=True) + print(json.dumps({"jsonrpc": "2.0", "method": "session.finished", "params": {"sessionId": root, "status": "ok"}}), flush=True) + print(json.dumps({"jsonrpc": "2.0", "id": msg["id"], "result": {"accepted": True}}), flush=True) + elif method == "shutdown": + print(json.dumps({"jsonrpc": "2.0", "id": msg["id"], "result": {}}), flush=True) + break +""".strip() + ) + + seen: list[str] = [] + with DeepSeekHarness( + launch_args_override=(sys.executable, str(script)), + cwd=str(tmp_path), + ) as harness: + result = harness.run( + "delegate recursively", + session_id="main", + on_notification=lambda notification: seen.append(notification.method), + ) + assert harness.client._notifications.qsize() == 0 + + assert result.status == "ok" + assert result.final_response == "root response" + assert [event["data"]["content"][0]["text"] for event in result.events] == ["root response"] + assert [notification.method for notification in result.notifications] == [ + "subagent.started", + "session.event", + "subagent.started", + "session.event", + "subagent.finished", + "subagent.finished", + "session.event", + "session.finished", + ] + assert seen == [notification.method for notification in result.notifications] + + def test_session_run_ignores_notifications_for_other_sessions(tmp_path: Path) -> None: script = tmp_path / "fake_runtime.py" script.write_text( @@ -356,6 +415,92 @@ def test_client_keeps_unmatched_notifications_available_globally_while_subscribe assert notification.payload["sessionId"] == "other" +def test_session_subscription_keeps_descendant_relationships_across_subscriptions() -> None: + client = HarnessClient() + with client.subscribe_session_notifications("main") as first: + client._handle_message({ + "jsonrpc": "2.0", + "method": "subagent.started", + "params": {"parentSessionId": "main", "childSessionId": "child"}, + }) + assert first.next().payload["childSessionId"] == "child" + + with client.subscribe_session_notifications("main") as second: + client._handle_message({ + "jsonrpc": "2.0", + "method": "subagent.started", + "params": {"parentSessionId": "child", "childSessionId": "grandchild"}, + }) + client._handle_message({ + "jsonrpc": "2.0", + "method": "session.event", + "params": {"sessionId": "grandchild", "event": {"type": "assistant/message"}}, + }) + assert second.next().payload["childSessionId"] == "grandchild" + assert second.next().payload["sessionId"] == "grandchild" + + assert client._notifications.qsize() == 0 + + +def test_session_subscription_preserves_reused_child_ancestry_after_late_finish() -> None: + client = HarnessClient() + old_seen: list[Notification] = [] + new_seen: list[Notification] = [] + with ( + client.subscribe_session_notifications("old-parent") as old_subscription, + client.subscribe_session_notifications("new-parent") as new_subscription, + ): + client._handle_message({ + "jsonrpc": "2.0", + "method": "subagent.started", + "params": {"parentSessionId": "old-parent", "childSessionId": "reused-child"}, + }) + old_subscription.drain(old_seen.append) + new_subscription.drain(new_seen.append) + assert [notification.method for notification in old_seen] == ["subagent.started"] + assert new_seen == [] + + client._handle_message({ + "jsonrpc": "2.0", + "method": "subagent.started", + "params": {"parentSessionId": "new-parent", "childSessionId": "reused-child"}, + }) + old_subscription.drain(old_seen.append) + new_subscription.drain(new_seen.append) + assert [notification.method for notification in new_seen] == ["subagent.started"] + + client._handle_message({ + "jsonrpc": "2.0", + "method": "subagent.finished", + "params": {"parentSessionId": "old-parent", "childSessionId": "reused-child"}, + }) + old_subscription.drain(old_seen.append) + new_subscription.drain(new_seen.append) + assert [notification.method for notification in old_seen] == [ + "subagent.started", + "subagent.finished", + ] + assert [notification.method for notification in new_seen] == ["subagent.started"] + + client._handle_message({ + "jsonrpc": "2.0", + "method": "session.event", + "params": {"sessionId": "reused-child", "event": {"type": "assistant/message"}}, + }) + old_subscription.drain(old_seen.append) + new_subscription.drain(new_seen.append) + + assert [notification.method for notification in old_seen] == [ + "subagent.started", + "subagent.finished", + ] + assert [notification.method for notification in new_seen] == [ + "subagent.started", + "session.event", + ] + assert client._notifications.qsize() == 0 + + def test_client_contains_notification_filter_failure_to_its_subscription(tmp_path: Path) -> None: script = tmp_path / "fake_bridge.py" script.write_text( diff --git a/scripts/cordis-config-files.spec.ts b/scripts/cordis-config-files.spec.ts new file mode 100644 index 0000000000..49da2c6aaf --- /dev/null +++ b/scripts/cordis-config-files.spec.ts @@ -0,0 +1,36 @@ +import { mkdirSync, mkdtempSync, rmSync, writeFileSync } from 'node:fs' +import { tmpdir } from 'node:os' +import { join } from 'node:path' +import { afterEach, describe, expect, it } from 'vitest' +import { cordisConfigFiles } from './cordis-config-files.ts' + +const roots: string[] = [] + +afterEach(() => { + for (const root of roots.splice(0)) rmSync(root, { recursive: true, force: true }) +}) + +describe('cordisConfigFiles', () => { + it('finds Loader YAML without treating translation records as configs', () => { + const root = mkdtempSync(join(tmpdir(), 'dsh-cordis-config-files-')) + roots.push(root) + for (const directory of ['.claude', 'docs', 'examples', 'node_modules/pkg', 'vendor/pkg']) { + mkdirSync(join(root, directory), { recursive: true }) + } + for (const file of [ + '.claude/hidden.cordis.yml', + 'docs/cordis-primer.i18n.yaml', + 'examples/agent.cordis.yaml', + 'examples/headless.cordis.yml', + 'node_modules/pkg/hidden.cordis.yml', + 'vendor/pkg/hidden.cordis.yml', + ]) { + writeFileSync(join(root, file), '[]\n') + } + + expect(cordisConfigFiles(root)).toEqual([ + 'examples/agent.cordis.yaml', + 'examples/headless.cordis.yml', + ]) + }) +}) diff --git a/scripts/cordis-config-files.ts b/scripts/cordis-config-files.ts new file mode 100644 index 0000000000..9473779efe --- /dev/null +++ b/scripts/cordis-config-files.ts @@ -0,0 +1,18 @@ +/** Cordis Loader configuration file discovery. */ + +import { globSync } from 'node:fs' + +/** + * Return repository-relative Cordis Loader YAML paths under `root`. + * + * Translation consistency records are YAML sidecars, never Loader inputs. + * + * @param root Repository root to scan. + * @returns Sorted repository-relative Loader configuration paths. + */ +export function cordisConfigFiles(root: string): string[] { + return globSync(['**/*cordis*.yml', '**/*cordis*.yaml'], { + cwd: root, + exclude: ['.claude/**', 'node_modules/**', 'vendor/**', '**/*.i18n.yaml'], + }).sort() +} diff --git a/scripts/doc-budgets.manifest.json b/scripts/doc-budgets.manifest.json index fe61bfa69d..74b0b41d6f 100644 --- a/scripts/doc-budgets.manifest.json +++ b/scripts/doc-budgets.manifest.json @@ -4,7 +4,7 @@ "docs/architecture.md": 1800, "docs/cordis-primer.md": 600, "docs/defensive-patterns.md": 550, - "docs/testing.md": 1060, + "docs/testing.md": 1030, "examples/AGENTS.md": 310, "packages/AGENTS.md": 660, "packages/README.md": 760 diff --git a/scripts/gen-cordis-api.ts b/scripts/gen-cordis-api.ts index 7c61b9395d..5f2080b149 100644 --- a/scripts/gen-cordis-api.ts +++ b/scripts/gen-cordis-api.ts @@ -30,8 +30,45 @@ function quote(value: string): string { } /** - * Collect exported interface and type shapes; omit names declared in multiple - * packages rather than risk serving the wrong package's shape. + * Reduce an exported class to its type shape: drop method/constructor bodies + * and property initializers so the catalog serves member signatures, not + * implementation. + */ +function classShape(node: ts.ClassDeclaration): ts.ClassDeclaration { + const isNonPublic = (member: ts.ClassElement): boolean => + (ts.canHaveModifiers(member) ? ts.getModifiers(member) : undefined)?.some(m => + m.kind === ts.SyntaxKind.PrivateKeyword || m.kind === ts.SyntaxKind.ProtectedKeyword) ?? false + const members = node.members.flatMap((member): ts.ClassElement[] => { + if (isNonPublic(member) || (ts.isPropertyDeclaration(member) && ts.isPrivateIdentifier(member.name))) return [] + if (ts.isMethodDeclaration(member)) { + return [ts.factory.updateMethodDeclaration( + member, member.modifiers, member.asteriskToken, member.name, member.questionToken, + member.typeParameters, member.parameters, member.type, undefined)] + } + if (ts.isConstructorDeclaration(member)) { + return [ts.factory.updateConstructorDeclaration(member, member.modifiers, member.parameters, undefined)] + } + if (ts.isGetAccessorDeclaration(member)) { + return [ts.factory.updateGetAccessorDeclaration( + member, member.modifiers, member.name, member.parameters, member.type, undefined)] + } + if (ts.isSetAccessorDeclaration(member)) { + return [ts.factory.updateSetAccessorDeclaration( + member, member.modifiers, member.name, member.parameters, undefined)] + } + if (ts.isPropertyDeclaration(member)) { + return [ts.factory.updatePropertyDeclaration( + member, member.modifiers, member.name, member.questionToken ?? member.exclamationToken, member.type, undefined)] + } + return [member] + }) + return ts.factory.updateClassDeclaration( + node, node.modifiers, node.name, node.typeParameters, node.heritageClauses, members) +} + +/** + * Collect exported interface, type-alias, and body-stripped class shapes; omit + * names declared in multiple packages rather than serve the wrong shape. */ function collectTypeDecls(scanRoot: string = root): Map<string, string> { const printer = ts.createPrinter({ removeComments: true }) @@ -41,14 +78,16 @@ function collectTypeDecls(scanRoot: string = root): Map<string, string> { const abs = resolve(scanRoot, rel) const sf = ts.createSourceFile(abs, readFileSync(abs, 'utf8'), ts.ScriptTarget.Latest, true) for (const stmt of sf.statements) { - if (!ts.isInterfaceDeclaration(stmt) && !ts.isTypeAliasDeclaration(stmt)) continue + const named = ts.isInterfaceDeclaration(stmt) || ts.isTypeAliasDeclaration(stmt) || ts.isClassDeclaration(stmt) + if (!named || stmt.name === undefined) continue if (!(stmt.modifiers?.some(m => m.kind === ts.SyntaxKind.ExportKeyword) ?? false)) continue const name = stmt.name.text if (decls.has(name)) { ambiguous.add(name) continue } - const printed = printer.printNode(ts.EmitHint.Unspecified, stmt, sf).replace(/\r/g, '') + const emit = ts.isClassDeclaration(stmt) ? classShape(stmt) : stmt + const printed = printer.printNode(ts.EmitHint.Unspecified, emit, sf).replace(/\r/g, '') decls.set(name, printed.length > MAX_DECL_CHARS ? `${printed.slice(0, MAX_DECL_CHARS)} /* …truncated — full shape in source */` : printed) diff --git a/scripts/gen-cordis-catalog.ts b/scripts/gen-cordis-catalog.ts index d87fba3d08..a3274a83c3 100644 --- a/scripts/gen-cordis-catalog.ts +++ b/scripts/gen-cordis-catalog.ts @@ -35,6 +35,8 @@ export const LINK_MAP: Record<string, string> = { ContinuationDecision: 'core.md', ContinuationStop: 'core.md', GenerateOptions: 'core.md', + AgentMessage: 'core.md', + AgentMessageId: 'core.md', HookContext: 'core.md', LlmCallConfig: 'core.md', LlmModelContext: 'core.md', diff --git a/scripts/gen-doc-graphs.ts b/scripts/gen-doc-graphs.ts index 5cfa05bc2f..1f54f7358f 100644 --- a/scripts/gen-doc-graphs.ts +++ b/scripts/gen-doc-graphs.ts @@ -918,8 +918,8 @@ function renderLifecycle(): string { ' participant Session', ' participant Persistence', ' participant SDK as UI or SDK listener', - ' User->>Agent: send(content)', - ` Agent-->>SDK: ${mermaidCode('agent/queued')}`, + ' User->>Agent: followup(content)', + ` Agent-->>SDK: ${mermaidCode('agent/inbox/enqueue')}`, ' Agent->>Driver: queued work wakes driver', ` Driver-->>SDK: ${mermaidCode('agent/status')} running`, ` Driver->>Session: ${mermaidCode('turn/start')}`, @@ -998,7 +998,7 @@ function renderToolPipeline(): string { ' normalized["Registry outer normalization<br/>pipeline/result snapshot throws become isError"]', ' finalize["ToolDefinition.finalizeContent<br/>last content-only invariant"]', ` final["${mermaidCode('tools/result')} synchronous notification<br/>frozen authoritative outcome"]`, - ' context["Active-batch additionalContexts FIFO<br/>context/message after recorded tool results"]', + ' context["Active-batch additionalContexts FIFO<br/>injected user/message after recorded tool results"]', ` toolResult["Session event: ${mermaidCode('tool/result')}<br/>single model-facing outcome"]`, ' allResults["Tool batch settled<br/>recorded tool/result events complete"]', ' presentResult["UI completed card<br/>presentResult(args, result)"]', diff --git a/scripts/gen-tool-catalog.ts b/scripts/gen-tool-catalog.ts index cc85d48ba5..0ddfff5aa6 100644 --- a/scripts/gen-tool-catalog.ts +++ b/scripts/gen-tool-catalog.ts @@ -263,7 +263,7 @@ const TOOL_PACKAGES: ToolPackage[] = [ dir: 'tool-goal', source: 'packages/goal/tool-goal/src/index.ts', requires: ['ctx.tools', 'ctx.agents', 'ctx.goals', 'ctx.systemPrompt', 'a calling Agent in an authorized open turn'], - writes: ['tool/call', 'context/message goal snapshot for mutations', 'tool/result'], + writes: ['tool/call', 'user/message goal snapshot for mutations', 'tool/result'], async mount(ctx) { await ctx.plugin(AgentRegistry) await ctx.plugin(GoalService) @@ -336,7 +336,7 @@ const TOOL_PACKAGES: ToolPackage[] = [ dir: 'tool-tasks', source: 'packages/tasks/tool-tasks/src/index.ts', requires: ['ctx.tools', 'ctx.tasks', 'ctx.systemPrompt'], - writes: ['tool/call', 'tool/result', 'context/message via agent.inject() for background completion notices'], + writes: ['tool/call', 'tool/result', 'user/message via agent.inject() for background completion notices'], async mount(ctx) { await ctx.plugin(TaskService) await ctx.plugin(ToolTasks) diff --git a/scripts/project-doc-site.spec.ts b/scripts/project-doc-site.spec.ts index 7d1c3c1550..e6cc11ae6e 100644 --- a/scripts/project-doc-site.spec.ts +++ b/scripts/project-doc-site.spec.ts @@ -172,13 +172,13 @@ describe('rewriteMarkdown', () => { }) describe('docsPages locale routes', () => { - it('publishes every route in both locales and selects paired user sources', () => { + it('publishes every route in both locales and selects paired sources', () => { const byRoute = new Map(docsPages.map(page => [page.route, page])) for (const page of docsPages.filter(page => page.locale === 'root')) { const counterpart = byRoute.get(`en/${page.route}`) expect(counterpart, page.route).toBeDefined() expect(counterpart?.locale).toBe('en') - if (page.source.startsWith('docs/user/')) { + if (page.contentLocale === 'zh-CN') { expect(page.source).toMatch(/\.zh\.md$/) expect(page.contentLocale).toBe('zh-CN') expect(counterpart?.source).toBe(page.source.replace(/\.zh\.md$/, '.md')) @@ -190,6 +190,22 @@ describe('docsPages locale routes', () => { } }) + it('projects translated core-data pages while retaining explicit English fallbacks', () => { + const rootPages = docsPages.filter(page => ( + page.locale === 'root' && page.route.startsWith('reference/core-data-structures/') + )) + const translated = rootPages.filter(page => page.contentLocale === 'zh-CN') + const fallbacks = rootPages.filter(page => page.contentLocale === 'en-US') + + expect(translated).toHaveLength(18) + expect(translated.every(page => page.source.endsWith('.zh.md'))).toBe(true) + expect(fallbacks.map(page => page.source).sort()).toEqual([ + 'docs/core-data-structures/commands.md', + 'docs/core-data-structures/goal.md', + 'docs/core-data-structures/pty.md', + ]) + }) + it('publishes the Cordis core API under matching locale structures', () => { const files = ['context.md', 'events.md', 'fiber.md', 'registry.md', 'service.md'] for (const file of files) { diff --git a/scripts/snapshots/translation-prompt-v4/request-response.expected.json b/scripts/snapshots/translation-prompt-v4/request-response.expected.json index b0a3a3d526..9aa08c3793 100644 --- a/scripts/snapshots/translation-prompt-v4/request-response.expected.json +++ b/scripts/snapshots/translation-prompt-v4/request-response.expected.json @@ -4,7 +4,7 @@ "messages": [ { "role": "system", - "content": "# Translation Prompt\n\nYou are a senior technical translator specializing in LLM and agent development documentation. Your task is to translate the given source document from English to Chinese, producing natural, professional technical prose.\n\n## Quality Requirements\n\n### Structure and Format Preservation\n- Output a complete translated document that maintains exactly the same structure as the source: heading hierarchy, list shape, table columns, link targets, and code blocks.\n- Fenced code blocks must be byte-identical to the source, including ALL comments inside them. Do NOT translate comments inside code blocks. This is a hard rule with no exceptions.\n- Inline code spans (commands, flags, paths, API names, version numbers) must be kept verbatim. Never translate or reformat them.\n- Every relative link must point to the same target as in the source. Link text is translated; link targets are not.\n- Language switcher line: when translating into Chinese, write `[English](source-filename.md) | 中文`. When translating into English, write `English | [中文](source-filename.zh.md)`. Do NOT copy the switcher line from the source file unchanged — you must flip the link direction.\n- After a closing bold marker `**`, insert a space before the next character when that character is a Latin letter, digit, or CJK ideograph. Never insert a space before any punctuation (full-width or half-width).\n\n### Tone and Style\n- The translation must read as if originally written in the target language by a native speaker. If an expression sounds like a word-for-word rendering from the source language, rephrase it.\n- Write in a professional, formal tone appropriate for developer documentation. Never use colloquial or casual expressions.\n- Use polite imperative forms where the text instructs the reader to do something.\n- Keep the author's register: concise stays concise, detailed stays detailed.\n\n### Sentence Structure\n- Break long sentences with commas or semicolons. Avoid run-on sentences.\n- Prefer active voice. Convert passive constructions to active if it reads more naturally.\n- Translate meaning, not words. Restructure sentences where the target language grammar requires it.\n- Do not invent words or expressions that do not exist in natural technical writing of the target language.\n\n### Word Choice\n- Prefer precise, formal vocabulary over casual or colloquial alternatives.\n- When multiple synonyms exist, choose the one most commonly used in professional technical documentation of the target language.\n- Avoid slang, internal jargon, or overly literal translations that would not be recognized by the general developer audience.\n- Do not use the same word to translate two different source-language terms that carry distinct meanings.\n- Avoid repeating the same verb in close proximity; vary word choice for readability.\n\n#### When translating into Chinese\n- When a number modifies a noun, always include a Chinese classifier or measure word (量词). For example: \"three-package seam\" → \"由三个包构成的 seam\", not \"三包 seam\".\n\n### Punctuation\n\n#### When translating into Chinese\n- Use full-width Chinese punctuation in prose: `,。:;?!()「」`.\n- Strongly prefer replacing all em-dashes (——) with colons, periods, commas, or parentheses. Keep an em-dash only if no other punctuation works at all.\n- Use enumeration commas (、) between parallel items, not regular commas.\n- List item endings: use semicolons or no punctuation. Do not end list items with commas.\n- Put one half-width space between Chinese text and Latin words/numbers.\n- For RFC 2119 keywords (MUST, MUST NOT, SHOULD, MAY), translate to the corresponding Chinese term (必须、禁止、应当、可以) and keep the SOURCE emphasis marker: plain source stays plain (必须), italic source stays italic (*必须*), and bold source stays bold (**必须**).\n\n#### When translating into English\n(To be added.)\n\n## Terminology\n\nA terminology table is provided below. Follow it strictly:\n- Render every listed term exactly as specified.\n- When the target language is Chinese, use the \"中文\" column. On first occurrence, write the \"首次出现\" value with its parenthetical gloss; on subsequent occurrences, write only the part before the parentheses.\n- When the target language is English, use the \"English\" column without a Chinese gloss; do not copy the \"中文\" or \"首次出现\" value into English prose.\n- If a term has already been glossed as part of a compound term, do not gloss it again when it appears alone later.\n- NEVER use translations listed in the \"不要译作\" column.\n- For technical terms not in the table, follow the target language: for a Chinese target, use an established Chinese rendering from a major Chinese-language OSS or vendor source, or keep the source term and flag it as pending when no such precedent exists; for an English target, use the established English technical term, or preserve an ambiguous source term with a short English gloss and flag it as pending. Do not invent a translation. This rule applies to terminology only; for general prose, freely restructure and paraphrase for natural expression.\n\n# Terminology\n\n本表约定本仓库的中英术语统一译法。\n\n**通用规则:**\n- \"中文\"列为中文译文的正文默认用词。若该列为英文,则中文译文的正文中保留英文不翻译。\n- 首次出现按\"首次出现\"列书写(带括号注释);后续出现只写括号前的部分(可能为中文,也可能为英文),不出现括号内的注释。\n- \"不要译作\"列为严格禁止的译法。\n- 如果某术语已经作为另一个术语的组成部分被括注过(如 `agent loop(智能体循环)` 中已包含 `agent` 的括注),则该术语后续单独出现时无需再次括注。\n\n## 缩写类(中英文文本中均使用缩写)\n\n| English | 中文 | 首次出现 | 不要译作 | 备注 |\n|---|---|---|---|---|\n| ACP | ACP | ACP(Agent Client Protocol) | | |\n| AI | AI | AI(人工智能) | | |\n| API | API | | | |\n| CI | CI | | | |\n| CLI | CLI | CLI(命令行界面) | | |\n| e2e | e2e | | | |\n| HMR | HMR | HMR(热模块替换) | | |\n| JSON Schema | JSON Schema | | | |\n| JSONL | JSONL | | | |\n| LLM | LLM | LLM(大语言模型) | | |\n| MCP | MCP | | | |\n| PR | PR | PR(Pull Request) | | |\n| RAG | RAG | RAG(检索增强生成) | | |\n| SDK | SDK | | | |\n| SSE | SSE | SSE(Server-Sent Events) | | |\n\n## 英文类(中英文文本中均使用英文)\n\n| English | 中文 | 首次出现 | 不要译作 | 备注 |\n|---|---|---|---|---|\n| agent | agent | agent(智能体) | | |\n| Agent Note | Agent Note | Agent Note(agent 决策记录) | 智能体注记、智能体笔记 | 本仓库中由 agent 撰写的提案与决策记录 |\n| agent harness | agent harness | agent harness(智能体框架) | | agent 组合词(agent harness/workflow/loop/skill 等)整体保留英文;未括注过 agent 时首现按对应组合词或 agent 行处理 |\n| agent loop | agent loop | agent loop(智能体循环) | | |\n| backlog | backlog | backlog(待翻清单) | | 仅在双语翻译语境里括注`待翻清单` |\n| blob hash | blob hash | | | `git hash-object` 的结果 |\n| Cordis | Cordis | | | |\n| dispose | dispose | dispose(资源释放) | | |\n| doc-sync | doc-sync | doc-sync(文档同步门禁) | | |\n| fiber | fiber | | | |\n| fixture | fixture | fixture(测试前置数据) | | |\n| fork | fork | | | |\n| Function Calling | Function Calling | Function Calling(函数调用) | | |\n| harness | harness | | | |\n| harness engineering | harness engineering | | | |\n| lint | lint | | | |\n| mock | mock | | | 保留英文;指测试替身 |\n| loader | loader | | | |\n| manifest | manifest | manifest(元数据清单) | | |\n| monorepo | monorepo | | | |\n| schema | schema | | | |\n| schema DSL | schema DSL | | | |\n| seam | seam | | | 与 `extension point` 是不同概念;根据具体语境,可译为`服务边界`或`可替换点` |\n| skill | skill | skill(技能) | | |\n| spawn | spawn | | | |\n| steering | steering | steering(中途引导) | | |\n| task id | task id | | 任务 id | 保留英文 |\n| subagent | subagent | | | |\n| thinking | thinking | | | API 字段保留英文;描述模型模式时译为`思考` |\n| transcript | transcript | transcript(文本记录) | | 指会话渲染给用户或编辑器的完整文本,区别于事件日志 |\n| waterfall | waterfall | waterfall(瀑布式事件) | | |\n| wheel | wheel 包 | | | Python 打包格式 |\n| worktree | worktree | | | git 工作区概念 |\n| Zstandard | Zstandard | | | RFC 8878 compression format; `zstd` remains a code value. |\n\n## 双语类(中英文文本各自使用中英文)\n\n| English | 中文 | 首次出现 | 不要译作 | 备注 |\n|---|---|---|---|---|\n| adapter | 适配器 | | | |\n| adapter contract | 适配器契约 | 适配器契约(adapter contract) | | |\n| append-only | 仅追加 | | | |\n| artifact | 产物 | | | |\n| backend | 后端 | | | |\n| background task | 后台任务 | | | |\n| block | 块 | | | |\n| build target | 构建目标 | | | |\n| cancel | 取消 | | | |\n| feature | 功能 | | 能力 | SDK 产品与工程模型中的可管理产品单元 |\n| feature option | 功能选项 | | variant | 一项 SDK 功能内有限、可选择的实现或配置 |\n| checkpoint | 检查点 | | | |\n| chunk | 分片 | | | |\n| compaction | 压缩 | 压缩(compaction) | | |\n| companion tool | 配套工具 | | | |\n| Cordis plugin config | Cordis 插件配置 | | | Cordis 插件公开的 `Config` 对象或配置结构 |\n| config key | 配置键 | | | Cordis 插件配置中的单个字段 |\n| consumer | 消费方 | | | |\n| content block | 内容块 | | | |\n| Cookbook | 实操手册 | | | 文档标题用语 |\n| context | 上下文 | | | |\n| counterpart | 对侧文件 | | 对应物、配对物 | 双语配对语境;泛指\"另一侧\"时可写「另一侧」 |\n| context compaction | 上下文压缩 | 上下文压缩(context compaction) | | |\n| contract | 契约 | | | 如:`pairing contract` →`配对契约` |\n| Cordis config entry | Cordis 配置项 | | | 指 `cordis.yml` 插件列表中的一项;插件实现本身写`Cordis 插件` |\n| Cordis plugin | Cordis 插件 | | | Cordis 加载的插件实现,不指 `cordis.yml` 中的一项配置 |\n| coverage | 覆盖率 | | | |\n| crash recovery | 崩溃恢复 | | | |\n| deploy root | 部署根目录 | | | |\n| durability | 持久性 | | | |\n| feature requirement | 功能依赖 | | | 功能或功能选项通过 `requires` 声明的关系 |\n| enforcement frontier | 执行红线 | | 强制边界 | i18n 配对机制用语:manifest `required` 清单所划的门禁生效范围;与金标样例(style-samples ⑦)一致 |\n| event | 事件 | | | |\n| event log | 事件日志 | | | |\n| event stream | 事件流 | | | |\n| event-sourced | 事件溯源 | | | 沿用 DDD 社区通行译法 |\n| executor | 执行器 | | | |\n| expected output | 预期输出 | | 金标 | 指 snapshot 比较产物;翻译语料的人工校准样例不在此列 |\n| extension | 扩展 | | | |\n| extension point | 扩展点 | | | 注意与 `seam` 区分 |\n| fail-fast | 快速失败 | | | |\n| fenced code block | 围栏代码块 | | | 沿用 MDN 中文翻译 |\n| fingerprint | 指纹 | | | 通用内容指纹;双语配对机制使用 sidecar record 记录两侧 blob hash |\n| finish reason | 结束原因 | | | |\n| foreground run | 前台运行 | | | |\n| freshness | 新鲜度 | | | 沿用 MDN 中文翻译;在本项目中指译文相对源文的同步状态 |\n| hook | 钩子 | | | |\n| implementation | 实现 | | | |\n| inference | 推理 | 推理(inference) | | 需要和 `reasoning` 区分时保留英文括注 |\n| info string | 信息字符串 | | | 沿用 CommonMark 中文翻译;指代码围栏 ``` 之后的语言标注 |\n| injection | 注入 | | | |\n| integration | 集成 | | | |\n| interface | 接口 | | | |\n| language switcher | 语言切换行 | | | i18n 配对机制用语:双语配对文件顶部的互链行 |\n| memory | 记忆 / 内存 | | | 与 `agent` 搭配时译为`记忆`(如 `agent memory` →`智能体记忆`);指系统资源时译为`内存` |\n| merge | 合并 | | | |\n| message | 消息 | | | |\n| mod | 模组 | | | |\n| model provider | 模型提供方 | | | |\n| module | 模块 | | | |\n| npm dependency | NPM 依赖 | | | `package.json` 中的包关系;`dependencies`、`devDependencies` 等字段保持原样 |\n| orphan | 遗留 | | 孤儿、孤立 | 指英文源已不存在的 `.zh.md`(如「遗留译文」);进程语境按 OS 惯用语译「孤儿进程」 |\n| orphan branch | 孤立分支 | | 孤儿分支 | 沿用 git 官方中文翻译 |\n| package | 包 | 包(package) | | 指 npm 包(`@deepseek-ai/dsh-*`);`package.json` 等代码标识保持原样 |\n| pairing | 配对 | | | |\n| peer dependency | 对等依赖 | 对等依赖(peer dependency) | | |\n| permission | 权限 | | | |\n| persistence | 持久化 | | | |\n| pipeline | 流水线 | | | |\n| plugin | 插件 | | | |\n| prompt | 提示词 | | | |\n| provider | 提供方 | | | |\n| provider-neutral | 提供方无关 | | | |\n| quality gate | 质量门禁 | | | |\n| reasoning | 推理 | 推理(reasoning) | | 需要和 `inference` 区分时保留英文括注 |\n| reasoning_content | 思考内容 | | | |\n| registry | 注册表 | | | |\n| replay | 回放 | | | |\n| resume | 恢复 | | | |\n| runtime | 运行时 | | | |\n| sandbox | 沙箱 | | | |\n| service | 服务 | | | |\n| serving surface | 对外服务接口 | | | |\n| session | 会话 | | | |\n| session event | 会话事件 | | | |\n| sidecar record | 伴随记录 | | 旁挂记录 | 指与文档同目录的伴随记录文件 |\n| smoke test | 冒烟测试 | | | |\n| snapshot | 快照 | | | |\n| source of truth | 真源 | | | |\n| spine | 主干 | | | |\n| staged | 暂存 | | | 沿用 git 官方中文翻译 |\n| stale | 陈旧 | | 过期 | 与 `fresh`(`新鲜`)成对;门禁输出中保留英文 `stale` 不翻译;`expired` 才译为`过期` |\n| step | 步骤 | | | |\n| stream | 流 | | | |\n| streaming | 流式输出 | | | |\n| structural signature | 结构签名 | | | i18n 配对机制用语:门禁比对两侧文件时提取的有序结构序列(标题层级、代码块、列表等) |\n| system prompt | 系统提示词 | | | |\n| taxonomy | 分类体系 | | | |\n| token usage | token 用量 | | | |\n| tool | 工具 | | | |\n| tool call | 工具调用 | | | |\n| tool result | 工具结果 | | | |\n| tool schema | 工具 schema | | | |\n| toolkit | 工具包 | | | |\n| turn | 轮次 | | | |\n| VFS | VFS | 虚拟文件系统(VFS) | | |\n| typecheck | 类型检查 | | | |\n| vocabulary | 词汇 | | | |\n| wire format | 协议格式 | 协议格式(wire format) | | |\n| workflow | 工作流 | | | |\n| wrapper | 包装层 | | | 软件层或 SDK 包装层 |\n| wrapper script | 包装脚本 | | | 可执行脚本包装层 |\n\n\n## Output Format\n\nProduce your output in three XML sections:\n\nThe outer section tags are framing. If Markdown inside any section body contains a line consisting only of `<translation>`, `</translation>`, `<review>`, `</review>`, `<final>`, or `</final>`, prefix that line with `\\`. If the original line already has one or more backslashes immediately before the tag, add one more. The parser removes exactly one framing escape; tags mentioned inline need no escaping.\n\n```xml\n<translation>\n(Complete translation of the source document)\n</translation>\n\n<review>\n(Self-review notes, one correction per line with category tag, e.g.)\n- [Tone] \"旁挂记录\" → \"伴随记录\"(生造词)\n- [Sentence] 第 3 段补充逗号断句\n- [Punctuation] 两处破折号替换为冒号\n- 无修正\n</review>\n\n<final>\n(Final translation after corrections)\n</final>\n```\n\n## Self-Review Instructions\n\nAfter writing `<translation>`, re-read it in the target language only, without looking at the source. Check by category:\n\n**Structure**\n- Is the heading hierarchy, list shape, and code block content identical to the source?\n- Are ALL comments inside code blocks left untranslated (byte-identical to source)?\n- Is the language switcher line correctly flipped (not copied from source)?\n- Are link targets preserved, and are spaces after bold markers present only before Latin letters, digits, or CJK ideographs?\n- Are wrapper-tag lines inside section bodies escaped with one additional backslash?\n\n**Tone & Style**\n- Does every sentence read as if originally written by a native speaker?\n- Is there any colloquial, casual, or overly informal phrasing?\n\n**Sentence Structure**\n- Are there run-on sentences that need breaking?\n- Are there stiff passive constructions that should be converted to active voice?\n\n**Word Choice**\n- Are there overly literal translations that sound unnatural?\n- Is the same target-language word used to translate two distinct source concepts?\n- Is any slang or internal jargon present?\n\n**Terminology**\n- For a Chinese target, are first-occurrence glosses correctly applied (not missing, not repeated)? For an English target, are Chinese glosses absent?\n- Are any \"不要译作\" forbidden translations present?\n- For unlisted terms, does a Chinese target use established Chinese precedent or retain the source term as pending, and does an English target use established English terminology or preserve only an ambiguous source term with a short English gloss?\n\n**Punctuation** (when target is Chinese)\n- Are there em-dashes that should be replaced with colons, periods, or commas?\n- Are list items ending with commas instead of semicolons?\n- Do RFC 2119 keywords preserve the source emphasis exactly?\n\nRecord corrections in `<review>` with category tags. Then output the corrected version in `<final>`. If no corrections are needed, write \"无修正\" in `<review>` and copy the translation unchanged into `<final>`.\n\n## Examples\n\nBelow are representative examples of common problems and their corrections. Follow the \"Good\" versions.\n\n### Colloquial verb → Professional verb\n- Source: `The repo pins pnpm@11.7.0 in package.json`\n- Bad: `仓库在 package.json 中钉住 pnpm@11.7.0`\n- Good: `该仓库在 package.json 中固定使用 pnpm@11.7.0`\n\n### Run-on sentence → Natural phrasing with pause\n- Source: `Read docs/architecture.md before changing anything under packages/.`\n- Bad: `改动 packages/ 下的任何东西之前先读 docs/architecture.md。`\n- Good: `在修改 packages/ 目录下的任何内容之前,请先阅读 docs/architecture.md。`\n\n### Stiff passive voice → Active and natural\n- Source: `a green gate means the pair was confirmed consistent at these exact contents, not that the confirmation was sound.`\n- Bad: `门禁绿意味着这对文档曾在当前内容上被确认一致,不意味着这次确认本身是对的。`\n- Good: `门禁通过意味着这组文档在当前内容上的一致性得到了确认,不代表确认本身正确可靠。`\n\n### Invented word → Natural expression\n- Source: `A sidecar record of both blob hashes makes consistency checkable`\n- Bad: `旁挂记录两侧 blob hash,使一致性可检查`\n- Good: `伴随记录保存两侧 blob hash,使一致性可检查`\n\n### Em-dash → Colon/period\n- Source: `FIXME — an issue that should block a new release. A release should not ship with an open FIXME unless reviewers explicitly agree the change can be merged anyway.`\n- Bad: `FIXME——应当阻塞新版本发布的问题。除非评审者明确同意可以照常合入,发布不应带着未解决的 FIXME 出门。`\n- Good: `FIXME:应当阻塞新版本发布的问题。除非评审者明确同意该更改可以合并,否则发布版本不应包含未解决的 FIXME。`\n\n### Overly literal → Meaningful rendering\n- Source: `awkward phrasing is easier to hear without the source anchoring you`\n- Bad: `没有源文锚着,别扭的表述更容易被听出来`\n- Good: `不对照原文时,更容易察觉别扭的表达`\n\n### Terminology — do not translate what should be kept in English\n- Source: `typed service seams, and explicit extension points`\n- Bad: `类型化的服务 seam(扩展点)与显式扩展点`\n- Good: `类型化的服务 seam 与显式扩展点`\n\n### Slang/jargon → Professional phrasing\n- Source: `The committed agent workflow lives in .agents/skills/dsh-translate-docs`\n- Bad: `进仓的 agent 工作流见 .agents/skills/dsh-translate-docs`\n- Good: `仓库内置的 agent 工作流见 .agents/skills/dsh-translate-docs`\n\n### \"For humans\" — translate the intent, not the word\n- Source: `For humans, start with the development guide`\n- Bad: `对于人工读者,请先从开发指南开始`(\"人工读者\"生硬)\n- Good: `面向开发者:请先阅读开发指南`(\"开发者\"自然,且中文里冒号在此处更自然)\n\n### Code block comments — NEVER translate\n- Source code block contains: `# full-screen TUI coding agent (needs DEEPSEEK_API_KEY)`\n- Bad: `# 全屏 TUI coding agent(需要 DEEPSEEK_API_KEY)`\n- Good: `# full-screen TUI coding agent (needs DEEPSEEK_API_KEY)` (keep exactly as-is, byte-for-byte)\n\n### Language switcher — flip direction\n- Source file (English) has: `English | [中文](README.zh.md)`\n- Bad (copying source unchanged): `English | [中文](README.zh.md)`\n- Good (flipped for Chinese file): `[English](README.md) | 中文`\n\n---\n\nNow translate the following document:" + "content": "# Translation Prompt\n\nYou are a senior technical translator specializing in LLM and agent development documentation. Your task is to translate the given source document from English to Chinese, producing natural, professional technical prose.\n\n## Quality Requirements\n\n### Structure and Format Preservation\n- Output a complete translated document that maintains exactly the same structure as the source: heading hierarchy, list shape, table columns, link targets, and code blocks.\n- Fenced code blocks must be byte-identical to the source, including ALL comments inside them. Do NOT translate comments inside code blocks. This is a hard rule with no exceptions.\n- Inline code spans (commands, flags, paths, API names, version numbers) must be kept verbatim. Never translate or reformat them.\n- Every relative link must point to the same target as in the source. Link text is translated; link targets are not.\n- Language switcher line: when translating into Chinese, write `[English](source-filename.md) | 中文`. When translating into English, write `English | [中文](source-filename.zh.md)`. Do NOT copy the switcher line from the source file unchanged — you must flip the link direction.\n- After a closing bold marker `**`, insert a space before the next character when that character is a Latin letter, digit, or CJK ideograph. Never insert a space before any punctuation (full-width or half-width).\n\n### Tone and Style\n- The translation must read as if originally written in the target language by a native speaker. If an expression sounds like a word-for-word rendering from the source language, rephrase it.\n- Write in a professional, formal tone appropriate for developer documentation. Never use colloquial or casual expressions.\n- Use polite imperative forms where the text instructs the reader to do something.\n- Keep the author's register: concise stays concise, detailed stays detailed.\n\n### Sentence Structure\n- Break long sentences with commas or semicolons. Avoid run-on sentences.\n- Prefer active voice. Convert passive constructions to active if it reads more naturally.\n- Translate meaning, not words. Restructure sentences where the target language grammar requires it.\n- Do not invent words or expressions that do not exist in natural technical writing of the target language.\n\n### Word Choice\n- Prefer precise, formal vocabulary over casual or colloquial alternatives.\n- When multiple synonyms exist, choose the one most commonly used in professional technical documentation of the target language.\n- Avoid slang, internal jargon, or overly literal translations that would not be recognized by the general developer audience.\n- Do not use the same word to translate two different source-language terms that carry distinct meanings.\n- Avoid repeating the same verb in close proximity; vary word choice for readability.\n\n#### When translating into Chinese\n- When a number modifies a noun, always include a Chinese classifier or measure word (量词). For example: \"three-package seam\" → \"由三个包构成的 seam\", not \"三包 seam\".\n\n### Punctuation\n\n#### When translating into Chinese\n- Use full-width Chinese punctuation in prose: `,。:;?!()「」`.\n- Strongly prefer replacing all em-dashes (——) with colons, periods, commas, or parentheses. Keep an em-dash only if no other punctuation works at all.\n- Use enumeration commas (、) between parallel items, not regular commas.\n- List item endings: use semicolons or no punctuation. Do not end list items with commas.\n- Put one half-width space between Chinese text and Latin words/numbers.\n- For RFC 2119 keywords (MUST, MUST NOT, SHOULD, MAY), translate to the corresponding Chinese term (必须、禁止、应当、可以) and keep the SOURCE emphasis marker: plain source stays plain (必须), italic source stays italic (*必须*), and bold source stays bold (**必须**).\n\n#### When translating into English\n(To be added.)\n\n## Terminology\n\nA terminology table is provided below. Follow it strictly:\n- Render every listed term exactly as specified.\n- When the target language is Chinese, use the \"中文\" column. On first occurrence, write the \"首次出现\" value with its parenthetical gloss; on subsequent occurrences, write only the part before the parentheses.\n- When the target language is English, use the \"English\" column without a Chinese gloss; do not copy the \"中文\" or \"首次出现\" value into English prose.\n- If a term has already been glossed as part of a compound term, do not gloss it again when it appears alone later.\n- NEVER use translations listed in the \"不要译作\" column.\n- For technical terms not in the table, follow the target language: for a Chinese target, use an established Chinese rendering from a major Chinese-language OSS or vendor source, or keep the source term and flag it as pending when no such precedent exists; for an English target, use the established English technical term, or preserve an ambiguous source term with a short English gloss and flag it as pending. Do not invent a translation. This rule applies to terminology only; for general prose, freely restructure and paraphrase for natural expression.\n\n# Terminology\n\n本表约定本仓库的中英术语统一译法。\n\n**通用规则:**\n- \"中文\"列为中文译文的正文默认用词。若该列为英文,则中文译文的正文中保留英文不翻译。\n- 首次出现按\"首次出现\"列书写(带括号注释);后续出现只写括号前的部分(可能为中文,也可能为英文),不出现括号内的注释。\n- \"不要译作\"列为严格禁止的译法。\n- 如果某术语已经作为另一个术语的组成部分被括注过(如 `agent loop(智能体循环)` 中已包含 `agent` 的括注),则该术语后续单独出现时无需再次括注。\n\n## 缩写类(中英文文本中均使用缩写)\n\n| English | 中文 | 首次出现 | 不要译作 | 备注 |\n|---|---|---|---|---|\n| ACP | ACP | ACP(Agent Client Protocol) | | |\n| AI | AI | AI(人工智能) | | |\n| API | API | | | |\n| CI | CI | | | |\n| CLI | CLI | CLI(命令行界面) | | |\n| e2e | e2e | | | |\n| HMR | HMR | HMR(热模块替换) | | |\n| JSON Schema | JSON Schema | | | |\n| JSONL | JSONL | | | |\n| LLM | LLM | LLM(大语言模型) | | |\n| MCP | MCP | | | |\n| PR | PR | PR(Pull Request) | | |\n| RAG | RAG | RAG(检索增强生成) | | |\n| SDK | SDK | | | |\n| SSE | SSE | SSE(Server-Sent Events) | | |\n\n## 英文类(中英文文本中均使用英文)\n\n| English | 中文 | 首次出现 | 不要译作 | 备注 |\n|---|---|---|---|---|\n| agent | agent | agent(智能体) | | |\n| Agent Note | Agent Note | Agent Note(agent 决策记录) | 智能体注记、智能体笔记 | 本仓库中由 agent 撰写的提案与决策记录 |\n| agent harness | agent harness | agent harness(智能体框架) | | agent 组合词(agent harness/workflow/loop/skill 等)整体保留英文;未括注过 agent 时首现按对应组合词或 agent 行处理 |\n| agent loop | agent loop | agent loop(智能体循环) | | |\n| backlog | backlog | backlog(待翻清单) | | 仅在双语翻译语境里括注`待翻清单` |\n| blob hash | blob hash | | | `git hash-object` 的结果 |\n| Cordis | Cordis | | | |\n| dispose | dispose | dispose(资源释放) | | |\n| doc-sync | doc-sync | doc-sync(文档同步门禁) | | |\n| fiber | fiber | | | |\n| fixture | fixture | fixture(测试前置数据) | | |\n| fork | fork | | | |\n| Function Calling | Function Calling | Function Calling(函数调用) | | |\n| harness | harness | | | |\n| harness engineering | harness engineering | | | |\n| lint | lint | | | |\n| mock | mock | | | 保留英文;指测试替身 |\n| loader | loader | | | |\n| manifest | manifest | manifest(元数据清单) | | |\n| monorepo | monorepo | | | |\n| Round | Round | | 回合、目标回合、Ralph 回合 | 外层策略使用 Round 时,领域层级为 Session > Round > Turn(轮次) > Step(步骤);Round 是可选的外层策略迭代,并非每个会话轮次都具有的通用层级。Goal Round 与 Ralph Round 均保留英文。一个 Round 承载一个轮次,步骤隶属于该轮次;明确的零步骤轮次仍保持原义。 |\n| schema | schema | | | |\n| schema DSL | schema DSL | | | |\n| seam | seam | | | 与 `extension point` 是不同概念;根据具体语境,可译为`服务边界`或`可替换点` |\n| skill | skill | skill(技能) | | |\n| spawn | spawn | | | |\n| steering | steering | steering(中途引导) | | |\n| task id | task id | | 任务 id | 保留英文 |\n| subagent | subagent | | | |\n| thinking | thinking | | | API 字段保留英文;描述模型模式时译为`思考` |\n| transcript | transcript | transcript(文本记录) | | 指会话渲染给用户或编辑器的完整文本,区别于事件日志 |\n| waterfall | waterfall | waterfall(瀑布式事件) | | |\n| wheel | wheel 包 | | | Python 打包格式 |\n| worktree | worktree | | | git 工作区概念 |\n| Zstandard | Zstandard | | | RFC 8878 compression format; `zstd` remains a code value. |\n\n## 双语类(中英文文本各自使用中英文)\n\n| English | 中文 | 首次出现 | 不要译作 | 备注 |\n|---|---|---|---|---|\n| adapter | 适配器 | | | |\n| adapter contract | 适配器契约 | 适配器契约(adapter contract) | | |\n| append-only | 仅追加 | | | |\n| artifact | 产物 | | | |\n| backend | 后端 | | | |\n| background task | 后台任务 | | | |\n| block | 块 | | | |\n| build target | 构建目标 | | | |\n| cancel | 取消 | | | |\n| feature | 功能 | | 能力 | SDK 产品与工程模型中的可管理产品单元 |\n| feature option | 功能选项 | | variant | 一项 SDK 功能内有限、可选择的实现或配置 |\n| checkpoint | 检查点 | | | |\n| chunk | 分片 | | | |\n| compaction | 压缩 | 压缩(compaction) | | |\n| companion tool | 配套工具 | | | |\n| Cordis plugin config | Cordis 插件配置 | | | Cordis 插件公开的 `Config` 对象或配置结构 |\n| config key | 配置键 | | | Cordis 插件配置中的单个字段 |\n| consumer | 消费方 | | | |\n| content block | 内容块 | | | |\n| Cookbook | 实操手册 | | | 文档标题用语 |\n| context | 上下文 | | | |\n| counterpart | 对侧文件 | | 对应物、配对物 | 双语配对语境;泛指\"另一侧\"时可写「另一侧」 |\n| context compaction | 上下文压缩 | 上下文压缩(context compaction) | | |\n| contract | 契约 | | | 如:`pairing contract` →`配对契约` |\n| Cordis config entry | Cordis 配置项 | | | 指 `cordis.yml` 插件列表中的一项;插件实现本身写`Cordis 插件` |\n| Cordis plugin | Cordis 插件 | | | Cordis 加载的插件实现,不指 `cordis.yml` 中的一项配置 |\n| coverage | 覆盖率 | | | |\n| crash recovery | 崩溃恢复 | | | |\n| deploy root | 部署根目录 | | | |\n| durability | 持久性 | | | |\n| feature requirement | 功能依赖 | | | 功能或功能选项通过 `requires` 声明的关系 |\n| enforcement frontier | 执行红线 | | 强制边界 | i18n 配对机制用语:manifest `required` 清单所划的门禁生效范围;与金标样例(style-samples ⑦)一致 |\n| ergonomics | 易用性 / 开发体验 | | 人体工学 | API 或面向模型的接口用「易用性」;工具链或开发者工作流用「开发体验」 |\n| event | 事件 | | | |\n| event log | 事件日志 | | | |\n| event stream | 事件流 | | | |\n| event-sourced | 事件溯源 | | | 沿用 DDD 社区通行译法 |\n| Executive summary | 摘要 | | | 事故复盘标题用语 |\n| executor | 执行器 | | | |\n| expected output | 预期输出 | | 金标 | 指 snapshot 比较产物;翻译语料的人工校准样例不在此列 |\n| extension | 扩展 | | | |\n| extension point | 扩展点 | | | 注意与 `seam` 区分 |\n| fail-fast | 快速失败 | | | |\n| fenced code block | 围栏代码块 | | | 沿用 MDN 中文翻译 |\n| fingerprint | 指纹 | | | 通用内容指纹;双语配对机制使用 sidecar record 记录两侧 blob hash |\n| finish reason | 结束原因 | | | |\n| foreground run | 前台运行 | | | |\n| freshness | 新鲜度 | | | 沿用 MDN 中文翻译;在本项目中指译文相对源文的同步状态 |\n| hook | 钩子 | | | |\n| implementation | 实现 | | | |\n| inference | 推理 | 推理(inference) | | 需要和 `reasoning` 区分时保留英文括注 |\n| info string | 信息字符串 | | | 沿用 CommonMark 中文翻译;指代码围栏 ``` 之后的语言标注 |\n| injection | 注入 | | | |\n| integration | 集成 | | | |\n| interface | 接口 | | | |\n| language switcher | 语言切换行 | | | i18n 配对机制用语:双语配对文件顶部的互链行 |\n| memory | 记忆 / 内存 | | | 与 `agent` 搭配时译为`记忆`(如 `agent memory` →`智能体记忆`);指系统资源时译为`内存` |\n| merge | 合并 | | | |\n| message | 消息 | | | |\n| mod | 模组 | | | |\n| model provider | 模型提供方 | | | |\n| module | 模块 | | | |\n| non-escalation | 非升权 | | 非升级、不可升级 | 仅用于安全与权限语境,指主体不得获得超出既有授权的权限;普通升级不适用此行 |\n| npm dependency | NPM 依赖 | | | `package.json` 中的包关系;`dependencies`、`devDependencies` 等字段保持原样 |\n| opt-out ratio | opt-out 比例 | | 退出检查比例 | |\n| orphan | 遗留 | | 孤儿、孤立 | 指英文源已不存在的 `.zh.md`(如「遗留译文」);进程语境按 OS 惯用语译「孤儿进程」 |\n| orphan branch | 孤立分支 | | 孤儿分支 | 沿用 git 官方中文翻译 |\n| package | 包 | 包(package) | | 指 npm 包(`@deepseek-ai/dsh-*`);`package.json` 等代码标识保持原样 |\n| pairing | 配对 | | | |\n| parent-subset grants | 父级子集授权 | | 父集合授权 | 指授权范围仅限于父级所持授权的子集 |\n| peer dependency | 对等依赖 | 对等依赖(peer dependency) | | |\n| permission | 权限 | | | |\n| persistence | 持久化 | | | |\n| pipeline | 流水线 | | | |\n| plugin | 插件 | | | |\n| prompt | 提示词 | | | |\n| provider | 提供方 | | | |\n| provider-neutral | 提供方无关 | | | |\n| quality gate | 质量门禁 | | | |\n| quiescence | 完全停稳 | | 静默、静止状态 | 指生命周期工作全部结算后的状态 |\n| reasoning | 推理 | 推理(reasoning) | | 需要和 `inference` 区分时保留英文括注 |\n| reasoning_content | 思考内容 | | | |\n| registry | 注册表 | | | |\n| replay | 回放 | | | |\n| resume | 恢复 | | | |\n| runtime | 运行时 | | | |\n| same-world subprocess | 与宿主共享文件系统和内核的子进程 | | 同世界子进程 | |\n| sandbox | 沙箱 | | | |\n| service | 服务 | | | |\n| serving surface | 对外服务接口 | | | |\n| session | 会话 | | | |\n| session event | 会话事件 | | | |\n| sidecar record | 伴随记录 | | 旁挂记录 | 指与文档同目录的伴随记录文件 |\n| smoke test | 冒烟测试 | | | |\n| snapshot | 快照 | | | |\n| source of truth | 真源 | | | |\n| spine | 主干 | | | |\n| staged | 暂存 | | | 沿用 git 官方中文翻译 |\n| stale | 陈旧 | | 过期 | 与 `fresh`(`新鲜`)成对;门禁输出中保留英文 `stale` 不翻译;`expired` 才译为`过期` |\n| step | 步骤 | | | |\n| stream | 流 | | | |\n| streaming | 流式输出 | | | |\n| structural signature | 结构签名 | | | i18n 配对机制用语:门禁比对两侧文件时提取的有序结构序列(标题层级、代码块、列表等) |\n| Summary | 概述 | | | 事故复盘标题用语 |\n| system prompt | 系统提示词 | | | |\n| taxonomy | 分类体系 | | | |\n| token usage | token 用量 | | | |\n| tool | 工具 | | | |\n| tool call | 工具调用 | | | |\n| tool result | 工具结果 | | | |\n| tool schema | 工具 schema | | | |\n| toolkit | 工具包 | | | |\n| turn | 轮次 | | | |\n| VFS | VFS | 虚拟文件系统(VFS) | | |\n| typecheck | 类型检查 | | | |\n| vocabulary | 词汇 | | | |\n| wire format | 协议格式 | 协议格式(wire format) | | |\n| workflow | 工作流 | | | |\n| wrapper | 包装层 | | | 软件层或 SDK 包装层 |\n| wrapper script | 包装脚本 | | | 可执行脚本包装层 |\n\n\n## Output Format\n\nProduce your output in three XML sections:\n\nThe outer section tags are framing. If Markdown inside any section body contains a line consisting only of `<translation>`, `</translation>`, `<review>`, `</review>`, `<final>`, or `</final>`, prefix that line with `\\`. If the original line already has one or more backslashes immediately before the tag, add one more. The parser removes exactly one framing escape; tags mentioned inline need no escaping.\n\n```xml\n<translation>\n(Complete translation of the source document)\n</translation>\n\n<review>\n(Self-review notes, one correction per line with category tag, e.g.)\n- [Tone] \"旁挂记录\" → \"伴随记录\"(生造词)\n- [Sentence] 第 3 段补充逗号断句\n- [Punctuation] 两处破折号替换为冒号\n- 无修正\n</review>\n\n<final>\n(Final translation after corrections)\n</final>\n```\n\n## Self-Review Instructions\n\nAfter writing `<translation>`, re-read it in the target language only, without looking at the source. Check by category:\n\n**Structure**\n- Is the heading hierarchy, list shape, and code block content identical to the source?\n- Are ALL comments inside code blocks left untranslated (byte-identical to source)?\n- Is the language switcher line correctly flipped (not copied from source)?\n- Are link targets preserved, and are spaces after bold markers present only before Latin letters, digits, or CJK ideographs?\n- Are wrapper-tag lines inside section bodies escaped with one additional backslash?\n\n**Tone & Style**\n- Does every sentence read as if originally written by a native speaker?\n- Is there any colloquial, casual, or overly informal phrasing?\n\n**Sentence Structure**\n- Are there run-on sentences that need breaking?\n- Are there stiff passive constructions that should be converted to active voice?\n\n**Word Choice**\n- Are there overly literal translations that sound unnatural?\n- Is the same target-language word used to translate two distinct source concepts?\n- Is any slang or internal jargon present?\n\n**Terminology**\n- For a Chinese target, are first-occurrence glosses correctly applied (not missing, not repeated)? For an English target, are Chinese glosses absent?\n- Are any \"不要译作\" forbidden translations present?\n- For unlisted terms, does a Chinese target use established Chinese precedent or retain the source term as pending, and does an English target use established English terminology or preserve only an ambiguous source term with a short English gloss?\n\n**Punctuation** (when target is Chinese)\n- Are there em-dashes that should be replaced with colons, periods, or commas?\n- Are list items ending with commas instead of semicolons?\n- Do RFC 2119 keywords preserve the source emphasis exactly?\n\nRecord corrections in `<review>` with category tags. Then output the corrected version in `<final>`. If no corrections are needed, write \"无修正\" in `<review>` and copy the translation unchanged into `<final>`.\n\n## Examples\n\nBelow are representative examples of common problems and their corrections. Follow the \"Good\" versions.\n\n### Colloquial verb → Professional verb\n- Source: `The repo pins pnpm@11.7.0 in package.json`\n- Bad: `仓库在 package.json 中钉住 pnpm@11.7.0`\n- Good: `该仓库在 package.json 中固定使用 pnpm@11.7.0`\n\n### Run-on sentence → Natural phrasing with pause\n- Source: `Read docs/architecture.md before changing anything under packages/.`\n- Bad: `改动 packages/ 下的任何东西之前先读 docs/architecture.md。`\n- Good: `在修改 packages/ 目录下的任何内容之前,请先阅读 docs/architecture.md。`\n\n### Stiff passive voice → Active and natural\n- Source: `a green gate means the pair was confirmed consistent at these exact contents, not that the confirmation was sound.`\n- Bad: `门禁绿意味着这对文档曾在当前内容上被确认一致,不意味着这次确认本身是对的。`\n- Good: `门禁通过意味着这组文档在当前内容上的一致性得到了确认,不代表确认本身正确可靠。`\n\n### Invented word → Natural expression\n- Source: `A sidecar record of both blob hashes makes consistency checkable`\n- Bad: `旁挂记录两侧 blob hash,使一致性可检查`\n- Good: `伴随记录保存两侧 blob hash,使一致性可检查`\n\n### Em-dash → Colon/period\n- Source: `FIXME — an issue that should block a new release. A release should not ship with an open FIXME unless reviewers explicitly agree the change can be merged anyway.`\n- Bad: `FIXME——应当阻塞新版本发布的问题。除非评审者明确同意可以照常合入,发布不应带着未解决的 FIXME 出门。`\n- Good: `FIXME:应当阻塞新版本发布的问题。除非评审者明确同意该更改可以合并,否则发布版本不应包含未解决的 FIXME。`\n\n### Overly literal → Meaningful rendering\n- Source: `awkward phrasing is easier to hear without the source anchoring you`\n- Bad: `没有源文锚着,别扭的表述更容易被听出来`\n- Good: `不对照原文时,更容易察觉别扭的表达`\n\n### Terminology — do not translate what should be kept in English\n- Source: `typed service seams, and explicit extension points`\n- Bad: `类型化的服务 seam(扩展点)与显式扩展点`\n- Good: `类型化的服务 seam 与显式扩展点`\n\n### Slang/jargon → Professional phrasing\n- Source: `The committed agent workflow lives in .agents/skills/dsh-translate-docs`\n- Bad: `进仓的 agent 工作流见 .agents/skills/dsh-translate-docs`\n- Good: `仓库内置的 agent 工作流见 .agents/skills/dsh-translate-docs`\n\n### \"For humans\" — translate the intent, not the word\n- Source: `For humans, start with the development guide`\n- Bad: `对于人工读者,请先从开发指南开始`(\"人工读者\"生硬)\n- Good: `面向开发者:请先阅读开发指南`(\"开发者\"自然,且中文里冒号在此处更自然)\n\n### Code block comments — NEVER translate\n- Source code block contains: `# full-screen TUI coding agent (needs DEEPSEEK_API_KEY)`\n- Bad: `# 全屏 TUI coding agent(需要 DEEPSEEK_API_KEY)`\n- Good: `# full-screen TUI coding agent (needs DEEPSEEK_API_KEY)` (keep exactly as-is, byte-for-byte)\n\n### Language switcher — flip direction\n- Source file (English) has: `English | [中文](README.zh.md)`\n- Bad (copying source unchanged): `English | [中文](README.zh.md)`\n- Good (flipped for Chinese file): `[English](README.md) | 中文`\n\n---\n\nNow translate the following document:" }, { "role": "user", @@ -24,11 +24,11 @@ }, { "role": "user", - "content": "# Bilingual documentation\n\nEnglish | [中文](README.zh.md)\n\nThis repo's documentation is read by people and agents both inside and outside the company, so the README, Agent Notes, and docs tree are maintained in English and Simplified Chinese. This page defines the pairing contract, the enforcement gate, and the rollout policy; [translation-rules.md](translation-rules.md) defines how to translate; [terminology.md](terminology.md) is the terminology source of truth. The committed agent workflow lives in [.agents/skills/dsh-translate-docs](../../.agents/skills/dsh-translate-docs/SKILL.md).\n\n## The pairing contract\n\n- **Both languages carry equal authority.** A document may be authored and reviewed in either language first — a Chinese-first Agent Note is as legitimate as an English-first one — and the counterpart is translated from it. Neither file outranks the other; what binds them is that they must say the same thing.\n- **A pair is three sibling files.** The English `foo.md`, the Chinese `foo.zh.md`, and a consistency record `foo.i18n.yaml`, all in the same directory. No locale directories, no separate translation repo, no interleaved bilingual files. Pairs merge whole: a PR never lands one language without the other two files.\n- **The consistency record.** `foo.i18n.yaml` holds the full git blob hash of each side as of the last time the two were confirmed to say the same thing:\n\n ```yaml\n foo.md: 3f786850e387550fdab836ed7e6dc881de23001b\n foo.zh.md: 89e6c98d92887913cadf06b2adb97f26cde4849b\n ```\n\n Blob hashes, not commit hashes, so the record is computable for files edited in the same PR (`git hash-object foo.md`) and consistency is a pure content comparison. The recorded hash also recovers the exact last-confirmed text of either side (`git cat-file -p <hash>`), so an out-of-sync pair is updated by diffing the edited side against its last-confirmed state and patching the counterpart minimally — never by re-translating whole files. After bringing the pair back in line, `pnpm run verify-translation-pairing --write` re-records both hashes; that yaml diff is the reviewable act of confirming consistency.\n- **Language switcher.** Both files link to each other immediately after their H1 heading: the English file carries `English | [中文](foo.zh.md)` and the Chinese file carries `[English](foo.md) | 中文`.\n- **Structure mirrors the counterpart.** Heading depths and order, list kinds, ordered-list starts, list item counts, table row and column counts, link targets, and verbatim code blocks match one to one across the pair — see [translation-rules.md](translation-rules.md) for the full preservation rules. Existing Markdown gates apply to `.zh.md` files unchanged (`verify-md-wrap`, `verify-md-links`).\n\n## The gate: verify-translation-pairing\n\n`pnpm run verify-translation-pairing` (part of `doc-sync`, which contributors run locally for documentation changes and CI runs exhaustively) enforces the contract mechanically:\n\n1. Every file listed as `required` in [scripts/translation-pairing.manifest.json](../../scripts/translation-pairing.manifest.json) has a complete pair.\n2. Every pair that exists at all — required or not — is complete and consistent: all three files present, each side's current blob hash equals the recorded one (editing either side without re-confirming the pair goes red), both sides carry the language switcher, and the structural signatures match in order — heading depths, verbatim code blocks (info string and content), table row and column counts, list kinds, ordered-list starts, item counts, and every link target apart from the switcher.\n3. Files listed as `excluded` have no `.zh.md` and no `.i18n.yaml` at all.\n4. Every date-named document (`yyyy-mm-dd-*.md`) dated on or after the manifest's `requiredSince` cutoff has a complete pair — new date-named Agent Notes merge bilingual from birth.\n\n`pnpm run verify-translation-pairing --list` prints the current pairing state of every document in scope — missing, out-of-sync, or ok — and is the work list for translation batches. It never fails; it reports.\n\nThe practical rule this gate creates: **when a PR edits either side of a paired document, the same PR updates the counterpart and re-records the pair** (run the [dsh-translate-docs](../../.agents/skills/dsh-translate-docs/SKILL.md) skill, then `--write`), exactly like the repo's existing doc-sync rule for code and READMEs. A PR that leaves a pair out of sync goes red in CI.\n\nThe gate's limit, stated plainly: **a green gate means the pair was confirmed consistent at these exact contents, not that the confirmation was sound.** It checks hashes and shape; it cannot judge whether the two sides actually say the same thing, or whether the wording is accurate, well-termed, and natural — that is the reviewer's half of the contract, per [translation-rules.md](translation-rules.md). A re-recorded pair with a sloppy counterpart passes the gate; it must not pass review.\n\n## Scope, exclusions, and rollout\n\n**Scope**: the root `README.md`, everything under `.agents/notes/**`, `docs/**`, and `python/**`. Package READMEs (`packages/**`) join the scope in a later batch.\n\n**Excluded** (never paired, and the gate rejects a `.zh.md` or `.i18n.yaml` for them):\n\n- `docs/cordis-catalog/`, `docs/tool-catalog/`, `docs/config-catalog.md`, `docs/persistence-catalog.md`, and `docs/module-graph.md` — generated files; their generators emit English only today, so a hand-written translation would go stale on every regeneration. The planned follow-up is to teach the generators to emit Chinese alongside English, at which point these leave the exclusion list.\n- `docs/AGENTS.md` and `.agents/notes/**/AGENTS.md` — agent instructions, maintained in English only like the root `AGENTS.md`.\n- `docs/i18n/terminology.md` and [style-samples.md](style-samples.md) — both are bilingual by construction.\n- [translation-prompt.md](translation-prompt.md) — the automated pipeline's prompt template; its body is machine-consumed verbatim, so a paired translation would change pipeline behavior.\n\n**Rollout**: a date-named document (`yyyy-mm-dd-*.md`, i.e. an Agent Note) dated on or after the manifest's `requiredSince` cutoff must merge with its pair. Earlier dates are backlog, including files created on the cutoff's eve. An Agent Note filename records its first-proposed date, so backdating past the cutoff is a review-visible violation. The manifest's `required` list is the current enforcement frontier, not the goal of full coverage. Translation batches add paths to `required`, ratcheting the gate forward. Unlisted documents remain visible in `--list`, while every existing pair is governed by the full contract. Because later edits must update both sides, expand `required` only as fast as translation review can support.\n\n## Division of labor\n\nCounterparts here are produced by an agent running [dsh-translate-docs](../../.agents/skills/dsh-translate-docs/SKILL.md) and reviewed by a human — inference is cheap here, review attention is the scarce resource. The gate checks pair completeness, recorded hashes, switchers, and its documented structural signature. Review still owns translation quality, terminology, and structural requirements that the signature does not encode. The prompt contract is executable: [scripts/translation-prompt.ts](../../scripts/translation-prompt.ts) renders the committed template (terminology injected; the template carries its own calibrated rules) into either direction and parses the three-section response, while `verify-translation-prompt` exercises both render directions and the checked-in example in `doc-sync`.\n" + "content": "# Bilingual documentation\n\nEnglish | [中文](README.zh.md)\n\nThis repo's documentation is read by people and agents both inside and outside the company, so the README, Agent Notes, and docs tree are maintained in English and Simplified Chinese. This page defines the pairing contract, the enforcement gate, and the rollout policy; [translation-rules.md](translation-rules.md) defines how to translate; [terminology.md](terminology.md) is the terminology source of truth. The committed agent workflow lives in [.agents/skills/dsh-translate-docs](../../.agents/skills/dsh-translate-docs/SKILL.md).\n\n## The pairing contract\n\n- **Both languages carry equal authority.** A document may be authored and reviewed in either language first — a Chinese-first Agent Note is as legitimate as an English-first one — and the counterpart is translated from it. Neither file outranks the other; what binds them is that they must say the same thing.\n- **A pair is three sibling files.** The English `foo.md`, the Chinese `foo.zh.md`, and a consistency record `foo.i18n.yaml`, all in the same directory. No locale directories, no separate translation repo, no interleaved bilingual files. Pairs merge whole: a PR never lands one language without the other two files.\n- **The consistency record.** `foo.i18n.yaml` holds the full git blob hash of each side as of the last time the two were confirmed to say the same thing:\n\n ```yaml\n foo.md: 3f786850e387550fdab836ed7e6dc881de23001b\n foo.zh.md: 89e6c98d92887913cadf06b2adb97f26cde4849b\n ```\n\n Blob hashes, not commit hashes, so the record is computable for files edited in the same PR (`git hash-object foo.md`) and consistency is a pure content comparison. The recorded hash also recovers the exact last-confirmed text of either side (`git cat-file -p <hash>`), so an out-of-sync pair is updated by diffing the edited side against its last-confirmed state and patching the counterpart minimally — never by re-translating whole files. After bringing the pair back in line, `pnpm run verify-translation-pairing --write` re-records both hashes; that yaml diff is the reviewable act of confirming consistency.\n- **Language switcher.** Both files link to each other immediately after their H1 heading: the English file carries `English | [中文](foo.zh.md)` and the Chinese file carries `[English](foo.md) | 中文`.\n- **Structure mirrors the counterpart.** Heading depths and order, list kinds, ordered-list starts, list item counts, table row and column counts, link targets, and verbatim code blocks match one to one across the pair — see [translation-rules.md](translation-rules.md) for the full preservation rules. Existing Markdown gates apply to `.zh.md` files unchanged (`verify-md-wrap`, `verify-md-links`).\n\n## The gate: verify-translation-pairing\n\n`pnpm run verify-translation-pairing` (part of `doc-sync`, which contributors run locally for documentation changes and CI runs exhaustively) enforces the contract mechanically:\n\n1. Every file listed as `required` in [scripts/translation-pairing.manifest.json](../../scripts/translation-pairing.manifest.json) has a complete pair.\n2. Every pair that exists at all — required or not — is complete and consistent: all three files present, each side's current blob hash equals the recorded one (editing either side without re-confirming the pair goes red), both sides carry the language switcher, and the structural signatures match in order — heading depths, verbatim code blocks (info string and content), table row and column counts, list kinds, ordered-list starts, item counts, and every link target apart from the switcher.\n3. Files listed as `excluded` have no `.zh.md` and no `.i18n.yaml` at all.\n4. Every date-named document (`yyyy-mm-dd-*.md`) dated on or after the manifest's `requiredSince` cutoff has a complete pair — new date-named Agent Notes merge bilingual from birth.\n\n`pnpm run verify-translation-pairing --list` prints the current pairing state of every document in scope — missing, out-of-sync, or ok — and is the work list for translation batches. It never fails; it reports.\n\nThe practical rule this gate creates: **when a PR edits either side of a paired document, the same PR updates the counterpart and re-records the pair** (run the [dsh-translate-docs](../../.agents/skills/dsh-translate-docs/SKILL.md) skill, then `--write`), exactly like the repo's existing doc-sync rule for code and READMEs. A PR that leaves a pair out of sync goes red in CI.\n\nThe gate's limit, stated plainly: **a green gate means the pair was confirmed consistent at these exact contents, not that the confirmation was sound.** It checks hashes and shape; it cannot judge whether the two sides actually say the same thing, or whether the wording is accurate, well-termed, and natural — that is the reviewer's half of the contract, per [translation-rules.md](translation-rules.md). A re-recorded pair with a sloppy counterpart passes the gate; it must not pass review.\n\n## Scope, exclusions, and rollout\n\n**Scope**: the root `README.md`, everything under `.agents/notes/**`, `docs/**`, and `python/**`. Package READMEs (`packages/**`) join the scope in a later batch.\n\n**Excluded** (never paired, and the gate rejects a `.zh.md` or `.i18n.yaml` for them):\n\n- `docs/cordis-catalog/`, `docs/tool-catalog/`, `docs/config-catalog.md`, `docs/persistence-catalog.md`, `docs/module-graph.md`, `docs/agent-lifecycle.md`, `docs/capability-seams.md`, `docs/event-producer-consumer.md`, `docs/graph-atlas.md`, and `docs/tool-execution-pipeline.md` — generated files; their generators emit English only today, so a hand-written translation would go stale on every regeneration. The planned follow-up is to teach the generators to emit Chinese alongside English, at which point these leave the exclusion list.\n- `docs/AGENTS.md` and `.agents/notes/**/AGENTS.md` — agent instructions, maintained in English only like the root `AGENTS.md`.\n- `docs/i18n/terminology.md` and [style-samples.md](style-samples.md) — both are bilingual by construction.\n- [translation-prompt.md](translation-prompt.md) — the automated pipeline's prompt template; its body is machine-consumed verbatim, so a paired translation would change pipeline behavior.\n\n**Rollout**: a date-named document (`yyyy-mm-dd-*.md`, i.e. an Agent Note) dated on or after the manifest's `requiredSince` cutoff must merge with its pair. Earlier dates are backlog, including files created on the cutoff's eve. An Agent Note filename records its first-proposed date, so backdating past the cutoff is a review-visible violation. The manifest's `required` list is the current enforcement frontier, not the goal of full coverage. Translation batches add paths to `required`, ratcheting the gate forward. Unlisted documents remain visible in `--list`, while every existing pair is governed by the full contract. Because later edits must update both sides, expand `required` only as fast as translation review can support.\n\n## Division of labor\n\nCounterparts here are produced by an agent running [dsh-translate-docs](../../.agents/skills/dsh-translate-docs/SKILL.md) and reviewed by a human — inference is cheap here, review attention is the scarce resource. The gate checks pair completeness, recorded hashes, switchers, and its documented structural signature. Review still owns translation quality, terminology, and structural requirements that the signature does not encode. The prompt contract is executable: [scripts/translation-prompt.ts](../../scripts/translation-prompt.ts) renders the committed template (terminology injected; the template carries its own calibrated rules) into either direction and parses the three-section response, while `verify-translation-prompt` exercises both render directions and the checked-in example in `doc-sync`.\n" }, { "role": "assistant", - "content": "# 双语文档\n\n[English](README.md) | 中文\n\n本仓库的文档会被公司内外的人和 agent(智能体)阅读,因此 README、Agent Note(agent 决策记录)与 docs 目录树以英文和简体中文双语维护。本页定义配对契约、强制门禁与推进策略;[translation-rules.md](translation-rules.md) 定义如何翻译;[terminology.md](terminology.md) 是术语真源。仓库内置的 agent 工作流见 [.agents/skills/dsh-translate-docs](../../.agents/skills/dsh-translate-docs/SKILL.md)。\n\n## 配对契约\n\n- **两种语言同权。** 一篇文档可以先用任一语言撰写和评审(先写中文的 Agent Note 与先写英文的一样正当),另一侧由它翻译而来。两个文件谁也不高于谁;约束它们的是二者必须说同样的话。\n- **一对文档是三个同目录文件。** 英文 `foo.md`、中文 `foo.zh.md`,加一份一致性记录 `foo.i18n.yaml`,都在同一目录。不用语言目录,不用独立翻译仓库,不用中英混排的单文件。配对必须整体合并:PR(Pull Request)永远不会只带一种语言而缺其余两个文件。\n- **一致性记录。**`foo.i18n.yaml` 保存两侧文件在上一次被确认「说同样的话」时各自的完整 git blob hash:\n\n ```yaml\n foo.md: 3f786850e387550fdab836ed7e6dc881de23001b\n foo.zh.md: 89e6c98d92887913cadf06b2adb97f26cde4849b\n ```\n\n 用 blob hash 而不是 commit hash,这样同一个 PR 里改动的文件也能算出记录(`git hash-object foo.md`),一致性是纯内容比较。记录的 hash 还能还原任一侧上次确认时的确切文本(`git cat-file -p <hash>`),所以失去同步的配对是「把被改的一侧与其上次确认状态做 diff、再最小化地修补另一侧」,从不整篇重译。两侧对齐后,`pnpm run verify-translation-pairing --write` 重新记录两个 hash;那份 yaml diff 就是「确认一致」这个动作本身,可以被评审。\n- **语言切换行。** 两个文件在各自 H1 标题之后立即互链:英文文件带 `English | [中文](foo.zh.md)`,中文文件带 `[English](foo.md) | 中文`。\n- **结构与另一侧一一对应。** 标题深度与顺序、列表类型、有序列表起始编号、列表项数量、表格行列数、链接目标与逐字节一致的代码块在配对两侧一一对应;完整保持规则见 [translation-rules.md](translation-rules.md)。既有 Markdown 门禁对 `.zh.md` 文件原样生效(`verify-md-wrap`、`verify-md-links`)。\n\n## 门禁:verify-translation-pairing\n\n`pnpm run verify-translation-pairing`(`doc-sync`(文档同步门禁)的一环,贡献者会针对文档变更在本地运行,CI 则会完整运行)机械地强制执行这份契约:\n\n1. [scripts/translation-pairing.manifest.json](../../scripts/translation-pairing.manifest.json) 中 `required` 列出的每个文件都有完整配对。\n2. 任何已存在的配对(无论是否 required)都完整且一致:三个文件齐全、每一侧的当前 blob hash 等于记录值(改了任一侧而没重新确认配对就变红)、双方都带语言切换行、结构签名按序一致:标题深度、逐字节一致的代码块(信息字符串与内容)、表格行列数、列表类型、有序列表起始编号、列表项数量,以及除切换行之外的每个链接目标。\n3. 列为 `excluded` 的文件完全没有 `.zh.md`,也没有 `.i18n.yaml`。\n4. 凡文件名符合 `yyyy-mm-dd-*.md` 且日期不早于 manifest(元数据清单)中 `requiredSince` 分界日期的文档,都必须有完整配对;新建的日期命名 Agent Note 从创建起便须配齐中英文。\n\n`pnpm run verify-translation-pairing --list` 打印范围内每篇文档的当前配对状态(missing、out-of-sync 或 ok),是翻译批次的工作清单。它从不失败;它只报告。\n\n这个门禁带来的实际规则是:**当一个 PR 修改了已配对文档的任一侧时,同一个 PR 更新另一侧并重新记录配对**(运行 [dsh-translate-docs](../../.agents/skills/dsh-translate-docs/SKILL.md) skill(技能),再 `--write`),与本仓库既有的代码与 README 的 doc-sync 规则完全一致。留下失去同步的配对的 PR 会在 CI 变红。\n\n把门禁的边界说白:**门禁通过意味着这组文档在当前内容上的一致性得到了确认,不代表确认本身正确可靠。** 它检查记录的 hash 与结构签名;它无法判断两侧是否真的在说同样的话,也无法判断措辞是否准确、术语是否得当、行文是否自然;这部分契约由评审者把关,见 [translation-rules.md](translation-rules.md)。重新记录了 hash 但另一侧翻得潦草的配对能通过门禁;它不得通过评审。\n\n## 范围、排除与推进\n\n**范围**:根 `README.md`,以及 `.agents/notes/**`、`docs/**` 与 `python/**` 下的全部内容。包(package)README(`packages/**`)在后续批次加入范围。\n\n**排除**(永不配对,门禁拒绝为它们建 `.zh.md` 或 `.i18n.yaml`):\n\n- `docs/cordis-catalog/`、`docs/tool-catalog/`、`docs/config-catalog.md`、`docs/persistence-catalog.md` 与 `docs/module-graph.md`:生成文件;生成器目前只输出英文,手写译文在每次重新生成时必然陈旧。计划中的后续工作是让生成器同时输出中文,届时这些文件移出排除清单。\n- `docs/AGENTS.md` 与 `.agents/notes/**/AGENTS.md`:agent 指令,与根 `AGENTS.md` 一样只以英文维护。\n- `docs/i18n/terminology.md` 与 [style-samples.md](style-samples.md):二者本身即为中英对照文档。\n- [translation-prompt.md](translation-prompt.md):自动翻译流水线的提示词模板;正文逐字进入模型请求,配对翻译会改变流水线行为。\n\n**推进**:以日期命名的文档(`yyyy-mm-dd-*.md`,即 Agent Note),只要标注日期等于或晚于 manifest 的 `requiredSince` 分界日期,合并时就必须配齐双语文件。更早日期的文件属于 backlog(待翻清单),包括分界前夜创建的文件。Agent Note 文件名记录首次提出日期,因此倒填日期绕过分界属于评审可见的违规。manifest 中的 `required` 列表是当前执行红线,并非全量覆盖这一最终目标。翻译批次将路径加入 `required`,使门禁只向前收紧。未列入的文档仍可通过 `--list` 查看,而任何已存在的配对都受完整契约约束。后续修改必须同步更新两侧,因此 `required` 的扩展速度不能超过翻译评审的承载能力。\n\n## 分工\n\n这里的对侧文件由运行 [dsh-translate-docs](../../.agents/skills/dsh-translate-docs/SKILL.md) 的 agent 生成,再由人评审:在这里推理(inference)很便宜,评审注意力才是稀缺资源。门禁负责检查配对是否完整、记录的 hash、语言切换行以及本文列出的结构签名;翻译质量、术语和签名未涵盖的结构要求仍由评审把关。提示词契约也有可执行实现:[scripts/translation-prompt.ts](../../scripts/translation-prompt.ts) 会把仓库内置的模板(注入术语表;模板自带经人工校准的规则)渲染为英译中或中译英两个方向的提示词,并解析三段式响应;`doc-sync` 中的 `verify-translation-prompt` 会检查两个渲染方向与仓库内示例。\n" + "content": "# 双语文档\n\n[English](README.md) | 中文\n\n本仓库的文档会被公司内外的人和 agent(智能体)阅读,因此 README、Agent Note(agent 决策记录)与 docs 目录树以英文和简体中文双语维护。本页定义配对契约、强制门禁与推进策略;[translation-rules.md](translation-rules.md) 定义如何翻译;[terminology.md](terminology.md) 是术语真源。仓库内置的 agent 工作流见 [.agents/skills/dsh-translate-docs](../../.agents/skills/dsh-translate-docs/SKILL.md)。\n\n## 配对契约\n\n- **两种语言同权。** 一篇文档可以先用任一语言撰写和评审(先写中文的 Agent Note 与先写英文的一样正当),另一侧由它翻译而来。两个文件谁也不高于谁;约束它们的是二者必须说同样的话。\n- **一对文档是三个同目录文件。** 英文 `foo.md`、中文 `foo.zh.md`,加一份一致性记录 `foo.i18n.yaml`,都在同一目录。不用语言目录,不用独立翻译仓库,不用中英混排的单文件。配对必须整体合并:PR(Pull Request)永远不会只带一种语言而缺其余两个文件。\n- **一致性记录。**`foo.i18n.yaml` 保存两侧文件在上一次被确认「说同样的话」时各自的完整 git blob hash:\n\n ```yaml\n foo.md: 3f786850e387550fdab836ed7e6dc881de23001b\n foo.zh.md: 89e6c98d92887913cadf06b2adb97f26cde4849b\n ```\n\n 用 blob hash 而不是 commit hash,这样同一个 PR 里改动的文件也能算出记录(`git hash-object foo.md`),一致性是纯内容比较。记录的 hash 还能还原任一侧上次确认时的确切文本(`git cat-file -p <hash>`),所以失去同步的配对是「把被改的一侧与其上次确认状态做 diff、再最小化地修补另一侧」,从不整篇重译。两侧对齐后,`pnpm run verify-translation-pairing --write` 重新记录两个 hash;那份 yaml diff 就是「确认一致」这个动作本身,可以被评审。\n- **语言切换行。** 两个文件在各自 H1 标题之后立即互链:英文文件带 `English | [中文](foo.zh.md)`,中文文件带 `[English](foo.md) | 中文`。\n- **结构与另一侧一一对应。** 标题深度与顺序、列表类型、有序列表起始编号、列表项数量、表格行列数、链接目标与逐字节一致的代码块在配对两侧一一对应;完整保持规则见 [translation-rules.md](translation-rules.md)。既有 Markdown 门禁对 `.zh.md` 文件原样生效(`verify-md-wrap`、`verify-md-links`)。\n\n## 门禁:verify-translation-pairing\n\n`pnpm run verify-translation-pairing`(`doc-sync`(文档同步门禁)的一环,贡献者会针对文档变更在本地运行,CI 则会完整运行)机械地强制执行这份契约:\n\n1. [scripts/translation-pairing.manifest.json](../../scripts/translation-pairing.manifest.json) 中 `required` 列出的每个文件都有完整配对。\n2. 任何已存在的配对(无论是否 required)都完整且一致:三个文件齐全、每一侧的当前 blob hash 等于记录值(改了任一侧而没重新确认配对就变红)、双方都带语言切换行、结构签名按序一致:标题深度、逐字节一致的代码块(信息字符串与内容)、表格行列数、列表类型、有序列表起始编号、列表项数量,以及除切换行之外的每个链接目标。\n3. 列为 `excluded` 的文件完全没有 `.zh.md`,也没有 `.i18n.yaml`。\n4. 凡文件名符合 `yyyy-mm-dd-*.md` 且日期不早于 manifest(元数据清单)中 `requiredSince` 分界日期的文档,都必须有完整配对;新建的日期命名 Agent Note 从创建起便须配齐中英文。\n\n`pnpm run verify-translation-pairing --list` 打印范围内每篇文档的当前配对状态(missing、out-of-sync 或 ok),是翻译批次的工作清单。它从不失败;它只报告。\n\n这个门禁带来的实际规则是:**当一个 PR 修改了已配对文档的任一侧时,同一个 PR 更新另一侧并重新记录配对**(运行 [dsh-translate-docs](../../.agents/skills/dsh-translate-docs/SKILL.md) skill(技能),再 `--write`),与本仓库既有的代码与 README 的 doc-sync 规则完全一致。留下失去同步的配对的 PR 会在 CI 变红。\n\n把门禁的边界说白:**门禁通过意味着这组文档在当前内容上的一致性得到了确认,不代表确认本身正确可靠。** 它检查记录的 hash 与结构签名;它无法判断两侧是否真的在说同样的话,也无法判断措辞是否准确、术语是否得当、行文是否自然;这部分契约由评审者把关,见 [translation-rules.md](translation-rules.md)。重新记录了 hash 但另一侧翻得潦草的配对能通过门禁;它不得通过评审。\n\n## 范围、排除与推进\n\n**范围**:根 `README.md`,以及 `.agents/notes/**`、`docs/**` 与 `python/**` 下的全部内容。包(package)README(`packages/**`)在后续批次加入范围。\n\n**排除**(永不配对,门禁拒绝为它们建 `.zh.md` 或 `.i18n.yaml`):\n\n- `docs/cordis-catalog/`、`docs/tool-catalog/`、`docs/config-catalog.md`、`docs/persistence-catalog.md`、`docs/module-graph.md`、`docs/agent-lifecycle.md`、`docs/capability-seams.md`、`docs/event-producer-consumer.md`、`docs/graph-atlas.md` 与 `docs/tool-execution-pipeline.md`:生成文件;生成器目前只输出英文,手写译文在每次重新生成时必然陈旧。计划中的后续工作是让生成器同时输出中文,届时这些文件移出排除清单。\n- `docs/AGENTS.md` 与 `.agents/notes/**/AGENTS.md`:agent 指令,与根 `AGENTS.md` 一样只以英文维护。\n- `docs/i18n/terminology.md` 与 [style-samples.md](style-samples.md):二者本身即为中英对照文档。\n- [translation-prompt.md](translation-prompt.md):自动翻译流水线的提示词模板;正文逐字进入模型请求,配对翻译会改变流水线行为。\n\n**推进**:以日期命名的文档(`yyyy-mm-dd-*.md`,即 Agent Note),只要标注日期等于或晚于 manifest 的 `requiredSince` 分界日期,合并时就必须配齐双语文件。更早日期的文件属于 backlog(待翻清单),包括分界前夜创建的文件。Agent Note 文件名记录首次提出日期,因此倒填日期绕过分界属于评审可见的违规。manifest 中的 `required` 列表是当前执行红线,并非全量覆盖这一最终目标。翻译批次将路径加入 `required`,使门禁只向前收紧。未列入的文档仍可通过 `--list` 查看,而任何已存在的配对都受完整契约约束。后续修改必须同步更新两侧,因此 `required` 的扩展速度不能超过翻译评审的承载能力。\n\n## 分工\n\n这里的对侧文件由运行 [dsh-translate-docs](../../.agents/skills/dsh-translate-docs/SKILL.md) 的 agent 生成,再由人评审:在这里推理(inference)很便宜,评审注意力才是稀缺资源。门禁负责检查配对是否完整、记录的 hash、语言切换行以及本文列出的结构签名;翻译质量、术语和签名未涵盖的结构要求仍由评审把关。提示词契约也有可执行实现:[scripts/translation-prompt.ts](../../scripts/translation-prompt.ts) 会把仓库内置的模板(注入术语表;模板自带经人工校准的规则)渲染为英译中或中译英两个方向的提示词,并解析三段式响应;`doc-sync` 中的 `verify-translation-prompt` 会检查两个渲染方向与仓库内示例。\n" }, { "role": "user", @@ -40,11 +40,11 @@ }, { "role": "user", - "content": "# Agent Note: Bilingual documentation via paired sibling files and a pairing gate\n\nStatus: implemented\n\nEnglish | [中文](2026-07-02-bilingual-docs-and-pairing-gate.zh.md)\n\n## Problem\n\nThis repo's README and docs tree are read by people and agents inside and outside the company, in both English and Chinese. Maintaining a second language by hand, with no mechanism, is how translations rot: one side moves on, the other silently lies, and no gate notices. The repo's standing answer to invariants of this kind is to encode them as a mechanical check (see [quality gates](2026-06-11-quality-gates.md) and [doc-sync enforcement](2026-06-11-doc-sync-enforcement.md)), so the bilingual policy ships with one.\n\n## Decision\n\n- **Paired sibling files with equal authority.** A documentation pair is three sibling files: English `foo.md`, Chinese `foo.zh.md`, and a consistency record `foo.i18n.yaml`. Neither language is canonical — a document may be authored and reviewed Chinese-first and translated to English afterwards, or the reverse; what binds the pair is that both sides must say the same thing, and pairs merge whole (both languages plus the record, never one alone). Policy: [docs/i18n/README.md](../../../../docs/i18n/README.md); translation rules: [docs/i18n/translation-rules.md](../../../../docs/i18n/translation-rules.md); terminology source of truth: [docs/i18n/terminology.md](../../../../docs/i18n/terminology.md).\n- **A sidecar record of both blob hashes makes consistency checkable.** `foo.i18n.yaml` holds the full git blob hash of each side as of the last confirmed-consistent state. An edit to either side without re-confirming the pair is then mechanically detectable as a pure content comparison — no history lookup — and the hashes are computable for files edited in the same PR, which a commit-hash record is not. Re-recording (`verify-translation-pairing --write`) produces a reviewable yaml diff: confirming consistency is an explicit, visible act in the PR.\n- **`verify-translation-pairing` joins `doc-sync`.** The gate ([scripts/verify-translation-pairing.ts](../../../../scripts/verify-translation-pairing.ts)) enforces: required pairs exist, every existing pair is complete (all three files) and consistent (both hashes match, switcher links both ways, structural signatures identical), excluded (generated or bilingual-by-construction) files stay unpaired, and date-named documents on or after the manifest's `requiredSince` cutoff have complete pairs. The `required` list in [scripts/translation-pairing.manifest.json](../../../../scripts/translation-pairing.manifest.json) is a ratchet: each merged translation batch adds its files, so coverage only grows.\n- **Translation is agent work with human review.** The committed workflow is [.agents/skills/dsh-translate-docs](../../../skills/dsh-translate-docs/SKILL.md), following the same pattern as [dsh-code-review](../../../skills/dsh-code-review/SKILL.md): the skill carries the workflow and defers to the docs as sources of truth. The skill directs the orchestrating agent to delegate translation writing to a subagent.\n\n## Alternatives considered\n\n- **English as the canonical source with a fingerprint inside the translation** — the design first proposed for this Agent Note: `.zh.md` files carried an HTML comment recording the English source's blob hash, and translation flowed EN → ZH only. Revised in review: the team wants Chinese-first authoring (write and review a Chinese Agent Note, then translate to English) with the two languages holding equal authority, which a one-directional canonical model cannot express. The sidecar record covering BOTH sides replaced the in-file one-directional fingerprint; the blob-hash mechanics survived unchanged.\n- **Locale directories (`docs/en/` + `docs/zh/`, the Kubernetes/ECharts model)** — rejected: this repo has no docs-site framework to map locales to routes, moving every English file would churn every existing cross-reference, and `verify-md-links`/`verify-doc-refs` would need path-mapping logic instead of working unchanged.\n- **A separate translation repo (the PingCAP `docs`/`docs-cn` model)** — rejected: right for a docs product with independent release trains, overkill for a monorepo's own documentation; it also puts the translation outside the reach of this repo's gates.\n- **Interleaved bilingual files (single file, both languages)** — rejected: doubles every diff, breaks the one-line-per-paragraph convention's diff ergonomics, and makes partial inconsistency invisible.\n- **Commit-hash records (the MDN `l10n.sourceCommit` model)** — rejected in favor of blob hashes: a same-PR edit has no commit hash yet, so the MDN model cannot express \"consistent as of the state this PR introduces\", and verifying it requires git history instead of file content.\n- **Comparing git timestamps of the pair (no record)** — rejected: formatting-only edits would false-positive, and a counterpart committed after an unrelated edit would false-negative; content identity is the only signal that means what the gate claims.\n\n## Industry precedent\n\nPaired sibling files with locale suffixes are the dominant Chinese big-tech convention (ant-design `index.zh-CN.md`/`index.en-US.md`; arco-design `README.zh-CN.md` with a top-of-file switcher; Apache ShardingSphere's 387 `.cn.md`/`.en.md` pairs) — but none of those repos *enforce* pairing or consistency in CI; the convention holds by review alone. Consistency automation exists outside China: MDN's `l10n.sourceCommit` front-matter fingerprint, Vue's Ryu-Cho action (upstream-commit watcher that opens issues/PRs for stale translations), Kubernetes' localization drift scripts, and Microsoft's Azure co-op-translator (source-hash-driven LLM re-translation in CI). This design combines the two: the Chinese-ecosystem file layout with a hash-pair gate, plus a committed agent skill in place of a bot service.\n\n## Consequences\n\n- Editing either side of a paired document obligates the same PR to update the counterpart and re-record the pair — the gate makes the doc-sync rule bilingual, and CI (not reviewer memory) carries the invariant.\n- Every pair adds a third file to the tree. The record is machine-written (`--write`), so the cost is directory noise, not maintenance effort; in exchange, \"who confirmed these consistent, and when\" is answerable from git blame on the yaml.\n- When the two sides disagree, no mechanical rule picks a winner — the PR review does. That is the price of equal authority, accepted deliberately: the alternative (a canonical language) forbids Chinese-first authoring.\n- Generated docs (`cordis-catalog/`, `tool-catalog/`, `module-graph.md`) are excluded for now; the planned follow-up is to teach their generators to emit Chinese alongside English, at which point they leave the exclusion list.\n- Rollout is incremental by design: documents outside `required` are visible backlog (`--list`), not red CI, so pairs land in reviewable batches without a big-bang PR. A date-named document dated on or after the manifest's `requiredSince` cutoff merges bilingual or not at all, so new date-named Agent Notes do not enlarge that backlog.\n- The recorded hashes double as the update tool (`git cat-file -p <hash>` recovers either side's last-confirmed text for a minimal diff-based update), so re-translation of whole files is never forced by the mechanism.\n" + "content": "# Agent Note: Bilingual documentation via paired sibling files and a pairing gate\n\nStatus: implemented\n\nEnglish | [中文](2026-07-02-bilingual-docs-and-pairing-gate.zh.md)\n\n## Problem\n\nThis repo's README and docs tree are read by people and agents inside and outside the company, in both English and Chinese. Maintaining a second language by hand, with no mechanism, is how translations rot: one side moves on, the other silently lies, and no gate notices. The repo's standing answer to invariants of this kind is to encode them as a mechanical check (see [quality gates](2026-06-11-quality-gates.md) and [doc-sync enforcement](2026-06-11-doc-sync-enforcement.md)), so the bilingual policy ships with one.\n\n## Decision\n\n- **Paired sibling files with equal authority.** A documentation pair is three sibling files: English `foo.md`, Chinese `foo.zh.md`, and a consistency record `foo.i18n.yaml`. Neither language is canonical — a document may be authored and reviewed Chinese-first and translated to English afterwards, or the reverse; what binds the pair is that both sides must say the same thing, and pairs merge whole (both languages plus the record, never one alone). Policy: [docs/i18n/README.md](../../../../docs/i18n/README.md); translation rules: [docs/i18n/translation-rules.md](../../../../docs/i18n/translation-rules.md); terminology source of truth: [docs/i18n/terminology.md](../../../../docs/i18n/terminology.md).\n- **A sidecar record of both blob hashes makes consistency checkable.** `foo.i18n.yaml` holds the full git blob hash of each side as of the last confirmed-consistent state. An edit to either side without re-confirming the pair is then mechanically detectable as a pure content comparison — no history lookup — and the hashes are computable for files edited in the same PR, which a commit-hash record is not. Re-recording (`verify-translation-pairing --write`) produces a reviewable yaml diff: confirming consistency is an explicit, visible act in the PR.\n- **`verify-translation-pairing` joins `doc-sync`.** The gate ([scripts/verify-translation-pairing.ts](../../../../scripts/verify-translation-pairing.ts)) enforces: required pairs exist, every existing pair is complete (all three files) and consistent (both hashes match, switcher links both ways, structural signatures identical), excluded (generated or bilingual-by-construction) files stay unpaired, and date-named documents on or after the manifest's `requiredSince` cutoff have complete pairs. The `required` list in [scripts/translation-pairing.manifest.json](../../../../scripts/translation-pairing.manifest.json) is a ratchet: each merged translation batch adds its files, so coverage only grows.\n- **The enforcement frontier advances in coherent review batches.** A related set enters `required` only when reviewers can evaluate it as a unit. The core frontier groups [architecture](../../../../docs/architecture.md), the [Cordis primer](../../../../docs/cordis-primer.md), [defensive patterns](../../../../docs/defensive-patterns.md), the [glossary](../../../../docs/glossary.md), and [testing](../../../../docs/testing.md) because their terminology, links, and contributor contracts inform one another; admitting only part would leave the enforced corpus internally inconsistent. A site-published pair uses `pairedPages()` so the root locale projects `.zh.md` and `/en/` projects `.md`; creating a counterpart alone does not publish it.\n- **Pairing records are metadata, not Cordis Loader configuration.** Cordis configuration discovery accepts actual `.cordis.yml` and `.cordis.yaml` files while excluding `*.i18n.yaml`, even when the document name contains `cordis`. This preserves validation of executable Loader entries without parsing translation hashes as configuration.\n- **Translation is agent work with human review.** The committed workflow is [.agents/skills/dsh-translate-docs](../../../skills/dsh-translate-docs/SKILL.md), following the same pattern as [dsh-code-review](../../../skills/dsh-code-review/SKILL.md): the skill carries the workflow and defers to the docs as sources of truth. The skill directs the orchestrating agent to delegate translation writing to a subagent.\n\n## Verification\n\nThe verification contract covers each boundary independently. `verify-translation-pairing` pins pair completeness, hashes, switchers, and structure; [`project-doc-site.spec.ts`](../../../../scripts/project-doc-site.spec.ts) pins locale-specific source selection for published pairs; [`cordis-config-files.spec.ts`](../../../../scripts/cordis-config-files.spec.ts) pins discovery of Loader YAML and exclusion of translation records; and the [translation-prompt runnable snapshot](../../../../scripts/translation-prompt.snapshot.ts) pins the rendered system message, five reviewed example pairs, source request, and consumed response. Together these checks make pair drift, publication drift, configuration misclassification, and model-visible prompt drift review-visible.\n\n## Alternatives considered\n\n- **English as the canonical source with a fingerprint inside the translation** — the design first proposed for this Agent Note: `.zh.md` files carried an HTML comment recording the English source's blob hash, and translation flowed EN → ZH only. Revised in review: the team wants Chinese-first authoring (write and review a Chinese Agent Note, then translate to English) with the two languages holding equal authority, which a one-directional canonical model cannot express. The sidecar record covering BOTH sides replaced the in-file one-directional fingerprint; the blob-hash mechanics survived unchanged.\n- **Locale directories (`docs/en/` + `docs/zh/`, the Kubernetes/ECharts model)** — rejected: this repo has no docs-site framework to map locales to routes, moving every English file would churn every existing cross-reference, and `verify-md-links`/`verify-doc-refs` would need path-mapping logic instead of working unchanged.\n- **A separate translation repo (the PingCAP `docs`/`docs-cn` model)** — rejected: right for a docs product with independent release trains, overkill for a monorepo's own documentation; it also puts the translation outside the reach of this repo's gates.\n- **Interleaved bilingual files (single file, both languages)** — rejected: doubles every diff, breaks the one-line-per-paragraph convention's diff ergonomics, and makes partial inconsistency invisible.\n- **Commit-hash records (the MDN `l10n.sourceCommit` model)** — rejected in favor of blob hashes: a same-PR edit has no commit hash yet, so the MDN model cannot express \"consistent as of the state this PR introduces\", and verifying it requires git history instead of file content.\n- **Comparing git timestamps of the pair (no record)** — rejected: formatting-only edits would false-positive, and a counterpart committed after an unrelated edit would false-negative; content identity is the only signal that means what the gate claims.\n\n## Industry precedent\n\nPaired sibling files with locale suffixes are the dominant Chinese big-tech convention (ant-design `index.zh-CN.md`/`index.en-US.md`; arco-design `README.zh-CN.md` with a top-of-file switcher; Apache ShardingSphere's 387 `.cn.md`/`.en.md` pairs) — but none of those repos *enforce* pairing or consistency in CI; the convention holds by review alone. Consistency automation exists outside China: MDN's `l10n.sourceCommit` front-matter fingerprint, Vue's Ryu-Cho action (upstream-commit watcher that opens issues/PRs for stale translations), Kubernetes' localization drift scripts, and Microsoft's Azure co-op-translator (source-hash-driven LLM re-translation in CI). This design combines the two: the Chinese-ecosystem file layout with a hash-pair gate, plus a committed agent skill in place of a bot service.\n\n## Consequences\n\n- Editing either side of a paired document obligates the same PR to update the counterpart and re-record the pair — the gate makes the doc-sync rule bilingual, and CI (not reviewer memory) carries the invariant.\n- Every pair adds a third file to the tree. The record is machine-written (`--write`), so the cost is directory noise, not maintenance effort; in exchange, \"who confirmed these consistent, and when\" is answerable from git blame on the yaml.\n- When the two sides disagree, no mechanical rule picks a winner — the PR review does. That is the price of equal authority, accepted deliberately: the alternative (a canonical language) forbids Chinese-first authoring.\n- Generated docs (`cordis-catalog/`, `tool-catalog/`, `module-graph.md`) are excluded for now; the planned follow-up is to teach their generators to emit Chinese alongside English, at which point they leave the exclusion list.\n- Rollout is incremental by design: documents outside `required` are visible backlog (`--list`), not red CI, so pairs land in reviewable batches without a big-bang PR. A date-named document dated on or after the manifest's `requiredSince` cutoff merges bilingual or not at all, so new date-named Agent Notes do not enlarge that backlog.\n- The recorded hashes double as the update tool (`git cat-file -p <hash>` recovers either side's last-confirmed text for a minimal diff-based update), so re-translation of whole files is never forced by the mechanism.\n" }, { "role": "assistant", - "content": "# Agent Note:通过配对兄弟文件与配对门禁实现双语文档\n\nStatus: implemented\n\n[English](2026-07-02-bilingual-docs-and-pairing-gate.md) | 中文\n\n## 问题\n\n本仓库的 README 与 docs 目录树会被公司内外的人和 agent(智能体)以中英两种语言阅读。在没有机制的情况下纯靠手工维护第二语言,正是译文腐烂的根源:一侧持续演进,另一侧默默失实,而没有门禁会注意到。对于这类不变式,本仓库一贯的做法是将其编码为机械检查(见[质量门禁](2026-06-11-quality-gates.md)与 [doc-sync 强制](2026-06-11-doc-sync-enforcement.md)),因此双语政策随附一道门禁一起交付。\n\n## 决策\n\n- **配对兄弟文件,两种语言同权。** 一对文档由三个兄弟文件组成:英文 `foo.md`、中文 `foo.zh.md`,以及一份一致性记录 `foo.i18n.yaml`。没有哪种语言是正典:一篇文档可以先用中文撰写和评审、之后再译成英文,反之亦可;约束配对的是:两侧必须表达相同的内容,且配对整体合并(两种语言加记录,绝不单独落一侧)。政策见 [docs/i18n/README.md](../../../../docs/i18n/README.md);翻译规则见 [docs/i18n/translation-rules.md](../../../../docs/i18n/translation-rules.md);术语真源见 [docs/i18n/terminology.md](../../../../docs/i18n/terminology.md)。\n- **伴随记录保存两侧 blob hash,使一致性可检查。** `foo.i18n.yaml` 保存两侧文件在上一次确认一致时各自的完整 git blob hash。此后修改了任一侧而未重新确认配对,都能被机械检测出来(纯内容比较,无需查询历史),而且同一个 PR(Pull Request)内改动的文件也能计算出 hash,commit hash 式的记录做不到这一点。重新记录(`verify-translation-pairing --write`)会产生一份可评审的 yaml diff:确认一致在 PR 中是一个显式、可见的动作。\n- **`verify-translation-pairing` 加入 `doc-sync`。** 门禁([scripts/verify-translation-pairing.ts](../../../../scripts/verify-translation-pairing.ts))强制执行以下规则:required 的配对必须存在;任何已存在的配对必须完整(三个文件齐全)且一致(两个 hash 匹配、切换行双向互链、结构签名一致);被排除的文件(生成物或本身即双语的)不得配对;凡文件名以日期开头且日期不早于 manifest(元数据清单)中 `requiredSince` 分界日期的文档,也必须有完整配对。[scripts/translation-pairing.manifest.json](../../../../scripts/translation-pairing.manifest.json) 中的 `required` 清单只进不退:每个合并的翻译批次将自己的文件加入其中,覆盖面只增不减。\n- **翻译是 agent 的工作,由人评审。** 仓库内置的工作流是 [.agents/skills/dsh-translate-docs](../../../skills/dsh-translate-docs/SKILL.md),与 [dsh-code-review](../../../skills/dsh-code-review/SKILL.md) 模式相同:skill(技能)承载工作流,并将文档作为真源。该 skill 要求编排 agent 把翻译写作委派给 subagent。\n\n## 曾考虑的替代方案\n\n- **英文为正典源、指纹放在译文内**:本 Agent Note 最初提出的设计:`.zh.md` 文件携带一条 HTML 注释记录英文源的 blob hash,翻译只沿 EN → ZH 单向流动。评审中修订:团队需要中文先行的撰写方式(先写、先审中文 Agent Note,再译英文),两种语言同权,而单向正典模型无法表达这一点。覆盖**两侧**的伴随记录取代了文件内的单向指纹;blob hash 的机制本身保持不变。\n- **语言目录(`docs/en/` + `docs/zh/`,Kubernetes/ECharts 模式)**:否决。本仓库没有将 locale 映射到路由的文档站框架;如果移动所有英文文件,所有既有交叉引用都要随之修改;且 `verify-md-links`/`verify-doc-refs` 将需要路径映射逻辑,而非原样工作。\n- **独立翻译仓库(PingCAP `docs`/`docs-cn` 模式)**:否决。适合有独立发布节奏的文档产品,对 monorepo 自身的文档而言过重;还会把译文置于本仓库门禁触及不到的地方。\n- **中英混排单文件(一个文件、两种语言)**:否决。每个 diff 都翻倍,破坏一段一行约定的 diff 易读性,且局部不一致不可见。\n- **Commit hash 式记录(MDN `l10n.sourceCommit` 模式)**:否决,改用 blob hash。同一个 PR 内的改动还没有 commit hash,MDN 模式无法表达「与本 PR 引入的状态一致」,且校验它需要 git 历史而非文件内容。\n- **比较配对两侧的 git 时间戳(无记录)**:否决。纯格式化的改动会误报,一次无关改动之后提交的对侧文件会漏报;只有内容同一性这个信号才与门禁的承诺名实相符。\n\n## 业界先例\n\n带语言后缀的配对兄弟文件是中国大厂的主流约定(ant-design 的 `index.zh-CN.md`/`index.en-US.md`;arco-design 的 `README.zh-CN.md` 加顶部切换行;Apache ShardingSphere 的 387 对 `.cn.md`/`.en.md`),但这些仓库都没有在 CI 中**强制**配对或一致性检查;约定纯靠评审维系。一致性自动化存在于中国以外:MDN 的 `l10n.sourceCommit` front-matter 指纹、Vue 的 Ryu-Cho action(监视上游 commit,为陈旧译文自动开 issue/PR)、Kubernetes 的本地化漂移脚本、微软 Azure co-op-translator(CI 中由源 hash 驱动的 LLM 重译)。本设计将两者结合:中文生态的文件布局,加上 hash 配对门禁,再加一个仓库内置的 agent skill 替代 bot 服务。\n\n## 后果\n\n- 修改已配对文档的任一侧,同一个 PR 就有义务更新对侧并重新记录配对。门禁将 doc-sync 规则双语化,不变式由 CI(而非评审者的记忆)承载。\n- 每个配对给目录树多添一个文件。记录由机器写入(`--write`),代价是目录噪音而非维护负担;换来的是「谁在何时确认过这对文档一致」可以从 yaml 的 git blame 直接回答。\n- 两侧说法冲突时,没有机械规则裁决谁赢,由 PR 评审裁决。这是同权的代价,且是有意接受的:另一个选项(正典语言)会禁止中文先行撰写。\n- 生成文档(`cordis-catalog/`、`tool-catalog/`、`module-graph.md`)暂被排除;计划中的后续工作是让生成器在输出英文的同时输出中文,届时将这些文件移出排除清单。\n- 推进天然是渐进的:`required` 之外的文档是可见的 backlog(待翻清单,`--list`),而非红色的 CI;因此配对按可评审的批次落地,无需一个巨型 PR。凡文件名以日期开头且日期不早于 manifest 中 `requiredSince` 分界日期的文档,都必须配齐双语文件,因此新建的日期命名 Agent Note 不会增加这份 backlog。\n- 记录的 hash 兼作更新工具(`git cat-file -p <hash>` 能还原任一侧上次确认的文本,用于基于 diff 的最小更新),因此这套机制从不强迫整篇重译。\n" + "content": "# Agent Note:通过配对兄弟文件与配对门禁实现双语文档\n\nStatus: implemented\n\n[English](2026-07-02-bilingual-docs-and-pairing-gate.md) | 中文\n\n## 问题\n\n本仓库的 README 与 docs 目录树会被公司内外的人和 agent(智能体)以中英两种语言阅读。在没有机制的情况下纯靠手工维护第二语言,正是译文腐烂的根源:一侧持续演进,另一侧默默失实,而没有门禁会注意到。对于这类不变式,本仓库一贯的做法是将其编码为机械检查(见[质量门禁](2026-06-11-quality-gates.md)与 [doc-sync 强制](2026-06-11-doc-sync-enforcement.md)),因此双语政策随附一道门禁一起交付。\n\n## 决策\n\n- **配对兄弟文件,两种语言同权。** 一对文档由三个兄弟文件组成:英文 `foo.md`、中文 `foo.zh.md`,以及一份一致性记录 `foo.i18n.yaml`。没有哪种语言是正典:一篇文档可以先用中文撰写和评审、之后再译成英文,反之亦可;约束配对的是:两侧必须表达相同的内容,且配对整体合并(两种语言加记录,绝不单独落一侧)。政策见 [docs/i18n/README.md](../../../../docs/i18n/README.md);翻译规则见 [docs/i18n/translation-rules.md](../../../../docs/i18n/translation-rules.md);术语真源见 [docs/i18n/terminology.md](../../../../docs/i18n/terminology.md)。\n- **伴随记录保存两侧 blob hash,使一致性可检查。** `foo.i18n.yaml` 保存两侧文件在上一次确认一致时各自的完整 git blob hash。此后修改了任一侧而未重新确认配对,都能被机械检测出来(纯内容比较,无需查询历史),而且同一个 PR(Pull Request)内改动的文件也能计算出 hash,commit hash 式的记录做不到这一点。重新记录(`verify-translation-pairing --write`)会产生一份可评审的 yaml diff:确认一致在 PR 中是一个显式、可见的动作。\n- **`verify-translation-pairing` 加入 `doc-sync`。** 门禁([scripts/verify-translation-pairing.ts](../../../../scripts/verify-translation-pairing.ts))强制执行以下规则:required 的配对必须存在;任何已存在的配对必须完整(三个文件齐全)且一致(两个 hash 匹配、切换行双向互链、结构签名一致);被排除的文件(生成物或本身即双语的)不得配对;凡文件名以日期开头且日期不早于 manifest(元数据清单)中 `requiredSince` 分界日期的文档,也必须有完整配对。[scripts/translation-pairing.manifest.json](../../../../scripts/translation-pairing.manifest.json) 中的 `required` 清单只进不退:每个合并的翻译批次将自己的文件加入其中,覆盖面只增不减。\n- **执行红线按连贯的评审批次推进。** 一组相关文档只有在评审者能够将其作为整体评估时,才进入 `required`。核心红线将[架构](../../../../docs/architecture.md)、[Cordis 入门](../../../../docs/cordis-primer.md)、[防御性模式](../../../../docs/defensive-patterns.md)、[术语表](../../../../docs/glossary.md)和[测试](../../../../docs/testing.md)归为一组,因为它们的术语、链接和贡献者契约相互关联;只纳入其中一部分会使受门禁约束的文档集合内部不一致。发布到文档站的配对使用 `pairedPages()`,由根 locale 投影 `.zh.md`,由 `/en/` 投影 `.md`;仅创建对侧文件并不会发布它。\n- **配对记录是元数据,而不是 Cordis Loader 配置。** Cordis 配置发现会接受实际的 `.cordis.yml` 和 `.cordis.yaml` 文件,同时排除 `*.i18n.yaml`,即使文档名中包含 `cordis` 也不例外。这样既能继续校验可执行的 Loader 配置项,又不会把翻译 hash 当作配置来解析。\n- **翻译是 agent 的工作,由人评审。** 仓库内置的工作流是 [.agents/skills/dsh-translate-docs](../../../skills/dsh-translate-docs/SKILL.md),与 [dsh-code-review](../../../skills/dsh-code-review/SKILL.md) 模式相同:skill(技能)承载工作流,并将文档作为真源。该 skill 要求编排 agent 把翻译写作委派给 subagent。\n\n## 验证\n\n验证契约分别覆盖每个边界。`verify-translation-pairing` 固定配对完整性、hash、切换行和结构;[`project-doc-site.spec.ts`](../../../../scripts/project-doc-site.spec.ts) 固定已发布配对按 locale 选择对应源文件;[`cordis-config-files.spec.ts`](../../../../scripts/cordis-config-files.spec.ts) 固定 Loader YAML 的发现以及翻译记录的排除;[翻译提示词可运行快照](../../../../scripts/translation-prompt.snapshot.ts)则固定渲染后的系统消息、五对经评审的示例、源请求和响应消费结果。这些检查共同使配对漂移、发布漂移、配置误分类和模型可见提示词漂移都可在评审中看见。\n\n## 曾考虑的替代方案\n\n- **英文为正典源、指纹放在译文内**:本 Agent Note 最初提出的设计:`.zh.md` 文件携带一条 HTML 注释记录英文源的 blob hash,翻译只沿 EN → ZH 单向流动。评审中修订:团队需要中文先行的撰写方式(先写、先审中文 Agent Note,再译英文),两种语言同权,而单向正典模型无法表达这一点。覆盖**两侧**的伴随记录取代了文件内的单向指纹;blob hash 的机制本身保持不变。\n- **语言目录(`docs/en/` + `docs/zh/`,Kubernetes/ECharts 模式)**:否决。本仓库没有将 locale 映射到路由的文档站框架;如果移动所有英文文件,所有既有交叉引用都要随之修改;且 `verify-md-links`/`verify-doc-refs` 将需要路径映射逻辑,而非原样工作。\n- **独立翻译仓库(PingCAP `docs`/`docs-cn` 模式)**:否决。适合有独立发布节奏的文档产品,对 monorepo 自身的文档而言过重;还会把译文置于本仓库门禁触及不到的地方。\n- **中英混排单文件(一个文件、两种语言)**:否决。每个 diff 都翻倍,破坏一段一行约定的 diff 易读性,且局部不一致不可见。\n- **Commit hash 式记录(MDN `l10n.sourceCommit` 模式)**:否决,改用 blob hash。同一个 PR 内的改动还没有 commit hash,MDN 模式无法表达「与本 PR 引入的状态一致」,且校验它需要 git 历史而非文件内容。\n- **比较配对两侧的 git 时间戳(无记录)**:否决。纯格式化的改动会误报,一次无关改动之后提交的对侧文件会漏报;只有内容同一性这个信号才与门禁的承诺名实相符。\n\n## 业界先例\n\n带语言后缀的配对兄弟文件是中国大厂的主流约定(ant-design 的 `index.zh-CN.md`/`index.en-US.md`;arco-design 的 `README.zh-CN.md` 加顶部切换行;Apache ShardingSphere 的 387 对 `.cn.md`/`.en.md`),但这些仓库都没有在 CI 中**强制**配对或一致性检查;约定纯靠评审维系。一致性自动化存在于中国以外:MDN 的 `l10n.sourceCommit` front-matter 指纹、Vue 的 Ryu-Cho action(监视上游 commit,为陈旧译文自动开 issue/PR)、Kubernetes 的本地化漂移脚本、微软 Azure co-op-translator(CI 中由源 hash 驱动的 LLM 重译)。本设计将两者结合:中文生态的文件布局,加上 hash 配对门禁,再加一个仓库内置的 agent skill 替代 bot 服务。\n\n## 后果\n\n- 修改已配对文档的任一侧,同一个 PR 就有义务更新对侧并重新记录配对。门禁将 doc-sync 规则双语化,不变式由 CI(而非评审者的记忆)承载。\n- 每个配对给目录树多添一个文件。记录由机器写入(`--write`),代价是目录噪音而非维护负担;换来的是「谁在何时确认过这对文档一致」可以从 yaml 的 git blame 直接回答。\n- 两侧说法冲突时,没有机械规则裁决谁赢,由 PR 评审裁决。这是同权的代价,且是有意接受的:另一个选项(正典语言)会禁止中文先行撰写。\n- 生成文档(`cordis-catalog/`、`tool-catalog/`、`module-graph.md`)暂被排除;计划中的后续工作是让生成器在输出英文的同时输出中文,届时将这些文件移出排除清单。\n- 推进天然是渐进的:`required` 之外的文档是可见的 backlog(待翻清单,`--list`),而非红色的 CI;因此配对按可评审的批次落地,无需一个巨型 PR。凡文件名以日期开头且日期不早于 manifest 中 `requiredSince` 分界日期的文档,都必须配齐双语文件,因此新建的日期命名 Agent Note 不会增加这份 backlog。\n- 记录的 hash 兼作更新工具(`git cat-file -p <hash>` 能还原任一侧上次确认的文本,用于基于 diff 的最小更新),因此这套机制从不强迫整篇重译。\n" }, { "role": "user", diff --git a/scripts/translation-pairing.manifest.json b/scripts/translation-pairing.manifest.json index a4fcc93352..a6503ce282 100644 --- a/scripts/translation-pairing.manifest.json +++ b/scripts/translation-pairing.manifest.json @@ -1,24 +1,201 @@ { "requiredSince": "2026-07-14", "required": [ + ".agents/notes/README.md", + ".agents/notes/implemented/architecture/2026-06-11-content-block-vocabulary.md", + ".agents/notes/implemented/architecture/2026-06-11-custom-schema-dsl.md", + ".agents/notes/implemented/architecture/2026-06-11-dev-invariants-over-deep-readonly.md", + ".agents/notes/implemented/architecture/2026-06-11-event-sourced-sessions.md", + ".agents/notes/implemented/architecture/2026-06-11-microkernel-event-taxonomy.md", + ".agents/notes/implemented/architecture/2026-06-11-runtime-arg-validation.md", + ".agents/notes/implemented/architecture/2026-06-11-structured-error-taxonomy.md", + ".agents/notes/implemented/architecture/2026-06-11-tool-schemas-in-prompt-assembly.md", + ".agents/notes/implemented/architecture/2026-06-13-capability-seams.md", + ".agents/notes/implemented/architecture/2026-06-13-twin-llm-adapters.md", + ".agents/notes/implemented/architecture/2026-06-14-session-persistence.md", + ".agents/notes/implemented/architecture/2026-06-15-turn-enclosure-invariant.md", + ".agents/notes/implemented/architecture/2026-06-17-filesystem-capability-seam.md", + ".agents/notes/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.md", + ".agents/notes/implemented/architecture/2026-06-18-session-surface.md", + ".agents/notes/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.md", + ".agents/notes/implemented/architecture/2026-06-20-branded-ids.md", + ".agents/notes/implemented/architecture/2026-06-20-extract-example-app-packages.md", + ".agents/notes/implemented/architecture/2026-06-20-generic-long-running-tool-runtime.md", + ".agents/notes/implemented/architecture/2026-06-20-package-hierarchy.md", + ".agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.md", + ".agents/notes/implemented/architecture/2026-06-24-web-capability-seam.md", + ".agents/notes/implemented/architecture/2026-06-26-file-context-as-event-gate.md", + ".agents/notes/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md", + ".agents/notes/implemented/architecture/2026-06-30-event-domain-semantics.md", + ".agents/notes/implemented/architecture/2026-07-02-fs-per-session-cwd.md", + ".agents/notes/implemented/architecture/2026-07-02-result-time-applied-hunk-diffs.md", + ".agents/notes/implemented/architecture/2026-07-02-tool-render-intent-union.md", + ".agents/notes/implemented/architecture/2026-07-03-filesystem-directory-listing-seam.md", + ".agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md", + ".agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.md", + ".agents/notes/implemented/architecture/2026-07-05-subagent-provider-lifecycle-events.md", + ".agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.md", + ".agents/notes/implemented/architecture/2026-07-07-tool-call-timeout-policy.md", + ".agents/notes/implemented/architecture/2026-07-08-agent-scope-contexts.md", ".agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md", + ".agents/notes/implemented/architecture/2026-07-12-agent-scope-runtime-design.md", ".agents/notes/implemented/architecture/2026-07-16-explicit-turn-cancellation.md", ".agents/notes/implemented/architecture/2026-07-19-gui-layering-and-rpc-protocol.md", ".agents/notes/implemented/architecture/2026-07-19-gui-web-client-architecture.md", ".agents/notes/implemented/architecture/2026-07-22-slot-type-chain-implementation.md", ".agents/notes/implemented/architecture/2026-07-23-client-plugin-loading-model.md", + ".agents/notes/implemented/feature/2026-06-14-acp-agent-client-protocol.md", + ".agents/notes/implemented/feature/2026-06-14-acp-multi-session.md", + ".agents/notes/implemented/feature/2026-06-15-code-mode.md", + ".agents/notes/implemented/feature/2026-06-17-filesystem-tool-schemas.md", + ".agents/notes/implemented/feature/2026-06-18-acp-terminal-and-tool-rendering.md", + ".agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.md", + ".agents/notes/implemented/feature/2026-06-21-subagent-capability-seam.md", + ".agents/notes/implemented/feature/2026-06-22-acp-subagent-backend.md", + ".agents/notes/implemented/feature/2026-06-25-ask-user-question.md", + ".agents/notes/implemented/feature/2026-06-29-todo-write-tool.md", + ".agents/notes/implemented/feature/2026-06-30-hook-bridges.md", + ".agents/notes/implemented/feature/2026-06-30-hook-protocol-lib.md", + ".agents/notes/implemented/feature/2026-06-30-interception-seams.md", + ".agents/notes/implemented/feature/2026-06-30-session-store-fork-api.md", + ".agents/notes/implemented/feature/2026-06-30-subagent-observe-enrich.md", + ".agents/notes/implemented/feature/2026-07-05-dynamic-workflows.md", + ".agents/notes/implemented/feature/2026-07-05-skill-system.md", + ".agents/notes/implemented/feature/2026-07-06-approval-seam.md", + ".agents/notes/implemented/feature/2026-07-06-explicit-tool-order.md", + ".agents/notes/implemented/feature/2026-07-06-sandbox.md", + ".agents/notes/implemented/feature/2026-07-07-mcp-client-plugin.md", + ".agents/notes/implemented/feature/2026-07-07-session-prefix.md", + ".agents/notes/implemented/feature/2026-07-08-repeat-tool-guard.md", + ".agents/notes/implemented/feature/2026-07-08-self-referential-cordis-toolset.md", + ".agents/notes/implemented/feature/2026-07-10-session-query-service.md", + ".agents/notes/implemented/feature/2026-07-12-subagent-persona-tool-filter-and-depth.md", + ".agents/notes/implemented/process/2026-06-11-doc-sync-enforcement.md", + ".agents/notes/implemented/process/2026-06-11-quality-gates.md", + ".agents/notes/implemented/process/2026-06-11-tsdown-over-dumble.md", + ".agents/notes/implemented/process/2026-06-11-vendor-cordis-as-source.md", + ".agents/notes/implemented/process/2026-06-16-pnpm-over-yarn.md", + ".agents/notes/implemented/process/2026-06-17-ts-build-config.md", + ".agents/notes/implemented/process/2026-06-18-markdown-cross-link-lint.md", + ".agents/notes/implemented/process/2026-06-20-agent-note-classification.md", + ".agents/notes/implemented/process/2026-06-20-core-data-structures-catalog.md", + ".agents/notes/implemented/process/2026-06-20-generated-cordis-catalog.md", ".agents/notes/implemented/process/2026-07-02-bilingual-docs-and-pairing-gate.md", + ".agents/notes/implemented/process/2026-07-02-tool-schema-catalog.md", + ".agents/notes/implemented/process/2026-07-03-documentation-graph-atlas.md", + ".agents/notes/implemented/process/2026-07-04-cordis-jsdoc-completeness-gate.md", + ".agents/notes/implemented/process/2026-07-04-doc-tiers-and-budgets.md", + ".agents/notes/implemented/process/2026-07-04-persistence-log-catalog.md", + ".agents/notes/implemented/process/2026-07-05-uniform-agent-note-format.md", + ".agents/notes/implemented/process/2026-07-06-export-surface-jsdoc-gate.md", + ".agents/notes/implemented/process/2026-07-06-generated-config-catalog.md", + ".agents/notes/implemented/process/2026-07-06-node-engine-floor.md", + ".agents/notes/implemented/process/2026-07-06-parallel-github-ci-gates.md", + ".agents/notes/implemented/process/2026-07-06-parallel-pre-push-gates.md", + ".agents/notes/implemented/process/2026-07-10-readme-known-limitations-gate.md", + ".agents/notes/implemented/process/2026-07-12-package-model-experience-contract.md", ".agents/notes/implemented/process/2026-07-19-web-styling-system.md", + ".agents/notes/implemented/simplification/2026-06-19-drop-mutable-session-summary.md", + ".agents/notes/implemented/simplification/2026-06-20-collapse-trace-only-session-events.md", + ".agents/notes/implemented/simplification/2026-06-20-drop-unconsumed-llm-adapter-change-event.md", + ".agents/notes/implemented/simplification/2026-06-20-drop-unconsumed-llm-assembled-surfaces.md", + ".agents/notes/implemented/simplification/2026-06-20-prune-dead-seam-methods.md", + ".agents/notes/implemented/simplification/2026-06-20-public-agent-stop-surface.md", + ".agents/notes/implemented/simplification/2026-06-20-remove-agent-boundary-mirror-events.md", + ".agents/notes/implemented/simplification/2026-06-20-unify-agent-and-session-id.md", + ".agents/notes/implemented/simplification/2026-06-26-fsspec-style-fs-seam.md", + ".agents/notes/implemented/simplification/2026-07-02-remove-stream-chunk-mirror.md", + ".agents/notes/implemented/simplification/2026-07-04-drop-image-content-block.md", + ".agents/notes/implemented/simplification/2026-07-04-drop-inert-request-knobs.md", + ".agents/notes/implemented/simplification/2026-07-04-drop-unconsumed-web-observation-surface.md", + ".agents/notes/implemented/simplification/2026-07-04-fold-stdio-ui-helper.md", + ".agents/notes/implemented/simplification/2026-07-04-prune-producerless-vocabulary-variants.md", + ".agents/notes/implemented/simplification/2026-07-04-prune-write-only-fs-surface.md", + ".agents/notes/implemented/simplification/2026-07-04-remove-agent-steering-mirror.md", + ".agents/notes/implemented/simplification/2026-07-04-share-app-bin-boot-glue.md", + ".agents/notes/implemented/simplification/2026-07-04-tighten-hook-protocol-contract.md", + ".agents/notes/implemented/simplification/2026-07-04-trim-acp-bridge-unreachable-surface.md", + ".agents/notes/implemented/simplification/2026-07-12-drop-unconsumed-skill-provider-events.md", + ".agents/notes/implemented/simplification/2026-07-12-prune-unused-web-seam-fields.md", + ".agents/notes/implemented/simplification/2026-07-12-simplify-session-log-representation.md", + ".agents/notes/implemented/testing/2026-06-11-property-based-testing.md", + ".agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.md", + ".agents/notes/implemented/testing/2026-06-19-real-api-e2e-ci.md", + ".agents/notes/implemented/testing/2026-06-20-remove-redundant-snapshot-log-expected-output.md", + ".agents/notes/implemented/testing/2026-06-22-fork-child-replay-seed-boundary.md", + ".agents/notes/implemented/testing/2026-06-22-fork-snapshot-scenarios.md", + ".agents/notes/implemented/testing/2026-06-22-subagent-snapshot-replay.md", + ".agents/notes/implemented/testing/2026-07-04-hook-snapshot-matrix.md", + ".agents/notes/implemented/testing/2026-07-04-single-source-acp-replay-config.md", + ".agents/notes/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md", + ".agents/notes/implemented/testing/2026-07-08-shared-acp-snapshot-package.md", + ".agents/notes/proposed/architecture/2026-06-16-typed-event-schemas.md", + ".agents/notes/proposed/feature/2026-06-30-pre-tool-input-rewrite.md", + ".agents/notes/proposed/feature/2026-07-07-claude-code-and-codex-subagent-backends.md", + ".agents/notes/proposed/feature/2026-07-08-interactive-side-sessions.md", + ".agents/notes/implemented/feature/2026-07-10-sqlite-session-query-provider.md", + ".agents/notes/proposed/feature/2026-07-13-stream-workflow-progress-through-tool-calls.md", + ".agents/notes/proposed/process/2026-06-11-api-extractor-reports.md", + ".agents/notes/proposed/process/2026-06-11-architectural-conformance.md", + ".agents/notes/proposed/process/2026-06-11-supply-chain-and-vendor-drift.md", + ".agents/notes/proposed/process/2026-06-20-discover-package-inventory.md", + ".agents/notes/proposed/simplification/2026-07-04-prune-dead-core-spine-surface.md", + ".agents/notes/proposed/testing/2026-06-11-deterministic-and-stress-testing.md", + ".agents/notes/proposed/testing/2026-06-11-mutation-testing.md", + ".agents/notes/rejected/architecture/2026-06-11-immutable-public-surfaces.md", + ".agents/notes/rejected/architecture/2026-06-20-providerless-example-base.md", + ".agents/notes/rejected/process/2026-07-04-generate-agent-note-index-tables.md", + ".agents/notes/rejected/simplification/2026-06-20-assembled-assistant-messages-only.md", + ".agents/notes/rejected/simplification/2026-06-20-drop-acp-session-load.md", + ".agents/notes/rejected/simplification/2026-06-20-drop-acp-terminal-meta.md", + ".agents/notes/rejected/simplification/2026-06-20-drop-bash-output-spill-files.md", + ".agents/notes/rejected/simplification/2026-06-20-drop-durable-step-boundaries.md", + ".agents/notes/rejected/simplification/2026-06-20-drop-unused-session-lineage.md", + ".agents/notes/rejected/simplification/2026-06-20-fold-session-persistence-interface.md", + ".agents/notes/rejected/simplification/2026-06-20-generic-tool-rendering.md", + ".agents/notes/rejected/simplification/2026-06-20-retire-mid-turn-steering.md", + ".agents/notes/rejected/simplification/2026-06-20-single-session-acp-bridge.md", + ".agents/notes/rejected/simplification/2026-06-20-truncate-interrupted-turns.md", + ".agents/notes/rejected/simplification/2026-07-04-prune-unimplemented-subagent-vocabulary.md", + ".agents/notes/rejected/simplification/2026-07-12-collapse-workflow-to-foreground-core.md", + ".agents/notes/rejected/simplification/2026-07-12-prune-unused-skill-registry-surface.md", "README.md", + "docs/architecture.md", "docs/cookbook/adding-a-package.md", "docs/cookbook/adding-a-tool.md", "docs/cookbook/adding-a-vendored-package.md", "docs/cookbook/adding-an-llm-adapter.md", "docs/cookbook/extension-cookbook.md", "docs/cookbook/responding-to-pr-review-on-a-stack.md", + "docs/cordis-primer.md", + "docs/core-data-structures/approval.md", + "docs/core-data-structures/bash.md", + "docs/core-data-structures/code-runtime.md", + "docs/core-data-structures/compaction.md", + "docs/core-data-structures/core.md", + "docs/core-data-structures/filesystem.md", + "docs/core-data-structures/llm-streaming.md", + "docs/core-data-structures/persistence.md", + "docs/core-data-structures/sandbox.md", + "docs/core-data-structures/scope.md", + "docs/core-data-structures/session-query.md", + "docs/core-data-structures/session.md", + "docs/core-data-structures/skills.md", + "docs/core-data-structures/subagent.md", + "docs/core-data-structures/system-prompt.md", + "docs/core-data-structures/tools.md", + "docs/core-data-structures/user-interaction.md", + "docs/core-data-structures/web.md", + "docs/core-data-structures/workflow.md", + "docs/defensive-patterns.md", "docs/development.md", + "docs/glossary.md", "docs/i18n/README.md", "docs/i18n/translation-rules.md", + "docs/postmortem/0001-acp-default-export-drops-inject.md", + "docs/postmortem/0002-js-expression-disabled-filesystem-tools.md", + "docs/postmortem/README.md", + "docs/testing.md", "docs/user/develop/basic/config.md", "docs/user/develop/basic/index.md", "docs/user/develop/basic/tool.md", @@ -39,14 +216,19 @@ ".agents/notes/AGENTS.md", ".agents/notes/implemented/AGENTS.md", "docs/AGENTS.md", + "docs/agent-lifecycle.md", + "docs/capability-seams.md", "docs/config-catalog.md", "docs/cordis-catalog/", + "docs/event-producer-consumer.md", + "docs/graph-atlas.md", "docs/i18n/style-samples.md", "docs/i18n/terminology.md", "docs/i18n/translation-prompt.md", "docs/module-graph.md", "docs/persistence-catalog.md", "docs/tool-catalog.md", + "docs/tool-execution-pipeline.md", "python/sdk-runtime/src/deepseek_harness_runtime/runtime/node/" ] } diff --git a/scripts/type-equiv.manifest.json b/scripts/type-equiv.manifest.json index db5fc0b85d..3c199d4d04 100644 --- a/scripts/type-equiv.manifest.json +++ b/scripts/type-equiv.manifest.json @@ -73,12 +73,32 @@ }, { "doc": "docs/core-data-structures/core.md", - "symbol": "AgentCancelCause", + "symbol": "InjectOptions", "source": "packages/core/agent/src/types.ts" }, { "doc": "docs/core-data-structures/core.md", - "symbol": "InjectOptions", + "symbol": "ResolvedAgentInput", + "source": "packages/core/agent/src/types.ts" + }, + { + "doc": "docs/core-data-structures/core.md", + "symbol": "AgentMessageId", + "source": "packages/core/agent/src/types.ts" + }, + { + "doc": "docs/core-data-structures/core.md", + "symbol": "AgentMessage", + "source": "packages/core/agent/src/types.ts" + }, + { + "doc": "docs/core-data-structures/core.md", + "symbol": "CancelOptions", + "source": "packages/core/agent/src/types.ts" + }, + { + "doc": "docs/core-data-structures/core.md", + "symbol": "AgentCancelCause", "source": "packages/core/agent/src/types.ts" }, { @@ -439,26 +459,6 @@ "symbol": "SessionEventTrace", "source": "packages/session-query/session-query/src/types.ts" }, - { - "doc": "docs/core-data-structures/session-reference.md", - "symbol": "SessionReferenceInput", - "source": "packages/context/session-reference/src/types.ts" - }, - { - "doc": "docs/core-data-structures/session-reference.md", - "symbol": "SessionReferenceCandidate", - "source": "packages/context/session-reference/src/types.ts" - }, - { - "doc": "docs/core-data-structures/session-reference.md", - "symbol": "PreparedReferencedMessage", - "source": "packages/context/session-reference/src/types.ts" - }, - { - "doc": "docs/core-data-structures/session-reference.md", - "symbol": "SessionReferenceErrorCode", - "source": "packages/context/session-reference/src/config.ts" - }, { "doc": "docs/core-data-structures/session-title.md", "symbol": "SessionTitleProviderId", @@ -514,6 +514,26 @@ "symbol": "SessionTitleProvider", "source": "packages/session-title/session-title/src/index.ts" }, + { + "doc": "docs/core-data-structures/session-reference.md", + "symbol": "SessionReferenceInput", + "source": "packages/context/session-reference/src/types.ts" + }, + { + "doc": "docs/core-data-structures/session-reference.md", + "symbol": "SessionReferenceCandidate", + "source": "packages/context/session-reference/src/types.ts" + }, + { + "doc": "docs/core-data-structures/session-reference.md", + "symbol": "PreparedReferencedMessage", + "source": "packages/context/session-reference/src/types.ts" + }, + { + "doc": "docs/core-data-structures/session-reference.md", + "symbol": "SessionReferenceErrorCode", + "source": "packages/context/session-reference/src/config.ts" + }, { "doc": "docs/core-data-structures/tools.md", "symbol": "ToolOutputDefinition", @@ -1208,6 +1228,929 @@ "doc": "docs/core-data-structures/session-query.md", "symbol": "SessionSearchHit", "source": "packages/session-query/session-query/src/types.ts" + }, + { + "doc": "docs/core-data-structures/core.zh.md", + "symbol": "Branded", + "source": "packages/util/brand/src/index.ts" + }, + { + "doc": "docs/core-data-structures/core.zh.md", + "symbol": "ContentBlockMap", + "source": "packages/llm/llm/src/types.ts" + }, + { + "doc": "docs/core-data-structures/core.zh.md", + "symbol": "AssistantProvenance", + "source": "packages/llm/llm/src/types.ts" + }, + { + "doc": "docs/core-data-structures/core.zh.md", + "symbol": "Message", + "source": "packages/llm/llm/src/types.ts" + }, + { + "doc": "docs/core-data-structures/core.zh.md", + "symbol": "MessageSourceMap", + "source": "packages/llm/llm/src/types.ts" + }, + { + "doc": "docs/core-data-structures/core.zh.md", + "symbol": "FinishReasonMap", + "source": "packages/llm/llm/src/types.ts" + }, + { + "doc": "docs/core-data-structures/core.zh.md", + "symbol": "LlmProviderInfo", + "source": "packages/llm/llm/src/types.ts" + }, + { + "doc": "docs/core-data-structures/core.zh.md", + "symbol": "LlmModelInfo", + "source": "packages/llm/llm/src/types.ts" + }, + { + "doc": "docs/core-data-structures/core.zh.md", + "symbol": "LlmModelContext", + "source": "packages/llm/llm/src/types.ts" + }, + { + "doc": "docs/core-data-structures/core.zh.md", + "symbol": "GenerateOptions", + "source": "packages/llm/llm/src/types.ts" + }, + { + "doc": "docs/core-data-structures/core.zh.md", + "symbol": "ToolSchema", + "source": "packages/llm/llm/src/types.ts" + }, + { + "doc": "docs/core-data-structures/core.zh.md", + "symbol": "LlmCallConfig", + "source": "packages/llm/llm/src/call-config.ts" + }, + { + "doc": "docs/core-data-structures/core.zh.md", + "symbol": "SessionEvent", + "source": "packages/core/session/src/types.ts" + }, + { + "doc": "docs/core-data-structures/core.zh.md", + "symbol": "SendOptions", + "source": "packages/core/agent/src/types.ts" + }, + { + "doc": "docs/core-data-structures/core.zh.md", + "symbol": "AgentCancelCause", + "source": "packages/core/agent/src/types.ts" + }, + { + "doc": "docs/core-data-structures/core.zh.md", + "symbol": "InjectOptions", + "source": "packages/core/agent/src/types.ts" + }, + { + "doc": "docs/core-data-structures/core.zh.md", + "symbol": "ResolvedAgentInput", + "source": "packages/core/agent/src/types.ts" + }, + { + "doc": "docs/core-data-structures/core.zh.md", + "symbol": "AgentMessageId", + "source": "packages/core/agent/src/types.ts" + }, + { + "doc": "docs/core-data-structures/core.zh.md", + "symbol": "AgentMessage", + "source": "packages/core/agent/src/types.ts" + }, + { + "doc": "docs/core-data-structures/core.zh.md", + "symbol": "CancelOptions", + "source": "packages/core/agent/src/types.ts" + }, + { + "doc": "docs/core-data-structures/core.zh.md", + "symbol": "Agent", + "source": "packages/core/agent/src/types.ts" + }, + { + "doc": "docs/core-data-structures/core.zh.md", + "symbol": "HookContext", + "source": "packages/core/agent/src/types.ts" + }, + { + "doc": "docs/core-data-structures/core.zh.md", + "symbol": "PromptDecision", + "source": "packages/core/agent/src/types.ts" + }, + { + "doc": "docs/core-data-structures/core.zh.md", + "symbol": "ContinuationDecision", + "source": "packages/core/agent/src/types.ts" + }, + { + "doc": "docs/core-data-structures/core.zh.md", + "symbol": "RequestError", + "source": "packages/core/agent/src/types.ts" + }, + { + "doc": "docs/core-data-structures/core.zh.md", + "symbol": "RequestErrorDecision", + "source": "packages/core/agent/src/types.ts" + }, + { + "doc": "docs/core-data-structures/core.zh.md", + "symbol": "ContinuationStop", + "source": "packages/core/agent/src/types.ts" + }, + { + "doc": "docs/core-data-structures/core.zh.md", + "symbol": "SessionStartSource", + "source": "packages/core/agent/src/types.ts" + }, + { + "doc": "docs/core-data-structures/scope.zh.md", + "symbol": "ScopeKey", + "source": "packages/core/scope/src/index.ts" + }, + { + "doc": "docs/core-data-structures/scope.zh.md", + "symbol": "Scoped", + "source": "packages/core/scope/src/index.ts" + }, + { + "doc": "docs/core-data-structures/scope.zh.md", + "symbol": "Scope", + "source": "packages/core/scope/src/index.ts" + }, + { + "doc": "docs/core-data-structures/scope.zh.md", + "symbol": "ScopeLayer", + "source": "packages/core/scope/src/store.ts" + }, + { + "doc": "docs/core-data-structures/system-prompt.zh.md", + "symbol": "AssembleContext", + "source": "packages/core/system-prompt/src/index.ts" + }, + { + "doc": "docs/core-data-structures/system-prompt.zh.md", + "symbol": "PromptSection", + "source": "packages/core/system-prompt/src/index.ts" + }, + { + "doc": "docs/core-data-structures/system-prompt.zh.md", + "symbol": "ToolProviderResult", + "source": "packages/core/system-prompt/src/index.ts" + }, + { + "doc": "docs/core-data-structures/llm-streaming.zh.md", + "symbol": "StreamChunk", + "source": "packages/llm/llm/src/types.ts" + }, + { + "doc": "docs/core-data-structures/llm-streaming.zh.md", + "symbol": "LlmFailure", + "source": "packages/llm/llm/src/types.ts" + }, + { + "doc": "docs/core-data-structures/llm-streaming.zh.md", + "symbol": "TokenUsage", + "source": "packages/llm/llm/src/types.ts" + }, + { + "doc": "docs/core-data-structures/llm-streaming.zh.md", + "symbol": "ContentBlockMap", + "source": "packages/llm/llm/src/types.ts" + }, + { + "doc": "docs/core-data-structures/llm-streaming.zh.md", + "symbol": "AppIdentity", + "source": "packages/llm/llm/src/attribution.ts" + }, + { + "doc": "docs/core-data-structures/llm-streaming.zh.md", + "symbol": "BlockAssembler", + "source": "packages/llm/llm/src/assembler.ts", + "projection": "public-api" + }, + { + "doc": "docs/core-data-structures/llm-streaming.zh.md", + "symbol": "LlmAdapter", + "source": "packages/llm/llm/src/index.ts", + "projection": "public-api" + }, + { + "doc": "docs/core-data-structures/session.zh.md", + "symbol": "PromptMessageData", + "source": "packages/core/session/src/types.ts" + }, + { + "doc": "docs/core-data-structures/session.zh.md", + "symbol": "SessionEventMap", + "source": "packages/core/session/src/types.ts" + }, + { + "doc": "docs/core-data-structures/session.zh.md", + "symbol": "OutOfBandSessionEventMap", + "source": "packages/core/session/src/types.ts" + }, + { + "doc": "docs/core-data-structures/session.zh.md", + "symbol": "EpochHeader", + "source": "packages/core/session/src/types.ts" + }, + { + "doc": "docs/core-data-structures/session.zh.md", + "symbol": "TodoItem", + "source": "packages/core/session/src/types.ts" + }, + { + "doc": "docs/core-data-structures/session.zh.md", + "symbol": "SessionEvent", + "source": "packages/core/session/src/types.ts" + }, + { + "doc": "docs/core-data-structures/session.zh.md", + "symbol": "TurnTriggerMap", + "source": "packages/core/session/src/types.ts" + }, + { + "doc": "docs/core-data-structures/session.zh.md", + "symbol": "TurnEndReasonMap", + "source": "packages/core/session/src/types.ts" + }, + { + "doc": "docs/core-data-structures/session.zh.md", + "symbol": "SurfaceEventType", + "source": "packages/core/session/src/types.ts" + }, + { + "doc": "docs/core-data-structures/session.zh.md", + "symbol": "SurfaceOp", + "source": "packages/core/session/src/types.ts" + }, + { + "doc": "docs/core-data-structures/session.zh.md", + "symbol": "SurfaceIntent", + "source": "packages/core/session/src/types.ts" + }, + { + "doc": "docs/core-data-structures/session.zh.md", + "symbol": "SessionSurface", + "source": "packages/core/session/src/surface.ts" + }, + { + "doc": "docs/core-data-structures/session.zh.md", + "symbol": "SurfaceFoldReplacement", + "source": "packages/core/session/src/surface.ts" + }, + { + "doc": "docs/core-data-structures/session.zh.md", + "symbol": "SurfaceFoldResult", + "source": "packages/core/session/src/surface.ts" + }, + { + "doc": "docs/core-data-structures/session.zh.md", + "symbol": "Session", + "source": "packages/core/session/src/index.ts", + "projection": "public-api" + }, + { + "doc": "docs/core-data-structures/persistence.zh.md", + "symbol": "SessionHeader", + "source": "packages/core/session/src/types.ts" + }, + { + "doc": "docs/core-data-structures/persistence.zh.md", + "symbol": "CreateSessionOptions", + "source": "packages/core/session/src/types.ts" + }, + { + "doc": "docs/core-data-structures/persistence.zh.md", + "symbol": "SessionLocation", + "source": "packages/session-persistence/session-persistence/src/index.ts" + }, + { + "doc": "docs/core-data-structures/persistence.zh.md", + "symbol": "SessionPersistenceRevision", + "source": "packages/session-persistence/session-persistence/src/revision.ts" + }, + { + "doc": "docs/core-data-structures/persistence.zh.md", + "symbol": "SessionPersistenceSnapshot", + "source": "packages/session-persistence/session-persistence/src/index.ts" + }, + { + "doc": "docs/core-data-structures/session-query.zh.md", + "symbol": "SessionEventSurface", + "source": "packages/session-query/session-query/src/types.ts" + }, + { + "doc": "docs/core-data-structures/session-query.zh.md", + "symbol": "SessionRecord", + "source": "packages/session-query/session-query/src/types.ts" + }, + { + "doc": "docs/core-data-structures/session-query.zh.md", + "symbol": "SessionLogSnapshot", + "source": "packages/session-query/session-query/src/types.ts" + }, + { + "doc": "docs/core-data-structures/session-query.zh.md", + "symbol": "SessionSurfaceSnapshot", + "source": "packages/session-query/session-query/src/types.ts" + }, + { + "doc": "docs/core-data-structures/session-query.zh.md", + "symbol": "SessionEventRecord", + "source": "packages/session-query/session-query/src/types.ts" + }, + { + "doc": "docs/core-data-structures/session-query.zh.md", + "symbol": "SessionResultFilter", + "source": "packages/session-query/session-query/src/types.ts" + }, + { + "doc": "docs/core-data-structures/session-query.zh.md", + "symbol": "SessionEventResultFilter", + "source": "packages/session-query/session-query/src/types.ts" + }, + { + "doc": "docs/core-data-structures/session-query.zh.md", + "symbol": "SessionEventSearchDocument", + "source": "packages/session-query/session-query/src/types.ts" + }, + { + "doc": "docs/core-data-structures/session-query.zh.md", + "symbol": "SessionSearchCursor", + "source": "packages/session-query/session-query/src/cursor.ts" + }, + { + "doc": "docs/core-data-structures/session-query.zh.md", + "symbol": "SessionSearchRequest", + "source": "packages/session-query/session-query/src/types.ts" + }, + { + "doc": "docs/core-data-structures/session-query.zh.md", + "symbol": "SessionEventSearchRequest", + "source": "packages/session-query/session-query/src/types.ts" + }, + { + "doc": "docs/core-data-structures/session-query.zh.md", + "symbol": "SessionSearchPage", + "source": "packages/session-query/session-query/src/types.ts" + }, + { + "doc": "docs/core-data-structures/session-query.zh.md", + "symbol": "SessionEventSearchHit", + "source": "packages/session-query/session-query/src/types.ts" + }, + { + "doc": "docs/core-data-structures/session-query.zh.md", + "symbol": "SessionSearchHit", + "source": "packages/session-query/session-query/src/types.ts" + }, + { + "doc": "docs/core-data-structures/session-query.zh.md", + "symbol": "SessionLineageNode", + "source": "packages/session-query/session-query/src/types.ts" + }, + { + "doc": "docs/core-data-structures/session-query.zh.md", + "symbol": "SessionLineageTrace", + "source": "packages/session-query/session-query/src/types.ts" + }, + { + "doc": "docs/core-data-structures/session-query.zh.md", + "symbol": "SessionQueryErrorCode", + "source": "packages/session-query/session-query/src/config.ts" + }, + { + "doc": "docs/core-data-structures/session-query.zh.md", + "symbol": "SessionEventReadRequest", + "source": "packages/session-query/session-query/src/types.ts" + }, + { + "doc": "docs/core-data-structures/session-query.zh.md", + "symbol": "SessionEventWindow", + "source": "packages/session-query/session-query/src/types.ts" + }, + { + "doc": "docs/core-data-structures/session-query.zh.md", + "symbol": "SessionEventTraceRequest", + "source": "packages/session-query/session-query/src/types.ts" + }, + { + "doc": "docs/core-data-structures/session-query.zh.md", + "symbol": "SessionEventTrace", + "source": "packages/session-query/session-query/src/types.ts" + }, + { + "doc": "docs/core-data-structures/tools.zh.md", + "symbol": "ToolOutputDefinition", + "source": "packages/core/tools/src/index.ts" + }, + { + "doc": "docs/core-data-structures/tools.zh.md", + "symbol": "ToolDefinition", + "source": "packages/core/tools/src/index.ts" + }, + { + "doc": "docs/core-data-structures/tools.zh.md", + "symbol": "ValueSchemaSpec", + "source": "packages/core/tools/src/schema.ts" + }, + { + "doc": "docs/core-data-structures/tools.zh.md", + "symbol": "ParameterPropertySpec", + "source": "packages/core/tools/src/schema.ts" + }, + { + "doc": "docs/core-data-structures/tools.zh.md", + "symbol": "ParameterSchemaSpec", + "source": "packages/core/tools/src/schema.ts" + }, + { + "doc": "docs/core-data-structures/tools.zh.md", + "symbol": "InferValue", + "source": "packages/core/tools/src/schema.ts" + }, + { + "doc": "docs/core-data-structures/tools.zh.md", + "symbol": "InferArgs", + "source": "packages/core/tools/src/schema.ts" + }, + { + "doc": "docs/core-data-structures/tools.zh.md", + "symbol": "ToolExecutionToken", + "source": "packages/core/tools/src/index.ts" + }, + { + "doc": "docs/core-data-structures/tools.zh.md", + "symbol": "ToolExecutionInput", + "source": "packages/core/tools/src/index.ts" + }, + { + "doc": "docs/core-data-structures/tools.zh.md", + "symbol": "ToolExecution", + "source": "packages/core/tools/src/index.ts" + }, + { + "doc": "docs/core-data-structures/tools.zh.md", + "symbol": "ToolDispatchExecution", + "source": "packages/core/tools/src/index.ts" + }, + { + "doc": "docs/core-data-structures/tools.zh.md", + "symbol": "ToolExecutionMode", + "source": "packages/core/tools/src/index.ts" + }, + { + "doc": "docs/core-data-structures/tools.zh.md", + "symbol": "ToolRunContext", + "source": "packages/core/tools/src/index.ts" + }, + { + "doc": "docs/core-data-structures/tools.zh.md", + "symbol": "ToolGuard", + "source": "packages/core/tools/src/index.ts" + }, + { + "doc": "docs/core-data-structures/tools.zh.md", + "symbol": "ToolRestriction", + "source": "packages/core/tools/src/index.ts" + }, + { + "doc": "docs/core-data-structures/tools.zh.md", + "symbol": "ToolFailure", + "source": "packages/core/tools/src/index.ts" + }, + { + "doc": "docs/core-data-structures/tools.zh.md", + "symbol": "ToolExecutionSuccess", + "source": "packages/core/tools/src/index.ts" + }, + { + "doc": "docs/core-data-structures/tools.zh.md", + "symbol": "ToolExecutionFailure", + "source": "packages/core/tools/src/index.ts" + }, + { + "doc": "docs/core-data-structures/tools.zh.md", + "symbol": "ToolExecutionResult", + "source": "packages/core/tools/src/index.ts" + }, + { + "doc": "docs/core-data-structures/tools.zh.md", + "symbol": "PreToolDecision", + "source": "packages/core/tools/src/index.ts" + }, + { + "doc": "docs/core-data-structures/tools.zh.md", + "symbol": "PostToolDecision", + "source": "packages/core/tools/src/index.ts" + }, + { + "doc": "docs/core-data-structures/tools.zh.md", + "symbol": "JsonSchemaScalar", + "source": "packages/core/tools/src/json-schema.ts" + }, + { + "doc": "docs/core-data-structures/tools.zh.md", + "symbol": "JsonSchemaType", + "source": "packages/core/tools/src/json-schema.ts" + }, + { + "doc": "docs/core-data-structures/tools.zh.md", + "symbol": "JsonSchemaNode", + "source": "packages/core/tools/src/json-schema.ts" + }, + { + "doc": "docs/core-data-structures/tools.zh.md", + "symbol": "ObjectJsonSchema", + "source": "packages/core/tools/src/json-schema.ts" + }, + { + "doc": "docs/core-data-structures/user-interaction.zh.md", + "symbol": "AskUserQuestionOption", + "source": "packages/ui/user-interaction/src/types.ts" + }, + { + "doc": "docs/core-data-structures/user-interaction.zh.md", + "symbol": "AskUserQuestionItem", + "source": "packages/ui/user-interaction/src/types.ts" + }, + { + "doc": "docs/core-data-structures/user-interaction.zh.md", + "symbol": "AskUserQuestionRequest", + "source": "packages/ui/user-interaction/src/index.ts" + }, + { + "doc": "docs/core-data-structures/user-interaction.zh.md", + "symbol": "AskUserQuestionAnswerItem", + "source": "packages/ui/user-interaction/src/types.ts" + }, + { + "doc": "docs/core-data-structures/user-interaction.zh.md", + "symbol": "AskUserQuestionAnswer", + "source": "packages/ui/user-interaction/src/types.ts" + }, + { + "doc": "docs/core-data-structures/user-interaction.zh.md", + "symbol": "UserInteractionProvider", + "source": "packages/ui/user-interaction/src/index.ts" + }, + { + "doc": "docs/core-data-structures/user-interaction.zh.md", + "symbol": "UserInteractionError", + "source": "packages/ui/user-interaction/src/index.ts" + }, + { + "doc": "docs/core-data-structures/approval.zh.md", + "symbol": "ApprovalRequestId", + "source": "packages/ui/user-approval/src/types.ts" + }, + { + "doc": "docs/core-data-structures/approval.zh.md", + "symbol": "ApprovalOutcome", + "source": "packages/ui/user-approval/src/types.ts" + }, + { + "doc": "docs/core-data-structures/approval.zh.md", + "symbol": "ApprovalPolicy", + "source": "packages/ui/user-approval/src/index.ts" + }, + { + "doc": "docs/core-data-structures/approval.zh.md", + "symbol": "ApprovalRequest", + "source": "packages/ui/user-approval/src/index.ts" + }, + { + "doc": "docs/core-data-structures/bash.zh.md", + "symbol": "DshEnvironmentKey", + "source": "packages/bash/bash/src/types.ts" + }, + { + "doc": "docs/core-data-structures/bash.zh.md", + "symbol": "DshEnvironment", + "source": "packages/bash/bash/src/types.ts" + }, + { + "doc": "docs/core-data-structures/bash.zh.md", + "symbol": "BashExecRequest", + "source": "packages/bash/bash/src/types.ts" + }, + { + "doc": "docs/core-data-structures/bash.zh.md", + "symbol": "BashExecSpec", + "source": "packages/bash/bash/src/types.ts" + }, + { + "doc": "docs/core-data-structures/bash.zh.md", + "symbol": "BashRunResult", + "source": "packages/bash/bash/src/types.ts" + }, + { + "doc": "docs/core-data-structures/bash.zh.md", + "symbol": "BashSandboxInfo", + "source": "packages/bash/bash/src/types.ts" + }, + { + "doc": "docs/core-data-structures/bash.zh.md", + "symbol": "CollectedOutput", + "source": "packages/bash/bash/src/types.ts" + }, + { + "doc": "docs/core-data-structures/bash.zh.md", + "symbol": "BashProcess", + "source": "packages/bash/bash/src/types.ts" + }, + { + "doc": "docs/core-data-structures/bash.zh.md", + "symbol": "BashProcessRead", + "source": "packages/bash/bash/src/types.ts" + }, + { + "doc": "docs/core-data-structures/sandbox.zh.md", + "symbol": "SandboxMode", + "source": "packages/sandbox/sandbox/src/index.ts" + }, + { + "doc": "docs/core-data-structures/sandbox.zh.md", + "symbol": "ConfinedSandboxMode", + "source": "packages/sandbox/sandbox/src/index.ts" + }, + { + "doc": "docs/core-data-structures/sandbox.zh.md", + "symbol": "SandboxExecutionPolicy", + "source": "packages/sandbox/sandbox/src/index.ts" + }, + { + "doc": "docs/core-data-structures/sandbox.zh.md", + "symbol": "SandboxEnforcement", + "source": "packages/sandbox/sandbox/src/index.ts" + }, + { + "doc": "docs/core-data-structures/sandbox.zh.md", + "symbol": "SandboxPolicy", + "source": "packages/sandbox/sandbox/src/index.ts" + }, + { + "doc": "docs/core-data-structures/sandbox.zh.md", + "symbol": "SandboxPolicyRequest", + "source": "packages/sandbox/sandbox-policy/src/index.ts" + }, + { + "doc": "docs/core-data-structures/sandbox.zh.md", + "symbol": "ConfinedArgv", + "source": "packages/sandbox/sandbox/src/index.ts" + }, + { + "doc": "docs/core-data-structures/code-runtime.zh.md", + "symbol": "CodeJsonValue", + "source": "packages/code-runtime/code-runtime/src/types.ts" + }, + { + "doc": "docs/core-data-structures/code-runtime.zh.md", + "symbol": "CodeRunRequest", + "source": "packages/code-runtime/code-runtime/src/types.ts" + }, + { + "doc": "docs/core-data-structures/code-runtime.zh.md", + "symbol": "CodeRunResult", + "source": "packages/code-runtime/code-runtime/src/types.ts" + }, + { + "doc": "docs/core-data-structures/code-runtime.zh.md", + "symbol": "CodeBindingNamespace", + "source": "packages/code-runtime/code-runtime/src/types.ts" + }, + { + "doc": "docs/core-data-structures/code-runtime.zh.md", + "symbol": "CodeBindingErrorClass", + "source": "packages/code-runtime/code-runtime/src/types.ts" + }, + { + "doc": "docs/core-data-structures/code-runtime.zh.md", + "symbol": "CodeBindingFunction", + "source": "packages/code-runtime/code-runtime/src/types.ts" + }, + { + "doc": "docs/core-data-structures/code-runtime.zh.md", + "symbol": "CodeRunFailure", + "source": "packages/code-runtime/code-runtime/src/types.ts" + }, + { + "doc": "docs/core-data-structures/filesystem.zh.md", + "symbol": "FsTarget", + "source": "packages/fs/fs/src/types.ts" + }, + { + "doc": "docs/core-data-structures/filesystem.zh.md", + "symbol": "FsTargetKey", + "source": "packages/fs/fs/src/types.ts" + }, + { + "doc": "docs/core-data-structures/filesystem.zh.md", + "symbol": "FsVersion", + "source": "packages/fs/fs/src/types.ts" + }, + { + "doc": "docs/core-data-structures/filesystem.zh.md", + "symbol": "FsInfo", + "source": "packages/fs/fs/src/types.ts" + }, + { + "doc": "docs/core-data-structures/filesystem.zh.md", + "symbol": "FsPathInfo", + "source": "packages/fs/fs/src/types.ts" + }, + { + "doc": "docs/core-data-structures/filesystem.zh.md", + "symbol": "FsDirEntry", + "source": "packages/fs/fs/src/types.ts" + }, + { + "doc": "docs/core-data-structures/filesystem.zh.md", + "symbol": "FsWriteIntent", + "source": "packages/fs/fs/src/types.ts" + }, + { + "doc": "docs/core-data-structures/filesystem.zh.md", + "symbol": "FsWriteOutcome", + "source": "packages/fs/fs/src/types.ts" + }, + { + "doc": "docs/core-data-structures/filesystem.zh.md", + "symbol": "FsEditRequest", + "source": "packages/fs/fs/src/types.ts" + }, + { + "doc": "docs/core-data-structures/filesystem.zh.md", + "symbol": "FsEditOutcome", + "source": "packages/fs/fs/src/types.ts" + }, + { + "doc": "docs/core-data-structures/filesystem.zh.md", + "symbol": "FsErrorCode", + "source": "packages/fs/fs/src/types.ts" + }, + { + "doc": "docs/core-data-structures/filesystem.zh.md", + "symbol": "FsPolicyExec", + "source": "packages/fs/fs-policy/src/types.ts" + }, + { + "doc": "docs/core-data-structures/filesystem.zh.md", + "symbol": "FileReadOutcome", + "source": "packages/fs/tool-fs/src/read-render.ts" + }, + { + "doc": "docs/core-data-structures/skills.zh.md", + "symbol": "SkillSource", + "source": "packages/skill/skill/src/index.ts" + }, + { + "doc": "docs/core-data-structures/skills.zh.md", + "symbol": "SkillResourceBase", + "source": "packages/skill/skill/src/index.ts" + }, + { + "doc": "docs/core-data-structures/skills.zh.md", + "symbol": "SkillSummary", + "source": "packages/skill/skill/src/index.ts" + }, + { + "doc": "docs/core-data-structures/skills.zh.md", + "symbol": "SkillCandidate", + "source": "packages/skill/skill/src/index.ts" + }, + { + "doc": "docs/core-data-structures/skills.zh.md", + "symbol": "SkillDefinition", + "source": "packages/skill/skill/src/index.ts" + }, + { + "doc": "docs/core-data-structures/skills.zh.md", + "symbol": "SkillRegistration", + "source": "packages/skill/skill/src/index.ts" + }, + { + "doc": "docs/core-data-structures/skills.zh.md", + "symbol": "SkillLookupOptions", + "source": "packages/skill/skill/src/index.ts" + }, + { + "doc": "docs/core-data-structures/skills.zh.md", + "symbol": "SkillProvider", + "source": "packages/skill/skill/src/index.ts" + }, + { + "doc": "docs/core-data-structures/skills.zh.md", + "symbol": "Config", + "source": "packages/skill/skill/src/index.ts" + }, + { + "doc": "docs/core-data-structures/compaction.zh.md", + "symbol": "CompactionResult", + "source": "packages/compact/compact/src/types.ts" + }, + { + "doc": "docs/core-data-structures/compaction.zh.md", + "symbol": "CompactionTrigger", + "source": "packages/compact/compact/src/index.ts" + }, + { + "doc": "docs/core-data-structures/compaction.zh.md", + "symbol": "PrunedEntry", + "source": "packages/compact/compact-tool-result-prune/src/types.ts" + }, + { + "doc": "docs/core-data-structures/compaction.zh.md", + "symbol": "PruneResult", + "source": "packages/compact/compact-tool-result-prune/src/types.ts" + }, + { + "doc": "docs/core-data-structures/subagent.zh.md", + "symbol": "SubagentCapabilities", + "source": "packages/subagent/subagent/src/types.ts" + }, + { + "doc": "docs/core-data-structures/subagent.zh.md", + "symbol": "SubagentStartRequest", + "source": "packages/subagent/subagent/src/types.ts" + }, + { + "doc": "docs/core-data-structures/subagent.zh.md", + "symbol": "SubagentResult", + "source": "packages/subagent/subagent/src/types.ts" + }, + { + "doc": "docs/core-data-structures/subagent.zh.md", + "symbol": "SubagentStopReasonMap", + "source": "packages/subagent/subagent/src/types.ts" + }, + { + "doc": "docs/core-data-structures/subagent.zh.md", + "symbol": "SubagentRun", + "source": "packages/subagent/subagent/src/types.ts" + }, + { + "doc": "docs/core-data-structures/subagent.zh.md", + "symbol": "SubagentProvider", + "source": "packages/subagent/subagent/src/types.ts" + }, + { + "doc": "docs/core-data-structures/web.zh.md", + "symbol": "WebSearchRequest", + "source": "packages/web/web/src/types.ts" + }, + { + "doc": "docs/core-data-structures/web.zh.md", + "symbol": "WebSearchResult", + "source": "packages/web/web/src/types.ts" + }, + { + "doc": "docs/core-data-structures/web.zh.md", + "symbol": "WebSearchSource", + "source": "packages/web/web/src/types.ts" + }, + { + "doc": "docs/core-data-structures/web.zh.md", + "symbol": "WebFetchRequest", + "source": "packages/web/web/src/types.ts" + }, + { + "doc": "docs/core-data-structures/web.zh.md", + "symbol": "WebFetchResult", + "source": "packages/web/web/src/types.ts" + }, + { + "doc": "docs/core-data-structures/web.zh.md", + "symbol": "WebFetchBody", + "source": "packages/web/web/src/types.ts" + }, + { + "doc": "docs/core-data-structures/workflow.zh.md", + "symbol": "WorkflowStartRequest", + "source": "packages/workflow/workflow/src/types.ts" + }, + { + "doc": "docs/core-data-structures/workflow.zh.md", + "symbol": "WorkflowMeta", + "source": "packages/workflow/workflow/src/types.ts" + }, + { + "doc": "docs/core-data-structures/workflow.zh.md", + "symbol": "WorkflowResult", + "source": "packages/workflow/workflow/src/types.ts" + }, + { + "doc": "docs/core-data-structures/workflow.zh.md", + "symbol": "WorkflowRun", + "source": "packages/workflow/workflow/src/types.ts" } ] } diff --git a/scripts/verify-cordis-config.ts b/scripts/verify-cordis-config.ts index 916db4a168..6041be78ed 100644 --- a/scripts/verify-cordis-config.ts +++ b/scripts/verify-cordis-config.ts @@ -12,6 +12,7 @@ import { globSync, readFileSync } from 'node:fs' import { dirname, relative, resolve } from 'node:path' import * as yaml from 'js-yaml' import ts from 'typescript' +import { cordisConfigFiles } from './cordis-config-files.ts' interface JsExpr { __jsExpr: string @@ -39,10 +40,7 @@ const jsExprType = new yaml.Type('tag:yaml.org,2002:js', { }) const schema = yaml.JSON_SCHEMA.extend(jsExprType) -const files = globSync(['**/*cordis*.yml', '**/*cordis*.yaml'], { - cwd: root, - exclude: ['.claude/**', 'node_modules/**', 'vendor/**'], -}).sort() +const files = cordisConfigFiles(root) const errors: string[] = [] const examplePluginReferences: PluginReference[] = [] diff --git a/website/docs.ts b/website/docs.ts index ee7ad64061..1888cd908c 100644 --- a/website/docs.ts +++ b/website/docs.ts @@ -226,14 +226,53 @@ const cordisTutorial = mirroredPages(([ ...(file === 'index.md' ? { sourceAliases: ['docs/cordis-tutorial'] } : {}), }))) +const cordisPrimerReference = pairedPages([ + { + source: 'docs/cordis-primer.md', + route: 'reference/cordis-primer.md', + label: { root: 'Cordis 入门', en: 'Cordis primer' }, + sidebar: { root: 'zh-reference', en: 'en-reference' }, + section: { root: '概念', en: 'Concepts' }, + order: 1, + }, +]) + +const coreDataReference = pairedPages(([ + ['core.md', '核心数据结构', 'Core data structures', 0], + ['scope.md', '作用域', 'Scopes', 1], + ['session.md', '会话', 'Sessions', 2], + ['system-prompt.md', '系统提示词', 'System prompts', 4], + ['tools.md', '工具', 'Tools', 5], + ['llm-streaming.md', 'LLM 流式响应', 'LLM streaming', 6], + ['bash.md', 'Bash 执行', 'Bash execution', 7], + ['filesystem.md', '文件系统', 'Filesystem', 9], + ['code-runtime.md', '代码运行时', 'Code runtime', 10], + ['compaction.md', '上下文压缩', 'Compaction', 11], + ['subagent.md', '子代理', 'Subagents', 12], + ['workflow.md', '工作流', 'Workflows', 13], + ['skills.md', '技能', 'Skills', 14], + ['approval.md', '审批', 'Approvals', 15], + ['user-interaction.md', '用户交互', 'User interaction', 16], + ['sandbox.md', '沙箱', 'Sandboxing', 18], + ['web.md', 'Web 访问', 'Web access', 19], + ['persistence.md', '会话持久化', 'Session persistence', 20], +] as const).map(([file, rootLabel, enLabel, order]): PairedPage => ({ + source: `docs/core-data-structures/${file}`, + route: `reference/core-data-structures/${file}`, + label: { root: rootLabel, en: enLabel }, + sidebar: { root: 'zh-reference', en: 'en-reference' }, + section: { root: '数据结构', en: 'Data structures' }, + order, + ...(file === 'core.md' ? { sourceAliases: ['docs/core-data-structures'] } : {}), +}))) + const reference = mirroredPages([ ...([ - ['docs/architecture.md', 'reference/index.md', '架构', 'Architecture'], - ['docs/cordis-primer.md', 'reference/cordis-primer.md', 'Cordis 入门', 'Cordis primer'], - ['docs/capability-seams.md', 'reference/capability-seams.md', '能力服务', 'Capability services'], - ['docs/agent-lifecycle.md', 'reference/agent-lifecycle.md', 'Agent 生命周期', 'Agent lifecycle'], - ['docs/tool-execution-pipeline.md', 'reference/tool-execution-pipeline.md', 'Tool 执行', 'Tool execution'], - ] as const).map(([source, route, rootLabel, enLabel], order): MirroredPage => ({ + ['docs/architecture.md', 'reference/index.md', '架构', 'Architecture', 0], + ['docs/capability-seams.md', 'reference/capability-seams.md', '能力服务', 'Capability services', 2], + ['docs/agent-lifecycle.md', 'reference/agent-lifecycle.md', 'Agent 生命周期', 'Agent lifecycle', 3], + ['docs/tool-execution-pipeline.md', 'reference/tool-execution-pipeline.md', 'Tool 执行', 'Tool execution', 4], + ] as const).map(([source, route, rootLabel, enLabel, order]): MirroredPage => ({ source, route, contentLocale: 'en-US', @@ -273,28 +312,10 @@ const reference = mirroredPages([ order, })), ...([ - ['core.md', '核心数据结构', 'Core data structures'], - ['scope.md', '作用域', 'Scopes'], - ['session.md', '会话', 'Sessions'], - ['goal.md', '目标', 'Goals'], - ['system-prompt.md', '系统提示词', 'System prompts'], - ['tools.md', '工具', 'Tools'], - ['llm-streaming.md', 'LLM 流式响应', 'LLM streaming'], - ['bash.md', 'Bash 执行', 'Bash execution'], - ['pty.md', 'PTY 会话', 'PTY sessions'], - ['filesystem.md', '文件系统', 'Filesystem'], - ['code-runtime.md', '代码运行时', 'Code runtime'], - ['compaction.md', '上下文压缩', 'Compaction'], - ['subagent.md', '子代理', 'Subagents'], - ['workflow.md', '工作流', 'Workflows'], - ['skills.md', '技能', 'Skills'], - ['approval.md', '审批', 'Approvals'], - ['user-interaction.md', '用户交互', 'User interaction'], - ['commands.md', '命令', 'Human commands'], - ['sandbox.md', '沙箱', 'Sandboxing'], - ['web.md', 'Web 访问', 'Web access'], - ['persistence.md', '会话持久化', 'Session persistence'], - ] as const).map(([file, rootLabel, enLabel], order): MirroredPage => ({ + ['goal.md', '目标', 'Goals', 3], + ['pty.md', 'PTY 会话', 'PTY sessions', 8], + ['commands.md', '命令', 'Human commands', 17], + ] as const).map(([file, rootLabel, enLabel, order]): MirroredPage => ({ source: `docs/core-data-structures/${file}`, route: `reference/core-data-structures/${file}`, contentLocale: 'en-US', @@ -302,7 +323,6 @@ const reference = mirroredPages([ sidebar: { root: 'zh-reference', en: 'en-reference' }, section: { root: '数据结构', en: 'Data structures' }, order, - ...(file === 'core.md' ? { sourceAliases: ['docs/core-data-structures'] } : {}), })), ...([ ['adding-a-package.md', '新增 Package', 'Adding a package'], @@ -325,5 +345,7 @@ export const docsPages: DocsPage[] = [ ...homeAndGuide, ...develop, ...cordisTutorial, + ...cordisPrimerReference, + ...coreDataReference, ...reference, ]