test(i18n): refresh translation prompt snapshot

This commit is contained in:
xjt committed 2026-08-12 17:23:06 +08:00
1 parent 7325036d50
commit ef2b2f3178
1 file changed
+4 -6
@@ -4,7 +4,7 @@
"messages": [ "messages": [
{ {
"role": "system", "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 terms over literal renderings. Replace metaphors with direct descriptions that preserve the source meaning.\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- UseLine 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 terms over literal renderings. Replace metaphors with direct descriptions that preserve the source meaning.\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- UseLine truncated
}, },
{ {
"role": "user", "role": "user",
@@ -12,7 +12,7 @@
}, },
{ {
"role": "assistant", "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(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## 运行\n\n安装 Node.js ^22.19 或 >= 24 和 pnpm 11,然后运行已发布的包:\n\n```sh\nnpx @deepseek-ai/dsh web\n```\n\n该命令会初始化 Web profile 并打印 Web UI 地址,默认地址为 `http://127.0.0.1:3080`。打开该地址,在**设置 → 模型**中添加 DeepSeek API 密钥,然后启动一个会话。调用目录是默认工作区;你可以尝试输入 `Summarize this repository and identify its main packages.`。\n\n下一步请阅读 [Web UI 指南](docs/user/guide/index.md)。\n\n### 从源码运行\n\n如需改为运行仓库 checkout:\n\n```sh\ngit clone https://github.com/deepseek-harness/deepseek-harness.git\ncd deepseek-harness\npnpm install\npnpm run build\npnpm dsh web\n```\n\n`pnpm run build` 准备仓库产物。`pnpm dsh web` 启动 Web UI,不会重新构建,并进入相同的路径。\n\n## Profile 与插件\n\nprofile 是按顺序排列的插件 bundle 列表。随附的 `web` profile 为 `dsh web` 提供功能。使用 `dsh plugin --profile <name> <pnpm args>` 管理 profile;该命令会在对应 profile 目录中将剩余参数转发给 pnpm:\n\n```sh\nnpx -p @deepseek-ai/dsh dsh plugin --profile web add <package>\nnpx -p @deepseek-ai/dsh dsh plugin --profile web remove <package>\n```\n\n`add`、`remove`、`update`、`why` 等 pnpm 命令均可直接使用。该命令会先初始化不存在的 profile,再修改其中的包,并根据声明了 `dsh.bundle` 的已安装包更新 bundle 列表。准确行为见 [CLI 参考](apps/cli/reference/README.md#plugin-management)。\n\n[CLI(命令行界面)参考](apps/cli/README.md)介绍 headless 执行与自定义 profile。[Python SDK](python/README.md) 和[示例](examples/README.md)介绍程序化组合与自定义组合。\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\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\n## 参与贡献\n\n向本仓库贡献前,请阅读 [CONTRIBUTING.md](CONTRIBUTING.md)。\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## 内测说明\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内测版本默认上传所有会话日志,以帮助我们排查反馈的问题。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## 运行\n\n请先安装 Node.js(版本要求:`^22.19` 或 `>=24`)和 pnpm 11,然后运行已发布的包:\n\n```sh\nnpx @deepseek-ai/dsh web\n```\n\n该命令会初始化 Web profile 并打印 Web UI 地址,默认地址为 `http://127.0.0.1:3080`。打开该地址,在**设置 → 模型**中添加 DeepSeek API 密钥,然后启动一个会话。运行命令时所在的目录将作为默认工作区;你可以尝试输入 `Summarize this repository and identify its main packages.`。\n\n下一步请阅读 [Web UI 指南](docs/user/guide/index.md)。\n\n### 从源码运行\n\n如需从仓库源码运行:\n\n```sh\ngit clone https://github.com/deepseek-harness/deepseek-harness.git\ncd deepseek-harness\npnpm install\npnpm run build\npnpm dsh web\n```\n\n`pnpm run build` 会准备仓库产物。`pnpm dsh web` 不会重新构建,而是直接启动同一个 Web UI。\n\n## Profile 与插件\n\nprofile 由一组按顺序排列的插件组合包构成。随附的 `web` profile 用于运行 `dsh web`。使用 `dsh plugin --profile <name> <pnpm args>` 管理 profile;该命令会在对应 profile 目录中将剩余参数转发给 pnpm:\n\n```sh\nnpx -p @deepseek-ai/dsh dsh plugin --profile web add <package>\nnpx -p @deepseek-ai/dsh dsh plugin --profile web remove <package>\n```\n\n`add`、`remove`、`update`、`why` 等 pnpm 命令均可直接使用。该命令会先初始化不存在的 profile,再修改其中的包,并根据声明了 `dsh.bundle` 的已安装包更新 bundle 列表。具体行为见 [CLI 参考](apps/cli/reference/README.md#plugin-management)。\n\n[CLI(命令行界面)参考](apps/cli/README.md)介绍 headless 执行与自定义 profile。[Python SDK](python/README.md) 和[示例](examples/README.md)介绍程序化组合与自定义组合。\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\n## 许可证\n\n[BSD 3-Clause](LICENSE)\n\n第三方依赖及其许可证见 [THIRD_PARTY_NOTICES.md](THIRD_PARTY_NOTICES.md)。\n\n## 参与贡献\n\n向本仓库贡献前,请阅读 [CONTRIBUTING.md](CONTRIBUTING.md)。\n"
}, },
{ {
"role": "user", "role": "user",
@@ -20,8 +20,7 @@
}, },
{ {
"role": "assistant", "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 组织方式。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` | 浏览器编译设置(`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;该门禁按「两个 leaf 配置同时存在」自动发现拆分包,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,直到检出目录通过检查。后面的贡献者参考介绍仓库布局、日常工作流和 CI 组织方式。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。普通包只登记进其中一个 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 包、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/*` 包及其测试、`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` | 浏览器编译设置(`jsx`、DOM lib、`types: []`),由 Client aggregate 和每个 `packages/client/*` 包 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` 的脚本显式以 `tsconfig.host.json` 或 `tsconfig.client.json` 为种子——根 solution 永不作为种子,因为把两个 aggregate 展平进一个 program 会撞上 `Context` 合并冲突。\n- 新包只登记进一个 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 插件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;该门禁按「两个 leaf 配置同时存在」自动发现拆分包,所以Line truncated
}, },
{ {
"role": "user", "role": "user",
@@ -29,8 +28,7 @@
}, },
{ {
"role": "assistant", "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。本页定义配对约定、检查、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。agent 的日常工作遵循 [docs/AGENTS.md](../AGENTS.md) 中的轻量路径;扩展版 [.agents/skills/dsh-translate-docs](../../.agents/skills/dsh-translate-docs/SKILL.md) 工作流仅在用户显式调用时可用。\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。日常工作会直接完成这份修补;用户显式调用扩展工作流时,可改由 `pnpm run gen-translation-brief <pair>` 以能安全对齐的最窄粒度汇集这次更新,并由 `--apply` 在结构校验后拼接仅涉及围栏代码块的改动([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必需的语言切换行和结构签名时,组合出一份新记录。中文文件必须保留指向英文的反向链接;普通撰写的英文源必须保留指向中文的链接,而清单内的生成英文源不作此要求。任何合并驱动无法验证的结构都保留为普通冲突;`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。** 中文文件一律在 H1 标题后立即以 `[English](foo.md) | 中文` 链回英文。普通撰写的英文文件在同一位置以 `English | [中文](foo.zh.md)` 互链;清单内的生成英文源省略此行,以便与生成器输出逐字节一致。发布到 GitHub 以外位置的 README(例如 PyPI 项目元数据)可以改用指向同一对侧文件的规范 `https://github.com/deepseek-ai/deepseek-harness/blob/master/<repository-path>` URL,使切换行在该位置仍可访问。\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、检查、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。agent 的日常工作遵循 [docs/AGENTS.md](../AGENTS.md) 中的轻量路径;扩展版 [.agents/skills/dsh-translate-docs](../../.agents/skills/dsh-translate-docs/SKILL.md) 工作流仅在用户显式调用时可用。\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 worktree 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。日常工作会直接完成这份修补;用户显式调用扩展工作流时,可改由 `pnpm run gen-translation-brief <pair>` 以能安全对齐的最窄粒度汇集这次更新,并由 `--apply` 在结构校验后拼接仅涉及围栏代码块的改动([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必需的语言切换行和结构签名时,组合出一份新记录。中文文件必须保留指向英文的反向链接;普通撰写的英文源必须保留指向中文的链接,而清单内的生成英文源不作此要求。任何合并驱动无法验证的结构都保留为普通冲突;`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。** 中文文件一律在 H1 标题后立即以 `[English](foo.md) | 中文` 链回英文。普通撰写的英文文件在同一位置以 `English | [中文](foo.zh.md)` 互链;清单内的生成英文源省略此行,以便与生成器输出逐字节一致。发布到 GitHub 以外位置的 README(例如 PyPI 项目元数据)可以改用指向同一对侧文件的规范 `https://github.com/deepseek-ai/deepseek-harness/blob/master/<repository-path>` URL,使切换行在该位置仍可访问。\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Line truncated
}, },
{ {
"role": "user", "role": "user",