Merge remote-tracking branch 'origin/master' into worktree/ci-native-windows-20260808

# Conflicts:
#	.agents/notes/archived/process/2026-07-27-wine-windows-gates-experiment.i18n.yaml
#	.agents/notes/implemented/process/2026-07-21-serial-cross-platform-ci-reference.i18n.yaml
#	.agents/notes/implemented/process/2026-07-21-serial-cross-platform-ci-reference.zh.md
#	.agents/notes/implemented/process/2026-07-23-portable-required-pull-request-ci.i18n.yaml
#	.agents/notes/implemented/process/2026-07-23-portable-required-pull-request-ci.zh.md
This commit is contained in:
Tianyi Cui committed 2026-08-09 13:26:11 +08:00
commit eb9e7c19eb
1007 files changed
+1965 -1893

No files matched your search

@@ -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 complete source document from English to Chinese, producing natural, professional technical prose.\n\nRead each complete semantic unit, understand it, and restate it as a native technical author would write it in the target language. Do not mechanically preserve source-language syntax. Then verify the translation against the source clause by clause: preserve every proposition and add none. Fluency never justifies losing or altering meaning, and completeness never justifies unnatural word-for-word prose.\n\n## Priority\n\nApply these authorities in order:\n\n1. Preserve the source meaning and the required document structure, protected content, and formatting.\n2. Follow the injected terminology table exactly.\n3. Use the injected whole-document gold pairs to calibrate target-language voice and phrasing.\n4. Apply the general writing guidance and illustrative examples in this prompt.\n\nA lower-priority rule may refine but never override a higher-priority requirement. Gold pairs calibrate voice; they are not a translation memory. No style preference, gold-pair phrasing, or embedded example may override source meaning, required structure, protected content, or the terminology table.\n\n## Quality Requirements\n\n### Structure and Format Preservation\n- Output a complete translated document that maintains the same document frame as the source: heading hierarchy and order, list kinds and item counts, ordered-list starts, table rows and columns, link targets, and code blocks.\n- Paragraph boundaries may change within the same structural unit when the target language needs different semantic grouping. Do not merge or move content across headings, list items, table cells, or other independent structural units.\n- Keep each prose paragraph on one physical line. Use paragraph breaks, not hard-wrapped lines inside a paragraph.\n- Fenced code blocks must be byte-identical to the source, including info strings, whitespace, and ALL comments inside them. Do NOT translate or reformat any content inside code blocks. This is a hard rule with no exceptions.\n- Inline code spans must be kept verbatim. This includes commands, flags, paths, identifiers, API and event names, config keys, protocol values, version numbers, and other machine-readable tokens. Never translate or reformat them.\n- Every relative link must point to the same target as in the source. Translate link text; do not change link targets.\n- Language switcher line: when an English source contains `English | [中文](source-filename.zh.md)`, write `[English](source-filename.md) | 中文`. When a Chinese source contains `[English](source-filename.md) | 中文`, write `English | [中文](source-filename.zh.md)`. Do NOT copy the source switcher unchanged. If the source has no switcher, do not invent a filename or switcher; the pipeline inserts the canonical target switcher after parsing `<final>`.\n- Preserve emphasis marker types and the semantic spans they cover. Do not add, remove, move, or change bold and italic markers.\n\n### Faithfulness\n- Preserve every proposition in the source and add none. Every sentence, list item, note, FIXME, warning, example, caveat, prerequisite, and guarantee must have an equivalent in the translation. Count list items on both sides.\n- Preserve actors, objects, conditions, exceptions, negation, modality, causal relationships, and distinctions between concepts.\n- Preserve the exact strength and orientation of contracts. Completion and lifecycle conditions, failure behavior, directions and data flow, normal and exceptional result channels, ownership changes, and quantitative bounds must not be weakened, strengthened, reversed, or merged.\n- Translate ideas rather than source-language idioms, but never use fluency as a reason to omit or alter meaning.\n\n### Tone and Style\n- The translation must read as if originally written in the target language by a native technical author. 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- Name an actor when the target language would otherwise obscure an actor that the source states or unambiguously implies. Never invent responsibility merely to avoid a passive construction.\n- Prefer established target-language engineering idiom over literal renderings, and localize metaphors instead of transplanting them.\n- Use polite imperative forms where the text instructs the reader to do something. In Chinese, address the reader as `你`, not `您`.\n- Keep the author's register: concise stays concise, detailed stays detailed.\n\n### Sentence Structure\n- Break long sentences where the target language needs a pause. Avoid run-on sentences.\n- Use active voice when it iLine truncated
"content": "# Translation Prompt\n\nYou are a senior technical translator specializing in LLM and agent development documentation. Your task is to translate the complete source document from English to Chinese, producing natural, professional technical prose.\n\nRead each complete semantic unit, understand it, and restate it as a native technical author would write it in the target language. Do not mechanically preserve source-language syntax. Then verify the translation against the source clause by clause: preserve every proposition and add none. Fluency never justifies losing or altering meaning, and completeness never justifies unnatural word-for-word prose.\n\n## Priority\n\nApply these authorities in order:\n\n1. Preserve the source meaning and the required document structure, protected content, and formatting.\n2. Follow the injected terminology table exactly.\n3. Use the injected whole-document gold pairs to calibrate target-language voice and phrasing.\n4. Apply the general writing guidance and illustrative examples in this prompt.\n\nA lower-priority rule may refine but never override a higher-priority requirement. Gold pairs calibrate voice; they are not a translation memory. No style preference, gold-pair phrasing, or embedded example may override source meaning, required structure, protected content, or the terminology table.\n\n## Quality Requirements\n\n### Structure and Format Preservation\n- Output a complete translated document that maintains the same document frame as the source: heading hierarchy and order, list kinds and item counts, ordered-list starts, table rows and columns, link targets, and code blocks.\n- Paragraph boundaries may change within the same structural unit when the target language needs different semantic grouping. Do not merge or move content across headings, list items, table cells, or other independent structural units.\n- Keep each prose paragraph on one physical line. Use paragraph breaks, not hard-wrapped lines inside a paragraph.\n- Fenced code blocks must be byte-identical to the source, including info strings, whitespace, and ALL comments inside them. Do NOT translate or reformat any content inside code blocks. This is a hard rule with no exceptions.\n- Inline code spans must be kept verbatim. This includes commands, flags, paths, identifiers, API and event names, config keys, protocol values, version numbers, and other machine-readable tokens. Never translate or reformat them.\n- Every relative link must point to the same target as in the source. Translate link text; do not change link targets.\n- Language switcher line: when an English source contains `English | [中文](source-filename.zh.md)`, write `[English](source-filename.md) | 中文`. When a Chinese source contains `[English](source-filename.md) | 中文`, write `English | [中文](source-filename.zh.md)`. Do NOT copy the source switcher unchanged. If the source has no switcher, do not invent a filename or switcher; the pipeline inserts the canonical target switcher after parsing `<final>`.\n- Preserve emphasis marker types and the semantic spans they cover. Do not add, remove, move, or change bold and italic markers.\n\n### Faithfulness\n- Preserve every proposition in the source and add none. Every sentence, list item, note, FIXME, warning, example, caveat, prerequisite, and guarantee must have an equivalent in the translation. Count list items on both sides.\n- Preserve actors, objects, conditions, exceptions, negation, modality, causal relationships, and distinctions between concepts.\n- Preserve the exact strength and orientation of contracts. Completion and lifecycle conditions, failure behavior, directions and data flow, normal and exceptional result channels, ownership changes, and quantitative bounds must not be weakened, strengthened, reversed, or merged.\n- Translate ideas rather than source-language idioms, but never use fluency as a reason to omit or alter meaning.\n\n### Tone and Style\n- The translation must read as if originally written in the target language by a native technical author. 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- Name an actor when the target language would otherwise obscure an actor that the source states or unambiguously implies. Never invent responsibility merely to avoid a passive construction.\n- Prefer established target-language engineering idiom over literal renderings, and localize metaphors instead of transplanting them.\n- Use polite imperative forms where the text instructs the reader to do something. In Chinese, address the reader as `你`, not `您`.\n- Keep the author's register: concise stays concise, detailed stays detailed.\n\n### Sentence Structure\n- Break long sentences where the target language needs a pause. Avoid run-on sentences.\n- Use active voice when it iLine truncated
},
{
"role": "user",
@@ -12,7 +12,7 @@
},
{
"role": "assistant",
"content": "# DeepSeek Harness\n\n[English](README.md) | 中文\n\nDeepSeek Harness(`dsh`)是一款基于 DeepSeek Harness SDK 构建的开源 coding agent(编程智能体)。\n\n它采用了**一切皆插件**的架构。\n\n## 内测声明\n\nDeepSeek Harness 正处于内部测试阶段,功能和接口可能发生变化。\n\n为帮助诊断上报的问题,内测版本默认上传所有会话日志。设置 `DSH_TELEMETRY_DISABLED=1` 可关闭遥测。请通过内部企业微信群反馈问题和建议。\n\n## 安装\n\n克隆仓库,然后运行安装器:\n\n```sh\ngit clone <repo-url>\ncd deepseek-harness\nscripts/install.sh\n```\n\n安装器要求系统已安装 `git` 和 Node `^22.19 || >=24`,缺少 `pnpm` 时可代为安装,并会提示输入 DeepSeek API 密钥,然后构建所需的仓库产物并启动 Web UI。\n\n默认生效的检出位于 `~/.dsh/source/current`,启动器链接到 `~/.local/bin`。再次运行安装器即可更新。其他位置、更新机制和恢复选项由 [`scripts/install.sh`](scripts/install.sh) 负责。\n\n## 使用 DeepSeek Harness\n\n### Web UI\n\n推荐在本地使用 Web UI;安装结束时,选择 Web UI 即可。以后需要启动时,或更新当前生效的检出后,请构建仓库并运行:\n\n```sh\n(cd ~/.dsh/source/current && pnpm run build)\ndsh web\n```\n\n上述路径是安装器的默认位置。如果你设置过 `DSH_SOURCE` 或 `DSH_CURRENT`,或者复用了已有检出,请把 `~/.dsh/source/current` 换成该检出路径;详情见 [`scripts/install.sh`](scripts/install.sh)。Web UI 默认通过 `http://127.0.0.1:3080` 提供服务。\n\n### Profile\n\n`dsh` 启动 profile:按序叠放的插件组合包 patch 层,之上再叠加你在 `$DSH_HOME/profiles/<name>` 中的自有覆盖层:\n\n```sh\ndsh --profile web # the browser UI (same as: dsh web)\ndsh plugin --profile tui add <package> # install a plugin into a custom profile\ndsh --profile tui # boot it\n```\n\nprofile 布局、层语义与配置输出命令详见 [CLI(命令行界面)契约](apps/cli/README.md#profiles)。\n\n### Headless\n\n运行一项任务,打印最终答案后退出:\n\n```sh\ndsh run \"summarize this workspace\"\n```\n\n### 自动化与 SDK\n\n在源码检出中通过环境变量或根目录 `.env` 设置 `DEEPSEEK_API_KEY`,然后启动 ACP(Agent Client Protocol)自动化服务器:\n\n```sh\npnpm run demo:acp\n```\n\n[Python SDK](python/README.md) 驱动随附的 JSON-RPC 运行时。[示例](examples/README.md)涵盖可运行的 headless、ACP、JSON-RPC、Code Mode 和自指组合。\n\n## 为什么选择 DeepSeek Harness\n\n内置功能涵盖文件读取、编辑与搜索、shell 和持久 PTY 执行、可复用 skill(技能)、任务跟踪、目标、计划、待办事项与后台任务、subagent 与工作流、沙箱与审批、设置与凭据、可持久化、恢复、fork 与查询的会话、LSP 与 Web 访问、上下文压缩(context compaction),以及遥测。每个组合只选用适合其使用方式的能力子集。Web UI 包含 Plan Mode。\n\n- **一切皆插件。** 模型、工具、策略、存储、上下文管理和界面均可组合为 [Cordis 插件](docs/user/develop/basic/index.md),部署方无需 fork agent loop(智能体循环)即可扩展或替换行为。底层设计见[架构文档](docs/architecture.md)。\n- **运行可重建。** 凡是模型可见的内容,都会记录在权威会话流中;持久化、恢复/fork/查询、回放、遥测和 UI 均从同一组事件派生。参见[会话日志架构](docs/architecture.md#session-log)。\n- **Code Mode(需显式启用)。** 它会提供 `run_code` 工具和生成的 TypeScript SDK,只有程序输出会重新进入模型上下文。参见 [Code Mode](packages/core/tools/README.md#code-mode)。\n- **自指 Cordis 工具需显式启用。** 这些工具可让 agent 检查自身的实时运行时,并在运行中挂载或卸载插件。参见 [Cordis 工具](packages/self-modification/tool-cordis/README.md)。\n\n## 社区\n\n扫描二维码,或打开 <a href=\"https://wj.qq.com/s2/27234598/03eb/\">DeepSeek Harness 微信社区申请页面</a> 申请加入。\n\n<p>\n <img src=\"assets/community-wecom-survey.png\" alt=\"DeepSeek Harness 微信社区二维码\" width=\"240\">\n</p>\n\n## 开发\n\n请先阅读[开发指南](docs/development.md);修改包之前,请阅读[架构文档](docs/architecture.md)。\n\n面向 agent:遵循 [AGENTS.md](AGENTS.md)。\n\nDeepSeek Harness 目前处于内测阶段。\n\n## 许可证\n\n[BSD 3-Clause](LICENSE)\n\n第三方依赖及其许可证在 [THIRD_PARTY_NOTICES.md](THIRD_PARTY_NOTICES.md) 中披露。\n"
"content": "# DeepSeek Harness\n\n[English](README.md) | 中文\n\nDeepSeek Harness(`dsh`)是一款基于 DeepSeek Harness SDK 构建的开源 coding agent(编程智能体)。\n\n它采用了**一切皆插件**的架构。\n\n## 内测声明\n\nDeepSeek Harness 正处于内部测试阶段,功能和接口可能发生变化。\n\n为帮助诊断上报的问题,内测版本默认上传所有会话日志。设置 `DSH_TELEMETRY_DISABLED=1` 可关闭遥测。请通过内部企业微信群反馈问题和建议。\n\n## 安装\n\n克隆仓库,然后运行安装器:\n\n```sh\ngit clone <repo-url>\ncd deepseek-harness\nscripts/install.sh\n```\n\n安装器要求系统已安装 `git` 和 Node `^22.19 || >=24`,缺少 `pnpm` 时可代为安装,并会提示输入 DeepSeek API 密钥,然后构建所需的仓库产物并启动 Web UI。\n\n默认生效的检出位于 `~/.dsh/source/current`,启动器链接到 `~/.local/bin`。再次运行安装器即可更新。其他位置、更新机制和恢复选项由 [`scripts/install.sh`](scripts/install.sh) 负责。\n\n## 使用 DeepSeek Harness\n\n### Web UI\n\n推荐在本地使用 Web UI;安装结束时,选择 Web UI 即可。以后需要启动时,或更新当前生效的检出后,请构建仓库并运行:\n\n```sh\n(cd ~/.dsh/source/current && pnpm run build)\ndsh web\n```\n\n上述路径是安装器的默认位置。如果你设置过 `DSH_SOURCE` 或 `DSH_CURRENT`,或者复用了已有检出,请把 `~/.dsh/source/current` 换成该检出路径;详情见 [`scripts/install.sh`](scripts/install.sh)。Web UI 默认通过 `http://127.0.0.1:3080` 提供服务。\n\n### Profile\n\n`dsh` 启动 profile:按序叠放的插件组合包 patch 层,之上再叠加你在 `$DSH_HOME/profiles/<name>` 中的自有覆盖层:\n\n```sh\ndsh --profile web # the browser UI (same as: dsh web)\ndsh plugin --profile tui add <package> # install a plugin into a custom profile\ndsh --profile tui # boot it\n```\n\nprofile 布局、层语义与配置输出命令详见 [CLI(命令行界面)约定](apps/cli/README.md#profiles)。\n\n### Headless\n\n运行一项任务,打印最终答案后退出:\n\n```sh\ndsh run \"summarize this workspace\"\n```\n\n### 自动化与 SDK\n\n在源码检出中通过环境变量或根目录 `.env` 设置 `DEEPSEEK_API_KEY`,然后启动 ACP(Agent Client Protocol)自动化服务器:\n\n```sh\npnpm run demo:acp\n```\n\n[Python SDK](python/README.md) 驱动随附的 JSON-RPC 运行时。[示例](examples/README.md)涵盖可运行的 headless、ACP、JSON-RPC、Code Mode 和自指组合。\n\n## 为什么选择 DeepSeek Harness\n\n内置功能涵盖文件读取、编辑与搜索、shell 和持久 PTY 执行、可复用 skill(技能)、任务跟踪、目标、计划、待办事项与后台任务、subagent 与工作流、沙箱与审批、设置与凭据、可持久化、恢复、fork 与查询的会话、LSP 与 Web 访问、上下文压缩(context compaction),以及遥测。每个组合只选用适合其使用方式的能力子集。Web UI 包含 Plan Mode。\n\n- **一切皆插件。** 模型、工具、策略、存储、上下文管理和界面均可组合为 [Cordis 插件](docs/user/develop/basic/index.md),部署方无需 fork agent loop(智能体循环)即可扩展或替换行为。底层设计见[架构文档](docs/architecture.md)。\n- **运行可重建。** 凡是模型可见的内容,都会记录在权威会话流中;持久化、恢复/fork/查询、回放、遥测和 UI 均从同一组事件派生。参见[会话日志架构](docs/architecture.md#session-log)。\n- **Code Mode(需显式启用)。** 它会提供 `run_code` 工具和生成的 TypeScript SDK,只有程序输出会重新进入模型上下文。参见 [Code Mode](packages/core/tools/README.md#code-mode)。\n- **自指 Cordis 工具需显式启用。** 这些工具可让 agent 检查自身的实时运行时,并在运行中挂载或卸载插件。参见 [Cordis 工具](packages/self-modification/tool-cordis/README.md)。\n\n## 社区\n\n扫描二维码,或打开 <a href=\"https://wj.qq.com/s2/27234598/03eb/\">DeepSeek Harness 微信社区申请页面</a> 申请加入。\n\n<p>\n <img src=\"assets/community-wecom-survey.png\" alt=\"DeepSeek Harness 微信社区二维码\" width=\"240\">\n</p>\n\n## 开发\n\n请先阅读[开发指南](docs/development.md);修改包之前,请阅读[架构文档](docs/architecture.md)。\n\n面向 agent:遵循 [AGENTS.md](AGENTS.md)。\n\nDeepSeek Harness 目前处于内测阶段。\n\n## 许可证\n\n[BSD 3-Clause](LICENSE)\n\n第三方依赖及其许可证在 [THIRD_PARTY_NOTICES.md](THIRD_PARTY_NOTICES.md) 中披露。\n"
},
{
"role": "user",
@@ -20,7 +20,7 @@
},
{
"role": "assistant",
"content": "# 开发指南\n\n[English](development.md) | 中文\n\n搭建教程引导新贡献者从准备前置条件开始,直到检出通过检查。后面的贡献者参考介绍仓库布局、日常工作流和 CI 形态。设计依据与实现细节属于链接的 Agent Note 和脚本。\n\n## 搭建教程\n\n### 前置条件\n\n- Node.js 支持 22.19+ 与 24+。CI 覆盖 22.19、24 和 26;见 [Node 引擎下限 Agent Note](../.agents/notes/implemented/process/2026-07-06-node-engine-floor.md)。\n- 启用了 Corepack 的 pnpm。仓库在 `package.json` 中固定使用 `pnpm@11.7.0`;如果 `pnpm --version` 无法通过 Corepack 解析,请先运行 `corepack enable`。\n- Git 2.26 或更高版本;钩子设置会启用 Git 的 worktree 专属配置扩展。\n- 可选:一个 DeepSeek API key,用于 Web、headless 和 ACP(Agent Client Protocol)自动化 agent(智能体)演示以及真实 API 的 e2e 测试。\n\n### 首次搭建\n\n在仓库根目录安装依赖:\n\n```sh\npnpm install\n```\n\n安装过程还会通过 `scripts/install-lefthook.mjs` 配置 worktree 本地的 Lefthook 钩子和 `dsh-translation-pairing` Git 合并驱动。[worktree 本地钩子 Agent Note](../.agents/notes/implemented/process/2026-07-27-worktree-local-lefthook.md) 负责钩子路径的安全契约;[自动配对合并 Agent Note](../.agents/notes/implemented/process/2026-08-08-automatic-translation-pairing-merges.md) 负责合并驱动。\n\n如果依赖是从缓存恢复或 `postinstall` 被跳过而导致任一集成缺失,请手动安装:\n\n```sh\nnode scripts/install-lefthook.mjs\n```\n\n如果包装脚本拒绝现有 Git 配置或报告陈旧锁,请遵循其诊断和所链接的 Agent Note,不要凭猜测编辑 worktree 元数据。移动检出目录后,请重新运行包装脚本以重新生成自有路径。\n\n新克隆后请先运行一次类型检查:\n\n```sh\npnpm run typecheck\n```\n\n`pnpm run typecheck` 成功退出即表示搭建完成。\n\n## 贡献者参考\n\n### TypeScript 项目布局\n\n仓库使用相互隔离的 Host 与 Client aggregate。普通 package 只登记进其中一个 aggregate;Host 包进入 `tsconfig.host.json`,Client 包进入 `tsconfig.client.json`。\n\n| 文件 | 角色 | 是否构成 program? |\n|---|---|---|\n| `tsconfig.json` | solution 根:`extends` base、`files: []`、引用两个 aggregate。它是 tsserver 发现入口,也是显式执行整张 Project Reference 图时的入口;经继承的 `paths` 充当 tsx 运行 `examples/` 与 `scripts/` 时的解析配置。 | 否 |\n| `tsconfig.host.json` | Host aggregate:Host package、示例、测试、脚本和 website,以及 `api/remotes` 的 Host 特例 project。 | 是 |\n| `tsconfig.client.json` | Client aggregate:`packages/client/*` package 及其测试、`apps/web`,以及 `api/remotes` 的 Client 特例 project。 | 是 |\n| `tsconfig.base.json` | 共享 compilerOptions 与源码 `paths` 映射。同时是各 vitest 配置让 vite-tsconfig-paths 指向的解析门面:它没有 `include`,因此其 `paths` 适用于任何 importer。 | 否 |\n| `tsconfig.base.client.json` | 浏览器编译形状(`jsx`、DOM lib、`types: []`),由 Client aggregate 和每个 `packages/client/*` package extends。 | 否 |\n\nHost 与 Client 保持两个 aggregate program,是因为两侧在相同键下以不同服务对 cordis `Context` 接口做声明合并;单一 program 同时看到两份合并会报冲突。这种冲突只存在于 `ts.Program` 内部——模块解析永远不会触发它——所以 solution 可以同时引用两个 aggregate,一个 paths 门面也可以横跨两侧。由此推出三条纪律:\n\n- `tsconfig.base.json` 永不添加 `include` 或 `files`:它们会泄漏进每个 extends 它的包项目,并收窄门面的全匹配范围。\n- 构造全仓 `ts.Program` 的脚本显式种子 `tsconfig.host.json` 或 `tsconfig.client.json`——永不种子根 solution,因为把两个 aggregate 展平进一个 program 会撞上 `Context` 合并冲突。\n- 新 package 只登记进一个 aggregate。包同时具有 Node loader 入口和 browser 入口并不构成拆分理由;普通 Client plugin 的两份运行时产物都在 Client 构建阶段生成。\n\n`api/remotes` 是唯一拆分 Host/Client tsconfig 的仓库特例。它的 Host 入口必须进入 Host TypeRT 图,而 Client 入口导入 Host tsdown 才会生成的 `/remote` 声明,因此本包根 `tsconfig.json` 只作为 solution,两个 aggregate 和直接消费方分别引用 `tsconfig.host.json` 或 `tsconfig.client.json`。workspace `constraints` 门禁遍历可达的 Project Reference 图,并按各引用 project 自身的 compiler face 检查:只有单一配置的目标可由任一 face 引用,拆分配置的目标则必须引用匹配的 leaf,不得引用 solution 根或另一侧 leaf。不要把该结构推广到其他包;完整边界见 [`api-remotes` README](Line truncated
"content": "# 开发指南\n\n[English](development.md) | 中文\n\n搭建教程引导新贡献者从准备前置条件开始,直到检出通过检查。后面的贡献者参考介绍仓库布局、日常工作流和 CI 形态。设计依据与实现细节属于链接的 Agent Note 和脚本。\n\n## 搭建教程\n\n### 前置条件\n\n- Node.js 支持 22.19+ 与 24+。CI 覆盖 22.19、24 和 26;见 [Node 引擎下限 Agent Note](../.agents/notes/implemented/process/2026-07-06-node-engine-floor.md)。\n- 启用了 Corepack 的 pnpm。仓库在 `package.json` 中固定使用 `pnpm@11.7.0`;如果 `pnpm --version` 无法通过 Corepack 解析,请先运行 `corepack enable`。\n- Git 2.26 或更高版本;钩子设置会启用 Git 的 worktree 专属配置扩展。\n- 可选:一个 DeepSeek API key,用于 Web、headless 和 ACP(Agent Client Protocol)自动化 agent(智能体)演示以及真实 API 的 e2e 测试。\n\n### 首次搭建\n\n在仓库根目录安装依赖:\n\n```sh\npnpm install\n```\n\n安装过程还会通过 `scripts/install-lefthook.mjs` 配置 worktree 本地的 Lefthook 钩子和 `dsh-translation-pairing` Git 合并驱动。[worktree 本地钩子 Agent Note](../.agents/notes/implemented/process/2026-07-27-worktree-local-lefthook.md) 负责钩子路径的安全约定;[自动配对合并 Agent Note](../.agents/notes/implemented/process/2026-08-08-automatic-translation-pairing-merges.md) 负责合并驱动。\n\n如果依赖是从缓存恢复或 `postinstall` 被跳过而导致任一集成缺失,请手动安装:\n\n```sh\nnode scripts/install-lefthook.mjs\n```\n\n如果包装脚本拒绝现有 Git 配置或报告陈旧锁,请遵循其诊断和所链接的 Agent Note,不要凭猜测编辑 worktree 元数据。移动检出目录后,请重新运行包装脚本以重新生成自有路径。\n\n新克隆后请先运行一次类型检查:\n\n```sh\npnpm run typecheck\n```\n\n`pnpm run typecheck` 成功退出即表示搭建完成。\n\n## 贡献者参考\n\n### TypeScript 项目布局\n\n仓库使用相互隔离的 Host 与 Client aggregate。普通 package 只登记进其中一个 aggregate;Host 包进入 `tsconfig.host.json`,Client 包进入 `tsconfig.client.json`。\n\n| 文件 | 角色 | 是否构成 program? |\n|---|---|---|\n| `tsconfig.json` | solution 根:`extends` base、`files: []`、引用两个 aggregate。它是 tsserver 发现入口,也是显式执行整张 Project Reference 图时的入口;经继承的 `paths` 充当 tsx 运行 `examples/` 与 `scripts/` 时的解析配置。 | 否 |\n| `tsconfig.host.json` | Host aggregate:Host package、示例、测试、脚本和 website,以及 `api/remotes` 的 Host 特例 project。 | 是 |\n| `tsconfig.client.json` | Client aggregate:`packages/client/*` package 及其测试、`apps/web`,以及 `api/remotes` 的 Client 特例 project。 | 是 |\n| `tsconfig.base.json` | 共享 compilerOptions 与源码 `paths` 映射。同时是各 vitest 配置让 vite-tsconfig-paths 指向的解析门面:它没有 `include`,因此其 `paths` 适用于任何 importer。 | 否 |\n| `tsconfig.base.client.json` | 浏览器编译形状(`jsx`、DOM lib、`types: []`),由 Client aggregate 和每个 `packages/client/*` package extends。 | 否 |\n\nHost 与 Client 保持两个 aggregate program,是因为两侧在相同键下以不同服务对 cordis `Context` 接口做声明合并;单一 program 同时看到两份合并会报冲突。这种冲突只存在于 `ts.Program` 内部——模块解析永远不会触发它——所以 solution 可以同时引用两个 aggregate,一个 paths 门面也可以横跨两侧。由此推出三条纪律:\n\n- `tsconfig.base.json` 永不添加 `include` 或 `files`:它们会泄漏进每个 extends 它的包项目,并收窄门面的全匹配范围。\n- 构造全仓 `ts.Program` 的脚本显式种子 `tsconfig.host.json` 或 `tsconfig.client.json`——永不种子根 solution,因为把两个 aggregate 展平进一个 program 会撞上 `Context` 合并冲突。\n- 新 package 只登记进一个 aggregate。包同时具有 Node loader 入口和 browser 入口并不构成拆分理由;普通 Client plugin 的两份运行时产物都在 Client 构建阶段生成。\n\n`api/remotes` 是唯一拆分 Host/Client tsconfig 的仓库特例。它的 Host 入口必须进入 Host TypeRT 图,而 Client 入口导入 Host tsdown 才会生成的 `/remote` 声明,因此本包根 `tsconfig.json` 只作为 solution,两个 aggregate 和直接消费方分别引用 `tsconfig.host.json` 或 `tsconfig.client.json`。workspace `constraints` 门禁遍历可达的 Project Reference 图,并按各引用 project 自身的 compiler face 检查:只有单一配置的目标可由任一 face 引用,拆分配置的目标则必须引用匹配的 leaf,不得引用 solution 根或另一侧 leaf。不要把该结构推广到其他包;完整边界见 [`api-remotes` README](Line truncated
},
{
"role": "user",
@@ -28,7 +28,7 @@
},
{
"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,因此范围内的每篇文档都以英文和简体中文维护。本页定义配对契约、强制门禁、范围与排除规则;[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。`--write` 会先把这些快照存入本地 Git 对象库再写下记录,未提交的工作树内容也不例外;它还会在内容寻址的 `refs/dsh/translation-pairing/snapshots/` ref 下固定每个不同的已存 blob,使垃圾回收无法让已记录的恢复指针失效。因此记录的 hash 能还原任一侧上次确认时的确切文本,所以失去同步的配对是「按被改一侧的 diff 最小化地修补另一侧」,从不整篇重译。`pnpm run gen-translation-brief <pair>` 会以能安全对齐的最窄粒度——先是有改动的 Markdown 单元,再是标题小节,最后是整篇文档——机械地汇集这次更新的工作集:被改一侧自上次确认以来的 diff、每个改动块的三方文本、改动触及的术语表行,以及有约束力的更新规则;仅落在配对中逐字节一致的围栏代码块内的改动可以直接算出,`--apply` 则经结构签名校验后把它拼接进对侧文件([briefed-updates Agent Note](../../.agents/notes/implemented/process/2026-07-26-briefed-minimal-translation-updates.md))。两侧对齐后,`pnpm run verify-translation-pairing --write <pair>` 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,也正因如此,`--write` 要求点名你确认过的配对(`--write --all` 是显式的全语料形式)。\n\n 当两个分支都包含同一配对的有效确认时,已安装的 `dsh-translation-pairing` Git 合并驱动只会在 Git 默认文本合并能分别干净合并记录所指向的英文三方 blob 与中文三方 blob,且合并后的配对仍保留两侧的语言切换行和结构签名时,组合出一份新记录。任何无法确定的情形都保留为普通冲突;`pnpm run resolve-translation-pairing-conflicts` 会对已经停止的合并执行同一套遇错即保留冲突的操作,暂存每份可安全生成的配对记录,并在还有其他配对冲突时以非零状态退出。[自动配对合并 Agent Note](../../.agents/notes/implemented/process/2026-08-08-automatic-translation-pairing-merges.md) 负责记录该机制与备选方案。\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. 范围内的每篇文档都有完整配对。发现 README 时,basename 不区分大小写,因此 `missions/readme.md` 与其他文档根一样属于范围。\n2. 任何已存在的配对产物都完整且一致: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)、Line truncated
"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,因此范围内的每篇文档都以英文和简体中文维护。本页定义配对约定、强制门禁、范围与排除规则;[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## 配对约定\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。`--write` 会先把这些快照存入本地 Git 对象库再写下记录,未提交的工作树内容也不例外;它还会在内容寻址的 `refs/dsh/translation-pairing/snapshots/` ref 下固定每个不同的已存 blob,使垃圾回收无法让已记录的恢复指针失效。因此记录的 hash 能还原任一侧上次确认时的确切文本,所以失去同步的配对是「按被改一侧的 diff 最小化地修补另一侧」,从不整篇重译。`pnpm run gen-translation-brief <pair>` 会以能安全对齐的最窄粒度——先是有改动的 Markdown 单元,再是标题小节,最后是整篇文档——机械地汇集这次更新的工作集:被改一侧自上次确认以来的 diff、每个改动块的三方文本、改动触及的术语表行,以及有约束力的更新规则;仅落在配对中逐字节一致的围栏代码块内的改动可以直接算出,`--apply` 则经结构签名校验后把它拼接进对侧文件([briefed-updates Agent Note](../../.agents/notes/implemented/process/2026-07-26-briefed-minimal-translation-updates.md))。两侧对齐后,`pnpm run verify-translation-pairing --write <pair>` 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,也正因如此,`--write` 要求点名你确认过的配对(`--write --all` 是显式的全语料形式)。\n\n 当两个分支都包含同一配对的有效确认时,已安装的 `dsh-translation-pairing` Git 合并驱动只会在 Git 默认文本合并能分别干净合并记录所指向的英文三方 blob 与中文三方 blob,且合并后的配对仍保留两侧的语言切换行和结构签名时,组合出一份新记录。任何无法确定的情形都保留为普通冲突;`pnpm run resolve-translation-pairing-conflicts` 会对已经停止的合并执行同一套遇错即保留冲突的操作,暂存每份可安全生成的配对记录,并在还有其他配对冲突时以非零状态退出。[自动配对合并 Agent Note](../../.agents/notes/implemented/process/2026-08-08-automatic-translation-pairing-merges.md) 负责记录该机制与备选方案。\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约定:\n\n1. 范围内的每篇文档都有完整配对。发现 README 时,basename 不区分大小写,因此 `missions/readme.md` 与其他文档根一样属于范围。\n2. 任何已存在的配对产物都完整且一致: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)、Line truncated
},
{
"role": "user",
@@ -44,7 +44,7 @@
},
{
"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本仓库的文档语料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](../../archived/process/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 <pair>`,要求点名所确认的配对;批量重新记录是显式的 `--write --all`)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:每个已发现且未排除的源文档都有完整配对;每个现有配对都完整(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);被排除的生成文档、指令文档或本身即双语的文档不得配对。[scripts/translation-pairing.manifest.json](../../../../scripts/translation-pairing.manifest.json) 只包含显式排除项,因此任何要求都无法绕过发现流程而接受较弱的检查。只有当 `.zh.md` 围栏序列与其无后缀兄弟文件拥有顺序相同、正文按字节一致的同一组受跟踪围栏时,面向源码的代码门禁才会将其作为派生内容消费;不完整、顺序变更、重分类或已改动的序列仍会独立受检,因此由其所属的代码门禁或配对门禁报告不匹配。\n- **全语料统一要求。** 范围内的每篇文档从创建起就必须有完整配对;政策没有逐文件推进状态、日期分界或 README 专用类别。README 发现会覆盖 vendor 源码、依赖目录与被忽略的构建产物目录之外所有文件名不区分大小写匹配 README 的文件,包括今后新增的顶层目录。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Line truncated
"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本仓库的文档语料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](../../archived/process/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 <pair>`,要求点名所确认的配对;批量重新记录是显式的 `--write --all`)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:每个已发现且未排除的源文档都有完整配对;每个现有配对都完整(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);被排除的生成文档、指令文档或本身即双语的文档不得配对。[scripts/translation-pairing.manifest.json](../../../../scripts/translation-pairing.manifest.json) 只包含显式排除项,因此任何要求都无法绕过发现流程而接受较弱的检查。只有当 `.zh.md` 围栏序列与其无后缀兄弟文件拥有顺序相同、正文按字节一致的同一组受跟踪围栏时,面向源码的代码门禁才会将其作为派生内容消费;不完整、顺序变更、重分类或已改动的序列仍会独立受检,因此由其所属的代码门禁或配对门禁报告不匹配。\n- **全语料统一要求。** 范围内的每篇文档从创建起就必须有完整配对;政策没有逐文件推进状态、日期分界或 README 专用类别。README 发现会覆盖 vendor 源码、依赖目录与被忽略的构建产物目录之外所有文件名不区分大小写匹配 README 的文件,包括今后新增的顶层目录。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验证约定分别覆盖每个边界。`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Line truncated
},
{
"role": "user",