From 37bfac749b36fda839cb66f8681658d0ecc691de Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 26 Jul 2026 03:29:11 +0800 Subject: [PATCH] docs: enforce bilingual README coverage --- ...-bilingual-docs-and-pairing-gate.i18n.yaml | 4 +- ...6-07-02-bilingual-docs-and-pairing-gate.md | 4 +- ...7-02-bilingual-docs-and-pairing-gate.zh.md | 4 +- docs/i18n/README.i18n.yaml | 4 +- docs/i18n/README.md | 4 +- docs/i18n/README.zh.md | 4 +- docs/i18n/style-samples.md | 4 +- .../request-response.expected.json | 8 +-- scripts/translation-pairing.manifest.json | 3 +- scripts/translation-pairing.spec.ts | 40 +++++++++++++ scripts/translation-pairing.ts | 57 +++++++++++++++++++ scripts/verify-translation-pairing.ts | 18 +++--- 12 files changed, 126 insertions(+), 28 deletions(-) diff --git a/.agents/notes/implemented/process/2026-07-02-bilingual-docs-and-pairing-gate.i18n.yaml b/.agents/notes/implemented/process/2026-07-02-bilingual-docs-and-pairing-gate.i18n.yaml index 7b523ab8b4..bdda20cd5e 100644 --- a/.agents/notes/implemented/process/2026-07-02-bilingual-docs-and-pairing-gate.i18n.yaml +++ b/.agents/notes/implemented/process/2026-07-02-bilingual-docs-and-pairing-gate.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -2026-07-02-bilingual-docs-and-pairing-gate.md: ece3ccc183893a85335a36eb9b00cb42d32a1a37 -2026-07-02-bilingual-docs-and-pairing-gate.zh.md: dc8c648cc4ce9dd7739383c620ee2b1c3794f2ee +2026-07-02-bilingual-docs-and-pairing-gate.md: 45a587586b1387d7c351f9c268bd038fcd549ed5 +2026-07-02-bilingual-docs-and-pairing-gate.zh.md: 4875e48b43f2324ae117bb7aec1bf81dce3bc2bb diff --git a/.agents/notes/implemented/process/2026-07-02-bilingual-docs-and-pairing-gate.md b/.agents/notes/implemented/process/2026-07-02-bilingual-docs-and-pairing-gate.md index ece3ccc183..45a587586b 100644 --- a/.agents/notes/implemented/process/2026-07-02-bilingual-docs-and-pairing-gate.md +++ b/.agents/notes/implemented/process/2026-07-02-bilingual-docs-and-pairing-gate.md @@ -13,7 +13,7 @@ This repo's README and docs tree are read by people and agents inside and outsid - **Paired sibling files with equal authority.** A documentation pair is three sibling files: English `foo.md`, Chinese `foo.zh.md`, and a consistency record `foo.i18n.yaml`. Neither language is canonical — a document may be authored and reviewed Chinese-first and translated to English afterwards, or the reverse; what binds the pair is that both sides must say the same thing, and pairs merge whole (both languages plus the record, never one alone). Policy: [docs/i18n/README.md](../../../../docs/i18n/README.md); translation rules: [docs/i18n/translation-rules.md](../../../../docs/i18n/translation-rules.md); terminology source of truth: [docs/i18n/terminology.md](../../../../docs/i18n/terminology.md). - **A sidecar record of both blob hashes makes consistency checkable.** `foo.i18n.yaml` holds the full git blob hash of each side as of the last confirmed-consistent state. An edit to either side without re-confirming the pair is then mechanically detectable as a pure content comparison — no history lookup — and the hashes are computable for files edited in the same PR, which a commit-hash record is not. Re-recording (`verify-translation-pairing --write`) produces a reviewable yaml diff: confirming consistency is an explicit, visible act in the PR. - **`verify-translation-pairing` joins `doc-sync`.** The gate ([scripts/verify-translation-pairing.ts](../../../../scripts/verify-translation-pairing.ts)) enforces: sources selected explicitly, by document class, or by the manifest's `requiredSince` cutoff have complete pairs; every existing pair is complete (all three files) and consistent (both hashes match, switcher links both ways, structural signatures identical); and excluded generated, instruction, or bilingual-by-construction files stay unpaired. The `requiredClasses` set in [scripts/translation-pairing.manifest.json](../../../../scripts/translation-pairing.manifest.json) closes a translated class for all present and future files instead of relying on an enumerated snapshot. 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. -- **The enforcement frontier advances in coherent review batches, then closes by class.** Explicit `required` entries admit related files while their back-catalog is still being reviewed; after that catalog is complete, its `non-readme` or `readme` class enters `requiredClasses` and can no longer grow a backlog. 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. +- **The enforcement frontier advances in coherent review batches, then closes by class.** Explicit `required` entries admit related files while their back-catalog is still being reviewed; after that catalog is complete, its `non-readme` or `readme` class enters `requiredClasses` and can no longer grow a backlog. Both classes are closed. 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.** The committed workflow is [.agents/skills/dsh-translate-docs](../../../skills/dsh-translate-docs/SKILL.md), following the same pattern as [dsh-code-review](../../../skills/dsh-code-review/SKILL.md): the skill carries the workflow and defers to the docs as sources of truth. The skill directs the orchestrating agent to delegate translation writing to a subagent. @@ -40,5 +40,5 @@ Paired sibling files with locale suffixes are the dominant Chinese big-tech conv - Every pair adds a third file to the tree. The record is machine-written (`--write`), so the cost is directory noise, not maintenance effort; in exchange, "who confirmed these consistent, and when" is answerable from git blame on the yaml. - When the two sides disagree, no mechanical rule picks a winner — the PR review does. That is the price of equal authority, accepted deliberately: the alternative (a canonical language) forbids Chinese-first authoring. - Generated docs (`cordis-catalog/`, `tool-catalog/`, `module-graph.md`) are excluded for now; the planned follow-up is to teach their generators to emit Chinese alongside English, at which point they leave the exclusion list. -- Rollout remains incremental until a document class is complete: explicit `required` entries and the date cutoff prevent regression during review batches, while a closed class makes every current and future member mandatory. The non-README class is closed, so only the README class can still appear as backlog. +- Explicit `required` entries and the date cutoff preserve the reviewed rollout history, while the two closed classes make every current and future in-scope document mandatory. No document class can grow a new backlog. - The recorded hashes double as the update tool (`git cat-file -p ` recovers either side's last-confirmed text for a minimal diff-based update), so re-translation of whole files is never forced by the mechanism. diff --git a/.agents/notes/implemented/process/2026-07-02-bilingual-docs-and-pairing-gate.zh.md b/.agents/notes/implemented/process/2026-07-02-bilingual-docs-and-pairing-gate.zh.md index dc8c648cc4..4875e48b43 100644 --- a/.agents/notes/implemented/process/2026-07-02-bilingual-docs-and-pairing-gate.zh.md +++ b/.agents/notes/implemented/process/2026-07-02-bilingual-docs-and-pairing-gate.zh.md @@ -13,7 +13,7 @@ Status: implemented - **配对兄弟文件，两种语言同权。** 一对文档由三个兄弟文件组成：英文 `foo.md`、中文 `foo.zh.md`，以及一份一致性记录 `foo.i18n.yaml`。没有哪种语言是正典：一篇文档可以先用中文撰写和评审、之后再译成英文，反之亦可；约束配对的是：两侧必须表达相同的内容，且配对整体合并（两种语言加记录，绝不单独落一侧）。政策见 [docs/i18n/README.md](../../../../docs/i18n/README.md)；翻译规则见 [docs/i18n/translation-rules.md](../../../../docs/i18n/translation-rules.md)；术语真源见 [docs/i18n/terminology.md](../../../../docs/i18n/terminology.md)。 - **伴随记录保存两侧 blob hash，使一致性可检查。** `foo.i18n.yaml` 保存两侧文件在上一次确认一致时各自的完整 git blob hash。此后修改了任一侧而未重新确认配对，都能被机械检测出来（纯内容比较，无需查询历史），而且同一个 PR（Pull Request）内改动的文件也能计算出 hash，commit hash 式的记录做不到这一点。重新记录（`verify-translation-pairing --write`）会产生一份可评审的 yaml diff：确认一致在 PR 中是一个显式、可见的动作。 - **`verify-translation-pairing` 加入 `doc-sync`。** 门禁（[scripts/verify-translation-pairing.ts](../../../../scripts/verify-translation-pairing.ts)）强制执行以下规则：通过显式指定、文档类别或 manifest（元数据清单）的 `requiredSince` 分界日期选中的源文档必须有完整配对；任何已存在的配对必须完整（三个文件齐全）且一致（两个 hash 匹配、切换行双向互链、结构签名一致）；被排除的生成文档、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) 中的 `requiredClasses` 集合会将已完成翻译的类别纳入强制范围，对其当前及今后所有文件强制执行契约，而不再依赖一份枚举式快照。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。 -- **执行红线按连贯的评审批次推进，再以类别为单位完成强制覆盖。** 在存量文档仍处于评审阶段时，显式 `required` 条目会纳入相关文件；存量文档全部完成后，其 `non-readme` 或 `readme` 类别进入 `requiredClasses`，不再产生新的 backlog。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。 +- **执行红线按连贯的评审批次推进，再以类别为单位完成强制覆盖。** 在存量文档仍处于评审阶段时，显式 `required` 条目会纳入相关文件；存量文档全部完成后，其 `non-readme` 或 `readme` 类别进入 `requiredClasses`，不再产生新的 backlog。这两个类别均已纳入强制范围。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。** 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。 @@ -40,5 +40,5 @@ Status: implemented - 每个配对给目录树多添一个文件。记录由机器写入（`--write`），代价是目录噪音而非维护负担；换来的是「谁在何时确认过这对文档一致」可以从 yaml 的 git blame 直接回答。 - 两侧说法冲突时，没有机械规则裁决谁赢，由 PR 评审裁决。这是同权的代价，且是有意接受的：另一个选项（正典语言）会禁止中文先行撰写。 - 生成文档（`cordis-catalog/`、`tool-catalog/`、`module-graph.md`）暂被排除；计划中的后续工作是让生成器在输出英文的同时输出中文，届时将这些文件移出排除清单。 -- 在文档类别全部完成之前，推进仍然是渐进的：显式 `required` 条目与日期分界可在评审批次期间防止回退，已纳入强制范围的类别则将其当前及今后的每个成员都列为必选项。非 README 类别已纳入强制范围，因此只有 README 类别仍可能出现 backlog（待翻清单）。 +- 显式 `required` 条目与日期分界保留已经评审的推进历史，而两个已纳入强制范围的类别会将当前及今后所有范围内的文档列为必选项。任何文档类别都不能新增 backlog（待翻清单）。 - 记录的 hash 兼作更新工具（`git cat-file -p ` 能还原任一侧上次确认的文本，用于基于 diff 的最小更新），因此这套机制从不强迫整篇重译。 diff --git a/docs/i18n/README.i18n.yaml b/docs/i18n/README.i18n.yaml index b0d5a550df..51e3ffbca8 100644 --- a/docs/i18n/README.i18n.yaml +++ b/docs/i18n/README.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -README.md: 053453bc622f58083a5e0e2992f1b8a820e3f3f9 -README.zh.md: 7f6242e8ff2a3ec69e2b84402dab447297047991 +README.md: 25c4698b2efacbb0cb1dd5b8f27ad94be051c558 +README.zh.md: e5faefff97d4ef8de9bf05613f257ede06c5e4a7 diff --git a/docs/i18n/README.md b/docs/i18n/README.md index 053453bc62..25c4698b2e 100644 --- a/docs/i18n/README.md +++ b/docs/i18n/README.md @@ -38,7 +38,7 @@ The gate's limit, stated plainly: **a green gate means the pair was confirmed co ## Scope, exclusions, and rollout -**Scope**: the root `README.md`, everything under `.agents/notes/**`, `docs/**`, and `python/**`. Package READMEs (`packages/**`) join the scope in a later batch. +**Scope**: every non-vendor README, plus every 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 are discovery exclusions, not source documentation. **Excluded** (never paired, and the gate rejects a `.zh.md` or `.i18n.yaml` for them): @@ -47,7 +47,7 @@ The gate's limit, stated plainly: **a green gate means the pair was confirmed co - `docs/i18n/terminology.md` and [style-samples.md](style-samples.md) — both are bilingual by construction. - [translation-prompt.md](translation-prompt.md) — the automated pipeline's prompt template; its body is machine-consumed verbatim, so a paired translation would change pipeline behavior. -**Enforcement frontier**: `requiredClasses` closes a whole document class after its back-catalog has been translated. `non-readme` is closed: every current or future in-scope non-README document must merge bilingual. README coverage remains an explicit-file rollout until `readme` joins the closed set. The manifest's `required` list retains already-admitted files, and a date-named document (`yyyy-mm-dd-*.md`, i.e. an Agent Note) dated on or after `requiredSince` must merge with its pair regardless of class. `--list` reports any unclosed-class backlog while every existing pair remains governed by the full contract. +**Enforcement frontier**: `requiredClasses` closes a whole document class after its back-catalog has been translated. Both `non-readme` and `readme` are closed: every current or future in-scope document must merge bilingual. The manifest's `required` list retains already-admitted files, and a date-named document (`yyyy-mm-dd-*.md`, i.e. an Agent Note) dated on or after `requiredSince` must merge with its pair regardless of class. `--list` reports any unclosed-class backlog while every existing pair remains governed by the full contract. ## Division of labor diff --git a/docs/i18n/README.zh.md b/docs/i18n/README.zh.md index 7f6242e8ff..e5faefff97 100644 --- a/docs/i18n/README.zh.md +++ b/docs/i18n/README.zh.md @@ -38,7 +38,7 @@ ## 范围、排除与推进 -**范围**：根 `README.md`，以及 `.agents/notes/**`、`docs/**` 与 `python/**` 下的全部内容。包（package）README（`packages/**`）在后续批次加入范围。 +**范围**：除 vendor 源码外的全部 README，以及 `.agents/notes/**`、`docs/**` 与 `python/**` 下的全部文档。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。依赖目录和被忽略的构建产物目录只在发现阶段排除，并非源文档。 **排除**（永不配对，门禁拒绝为它们建 `.zh.md` 或 `.i18n.yaml`）： @@ -47,7 +47,7 @@ - `docs/i18n/terminology.md` 与 [style-samples.md](style-samples.md)：二者本身即为中英对照文档。 - [translation-prompt.md](translation-prompt.md)：自动翻译流水线的提示词模板；正文逐字进入模型请求，配对翻译会改变流水线行为。 -**执行红线**：某个文档类别的存量文档全部翻译完成后，`requiredClasses` 会将整个类别纳入强制范围。`non-readme` 已纳入强制范围：当前及今后所有纳入范围的非 README 文档，合并时都必须配齐双语文件。README 覆盖仍按显式文件逐步推进，直到 `readme` 加入这一强制范围。manifest 的 `required` 列表保留已纳入的文件；以日期命名的文档（`yyyy-mm-dd-*.md`，即 Agent Note）只要日期不早于 `requiredSince`，就无论所属类别都必须与对侧文件一同合并。`--list` 会报告尚未纳入强制范围的类别中的任何 backlog（待翻清单），而每个已存在的配对仍受完整契约约束。 +**执行红线**：某个文档类别的存量文档全部翻译完成后，`requiredClasses` 会将整个类别纳入强制范围。`non-readme` 与 `readme` 均已纳入强制范围：当前及今后所有纳入范围的文档，合并时都必须配齐双语文件。manifest 的 `required` 列表保留已纳入的文件；以日期命名的文档（`yyyy-mm-dd-*.md`，即 Agent Note）只要日期不早于 `requiredSince`，就无论所属类别都必须与对侧文件一同合并。`--list` 会报告尚未纳入强制范围的类别中的任何 backlog（待翻清单），而每个已存在的配对仍受完整契约约束。 ## 分工 diff --git a/docs/i18n/style-samples.md b/docs/i18n/style-samples.md index c62ae259d0..53d8851325 100644 --- a/docs/i18n/style-samples.md +++ b/docs/i18n/style-samples.md @@ -70,9 +70,9 @@ ## ⑦ 推进策略（长段拆分示范） -> **Enforcement frontier**: a document class enters the manifest's `requiredClasses` set only after its back-catalog has been translated and reviewed. The `non-readme` class is closed, so every current or future in-scope non-README document must merge bilingual; README coverage remains an explicit-file rollout until that class is ready to close. […] Pairing a document is a commitment: every later edit to either side must carry the counterpart along, so close a class only when translation review can sustain it. +> **Enforcement frontier**: a document class enters the manifest's `requiredClasses` set only after its back-catalog has been translated and reviewed. The `non-readme` and `readme` classes are closed, so every current or future in-scope document must merge bilingual. […] Pairing a document is a commitment: every later edit to either side must carry the counterpart along, so close a class only when translation review can sustain it. -**执行红线**：只有在某个文档类别的存量文档全部完成翻译和评审后，该类别才会进入 manifest（元数据清单）的 `requiredClasses` 集合。`non-readme` 类别已纳入强制范围，因此当前及今后所有纳入范围的非 README 文档，合入时都必须配齐双语文件；README 覆盖仍按显式文件逐步推进，直到该类别具备整体纳入强制范围的条件。（……）一旦文档完成配对，后续修改任一侧都必须同步更新另一侧。因此，只有在翻译评审能力足以持续支撑时，才应将整个类别纳入强制范围。 +**执行红线**：只有在某个文档类别的存量文档全部完成翻译和评审后，该类别才会进入 manifest（元数据清单）的 `requiredClasses` 集合。`non-readme` 与 `readme` 类别均已纳入强制范围，因此当前及今后所有纳入范围的文档，合入时都必须配齐双语文件。（……）一旦文档完成配对，后续修改任一侧都必须同步更新另一侧。因此，只有在翻译评审能力足以持续支撑时，才应将整个类别纳入强制范围。 ## 从样例提炼的要点 diff --git a/scripts/snapshots/translation-prompt-v4/request-response.expected.json b/scripts/snapshots/translation-prompt-v4/request-response.expected.json index 36a701f376..2314b67221 100644 --- a/scripts/snapshots/translation-prompt-v4/request-response.expected.json +++ b/scripts/snapshots/translation-prompt-v4/request-response.expected.json @@ -24,11 +24,11 @@ }, { "role": "user", - "content": "# Bilingual documentation\n\nEnglish | [中文](README.zh.md)\n\nThis repo's documentation is read by people and agents both inside and outside the company, so the README, Agent Notes, and docs tree are maintained in English and Simplified Chinese. This page defines the pairing contract, the enforcement gate, and the rollout policy; [translation-rules.md](translation-rules.md) defines how to translate; [terminology.md](terminology.md) is the terminology source of truth. The committed agent workflow lives in [.agents/skills/dsh-translate-docs](../../.agents/skills/dsh-translate-docs/SKILL.md).\n\n## The pairing contract\n\n- **Both languages carry equal authority.** A document may be authored and reviewed in either language first — a Chinese-first Agent Note is as legitimate as an English-first one — and the counterpart is translated from it. Neither file outranks the other; what binds them is that they must say the same thing.\n- **A pair is three sibling files.** The English `foo.md`, the Chinese `foo.zh.md`, and a consistency record `foo.i18n.yaml`, all in the same directory. No locale directories, no separate translation repo, no interleaved bilingual files. Pairs merge whole: a PR never lands one language without the other two files.\n- **The consistency record.** `foo.i18n.yaml` holds the full git blob hash of each side as of the last time the two were confirmed to say the same thing:\n\n ```yaml\n foo.md: 3f786850e387550fdab836ed7e6dc881de23001b\n foo.zh.md: 89e6c98d92887913cadf06b2adb97f26cde4849b\n ```\n\n Blob hashes, not commit hashes, so the record is computable for files edited in the same PR (`git hash-object foo.md`) and consistency is a pure content comparison. The recorded hash also recovers the exact last-confirmed text of either side (`git cat-file -p `), so an out-of-sync pair is updated by diffing the edited side against its last-confirmed state and patching the counterpart minimally — never by re-translating whole files. After bringing the pair back in line, `pnpm run verify-translation-pairing --write` re-records both hashes; that yaml diff is the reviewable act of confirming consistency.\n- **Language switcher.** Both files link to each other immediately after their H1 heading: the English file carries `English | [中文](foo.zh.md)` and the Chinese file carries `[English](foo.md) | 中文`.\n- **Structure mirrors the counterpart.** Heading depths and order, list kinds, ordered-list starts, list item counts, table row and column counts, link targets, and verbatim code blocks match one to one across the pair — see [translation-rules.md](translation-rules.md) for the full preservation rules. Existing Markdown gates apply to `.zh.md` files unchanged (`verify-md-wrap`, `verify-md-links`).\n\n## The gate: verify-translation-pairing\n\n`pnpm run verify-translation-pairing` (part of `doc-sync`, which contributors run locally for documentation changes and CI runs exhaustively) enforces the contract mechanically:\n\n1. Every file listed as `required`, and every document whose class appears in `requiredClasses`, in [scripts/translation-pairing.manifest.json](../../scripts/translation-pairing.manifest.json) has a complete pair. The classes are `non-readme` and `readme`; class matching is case-insensitive on the basename, so `missions/readme.md` is a README.\n2. Every pair that exists at all — required or not — is complete and consistent: all three files present, each side's current blob hash equals the recorded one (editing either side without re-confirming the pair goes red), both sides carry the language switcher, and the structural signatures match in order — heading depths, verbatim code blocks (info string and content), table row and column counts, list kinds, ordered-list starts, item counts, and every link target apart from the switcher.\n3. Files listed as `excluded` have no `.zh.md` and no `.i18n.yaml` at all.\n4. Every date-named document (`yyyy-mm-dd-*.md`) dated on or after the manifest's `requiredSince` cutoff has a complete pair — new date-named Agent Notes merge bilingual from birth.\n\nSource-oriented code gates consume an exact `.zh.md` fence sequence as a derivative of its unsuffixed sibling instead of compiling or manifesting the same code twice. The sequence must match in length, order, fence kind, and byte-exact body; otherwise both copies remain independently checked and the pairing gate reports the structural mismatch.\n\n`pnpm run verify-translation-pairing --list` prints the current pairing state of every document in scope — missing, out-of-sync, or ok — and is the work list for translation batches. It never fails; it reports.\n\nThe practical rule this gate creates: **when a PR edits either side of a paired document, the same PR updates the counterpart and re-records the pair** (run the [dsh-translate-docs](../../.agents/skills/dsh-translate-docs/SKILL.md) skill, then `--write`), exactly like the repo's existing doc-sync rule for code and READMEs. A PR that leaves a pair out of sync goes red in CI.\n\nThe gate's limit, stated plainly: **a green gate means the pair was confirmed consistent at these exact contents, not that the confirmation was sound.** It checks hashes and shape; it cannot judge whether the two sides actually say the same thing, or whether the wording is accurate, well-termed, and natural — that is the reviewer's half of the contract, per [translation-rules.md](translation-rules.md). A re-recorded pair with a sloppy counterpart passes the gate; it must not pass review.\n\n## Scope, exclusions, and rollout\n\n**Scope**: the root `README.md`, everything under `.agents/notes/**`, `docs/**`, and `python/**`. Package READMEs (`packages/**`) join the scope in a later batch.\n\n**Excluded** (never paired, and the gate rejects a `.zh.md` or `.i18n.yaml` for them):\n\n- `docs/cordis-catalog/`, `docs/tool-catalog/`, `docs/config-catalog.md`, `docs/persistence-catalog.md`, `docs/module-graph.md`, `docs/agent-lifecycle.md`, `docs/capability-seams.md`, `docs/event-producer-consumer.md`, `docs/graph-atlas.md`, and `docs/tool-execution-pipeline.md` — generated files; their generators emit English only today, so a hand-written translation would go stale on every regeneration. The planned follow-up is to teach the generators to emit Chinese alongside English, at which point these leave the exclusion list.\n- `docs/AGENTS.md`, `.agents/notes/**/AGENTS.md`, and their `CLAUDE.md` instruction symlinks — agent instructions, maintained in English only like the root `AGENTS.md`.\n- `docs/i18n/terminology.md` and [style-samples.md](style-samples.md) — both are bilingual by construction.\n- [translation-prompt.md](translation-prompt.md) — the automated pipeline's prompt template; its body is machine-consumed verbatim, so a paired translation would change pipeline behavior.\n\n**Enforcement frontier**: `requiredClasses` closes a whole document class after its back-catalog has been translated. `non-readme` is closed: every current or future in-scope non-README document must merge bilingual. README coverage remains an explicit-file rollout until `readme` joins the closed set. The manifest's `required` list retains already-admitted files, and a date-named document (`yyyy-mm-dd-*.md`, i.e. an Agent Note) dated on or after `requiredSince` must merge with its pair regardless of class. `--list` reports any unclosed-class backlog while every existing pair remains governed by the full contract.\n\n## Division of labor\n\nCounterparts here are produced by an agent running [dsh-translate-docs](../../.agents/skills/dsh-translate-docs/SKILL.md) and reviewed by a human — inference is cheap here, review attention is the scarce resource. The gate checks pair completeness, recorded hashes, switchers, and its documented structural signature. Review still owns translation quality, terminology, and structural requirements that the signature does not encode. The prompt contract is executable: [scripts/translation-prompt.ts](../../scripts/translation-prompt.ts) renders the committed template (terminology injected; the template carries its own calibrated rules) into either direction and parses the three-section response, while `verify-translation-prompt` exercises both render directions and the checked-in example in `doc-sync`.\n" + "content": "# Bilingual documentation\n\nEnglish | [中文](README.zh.md)\n\nThis repo's documentation is read by people and agents both inside and outside the company, so the README, Agent Notes, and docs tree are maintained in English and Simplified Chinese. This page defines the pairing contract, the enforcement gate, and the rollout policy; [translation-rules.md](translation-rules.md) defines how to translate; [terminology.md](terminology.md) is the terminology source of truth. The committed agent workflow lives in [.agents/skills/dsh-translate-docs](../../.agents/skills/dsh-translate-docs/SKILL.md).\n\n## The pairing contract\n\n- **Both languages carry equal authority.** A document may be authored and reviewed in either language first — a Chinese-first Agent Note is as legitimate as an English-first one — and the counterpart is translated from it. Neither file outranks the other; what binds them is that they must say the same thing.\n- **A pair is three sibling files.** The English `foo.md`, the Chinese `foo.zh.md`, and a consistency record `foo.i18n.yaml`, all in the same directory. No locale directories, no separate translation repo, no interleaved bilingual files. Pairs merge whole: a PR never lands one language without the other two files.\n- **The consistency record.** `foo.i18n.yaml` holds the full git blob hash of each side as of the last time the two were confirmed to say the same thing:\n\n ```yaml\n foo.md: 3f786850e387550fdab836ed7e6dc881de23001b\n foo.zh.md: 89e6c98d92887913cadf06b2adb97f26cde4849b\n ```\n\n Blob hashes, not commit hashes, so the record is computable for files edited in the same PR (`git hash-object foo.md`) and consistency is a pure content comparison. The recorded hash also recovers the exact last-confirmed text of either side (`git cat-file -p `), so an out-of-sync pair is updated by diffing the edited side against its last-confirmed state and patching the counterpart minimally — never by re-translating whole files. After bringing the pair back in line, `pnpm run verify-translation-pairing --write` re-records both hashes; that yaml diff is the reviewable act of confirming consistency.\n- **Language switcher.** Both files link to each other immediately after their H1 heading: the English file carries `English | [中文](foo.zh.md)` and the Chinese file carries `[English](foo.md) | 中文`.\n- **Structure mirrors the counterpart.** Heading depths and order, list kinds, ordered-list starts, list item counts, table row and column counts, link targets, and verbatim code blocks match one to one across the pair — see [translation-rules.md](translation-rules.md) for the full preservation rules. Existing Markdown gates apply to `.zh.md` files unchanged (`verify-md-wrap`, `verify-md-links`).\n\n## The gate: verify-translation-pairing\n\n`pnpm run verify-translation-pairing` (part of `doc-sync`, which contributors run locally for documentation changes and CI runs exhaustively) enforces the contract mechanically:\n\n1. Every file listed as `required`, and every document whose class appears in `requiredClasses`, in [scripts/translation-pairing.manifest.json](../../scripts/translation-pairing.manifest.json) has a complete pair. The classes are `non-readme` and `readme`; class matching is case-insensitive on the basename, so `missions/readme.md` is a README.\n2. Every pair that exists at all — required or not — is complete and consistent: all three files present, each side's current blob hash equals the recorded one (editing either side without re-confirming the pair goes red), both sides carry the language switcher, and the structural signatures match in order — heading depths, verbatim code blocks (info string and content), table row and column counts, list kinds, ordered-list starts, item counts, and every link target apart from the switcher.\n3. Files listed as `excluded` have no `.zh.md` and no `.i18n.yaml` at all.\n4. Every date-named document (`yyyy-mm-dd-*.md`) dated on or after the manifest's `requiredSince` cutoff has a complete pair — new date-named Agent Notes merge bilingual from birth.\n\nSource-oriented code gates consume an exact `.zh.md` fence sequence as a derivative of its unsuffixed sibling instead of compiling or manifesting the same code twice. The sequence must match in length, order, fence kind, and byte-exact body; otherwise both copies remain independently checked and the pairing gate reports the structural mismatch.\n\n`pnpm run verify-translation-pairing --list` prints the current pairing state of every document in scope — missing, out-of-sync, or ok — and is the work list for translation batches. It never fails; it reports.\n\nThe practical rule this gate creates: **when a PR edits either side of a paired document, the same PR updates the counterpart and re-records the pair** (run the [dsh-translate-docs](../../.agents/skills/dsh-translate-docs/SKILL.md) skill, then `--write`), exactly like the repo's existing doc-sync rule for code and READMEs. A PR that leaves a pair out of sync goes red in CI.\n\nThe gate's limit, stated plainly: **a green gate means the pair was confirmed consistent at these exact contents, not that the confirmation was sound.** It checks hashes and shape; it cannot judge whether the two sides actually say the same thing, or whether the wording is accurate, well-termed, and natural — that is the reviewer's half of the contract, per [translation-rules.md](translation-rules.md). A re-recorded pair with a sloppy counterpart passes the gate; it must not pass review.\n\n## Scope, exclusions, and rollout\n\n**Scope**: every non-vendor README, plus every 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 are discovery exclusions, not source documentation.\n\n**Excluded** (never paired, and the gate rejects a `.zh.md` or `.i18n.yaml` for them):\n\n- `docs/cordis-catalog/`, `docs/tool-catalog/`, `docs/config-catalog.md`, `docs/persistence-catalog.md`, `docs/module-graph.md`, `docs/agent-lifecycle.md`, `docs/capability-seams.md`, `docs/event-producer-consumer.md`, `docs/graph-atlas.md`, and `docs/tool-execution-pipeline.md` — generated files; their generators emit English only today, so a hand-written translation would go stale on every regeneration. The planned follow-up is to teach the generators to emit Chinese alongside English, at which point these leave the exclusion list.\n- `docs/AGENTS.md`, `.agents/notes/**/AGENTS.md`, and their `CLAUDE.md` instruction symlinks — agent instructions, maintained in English only like the root `AGENTS.md`.\n- `docs/i18n/terminology.md` and [style-samples.md](style-samples.md) — both are bilingual by construction.\n- [translation-prompt.md](translation-prompt.md) — the automated pipeline's prompt template; its body is machine-consumed verbatim, so a paired translation would change pipeline behavior.\n\n**Enforcement frontier**: `requiredClasses` closes a whole document class after its back-catalog has been translated. Both `non-readme` and `readme` are closed: every current or future in-scope document must merge bilingual. The manifest's `required` list retains already-admitted files, and a date-named document (`yyyy-mm-dd-*.md`, i.e. an Agent Note) dated on or after `requiredSince` must merge with its pair regardless of class. `--list` reports any unclosed-class backlog while every existing pair remains governed by the full contract.\n\n## Division of labor\n\nCounterparts here are produced by an agent running [dsh-translate-docs](../../.agents/skills/dsh-translate-docs/SKILL.md) and reviewed by a human — inference is cheap here, review attention is the scarce resource. The gate checks pair completeness, recorded hashes, switchers, and its documented structural signature. Review still owns translation quality, terminology, and structural requirements that the signature does not encode. The prompt contract is executable: [scripts/translation-prompt.ts](../../scripts/translation-prompt.ts) renders the committed template (terminology injected; the template carries its own calibrated rules) into either direction and parses the three-section response, while `verify-translation-prompt` exercises both render directions and the checked-in example in `doc-sync`.\n" }, { "role": "assistant", - "content": "# 双语文档\n\n[English](README.md) | 中文\n\n本仓库的文档会被公司内外的人和 agent（智能体）阅读，因此 README、Agent Note（agent 决策记录）与 docs 目录树以英文和简体中文双语维护。本页定义配对契约、强制门禁与推进策略；[translation-rules.md](translation-rules.md) 定义如何翻译；[terminology.md](terminology.md) 是术语真源。仓库内置的 agent 工作流见 [.agents/skills/dsh-translate-docs](../../.agents/skills/dsh-translate-docs/SKILL.md)。\n\n## 配对契约\n\n- **两种语言同权。** 一篇文档可以先用任一语言撰写和评审（先写中文的 Agent Note 与先写英文的一样正当），另一侧由它翻译而来。两个文件谁也不高于谁；约束它们的是二者必须说同样的话。\n- **一对文档是三个同目录文件。** 英文 `foo.md`、中文 `foo.zh.md`，加一份一致性记录 `foo.i18n.yaml`，都在同一目录。不用语言目录，不用独立翻译仓库，不用中英混排的单文件。配对必须整体合并：PR（Pull Request）永远不会只带一种语言而缺其余两个文件。\n- **一致性记录。**`foo.i18n.yaml` 保存两侧文件在上一次被确认「说同样的话」时各自的完整 git blob hash：\n\n ```yaml\n foo.md: 3f786850e387550fdab836ed7e6dc881de23001b\n foo.zh.md: 89e6c98d92887913cadf06b2adb97f26cde4849b\n ```\n\n 用 blob hash 而不是 commit hash，这样同一个 PR 里改动的文件也能算出记录（`git hash-object foo.md`），一致性是纯内容比较。记录的 hash 还能还原任一侧上次确认时的确切文本（`git cat-file -p `），所以失去同步的配对是「把被改的一侧与其上次确认状态做 diff、再最小化地修补另一侧」，从不整篇重译。两侧对齐后，`pnpm run verify-translation-pairing --write` 重新记录两个 hash；那份 yaml diff 就是「确认一致」这个动作本身，可以被评审。\n- **语言切换行。** 两个文件在各自 H1 标题之后立即互链：英文文件带 `English | [中文](foo.zh.md)`，中文文件带 `[English](foo.md) | 中文`。\n- **结构与另一侧一一对应。** 标题深度与顺序、列表类型、有序列表起始编号、列表项数量、表格行列数、链接目标与逐字节一致的代码块在配对两侧一一对应；完整保持规则见 [translation-rules.md](translation-rules.md)。既有 Markdown 门禁对 `.zh.md` 文件原样生效（`verify-md-wrap`、`verify-md-links`）。\n\n## 门禁：verify-translation-pairing\n\n`pnpm run verify-translation-pairing`（`doc-sync`（文档同步门禁）的一环，贡献者会针对文档变更在本地运行，CI 则会完整运行）机械地强制执行这份契约：\n\n1. [scripts/translation-pairing.manifest.json](../../scripts/translation-pairing.manifest.json) 中 `required` 列出的每个文件，以及所属文档类别出现在 `requiredClasses` 中的每篇文档，都有完整配对。类别分为 `non-readme` 和 `readme`；判断类别时，basename 不区分大小写，因此 `missions/readme.md` 也属于 README。\n2. 任何已存在的配对（无论是否 required）都完整且一致：三个文件齐全、每一侧的当前 blob hash 等于记录值（改了任一侧而没重新确认配对就变红）、双方都带语言切换行、结构签名按序一致：标题深度、逐字节一致的代码块（信息字符串与内容）、表格行列数、列表类型、有序列表起始编号、列表项数量，以及除切换行之外的每个链接目标。\n3. 列为 `excluded` 的文件完全没有 `.zh.md`，也没有 `.i18n.yaml`。\n4. 凡文件名符合 `yyyy-mm-dd-*.md` 且日期不早于 manifest（元数据清单）中 `requiredSince` 分界日期的文档，都必须有完整配对；新建的日期命名 Agent Note 从创建起便须配齐中英文。\n\n面向源码的代码门禁会把精确的 `.zh.md` 围栏序列视为其无后缀兄弟文件的派生内容，而不会再次编译相同代码或在 manifest 中重复登记。该序列必须在长度、顺序、围栏类型和按字节精确的正文上一致；否则两份副本仍会独立受检，配对门禁也会报告结构不匹配。\n\n`pnpm run verify-translation-pairing --list` 打印范围内每篇文档的当前配对状态（missing、out-of-sync 或 ok），是翻译批次的工作清单。它从不失败；它只报告。\n\n这个门禁带来的实际规则是：**当一个 PR 修改了已配对文档的任一侧时，同一个 PR 更新另一侧并重新记录配对**（运行 [dsh-translate-docs](../../.agents/skills/dsh-translate-docs/SKILL.md) skill（技能），再 `--write`），与本仓库既有的代码与 README 的 doc-sync 规则完全一致。留下失去同步的配对的 PR 会在 CI 变红。\n\n把门禁的边界说白：**门禁通过意味着这组文档在当前内容上的一致性得到了确认，不代表确认本身正确可靠。** 它检查记录的 hash 与结构签名；它无法判断两侧是否真的在说同样的话，也无法判断措辞是否准确、术语是否得当、行文是否自然；这部分契约由评审者把关，见 [translation-rules.md](translation-rules.md)。重新记录了 hash 但另一侧翻得潦草的配对能通过门禁；它不得通过评审。\n\n## 范围、排除与推进\n\n**范围**：根 `README.md`，以及 `.agents/notes/**`、`docs/**` 与 `python/**` 下的全部内容。包（package）README（`packages/**`）在后续批次加入范围。\n\n**排除**（永不配对，门禁拒绝为它们建 `.zh.md` 或 `.i18n.yaml`）：\n\n- `docs/cordis-catalog/`、`docs/tool-catalog/`、`docs/config-catalog.md`、`docs/persistence-catalog.md`、`docs/module-graph.md`、`docs/agent-lifecycle.md`、`docs/capability-seams.md`、`docs/event-producer-consumer.md`、`docs/graph-atlas.md` 与 `docs/tool-execution-pipeline.md`：生成文件；生成器目前只输出英文，手写译文在每次重新生成时必然陈旧。计划中的后续工作是让生成器同时输出中文，届时这些文件移出排除清单。\n- `docs/AGENTS.md`、`.agents/notes/**/AGENTS.md` 以及指向它们的 `CLAUDE.md` 指令符号链接：agent 指令，与根 `AGENTS.md` 一样只以英文维护。\n- `docs/i18n/terminology.md` 与 [style-samples.md](style-samples.md)：二者本身即为中英对照文档。\n- [translation-prompt.md](translation-prompt.md)：自动翻译流水线的提示词模板；正文逐字进入模型请求，配对翻译会改变流水线行为。\n\n**执行红线**：某个文档类别的存量文档全部翻译完成后，`requiredClasses` 会将整个类别纳入强制范围。`non-readme` 已纳入强制范围：当前及今后所有纳入范围的非 README 文档，合并时都必须配齐双语文件。README 覆盖仍按显式文件逐步推进，直到 `readme` 加入这一强制范围。manifest 的 `required` 列表保留已纳入的文件；以日期命名的文档（`yyyy-mm-dd-*.md`，即 Agent Note）只要日期不早于 `requiredSince`，就无论所属类别都必须与对侧文件一同合并。`--list` 会报告尚未纳入强制范围的类别中的任何 backlog（待翻清单），而每个已存在的配对仍受完整契约约束。\n\n## 分工\n\n这里的对侧文件由运行 [dsh-translate-docs](../../.agents/skills/dsh-translate-docs/SKILL.md) 的 agent 生成，再由人评审：在这里推理（inference）很便宜，评审注意力才是稀缺资源。门禁负责检查配对是否完整、记录的 hash、语言切换行以及本文列出的结构签名；翻译质量、术语和签名未涵盖的结构要求仍由评审把关。提示词契约也有可执行实现：[scripts/translation-prompt.ts](../../scripts/translation-prompt.ts) 会把仓库内置的模板（注入术语表；模板自带经人工校准的规则）渲染为英译中或中译英两个方向的提示词，并解析三段式响应；`doc-sync` 中的 `verify-translation-prompt` 会检查两个渲染方向与仓库内示例。\n" + "content": "# 双语文档\n\n[English](README.md) | 中文\n\n本仓库的文档会被公司内外的人和 agent（智能体）阅读，因此 README、Agent Note（agent 决策记录）与 docs 目录树以英文和简体中文双语维护。本页定义配对契约、强制门禁与推进策略；[translation-rules.md](translation-rules.md) 定义如何翻译；[terminology.md](terminology.md) 是术语真源。仓库内置的 agent 工作流见 [.agents/skills/dsh-translate-docs](../../.agents/skills/dsh-translate-docs/SKILL.md)。\n\n## 配对契约\n\n- **两种语言同权。** 一篇文档可以先用任一语言撰写和评审（先写中文的 Agent Note 与先写英文的一样正当），另一侧由它翻译而来。两个文件谁也不高于谁；约束它们的是二者必须说同样的话。\n- **一对文档是三个同目录文件。** 英文 `foo.md`、中文 `foo.zh.md`，加一份一致性记录 `foo.i18n.yaml`，都在同一目录。不用语言目录，不用独立翻译仓库，不用中英混排的单文件。配对必须整体合并：PR（Pull Request）永远不会只带一种语言而缺其余两个文件。\n- **一致性记录。**`foo.i18n.yaml` 保存两侧文件在上一次被确认「说同样的话」时各自的完整 git blob hash：\n\n ```yaml\n foo.md: 3f786850e387550fdab836ed7e6dc881de23001b\n foo.zh.md: 89e6c98d92887913cadf06b2adb97f26cde4849b\n ```\n\n 用 blob hash 而不是 commit hash，这样同一个 PR 里改动的文件也能算出记录（`git hash-object foo.md`），一致性是纯内容比较。记录的 hash 还能还原任一侧上次确认时的确切文本（`git cat-file -p `），所以失去同步的配对是「把被改的一侧与其上次确认状态做 diff、再最小化地修补另一侧」，从不整篇重译。两侧对齐后，`pnpm run verify-translation-pairing --write` 重新记录两个 hash；那份 yaml diff 就是「确认一致」这个动作本身，可以被评审。\n- **语言切换行。** 两个文件在各自 H1 标题之后立即互链：英文文件带 `English | [中文](foo.zh.md)`，中文文件带 `[English](foo.md) | 中文`。\n- **结构与另一侧一一对应。** 标题深度与顺序、列表类型、有序列表起始编号、列表项数量、表格行列数、链接目标与逐字节一致的代码块在配对两侧一一对应；完整保持规则见 [translation-rules.md](translation-rules.md)。既有 Markdown 门禁对 `.zh.md` 文件原样生效（`verify-md-wrap`、`verify-md-links`）。\n\n## 门禁：verify-translation-pairing\n\n`pnpm run verify-translation-pairing`（`doc-sync`（文档同步门禁）的一环，贡献者会针对文档变更在本地运行，CI 则会完整运行）机械地强制执行这份契约：\n\n1. [scripts/translation-pairing.manifest.json](../../scripts/translation-pairing.manifest.json) 中 `required` 列出的每个文件，以及所属文档类别出现在 `requiredClasses` 中的每篇文档，都有完整配对。类别分为 `non-readme` 和 `readme`；判断类别时，basename 不区分大小写，因此 `missions/readme.md` 也属于 README。\n2. 任何已存在的配对（无论是否 required）都完整且一致：三个文件齐全、每一侧的当前 blob hash 等于记录值（改了任一侧而没重新确认配对就变红）、双方都带语言切换行、结构签名按序一致：标题深度、逐字节一致的代码块（信息字符串与内容）、表格行列数、列表类型、有序列表起始编号、列表项数量，以及除切换行之外的每个链接目标。\n3. 列为 `excluded` 的文件完全没有 `.zh.md`，也没有 `.i18n.yaml`。\n4. 凡文件名符合 `yyyy-mm-dd-*.md` 且日期不早于 manifest（元数据清单）中 `requiredSince` 分界日期的文档，都必须有完整配对；新建的日期命名 Agent Note 从创建起便须配齐中英文。\n\n面向源码的代码门禁会把精确的 `.zh.md` 围栏序列视为其无后缀兄弟文件的派生内容，而不会再次编译相同代码或在 manifest 中重复登记。该序列必须在长度、顺序、围栏类型和按字节精确的正文上一致；否则两份副本仍会独立受检，配对门禁也会报告结构不匹配。\n\n`pnpm run verify-translation-pairing --list` 打印范围内每篇文档的当前配对状态（missing、out-of-sync 或 ok），是翻译批次的工作清单。它从不失败；它只报告。\n\n这个门禁带来的实际规则是：**当一个 PR 修改了已配对文档的任一侧时，同一个 PR 更新另一侧并重新记录配对**（运行 [dsh-translate-docs](../../.agents/skills/dsh-translate-docs/SKILL.md) skill（技能），再 `--write`），与本仓库既有的代码与 README 的 doc-sync 规则完全一致。留下失去同步的配对的 PR 会在 CI 变红。\n\n把门禁的边界说白：**门禁通过意味着这组文档在当前内容上的一致性得到了确认，不代表确认本身正确可靠。** 它检查记录的 hash 与结构签名；它无法判断两侧是否真的在说同样的话，也无法判断措辞是否准确、术语是否得当、行文是否自然；这部分契约由评审者把关，见 [translation-rules.md](translation-rules.md)。重新记录了 hash 但另一侧翻得潦草的配对能通过门禁；它不得通过评审。\n\n## 范围、排除与推进\n\n**范围**：除 vendor 源码外的全部 README，以及 `.agents/notes/**`、`docs/**` 与 `python/**` 下的全部文档。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。依赖目录和被忽略的构建产物目录只在发现阶段排除，并非源文档。\n\n**排除**（永不配对，门禁拒绝为它们建 `.zh.md` 或 `.i18n.yaml`）：\n\n- `docs/cordis-catalog/`、`docs/tool-catalog/`、`docs/config-catalog.md`、`docs/persistence-catalog.md`、`docs/module-graph.md`、`docs/agent-lifecycle.md`、`docs/capability-seams.md`、`docs/event-producer-consumer.md`、`docs/graph-atlas.md` 与 `docs/tool-execution-pipeline.md`：生成文件；生成器目前只输出英文，手写译文在每次重新生成时必然陈旧。计划中的后续工作是让生成器同时输出中文，届时这些文件移出排除清单。\n- `docs/AGENTS.md`、`.agents/notes/**/AGENTS.md` 以及指向它们的 `CLAUDE.md` 指令符号链接：agent 指令，与根 `AGENTS.md` 一样只以英文维护。\n- `docs/i18n/terminology.md` 与 [style-samples.md](style-samples.md)：二者本身即为中英对照文档。\n- [translation-prompt.md](translation-prompt.md)：自动翻译流水线的提示词模板；正文逐字进入模型请求，配对翻译会改变流水线行为。\n\n**执行红线**：某个文档类别的存量文档全部翻译完成后，`requiredClasses` 会将整个类别纳入强制范围。`non-readme` 与 `readme` 均已纳入强制范围：当前及今后所有纳入范围的文档，合并时都必须配齐双语文件。manifest 的 `required` 列表保留已纳入的文件；以日期命名的文档（`yyyy-mm-dd-*.md`，即 Agent Note）只要日期不早于 `requiredSince`，就无论所属类别都必须与对侧文件一同合并。`--list` 会报告尚未纳入强制范围的类别中的任何 backlog（待翻清单），而每个已存在的配对仍受完整契约约束。\n\n## 分工\n\n这里的对侧文件由运行 [dsh-translate-docs](../../.agents/skills/dsh-translate-docs/SKILL.md) 的 agent 生成，再由人评审：在这里推理（inference）很便宜，评审注意力才是稀缺资源。门禁负责检查配对是否完整、记录的 hash、语言切换行以及本文列出的结构签名；翻译质量、术语和签名未涵盖的结构要求仍由评审把关。提示词契约也有可执行实现：[scripts/translation-prompt.ts](../../scripts/translation-prompt.ts) 会把仓库内置的模板（注入术语表；模板自带经人工校准的规则）渲染为英译中或中译英两个方向的提示词，并解析三段式响应；`doc-sync` 中的 `verify-translation-prompt` 会检查两个渲染方向与仓库内示例。\n" }, { "role": "user", @@ -40,11 +40,11 @@ }, { "role": "user", - "content": "# Agent Note: Bilingual documentation via paired sibling files and a pairing gate\n\nStatus: implemented\n\nEnglish | [中文](2026-07-02-bilingual-docs-and-pairing-gate.zh.md)\n\n## Problem\n\nThis repo's README and docs tree are read by people and agents inside and outside the company, in both English and Chinese. Maintaining a second language by hand, with no mechanism, is how translations rot: one side moves on, the other silently lies, and no gate notices. The repo's standing answer to invariants of this kind is to encode them as a mechanical check (see [quality gates](2026-06-11-quality-gates.md) and [doc-sync enforcement](2026-06-11-doc-sync-enforcement.md)), so the bilingual policy ships with one.\n\n## Decision\n\n- **Paired sibling files with equal authority.** A documentation pair is three sibling files: English `foo.md`, Chinese `foo.zh.md`, and a consistency record `foo.i18n.yaml`. Neither language is canonical — a document may be authored and reviewed Chinese-first and translated to English afterwards, or the reverse; what binds the pair is that both sides must say the same thing, and pairs merge whole (both languages plus the record, never one alone). Policy: [docs/i18n/README.md](../../../../docs/i18n/README.md); translation rules: [docs/i18n/translation-rules.md](../../../../docs/i18n/translation-rules.md); terminology source of truth: [docs/i18n/terminology.md](../../../../docs/i18n/terminology.md).\n- **A sidecar record of both blob hashes makes consistency checkable.** `foo.i18n.yaml` holds the full git blob hash of each side as of the last confirmed-consistent state. An edit to either side without re-confirming the pair is then mechanically detectable as a pure content comparison — no history lookup — and the hashes are computable for files edited in the same PR, which a commit-hash record is not. Re-recording (`verify-translation-pairing --write`) produces a reviewable yaml diff: confirming consistency is an explicit, visible act in the PR.\n- **`verify-translation-pairing` joins `doc-sync`.** The gate ([scripts/verify-translation-pairing.ts](../../../../scripts/verify-translation-pairing.ts)) enforces: sources selected explicitly, by document class, or by the manifest's `requiredSince` cutoff have complete pairs; every existing pair is complete (all three files) and consistent (both hashes match, switcher links both ways, structural signatures identical); and excluded generated, instruction, or bilingual-by-construction files stay unpaired. The `requiredClasses` set in [scripts/translation-pairing.manifest.json](../../../../scripts/translation-pairing.manifest.json) closes a translated class for all present and future files instead of relying on an enumerated snapshot. 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- **The enforcement frontier advances in coherent review batches, then closes by class.** Explicit `required` entries admit related files while their back-catalog is still being reviewed; after that catalog is complete, its `non-readme` or `readme` class enters `requiredClasses` and can no longer grow a backlog. A site-published pair uses `pairedPages()` so the root locale projects `.zh.md` and `/en/` projects `.md`; creating a counterpart alone does not publish it.\n- **Pairing records are metadata, not Cordis Loader configuration.** Cordis configuration discovery accepts actual `.cordis.yml` and `.cordis.yaml` files while excluding `*.i18n.yaml`, even when the document name contains `cordis`. This preserves validation of executable Loader entries without parsing translation hashes as configuration.\n- **Translation is agent work with human review.** The committed workflow is [.agents/skills/dsh-translate-docs](../../../skills/dsh-translate-docs/SKILL.md), following the same pattern as [dsh-code-review](../../../skills/dsh-code-review/SKILL.md): the skill carries the workflow and defers to the docs as sources of truth. The skill directs the orchestrating agent to delegate translation writing to a subagent.\n\n## Verification\n\nThe verification contract covers each boundary independently. `verify-translation-pairing` pins pair completeness, hashes, switchers, and structure; [`project-doc-site.spec.ts`](../../../../scripts/project-doc-site.spec.ts) pins locale-specific source selection for published pairs; [`cordis-config-files.spec.ts`](../../../../scripts/cordis-config-files.spec.ts) pins discovery of Loader YAML and exclusion of translation records; and the [translation-prompt runnable snapshot](../../../../scripts/translation-prompt.snapshot.ts) pins the rendered system message, five reviewed example pairs, source request, and consumed response. Together these checks make pair drift, publication drift, configuration misclassification, and model-visible prompt drift review-visible.\n\n## Alternatives considered\n\n- **English as the canonical source with a fingerprint inside the translation** — the design first proposed for this Agent Note: `.zh.md` files carried an HTML comment recording the English source's blob hash, and translation flowed EN → ZH only. Revised in review: the team wants Chinese-first authoring (write and review a Chinese Agent Note, then translate to English) with the two languages holding equal authority, which a one-directional canonical model cannot express. The sidecar record covering BOTH sides replaced the in-file one-directional fingerprint; the blob-hash mechanics survived unchanged.\n- **Locale directories (`docs/en/` + `docs/zh/`, the Kubernetes/ECharts model)** — rejected: this repo has no docs-site framework to map locales to routes, moving every English file would churn every existing cross-reference, and `verify-md-links`/`verify-doc-refs` would need path-mapping logic instead of working unchanged.\n- **A separate translation repo (the PingCAP `docs`/`docs-cn` model)** — rejected: right for a docs product with independent release trains, overkill for a monorepo's own documentation; it also puts the translation outside the reach of this repo's gates.\n- **Interleaved bilingual files (single file, both languages)** — rejected: doubles every diff, breaks the one-line-per-paragraph convention's diff ergonomics, and makes partial inconsistency invisible.\n- **Commit-hash records (the MDN `l10n.sourceCommit` model)** — rejected in favor of blob hashes: a same-PR edit has no commit hash yet, so the MDN model cannot express \"consistent as of the state this PR introduces\", and verifying it requires git history instead of file content.\n- **Comparing git timestamps of the pair (no record)** — rejected: formatting-only edits would false-positive, and a counterpart committed after an unrelated edit would false-negative; content identity is the only signal that means what the gate claims.\n\n## Industry precedent\n\nPaired sibling files with locale suffixes are the dominant Chinese big-tech convention (ant-design `index.zh-CN.md`/`index.en-US.md`; arco-design `README.zh-CN.md` with a top-of-file switcher; Apache ShardingSphere's 387 `.cn.md`/`.en.md` pairs) — but none of those repos *enforce* pairing or consistency in CI; the convention holds by review alone. Consistency automation exists outside China: MDN's `l10n.sourceCommit` front-matter fingerprint, Vue's Ryu-Cho action (upstream-commit watcher that opens issues/PRs for stale translations), Kubernetes' localization drift scripts, and Microsoft's Azure co-op-translator (source-hash-driven LLM re-translation in CI). This design combines the two: the Chinese-ecosystem file layout with a hash-pair gate, plus a committed agent skill in place of a bot service.\n\n## Consequences\n\n- Editing either side of a paired document obligates the same PR to update the counterpart and re-record the pair — the gate makes the doc-sync rule bilingual, and CI (not reviewer memory) carries the invariant.\n- Every pair adds a third file to the tree. The record is machine-written (`--write`), so the cost is directory noise, not maintenance effort; in exchange, \"who confirmed these consistent, and when\" is answerable from git blame on the yaml.\n- When the two sides disagree, no mechanical rule picks a winner — the PR review does. That is the price of equal authority, accepted deliberately: the alternative (a canonical language) forbids Chinese-first authoring.\n- Generated docs (`cordis-catalog/`, `tool-catalog/`, `module-graph.md`) are excluded for now; the planned follow-up is to teach their generators to emit Chinese alongside English, at which point they leave the exclusion list.\n- Rollout remains incremental until a document class is complete: explicit `required` entries and the date cutoff prevent regression during review batches, while a closed class makes every current and future member mandatory. The non-README class is closed, so only the README class can still appear as backlog.\n- The recorded hashes double as the update tool (`git cat-file -p ` recovers either side's last-confirmed text for a minimal diff-based update), so re-translation of whole files is never forced by the mechanism.\n" + "content": "# Agent Note: Bilingual documentation via paired sibling files and a pairing gate\n\nStatus: implemented\n\nEnglish | [中文](2026-07-02-bilingual-docs-and-pairing-gate.zh.md)\n\n## Problem\n\nThis repo's README and docs tree are read by people and agents inside and outside the company, in both English and Chinese. Maintaining a second language by hand, with no mechanism, is how translations rot: one side moves on, the other silently lies, and no gate notices. The repo's standing answer to invariants of this kind is to encode them as a mechanical check (see [quality gates](2026-06-11-quality-gates.md) and [doc-sync enforcement](2026-06-11-doc-sync-enforcement.md)), so the bilingual policy ships with one.\n\n## Decision\n\n- **Paired sibling files with equal authority.** A documentation pair is three sibling files: English `foo.md`, Chinese `foo.zh.md`, and a consistency record `foo.i18n.yaml`. Neither language is canonical — a document may be authored and reviewed Chinese-first and translated to English afterwards, or the reverse; what binds the pair is that both sides must say the same thing, and pairs merge whole (both languages plus the record, never one alone). Policy: [docs/i18n/README.md](../../../../docs/i18n/README.md); translation rules: [docs/i18n/translation-rules.md](../../../../docs/i18n/translation-rules.md); terminology source of truth: [docs/i18n/terminology.md](../../../../docs/i18n/terminology.md).\n- **A sidecar record of both blob hashes makes consistency checkable.** `foo.i18n.yaml` holds the full git blob hash of each side as of the last confirmed-consistent state. An edit to either side without re-confirming the pair is then mechanically detectable as a pure content comparison — no history lookup — and the hashes are computable for files edited in the same PR, which a commit-hash record is not. Re-recording (`verify-translation-pairing --write`) produces a reviewable yaml diff: confirming consistency is an explicit, visible act in the PR.\n- **`verify-translation-pairing` joins `doc-sync`.** The gate ([scripts/verify-translation-pairing.ts](../../../../scripts/verify-translation-pairing.ts)) enforces: sources selected explicitly, by document class, or by the manifest's `requiredSince` cutoff have complete pairs; every existing pair is complete (all three files) and consistent (both hashes match, switcher links both ways, structural signatures identical); and excluded generated, instruction, or bilingual-by-construction files stay unpaired. The `requiredClasses` set in [scripts/translation-pairing.manifest.json](../../../../scripts/translation-pairing.manifest.json) closes a translated class for all present and future files instead of relying on an enumerated snapshot. 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- **The enforcement frontier advances in coherent review batches, then closes by class.** Explicit `required` entries admit related files while their back-catalog is still being reviewed; after that catalog is complete, its `non-readme` or `readme` class enters `requiredClasses` and can no longer grow a backlog. Both classes are closed. 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.** The committed workflow is [.agents/skills/dsh-translate-docs](../../../skills/dsh-translate-docs/SKILL.md), following the same pattern as [dsh-code-review](../../../skills/dsh-code-review/SKILL.md): the skill carries the workflow and defers to the docs as sources of truth. The skill directs the orchestrating agent to delegate translation writing to a subagent.\n\n## Verification\n\nThe verification contract covers each boundary independently. `verify-translation-pairing` pins pair completeness, hashes, switchers, and structure; [`project-doc-site.spec.ts`](../../../../scripts/project-doc-site.spec.ts) pins locale-specific source selection for published pairs; [`cordis-config-files.spec.ts`](../../../../scripts/cordis-config-files.spec.ts) pins discovery of Loader YAML and exclusion of translation records; and the [translation-prompt runnable snapshot](../../../../scripts/translation-prompt.snapshot.ts) pins the rendered system message, five reviewed example pairs, source request, and consumed response. Together these checks make pair drift, publication drift, configuration misclassification, and model-visible prompt drift review-visible.\n\n## Alternatives considered\n\n- **English as the canonical source with a fingerprint inside the translation** — the design first proposed for this Agent Note: `.zh.md` files carried an HTML comment recording the English source's blob hash, and translation flowed EN → ZH only. Revised in review: the team wants Chinese-first authoring (write and review a Chinese Agent Note, then translate to English) with the two languages holding equal authority, which a one-directional canonical model cannot express. The sidecar record covering BOTH sides replaced the in-file one-directional fingerprint; the blob-hash mechanics survived unchanged.\n- **Locale directories (`docs/en/` + `docs/zh/`, the Kubernetes/ECharts model)** — rejected: this repo has no docs-site framework to map locales to routes, moving every English file would churn every existing cross-reference, and `verify-md-links`/`verify-doc-refs` would need path-mapping logic instead of working unchanged.\n- **A separate translation repo (the PingCAP `docs`/`docs-cn` model)** — rejected: right for a docs product with independent release trains, overkill for a monorepo's own documentation; it also puts the translation outside the reach of this repo's gates.\n- **Interleaved bilingual files (single file, both languages)** — rejected: doubles every diff, breaks the one-line-per-paragraph convention's diff ergonomics, and makes partial inconsistency invisible.\n- **Commit-hash records (the MDN `l10n.sourceCommit` model)** — rejected in favor of blob hashes: a same-PR edit has no commit hash yet, so the MDN model cannot express \"consistent as of the state this PR introduces\", and verifying it requires git history instead of file content.\n- **Comparing git timestamps of the pair (no record)** — rejected: formatting-only edits would false-positive, and a counterpart committed after an unrelated edit would false-negative; content identity is the only signal that means what the gate claims.\n\n## Industry precedent\n\nPaired sibling files with locale suffixes are the dominant Chinese big-tech convention (ant-design `index.zh-CN.md`/`index.en-US.md`; arco-design `README.zh-CN.md` with a top-of-file switcher; Apache ShardingSphere's 387 `.cn.md`/`.en.md` pairs) — but none of those repos *enforce* pairing or consistency in CI; the convention holds by review alone. Consistency automation exists outside China: MDN's `l10n.sourceCommit` front-matter fingerprint, Vue's Ryu-Cho action (upstream-commit watcher that opens issues/PRs for stale translations), Kubernetes' localization drift scripts, and Microsoft's Azure co-op-translator (source-hash-driven LLM re-translation in CI). This design combines the two: the Chinese-ecosystem file layout with a hash-pair gate, plus a committed agent skill in place of a bot service.\n\n## Consequences\n\n- Editing either side of a paired document obligates the same PR to update the counterpart and re-record the pair — the gate makes the doc-sync rule bilingual, and CI (not reviewer memory) carries the invariant.\n- Every pair adds a third file to the tree. The record is machine-written (`--write`), so the cost is directory noise, not maintenance effort; in exchange, \"who confirmed these consistent, and when\" is answerable from git blame on the yaml.\n- When the two sides disagree, no mechanical rule picks a winner — the PR review does. That is the price of equal authority, accepted deliberately: the alternative (a canonical language) forbids Chinese-first authoring.\n- Generated docs (`cordis-catalog/`, `tool-catalog/`, `module-graph.md`) are excluded for now; the planned follow-up is to teach their generators to emit Chinese alongside English, at which point they leave the exclusion list.\n- Explicit `required` entries and the date cutoff preserve the reviewed rollout history, while the two closed classes make every current and future in-scope document mandatory. No document class can grow a new backlog.\n- The recorded hashes double as the update tool (`git cat-file -p ` recovers either side's last-confirmed text for a minimal diff-based update), so re-translation of whole files is never forced by the mechanism.\n" }, { "role": "assistant", - "content": "# Agent Note：通过配对兄弟文件与配对门禁实现双语文档\n\nStatus: implemented\n\n[English](2026-07-02-bilingual-docs-and-pairing-gate.md) | 中文\n\n## 问题\n\n本仓库的 README 与 docs 目录树会被公司内外的人和 agent（智能体）以中英两种语言阅读。在没有机制的情况下纯靠手工维护第二语言，正是译文腐烂的根源：一侧持续演进，另一侧默默失实，而没有门禁会注意到。对于这类不变式，本仓库一贯的做法是将其编码为机械检查（见[质量门禁](2026-06-11-quality-gates.md)与 [doc-sync 强制](2026-06-11-doc-sync-enforcement.md)），因此双语政策随附一道门禁一起交付。\n\n## 决策\n\n- **配对兄弟文件，两种语言同权。** 一对文档由三个兄弟文件组成：英文 `foo.md`、中文 `foo.zh.md`，以及一份一致性记录 `foo.i18n.yaml`。没有哪种语言是正典：一篇文档可以先用中文撰写和评审、之后再译成英文，反之亦可；约束配对的是：两侧必须表达相同的内容，且配对整体合并（两种语言加记录，绝不单独落一侧）。政策见 [docs/i18n/README.md](../../../../docs/i18n/README.md)；翻译规则见 [docs/i18n/translation-rules.md](../../../../docs/i18n/translation-rules.md)；术语真源见 [docs/i18n/terminology.md](../../../../docs/i18n/terminology.md)。\n- **伴随记录保存两侧 blob hash，使一致性可检查。** `foo.i18n.yaml` 保存两侧文件在上一次确认一致时各自的完整 git blob hash。此后修改了任一侧而未重新确认配对，都能被机械检测出来（纯内容比较，无需查询历史），而且同一个 PR（Pull Request）内改动的文件也能计算出 hash，commit hash 式的记录做不到这一点。重新记录（`verify-translation-pairing --write`）会产生一份可评审的 yaml diff：确认一致在 PR 中是一个显式、可见的动作。\n- **`verify-translation-pairing` 加入 `doc-sync`。** 门禁（[scripts/verify-translation-pairing.ts](../../../../scripts/verify-translation-pairing.ts)）强制执行以下规则：通过显式指定、文档类别或 manifest（元数据清单）的 `requiredSince` 分界日期选中的源文档必须有完整配对；任何已存在的配对必须完整（三个文件齐全）且一致（两个 hash 匹配、切换行双向互链、结构签名一致）；被排除的生成文档、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) 中的 `requiredClasses` 集合会将已完成翻译的类别纳入强制范围，对其当前及今后所有文件强制执行契约，而不再依赖一份枚举式快照。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- **执行红线按连贯的评审批次推进，再以类别为单位完成强制覆盖。** 在存量文档仍处于评审阶段时，显式 `required` 条目会纳入相关文件；存量文档全部完成后，其 `non-readme` 或 `readme` 类别进入 `requiredClasses`，不再产生新的 backlog。发布到文档站的配对使用 `pairedPages()`，由根 locale 投影 `.zh.md`，由 `/en/` 投影 `.md`；仅创建对侧文件并不会发布它。\n- **配对记录是元数据，而不是 Cordis Loader 配置。** Cordis 配置发现会接受实际的 `.cordis.yml` 和 `.cordis.yaml` 文件，同时排除 `*.i18n.yaml`，即使文档名中包含 `cordis` 也不例外。这样既能继续校验可执行的 Loader 配置项，又不会把翻译 hash 当作配置来解析。\n- **翻译是 agent 的工作，由人评审。** 仓库内置的工作流是 [.agents/skills/dsh-translate-docs](../../../skills/dsh-translate-docs/SKILL.md)，与 [dsh-code-review](../../../skills/dsh-code-review/SKILL.md) 模式相同：skill（技能）承载工作流，并将文档作为真源。该 skill 要求编排 agent 把翻译写作委派给 subagent。\n\n## 验证\n\n验证契约分别覆盖每个边界。`verify-translation-pairing` 固定配对完整性、hash、切换行和结构；[`project-doc-site.spec.ts`](../../../../scripts/project-doc-site.spec.ts) 固定已发布配对按 locale 选择对应源文件；[`cordis-config-files.spec.ts`](../../../../scripts/cordis-config-files.spec.ts) 固定 Loader YAML 的发现以及翻译记录的排除；[翻译提示词可运行快照](../../../../scripts/translation-prompt.snapshot.ts)则固定渲染后的系统消息、五对经评审的示例、源请求和响应消费结果。这些检查共同使配对漂移、发布漂移、配置误分类和模型可见提示词漂移都可在评审中看见。\n\n## 曾考虑的替代方案\n\n- **英文为正典源、指纹放在译文内**：本 Agent Note 最初提出的设计：`.zh.md` 文件携带一条 HTML 注释记录英文源的 blob hash，翻译只沿 EN → ZH 单向流动。评审中修订：团队需要中文先行的撰写方式（先写、先审中文 Agent Note，再译英文），两种语言同权，而单向正典模型无法表达这一点。覆盖**两侧**的伴随记录取代了文件内的单向指纹；blob hash 的机制本身保持不变。\n- **语言目录（`docs/en/` + `docs/zh/`，Kubernetes/ECharts 模式）**：否决。本仓库没有将 locale 映射到路由的文档站框架；如果移动所有英文文件，所有既有交叉引用都要随之修改；且 `verify-md-links`/`verify-doc-refs` 将需要路径映射逻辑，而非原样工作。\n- **独立翻译仓库（PingCAP `docs`/`docs-cn` 模式）**：否决。适合有独立发布节奏的文档产品，对 monorepo 自身的文档而言过重；还会把译文置于本仓库门禁触及不到的地方。\n- **中英混排单文件（一个文件、两种语言）**：否决。每个 diff 都翻倍，破坏一段一行约定的 diff 易读性，且局部不一致不可见。\n- **Commit hash 式记录（MDN `l10n.sourceCommit` 模式）**：否决，改用 blob hash。同一个 PR 内的改动还没有 commit hash，MDN 模式无法表达「与本 PR 引入的状态一致」，且校验它需要 git 历史而非文件内容。\n- **比较配对两侧的 git 时间戳（无记录）**：否决。纯格式化的改动会误报，一次无关改动之后提交的对侧文件会漏报；只有内容同一性这个信号才与门禁的承诺名实相符。\n\n## 业界先例\n\n带语言后缀的配对兄弟文件是中国大厂的主流约定（ant-design 的 `index.zh-CN.md`/`index.en-US.md`；arco-design 的 `README.zh-CN.md` 加顶部切换行；Apache ShardingSphere 的 387 对 `.cn.md`/`.en.md`），但这些仓库都没有在 CI 中**强制**配对或一致性检查；约定纯靠评审维系。一致性自动化存在于中国以外：MDN 的 `l10n.sourceCommit` front-matter 指纹、Vue 的 Ryu-Cho action（监视上游 commit，为陈旧译文自动开 issue/PR）、Kubernetes 的本地化漂移脚本、微软 Azure co-op-translator（CI 中由源 hash 驱动的 LLM 重译）。本设计将两者结合：中文生态的文件布局，加上 hash 配对门禁，再加一个仓库内置的 agent skill 替代 bot 服务。\n\n## 后果\n\n- 修改已配对文档的任一侧，同一个 PR 就有义务更新对侧并重新记录配对。门禁将 doc-sync 规则双语化，不变式由 CI（而非评审者的记忆）承载。\n- 每个配对给目录树多添一个文件。记录由机器写入（`--write`），代价是目录噪音而非维护负担；换来的是「谁在何时确认过这对文档一致」可以从 yaml 的 git blame 直接回答。\n- 两侧说法冲突时，没有机械规则裁决谁赢，由 PR 评审裁决。这是同权的代价，且是有意接受的：另一个选项（正典语言）会禁止中文先行撰写。\n- 生成文档（`cordis-catalog/`、`tool-catalog/`、`module-graph.md`）暂被排除；计划中的后续工作是让生成器在输出英文的同时输出中文，届时将这些文件移出排除清单。\n- 在文档类别全部完成之前，推进仍然是渐进的：显式 `required` 条目与日期分界可在评审批次期间防止回退，已纳入强制范围的类别则将其当前及今后的每个成员都列为必选项。非 README 类别已纳入强制范围，因此只有 README 类别仍可能出现 backlog（待翻清单）。\n- 记录的 hash 兼作更新工具（`git cat-file -p ` 能还原任一侧上次确认的文本，用于基于 diff 的最小更新），因此这套机制从不强迫整篇重译。\n" + "content": "# Agent Note：通过配对兄弟文件与配对门禁实现双语文档\n\nStatus: implemented\n\n[English](2026-07-02-bilingual-docs-and-pairing-gate.md) | 中文\n\n## 问题\n\n本仓库的 README 与 docs 目录树会被公司内外的人和 agent（智能体）以中英两种语言阅读。在没有机制的情况下纯靠手工维护第二语言，正是译文腐烂的根源：一侧持续演进，另一侧默默失实，而没有门禁会注意到。对于这类不变式，本仓库一贯的做法是将其编码为机械检查（见[质量门禁](2026-06-11-quality-gates.md)与 [doc-sync 强制](2026-06-11-doc-sync-enforcement.md)），因此双语政策随附一道门禁一起交付。\n\n## 决策\n\n- **配对兄弟文件，两种语言同权。** 一对文档由三个兄弟文件组成：英文 `foo.md`、中文 `foo.zh.md`，以及一份一致性记录 `foo.i18n.yaml`。没有哪种语言是正典：一篇文档可以先用中文撰写和评审、之后再译成英文，反之亦可；约束配对的是：两侧必须表达相同的内容，且配对整体合并（两种语言加记录，绝不单独落一侧）。政策见 [docs/i18n/README.md](../../../../docs/i18n/README.md)；翻译规则见 [docs/i18n/translation-rules.md](../../../../docs/i18n/translation-rules.md)；术语真源见 [docs/i18n/terminology.md](../../../../docs/i18n/terminology.md)。\n- **伴随记录保存两侧 blob hash，使一致性可检查。** `foo.i18n.yaml` 保存两侧文件在上一次确认一致时各自的完整 git blob hash。此后修改了任一侧而未重新确认配对，都能被机械检测出来（纯内容比较，无需查询历史），而且同一个 PR（Pull Request）内改动的文件也能计算出 hash，commit hash 式的记录做不到这一点。重新记录（`verify-translation-pairing --write`）会产生一份可评审的 yaml diff：确认一致在 PR 中是一个显式、可见的动作。\n- **`verify-translation-pairing` 加入 `doc-sync`。** 门禁（[scripts/verify-translation-pairing.ts](../../../../scripts/verify-translation-pairing.ts)）强制执行以下规则：通过显式指定、文档类别或 manifest（元数据清单）的 `requiredSince` 分界日期选中的源文档必须有完整配对；任何已存在的配对必须完整（三个文件齐全）且一致（两个 hash 匹配、切换行双向互链、结构签名一致）；被排除的生成文档、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) 中的 `requiredClasses` 集合会将已完成翻译的类别纳入强制范围，对其当前及今后所有文件强制执行契约，而不再依赖一份枚举式快照。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- **执行红线按连贯的评审批次推进，再以类别为单位完成强制覆盖。** 在存量文档仍处于评审阶段时，显式 `required` 条目会纳入相关文件；存量文档全部完成后，其 `non-readme` 或 `readme` 类别进入 `requiredClasses`，不再产生新的 backlog。这两个类别均已纳入强制范围。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## 曾考虑的替代方案\n\n- **英文为正典源、指纹放在译文内**：本 Agent Note 最初提出的设计：`.zh.md` 文件携带一条 HTML 注释记录英文源的 blob hash，翻译只沿 EN → ZH 单向流动。评审中修订：团队需要中文先行的撰写方式（先写、先审中文 Agent Note，再译英文），两种语言同权，而单向正典模型无法表达这一点。覆盖**两侧**的伴随记录取代了文件内的单向指纹；blob hash 的机制本身保持不变。\n- **语言目录（`docs/en/` + `docs/zh/`，Kubernetes/ECharts 模式）**：否决。本仓库没有将 locale 映射到路由的文档站框架；如果移动所有英文文件，所有既有交叉引用都要随之修改；且 `verify-md-links`/`verify-doc-refs` 将需要路径映射逻辑，而非原样工作。\n- **独立翻译仓库（PingCAP `docs`/`docs-cn` 模式）**：否决。适合有独立发布节奏的文档产品，对 monorepo 自身的文档而言过重；还会把译文置于本仓库门禁触及不到的地方。\n- **中英混排单文件（一个文件、两种语言）**：否决。每个 diff 都翻倍，破坏一段一行约定的 diff 易读性，且局部不一致不可见。\n- **Commit hash 式记录（MDN `l10n.sourceCommit` 模式）**：否决，改用 blob hash。同一个 PR 内的改动还没有 commit hash，MDN 模式无法表达「与本 PR 引入的状态一致」，且校验它需要 git 历史而非文件内容。\n- **比较配对两侧的 git 时间戳（无记录）**：否决。纯格式化的改动会误报，一次无关改动之后提交的对侧文件会漏报；只有内容同一性这个信号才与门禁的承诺名实相符。\n\n## 业界先例\n\n带语言后缀的配对兄弟文件是中国大厂的主流约定（ant-design 的 `index.zh-CN.md`/`index.en-US.md`；arco-design 的 `README.zh-CN.md` 加顶部切换行；Apache ShardingSphere 的 387 对 `.cn.md`/`.en.md`），但这些仓库都没有在 CI 中**强制**配对或一致性检查；约定纯靠评审维系。一致性自动化存在于中国以外：MDN 的 `l10n.sourceCommit` front-matter 指纹、Vue 的 Ryu-Cho action（监视上游 commit，为陈旧译文自动开 issue/PR）、Kubernetes 的本地化漂移脚本、微软 Azure co-op-translator（CI 中由源 hash 驱动的 LLM 重译）。本设计将两者结合：中文生态的文件布局，加上 hash 配对门禁，再加一个仓库内置的 agent skill 替代 bot 服务。\n\n## 后果\n\n- 修改已配对文档的任一侧，同一个 PR 就有义务更新对侧并重新记录配对。门禁将 doc-sync 规则双语化，不变式由 CI（而非评审者的记忆）承载。\n- 每个配对给目录树多添一个文件。记录由机器写入（`--write`），代价是目录噪音而非维护负担；换来的是「谁在何时确认过这对文档一致」可以从 yaml 的 git blame 直接回答。\n- 两侧说法冲突时，没有机械规则裁决谁赢，由 PR 评审裁决。这是同权的代价，且是有意接受的：另一个选项（正典语言）会禁止中文先行撰写。\n- 生成文档（`cordis-catalog/`、`tool-catalog/`、`module-graph.md`）暂被排除；计划中的后续工作是让生成器在输出英文的同时输出中文，届时将这些文件移出排除清单。\n- 显式 `required` 条目与日期分界保留已经评审的推进历史，而两个已纳入强制范围的类别会将当前及今后所有范围内的文档列为必选项。任何文档类别都不能新增 backlog（待翻清单）。\n- 记录的 hash 兼作更新工具（`git cat-file -p ` 能还原任一侧上次确认的文本，用于基于 diff 的最小更新），因此这套机制从不强迫整篇重译。\n" }, { "role": "user", diff --git a/scripts/translation-pairing.manifest.json b/scripts/translation-pairing.manifest.json index 35688f62b7..1667a8eaef 100644 --- a/scripts/translation-pairing.manifest.json +++ b/scripts/translation-pairing.manifest.json @@ -1,6 +1,7 @@ { "requiredClasses": [ - "non-readme" + "non-readme", + "readme" ], "requiredSince": "2026-07-14", "required": [ diff --git a/scripts/translation-pairing.spec.ts b/scripts/translation-pairing.spec.ts index b8b880565a..5c10f80abb 100644 --- a/scripts/translation-pairing.spec.ts +++ b/scripts/translation-pairing.spec.ts @@ -4,6 +4,7 @@ import { describe, expect, it } from 'vitest' import { datedDocumentDate, isIsoDate, + isTranslationScopeFile, parseTranslationMarkdown, parseTranslationPairingManifest, requiresPairByDate, @@ -82,6 +83,45 @@ describe('document-class pairing frontier', () => { expect(requiresTranslationPair('docs/legacy/README.md', manifest)).toBe(true) expect(requiresTranslationPair('docs/new/README.md', manifest)).toBe(false) }) + + it('requires both document classes after the README frontier closes', () => { + const closed = parseTranslationPairingManifest(JSON.stringify({ + ...manifest, + requiredClasses: ['non-readme', 'readme'], + })) + expect(requiresTranslationPair('docs/guide.md', closed)).toBe(true) + expect(requiresTranslationPair('future/subtree/README.md', closed)).toBe(true) + }) +}) + +describe('translation scope discovery', () => { + it.each([ + 'README.md', + 'apps/cli/README.md', + 'future/subtree/readme.md', + 'packages/example/README.zh.md', + 'native/example/README.i18n.yaml', + '.agents/notes/proposed/feature.md', + 'docs/guide.md', + 'python/guide.md', + ])('includes %s', (file) => { + expect(isTranslationScopeFile(file)).toBe(true) + }) + + it.each([ + 'packages/example/guide.md', + 'examples/tutorial.md', + 'website/reference.md', + 'packages/example/README.txt', + 'vendor/example/README.md', + 'packages/example/node_modules/dependency/README.md', + 'packages/example/lib/README.md', + 'coverage/report/README.md', + 'python/sdk-runtime/src/deepseek_harness_runtime/runtime/dsh-jsonrpc-agent-macos-arm64/README.md', + 'python/sdk-runtime/src/deepseek_harness_runtime/runtime/node/README.md', + ])('excludes non-source or non-README path %s', (file) => { + expect(isTranslationScopeFile(file)).toBe(false) + }) }) describe('date-based pairing frontier', () => { diff --git a/scripts/translation-pairing.ts b/scripts/translation-pairing.ts index 92c38e8896..a41bcc3077 100644 --- a/scripts/translation-pairing.ts +++ b/scripts/translation-pairing.ts @@ -26,6 +26,63 @@ const TRANSLATION_DOCUMENT_CLASSES: TranslationDocumentClass[] = ['readme', 'non const ISO_DATE = /^\d{4}-\d{2}-\d{2}$/ const DATED_DOCUMENT = /(?:^|\/)(\d{4}-\d{2}-\d{2})-[^/]*\.md$/ +const README_ARTIFACT = /(?:^|\/)readme(?:\.md|\.zh\.md|\.i18n\.yaml)$/i +const NON_SOURCE_DIRECTORIES = new Set([ + 'node_modules', + 'lib', + '.pnpm-store', + '.cache', + 'coverage', + '.sessions', + '.storages', + 'tmp', + 'dist-exe', + '__pycache__', + '.pytest_cache', + '.artifacts', + 'vendor', +]) + +/** Glob traversal exclusions corresponding to the non-source path predicate. */ +export const TRANSLATION_SCOPE_GLOB_EXCLUDES = [ + '**/node_modules/**', + '**/lib/**', + '**/.pnpm-store/**', + '**/.cache/**', + '**/coverage/**', + '**/.doc-typecheck-*/**', + '**/.node-next-types-*/**', + '**/.sessions/**', + '**/.storages/**', + '**/tmp/**', + '**/dist-exe/**', + '**/__pycache__/**', + '**/.pytest_cache/**', + 'apps/web/dist/**', + '.artifacts/**', + 'python/sdk-runtime/src/deepseek_harness_runtime/runtime/dsh-jsonrpc-agent-*/**', + 'python/sdk-runtime/src/deepseek_harness_runtime/runtime/node/**', + 'vendor/**', +] + +/** Whether a repository-relative path belongs to a dependency or generated tree. */ +function isTranslationSourceExcluded(file: string): boolean { + const segments = file.split('/') + return segments.some(segment => NON_SOURCE_DIRECTORIES.has(segment) + || segment.startsWith('.doc-typecheck-') + || segment.startsWith('.node-next-types-')) + || file.startsWith('apps/web/dist/') + || file.startsWith('python/sdk-runtime/src/deepseek_harness_runtime/runtime/dsh-jsonrpc-agent-') + || file.startsWith('python/sdk-runtime/src/deepseek_harness_runtime/runtime/node/') +} + +/** Whether one discovered Markdown or sidecar path belongs to the bilingual source corpus. */ +export function isTranslationScopeFile(file: string): boolean { + return !isTranslationSourceExcluded(file) && (README_ARTIFACT.test(file) + || file.startsWith('.agents/notes/') + || file.startsWith('docs/') + || file.startsWith('python/')) +} /** Whether a string names one real calendar day in canonical ISO form. */ export function isIsoDate(value: string): boolean { diff --git a/scripts/verify-translation-pairing.ts b/scripts/verify-translation-pairing.ts index 9372064707..8e688d02e9 100644 --- a/scripts/verify-translation-pairing.ts +++ b/scripts/verify-translation-pairing.ts @@ -15,7 +15,9 @@ import { linksTo, parseTranslationMarkdown, parseTranslationPairingManifest, + isTranslationScopeFile, requiresTranslationPair, + TRANSLATION_SCOPE_GLOB_EXCLUDES, translationDocumentClass, translationStructureDiff, translationStructureSignature, @@ -25,17 +27,12 @@ const root = resolve(import.meta.dirname, '..') const listMode = process.argv.includes('--list') const writeMode = process.argv.includes('--write') -/** Scope of the bilingual contract: root docs, Agent Notes, the docs tree, and the Python SDK tree. */ +/** Discover source Markdown and pairing sidecars before applying the corpus predicate. */ const SCOPE_PATTERNS = [ - 'README.md', - 'README.zh.md', - 'README.i18n.yaml', + '**/*.md', + '**/*.i18n.yaml', '.agents/notes/**/*.md', '.agents/notes/**/*.i18n.yaml', - 'docs/**/*.md', - 'docs/**/*.i18n.yaml', - 'python/**/*.md', - 'python/**/*.i18n.yaml', ] const manifest = parseTranslationPairingManifest(readFileSync(join(root, 'scripts/translation-pairing.manifest.json'), 'utf8')) @@ -93,7 +90,10 @@ function renderMeta(source: string, sourceHash: string, zh: string, zhHash: stri // Enumerate the scope once. const files = new Set() for (const pattern of SCOPE_PATTERNS) { - for (const match of globSync(pattern, { cwd: root })) files.add(match.split(sep).join('/')) + for (const match of globSync(pattern, { cwd: root, exclude: TRANSLATION_SCOPE_GLOB_EXCLUDES })) { + const normalized = match.split(sep).join('/') + if (isTranslationScopeFile(normalized)) files.add(normalized) + } } const translations = [...files].filter(f => f.endsWith('.zh.md')).sort() const metas = [...files].filter(f => f.endsWith('.i18n.yaml')).sort()