feat(i18n): unit-mapped briefings with mechanical --apply, adopting the #684 planner mechanics

The briefing now maps each update at the narrowest safely aligned
granularity, widening deterministically on mapping failure: a change
confined to the pair's byte-identical code fences is computed outright
(--apply splices it into the counterpart and validates the result
against the pairing gate's structural signature before writing);
otherwise changed Markdown units — headings, paragraphs, table rows,
list items, fences, block quotes, HTML blocks, thematic breaks, link
definitions, matched by container-scoped kind sequences — each carry
their last-confirmed source, current source, and current counterpart
text; units that do not align fall back to depth-matched heading
sections (depth only, so translated heading text still maps); and when
sections do not align either, or both sides drifted, the briefing says
so and withholds the mapping. Terminology rows now match the changed
spans only, English terms on word boundaries with plural inflections,
and Chinese-target briefings track each relevant term's document-wide
first occurrence — a moved occurrence pulls the vacated and receiving
spans into the briefing with an explanatory note.

The unit mapping, mechanical code splice, and first-occurrence tracking
adopt the planner design from the incremental prompt-pipeline PR (#684),
whose provider-backed bake-off independently validated the same scope
ladder; this PR carries those mechanics into the agent-facing briefing
path so both consumers of the consistency records behave alike. The
prior line-hunk section mapping and its heading-text alignment (which
could not map cross-language sections) are replaced wholesale.

Docs: SKILL.md update path, i18n README pair, development.md pair, and
the briefed-updates Agent Note pair brought along; the development.md
fence edit was applied with --apply itself, and the prose updates were
made through the new unit/section briefings.

.agents/notes/implemented/process/2026-07-26-briefed-minimal-translation-updates.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 .agents/notes/implemented/process/2026-07-26-briefed-minimal-translation-updates.md
-2026-07-26-briefed-minimal-translation-updates.md: b155ee7e51a819cdea34051c4d734fbc06a1dca8
-2026-07-26-briefed-minimal-translation-updates.zh.md: 8da0b3c2b62113af47ea58334034feb6c5ee2959
+2026-07-26-briefed-minimal-translation-updates.md: 42baedc8d68557bc0d273c5a476806ac480d4afd
+2026-07-26-briefed-minimal-translation-updates.zh.md: 18653fe1097f4028a0671b6d15d1982ad137f47a

.agents/notes/implemented/process/2026-07-26-briefed-minimal-translation-updates.md

@@ -12,8 +12,8 @@ The [bilingual pairing contract](2026-07-02-bilingual-docs-and-pairing-gate.md)
 
 Pair updates run on a generated briefing instead of the guidance corpus; only new pairs still run the whole-document workflow, which is unchanged.
 
-- **`pnpm run gen-translation-brief [pair...]`** ([scripts/gen-translation-brief.ts](../../../../scripts/gen-translation-brief.ts), assembly in [scripts/translation-brief.ts](../../../../scripts/translation-brief.ts)) prints, per out-of-sync pair: the authored side's diff from its recorded last-confirmed blob to the working tree, the counterpart sections that diff lands in with current line numbers (mapped through the heading structure, which the gate proves aligned at the last confirmed state; when both sides drifted or headings do not align, the briefing says so and withholds the mapping instead of guessing), the terminology rows whose terms appear in the changed lines, and a fixed digest of the binding update rules. The briefing is the translator's whole working set; the full sources of truth remain the escalation path for decisions the briefing cannot answer.
-- **The update path in [dsh-translate-docs](../../../skills/dsh-translate-docs/SKILL.md)** consumes the briefing: mechanical diffs (changed lines confined to the byte-identical code fences) are applied by the orchestrator directly; prose diffs go to a subagent whose prompt is the briefing, not the corpus; verification is clause-by-clause on the changed hunks, not the whole document.
+- **`pnpm run gen-translation-brief [--apply] [pair...]`** ([scripts/gen-translation-brief.ts](../../../../scripts/gen-translation-brief.ts), assembly in [scripts/translation-brief.ts](../../../../scripts/translation-brief.ts)) prints, per out-of-sync pair, the authored side's diff from its recorded last-confirmed blob to the working tree plus the change mapped at the narrowest safely aligned granularity, deterministically widening on mapping failure: a change confined to the pair's byte-identical code fences is computed outright (`--apply` splices it into the counterpart and validates the result against the pairing gate's structural signature before writing); otherwise changed Markdown units (headings, paragraphs, table rows, list items, code fences, block quotes, HTML blocks, thematic breaks, link definitions — matched by container-scoped kind sequences) each carry their last-confirmed source, current source, and current counterpart text with line numbers; units that do not align fall back to depth-matched heading sections; and when sections do not align either, or both sides drifted, the briefing says so and withholds the mapping instead of guessing. Terminology rows are matched against the changed spans only (word-boundary English matching with plural inflections), and for Chinese targets the briefing tracks each relevant term's document-wide first occurrence — when an edit moves it, the vacated and receiving spans join the briefing with an explanatory note, since the 首次出现 annotation must move with it. The unit mapping, code splice, and first-occurrence mechanics adopt the planner design from the [incremental prompt-pipeline work](https://github.com/deepseek-harness/deepseek-harness/pull/684), whose provider-backed bake-off independently validated the same scope ladder for the automated pipeline. The briefing is the translator's whole working set; the full sources of truth remain the escalation path for decisions the briefing cannot answer.
+- **The update path in [dsh-translate-docs](../../../skills/dsh-translate-docs/SKILL.md)** consumes the briefing: mechanical (code-fence-only) changes are applied with `--apply`, no subagent; prose diffs go to a subagent whose prompt is the briefing, not the corpus; verification is clause-by-clause on the changed spans, not the whole document.
 - **The pairing gate takes pair arguments.** `verify-translation-pairing [pair...]` checks just the named pairs (any of a pair's three files, or the bare stem, names it); the corpus-wide sweep remains the no-argument form that `doc-sync` and CI run. `--write` now requires naming the confirmed pairs — bare `--write` refuses, and re-recording everything is an explicit `--write --all` — because the old bare form silently blessed every drifted pair in the tree, including ones the caller never looked at, and a prose-only drift would then stay green forever. Each record's comment names its own scoped command.
 
 ## Benchmark
@@ -31,7 +31,7 @@ The decision followed a controlled replay of ten real pair updates from this rep
 - **Keep the workflow, just scope the gate** — the gate scan was the smaller cost; the corpus loads and archaeology dominated. Scoping alone would have left the ~3x overhead in place.
 - **Whole-document re-translation as the update path** (what a naive pipeline does) — rejected on benchmark evidence: preservation collapse, terminology drift, highest cost. The contract's minimal-update rule survives with data behind it.
 - **Batching several pairs per subagent** — rejected: no measured saving (briefings already deduplicate the fixed content), and one stalled or confused pair holds the others hostage.
-- **Per-paragraph translation-memory records in the sidecar** (segment hashes instead of whole-file hashes) — rejected: paragraph boundaries may legitimately differ across the pair, either side can be authored first, and the records would bloat and conflict in merges. Heading-level mapping from the existing whole-file hashes recovers the same alignment when it is trustworthy and says so when it is not.
+- **Per-paragraph translation-memory records in the sidecar** (segment hashes instead of whole-file hashes) — rejected: paragraph boundaries may legitimately differ across the pair, either side can be authored first, and the records would bloat and conflict in merges. Span mapping computed on demand from the existing whole-file hashes recovers the same alignment when it is trustworthy and says so when it is not.
 - **An update mode in the automated prompt pipeline (prompt-v5)** — deferred, not designed here: nothing drives [scripts/translation-prompt.ts](../../../../scripts/translation-prompt.ts) today, and the agent path was the live cost center. The pipeline keeps its whole-document v4 contract until it has a consumer.
 
 ## Consequences
@@ -40,8 +40,9 @@ The decision followed a controlled replay of ten real pair updates from this rep
 - The briefing generator is a second consumer of the consistency records: recorded blob hashes now also drive diff recovery and section mapping, strengthening the incentive to keep records honest.
 - `--write` without arguments no longer works; muscle-memory callers must name pairs or pass `--all`. That is the point — the bulk bless is now a visible, deliberate act.
 - Scoped checks mean an update loop can be green while an unrelated pair elsewhere is red; the corpus-wide check in `doc-sync`/CI still owns the tree-level invariant.
-- The section mapping trusts heading alignment only where the gate proved it at the last confirmed state; documents restructured on one side fall back to an explicit "locate the regions yourself" briefing rather than a wrong map.
+- Span mapping trusts an alignment only when the kind sequences match across the last-confirmed source, current source, and current counterpart; a mapping failure widens deterministically (units → sections → whole document) rather than guessing, so a restructured document gets an explicit "locate the regions yourself" briefing, never a wrong map.
+- A first-occurrence move can enlarge a briefing beyond the directly changed spans; that cost is an explicit consequence of the 首次出现 contract, not an alignment heuristic.
 
 ## Testing
 
-[scripts/translation-brief.spec.ts](../../../../scripts/translation-brief.spec.ts) pins diff parsing, section mapping (including preamble and multi-section hunks), terminology row matching in both directions with word-boundary discipline, fence escalation, and the rendered briefing's contract (aligned sections, both-drifted warning, per-direction digests, scoped finish commands). [scripts/translation-pairing.spec.ts](../../../../scripts/translation-pairing.spec.ts) pins argument normalization (any pair file or bare stem to the anchor) and the CLI matrix: scoped check, bare `--write` refusal, `--write <pair>`, `--write --all`, `--list` exclusivity, unknown flags.
+[scripts/translation-brief.spec.ts](../../../../scripts/translation-brief.spec.ts) pins unit and section span extraction (container-scoped kinds, depth-only section alignment so translated heading text still maps, preamble), alignment and changed-index detection, the mechanical code splice and each of its refusal conditions, terminology row matching in both directions with word-boundary and plural-inflection discipline, first-occurrence movement tracking, fence escalation, and the rendered briefing's contract (unit bundles with three-way context, mechanical/sections/document scopes, per-direction digests, scoped finish commands). [scripts/translation-pairing.spec.ts](../../../../scripts/translation-pairing.spec.ts) pins argument normalization (any pair file or bare stem to the anchor) and the CLI matrix: scoped check, bare `--write` refusal, `--write <pair>`, `--write --all`, `--list` exclusivity, unknown flags.

.agents/notes/implemented/process/2026-07-26-briefed-minimal-translation-updates.zh.md

@@ -12,13 +12,13 @@ Status: implemented
 
 配对更新基于生成的简报（briefing）运行，而非基于指导语料；只有新建配对仍走整篇文档工作流，后者保持不变。
 
-- **`pnpm run gen-translation-brief [pair...]`**（[scripts/gen-translation-brief.ts](../../../../scripts/gen-translation-brief.ts)，组装逻辑在 [scripts/translation-brief.ts](../../../../scripts/translation-brief.ts)）针对每个失去同步的配对打印：被改一侧从其记录在案的上次确认 blob 到当前工作区的 diff；该 diff 落入的对侧章节及其当前行号（经标题结构映射得到；该结构在上次确认状态的对齐已由门禁证明；当两侧同时漂移或标题无法对齐时，简报会明说这一点并省略映射，而不是靠猜）；改动行所涉术语对应的术语表行；以及一份固定的约束性更新规则摘要。简报就是译者的全部工作集；简报回答不了的决策，仍以完整的真源文档作为升级求证路径。
-- **[dsh-translate-docs](../../../skills/dsh-translate-docs/SKILL.md) 中的更新路径**消费这份简报：机械类 diff（改动行全部落在逐字节一致的围栏代码块内）由编排 agent（智能体）直接应用；行文类 diff 交给 subagent，其提示词就是简报本身，而非指导语料；核验只对改动块逐句进行，不覆盖整篇文档。
+- **`pnpm run gen-translation-brief [--apply] [pair...]`**（[scripts/gen-translation-brief.ts](../../../../scripts/gen-translation-brief.ts)，组装逻辑在 [scripts/translation-brief.ts](../../../../scripts/translation-brief.ts)）针对每个失去同步的配对，打印被改一侧从其记录在案的上次确认 blob 到当前工作区的 diff，并附上以能安全对齐的最窄粒度映射的这次改动，映射失败时粒度确定性地逐级放宽：仅落在配对中逐字节一致的围栏代码块内的改动会直接算出（`--apply` 会把它拼接进对侧文件，并在写入前用配对门禁的结构签名校验所得结果）；否则，每个有改动的 Markdown 单元（标题、段落、表格行、列表项、围栏代码块、块引用、HTML 块、分隔线、链接定义；匹配依据是以容器为作用域的种类序列）都带上各自的上次确认源文、当前源文与当前对侧文本及行号；无法对齐的单元回退到按深度匹配的标题章节；当章节也无法对齐或两侧同时漂移时，简报会明说这一点并省略映射，而不是靠猜。术语表行只与改动块匹配（英文术语按词边界匹配，含复数变形）；当目标侧是中文时，简报还会跟踪每个相关术语在整篇文档中的首次出现：一旦某次编辑使其移位，腾出的与接收的两处区间就会附一条解释性说明加入简报，因为「首次出现」括注必须随之移动。单元映射、代码拼接与首次出现机制采纳了[增量提示词流水线工作](https://github.com/deepseek-harness/deepseek-harness/pull/684)中的规划器设计；该项工作中接入提供方的对比评测，已为自动流水线独立验证了同一套范围阶梯。简报就是译者的全部工作集；简报回答不了的决策，仍以完整的真源文档作为升级求证路径。
+- **[dsh-translate-docs](../../../skills/dsh-translate-docs/SKILL.md) 中的更新路径**消费这份简报：机械类改动（只涉及围栏代码块）用 `--apply` 应用，不动用 subagent；行文类 diff 交给 subagent，其提示词就是简报本身，而非指导语料；核验只对改动块逐句进行，不覆盖整篇文档。
 - **配对门禁接受配对参数。**`verify-translation-pairing [pair...]` 只检查被点名的配对（配对三个文件中的任意一个，或其裸词干，都能指代该配对）；全语料扫描仍是 `doc-sync`（文档同步门禁）与 CI 运行的无参数形式。`--write` 现在要求点名已确认的配对：裸 `--write` 会拒绝执行，重新记录全部配对必须显式写 `--write --all`；原因是旧的裸形式会默默为树中每一个漂移的配对背书，包括调用者从未看过的那些，纯行文层面的漂移于是可以永远保持绿灯。每份记录的注释都写明针对该配对自身的按对命令。
 
 ## 基准测试
 
-该决策来自对本仓库历史上十次真实配对更新的受控回放（2026 年 7 月；每例改动 1 到 64 行英文，涵盖 README、RFC、Agent Note（agent 决策记录）与用户文档）。每个样例都在临时仓库中重建到其真实的上次确认状态，英文改动保持未提交，再用全新的 subagent 分别跑过相互竞争的各条工作流：维持现状的语料加载路径、简报路径、无指导对照组、整篇重译、小模型上的简报路径，以及每个 agent 一次处理三对文档的批量方案。产出先经机械门禁把关，再由评委盲评打分；评委还同时收到真实的历史更新与原样未动的陈旧对侧文件作为对照。
+该决策来自对本仓库历史上十次真实配对更新的受控回放（2026 年 7 月；每例改动 1 到 64 行英文，涵盖 README、RFC、Agent Note（agent 决策记录）与用户文档）。每个样例都在临时仓库中重建到其真实的上次确认状态，英文改动保持未提交，再用全新的 subagent 分别跑过相互竞争的各条工作流：维持现状的语料加载路径、简报路径、无指导对照组、整篇重译、小模型上的简报路径，以及每个 agent（智能体）一次处理三对文档的批量方案。产出先经机械门禁把关，再由评委盲评打分；评委还同时收到真实的历史更新与原样未动的陈旧对侧文件作为对照。
 
 - 简报路径在盲评的忠实性、保留度与流畅度上与现状路径打平（两者都达到或超过真实历史更新的水平），而在未发生停滞的样例上只花费约三分之一的 token 用量与墙钟时间（全部十例的中位数：相对 token 成本单位 276k 对 595k，轮次数 14 对 32）。
 - 整篇重译被证实有害，而不只是浪费：它丢弃经评审的措辞，盲评保留度因此崩塌（4.4/10 对 9.8）；它还使各更新组保持住的既定术语发生漂移（既定译法本就写在对侧文件自身的正文里）；而且它是成本最高的一组。
@@ -31,7 +31,7 @@ Status: implemented
 - **保留原工作流，只让门禁支持按对检查**：门禁扫描本是较小的开销，大头在语料加载与翻查历史。只收窄检查范围，约 3 倍的开销仍会原地保留。
 - **把整篇重译作为更新路径**（朴素流水线的做法）：依据基准测试证据否决，理由是保留度崩塌、术语漂移、成本最高。契约的最小更新规则得以延续，且从此有数据支撑。
 - **每个 subagent 批量处理多对文档**：否决。没有实测出节省（简报本身已对固定内容做了去重），而且一对文档停滞或陷入混乱会把其余配对一并拖住。
-- **在伴随记录中保存逐段的翻译记忆条目**（用分段 hash 取代整文件 hash）：否决。配对两侧的段落边界可以合理地不同，任一侧都可能先撰写，这类条目还会不断膨胀并在合并时产生冲突。基于现有整文件 hash 的标题级映射，在对齐可信时能恢复同样的对齐关系，不可信时会明确说明。
+- **在伴随记录中保存逐段的翻译记忆条目**（用分段 hash 取代整文件 hash）：否决。配对两侧的段落边界可以合理地不同，任一侧都可能先撰写，这类条目还会不断膨胀并在合并时产生冲突。基于现有整文件 hash 按需计算的区间映射，在对齐可信时能恢复同样的对齐关系，不可信时会明确说明。
 - **给自动提示词流水线加一个更新模式（prompt-v5）**：推迟，本文不做设计。今天没有任何调用方在驱动 [scripts/translation-prompt.ts](../../../../scripts/translation-prompt.ts)，实际的成本中心是 agent 路径。流水线在拥有消费方之前，维持其整篇文档的 v4 契约。
 
 ## 后果
@@ -40,8 +40,9 @@ Status: implemented
 - 简报生成器成为一致性记录的第二个消费方：记录的 blob hash 如今还驱动 diff 还原与章节映射，这进一步强化了如实维护记录的动机。
 - 不带参数的 `--write` 不再可用；靠肌肉记忆的调用者必须点名配对或传 `--all`。这正是目的所在：批量背书如今是一个可见的、有意为之的动作。
 - 按对检查意味着一个更新循环可以在别处某个无关配对处于红灯时自己保持绿灯；`doc-sync`/CI 中的全语料检查仍然承载树级不变式。
-- 章节映射只在门禁已于上次确认状态证明标题对齐的范围内信任这种对齐；在单侧被重构过的文档会回退到一份明确写着「请自行定位相关区域」的简报，而不是拿到一张错误的地图。
+- 区间映射只在上次确认源文、当前源文与当前对侧文本三方的种类序列一致时才信任一处对齐；映射失败时粒度确定性地逐级放宽（单元 → 章节 → 整篇文档）而不是靠猜，因此被重构过的文档拿到的是一份明确写着「请自行定位相关区域」的简报，绝不会是一张错误的地图。
+- 「首次出现」的一次移位可能让简报扩大到直接改动块之外；这一成本是「首次出现」契约的明确后果，而非对齐启发式。
 
 ## 测试
 
-[scripts/translation-brief.spec.ts](../../../../scripts/translation-brief.spec.ts) 固定 diff 解析、章节映射（含首个标题前的序言与跨多个章节的改动块）、带词边界约束的双向术语行匹配、围栏升级，以及渲染后简报的契约（对齐的章节、两侧同时漂移的警告、分方向的规则摘要、按对的收尾命令）。[scripts/translation-pairing.spec.ts](../../../../scripts/translation-pairing.spec.ts) 固定参数归一化（配对的任一文件或裸词干都归一到锚点）与 CLI（命令行界面）用例矩阵：按对检查、裸 `--write` 拒绝执行、`--write <pair>`、`--write --all`、`--list` 的互斥性、未知标志。
+[scripts/translation-brief.spec.ts](../../../../scripts/translation-brief.spec.ts) 固定单元与章节的区间提取（以容器为作用域的种类、只按深度对齐章节从而让已翻译的标题文字仍能映射、首个标题前的序言）、对齐与改动索引检测、机械代码拼接及其每一个拒绝条件、带词边界与复数变形约束的双向术语行匹配、首次出现移位跟踪、围栏升级，以及渲染后简报的契约（带三方上下文的单元条目、机械／章节／整篇文档三种范围、分方向的规则摘要、按对的收尾命令）。[scripts/translation-pairing.spec.ts](../../../../scripts/translation-pairing.spec.ts) 固定参数归一化（配对的任一文件或裸词干都归一到锚点）与 CLI（命令行界面）用例矩阵：按对检查、裸 `--write` 拒绝执行、`--write <pair>`、`--write --all`、`--list` 的互斥性、未知标志。