diff --git a/scripts/snapshots/translation-prompt-v4/request-response.expected.json b/scripts/snapshots/translation-prompt-v4/request-response.expected.json index 7f2c71353e..ab862dba34 100644 --- a/scripts/snapshots/translation-prompt-v4/request-response.expected.json +++ b/scripts/snapshots/translation-prompt-v4/request-response.expected.json @@ -24,27 +24,43 @@ }, { "role": "user", +<<<<<<< HEAD "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. 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. `--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. `pnpm run gen-translation-brief ` assembles that update's working set mechanically at the narrowest safely aligned granularity — changed Markdown units, then heading sections, then whole document — with the edited side's diff since last confirmation, each changed span's three-way text, the terminology rows the change touches, and the binding update rules; a change confined to the pair's byte-identical code fences is computed outright, and `--apply` splices it into the counterpart 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 ` 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.\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 document in scope has a complete pair. README discovery is case-insensitive on the basename, so `missions/readme.md` is in scope alongside the other documentation roots.\n2. Every pair artifact that exists at all 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), the Chinese side and every authored English source carry their language switchers (listed generated English sources are exempt), 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. Frozen Agent Notes under `.agents/notes/archived/` are outside this evolving gate; their dedicated verifier requires and seals the complete existing triplet instead.\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. It never fails; `missing` and `out-of-sync` rows identify violations that the normal check rejects.\n\n`pnpm run verify-translation-pairing ` checks just the named pairs — any of a pair's three files (or its bare stem) names it — so an update loop verifies its own pair in seconds instead of re-scanning the corpus. The no-argument corpus-wide form is what `doc-sync` and CI run; a scoped green never substitutes for it at PR level.\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 Markdown structure; 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 and exclusions\n\n**Scope**: every non-vendor README, plus 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.\n\nGenerated 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. 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.\n\n**Excluded** (never paired, and the gate rejects a `.zh.md` or `.i18n.yaml` for them):\n\n- [cordis-api/inherited.md](../cordis-api/inherited.md) — generated without a reviewed Chinese counterpart, so both website locales project the English source.\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- `.agents/notes/archived/` — frozen historical triplets. [`verify-archived-agent-notes`](../../scripts/verify-archived-agent-notes.ts) validates their completeness and content seals; translation maintenance must never rewrite them.\n\n**Universal requirement**: every current or future document in scope must merge as a complete bilingual pair. [scripts/translation-pairing.manifest.json](../../scripts/translation-pairing.manifest.json) contains only explicit exclusions; there is no per-file rollout list, date cutoff, or README-specific policy class.\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, the Chinese backlink and authored-source switcher (with the documented generated-source exception), 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，因此范围内的每篇文档都以英文和简体中文维护。本页定义配对约定、检查、范围与排除规则；[translation-rules.md](translation-rules.md) 定义如何翻译；[terminology.md](terminology.md) 是术语真源。仓库内置的 agent 工作流见 [.agents/skills/dsh-translate-docs](../../.agents/skills/dsh-translate-docs/SKILL.md)。\n\n## 配对约定\n\n- **两种语言同权。** 一篇文档可以先用任一语言撰写和评审（先写中文的 Agent Note 与先写英文的一样正当），另一侧由它翻译而来。两个文件谁也不高于谁；约束它们的是二者必须说同样的话。\n- **一对文档是三个同目录文件。** 英文 `foo.md`、中文 `foo.zh.md`，加一份一致性记录 `foo.i18n.yaml`，都在同一目录。不用语言目录，不用独立翻译仓库，不用中英混排的单文件。配对必须整体合并：PR（Pull Request）永远不会只带一种语言而缺其余两个文件。\n- **一致性记录。**`foo.i18n.yaml` 保存两侧文件在上一次被确认「说同样的话」时各自的完整 git blob hash：\n\n ```yaml\n foo.md: 3f786850e387550fdab836ed7e6dc881de23001b\n foo.zh.md: 89e6c98d92887913cadf06b2adb97f26cde4849b\n ```\n\n 用 blob hash 而不是 commit hash，这样同一个 PR 里改动的文件也能算出记录（`git hash-object foo.md`），一致性是纯内容比较。`--write` 会先把这些快照存入本地 Git 对象库再写下记录，未提交的工作树内容也不例外；它还会在内容寻址的 `refs/dsh/translation-pairing/snapshots/` ref 下固定每个不同的已存 blob，使垃圾回收无法让已记录的恢复指针失效。因此记录的 hash 能还原任一侧上次确认时的确切文本，所以失去同步的配对是「按被改一侧的 diff 最小化地修补另一侧」，从不整篇重译。`pnpm run gen-translation-brief ` 会以能安全对齐的最窄粒度——先是有改动的 Markdown 单元，再是标题小节，最后是整篇文档——机械地汇集这次更新的工作集：被改一侧自上次确认以来的 diff、每个改动块的三方文本、改动触及的术语表行，以及有约束力的更新规则；仅落在配对中逐字节一致的围栏代码块内的改动可以直接算出，`--apply` 则经结构签名校验后把它拼接进对侧文件（[briefed-updates Agent Note](../../.agents/notes/implemented/process/2026-07-26-briefed-minimal-translation-updates.md)）。两侧对齐后，`pnpm run verify-translation-pairing --write ` 重新记录两个 hash；那份 yaml diff 就是「确认一致」这个动作本身，可以被评审，也正因如此，`--write` 要求点名你确认过的配对（`--write --all` 是显式的全语料形式）。\n\n 当两个分支都包含同一配对的有效确认时，已安装的 `dsh-translation-pairing` Git 合并驱动只会在 Git 默认文本合并能分别干净合并记录所指向的英文三方 blob 与中文三方 blob，且合并后的配对仍保留必需的语言切换行和结构签名时，组合出一份新记录。中文文件必须保留指向英文的反向链接；普通撰写的英文源必须保留指向中文的链接，而清单内的生成英文源不作此要求。任何合并驱动无法验证的结构都保留为普通冲突；`pnpm run resolve-translation-pairing-conflicts` 会对已经停止的合并执行同一套遇错即保留冲突的操作，暂存每份可安全生成的配对记录，并在还有其他配对冲突时以非零状态退出。[自动配对合并 Agent Note](../../.agents/notes/implemented/process/2026-08-08-automatic-translation-pairing-merges.md) 负责记录该机制与备选方案。\n- **语言切换行。** 中文文件一律在 H1 标题后立即以 `[English](foo.md) | 中文` 链回英文。普通撰写的英文文件在同一位置以 `English | [中文](foo.zh.md)` 互链；清单内的生成英文源省略此行，以便与生成器输出逐字节一致。\n- **结构与另一侧一一对应。** 标题深度与顺序、列表类型、有序列表起始编号、列表项数量、表格行列数、链接目标与逐字节一致的代码块在配对两侧一一对应；完整保持规则见 [translation-rules.md](translation-rules.md)。既有 Markdown 门禁对 `.zh.md` 文件原样生效（`verify-md-wrap`、`verify-md-links`）。\n\n## 门禁：verify-translation-pairing\n\n`pnpm run verify-translation-pairing`（`doc-sync`（文档同步门禁）的一环，贡献者会针对文档变更在本地运行，CI 则会完整运行）机械地强制执行这份约定：\n\n1. 范围内的每篇文档都有完整配对。发现 README 时，basename 不区分大小写，因此 `missions/readme.md` 与其他文档根一样属于范围。\n2. 任何已存在的配对产物都完整且一致：三个文件齐全、每一侧的当前 blob hash 等于记录值（改了任一侧而没重新确认配对就变红）、中文侧和所有普通撰写的英文源都带语言切换行（清单内的生成英文源除外）、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`。`.agents/notes/archived/` 下冻结的 Agent Note 不受这个持续演进的门禁约束；专用校验器会要求其现有的三个配对文件完整，并将其封存。\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）。它从不失败；其中 missing 与 out-of-sync 行指出普通检查会拒绝的违规。\n\n`pnpm run verify-translation-pairing ` 只检查被点名的配对——配对的三个文件中的任意一个（或其裸词干）都能点名它——因此更新循环几秒内就能验证自己的配对，而不必重新扫描全语料。`doc-sync` 与 CI 运行的是无参数的全语料形式；限定范围的绿灯在 PR 层面永远不能替代它。\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门禁的限制很明确：**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 Markdown 结构；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；这部分约定由评审者把关，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## 范围与排除\n\n**范围**：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。\n\n有经评审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。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。\n\n**排除**（永不配对，门禁拒绝为它们建 `.zh.md` 或 `.i18n.yaml`）：\n\n- [cordis-api/inherited.md](../cordis-api/inherited.md)：该生成文档没有经评审的中文对侧，因此网站的两个 locale 都投影英文源文件。\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- `.agents/notes/archived/`：冻结的历史三文件配对。[`verify-archived-agent-notes`](../../scripts/verify-archived-agent-notes.ts) 校验其完整性和内容封存记录；翻译维护绝不能重写这些文件。\n\n**统一要求**：当前及今后纳入范围的每篇文档，合并时都必须构成完整的双语配对。[scripts/translation-pairing.manifest.json](../../scripts/translation-pairing.manifest.json) 只包含显式排除项；不存在逐文件推进清单、日期分界或 README 专用政策类别。\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、中文反向链接和普通撰写源的切换行（生成源按本文规则例外），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。提示词约定也有可执行实现：[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", - "content": "# Translation rules\n\nEnglish | [中文](translation-rules.zh.md)\n\nHow to translate between the two sides of a documentation pair in this repo. Both languages carry equal authority ([README.md](README.md)): a change is authored in either language, and that side is the source for that update — these rules govern producing or updating the counterpart. They bind humans and agents equally; the committed agent workflow that applies them is [.agents/skills/dsh-translate-docs](../../.agents/skills/dsh-translate-docs/SKILL.md). Rule levels follow RFC 2119 usage: **MUST** / **MUST NOT** are gate- or review-blocking; **SHOULD** needs a stated reason to deviate; **MAY** is discretionary.\n\n## Faithfulness\n\n- The counterpart *MUST* say what the authored side says — no added behavior, prerequisites, warnings, version claims, or examples, and no dropped ones. If the pair disagrees on substance, neither language wins by default: fix the side that is wrong, then bring the other along in the same change.\n- The counterpart *SHOULD* read as natural technical writing in its own language, not word-by-word gloss. Translate meaning, restructure sentences where the target grammar wants it, and keep the author's register — terse stays terse.\n- Do not translate the untranslatable: if a sentence resists natural rendering because it leans on an idiom of the source language, translate the idea, not the idiom.\n\n## Voice\n\n- The register is calibrated by [style-samples.md](style-samples.md) — human-approved gold pairs, one per document genre. The counterpart MUST match the target-language side of the nearest sample; where its voice and a prose voice rule disagree, the sample wins. Chinese targets use institutional technical Chinese; English targets use concise professional developer prose.\n- Write as a native technical author restating the content, not as a translator transposing sentences. Then verify against the source clause by clause: nothing added, nothing dropped — fluency never justifies losing a clause.\n- Give sentences an explicit actor when the target language would otherwise obscure it; for Chinese, replace vague passives or abstract subjects with the actual actor (系统、门禁、评审人).\n- Prefer established target-language engineering idiom over calques (误报／漏检 for false positive/negative, 执行红线 for enforcement frontier); localize metaphors instead of transplanting them, and unpack noun chains where the target language requires it.\n- Split long paragraphs by semantic unit — one idea per paragraph. Paragraph boundaries MAY differ from the source; the structural signature does not count paragraphs.\n- When translating into Chinese, category nouns use Chinese with a first-mention English annotation (实操手册（cookbook）); when translating into English, use the conventional English category name. Literal directory or file references stay code-formatted English.\n\n## Structure preservation\n\nThe pairing gate checks heading depths, fenced code blocks, table row and column counts, list kinds, ordered-list starts, list item counts, and link targets. Preserve the rest of the frame manually; the paired files MUST match one to one in:\n\n- heading hierarchy (same levels, same order — heading TEXT is translated),\n- list shape and numbering,\n- tables (same columns, same row order; header cells translated per terminology),\n- fenced code blocks — **byte-identical, including comments**; the pairing signature compares their info strings and contents, and ` ```ts ` blocks compile under `doc-typecheck`,\n- inline code spans (commands, flags, config keys, file paths, event names, API names, version numbers) — verbatim, never translated or reformatted,\n- links and anchors: every relative link MUST point at the same target in both files — by convention the `.md` path, not the `.zh.md` sibling — so links never dangle when one pair lands before its neighbors. The ONLY zh-specific link is the language switcher. Link TEXT is translated; the target is not.\n\nThe repo's Markdown conventions apply to `.zh.md` files unchanged: one physical line per paragraph (`verify-md-wrap`), resolving relative links (`verify-md-links`), exactly one trailing newline.\n\n## Terminology\n\n- [terminology.md](terminology.md) is the source of truth in both directions. Before translating, load it; every listed term MUST follow its row and its \"不要译作\" prohibitions. A Chinese target uses the \"中文\" column and its \"首次出现\" annotation; an English target uses the \"English\" column without adding a Chinese gloss.\n- For a Chinese target, an unlisted technical term MAY use an established rendering from a major Chinese-language OSS or vendor source (K8s/Vue/MDN Chinese docs, 微软简中风格指南, big-tech project docs), cited in the PR. Without such precedent it MUST stay in English and be listed under 「待定术语」(pending terms) with a suggested rendering.\n- For an English target, use the established English technical term. If the source term has no unambiguous established equivalent, preserve it with a short explanatory gloss and list it under pending terms. Neither direction may invent a rendering inline; a decided term enters [terminology.md](terminology.md) in the same PR or a follow-up.\n\n## Typography\n\nThese rules govern the Chinese side; the English side follows the repo's normal Markdown conventions (root `AGENTS.md`). The mixed-script rules below follow the cross-project consensus of the [MDN Simplified Chinese translation guide](https://github.com/mdn/translated-content/blob/main/docs/zh-cn/translation-guide.md), the [Kubernetes zh-cn localization guide](https://kubernetes.io/zh-cn/docs/contribute/localization_zh/), the [Vue.js Chinese translation conventions](https://github.com/vuejs-translations/docs-zh-cn/wiki/%E7%BF%BB%E8%AF%91%E9%A1%BB%E7%9F%A5), and [中文文案排版指北](https://github.com/sparanoid/chinese-copywriting-guidelines), which in turn ground in [W3C clreq](https://www.w3.org/TR/clreq/) and GB/T 15834—2011:\n\n- MUST put one half-width space between Chinese text and Latin words, and between Chinese text and numerals: `每个 plugin 注册 3 个 tool`。No space between a full-width punctuation mark and anything.\n- MUST use full-width (Chinese) punctuation in Chinese prose: `，。：；？！（）「」`. Half-width punctuation stays inside code spans, inside complete English sentences quoted as-is, and in numbers (`3.5`, `1,024`).\n- Chinese prose *SHOULD* prefer colons, periods, commas, or parentheses over em dashes. Keep an em dash only when no other punctuation preserves the sentence naturally.\n- Enumeration commas: a Chinese list of parallel items uses 顿号（、）, not commas.\n- MUST NOT use full-width digits or full-width Latin letters — `１２３` never, `123` always.\n- Proper nouns keep their canonical casing: GitHub, TypeScript, DeepSeek — never `github`/`Github` unless quoting code.\n- Second person is 你, not 您 (matches the Vue and Kubernetes Chinese conventions and this repo's direct voice).\n- Emphasis markers (`**bold**`, `*italic*`) stay on the same spans as the source; Chinese has no italics, so the rendered emphasis may look identical — do not substitute quotation marks or other decoration.\n\n## Quality bar\n\n- A pair is done when a bilingual engineer reading either file alone gets everything a reader of the other gets — same facts, same caveats, same tone — and nothing extra.\n- Before handing off, self-check the result against this file and re-read the counterpart ALONE, without the source side by side; awkward phrasing is easier to hear without the source anchoring you.\n- Run `pnpm run verify-translation-pairing` and the rest of `doc-sync` for records, switchers, heading depths, code blocks, table row and column counts, list kinds, ordered-list starts, list item counts, links, and repository Markdown rules. Manually verify list and table order, noncanonical list numbering, inline code, emphasis, meaning, terminology, and tone.\n\n## References\n\nAuthorities cited by these rules, for humans and agents who want the underlying reasoning:\n\n- [中文文案排版指北](https://github.com/sparanoid/chinese-copywriting-guidelines) — the de-facto community standard for mixed CJK/Latin spacing and punctuation.\n- [MDN zh-CN translation guide](https://github.com/mdn/translated-content/blob/main/docs/zh-cn/translation-guide.md) — an in-repo translation-rules file of the same shape as this one; spacing, punctuation, and glossary practice.\n- [Kubernetes zh-cn localization guide](https://kubernetes.io/zh-cn/docs/contribute/localization_zh/) — terminology-first-occurrence and punctuation practice from the largest zh localization team.\n- [Vue.js docs-zh-cn 翻译须知](https://github.com/vuejs-translations/docs-zh-cn/wiki/%E7%BF%BB%E8%AF%91%E9%A1%BB%E7%9F%A5) — per-term translate/keep decisions and tone.\n- [zh-style-guide](https://zh-style-guide.readthedocs.io) — a community Chinese technical-writing style guide whose rule-level taxonomy (and RFC 2119 keyword levels) this file borrows; aggregates GB/T 15834/15835, clreq, and vendor guides.\n- [W3C clreq](https://www.w3.org/TR/clreq/) and the [Microsoft Simplified Chinese style guide](https://learn.microsoft.com/en-us/globalization/reference/microsoft-style-guides) — the formal typographic and vendor-localization baselines.\n- GB/T 19682-2005《翻译服务译文质量要求》 — the national standard whose three base requirements (忠实原文、术语统一、行文通顺) this file's Faithfulness and Terminology sections operationalize.\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 every document in scope is maintained in English and Simplified Chinese. This page defines the pairing contract, enforcement gate, 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 ` 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 ` 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- **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 document in scope has a complete pair. README discovery is case-insensitive on the basename, so `missions/readme.md` is in scope alongside the other documentation roots.\n2. Every pair artifact that exists at all 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. Frozen Agent Notes under `.agents/notes/archived/` are outside this evolving gate; their dedicated verifier requires and seals the complete existing triplet instead.\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. It never fails; `missing` and `out-of-sync` rows identify violations that the normal check rejects.\n\n`pnpm run verify-translation-pairing ` checks just the named pairs — any of a pair's three files (or its bare stem) names it — so an update loop verifies its own pair in seconds instead of re-scanning the corpus. The no-argument corpus-wide form is what `doc-sync` and CI run; a scoped green never substitutes for it at PR level.\n\nThe practical rule this gate creates: **when a PR edits either side of a paired document, the same PR updates the counterpart directly in one terminology-guided pass and re-records the pair with `--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 and exclusions\n\n**Scope**: every non-vendor README, plus 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.\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 whose generators emit English only; a hand-written translation would go stale on regeneration.\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- `.agents/notes/archived/` — frozen historical triplets. [`verify-archived-agent-notes`](../../scripts/verify-archived-agent-notes.ts) validates their completeness and content seals; translation maintenance must never rewrite them.\n\n**Universal requirement**: every current or future document in scope must merge as a complete bilingual pair. [scripts/translation-pairing.manifest.json](../../scripts/translation-pairing.manifest.json) contains only explicit exclusions; there is no per-file rollout list, date cutoff, or README-specific policy class.\n\n## Division of labor\n\nRoutine counterparts are updated directly by the working agent in one shot and one pass after it loads [terminology.md](terminology.md); it does not invoke a translation skill, generate a briefing, run a separate translation-review pass, or delegate to a subagent. The extended [dsh-translate-docs](../../.agents/skills/dsh-translate-docs/SKILL.md) workflow retains those heavier mechanisms for explicit user invocation. 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": "# 翻译规则\n\n[English](translation-rules.md) | 中文\n\n本文规定：如何在本仓库文档配对的中英文两种语言之间进行翻译。两种语言同权（见 [README.md](README.md)）：每次变更可以用任一语言撰写，被编辑的一侧即为本次更新的源；本文的规则约束如何产出或更新对侧文件。这些规则对人类和 agent（智能体）同等生效；应用这些规则的仓库内置 agent 工作流是 [.agents/skills/dsh-translate-docs](../../.agents/skills/dsh-translate-docs/SKILL.md)。规则级别沿用 RFC 2119 的用法：**必须（MUST）** ／ **禁止（MUST NOT）** 会卡门禁或评审；**应当（SHOULD）** 偏离时要说明理由；**可以（MAY）** 自行裁量。\n\n## 忠实性\n\n- 对侧文件*必须*传达与撰写侧相同的内容：不添加行为、前置条件、警告、版本声明或示例，也不漏掉任何一项。如果两侧在实质内容上不一致，没有哪种语言默认获胜；请修正错误的一侧，并在同一个变更里同步更新另一侧。\n- 对侧文件读起来*应当*是其语言自然的技术文字，而非逐词对照的译文。请根据语义翻译，在目标语言语法需要时重组句子，并保持原作者的语域（比如：简练的保持简练）。\n- 不要翻译不可译的内容：如果一句话依赖源语言的习语、无法自然转换，请翻译它的意思，而非习语本身。\n\n## 行文\n\n- 语体以 [style-samples.md](style-samples.md) 为校准锚点。人工定稿的金标样例按文体各一组，译文必须参照文体最接近的样例，采用其中目标语言一侧的语体；如果样例与本文的行文规则冲突，以样例为准。译成中文时，采用规范的技术制度文；译成英文时，采用简洁、专业的开发者文档语体。\n- 以母语技术作者的身份重述内容，而不是逐句转写的译者。写完后逐句对照原文核验：不添加、不遗漏——流畅永远不是丢掉语义成分的理由。\n- 如果直译会让执行主体含糊，请明确写出实际执行者；译成中文时，应由「系统、门禁、评审人」等实际执行者作主语，避免含糊的被动句或抽象主语。\n- 优先采用目标语言中通行的工程表达，避免生硬直译（false positive/negative→误报／漏检、enforcement frontier→执行红线）；隐喻应自然改写，名词链则按目标语言的习惯拆开。\n- 长段按语义单元拆分，一段一件事。段落边界可以与原文不同；结构签名不比对段落数。\n- 翻译为中文时，类别名词使用中文并在首现括注英文（实操手册（cookbook））；翻译为英文时，使用通行的英文类别名。指目录或文件本身时保留代码体英文。\n\n## 结构保持\n\n配对门禁会检查标题深度、围栏代码块、表格行列数、列表类型、有序列表起始编号、列表项数量与链接目标；门禁未覆盖的结构仍需人工核对。两个配对文件必须在以下方面一一对应：\n\n- 标题层级（相同级别、相同顺序；标题的**文字**要翻译）；\n- 列表形态与编号；\n- 表格（相同的列、相同的行序；表头单元格按术语表翻译）；\n- 围栏代码块：**逐字节一致，包括注释**。配对签名比对信息字符串与内容，` ```ts ` 块还要通过 `doc-typecheck` 编译；\n- 行内代码（命令、flag、配置键、文件路径、事件名、API 名、版本号）：原样保留，从不翻译或重排；\n- 链接与锚点：每个相对链接在两个文件中必须指向相同的目标（按约定是 `.md` 路径而非 `.zh.md` 兄弟文件），这样即使某对文档先于相邻文件落地，链接也不会悬空。唯一的 zh 特有链接是语言切换行。链接**文字**翻译；链接目标不翻。\n\n本仓库的 Markdown 约定对 `.zh.md` 文件原样生效：一个段落一个物理行（`verify-md-wrap`）、相对链接必须可解析（`verify-md-links`）、文件末尾恰好一个换行。\n\n## 术语\n\n- [terminology.md](terminology.md) 是双向的术语真源。翻译前请先加载它；表内术语必须遵守对应行与「不要译作」禁项。译成中文时，采用「中文」列，并按「首次出现」列括注；译成英文时，采用「English」列，不加中文括注。\n- 译成中文时，术语表未收录的技术术语只有在主流中文 OSS 文档或厂商资料中已有通行译法时才可以翻译（K8s／Vue／MDN 中文文档、微软简中风格指南、大厂项目文档），并须在 PR 中注明出处；否则必须保留英文，并在 PR 描述的「待定术语」中给出建议译法。\n- 译成英文时，采用通行的英文技术术语。如果源术语没有明确的通行对应词，则保留原词、附上简短说明，并列入「待定术语」。两个方向都不得自行创造译法；确定后的术语须在同一个 PR 或后续 PR 中加入 [terminology.md](terminology.md)。\n\n## 排版\n\n本节规则约束中文一侧；英文一侧遵循仓库常规的 Markdown 约定（根 `AGENTS.md`）。以下中西文混排规则遵循 [MDN 简体中文翻译指南](https://github.com/mdn/translated-content/blob/main/docs/zh-cn/translation-guide.md)、[Kubernetes 中文本地化指南](https://kubernetes.io/zh-cn/docs/contribute/localization_zh/)、[Vue.js 中文翻译须知](https://github.com/vuejs-translations/docs-zh-cn/wiki/%E7%BF%BB%E8%AF%91%E9%A1%BB%E7%9F%A5) 与[中文文案排版指北](https://github.com/sparanoid/chinese-copywriting-guidelines)的跨项目共识，其根据是 [W3C clreq](https://www.w3.org/TR/clreq/) 与 GB/T 15834—2011：\n\n- 必须在中文与拉丁词之间、中文与数字之间各留一个半角空格：`每个 plugin 注册 3 个 tool`。全角标点与任何字符之间不加空格。\n- 中文行文必须使用全角（中文）标点：`，。：；？！（）「」`。半角标点保留在代码内、按原样引用的完整英文句子内、以及数字内（`3.5`、`1,024`）。\n- 中文行文*应当*优先使用冒号、句号、逗号或括号，尽量不用破折号；只有其他标点都无法自然表达时才保留破折号。\n- 顿号：中文的并列项之间使用顿号（、），而非逗号。\n- 禁止使用全角数字或全角拉丁字母：永远不写 `１２３`，永远写 `123`。\n- 专有名词保持规范大小写：GitHub、TypeScript、DeepSeek。除非引用代码，否则绝不写 `github`／`Github`。\n- 第二人称用「你」，不用「您」（与 Vue、Kubernetes 中文约定及本仓库的直接语气一致）。\n- 强调标记（`**加粗**`、`*斜体*`）落在与对侧相同的文字段上。中文没有斜体，渲染效果可能看不出差别，不要用引号或其他装饰替代。\n\n## 质量标准\n\n- 一对文档的完成标准：一位双语工程师只读其中任一文件，能获得与另一文件读者完全相同的信息（相同的事实、相同的告诫、相同的语气），并且没有任何多余的内容。\n- 交付前，请对照本文自查一遍，并**单独通读对侧文件**，不与源侧对照；不对照原文时，更容易察觉别扭的表达。\n- 请运行 `pnpm run verify-translation-pairing` 与 `doc-sync` 的其余门禁。这些门禁会检查一致性记录、切换行、标题深度、代码块、表格行列数、列表类型、有序列表起始编号、列表项数量、链接及仓库 Markdown 规则；列表与表格的顺序、非常规列表编号、行内代码、强调标记、语义、术语和语体仍需人工核对。\n\n## 参考资料\n\n本文各规则引用的权威出处，供想了解底层依据的人和 agent 查阅：\n\n- [中文文案排版指北](https://github.com/sparanoid/chinese-copywriting-guidelines)：中西文混排空格与标点的社区事实标准。\n- [MDN 简体中文翻译指南](https://github.com/mdn/translated-content/blob/main/docs/zh-cn/translation-guide.md)：与本文同形态的仓库内置翻译规则文件；空格、标点与术语表实践。\n- [Kubernetes 中文本地化指南](https://kubernetes.io/zh-cn/docs/contribute/localization_zh/)：最大的中文本地化团队的术语首现与标点实践。\n- [Vue.js docs-zh-cn 翻译须知](https://github.com/vuejs-translations/docs-zh-cn/wiki/%E7%BF%BB%E8%AF%91%E9%A1%BB%E7%9F%A5)：逐术语的译／留决策与语气。\n- [zh-style-guide](https://zh-style-guide.readthedocs.io)：社区中文技术文档写作规范，本文借用了它的规则级别分类体系（与 RFC 2119 关键词分级）；它聚合了 GB/T 15834/15835、clreq 与各厂商指南。\n- [W3C clreq](https://www.w3.org/TR/clreq/) 与[微软简体中文风格指南](https://learn.microsoft.com/en-us/globalization/reference/microsoft-style-guides)：排版学与厂商本地化的正式基线。\n- GB/T 19682-2005《翻译服务译文质量要求》：国家标准；本文「忠实性」与「术语」两节将其三项基本要求（忠实原文、术语统一、行文通顺）落实为可操作的规则。\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，因此范围内的每篇文档都以英文和简体中文维护。本页定义配对契约、强制门禁、范围与排除规则；[translation-rules.md](translation-rules.md) 定义如何翻译；[terminology.md](terminology.md) 是术语真源。agent 的日常工作遵循 [docs/AGENTS.md](../AGENTS.md) 中的轻量路径；扩展版 [.agents/skills/dsh-translate-docs](../../.agents/skills/dsh-translate-docs/SKILL.md) 工作流仅在用户显式调用时可用。\n\n## 配对契约\n\n- **两种语言同权。** 一篇文档可以先用任一语言撰写和评审（先写中文的 Agent Note 与先写英文的一样正当），另一侧由它翻译而来。两个文件谁也不高于谁；约束它们的是二者必须说同样的话。\n- **一对文档是三个同目录文件。** 英文 `foo.md`、中文 `foo.zh.md`，加一份一致性记录 `foo.i18n.yaml`，都在同一目录。不用语言目录，不用独立翻译仓库，不用中英混排的单文件。配对必须整体合并：PR（Pull Request）永远不会只带一种语言而缺其余两个文件。\n- **一致性记录。**`foo.i18n.yaml` 保存两侧文件在上一次被确认「说同样的话」时各自的完整 git blob hash：\n\n ```yaml\n foo.md: 3f786850e387550fdab836ed7e6dc881de23001b\n foo.zh.md: 89e6c98d92887913cadf06b2adb97f26cde4849b\n ```\n\n 用 blob hash 而不是 commit hash，这样同一个 PR 里改动的文件也能算出记录（`git hash-object foo.md`），一致性是纯内容比较。`--write` 会先把这些快照存入本地 Git 对象库再写下记录，未提交的工作树内容也不例外；它还会在内容寻址的 `refs/dsh/translation-pairing/snapshots/` ref 下固定每个不同的已存 blob，使垃圾回收无法让已记录的恢复指针失效。因此记录的 hash 能还原任一侧上次确认时的确切文本，所以失去同步的配对是「按被改一侧的 diff 最小化地修补另一侧」，从不整篇重译。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 ` 以能安全对齐的最窄粒度汇集这次更新，并由 `--apply` 在结构校验后拼接仅涉及围栏代码块的改动（[briefed-updates Agent Note](../../.agents/notes/implemented/process/2026-07-26-briefed-minimal-translation-updates.md)）。两侧对齐后，`pnpm run verify-translation-pairing --write ` 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- **语言切换行。** 两个文件在各自 H1 标题之后立即互链：英文文件带 `English | [中文](foo.zh.md)`，中文文件带 `[English](foo.md) | 中文`。\n- **结构与另一侧一一对应。** 标题深度与顺序、列表类型、有序列表起始编号、列表项数量、表格行列数、链接目标与逐字节一致的代码块在配对两侧一一对应；完整保持规则见 [translation-rules.md](translation-rules.md)。既有 Markdown 门禁对 `.zh.md` 文件原样生效（`verify-md-wrap`、`verify-md-links`）。\n\n## 门禁：verify-translation-pairing\n\n`pnpm run verify-translation-pairing`（`doc-sync`（文档同步门禁）的一环，贡献者会针对文档变更在本地运行，CI 则会完整运行）机械地强制执行这份契约：\n\n1. 范围内的每篇文档都有完整配对。发现 README 时，basename 不区分大小写，因此 `missions/readme.md` 与其他文档根一样属于范围。\n2. 任何已存在的配对产物都完整且一致：三个文件齐全、每一侧的当前 blob hash 等于记录值（改了任一侧而没重新确认配对就变红）、双方都带语言切换行、结构签名按序一致：标题深度、逐字节一致的代码块（信息字符串与内容）、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`。`.agents/notes/archived/` 下冻结的 Agent Note 不受这个持续演进的门禁约束；专用校验器会要求其现有的三个配对文件完整，并将其封存。\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）。它从不失败；其中 missing 与 out-of-sync 行指出普通检查会拒绝的违规。\n\n`pnpm run verify-translation-pairing ` 只检查被点名的配对——配对的三个文件中的任意一个（或其裸词干）都能点名它——因此更新循环几秒内就能验证自己的配对，而不必重新扫描全语料。`doc-sync` 与 CI 运行的是无参数的全语料形式；限定范围的绿灯在 PR 层面永远不能替代它。\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 在术语指导下直接一次完成对侧文件的更新，并用 `--write ` 重新记录配对**，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## 范围与排除\n\n**范围**：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。\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，其生成器只输出英文；手写译文会在重新生成时变得陈旧。\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- `.agents/notes/archived/`：冻结的历史三文件配对。[`verify-archived-agent-notes`](../../scripts/verify-archived-agent-notes.ts) 校验其完整性和内容封存记录；翻译维护绝不能重写这些文件。\n\n**统一要求**：当前及今后纳入范围的每篇文档，合并时都必须构成完整的双语配对。[scripts/translation-pairing.manifest.json](../../scripts/translation-pairing.manifest.json) 只包含显式排除项；不存在逐文件推进清单、日期分界或 README 专用政策类别。\n\n## 分工\n\n日常更新对侧文件时，负责处理的 agent 会先加载 [terminology.md](terminology.md)，再直接一次性更新且只处理一遍；它不会调用翻译 skill（技能）、生成简报、执行单独的翻译评审轮次，也不会委派给 subagent。扩展版 [dsh-translate-docs](../../.agents/skills/dsh-translate-docs/SKILL.md) 工作流保留这些较重的机制，仅供用户显式调用。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" +>>>>>>> 45777c7624 (test(snapshot): refresh translation prompt fixture) }, { "role": "user", + "content": "# Translation rules\n\nEnglish | [中文](translation-rules.zh.md)\n\nHow to translate between the two sides of a documentation pair in this repo. Both languages carry equal authority ([README.md](README.md)): a change is authored in either language, and that side is the source for that update — these rules govern producing or updating the counterpart. They bind humans and agents equally. Routine agent work translates the changed content directly in one terminology-guided pass; the extended [.agents/skills/dsh-translate-docs](../../.agents/skills/dsh-translate-docs/SKILL.md) workflow runs only when the user explicitly invokes it. Rule levels follow RFC 2119 usage: **MUST** / **MUST NOT** are gate- or review-blocking; **SHOULD** needs a stated reason to deviate; **MAY** is discretionary.\n\n## Faithfulness\n\n- The counterpart *MUST* say what the authored side says — no added behavior, prerequisites, warnings, version claims, or examples, and no dropped ones. If the pair disagrees on substance, neither language wins by default: fix the side that is wrong, then bring the other along in the same change.\n- The counterpart *SHOULD* read as natural technical writing in its own language, not word-by-word gloss. Translate meaning, restructure sentences where the target grammar wants it, and keep the author's register — terse stays terse.\n- Do not translate the untranslatable: if a sentence resists natural rendering because it leans on an idiom of the source language, translate the idea, not the idiom.\n\n## Voice\n\n- The register is calibrated by [style-samples.md](style-samples.md) — human-approved gold pairs, one per document genre. The counterpart MUST match the target-language side of the nearest sample; where its voice and a prose voice rule disagree, the sample wins. Chinese targets use institutional technical Chinese; English targets use concise professional developer prose.\n- Write as a native technical author restating the content, not as a translator transposing sentences, while preserving every source clause: nothing added, nothing dropped — fluency never justifies losing a clause.\n- Give sentences an explicit actor when the target language would otherwise obscure it; for Chinese, replace vague passives or abstract subjects with the actual actor (系统、门禁、评审人).\n- Prefer established target-language engineering idiom over calques (误报／漏检 for false positive/negative, 执行红线 for enforcement frontier); localize metaphors instead of transplanting them, and unpack noun chains where the target language requires it.\n- Split long paragraphs by semantic unit — one idea per paragraph. Paragraph boundaries MAY differ from the source; the structural signature does not count paragraphs.\n- When translating into Chinese, category nouns use Chinese with a first-mention English annotation (实操手册（cookbook）); when translating into English, use the conventional English category name. Literal directory or file references stay code-formatted English.\n\n## Structure preservation\n\nThe pairing gate checks heading depths, fenced code blocks, table row and column counts, list kinds, ordered-list starts, list item counts, and link targets. Preserve the rest of the frame manually; the paired files MUST match one to one in:\n\n- heading hierarchy (same levels, same order — heading TEXT is translated),\n- list shape and numbering,\n- tables (same columns, same row order; header cells translated per terminology),\n- fenced code blocks — **byte-identical, including comments**; the pairing signature compares their info strings and contents, and ` ```ts ` blocks compile under `doc-typecheck`,\n- inline code spans (commands, flags, config keys, file paths, event names, API names, version numbers) — verbatim, never translated or reformatted,\n- links and anchors: every relative link MUST point at the same target in both files — by convention the `.md` path, not the `.zh.md` sibling — so links never dangle when one pair lands before its neighbors. The ONLY zh-specific link is the language switcher. Link TEXT is translated; the target is not.\n\nThe repo's Markdown conventions apply to `.zh.md` files unchanged: one physical line per paragraph (`verify-md-wrap`), resolving relative links (`verify-md-links`), exactly one trailing newline.\n\n## Terminology\n\n- [terminology.md](terminology.md) is the source of truth in both directions. Before translating, load it; every listed term MUST follow its row and its \"不要译作\" prohibitions. A Chinese target uses the \"中文\" column and its \"首次出现\" annotation; an English target uses the \"English\" column without adding a Chinese gloss.\n- For a Chinese target, an unlisted technical term MAY use an established rendering from a major Chinese-language OSS or vendor source (K8s/Vue/MDN Chinese docs, 微软简中风格指南, big-tech project docs), cited in the PR. Without such precedent it MUST stay in English and be listed under 「待定术语」(pending terms) with a suggested rendering.\n- For an English target, use the established English technical term. If the source term has no unambiguous established equivalent, preserve it with a short explanatory gloss and list it under pending terms. Neither direction may invent a rendering inline; a decided term enters [terminology.md](terminology.md) in the same PR or a follow-up.\n\n## Typography\n\nThese rules govern the Chinese side; the English side follows the repo's normal Markdown conventions (root `AGENTS.md`). The mixed-script rules below follow the cross-project consensus of the [MDN Simplified Chinese translation guide](https://github.com/mdn/translated-content/blob/main/docs/zh-cn/translation-guide.md), the [Kubernetes zh-cn localization guide](https://kubernetes.io/zh-cn/docs/contribute/localization_zh/), the [Vue.js Chinese translation conventions](https://github.com/vuejs-translations/docs-zh-cn/wiki/%E7%BF%BB%E8%AF%91%E9%A1%BB%E7%9F%A5), and [中文文案排版指北](https://github.com/sparanoid/chinese-copywriting-guidelines), which in turn ground in [W3C clreq](https://www.w3.org/TR/clreq/) and GB/T 15834—2011:\n\n- MUST put one half-width space between Chinese text and Latin words, and between Chinese text and numerals: `每个 plugin 注册 3 个 tool`。No space between a full-width punctuation mark and anything.\n- MUST use full-width (Chinese) punctuation in Chinese prose: `，。：；？！（）「」`. Half-width punctuation stays inside code spans, inside complete English sentences quoted as-is, and in numbers (`3.5`, `1,024`).\n- Chinese prose *SHOULD* prefer colons, periods, commas, or parentheses over em dashes. Keep an em dash only when no other punctuation preserves the sentence naturally.\n- Enumeration commas: a Chinese list of parallel items uses 顿号（、）, not commas.\n- MUST NOT use full-width digits or full-width Latin letters — `１２３` never, `123` always.\n- Proper nouns keep their canonical casing: GitHub, TypeScript, DeepSeek — never `github`/`Github` unless quoting code.\n- Second person is 你, not 您 (matches the Vue and Kubernetes Chinese conventions and this repo's direct voice).\n- Emphasis markers (`**bold**`, `*italic*`) stay on the same spans as the source; Chinese has no italics, so the rendered emphasis may look identical — do not substitute quotation marks or other decoration.\n\n## Quality bar\n\n- A pair is done when a bilingual engineer reading either file alone gets everything a reader of the other gets — same facts, same caveats, same tone — and nothing extra.\n- Run `pnpm run verify-translation-pairing` and the rest of `doc-sync` for records, switchers, heading depths, code blocks, table row and column counts, list kinds, ordered-list starts, list item counts, links, and repository Markdown rules. Human review owns list and table order, noncanonical list numbering, inline code, emphasis, meaning, terminology, and tone.\n\n## References\n\nAuthorities cited by these rules, for humans and agents who want the underlying reasoning:\n\n- [中文文案排版指北](https://github.com/sparanoid/chinese-copywriting-guidelines) — the de-facto community standard for mixed CJK/Latin spacing and punctuation.\n- [MDN zh-CN translation guide](https://github.com/mdn/translated-content/blob/main/docs/zh-cn/translation-guide.md) — an in-repo translation-rules file of the same shape as this one; spacing, punctuation, and glossary practice.\n- [Kubernetes zh-cn localization guide](https://kubernetes.io/zh-cn/docs/contribute/localization_zh/) — terminology-first-occurrence and punctuation practice from the largest zh localization team.\n- [Vue.js docs-zh-cn 翻译须知](https://github.com/vuejs-translations/docs-zh-cn/wiki/%E7%BF%BB%E8%AF%91%E9%A1%BB%E7%9F%A5) — per-term translate/keep decisions and tone.\n- [zh-style-guide](https://zh-style-guide.readthedocs.io) — a community Chinese technical-writing style guide whose rule-level taxonomy (and RFC 2119 keyword levels) this file borrows; aggregates GB/T 15834/15835, clreq, and vendor guides.\n- [W3C clreq](https://www.w3.org/TR/clreq/) and the [Microsoft Simplified Chinese style guide](https://learn.microsoft.com/en-us/globalization/reference/microsoft-style-guides) — the formal typographic and vendor-localization baselines.\n- GB/T 19682-2005《翻译服务译文质量要求》 — the national standard whose three base requirements (忠实原文、术语统一、行文通顺) this file's Faithfulness and Terminology sections operationalize.\n" + }, + { + "role": "assistant", + "content": "# 翻译规则\n\n[English](translation-rules.md) | 中文\n\n本文规定：如何在本仓库文档配对的中英文两种语言之间进行翻译。两种语言同权（见 [README.md](README.md)）：每次变更可以用任一语言撰写，被编辑的一侧即为本次更新的源；本文的规则约束如何产出或更新对侧文件。这些规则对人类和 agent（智能体）同等生效。日常工作中，agent 会在术语指导下直接一次完成有改动内容的翻译；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运行。规则级别沿用 RFC 2119 的用法：**必须（MUST）** ／ **禁止（MUST NOT）** 会卡门禁或评审；**应当（SHOULD）** 偏离时要说明理由；**可以（MAY）** 自行裁量。\n\n## 忠实性\n\n- 对侧文件*必须*传达与撰写侧相同的内容：不添加行为、前置条件、警告、版本声明或示例，也不漏掉任何一项。如果两侧在实质内容上不一致，没有哪种语言默认获胜；请修正错误的一侧，并在同一个变更里同步更新另一侧。\n- 对侧文件读起来*应当*是其语言自然的技术文字，而非逐词对照的译文。请根据语义翻译，在目标语言语法需要时重组句子，并保持原作者的语域（比如：简练的保持简练）。\n- 不要翻译不可译的内容：如果一句话依赖源语言的习语、无法自然转换，请翻译它的意思，而非习语本身。\n\n## 行文\n\n- 语体以 [style-samples.md](style-samples.md) 为校准锚点。人工定稿的金标样例按文体各一组，译文必须参照文体最接近的样例，采用其中目标语言一侧的语体；如果样例与本文的行文规则冲突，以样例为准。译成中文时，采用规范的技术制度文；译成英文时，采用简洁、专业的开发者文档语体。\n- 以母语技术作者的身份重述内容，而不是以译者身份逐句转写，同时保留原文的每个语义成分：不添加、不遗漏——流畅永远不是丢掉语义成分的理由。\n- 如果直译会让执行主体含糊，请明确写出实际执行者；译成中文时，应由「系统、门禁、评审人」等实际执行者作主语，避免含糊的被动句或抽象主语。\n- 优先采用目标语言中通行的工程表达，避免生硬直译（false positive/negative→误报／漏检、enforcement frontier→执行红线）；隐喻应自然改写，名词链则按目标语言的习惯拆开。\n- 长段按语义单元拆分，一段一件事。段落边界可以与原文不同；结构签名不比对段落数。\n- 翻译为中文时，类别名词使用中文并在首现括注英文（实操手册（cookbook））；翻译为英文时，使用通行的英文类别名。指目录或文件本身时保留代码体英文。\n\n## 结构保持\n\n配对门禁会检查标题深度、围栏代码块、表格行列数、列表类型、有序列表起始编号、列表项数量与链接目标；门禁未覆盖的结构仍需人工核对。两个配对文件必须在以下方面一一对应：\n\n- 标题层级（相同级别、相同顺序；标题的**文字**要翻译）；\n- 列表形态与编号；\n- 表格（相同的列、相同的行序；表头单元格按术语表翻译）；\n- 围栏代码块：**逐字节一致，包括注释**。配对签名比对信息字符串与内容，` ```ts ` 块还要通过 `doc-typecheck` 编译；\n- 行内代码（命令、flag、配置键、文件路径、事件名、API 名、版本号）：原样保留，从不翻译或重排；\n- 链接与锚点：每个相对链接在两个文件中必须指向相同的目标（按约定是 `.md` 路径而非 `.zh.md` 兄弟文件），这样即使某对文档先于相邻文件落地，链接也不会悬空。唯一的 zh 特有链接是语言切换行。链接**文字**翻译；链接目标不翻。\n\n本仓库的 Markdown 约定对 `.zh.md` 文件原样生效：一个段落一个物理行（`verify-md-wrap`）、相对链接必须可解析（`verify-md-links`）、文件末尾恰好一个换行。\n\n## 术语\n\n- [terminology.md](terminology.md) 是双向的术语真源。翻译前请先加载它；表内术语必须遵守对应行与「不要译作」禁项。译成中文时，采用「中文」列，并按「首次出现」列括注；译成英文时，采用「English」列，不加中文括注。\n- 译成中文时，术语表未收录的技术术语只有在主流中文 OSS 文档或厂商资料中已有通行译法时才可以翻译（K8s／Vue／MDN 中文文档、微软简中风格指南、大厂项目文档），并须在 PR 中注明出处；否则必须保留英文，并在 PR 描述的「待定术语」中给出建议译法。\n- 译成英文时，采用通行的英文技术术语。如果源术语没有明确的通行对应词，则保留原词、附上简短说明，并列入「待定术语」。两个方向都不得自行创造译法；确定后的术语须在同一个 PR 或后续 PR 中加入 [terminology.md](terminology.md)。\n\n## 排版\n\n本节规则约束中文一侧；英文一侧遵循仓库常规的 Markdown 约定（根 `AGENTS.md`）。以下中西文混排规则遵循 [MDN 简体中文翻译指南](https://github.com/mdn/translated-content/blob/main/docs/zh-cn/translation-guide.md)、[Kubernetes 中文本地化指南](https://kubernetes.io/zh-cn/docs/contribute/localization_zh/)、[Vue.js 中文翻译须知](https://github.com/vuejs-translations/docs-zh-cn/wiki/%E7%BF%BB%E8%AF%91%E9%A1%BB%E7%9F%A5) 与[中文文案排版指北](https://github.com/sparanoid/chinese-copywriting-guidelines)的跨项目共识，其根据是 [W3C clreq](https://www.w3.org/TR/clreq/) 与 GB/T 15834—2011：\n\n- 必须在中文与拉丁词之间、中文与数字之间各留一个半角空格：`每个 plugin 注册 3 个 tool`。全角标点与任何字符之间不加空格。\n- 中文行文必须使用全角（中文）标点：`，。：；？！（）「」`。半角标点保留在代码内、按原样引用的完整英文句子内、以及数字内（`3.5`、`1,024`）。\n- 中文行文*应当*优先使用冒号、句号、逗号或括号，尽量不用破折号；只有其他标点都无法自然表达时才保留破折号。\n- 顿号：中文的并列项之间使用顿号（、），而非逗号。\n- 禁止使用全角数字或全角拉丁字母：永远不写 `１２３`，永远写 `123`。\n- 专有名词保持规范大小写：GitHub、TypeScript、DeepSeek。除非引用代码，否则绝不写 `github`／`Github`。\n- 第二人称用「你」，不用「您」（与 Vue、Kubernetes 中文约定及本仓库的直接语气一致）。\n- 强调标记（`**加粗**`、`*斜体*`）落在与对侧相同的文字段上。中文没有斜体，渲染效果可能看不出差别，不要用引号或其他装饰替代。\n\n## 质量标准\n\n- 一对文档的完成标准：一位双语工程师只读其中任一文件，能获得与另一文件读者完全相同的信息（相同的事实、相同的告诫、相同的语气），并且没有任何多余的内容。\n- 请运行 `pnpm run verify-translation-pairing` 与 `doc-sync` 的其余门禁。这些门禁会检查一致性记录、切换行、标题深度、代码块、表格行列数、列表类型、有序列表起始编号、列表项数量、链接及仓库 Markdown 规则；列表与表格的顺序、非常规列表编号、行内代码、强调标记、语义、术语和语体则由人工评审负责。\n\n## 参考资料\n\n本文各规则引用的权威出处，供想了解底层依据的人和 agent 查阅：\n\n- [中文文案排版指北](https://github.com/sparanoid/chinese-copywriting-guidelines)：中西文混排空格与标点的社区事实标准。\n- [MDN 简体中文翻译指南](https://github.com/mdn/translated-content/blob/main/docs/zh-cn/translation-guide.md)：与本文同形态的仓库内置翻译规则文件；空格、标点与术语表实践。\n- [Kubernetes 中文本地化指南](https://kubernetes.io/zh-cn/docs/contribute/localization_zh/)：最大的中文本地化团队的术语首现与标点实践。\n- [Vue.js docs-zh-cn 翻译须知](https://github.com/vuejs-translations/docs-zh-cn/wiki/%E7%BF%BB%E8%AF%91%E9%A1%BB%E7%9F%A5)：逐术语的译／留决策与语气。\n- [zh-style-guide](https://zh-style-guide.readthedocs.io)：社区中文技术文档写作规范，本文借用了它的规则级别分类体系（与 RFC 2119 关键词分级）；它聚合了 GB/T 15834/15835、clreq 与各厂商指南。\n- [W3C clreq](https://www.w3.org/TR/clreq/) 与[微软简体中文风格指南](https://learn.microsoft.com/en-us/globalization/reference/microsoft-style-guides)：排版学与厂商本地化的正式基线。\n- GB/T 19682-2005《翻译服务译文质量要求》：国家标准；本文「忠实性」与「术语」两节将其三项基本要求（忠实原文、术语统一、行文通顺）落实为可操作的规则。\n" + }, + { + "role": "user", +<<<<<<< HEAD "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 `, 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. [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.** 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** — `.zh.md` files would carry an HTML comment recording the English source's blob hash, and translation would flow EN → ZH only. Rejected: 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 English documents remain derived from source and freshness-gated by their owning generators. A generated page with a reviewed Chinese counterpart participates in the three-file pairing workflow, with one structural exception: the generated English source has no language switcher because adding one would make the generator stale, while the Chinese counterpart links back to it. Generated pages without a reviewed counterpart remain explicit exclusions and use an English website projection.\n- The exclusions-only manifest makes every current and future in-scope document mandatory through the same path. There is no explicit requirement, cutoff, or class entry that can fall outside discovery while appearing enforced.\n- The recorded hashes double as the update tool: [gen-translation-brief](2026-07-26-briefed-minimal-translation-updates.md) recovers either side's last-confirmed text from them and assembles the minimal-update briefing, 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本仓库的文档语料会被公司内外的人和 agent（智能体）以中英两种语言阅读。在没有机制的情况下纯靠手工维护第二语言，正是译文腐烂的根源：一侧持续演进，另一侧默默失实，而没有门禁会注意到。对于这类不变式，本仓库一贯的做法是将其编码为机械检查（见[质量门禁](2026-06-11-quality-gates.md)与 [doc-sync 强制](../../archived/process/2026-06-11-doc-sync-enforcement.md)），因此双语政策随附一道门禁一起交付。\n\n## 决策\n\n- **配对兄弟文件，两种语言同权。** 一对文档由三个兄弟文件组成：英文 `foo.md`、中文 `foo.zh.md`，以及一份一致性记录 `foo.i18n.yaml`。没有哪种语言是正典：一篇文档可以先用中文撰写和评审、之后再译成英文，反之亦可；约束配对的是：两侧必须表达相同的内容，且配对整体合并（两种语言加记录，绝不单独落一侧）。政策见 [docs/i18n/README.md](../../../../docs/i18n/README.md)；翻译规则见 [docs/i18n/translation-rules.md](../../../../docs/i18n/translation-rules.md)；术语真源见 [docs/i18n/terminology.md](../../../../docs/i18n/terminology.md)。\n- **伴随记录保存两侧 blob hash，使一致性可检查。** `foo.i18n.yaml` 保存两侧文件在上一次确认一致时各自的完整 git blob hash。此后修改了任一侧而未重新确认配对，都能被机械检测出来（纯内容比较，无需查询历史），而且同一个 PR（Pull Request）内改动的文件也能计算出 hash，commit hash 式的记录做不到这一点。重新记录（`verify-translation-pairing --write `，要求点名所确认的配对；批量重新记录是显式的 `--write --all`）会产生一份可评审的 yaml diff：确认一致在 PR 中是一个显式、可见的动作。\n- **`verify-translation-pairing` 加入 `doc-sync`。** 门禁（[scripts/verify-translation-pairing.ts](../../../../scripts/verify-translation-pairing.ts)）强制执行以下规则：每个已发现且未排除的源文档都有完整配对；每个现有配对都完整（三个文件齐全）且一致（两个 hash 匹配、中文侧和所有普通撰写的英文源都带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。[scripts/translation-pairing.manifest.json](../../../../scripts/translation-pairing.manifest.json) 只包含显式排除项，因此任何要求都无法绕过发现流程而接受较弱的检查。只有当 `.zh.md` 围栏序列与其无后缀兄弟文件拥有顺序相同、正文按字节一致的同一组受跟踪围栏时，面向源码的代码门禁才会将其作为派生内容消费；不完整、顺序变更、重分类或已改动的序列仍会独立受检，因此由其所属的代码门禁或配对门禁报告不匹配。\n- **全语料统一要求。** 范围内的每篇文档从创建起就必须有完整配对；政策没有逐文件推进状态、日期分界或 README 专用类别。README 发现会覆盖 vendor 源码、依赖目录与被忽略的构建产物目录之外所有文件名不区分大小写匹配 README 的文件，包括今后新增的顶层目录。发布到文档站的配对使用 `pairedPages()`，由根 locale 投影 `.zh.md`，由 `/en/` 投影 `.md`；仅创建对侧文件并不会发布它。\n- **配对记录是元数据，而不是 Cordis Loader 配置。** Cordis 配置发现会接受实际的 `.cordis.yml` 和 `.cordis.yaml` 文件，同时排除 `*.i18n.yaml`，即使文档名中包含 `cordis` 也不例外。这样既能继续校验可执行的 Loader 配置项，又不会把翻译 hash 当作配置来解析。\n- **翻译是 agent 的工作，由人评审。** 仓库内置的工作流是 [.agents/skills/dsh-translate-docs](../../../skills/dsh-translate-docs/SKILL.md)，与 [dsh-code-review](../../../skills/dsh-code-review/SKILL.md) 模式相同：skill（技能）承载工作流，并将文档作为真源。该 skill 要求编排 agent 把翻译写作委派给 subagent。\n\n## 验证\n\n验证约定分别覆盖每个边界。`verify-translation-pairing` 固定配对完整性、hash、切换行和结构；[`project-doc-site.spec.ts`](../../../../scripts/project-doc-site.spec.ts) 固定已发布配对按 locale 选择对应源文件；[`cordis-config-files.spec.ts`](../../../../scripts/cordis-config-files.spec.ts) 固定 Loader YAML 的发现以及翻译记录的排除；[翻译提示词可运行快照](../../../../scripts/translation-prompt.snapshot.ts)则固定渲染后的系统消息、五对经评审的示例、源请求和响应消费结果。这些检查共同使配对漂移、发布漂移、配置误分类和模型可见提示词漂移都可在评审中看见。\n\n## 曾考虑的替代方案\n\n- **英文为正典源、指纹放在译文内**：`.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。否决：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- 生成的英文文档仍由源码派生，并由各自的生成器实施新鲜度门禁。有经评审中文对侧的生成页面遵循三文件配对工作流，但有一项结构例外：生成的英文源文件不含语言切换行，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。没有经评审对侧的生成页面保留为显式排除项，并在网站上投影英文。\n- 只含排除项的 manifest 通过同一路径，要求当前及今后纳入范围的每篇文档都必须配对。不存在显式要求、分界或类别条目可以落在发现范围之外，却看似已经强制执行。\n- 记录的 hash 兼作更新工具：[gen-translation-brief](2026-07-26-briefed-minimal-translation-updates.md) 会从中还原任一侧上次确认的文本并组装最小更新简报，因此这套机制从不强迫整篇重译。\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 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 `, 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, switcher links both ways, structural signatures identical); and excluded generated, instruction, or bilingual-by-construction files stay unpaired. [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` 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 an agent-run workflow 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- The exclusions-only manifest makes every current and future in-scope document mandatory through the same path. There is no explicit requirement, cutoff, or class entry that can fall outside discovery while appearing enforced.\n- The recorded hashes double as the update tool: [gen-translation-brief](2026-07-26-briefed-minimal-translation-updates.md) recovers either side's last-confirmed text from them and assembles the minimal-update briefing, 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本仓库的文档语料会被公司内外的人和 agent（智能体）以中英两种语言阅读。在没有机制的情况下纯靠手工维护第二语言，正是译文腐烂的根源：一侧持续演进，另一侧默默失实，而没有门禁会注意到。对于这类不变式，本仓库一贯的做法是将其编码为机械检查（见[质量门禁](2026-06-11-quality-gates.md)与 [doc-sync 强制](../../archived/process/2026-06-11-doc-sync-enforcement.md)），因此双语政策随附一道门禁一起交付。\n\n## 决策\n\n- **配对兄弟文件，两种语言同权。** 一对文档由三个兄弟文件组成：英文 `foo.md`、中文 `foo.zh.md`，以及一份一致性记录 `foo.i18n.yaml`。没有哪种语言是正典：一篇文档可以先用中文撰写和评审、之后再译成英文，反之亦可；约束配对的是：两侧必须表达相同的内容，且配对整体合并（两种语言加记录，绝不单独落一侧）。政策见 [docs/i18n/README.md](../../../../docs/i18n/README.md)；翻译规则见 [docs/i18n/translation-rules.md](../../../../docs/i18n/translation-rules.md)；术语真源见 [docs/i18n/terminology.md](../../../../docs/i18n/terminology.md)。\n- **伴随记录保存两侧 blob hash，使一致性可检查。** `foo.i18n.yaml` 保存两侧文件在上一次确认一致时各自的完整 git blob hash。此后修改了任一侧而未重新确认配对，都能被机械检测出来（纯内容比较，无需查询历史），而且同一个 PR（Pull Request）内改动的文件也能计算出 hash，commit hash 式的记录做不到这一点。重新记录（`verify-translation-pairing --write `，要求点名所确认的配对；批量重新记录是显式的 `--write --all`）会产生一份可评审的 yaml diff：确认一致在 PR 中是一个显式、可见的动作。\n- **`verify-translation-pairing` 加入 `doc-sync`。** 门禁（[scripts/verify-translation-pairing.ts](../../../../scripts/verify-translation-pairing.ts)）强制执行以下规则：每个已发现且未排除的源文档都有完整配对；每个现有配对都完整（三个文件齐全）且一致（两个 hash 匹配、切换行双向互链、结构签名一致）；被排除的生成文档、指令文档或本身即双语的文档不得配对。[scripts/translation-pairing.manifest.json](../../../../scripts/translation-pairing.manifest.json) 只包含显式排除项，因此任何要求都无法绕过发现流程而接受较弱的检查。只有当 `.zh.md` 围栏序列与其无后缀兄弟文件拥有顺序相同、正文按字节一致的同一组受跟踪围栏时，面向源码的代码门禁才会将其作为派生内容消费；不完整、顺序变更、重分类或已改动的序列仍会独立受检，因此由其所属的代码门禁或配对门禁报告不匹配。\n- **全语料统一要求。** 范围内的每篇文档从创建起就必须有完整配对；政策没有逐文件推进状态、日期分界或 README 专用类别。README 发现会覆盖 vendor 源码、依赖目录与被忽略的构建产物目录之外所有文件名不区分大小写匹配 README 的文件，包括今后新增的顶层目录。发布到文档站的配对使用 `pairedPages()`，由根 locale 投影 `.zh.md`，由 `/en/` 投影 `.md`；仅创建对侧文件并不会发布它。\n- **配对记录是元数据，而不是 Cordis Loader 配置。** Cordis 配置发现会接受实际的 `.cordis.yml` 和 `.cordis.yaml` 文件，同时排除 `*.i18n.yaml`，即使文档名中包含 `cordis` 也不例外。这样既能继续校验可执行的 Loader 配置项，又不会把翻译 hash 当作配置来解析。\n- **翻译是 agent 的工作，由人评审。** 常规改动采用由[轻量翻译决策](2026-08-08-lightweight-routine-documentation-translation.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，再加一个由 agent 运行的工作流替代 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- 只含排除项的 manifest 通过同一路径，要求当前及今后纳入范围的每篇文档都必须配对。不存在显式要求、分界或类别条目可以落在发现范围之外，却看似已经强制执行。\n- 记录的 hash 兼作更新工具：[gen-translation-brief](2026-07-26-briefed-minimal-translation-updates.md) 会从中还原任一侧上次确认的文本并组装最小更新简报，因此这套机制从不强迫整篇重译。\n" +>>>>>>> 45777c7624 (test(snapshot): refresh translation prompt fixture) }, { "role": "user",