docs(i18n): translation capability — style samples, voice rules, two-pass skill

Human-annotated gold pairs land as docs/i18n/style-samples.md (bilingual
by construction, excluded from pairing) and outrank prose tone rules.
translation-rules gains a Voice section; shape stays gate-owned so the
writer optimizes for natural Chinese. The skill's translate step becomes
two passes: native-author writing, then clause-level fidelity check.
Terminology rulings: hash -> 哈希 (blob 哈希/提交哈希), HMR and fiber
confirmed as tabled.

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: bbf292893fc1ca634f3437a8ea0bae855c5712cb
-README.zh.md: 29f7408d1e0511ebf5a708507e0ea93aeb7e9ff3
+README.md: f28676b7d555aca30d8b5b21eba9fb4222949763
+README.zh.md: 5353a8ba04288cf72defa30b5896731b3d419b69

docs/i18n/README.md

@@ -41,7 +41,7 @@ The gate's limit, stated plainly: **a green gate means the pair was confirmed co
 
 - `docs/cordis-catalog/`, `docs/tool-catalog/`, `docs/module-graph.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.
 - `docs/AGENTS.md` — agent instructions, maintained in English only like the root `AGENTS.md`.
-- `docs/i18n/terminology.md` — the terminology table is itself bilingual by construction.
+- `docs/i18n/terminology.md` and [style-samples.md](style-samples.md) — both are bilingual by construction.
 
 **Rollout**: new documents don't wait for a batch — a date-named document (`yyyy-mm-dd-*.md`, i.e. an RFC) dated on or after the manifest's `requiredSince` cutoff must merge with its pair, so everything new is bilingual from birth. Files dated before the cutoff are the grandfathered backlog by definition — including files created on the cutoff's eve — and a document's filename date is its first-proposed date per the RFC convention, so backdating past the cutoff is a review-visible violation, not a loophole. For the back-catalog, the `required` list in the manifest is the enforcement frontier, not the goal. The goal is full bilingual coverage of the scope. Pairs land in reviewable batches (core entry docs, cookbook, RFCs, postmortems, …); each merged batch adds its files to `required`, so the gate ratchets forward and never regresses. Documents not yet in `required` are backlog — visible in `--list` — but any pair that already exists is held to the full contract regardless of the list. Pairing a document is a commitment: every later edit to either side must carry the counterpart along, so grow the frontier at the pace translation review is actually resourced, not ahead of it.
 

docs/i18n/README.zh.md

@@ -41,7 +41,7 @@
 
 - `docs/cordis-catalog/`、`docs/tool-catalog/`、`docs/module-graph.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。
 - `docs/AGENTS.md`——agent 指令，与根 `AGENTS.md` 一样只以英文维护。
-- `docs/i18n/terminology.md`——术语表本身即是双语构造。
+- `docs/i18n/terminology.md` 与 [style-samples.md](style-samples.md)——二者本身即为中英对照文档。
 
 **推进**：新文档不等批次——文件名带日期的文档（`yyyy-mm-dd-*.md`，即 RFC）日期在 manifest 的 `requiredSince` 当天或之后，就必须连同配对一起合入，新增的一切生来即是双语。日期早于 cutoff 的文件按定义属于被豁免的存量——包括 cutoff 前夜创建的文件——而文件名日期按 RFC 惯例即首次提出日期，倒填日期绕过 cutoff 是评审可见的违规，不是漏洞。对于存量文档，manifest 中的 `required` 列表是强制边界，不是目标。目标是范围内的全量双语覆盖。配对按可评审的批次落地（核心入口文档、cookbook、RFC、postmortem……）；每个批次合入后把其文件加进 `required`，门禁只进不退。尚未进入 `required` 的文档是 backlog——在 `--list` 中可见——但任何已存在的配对无论在不在清单里都按完整契约检查。给一篇文档配对是一份承诺：此后对任一侧的每次修改都必须带上另一侧，所以边界的扩张要跟上翻译评审的实际投入节奏，不要抢在前面。
 

docs/i18n/style-samples.md

@@ -0,0 +1,61 @@
+# 翻译语体样例（style samples）
+
+本文件是翻译语体的校准锚点：每组样例是一段英文原文与一段人工定稿的中文译文，覆盖本仓库文档的主要文体。**译文的语体以这些样例为准**——它们的效力高于任何对语气的文字描述。翻译或评审时对照最接近的文体样例；样例与规则冲突时，样例胜出。本文件中英对照、自成双语，不参与配对（见 [README.md](README.md) 排除清单）。
+
+维护方式：人工评审校准出新的金标段落后追加到对应文体；样例只增不改，改动需评审人签字（PR 评审即签字）。
+
+## ① 架构叙述
+
+> This document describes the architecture of the DeepSeek Harness — the foundation of **DeepSeek Code**. The governing principle, from the microkernel design discussion: **everything is a plugin**. The core is deliberately tiny — a handful of abstract services plus one concrete loop plugin (`dsh-agent-loop`) — and every product feature is a plugin against the extension surface described here, without modifying the loop.
+
+本文介绍 DeepSeek Harness 整体架构，它是 **DeepSeek Code** 的底层基座。微内核设计讨论中确立了核心设计准则：**一切皆插件**。内核刻意做得极精简，仅包含少量抽象服务，外加一个实体循环插件 `dsh-agent-loop`。所有产品功能均基于本文定义的扩展接口开发为独立插件，无需改动主循环逻辑。
+
+> Dependency rule: extension plugins depend on interfaces, never on `dsh-agent-loop` (the loop is swappable); the sanctioned exception is the composition bundle `dsh-agent-core`, whose job is assembling the concrete spine.
+
+依赖约束规范：各类扩展插件仅依赖抽象接口，严禁直接依赖 `dsh-agent-loop`（该主循环支持替换实现）；唯一允许的特例是组合包 `dsh-agent-core`，它的职责是组装整套实体主干。
+
+## ② 防御模式规则
+
+> Hard-won bug-class rules: each pattern below is a class of defect that actually shipped or nearly shipped here, stated as the rule that prevents its recurrence. Read this before writing lifecycle, concurrency, subprocess, or teardown code.
+
+这些都是踩坑总结得出的缺陷分类规范：下文每种范式都对应一类曾上线、或险些流入线上的问题，每条规范旨在杜绝同类问题复现。编写生命周期、并发、子进程、资源销毁相关代码前，请务必阅读本文档。
+
+## ③ 测试政策清单
+
+> **Coverage gate** (`pnpm run test:coverage`): the gating run, per-file 100% on `packages/*/*/src`. An uncovered line is often dead code the gate is correctly flagging for deletion, not a missing test to bolt on. Line coverage is necessary, never sufficient — it proves lines ran, not that the feature works as shipped.
+
+覆盖率门禁（`pnpm run test:coverage`）：作为合入门禁校验，要求 `packages/*/*/src` 目录下每个文件行覆盖率达到 100%。未覆盖代码行大多是无用死代码，门禁标记这类代码是提示删除，而非单纯补充测试。行覆盖率是必要条件，但远不充分：它仅能证明代码被执行过，无法保证功能符合线上预期。
+
+## ④ 机制描述
+
+> 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 <hash>`), 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.
+
+系统采用文件 blob 哈希而非提交哈希记录状态。同一 PR 内修改文件时，可通过 `git hash-object foo.md` 直接算出对应哈希，仅对比文件内容即可判断双语文档是否同步。通过记录的哈希值，可使用 `git cat-file -p <hash>` 还原上次确认对齐时两侧的原文。当双语文档不一致时，只需对比修改版本与上次确认版本的差异，最小幅度同步修改另一侧译文，无需全文重新翻译。
+
+## ⑤ 政策声明
+
+> The 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 — that is the reviewer's half of the contract. A re-recorded pair with a sloppy counterpart passes the gate; it must not pass review.
+
+明确门禁校验边界：门禁校验通过，仅代表两份文档哈希与结构完全匹配，不代表译文内容准确无误。门禁仅校验哈希与结构，无法判断双语表意是否统一——译文质量把关是评审人的责任。即便译文粗糙、表意偏差，只要哈希匹配，门禁就会放行，但这类 PR 绝不能通过人工评审。
+
+## ⑥ RFC 论证
+
+> 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.
+
+对比双语文件的 git 时间戳（无哈希记录方案）——不予采纳：仅调整格式的改动会触发误报，无关修改后再提交译文又会造成漏检。只有文件内容完全一致，才能作为门禁可信的校验依据。
+
+## ⑦ 推进策略（长段拆分示范）
+
+> **Rollout**: new documents don't wait for a batch — a date-named document dated on or after the manifest's `requiredSince` cutoff must merge with its pair, so everything new is bilingual from birth. For the back-catalog, the `required` list in the manifest is the enforcement frontier, not the goal. […] Pairing a document is a commitment: every later edit to either side must carry the counterpart along, so grow the frontier at the pace translation review is actually resourced, not ahead of it.
+
+**推进**：新增文档不再走批量分批翻译流程。以日期命名的文档，若其标注日期等于或晚于 manifest 里 `requiredSince` 分界时间，提交合入时必须配套对应的双语译文文件——所有新文档从创建起就要求中英双语齐备。针对存量旧文档：manifest 内的强制翻译列表只是当下执行红线，并非最终目标。（……）文档完成双语配对等同于一份长期约束承诺：后续只要修改任一版本，就必须同步更新对应另一语种文件。因此强制翻译范围的推进节奏，要匹配翻译评审实际可投入人力，切勿超前铺开。
+
+## 从样例提炼的要点
+
+- 语体是规范制度文：完整主谓、确定语气；不口语化，也不学术腔。
+- 给句子补显式执行主体：英文的被动句和抽象主语，中文写成「系统／门禁／工具／评审人」做主语。
+- 用中文工程惯用语替换直译：false positive/negative→误报／漏检、enforcement frontier→执行红线、ratchet→只向前收紧不倒退放宽、reviewable act→评审凭证。
+- 隐喻本地化而非移植：bilingual from birth→从创建起就要求双语齐备；grandfathered→历史存量遗留。
+- 类别名词说中文并在首现括注英文：实操手册（cookbook）、事故复盘（postmortem）；指目录或路径时保留代码体英文。
+- 长段按语义单元拆段，一段一件事；名词短语展开为动词句。
+- 母语重写不等于删减：原文每个语义成分都要落地。

docs/i18n/terminology.md

@@ -25,7 +25,9 @@
 | agent | agent | 首次出现可写：agent（智能体） |
 | agent loop | agent loop | |
 | backlog | backlog | 双语翻译语境指待翻清单 |
-| blob hash | blob hash | git 对象哈希；`git hash-object` 的结果 |
+| blob hash | blob 哈希 | git 对象哈希；`git hash-object` 的结果 |
+| commit hash | 提交哈希 | |
+| hash | 哈希 | 代码与命令中保留英文（如 `git hash-object`、`<hash>` 占位符） |
 | doc-sync | doc-sync | 仓库门禁名，保留英文 |
 | e2e | e2e | |
 | fiber | fiber | 首次出现可写：fiber（插件运行时） |

docs/i18n/translation-rules.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
-translation-rules.md: 4e190f58469f7d402dfa5600f17cf1621484f138
-translation-rules.zh.md: 89a1cddd23126f24354ce1f8d9af4e7bd403454d
+translation-rules.md: 3e99aa5432ccd904f702238e9b802a9ed9bf6832
+translation-rules.zh.md: 78778907f959d62dad2c9b4c02baf1f664791a43

docs/i18n/translation-rules.md

@@ -10,9 +10,18 @@ How to translate between the two sides of a documentation pair in this repo. Bot
 - 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.
 - 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.
 
+## Voice
+
+- The register is calibrated by [style-samples.md](style-samples.md) — human-approved gold pairs, one per document genre. The counterpart MUST match the register of the nearest sample; where a sample and a prose rule here disagree, the sample wins. The target is institutional technical Chinese: complete sentences, declarative, neither chatty nor academic.
+- 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.
+- Give sentences an explicit agent: where the English uses a passive or an abstract subject, name the actor (系统、门禁、评审人).
+- Prefer established Chinese 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 English noun chains into verb clauses.
+- Split long paragraphs by semantic unit — one idea per paragraph. Paragraph boundaries MAY differ from the source; the structural signature does not count paragraphs.
+- Category nouns render in Chinese with a first-mention English annotation (实操手册（cookbook）); literal directory or file references stay code-formatted English.
+
 ## Structure preservation
 
-The paired files MUST match one to one in:
+Shape is enforced by the pairing gate, so the writer never trades fluency against it — write naturally inside the frame. The paired files MUST match one to one in:
 
 - heading hierarchy (same levels, same order — heading TEXT is translated),
 - list shape and numbering,

docs/i18n/translation-rules.zh.md

@@ -10,9 +10,18 @@
 - 另一侧应当读起来是其语言自然的技术文字，而不是逐词对照。翻译语义，在目标语言语法需要处重组句子，并保持原作者的语域——简练的保持简练。
 - 不要翻译不可译的东西：一句话如果依赖源语言的习语而无法自然转换，就翻译它的意思，而不是习语本身。
 
+## 行文
+
+- 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，译文必须对齐最接近的样例语体；样例与本文条款冲突时，以样例为准。目标语体是规范的技术制度文：完整主谓、确定语气，不口语化也不学术腔。
+- 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。
+- 给句子补显式执行主体：英文的被动句和抽象主语，中文写成「系统、门禁、评审人」等实际执行者做主语。
+- 优先使用中文工程惯用语而非直译（false positive/negative→误报／漏检、enforcement frontier→执行红线）；隐喻做本地化替换而不是移植，英文名词链展开为动词句。
+- 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。
+- 类别名词说中文并在首现括注英文（实操手册（cookbook））；指目录或文件本身时保留代码体英文。
+
 ## 结构保持
 
-配对的两个文件必须在以下方面一一对应：
+形状由配对门禁强制，译者不需要用流畅度去换结构——在框架内自然行文即可。配对的两个文件必须在以下方面一一对应：
 
 - 标题层级（相同级别、相同顺序——标题的**文字**要翻译），
 - 列表形态与编号，