Merge pull request #2560 from deepseek-harness/codex/add-security-policy

docs: add bilingual experimental safety notice
This commit is contained in:
Turtle authored and GitHub committed 2026-08-23 11:10:52 +08:00
1 parent 92f8fb6c4a
commit cc8ea70dc0
15 files changed
+87 -22

No files matched your search

@@ -2,5 +2,5 @@
# side as of the last confirmed-consistent state. Both languages carry equal authority;
# after editing either side, bring the other along and re-record with:
# pnpm run verify-translation-pairing --write .agents/notes/implemented/process/2026-07-02-bilingual-docs-and-pairing-gate.md
2026-07-02-bilingual-docs-and-pairing-gate.md: 3a93b4aa68e6f6092abf42a40ec148a205a78691
2026-07-02-bilingual-docs-and-pairing-gate.zh.md: e145afe7cff8d0d0632541110d1c0f2bf70d11f2
2026-07-02-bilingual-docs-and-pairing-gate.md: 8fbda5e8987d7c575e3ef96f1724b04dd7070621
2026-07-02-bilingual-docs-and-pairing-gate.zh.md: b022abf61be733368263ff3de4176e43832b09a2
@@ -13,13 +13,13 @@ This repo's documentation corpus is read by people and agents inside and outside
- **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 <pair>`, which requires naming the confirmed pairs — bulk re-record is an explicit `--write --all`) 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: every discovered, non-excluded source has a complete pair; every existing pair is complete (all three files) and consistent (both hashes match, the Chinese side and every authored English source carry their switchers while listed generated English sources are exempt, structural signatures identical); and excluded generated, instruction, or bilingual-by-construction files stay unpaired. Relative document links whose targets belong to that active corpus use the target sibling matching the source locale, while the structure signature normalizes `.md` and `.zh.md` siblings to one semantic target and retains the exact query/fragment suffix; the [localized bilingual links decision](2026-08-18-localized-bilingual-links.md) owns that refinement. [scripts/translation-pairing.manifest.json](../../../../scripts/translation-pairing.manifest.json) contains only explicit exclusions, so no requirement can bypass discovery and receive a weaker check. Source-oriented code gates consume a `.zh.md` fence sequence as a derivative only when its unsuffixed sibling has the same tracked fences in the same order with byte-identical bodies; an incomplete, reordered, reclassified, or changed sequence stays independent, so the owning code gate or pairing gate reports the mismatch.
- **One corpus-wide requirement.** Every document in scope requires a complete pair from creation; the policy has no per-file rollout state, date cutoff, or README-specific class. README discovery covers every case-insensitive README basename outside vendored, dependency, and ignored build-output trees, including future top-level directories. 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.
- **One corpus-wide requirement.** Every document in scope requires a complete pair from creation; the policy has no per-file rollout state, date cutoff, or README-specific class. Repository-root policy documents are named explicitly: `CONTRIBUTING.md`, `BRAND_GUIDELINES.md`, and `SAFETY.md` participate in the same discovery and pairing rules even though they are outside documentation directories. README discovery covers every case-insensitive README basename outside vendored, dependency, and ignored build-output trees, including future top-level directories. 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.** Routine changes use the direct one-pass path owned by the [lightweight-translation decision](2026-08-08-lightweight-routine-documentation-translation.md). The [extended translation skill](../../../skills/dsh-translate-docs/SKILL.md) retains delegated translation and the other heavier mechanisms for explicit user invocation; both paths defer to the documentation contracts as their sources of truth.
## 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.
The verification contract covers each boundary independently. `verify-translation-pairing` pins pair completeness, hashes, switchers, and structure, while its discovery tests pin the named root policy documents and automatic README coverage; [`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
@@ -13,13 +13,13 @@ 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.zh.md);翻译规则见 [docs/i18n/translation-rules.md](../../../../docs/i18n/translation-rules.zh.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 <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。
- **`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(两侧的 hash 均与记录匹配、中文侧和所有人工撰写的英文源都带语言切换行而清单内的生成英文源除外、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。目标属于该活跃语料的相对文档链接使用与源文件 locale 相同的目标兄弟文件;结构签名则把 `.md` 与 `.zh.md` 兄弟文件规范化为同一个语义目标,并保留完全相同的 query/fragment 后缀;该细化规则由[双语文档链接本地化决策](2026-08-18-localized-bilingual-links.zh.md)负责。[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。
- **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。
- **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。仓库根目录的政策文档会被显式点名:`CONTRIBUTING.md`、`BRAND_GUIDELINES.md` 与 `SAFETY.md` 虽然不在文档目录中,仍遵循同一套发现与配对规则。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。
- **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。** 常规改动采用由[轻量翻译决策](2026-08-08-lightweight-routine-documentation-translation.zh.md)确立的直接单遍路径。[扩展翻译 skill(技能)](../../../skills/dsh-translate-docs/SKILL.md)保留委派翻译和其他较重机制,供用户显式调用;两条路径均以文档契约为真源。
## 验证
验证约定分别覆盖每个边界。`verify-translation-pairing` 固定配对完整性、hash、语言切换行和结构;[`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、源请求和所消费的响应。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。
验证约定分别覆盖每个边界。`verify-translation-pairing` 固定配对完整性、hash、语言切换行和结构,其发现测试则固定具名的根目录政策文档与自动 README 覆盖;[`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、源请求和所消费的响应。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
+2 -2
View File
@@ -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
README.md: a007b230b0f766537a04c99db920271c96600d1d
README.zh.md: 63899fd3abb2333fcce8b0975c8be7f309845b33
README.md: 9847d1fc35d5eceea484c229872dc8614ba3654a
README.zh.md: 6838b7c712e181dc44ca467225adf2aadf7ad947
+2
View File
@@ -12,6 +12,8 @@ Documentation: [https://deepseek-harness.github.io/deepseek-harness/](https://de
DeepSeek Harness is currently in _developer preview_ and is iterating rapidly. **THERE WILL BE COMPATIBILITY-BREAKING CHANGES.**
Review the [safety notice](SAFETY.md) before running the project.
## Run
### Run from `npm`
+2
View File
@@ -12,6 +12,8 @@ DeepSeek Harness(`dsh`)是由 [DeepSeek AI](https://deepseek.com) 开发的
DeepSeek Harness 目前处于 _开发者预览_ 阶段,正在快速迭代。**未来将出现破坏兼容性的变更。**
运行本项目前,请阅读[安全说明](SAFETY.zh.md)。
<a id="run"></a>
## 运行
+6
View File
@@ -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 SAFETY.md
SAFETY.md: 2b76f00e0619ee69553afdc507df361080f4d3ac
SAFETY.zh.md: 6f7dae47b3e47ddfb155adb9c8c868b516d75360
+27
View File
@@ -0,0 +1,27 @@
# Safety
English | [中文](SAFETY.zh.md)
## Experimental status
DeepSeek Harness is experimental developer-preview software. It has not undergone a security audit and must not be treated as secure or production-ready.
The project can execute model-generated code and commands, load third-party plugins, and access the network, processes, credentials, and files made available to it. Incorrect model output, defects, misconfiguration, malicious input, or untrusted plugins may damage the host computer, modify or delete files, disclose data or credentials, or cause other unintended effects.
## Sandbox limitations
Sandboxing, approval prompts, and permission controls can reduce risk, but they do not guarantee isolation or prevent damage. Even correctly enforced restrictions cannot protect resources that the project is allowed to access.
Do not rely on DeepSeek Harness as the sole security control for untrusted workloads.
## Responsible use
- Run the project with the least privileges and access required.
- Prefer a disposable virtual machine, container, or dedicated environment.
- Keep backups of files that the project can access.
- Do not expose sensitive credentials or data unless you accept the risk.
- Review plugins, configuration, and proposed commands before allowing them to run.
## No warranty or liability
Use DeepSeek Harness at your own risk. The software is provided without warranty under the [MIT License](LICENSE). To the maximum extent permitted by applicable law, the authors and copyright holders are not responsible for damage to computers, loss or disclosure of data, loss of files, or other harm arising from use of the project.
+27
View File
@@ -0,0 +1,27 @@
# 安全
[English](SAFETY.md) | 中文
## 实验性状态
DeepSeek Harness 是实验性的开发者预览软件。它尚未接受安全审计,不得视为安全或可用于生产环境的软件。
本项目可以执行模型生成的代码与命令、加载第三方插件,并访问向其开放的网络、进程、凭据和文件。错误的模型输出、缺陷、配置错误、恶意输入或不可信插件可能损坏宿主计算机、修改或删除文件、泄露数据或凭据,或造成其他非预期影响。
## 沙箱限制
沙箱、审批提示与权限控制可以降低风险,但不保证隔离,也不能保证防止损害。即使限制得到正确执行,也无法保护本项目获准访问的资源。
不要把 DeepSeek Harness 当作不可信工作负载唯一的安全控制措施。
## 负责任地使用
- 仅向本项目授予所需的最小权限和访问范围。
- 优先在一次性虚拟机、容器或专用环境中运行。
- 备份本项目可以访问的文件。
- 除非你接受相关风险,否则不要向其暴露敏感凭据或数据。
- 在允许运行前检查插件、配置和拟执行命令。
## 不提供保证,不承担责任
请在充分了解相关风险的前提下使用 DeepSeek Harness。本软件依照 [MIT License](LICENSE) 提供,不附带任何保证。在适用法律允许的最大范围内,对于使用本项目造成的计算机损坏、数据丢失或泄露、文件丢失或其他损害,作者和版权持有人不承担责任。
+2 -2
View File
@@ -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 docs/i18n/README.md
README.md: 1f0149184844e88eb79c3a7246572de78c11ca28
README.zh.md: e7fc2bce607c3b68fc54e3292ba8268c78d15aff
README.md: 71092a518db6b75c25a5c357168ab0b0437050b5
README.zh.md: 568c987b16e6c88dde16bf4c769f81be264dbbcb
+1 -1
View File
@@ -41,7 +41,7 @@ The gate's limit, stated plainly: **a green gate means the pair was confirmed co
## Scope and exclusions
**Scope**: the root CONTRIBUTING and BRAND_GUIDELINES documents, every non-vendor README, and every active document under `.agents/notes/**`, `docs/**`, and `python/**`. README matching is case-insensitive on the basename and covers future directories without another manifest edit. Dependency and ignored build-output trees and the frozen `.agents/notes/archived/` tree are discovery exclusions, not evolving translation source.
**Scope**: the root `CONTRIBUTING.md`, `BRAND_GUIDELINES.md`, and `SAFETY.md` documents, every non-vendor README, and every active document under `.agents/notes/**`, `docs/**`, and `python/**`. README matching is case-insensitive on the basename and covers future directories without another manifest edit. Dependency and ignored build-output trees and the frozen `.agents/notes/archived/` tree are discovery exclusions, not evolving translation source.
Generated English references and graphs participate in pairing when a reviewed Chinese counterpart is available. Their generators remain the English source of truth, and freshness and pairing gates enforce their respective invariants independently; regeneration that changes English leaves the pair out of sync until the reviewed Chinese counterpart is updated and re-recorded. A generator that owns both sides, such as the Cordis subsystem-region generator, projects paired document paths to each output locale while keeping every other generated byte equal. Generated English sources omit the language switcher that ordinary authored sources carry, because adding it would make the generator stale; their Chinese counterparts still link back to the English source. A generated page's Chinese counterpart may rewrite only self-referential generation and maintenance statements that would otherwise be false for the reviewed translation; all technical content remains subject to the ordinary faithfulness rules.
+1 -1
View File
@@ -43,7 +43,7 @@
## 范围与排除
**范围**:根目录 CONTRIBUTING 与 BRAND_GUIDELINES 文档、除 vendor 源码外的全部 README,以及 `.agents/notes/**`、`docs/**` 与 `python/**` 下的全部活跃文档。匹配 README 时只看文件名且不区分大小写,因此今后新增的目录无需再修改 manifest。依赖目录、被忽略的构建产物目录以及冻结的 `.agents/notes/archived/` 目录树只在发现阶段排除,不属于持续演进的翻译源文档。
**范围**:根目录 `CONTRIBUTING.md`、`BRAND_GUIDELINES.md` 与 `SAFETY.md` 文档、除 vendor 源码外的全部 README,以及 `.agents/notes/**`、`docs/**` 与 `python/**` 下的全部活跃文档。匹配 README 时只看文件名且不区分大小写,因此今后新增的目录无需再修改 manifest。依赖目录、被忽略的构建产物目录以及冻结的 `.agents/notes/archived/` 目录树只在发现阶段排除,不属于持续演进的翻译源文档。
有经评审的中文对侧的生成英文参考文档和图文档遵循配对规则。生成器仍是英文真源,新鲜度门禁与配对门禁各自独立强制其约束;重新生成导致英文变化后,配对会保持失去同步状态,直至经评审的中文对侧完成更新并重新记录。Cordis subsystem 区块生成器等同时拥有两侧输出的生成器,会把配对文档路径投影到各自 locale,同时保持其余生成字节一致。生成的英文源文件不含普通撰写文档所带的语言切换行,因为添加该行会使生成器新鲜度检查失败;中文对侧仍链接回英文源。生成页的中文对侧只能改写若直译便不再符合经评审译文事实的自指生成与维护说明;所有技术内容仍受普通忠实性规则约束。
@@ -8,11 +8,11 @@
},
{
"role": "user",
"content": "# DeepSeek Harness\n\nEnglish | [中文](README.zh.md)\n\nDeepSeek Harness (`dsh`) is an open-source agent harness developed by [DeepSeek AI](https://deepseek.com).\n\nIt uses an architecture where **everything is a plugin**, and is powered by [Cordis](https://github.com/cordiverse/cordis), whose design is described in [_A Programming Paradigm for Spatiotemporal Composability_](https://github.com/cordiverse/paper).\n\nDocumentation: [https://deepseek-harness.github.io/deepseek-harness/](https://deepseek-harness.github.io/deepseek-harness/)\n\n## Developer preview\n\nDeepSeek Harness is currently in _developer preview_ and is iterating rapidly. **THERE WILL BE COMPATIBILITY-BREAKING CHANGES.**\n\n## Run\n\n### Run from `npm`\n\nInstall `Node.js`, then run:\n\n```sh\nnpx @deepseek-ai/dsh web\n```\n\nThe command starts the Web UI at `http://127.0.0.1:3080` by default and opens it in the default browser for a local launch. An SSH launch only prints the host URL because the SSH client or editor owns the local forwarded address. Pass `--no-open` to run the server without opening a browser. See [Web UI guide](docs/user/guide/index.md).\n\n### Run from source\n\nTo run from a repository checkout:\n\n```sh\ngit clone https://github.com/deepseek-ai/deepseek-harness.git\ncd deepseek-harness\npnpm install\npnpm run build\npnpm dsh web\n```\n\n`pnpm run build` prepares the repository artifacts. `pnpm dsh web` uses those built artifacts without rebuilding.\n\n## Community and support\n\n- Feel free to submit feedback or bug reports through [GitHub Discussions](https://github.com/deepseek-ai/deepseek-harness/discussions).\n- Add the [`dsh-plugin`](https://github.com/topics/dsh-plugin) topic to your plugin repository for discoverability.\n- Join <a href=\"https://discord.gg/Ycq5dCaS4\">DeepSeek Harness Discord community</a>.\n\n## Contributing\n\nSee [CONTRIBUTING.md](CONTRIBUTING.md).\n\n## Development\n\nStart with the [development guide](docs/development.md) and [architecture documentation](docs/architecture.md).\n\nFor agents, follow [AGENTS.md](AGENTS.md).\n\n## License\n\n[MIT](LICENSE)\n\nThird-party dependencies and their licenses are disclosed in [THIRD_PARTY_NOTICES.md](THIRD_PARTY_NOTICES.md).\n"
"content": "# DeepSeek Harness\n\nEnglish | [中文](README.zh.md)\n\nDeepSeek Harness (`dsh`) is an open-source agent harness developed by [DeepSeek AI](https://deepseek.com).\n\nIt uses an architecture where **everything is a plugin**, and is powered by [Cordis](https://github.com/cordiverse/cordis), whose design is described in [_A Programming Paradigm for Spatiotemporal Composability_](https://github.com/cordiverse/paper).\n\nDocumentation: [https://deepseek-harness.github.io/deepseek-harness/](https://deepseek-harness.github.io/deepseek-harness/)\n\n## Developer preview\n\nDeepSeek Harness is currently in _developer preview_ and is iterating rapidly. **THERE WILL BE COMPATIBILITY-BREAKING CHANGES.**\n\nReview the [safety notice](SAFETY.md) before running the project.\n\n## Run\n\n### Run from `npm`\n\nInstall `Node.js`, then run:\n\n```sh\nnpx @deepseek-ai/dsh web\n```\n\nThe command starts the Web UI at `http://127.0.0.1:3080` by default and opens it in the default browser for a local launch. An SSH launch only prints the host URL because the SSH client or editor owns the local forwarded address. Pass `--no-open` to run the server without opening a browser. See [Web UI guide](docs/user/guide/index.md).\n\n### Run from source\n\nTo run from a repository checkout:\n\n```sh\ngit clone https://github.com/deepseek-ai/deepseek-harness.git\ncd deepseek-harness\npnpm install\npnpm run build\npnpm dsh web\n```\n\n`pnpm run build` prepares the repository artifacts. `pnpm dsh web` uses those built artifacts without rebuilding.\n\n## Community and support\n\n- Feel free to submit feedback or bug reports through [GitHub Discussions](https://github.com/deepseek-ai/deepseek-harness/discussions).\n- Add the [`dsh-plugin`](https://github.com/topics/dsh-plugin) topic to your plugin repository for discoverability.\n- Join <a href=\"https://discord.gg/Ycq5dCaS4\">DeepSeek Harness Discord community</a>.\n\n## Contributing\n\nSee [CONTRIBUTING.md](CONTRIBUTING.md).\n\n## Development\n\nStart with the [development guide](docs/development.md) and [architecture documentation](docs/architecture.md).\n\nFor agents, follow [AGENTS.md](AGENTS.md).\n\n## License\n\n[MIT](LICENSE)\n\nThird-party dependencies and their licenses are disclosed in [THIRD_PARTY_NOTICES.md](THIRD_PARTY_NOTICES.md).\n"
},
{
"role": "assistant",
"content": "# DeepSeek Harness\n\n[English](README.md) | 中文\n\nDeepSeek Harness(`dsh`)是由 [DeepSeek AI](https://deepseek.com) 开发的开源 agent harness(智能体框架)。\n\n它采用**一切皆插件**的架构,并由 [Cordis](https://github.com/cordiverse/cordis) 驱动,其设计参见论文 [_A Programming Paradigm for Spatiotemporal Composability_](https://github.com/cordiverse/paper)。\n\n文档:[https://deepseek-harness.github.io/deepseek-harness/](https://deepseek-harness.github.io/deepseek-harness/)\n\n## 开发者预览\n\nDeepSeek Harness 目前处于 _开发者预览_ 阶段,正在快速迭代。**未来将出现破坏兼容性的变更。**\n\n<a id=\"run\"></a>\n\n## 运行\n\n### 通过 `npm` 运行\n\n安装 `Node.js`,然后运行:\n\n```sh\nnpx @deepseek-ai/dsh web\n```\n\n该命令默认会在 `http://127.0.0.1:3080` 启动 Web UI,本机启动时还会用默认浏览器打开页面。通过 SSH 启动时只打印宿主机 URL,因为本地转发地址由 SSH 客户端或编辑器持有。传入 `--no-open` 可仅运行服务器而不打开浏览器。详见 [Web UI 指南](docs/user/guide/index.zh.md)。\n\n<a id=\"run-from-source\"></a>\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-ai/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` 会直接使用这些已构建产物,不会重新构建。\n\n## 社区与支持\n\n- 欢迎通过 [GitHub Discussions](https://github.com/deepseek-ai/deepseek-harness/discussions) 提交反馈或 bug 报告。\n- 为你的插件仓库添加 [`dsh-plugin`](https://github.com/topics/dsh-plugin) 话题,便于被发现。\n- 欢迎加入 DeepSeek Harness 企微群:扫码添加企微小助手并填写入群问卷,完成后小助手会邀请你入群。\n\n<table>\n <thead>\n <tr>\n <th align=\"center\">企微小助手</th>\n <th align=\"center\">入群问卷</th>\n <th align=\"center\">微信公众号</th>\n </tr>\n </thead>\n <tbody>\n <tr>\n <td align=\"center\"><img src=\"https://cdn.deepseek.com/harness/readme/community-wecom-assistant.png\" alt=\"DeepSeek Harness 企微小助手二维码\" width=\"180\" height=\"180\"></td>\n <td align=\"center\"><a href=\"https://trtgsjkv6r.feishu.cn/share/base/form/shrcnIt5twSVdLGD52KJBckGCgg\"><img src=\"https://cdn.deepseek.com/harness/readme/community-wecom-survey.png\" alt=\"DeepSeek Harness 入群问卷二维码\" width=\"180\" height=\"180\"></a></td>\n <td align=\"center\"><img src=\"https://cdn.deepseek.com/harness/readme/community-wechat-official-account.png\" alt=\"DeepSeek Harness 团队微信公众号二维码\" width=\"180\" height=\"180\"></td>\n </tr>\n </tbody>\n</table>\n\n## 参与贡献\n\n参见 [CONTRIBUTING.md](CONTRIBUTING.zh.md)。\n\n## 开发\n\n请先阅读[开发指南](docs/development.zh.md)与[架构文档](docs/architecture.zh.md)。\n\n面向 agent:请遵循 [AGENTS.md](AGENTS.md)。\n\n## 许可证\n\n[MIT](LICENSE)\n\n第三方依赖及其许可证见 [THIRD_PARTY_NOTICES.md](THIRD_PARTY_NOTICES.md)。\n"
"content": "# DeepSeek Harness\n\n[English](README.md) | 中文\n\nDeepSeek Harness(`dsh`)是由 [DeepSeek AI](https://deepseek.com) 开发的开源 agent harness(智能体框架)。\n\n它采用**一切皆插件**的架构,并由 [Cordis](https://github.com/cordiverse/cordis) 驱动,其设计参见论文 [_A Programming Paradigm for Spatiotemporal Composability_](https://github.com/cordiverse/paper)。\n\n文档:[https://deepseek-harness.github.io/deepseek-harness/](https://deepseek-harness.github.io/deepseek-harness/)\n\n## 开发者预览\n\nDeepSeek Harness 目前处于 _开发者预览_ 阶段,正在快速迭代。**未来将出现破坏兼容性的变更。**\n\n运行本项目前,请阅读[安全说明](SAFETY.zh.md)。\n\n<a id=\"run\"></a>\n\n## 运行\n\n### 通过 `npm` 运行\n\n安装 `Node.js`,然后运行:\n\n```sh\nnpx @deepseek-ai/dsh web\n```\n\n该命令默认会在 `http://127.0.0.1:3080` 启动 Web UI,本机启动时还会用默认浏览器打开页面。通过 SSH 启动时只打印宿主机 URL,因为本地转发地址由 SSH 客户端或编辑器持有。传入 `--no-open` 可仅运行服务器而不打开浏览器。详见 [Web UI 指南](docs/user/guide/index.zh.md)。\n\n<a id=\"run-from-source\"></a>\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-ai/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` 会直接使用这些已构建产物,不会重新构建。\n\n## 社区与支持\n\n- 欢迎通过 [GitHub Discussions](https://github.com/deepseek-ai/deepseek-harness/discussions) 提交反馈或 bug 报告。\n- 为你的插件仓库添加 [`dsh-plugin`](https://github.com/topics/dsh-plugin) 话题,便于被发现。\n- 欢迎加入 DeepSeek Harness 企微群:扫码添加企微小助手并填写入群问卷,完成后小助手会邀请你入群。\n\n<table>\n <thead>\n <tr>\n <th align=\"center\">企微小助手</th>\n <th align=\"center\">入群问卷</th>\n <th align=\"center\">微信公众号</th>\n </tr>\n </thead>\n <tbody>\n <tr>\n <td align=\"center\"><img src=\"https://cdn.deepseek.com/harness/readme/community-wecom-assistant.png\" alt=\"DeepSeek Harness 企微小助手二维码\" width=\"180\" height=\"180\"></td>\n <td align=\"center\"><a href=\"https://trtgsjkv6r.feishu.cn/share/base/form/shrcnIt5twSVdLGD52KJBckGCgg\"><img src=\"https://cdn.deepseek.com/harness/readme/community-wecom-survey.png\" alt=\"DeepSeek Harness 入群问卷二维码\" width=\"180\" height=\"180\"></a></td>\n <td align=\"center\"><img src=\"https://cdn.deepseek.com/harness/readme/community-wechat-official-account.png\" alt=\"DeepSeek Harness 团队微信公众号二维码\" width=\"180\" height=\"180\"></td>\n </tr>\n </tbody>\n</table>\n\n## 参与贡献\n\n参见 [CONTRIBUTING.md](CONTRIBUTING.zh.md)。\n\n## 开发\n\n请先阅读[开发指南](docs/development.zh.md)与[架构文档](docs/architecture.zh.md)。\n\n面向 agent:请遵循 [AGENTS.md](AGENTS.md)。\n\n## 许可证\n\n[MIT](LICENSE)\n\n第三方依赖及其许可证见 [THIRD_PARTY_NOTICES.md](THIRD_PARTY_NOTICES.md)。\n"
},
{
"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 every document in scope is maintained in English and Simplified Chinese. This page defines the pairing contract, checks, scope, and exclusions; [translation-rules.md](translation-rules.md) defines how to translate; [terminology.md](terminology.md) is the terminology source of truth. Routine agent work follows the lightweight path in [docs/AGENTS.md](../AGENTS.md); the extended [.agents/skills/dsh-translate-docs](../../.agents/skills/dsh-translate-docs/SKILL.md) workflow is available only through explicit user invocation.\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. `--write` stores those snapshots in the local Git object database before recording them, including uncommitted working-tree contents, and pins every distinct stored blob under a content-addressed `refs/dsh/translation-pairing/snapshots/` ref so garbage collection cannot invalidate a recorded recovery pointer. The recorded hashes therefore recover the exact last-confirmed text of either side, so an out-of-sync pair is updated by patching the counterpart minimally against the edited side's diff — never by re-translating whole files. Routine work makes that patch directly; when the user explicitly invokes the extended workflow, `pnpm run gen-translation-brief <pair>` can instead assemble the update at the narrowest safely aligned granularity and `--apply` can splice a code-fence-only change after structural validation ([briefed-updates Agent Note](../../.agents/notes/implemented/process/2026-07-26-briefed-minimal-translation-updates.md)). After bringing the pair back in line, `pnpm run verify-translation-pairing --write <pair>` re-records both hashes; that yaml diff is the reviewable act of confirming consistency, which is why `--write` requires naming the pairs you confirmed (`--write --all` is the explicit corpus-wide form).\n\n When two branches contain valid confirmations of the same pair, the installed `dsh-translation-pairing` Git merge driver composes a new record only if Git's default text merge succeeds for both recorded owner-blob triplets and the merged pair retains its required switchers and structural signature. The Chinese file must retain its English backlink; an authored English source must retain its Chinese link, while a listed generated English source is exempt. Any structure the driver cannot verify remains an ordinary conflict; `pnpm run resolve-translation-pairing-conflicts` applies the same fail-closed operation to a merge that has already stopped, stages every safe pairing record, and exits unsuccessfully when other pairing conflicts remain. The [automatic pairing merges Agent Note](../../.agents/notes/implemented/process/2026-08-08-automatic-translation-pairing-merges.md) owns the mechanism and alternatives.\n- **Language switcher.** The Chinese file always links back immediately after its H1 heading with `[English](foo.md) | 中文`. An authored English file reciprocates there with `English | [中文](foo.zh.md)`; a listed generated English source omits that line so it remains byte-identical to generator output. A README published outside GitHub, such as PyPI project metadata, may use the canonical `https://github.com/deepseek-ai/deepseek-harness/blob/master/<repository-path>` URL to the same counterpart so the switcher still resolves there.\n- **Structure mirrors the counterpart.** Heading depths and order, list kinds, ordered-list starts, list item counts, table row and column counts, semantic link targets with exact query/fragment suffixes, and verbatim code blocks match one to one across the pair. When a relative document link targets the active bilingual corpus, the English side uses its `.md` path and the Chinese side uses its `.zh.md` path. A missing counterpart in that corpus is a pair-cLine truncated
"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 every document in scope is maintained in English and Simplified Chinese. This page defines the pairing contract, checks, scope, and exclusions; [translation-rules.md](translation-rules.md) defines how to translate; [terminology.md](terminology.md) is the terminology source of truth. Routine agent work follows the lightweight path in [docs/AGENTS.md](../AGENTS.md); the extended [.agents/skills/dsh-translate-docs](../../.agents/skills/dsh-translate-docs/SKILL.md) workflow is available only through explicit user invocation.\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. `--write` stores those snapshots in the local Git object database before recording them, including uncommitted working-tree contents, and pins every distinct stored blob under a content-addressed `refs/dsh/translation-pairing/snapshots/` ref so garbage collection cannot invalidate a recorded recovery pointer. The recorded hashes therefore recover the exact last-confirmed text of either side, so an out-of-sync pair is updated by patching the counterpart minimally against the edited side's diff — never by re-translating whole files. Routine work makes that patch directly; when the user explicitly invokes the extended workflow, `pnpm run gen-translation-brief <pair>` can instead assemble the update at the narrowest safely aligned granularity and `--apply` can splice a code-fence-only change after structural validation ([briefed-updates Agent Note](../../.agents/notes/implemented/process/2026-07-26-briefed-minimal-translation-updates.md)). After bringing the pair back in line, `pnpm run verify-translation-pairing --write <pair>` re-records both hashes; that yaml diff is the reviewable act of confirming consistency, which is why `--write` requires naming the pairs you confirmed (`--write --all` is the explicit corpus-wide form).\n\n When two branches contain valid confirmations of the same pair, the installed `dsh-translation-pairing` Git merge driver composes a new record only if Git's default text merge succeeds for both recorded owner-blob triplets and the merged pair retains its required switchers and structural signature. The Chinese file must retain its English backlink; an authored English source must retain its Chinese link, while a listed generated English source is exempt. Any structure the driver cannot verify remains an ordinary conflict; `pnpm run resolve-translation-pairing-conflicts` applies the same fail-closed operation to a merge that has already stopped, stages every safe pairing record, and exits unsuccessfully when other pairing conflicts remain. The [automatic pairing merges Agent Note](../../.agents/notes/implemented/process/2026-08-08-automatic-translation-pairing-merges.md) owns the mechanism and alternatives.\n- **Language switcher.** The Chinese file always links back immediately after its H1 heading with `[English](foo.md) | 中文`. An authored English file reciprocates there with `English | [中文](foo.zh.md)`; a listed generated English source omits that line so it remains byte-identical to generator output. A README published outside GitHub, such as PyPI project metadata, may use the canonical `https://github.com/deepseek-ai/deepseek-harness/blob/master/<repository-path>` URL to the same counterpart so the switcher still resolves there.\n- **Structure mirrors the counterpart.** Heading depths and order, list kinds, ordered-list starts, list item counts, table row and column counts, semantic link targets with exact query/fragment suffixes, and verbatim code blocks match one to one across the pair. When a relative document link targets the active bilingual corpus, the English side uses its `.md` path and the Chinese side uses its `.zh.md` path. A missing counterpart in that corpus is a pair-cLine truncated
},
{
"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.zh.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<a id=\"the-pairing-contract\"></a>\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.zh.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.zh.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、保留原样 query/fragment 后缀的语义链接目标,以及逐字节一致的代码块在配对两侧一一对应。相对文档链接的目标属于活跃双语语料时,英文侧使用其 `.md` 路径,中文侧使用其 `.zh.md` 路径。该范围内缺少对侧属于配对完整性错误,不得回退;范围外的目标保留原路径。完整保持规则见 [translation-rules.md](translation-rules.zh.md)。既有 Markdown 门禁对 `.zh.md` 文件原样生效(`verify-md-wrap`、`verify-md-links`)。\n\n## 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.zh.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<a id=\"the-pairing-contract\"></a>\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.zh.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.zh.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、保留原样 query/fragment 后缀的语义链接目标,以及逐字节一致的代码块在配对两侧一一对应。相对文档链接的目标属于活跃双语语料时,英文侧使用其 `.md` 路径,中文侧使用其 `.zh.md` 路径。该范围内缺少对侧属于配对完整性错误,不得回退;范围外的目标保留原路径。完整保持规则见 [translation-rules.md](translation-rules.zh.md)。既有 Markdown 门禁对 `.zh.md` 文件原样生效(`verify-md-wrap`、`verify-md-links`)。\n\n## Line truncated
},
{
"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 documentation corpus is 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](../../archived/process/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 <pair>`, which requires naming the confirmed pairs — bulk re-record is an explicit `--write --all`) 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: every discovered, non-excluded source has a complete pair; every existing pair is complete (all three files) and consistent (both hashes match, the Chinese side and every authored English source carry their switchers while listed generated English sources are exempt, structural signatures identical); and excluded generated, instruction, or bilingual-by-construction files stay unpaired. Relative document links whose targets belong to that active corpus use the target sibling matching the source locale, while the structure signature normalizes `.md` and `.zh.md` siblings to one semantic target and retains the exact query/fragment suffix; the [localized bilingual links decision](2026-08-18-localized-bilingual-links.md) owns that refinement. [scripts/translation-pairing.manifest.json](../../../../scripts/translation-pairing.manifest.json) contains only explicit exclusions, so no requirement can bypass discovery and receive a weaker check. Source-oriented code gates consume a `.zh.md` fence sequence as a derivative only when its unsuffixed sibling has the same tracked fences in the same order with byte-identical bodies; an incomplete, reordered, reclassified, or changed sequence stays independent, so the owning code gate or pairing gate reports the mismatch.\n- **One corpus-wide requirement.** Every document in scope requires a complete pair from creation; the policy has no per-file rollout state, date cutoff, or README-specific class. README discovery covers every case-insensitive README basename outside vendored, dependency, and ignored build-output trees, including future top-level directories. 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.** Routine changes use the direct one-pass path owned by the [lightweight-translation decision](2026-08-08-lightweight-routine-documentation-translation.md). The [extended translation skill](../../../skills/dsh-translate-docs/SKILL.md) retains delegated translation and the other heavier mechanisms for explicit user invocation; both paths defer to the documentation contracts as their sources of truth.\n\n## Verification\n\nThe verification contract covers each boundary independently. `verify-translation-pairing` pinsLine truncated
"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 documentation corpus is 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](../../archived/process/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 <pair>`, which requires naming the confirmed pairs — bulk re-record is an explicit `--write --all`) 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: every discovered, non-excluded source has a complete pair; every existing pair is complete (all three files) and consistent (both hashes match, the Chinese side and every authored English source carry their switchers while listed generated English sources are exempt, structural signatures identical); and excluded generated, instruction, or bilingual-by-construction files stay unpaired. Relative document links whose targets belong to that active corpus use the target sibling matching the source locale, while the structure signature normalizes `.md` and `.zh.md` siblings to one semantic target and retains the exact query/fragment suffix; the [localized bilingual links decision](2026-08-18-localized-bilingual-links.md) owns that refinement. [scripts/translation-pairing.manifest.json](../../../../scripts/translation-pairing.manifest.json) contains only explicit exclusions, so no requirement can bypass discovery and receive a weaker check. Source-oriented code gates consume a `.zh.md` fence sequence as a derivative only when its unsuffixed sibling has the same tracked fences in the same order with byte-identical bodies; an incomplete, reordered, reclassified, or changed sequence stays independent, so the owning code gate or pairing gate reports the mismatch.\n- **One corpus-wide requirement.** Every document in scope requires a complete pair from creation; the policy has no per-file rollout state, date cutoff, or README-specific class. Repository-root policy documents are named explicitly: `CONTRIBUTING.md`, `BRAND_GUIDELINES.md`, and `SAFETY.md` participate in the same discovery and pairing rules even though they are outside documentation directories. README discovery covers every case-insensitive README basename outside vendored, dependency, and ignored build-output trees, including future top-level directories. 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.** Routine changes use the direct one-pass path owned by the [lightweight-translation decision](2026-08-08-lightweight-routine-documentation-translation.md). The [extended translation skill](../../../skills/dsh-translate-docs/SKILL.md) retains delegated translation and the other heavier mechanisms fLine truncated
},
{
"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,而没有门禁能够发现。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.zh.md)与 [doc-sync(文档同步门禁)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.zh.md);翻译规则见 [docs/i18n/translation-rules.md](../../../../docs/i18n/translation-rules.zh.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(两侧的 hash 均与记录匹配、中文侧和所有人工撰写的英文源都带语言切换行而清单内的生成英文源除外、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。目标属于该活跃语料的相对文档链接使用与源文件 locale 相同的目标兄弟文件;结构签名则把 `.md` 与 `.zh.md` 兄弟文件规范化为同一个语义目标,并保留完全相同的 query/fragment 后缀;该细化规则由[双语文档链接本地化决策](2026-08-18-localized-bilingual-links.zh.md)负责。[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。** 常规改动采用由[轻量翻译决策](2026-08-08-lightweight-routine-documentation-translation.zh.md)确立的直接单遍路径。[扩展翻译 skill(技能)](../../../skills/dsh-translate-docs/SKILL.md)保留委派翻译和其他较重机制,供用户显式调用;两条路径均以文档契约为真源。\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、语言切换行和结构;[`project-doc-site.spec.ts`](../../../../scripts/project-doc-site.spec.ts) 固定已发布配对按 locale 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,而没有门禁能够发现。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.zh.md)与 [doc-sync(文档同步门禁)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.zh.md);翻译规则见 [docs/i18n/translation-rules.md](../../../../docs/i18n/translation-rules.zh.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(两侧的 hash 均与记录匹配、中文侧和所有人工撰写的英文源都带语言切换行而清单内的生成英文源除外、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。目标属于该活跃语料的相对文档链接使用与源文件 locale 相同的目标兄弟文件;结构签名则把 `.md` 与 `.zh.md` 兄弟文件规范化为同一个语义目标,并保留完全相同的 query/fragment 后缀;该细化规则由[双语文档链接本地化决策](2026-08-18-localized-bilingual-links.zh.md)负责。[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。仓库根目录的政策文档会被显式点名:`CONTRIBUTING.md`、`BRAND_GUIDELINES.md` 与 `SAFETY.md` 虽然不在文档目录中,仍遵循同一套发现与配对规则。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。** 常规改动采用由[轻量翻译决策](2026-08-08-lightweight-routine-documentation-translation.zh.md)确立的直接单遍路径。[扩展翻译 skill(技能)](../../../skills/dsh-translate-docs/SKILL.md)保留委派翻译和其他较重机制,供用户显式调用;两条路径均以文档契约为真源。\n\n## 验证\n\n验证约定分别覆盖每个边界。`verify-translLine truncated
},
{
"role": "user",
+3
View File
@@ -285,6 +285,9 @@ describe('translation scope discovery', () => {
'BRAND_GUIDELINES.md',
'BRAND_GUIDELINES.zh.md',
'BRAND_GUIDELINES.i18n.yaml',
'SAFETY.md',
'SAFETY.zh.md',
'SAFETY.i18n.yaml',
'apps/cli/README.md',
'future/subtree/readme.md',
'packages/example/README.zh.md',
+2 -4
View File
@@ -130,8 +130,7 @@ export interface TranslationPairingManifest {
}
const README_ARTIFACT = /(?:^|\/)readme(?:\.md|\.zh\.md|\.i18n\.yaml)$/i
const ROOT_CONTRIBUTING_ARTIFACT = /^contributing(?:\.md|\.zh\.md|\.i18n\.yaml)$/i
const ROOT_BRAND_GUIDELINES_ARTIFACT = /^brand_guidelines(?:\.md|\.zh\.md|\.i18n\.yaml)$/i
const ROOT_PAIRED_DOCUMENT_ARTIFACT = /^(?:brand_guidelines|contributing|safety)(?:\.md|\.zh\.md|\.i18n\.yaml)$/i
const NON_SOURCE_DIRECTORIES = new Set([
'node_modules',
'lib',
@@ -186,8 +185,7 @@ function isTranslationSourceExcluded(file: string): boolean {
export function isTranslationScopeFile(file: string): boolean {
return !file.startsWith('.agents/notes/archived/')
&& !isTranslationSourceExcluded(file) && (README_ARTIFACT.test(file)
|| ROOT_CONTRIBUTING_ARTIFACT.test(file)
|| ROOT_BRAND_GUIDELINES_ARTIFACT.test(file)
|| ROOT_PAIRED_DOCUMENT_ARTIFACT.test(file)
|| file.startsWith('.agents/notes/')
|| file.startsWith('docs/')
|| file.startsWith('python/'))