dsh-vibe-math 2.5.0 → 2.6.0

package/README.en.md

@@ -725,6 +725,15 @@ The main agent `vibe_math_status`: in `qs/qs.json`, `q1` has been written back w
 | `leanCommand` | `'lean'` | The Lean executable to run (e.g. `'lake'`) |
 | `leanArgs` | `[]` | Additional arguments inserted before the file name (e.g. `['env','lean']` together with `leanCommand='lake'`) |
 | `leanTimeoutMs` | `120000` | Upper limit for a single Lean run (milliseconds) |
+| `finalPaper` | `true` | **Final paper**: written automatically at closure (`false` disables only the automatic trigger; the manual command still works). Full contract: `docs/final-paper.md` |
+| `paperFormat` | `both` | Which text versions to produce: `both` (md+tex) / `md` (skips compilation and must not warn about a missing tex) / `tex` |
+| `paperLanguage` | `zh` | Paper language: `zh` (ctexart, engine prefers xelatex) / `en` (article, pdflatex first) |
+| `paperCompilePdf` | `true` | Compile `paper.pdf` when a LaTeX engine is detected; with no engine or a failed compile, tex+md are still delivered and a warning is logged |
+| `paperLatexCommand` | `''` | Force one LaTeX engine executable (empty = auto-detect per language: xelatex→latexmk→pdflatex→lualatex→tectonic) |
+
+#### Final paper
+
+All four presets have it **on by default**: after the closure signal fires and **before the run is marked complete**, the run enters the paper phase. In v2 a dedicated "paper writer" subagent assembles the concluded evidence into `Paper/<project>/{paper.md,paper.tex,paper.meta.json,paper.log.md}` (plus `paper.pdf` only when an engine is detected). Manual: `/vibe paper [lang=zh|en] [format=both|md|tex] [force]`. A PDF needs a LaTeX engine on the host (`xelatex` preferred for Chinese); with no engine or a failed compile the tex+md are still delivered with only a logged warning — the finalisation is never blocked and an existing pdf is never overwritten. Full contract: `docs/final-paper.md`.
 
 ### v3 (paper-style md + planner agent + method library) defaults
 
@@ -749,6 +758,15 @@ Added/adjusted on top of all v2 parameters:
 | `leanCommand` | `'lean'` | The Lean executable to run (e.g. `'lake'`) |
 | `leanArgs` | `[]` | Additional arguments inserted before the file name (e.g. `['env','lean']` together with `leanCommand='lake'`) |
 | `leanTimeoutMs` | `120000` | Upper limit for a single Lean run (milliseconds) |
+| `finalPaper` | `true` | **Final paper**: written automatically at closure (`false` disables only the automatic trigger; the manual command still works). Full contract: `docs/final-paper.md` |
+| `paperFormat` | `both` | Which text versions to produce: `both` (md+tex) / `md` (skips compilation and must not warn about a missing tex) / `tex` |
+| `paperLanguage` | `zh` | Paper language: `zh` (ctexart, engine prefers xelatex) / `en` (article, pdflatex first) |
+| `paperCompilePdf` | `true` | Compile `paper.pdf` when a LaTeX engine is detected; with no engine or a failed compile, tex+md are still delivered and a warning is logged |
+| `paperLatexCommand` | `''` | Force one LaTeX engine executable (empty = auto-detect per language: xelatex→latexmk→pdflatex→lualatex→tectonic) |
+
+#### Final paper
+
+v3 uses the same switch and the same ordering as v2 (strict termination; the writer is spawned **before** the scheduler stops): a dedicated "paper writer" subagent produces `Paper/<project>/{paper.md,paper.tex,paper.meta.json,paper.log.md}` (plus `paper.pdf` when an engine is detected). Manual: `/vibe paper [lang=zh|en] [format=both|md|tex] [force]`. No engine or a failed compile still delivers tex+md, logs a warning and never blocks the finalisation. Full contract: `docs/final-paper.md`.
 
 ### v4 (resident self-organization · experimental) defaults
 
@@ -771,6 +789,16 @@ Adjustable via `vibe_v4_set` (persisted to `State/settings.json`):
 | `leanCommand` | `'lean'` | The Lean executable to run (e.g. `'lake'`) |
 | `leanArgs` | `[]` | Additional arguments inserted before the file name (e.g. `['env','lean']` together with `leanCommand='lake'`) |
 | `leanTimeoutMs` | `120000` | Upper limit for a single Lean run (milliseconds) |
+| `finalPaper` | `true` | **Final paper**: written automatically at closure (`false` disables only the automatic trigger; the manual command still works). Full contract: `docs/final-paper.md` |
+| `paperFormat` | `both` | Which text versions to produce: `both` (md+tex) / `md` (skips compilation and must not warn about a missing tex) / `tex` |
+| `paperLanguage` | `zh` | Paper language: `zh` (ctexart, engine prefers xelatex) / `en` (article, pdflatex first) |
+| `paperCompilePdf` | `true` | Compile `paper.pdf` when a LaTeX engine is detected; with no engine or a failed compile, tex+md are still delivered and a warning is logged |
+| `paperLatexCommand` | `''` | Force one LaTeX engine executable (empty = auto-detect per language: xelatex→latexmk→pdflatex→lualatex→tectonic) |
+| `paperEditor` | `office` | Who finalises: `office` (the session root / human side, default) or `resident:<id>` (if that resident has left, it degrades to office and the meta/log say so) |
+
+#### Final paper
+
+On by default; v4 enters the paper phase after the closing meeting casts its unanimous stop vote and **before** the run is marked complete. Team flow: each resident writes its own part → merge (deduplicate, unify terms and notation) → at least one **cross-review** round → the editor named by `paperEditor` (default `office`, or `resident:<id>`) turns it into the final draft → the paper is finalised only on **unanimous "deliverable"** (objections keep iterating; past the round cap a warning is recorded and the disagreement goes into the appendix). Manual: `/v4 paper [lang=] [format=] [editor=office|resident:<id>] [force]`. Output: `Paper/<run id>/{paper.md,paper.tex,paper.meta.json,paper.log.md}` (plus `paper.pdf` when an engine is available). Full contract: `docs/final-paper.md`.
 
 ### v5 (institute system · experimental) defaults
 
@@ -802,6 +830,16 @@ Adjustable via `vibe_v5_set` (persisted in the institute state file `State/<inst
 | `leanCommand` | `'lean'` | The Lean executable to run (e.g. `'lake'`) |
 | `leanArgs` | `[]` | Additional arguments inserted before the file name (e.g. `['env','lean']` together with `leanCommand='lake'`) |
 | `leanTimeoutMs` | `120000` | Upper limit for a single Lean run (milliseconds) |
+| `finalPaper` | `true` | **Final paper**: written automatically at closure (`false` disables only the automatic trigger; the manual command still works). Full contract: `docs/final-paper.md` |
+| `paperFormat` | `both` | Which text versions to produce: `both` (md+tex) / `md` (skips compilation and must not warn about a missing tex) / `tex` |
+| `paperLanguage` | `zh` | Paper language: `zh` (ctexart, engine prefers xelatex) / `en` (article, pdflatex first) |
+| `paperCompilePdf` | `true` | Compile `paper.pdf` when a LaTeX engine is detected; with no engine or a failed compile, tex+md are still delivered and a warning is logged |
+| `paperLatexCommand` | `''` | Force one LaTeX engine executable (empty = auto-detect per language: xelatex→latexmk→pdflatex→lualatex→tectonic) |
+| `paperEditor` | `academician` | Who finalises: `academician` (default, the only editor an unattended run can reach) or `office` (manual `/v5 paper editor=office` only, and only after consulting the whole institute) |
+
+#### Final paper
+
+On by default; v5 enters the paper phase after `checkSolved` concludes the problem is solved and **before** the run is marked complete. The permanent staff and the academician write their own parts, merge them and cross-review; the editor is set by `paperEditor`: the **automatic flow always uses `academician`** (the office is the root session and has no wake path), while `office` is available only through the manual `/v5 paper editor=office`. That path requires the office to consult the whole institute first (>=1 `vibe_v5_message` plus >=1 `vibe_v5_meeting`), state the conclusion in the finalisation note, and then call `vibe_v5_finalize_paper`; without both counts it is refused (`V5_PAPER_CONSULT_REQUIRED`). Tools: `vibe_v5_paper`, `vibe_v5_finalize_paper`. Output: `Paper/<institute id>/{paper.md,paper.tex,paper.meta.json,paper.log.md}` (plus `paper.pdf` when an engine is available). Full contract: `docs/final-paper.md`.
 
 Common controls: `vibe_v5_configure` (configure first) → `vibe_v5_start` (start work) → `vibe_v5_report` / `vibe_v5_status`; `vibe_v5_message` / `vibe_v5_meeting` / `vibe_v5_members` / `vibe_v5_hire` / `vibe_v5_fire` (temp worker) / `vibe_v5_add_researcher` / `vibe_v5_remove_researcher` (add/remove residents, institute office only) / `vibe_v5_pause` / `vibe_v5_resume` / `vibe_v5_stop`; slash command `/v5`.
 
@@ -825,8 +863,9 @@ Common controls: `vibe_v5_configure` (configure first) → `vibe_v5_start` (star
 - **Four sets of Lean prompt corpora**: [`prompt-corpus-v2/formal-verify-v2.md`](prompt-corpus-v2/formal-verify-v2.md) · [`prompt-corpus-v3/formal-verify-v3.md`](prompt-corpus-v3/formal-verify-v3.md) · [`prompt-corpus-v4/formal-verify-v4.md`](prompt-corpus-v4/formal-verify-v4.md) (each covering off / encourage / **require** / fidelity branches / work rounds / receipt contract; the workspace is normalized to `<WS>` and the VibeMath root to `<VIBEMATH>`)
 - **The persona source text of the four presets**: [`prompt-corpus-persona/persona-corpus.md`](prompt-corpus-persona/persona-corpus.md) (the prompts the main agent actually receives: which tools, which parameters, which slash subcommands; generated by `audit-persona-surface.test.mjs` and shipped with the package)
 - **Lean formal verification (a contract shared by the four architectures)**: [`docs/formal-verification.md`](docs/formal-verification.md)
-- **Test timing baseline and parallel run recipes**: [`docs/test-timing.md`](docs/test-timing.md) (`node tests/run-tests.mjs` runs **every suite AND every probe** in parallel: `TOTAL 56` (38 suites + 18 probes/variants) in ≈3.5 min; which 18 of them ship in the package and which are repository-only is in §1.1 of that document; every runner prints its elapsed time/speedup so the next strategy can be chosen from data)
-- **Static prompt-surface consistency (persona ↔ tool registry ↔ slash command hint/usage)**: [`audit-persona-surface.test.mjs`](tests/audit-persona-surface.test.mjs) (196 assertions, and generates [`prompt-corpus-persona/persona-corpus.md`](prompt-corpus-persona/persona-corpus.md) for manual review) + [`audit-persona-sensitivity.mjs`](tests/audit-persona-sensitivity.mjs) (11 sensitivity probes) — guarding "every registered tool must appear in the persona / every name in the persona must really be registered / the `prefix` and `text` blocks must match line by line / hint, usage, and the actual branch must agree in all three places"
+- **Final paper (a contract shared by the four architectures)**: [`docs/final-paper.md`](docs/final-paper.md) (the five parameters plus `paperEditor` on v4/v5, the "paper phase before the run is marked complete" ordering, the `Paper/<id>/` artifacts and the nine-section skeleton, LaTeX detection with repair-then-degrade, the v4/v5 team co-authoring flow and the v5 office-consultation rule)
+- **Test timing baseline and parallel run recipes**: [`docs/test-timing.md`](docs/test-timing.md) (`node tests/run-tests.mjs` runs **every suite AND every probe** in parallel: `TOTAL 57` (39 suites + 18 probes/variants) in ≈3.5 min; which 18 of them ship in the package and which are repository-only is in §1.1 of that document; every runner prints its elapsed time/speedup so the next strategy can be chosen from data)
+- **Static prompt-surface consistency (persona ↔ tool registry ↔ slash command hint/usage)**: [`audit-persona-surface.test.mjs`](tests/audit-persona-surface.test.mjs) (208 assertions, and generates [`prompt-corpus-persona/persona-corpus.md`](prompt-corpus-persona/persona-corpus.md) for manual review) + [`audit-persona-sensitivity.mjs`](tests/audit-persona-sensitivity.mjs) (16 sensitivity probes) — guarding "every registered tool must appear in the persona / every name in the persona must really be registered / the `prefix` and `text` blocks must match line by line / hint, usage, and the actual branch must agree in all three places"
 - **Mandatory checklist for a full review**: [`AUDIT-CHECKLIST.md`](docs/AUDIT-CHECKLIST.md) (this repository's mandatory audit process; §1.9 specifically checks "whether the tool parameter schema can accommodate them")
 - **Prompt/interaction invariants (all four sets together, re-checkable in one command)**: [`audit-prompt-invariants.mjs`](tests/audit-prompt-invariants.mjs) (157 assertions) — encoding, one by one, "the classes of prompt/tool-surface defects that have really occurred historically" as static invariants (abbreviated tool names, projecting a fidelity defect as 0, `defect` written only in the prompt but not implemented, a receipt contract missing `defect`, passing without a note, wrong field names, the `off` tier still being able to write state in its receipt, uncertain corpora, missing probes, **a tool's closed schema that cannot accommodate the parameters in its own documentation**, **keys that the schema declares at the parameter level but silently drops**). Adding `--self-probe` injects these defect shapes in memory and requires the corresponding invariants to **turn red** while the unmutated control run **stays green** (5/5); the script itself additionally carries six self-checks X5–X8b (the comment scanner must recognize regex literals — including regexes **after a keyword** such as `return /…/` — `//` inside strings must be preserved, stripping comments must not change line structure, and the parse-level criterion that "the four sets of source, with comments stripped, must still parse under `node --check`")
 - **Specification ↔ code traceability (all four sets together)**: [`audit-spec-traceability.mjs`](tests/audit-spec-traceability.mjs) (94 assertions) — tools promised in `实现方案.md`/README must really be registered; the four Lean parameters must be accepted by both the documentation and the code

package/README.md

@@ -726,6 +726,15 @@ v5 的完整架构（含成员生命周期、一轮时序、共识状态机、
 | `leanCommand` | `'lean'` | 要执行的 Lean 可执行文件（例：`'lake'`） |
 | `leanArgs` | `[]` | 插在文件名之前的附加参数（例：`['env','lean']` 配合 `leanCommand='lake'`） |
 | `leanTimeoutMs` | `120000` | 单次 Lean 运行的上限（毫秒） |
+| `finalPaper` | `true` | **最终论文**：收口时自动撰写（`false` 只关自动触发，手动命令仍可用）。完整契约见 `docs/final-paper.md` |
+| `paperFormat` | `both` | 论文产出格式：`both`（md+tex）/ `md`（跳过编译，且不报"缺 tex"）/ `tex` |
+| `paperLanguage` | `zh` | 论文语言：`zh`（ctexart，引擎优先 xelatex）/ `en`（article，pdflatex 优先） |
+| `paperCompilePdf` | `true` | 检测到 LaTeX 时编译 `paper.pdf`；无引擎或编译失败则保留 tex+md 并记日志告警 |
+| `paperLatexCommand` | `''` | 指定 LaTeX 引擎可执行文件（空 = 按语言自动探测 xelatex→latexmk→pdflatex→lualatex→tectonic） |
+
+#### 最终论文（final paper）
+
+四个预设都**默认开启**：收口判定命中后、**在 run 被标记完成之前**进入 paper 阶段。v2 由一名专职「论文撰写」子代理把已定论证据整理成 `Paper/<项目>/{paper.md,paper.tex,paper.meta.json,paper.log.md}`（检测到引擎时才有 `paper.pdf`）。手动：`/vibe paper [lang=zh|en] [format=both|md|tex] [force]`。PDF 需要宿主上有 LaTeX 引擎（中文优先 `xelatex`）；没有引擎或编译失败时 tex+md 照常交付，只记日志告警——不阻塞定稿、不覆盖已有 pdf。完整契约见 `docs/final-paper.md`。
 
 ### v3（论文式 md + 规划代理 + 方法库）默认值
 
@@ -750,6 +759,15 @@ v5 的完整架构（含成员生命周期、一轮时序、共识状态机、
 | `leanCommand` | `'lean'` | 要执行的 Lean 可执行文件（例：`'lake'`） |
 | `leanArgs` | `[]` | 插在文件名之前的附加参数（例：`['env','lean']` 配合 `leanCommand='lake'`） |
 | `leanTimeoutMs` | `120000` | 单次 Lean 运行的上限（毫秒） |
+| `finalPaper` | `true` | **最终论文**：收口时自动撰写（`false` 只关自动触发，手动命令仍可用）。完整契约见 `docs/final-paper.md` |
+| `paperFormat` | `both` | 论文产出格式：`both`（md+tex）/ `md`（跳过编译，且不报"缺 tex"）/ `tex` |
+| `paperLanguage` | `zh` | 论文语言：`zh`（ctexart，引擎优先 xelatex）/ `en`（article，pdflatex 优先） |
+| `paperCompilePdf` | `true` | 检测到 LaTeX 时编译 `paper.pdf`；无引擎或编译失败则保留 tex+md 并记日志告警 |
+| `paperLatexCommand` | `''` | 指定 LaTeX 引擎可执行文件（空 = 按语言自动探测 xelatex→latexmk→pdflatex→lualatex→tectonic） |
+
+#### 最终论文（final paper）
+
+v3 与 v2 同一开关、同一时序（严格收口；**在调度器停止之前**派遣撰写者）：专职「论文撰写」子代理产出 `Paper/<项目>/{paper.md,paper.tex,paper.meta.json,paper.log.md}`（检测到引擎时才有 `paper.pdf`）。手动：`/vibe paper [lang=zh|en] [format=both|md|tex] [force]`。无引擎或编译失败仍交付 tex+md、记警告、不阻塞定稿。完整契约见 `docs/final-paper.md`。
 
 ### v4（常驻自组织 · 实验）默认值
 
@@ -772,6 +790,16 @@ v5 的完整架构（含成员生命周期、一轮时序、共识状态机、
 | `leanCommand` | `'lean'` | 要执行的 Lean 可执行文件（例：`'lake'`） |
 | `leanArgs` | `[]` | 插在文件名之前的附加参数（例：`['env','lean']` 配合 `leanCommand='lake'`） |
 | `leanTimeoutMs` | `120000` | 单次 Lean 运行的上限（毫秒） |
+| `finalPaper` | `true` | **最终论文**：收口时自动撰写（`false` 只关自动触发，手动命令仍可用）。完整契约见 `docs/final-paper.md` |
+| `paperFormat` | `both` | 论文产出格式：`both`（md+tex）/ `md`（跳过编译，且不报"缺 tex"）/ `tex` |
+| `paperLanguage` | `zh` | 论文语言：`zh`（ctexart，引擎优先 xelatex）/ `en`（article，pdflatex 优先） |
+| `paperCompilePdf` | `true` | 检测到 LaTeX 时编译 `paper.pdf`；无引擎或编译失败则保留 tex+md 并记日志告警 |
+| `paperLatexCommand` | `''` | 指定 LaTeX 引擎可执行文件（空 = 按语言自动探测 xelatex→latexmk→pdflatex→lualatex→tectonic） |
+| `paperEditor` | `office` | 定稿代表：`office`（会话根/人类侧，默认）或 `resident:<id>`（该 resident 已离职则降级 office 并在 meta/log 记明） |
+
+#### 最终论文（final paper）
+
+默认开启；v4 在一致性会议投出「一致停止」票后、**标记完成之前**进入 paper 阶段。团队流程：各 resident 写自己库里的部分 → 合并（去重、统一术语与记号）→ 至少一轮**交叉互审** → 定稿代表按 `paperEditor`（默认 `office`，或 `resident:<id>`）梳理成最终稿 → **全体明确"可交付"**才定稿（有反对则继续迭代，超轮次上限记警告并把分歧写进附录）。手动：`/v4 paper [lang=] [format=] [editor=office|resident:<id>] [force]`。产物 `Paper/<run id>/{paper.md,paper.tex,paper.meta.json,paper.log.md}`（引擎可用时另有 `paper.pdf`）。完整契约见 `docs/final-paper.md`。
 
 ### v5（研究所体系 · 实验）默认值
 
@@ -803,6 +831,16 @@ v5 的完整架构（含成员生命周期、一轮时序、共识状态机、
 | `leanCommand` | `'lean'` | 要执行的 Lean 可执行文件（例：`'lake'`） |
 | `leanArgs` | `[]` | 插在文件名之前的附加参数（例：`['env','lean']` 配合 `leanCommand='lake'`） |
 | `leanTimeoutMs` | `120000` | 单次 Lean 运行的上限（毫秒） |
+| `finalPaper` | `true` | **最终论文**：收口时自动撰写（`false` 只关自动触发，手动命令仍可用）。完整契约见 `docs/final-paper.md` |
+| `paperFormat` | `both` | 论文产出格式：`both`（md+tex）/ `md`（跳过编译，且不报"缺 tex"）/ `tex` |
+| `paperLanguage` | `zh` | 论文语言：`zh`（ctexart，引擎优先 xelatex）/ `en`（article，pdflatex 优先） |
+| `paperCompilePdf` | `true` | 检测到 LaTeX 时编译 `paper.pdf`；无引擎或编译失败则保留 tex+md 并记日志告警 |
+| `paperLatexCommand` | `''` | 指定 LaTeX 引擎可执行文件（空 = 按语言自动探测 xelatex→latexmk→pdflatex→lualatex→tectonic） |
+| `paperEditor` | `academician` | 定稿代表：`academician`（默认，无人值守也能完成）或 `office`（仅手动 `/v5 paper editor=office`，须先与全所交流 + 开会） |
+
+#### 最终论文（final paper）
+
+默认开启；v5 在 `checkSolved` 判定「已解决」后、**标记完成之前**进入 paper 阶段。常驻研究员与院士各自写、合并、交叉互审，定稿代表由 `paperEditor` 决定：**自动流程固定用 `academician`**（所办是根会话，没有唤醒路径）；`office` 只能通过手动 `/v5 paper editor=office` 选择，此时**所办必须先与全所交流、商讨、优化、审查**（≥1 条 `vibe_v5_message` + ≥1 次 `vibe_v5_meeting`），把结论写进定稿说明，再调用 `vibe_v5_finalize_paper`；缺一即被拒（`V5_PAPER_CONSULT_REQUIRED`）。工具入口：`vibe_v5_paper`、`vibe_v5_finalize_paper`。产物 `Paper/<研究所 id>/{paper.md,paper.tex,paper.meta.json,paper.log.md}`（引擎可用时另有 `paper.pdf`）。完整契约见 `docs/final-paper.md`。
 
 常用控制：`vibe_v5_configure`（先配置）→ `vibe_v5_start`（开工）→ `vibe_v5_report` / `vibe_v5_status`；`vibe_v5_message` / `vibe_v5_meeting` / `vibe_v5_members` / `vibe_v5_hire` / `vibe_v5_fire`（临时工）/ `vibe_v5_add_researcher` / `vibe_v5_remove_researcher`（增删常驻，仅所办）/ `vibe_v5_pause` / `vibe_v5_resume` / `vibe_v5_stop`；斜杠命令 `/v5`。
 
@@ -826,8 +864,9 @@ v5 的完整架构（含成员生命周期、一轮时序、共识状态机、
 - **四套 Lean 提示词语料**：[`prompt-corpus-v2/formal-verify-v2.md`](prompt-corpus-v2/formal-verify-v2.md) · [`prompt-corpus-v3/formal-verify-v3.md`](prompt-corpus-v3/formal-verify-v3.md) · [`prompt-corpus-v4/formal-verify-v4.md`](prompt-corpus-v4/formal-verify-v4.md)（各自覆盖 off / encourage / **require** / 忠实性分支 / 工作轮 / 回执契约；工作区归一化为 `<WS>`、VibeMath 根为 `<VIBEMATH>`）
 - **四个预设的 persona 原文**：[`prompt-corpus-persona/persona-corpus.md`](prompt-corpus-persona/persona-corpus.md)（主代理实际收到的提示词：有哪些工具、哪些参数、哪些斜杠子命令；由 `audit-persona-surface.test.mjs` 生成，随包发布）
 - **Lean 形式化验证（四架构共用契约）**：[`docs/formal-verification.md`](docs/formal-verification.md)
-- **测试耗时基线与并行跑法**：[`docs/test-timing.md`](docs/test-timing.md)（`node tests/run-tests.mjs` 并行跑**全部套件 + 全部探针**：`TOTAL 56`（38 套件 + 18 探针/变体）≈3.5 min；哪 18 项随包发布、哪些仅仓库见该文档 §1.1；每个 runner 都会打印耗时/加速比供下次选策略）
-- **静态提示词面一致性（persona ↔ 工具注册表 ↔ 斜杠命令 hint/usage）**：[`audit-persona-surface.test.mjs`](tests/audit-persona-surface.test.mjs)（196 条断言，并生成 [`prompt-corpus-persona/persona-corpus.md`](prompt-corpus-persona/persona-corpus.md) 供人工复核）+ [`audit-persona-sensitivity.mjs`](tests/audit-persona-sensitivity.mjs)（11 条灵敏度探针）——守"注册的工具必须在 persona 里出现 / persona 里的名字必须真的注册 / `prefix` 与 `text` 两块逐行一致 / hint、usage、实际分支三处必须一致"
+- **最终论文（四架构共用契约）**：[`docs/final-paper.md`](docs/final-paper.md)（五个参数与 v4/v5 的 `paperEditor`、收口顺序"先论文后完成"、`Paper/<id>/` 产物与 9 节骨架、LaTeX 检测顺序与"先修复后降级"、v4/v5 团队合写流程与 v5 所办咨询规则）
+- **测试耗时基线与并行跑法**：[`docs/test-timing.md`](docs/test-timing.md)（`node tests/run-tests.mjs` 并行跑**全部套件 + 全部探针**：`TOTAL 57`（39 套件 + 18 探针/变体）≈3.5 min；哪 18 项随包发布、哪些仅仓库见该文档 §1.1；每个 runner 都会打印耗时/加速比供下次选策略）
+- **静态提示词面一致性（persona ↔ 工具注册表 ↔ 斜杠命令 hint/usage）**：[`audit-persona-surface.test.mjs`](tests/audit-persona-surface.test.mjs)（208 条断言，并生成 [`prompt-corpus-persona/persona-corpus.md`](prompt-corpus-persona/persona-corpus.md) 供人工复核）+ [`audit-persona-sensitivity.mjs`](tests/audit-persona-sensitivity.mjs)（16 条灵敏度探针）——守"注册的工具必须在 persona 里出现 / persona 里的名字必须真的注册 / `prefix` 与 `text` 两块逐行一致 / hint、usage、实际分支三处必须一致"
 - **全面检查必查清单**：[`AUDIT-CHECKLIST.md`](docs/AUDIT-CHECKLIST.md)（本仓库的强制审计流程；§1.9 专门查"工具参数 schema 收不收得下"）
 - **提示词/交互不变式（四套一起，可一键复核）**：[`audit-prompt-invariants.mjs`](tests/audit-prompt-invariants.mjs)（157 条断言）——把"历史上真实发生过的提示词/工具面缺陷类别"逐条编码成静态不变式（缩写工具名、把忠实性缺陷投成 0、`defect` 只写在提示词里没实现、回执契约缺 `defect`、无 note 放行、字段名错、`off` 档回执仍能写状态、语料不确定、探针缺失、**工具的封闭 schema 收不下它自己文档里的参数**、**schema 声明了参数层却静默丢弃的键**）。加 `--self-probe` 会在内存里注入这些缺陷形状，要求对应不变式**变红**、未变异的对照跑**仍为绿**（5/5）；脚本自身另带 X5–X8b 六条自检（注释扫描器必须认正则字面量——包括 `return /…/ ` 这种**关键字后面**的正则——字符串里的 `//` 必须保留、抹注释不改变行结构，以及"四套源码抹掉注释后仍必须能被 `node --check` 解析"这条解析级判据）
 - **规格 ↔ 代码可追溯（四套一起）**：[`audit-spec-traceability.mjs`](tests/audit-spec-traceability.mjs)（94 条断言）——`实现方案.md`/README 里承诺的工具必须真的注册；四个 Lean 参数必须同时被文档与代码接受

package/cordis.patch.yml

@@ -70,7 +70,7 @@
                 - vibe_math_status / vibe_math_report — read scheduler status / full progress report (report also writes Progress_Logs/report.json).
                 - vibe_math_pause / vibe_math_abort — pause / abort (abort interrupts all children).
                 - vibe_math_set_mode {mode: manual|auto} — switch manual / auto control.
-                - vibe_math_set_params {...} — tune any parameter (see vibe_math_setup for the full schema; e.g. reportMode file|push|both, promoteValueThreshold, verdictMode flat|forced, formalVerify off|encourage|require).
+                - vibe_math_set_params {...} — tune any parameter (see vibe_math_setup for the full schema; e.g. reportMode file|push|both, promoteValueThreshold, verdictMode flat|forced, formalVerify off|encourage|require, finalPaper true|false, paperFormat both|md|tex, paperLanguage zh|en, paperCompilePdf true|false, paperLatexCommand <engine>).
                 - vibe_math_setup / vibe_math_save_settings / vibe_math_template — guided configuration / persist defaults / generate template.
                 - vibe_math_new_project / vibe_math_set_project / vibe_math_list_projects — per-project folders.
                 - vibe_math_list_decisions / vibe_math_decide {id, action: approve|reject|override, verdict?} — resolve manual decisions.
@@ -79,7 +79,12 @@
                   verification (execute / archive / list the reuse library). The scheduler's child agents
                   use them too; they work in every mode.
 
-                A /vibe slash command mirrors the main controls. Data lives under {{cwd}}/VibeMath/Projects/<project>/
+                Final paper: strict termination writes Paper/<project>/{paper.md,paper.tex,paper.pdf,paper.meta.json,paper.log.md}
+                automatically — a dedicated paper-writing child assembles the solved material (finalPaper=false disables only that
+                automatic run). /vibe paper [lang=zh|en] [format=both|md|tex] [force] writes or rewrites it by hand. md/tex follow
+                paperFormat; a PDF is produced only when a LaTeX engine is detected and paperCompilePdf is true.
+                A /vibe slash command mirrors the main controls (/vibe start|resume|pause|abort|status|report|mode <auto|manual>|setup|save|template [global|project]|add <id> <desc>|add-proposition <id> <概述>|list-propositions|project [list|new <name>|<name>]|decisions|agents|paper [lang=zh|en] [format=both|md|tex] [force]).
+                Data lives under {{cwd}}/VibeMath/Projects/<project>/
                 (qs/qs.json, Propos/<分类>_Propos.json, Reliable/, Verified/, Verification_logs/, Progress_Logs/, VibeMath_State/)
                 and survives restarts via vibe_math_resume.
 
@@ -341,7 +346,10 @@
                   plannerEnabled/plannerProvider/plannerModel/plannerPersona, planMinIntervalMs, plannerMaxFails,
                   methodKeepIntervalMs/methodKeepEvery, methodAutoPromote, indexAutoRebuild, projectLockTimeoutMs,
                   formalVerify/leanCommand/leanArgs/leanTimeoutMs — Lean 形式化验证（off = 默认不额外要求，
-                  encourage = 按实现难度自行形式化、Lean 通过后审查对象变为忠实性，require = 同上并加结论门禁）).
+                  encourage = 按实现难度自行形式化、Lean 通过后审查对象变为忠实性，require = 同上并加结论门禁）,
+                  finalPaper/paperFormat/paperLanguage/paperCompilePdf/paperLatexCommand — 最终论文（收口时自动派遣
+                  「论文撰写」子代理，把已收口的解法/命题/成果整理成 Paper/<project>/；finalPaper=false 只关自动触发，
+                  /vibe paper 仍可手动触发）。
                 - vibe_math_setup / vibe_math_save_settings / vibe_math_template — guided configuration / persist defaults / generate template.
                 - vibe_math_plan {force?} — show queued plan / last plan, or force a planning round.
                 - vibe_math_index — rebuild State/index.json from the Markdown knowledge base.
@@ -356,7 +364,7 @@
                   use them too; they work in every mode.
 
                 A /vibe slash command mirrors the main controls (/vibe start [override]|resume [override]|pause|abort|status|report|mode
-                <auto|manual>|setup|save|add <id> <desc>|add-proposition <id> <概述>|list-propositions|methods|index|plan|lock|...).
+                <auto|manual>|setup|save|template [global|project]|add <id> <desc>|add-proposition <id> <概述>|list-propositions|methods|index|plan|lock|project [list|new <name>|<name>]|decisions|agents|paper [lang=zh|en] [format=both|md|tex] [force]).
                 Data survives restarts via vibe_math_resume.
 
                 Key rules when reporting: a problem is "solved" when one of its 解法候选 entries reaches 概率 = 1
@@ -627,7 +635,7 @@
                 Main controls (recommended flow: configure FIRST, then start):
                   - vibe_v4_configure {project?, problem?, params?} — create/configure the project (name, problem, params) WITHOUT starting a run; set everything here first.
                   - vibe_v4_start {problem?, residentCount?, seedDirections?} — begin the run (spawn residents, brainstorm). If problem was configured, omit it.
-                  - vibe_v4_set {residentCount, compactThreshold, compactAfterRounds, meetingKeepEvery, maxParallel, activityTimeoutMs, stallAutoMeetingMs, verdictMaxRounds, provider, model, residentPersona, toolAllow, toolDeny, formalVerify, leanCommand, leanArgs, leanTimeoutMs} — tune params (persisted to the settings file). provider/model override the residents' LLM route (empty = they inherit YOUR model/provider); toolAllow/toolDeny are per-resident tool permissions (empty = they inherit all tools). stallAutoMeetingMs is the stalled-group auto-sync-meeting threshold (分级保活 B). formalVerify (off|encourage|require, default off) enables Lean formal verification; leanCommand/leanArgs/leanTimeoutMs configure the toolchain.
+                  - vibe_v4_set {residentCount, compactThreshold, compactAfterRounds, meetingKeepEvery, maxParallel, activityTimeoutMs, stallAutoMeetingMs, verdictMaxRounds, provider, model, residentPersona, toolAllow, toolDeny, formalVerify, leanCommand, leanArgs, leanTimeoutMs, finalPaper, paperFormat, paperLanguage, paperCompilePdf, paperEditor, paperLatexCommand} — tune params (persisted to the settings file). provider/model override the residents' LLM route (empty = they inherit YOUR model/provider); toolAllow/toolDeny are per-resident tool permissions (empty = they inherit all tools). stallAutoMeetingMs is the stalled-group auto-sync-meeting threshold (分级保活 B). formalVerify (off|encourage|require, default off) enables Lean formal verification; leanCommand/leanArgs/leanTimeoutMs configure the toolchain. The FINAL PAPER is tuned by finalPaper (true|false, default true), paperFormat (both|md|tex), paperLanguage (zh|en), paperCompilePdf (true|false), paperEditor (office|resident:<id>, default office = the human/assistant side finalises) and paperLatexCommand.
                   - vibe_v4_resume / vibe_v4_pause / vibe_v4_abort / vibe_v4_status / vibe_v4_report.
                   - vibe_v4_message {to|all, content} — inject a message to a resident (human/assistant intervention).
                   - vibe_v4_meeting {agenda} — force a meeting.
@@ -638,7 +646,11 @@
                   - vibe_v4_formal_report — human-readable Lean formal-verification mirror (mode, Lean-passed
                     objects, recorded blockers, formalization TODO, library paths).
                   - vibe_v4_prompts {which: brainstorm|normal|heartbeat|meeting|verify|coreRules, member?, target?, stage?} — read the exact prompt text a resident would receive (prompt auditing; prompt text is the product).
-                A /v4 slash command mirrors the main controls (configure|start [problem]|resume|pause|abort|status|report|message <to|all> <content>|meeting|members|add|remove|set <k=v>...).
+                A /v4 slash command mirrors the main controls (configure|start [problem]|resume|pause|abort|status|report|message <to|all> <content>|meeting|paper [lang=zh|en] [format=md|tex|both] [editor=office|resident:<id>] [force]|members|add|remove|set <k=v>...).
+                Final paper: after the unanimous stop vote the run enters a PAPER phase — every resident writes their part, each
+                cross-reviews at least one other part, and the paperEditor finalises (office = the human/assistant side, or one named
+                resident); only then is the run marked complete. finalPaper=false skips the phase; /v4 paper [lang=zh|en]
+                [format=md|tex|both] [editor=office|resident:<id>] [force] starts or re-runs it by hand.
 
                 TRUST RULE: only Verified/ (and Propos/ entries marked 已验证·真/假) are absolutely
                 trustworthy; everything else — unverified resident claims, Progress/, Method claims —
@@ -941,17 +953,19 @@
                 Main controls (recommended flow: configure FIRST, then start):
                   - vibe_v5_configure {project?, institute?, problem?, params?} — create/configure the institute WITHOUT starting it.
                   - vibe_v5_start {problem?, researcherCount?, academician?, seedDirections?} — found the institute (academician + researchers) and begin.
-                  - vibe_v5_set {…} — tune params (persisted). provider/model override staff LLM routes (empty = inherit YOUR route); toolAllow/toolDeny restrict staff tools.
+                  - vibe_v5_set {…} — tune params (persisted). provider/model override staff LLM routes (empty = inherit YOUR route); toolAllow/toolDeny restrict staff tools; finalPaper/paperFormat/paperLanguage/paperCompilePdf/paperEditor/paperLatexCommand tune the FINAL PAPER.
                   - vibe_v5_pause / vibe_v5_resume / vibe_v5_stop / vibe_v5_status / vibe_v5_report.
                   - vibe_v5_message {to|all, content} — relay a human message into the institute.
                   - vibe_v5_meeting {agenda, kind} — convene a meeting.
                   - vibe_v5_members — roster (office/employer/status/direction).
                   - vibe_v5_hire / vibe_v5_fire — temp workers: hire one (office, academician or a permanent researcher) / dismiss one for real.
                   - vibe_v5_add_researcher / vibe_v5_remove_researcher — OFFICE only: add or dismiss a PERMANENT researcher (the academician can only propose those).
+                  - vibe_v5_paper {lang?, format?, editor?, force?} — write the FINAL PAPER: the permanent staff write their own parts, cross-review each other, then the editor finalises. lang/format/editor override this one paper only.
+                  - vibe_v5_finalize_paper {decision, note, conclusion?} — OFFICE only when paperEditor=office: consult the institute first (>=1 office message + >=1 meeting), then finalise and put the conclusion in note.
                   - vibe_v5_lean_run / vibe_v5_lean_archive / vibe_v5_lean_lib — Lean formal
                     verification (execute / archive / list the reuse library). Members use them
                     too; they work in every mode.
-                A /v5 slash command mirrors these (configure|start|resume|pause|stop|status|report|members|message|meeting|hire|fire|add|remove|set).
+                A /v5 slash command mirrors these (configure|start|resume|pause|stop|status|report|members|message|meeting|hire|fire|add|remove|set|paper).
 
                 LEAN FORMAL VERIFICATION (formalVerify, a tunable parameter):
                   - 'off' (default, no extra requirement) | 'encourage' (members decide by

package/docs/AUDIT-CHECKLIST.md

@@ -95,7 +95,7 @@
 - [ ] 人设里写的路径/模式名（`Formal/Lib`、`off|encourage|require`）是否与实现中的字符串**逐字**一致？
 
 `audit-persona-surface.test.mjs` 把上述各条变成断言（"未文档化工具"用**显式快照**表示：
-新增工具必须主动改快照、或在 persona 里写清）；`audit-persona-sensitivity.mjs` 用 11 条探针
+新增工具必须主动改快照、或在 persona 里写清）；`audit-persona-sensitivity.mjs` 用 16 条探针
 证明这套断言真的会变红。**v2.3.0 修的就是这一类缺陷**：三个 `*_lean_*` 工具无条件注册，
 而 v2/v3/v4 的 persona 从未列出它们（只有 v5 列了），v4 的 `vibe_v4_set` 参数表也漏了
 `formalVerify`/`leanCommand`/`leanArgs`/`leanTimeoutMs`——当时**所有既有套件全绿**。
@@ -217,7 +217,7 @@ v2/v3/v4/v5 是**同构实现**（同一份契约、四份独立代码，刻意
       **逐行比对**（`_oneoff/layout-invariance.mjs`）；③ 相对链接扫描 0 失效（`_oneoff/scan-links.mjs`）。
 - [ ] 讲"全套件 / 门禁 / 多少次全绿"时，是否区分了**随包发布面**与**仓库**？`package.json` 的 `files`
       只发 `tests/` 的 **18 项**（其中 `.test.mjs` **10** 个），完整门禁（`node tests/run-tests.mjs`，
-      Round B 起 **56 项 = 38 套件 + 18 探针/变体**）只在开发检出里成立。两边的清单见
+      Round B 起 **57 项 = 39 套件 + 18 探针/变体**）只在开发检出里成立。两边的清单见
       `docs/test-timing.md` §1.1；发布物里的 runner 会把缺失/跳过项**打印出来**（不会静默少跑），
       所以"安装用户照文档跑得到全套件"这类说法必须避免。
 - [ ] **runner 本身也要跑一遍**：直接跑套件通过 ≠ 并行 runner 通过（2.3.13 就出现过

package/docs/final-paper.md

@@ -0,0 +1,171 @@
+# 最终论文（final paper）——四套预设的统一契约
+
+> **这是随包发布的绑定契约。** v2 / v3 / v4 / v5 四个预设的 final-paper 参数、命令、触发时序、
+> 产物与守卫都以本文为准；`实现方案.md` 与工具描述是它的实现说明，冲突时以本文为准。
+>
+> 本文由**用户已确认的规格**（仓库外的 `_oneoff/spec-final-paper.md`）与其后的**设计审计修订**
+> （`_oneoff/spec-final-paper-v2-amendments.md`）合并而成。两份原始文件不在发布物里，所以契约
+> 现在落在仓库内；两者冲突处以**修订**为准，合并时不做美化——修订推翻 v1 的地方在下面写明。
+>
+> 实现位置：v2/v3 的 paper 段（`/vibe paper`）、`vibe-math-v4.js` 的 paper 流程（`/v4 paper`）、
+> `vibe-math-v5.js` 的 paper 流程（`/v5 paper` + `vibe_v5_paper` / `vibe_v5_finalize_paper`）。
+
+## 1. 一句话
+
+四个预设都**默认开启**最终论文：当各自的收口信号命中时，**先进入 paper 阶段，论文完成（或降级结束）
+之后才把这次 run 标记为完成**。论文只整理已有证据，产物落在 `Paper/<运行或研究所 id>/`，
+文本版永远交付，PDF 只在宿主真的检测到 LaTeX 引擎时才尝试编译。
+
+## 2. 参数
+
+参数进入各预设既有的参数体系（`setParams` 工具的 schema + 帮助文本 + 命令 hint），默认值如下：
+
+| 参数 | 类型 | 默认 | 作用域 | 说明 |
+|---|---|---|---|---|
+| `finalPaper` | boolean | `true` | 四套 | 收口时是否**自动**撰写最终论文。`false` 只关自动触发，手动命令仍可用（返回里会写明"自动已关闭"） |
+| `paperFormat` | enum `both`\|`md`\|`tex` | `both` | 四套 | 产出哪几种文本版本；`md` 不产出 tex、因此跳过编译，且**不得**报"缺 tex"警告 |
+| `paperLanguage` | enum `zh`\|`en` | `zh` | 四套 | 论文语言，同时决定 LaTeX 模板（`ctexart`/`article`）与引擎优先顺序 |
+| `paperCompilePdf` | boolean | `true` | 四套 | 检测到 LaTeX 时是否编译 `paper.pdf` |
+| `paperLatexCommand` | string | `''` | 四套 | 强制指定**一个**引擎可执行文件；空 = 按语言自动探测。指定但解析不到时按"未检测到"降级 |
+| `paperEditor` | enum | v4 `office`；v5 `academician` | **仅 v4/v5** | 定稿代表。v4：`office`（会话根/人类侧）或 `resident:<id>`；v5：`academician` 或 `office`（见 §7） |
+
+归一化：**枚举**的非法值一律回退到上表默认值（绝不回退到更强的档位）；**未知键不会直通参数层**
+（v2/v3 的参数归一化只遍历已知默认键，v4 把被忽略的键列在返回的 `ignored` 里，v5 的 set-schema 是闭集，
+新键必须同时进闭集与枚举校验，参照 `quorumMode`）。**boolean** 接受 `true`/`false`；v4/v5 另外接受
+`1/0/yes/no/on/off` 等拼写——命令行的 `k=v` 传的是原始字符串，`'false'` 必须真的变成 `false`，
+不能保持真值；v2/v3 只接受真正的 JSON boolean，其余值回退默认。
+
+## 3. 自动触发：用**真实的**收口信号，且先论文、后完成
+
+各预设的收口信号以代码中的精确分支为准（v1 规格曾写成"更强的完整性判据"，那会永不触发；此处按修订修正）：
+
+- **v2**：严格终止（任务清空且无在途）。**「论文撰写」子代理本身不计入"在途"**——否则撰写者会阻止收口。
+- **v3**：`checkTermination` 的完整收口分支；真实的完整性判据是 `leftoverVerify`（不是"`Verified/` 全覆盖"）。
+- **v4**：一致性会议的**一致停止票**（`finalizeMeeting` 的 `allSolved` 分支）；该分支会忽略并清空待验证对象与邮箱。
+- **v5**：`checkSolved` 在**每一次解题票**上判定（不要求 verify/meeting 前置）。
+
+**时序（修订 §A，HIGH）**：论文阶段必须发生在"标记完成"**之前**。收口分支一旦同时置
+`running=false; autoDone=true`（v4）或 `phase='solved'`（v5），`startMeeting` / `wakeIfIdle` /
+`onResidentEnd` / `scheduleNext` 都会拒绝，团队就再也无法合写与互审。因此：
+
+- v4 在 `finalizeMeeting` 的 `allSolved` 分支内、v5 在 `checkSolved` 与 `finishRun` 之间**拦截**，
+  先进入 paper 阶段，用既有的会议/唤醒机制完成合写与审稿，论文结束（或降级结束）后才真正置完成标志；
+- v2/v3 **在停止翻转之前**派遣「论文撰写」子代理（`scheduler.running=false` 之后 `scheduleTick()` 是空操作，
+  而且 v2/v3 没有激活上限处理，被拒/失败的撰写者会静默消失）。
+
+**幂等**：同一 run 只写一次。`paper.meta.json` 记 `finalizedAt`；重复触发**只补写缺失产物**。
+`finalPaper=false` 只关闭上面这条自动路径。
+
+## 4. 手动命令
+
+| 预设 | 命令 | 说明 |
+|---|---|---|
+| v2 / v3 | `/vibe paper [lang=zh\|en] [format=both\|md\|tex] [force]` | 单作者流程 |
+| v4 | `/v4 paper [lang=zh\|en] [format=both\|md\|tex] [editor=office\|resident:<id>] [force]` | 团队流程，`editor=` 只作用于本次 |
+| v5 | `/v5 paper [lang=zh\|en] [format=both\|md\|tex] [editor=office\|academician] [force]` | 团队流程；`editor=office` 走人工定稿路径（§7） |
+
+- 命令行覆盖只作用于**本次**调用，不写回持久参数（v5 的 `editor=` 是一次性的）。
+- 非法参数一律 `kind:'error'`（绝不静默成功）；`force` 重写已定稿的论文。
+- v5 另有工具入口 `vibe_v5_paper`（与命令同义）与 `vibe_v5_finalize_paper`（所办定稿）。
+
+## 5. 产物
+
+目录：`Paper/<运行或研究所 id>/`（id 经各预设既有的 `slugify`/`safeId`/`idSafe` 归一化，
+所有路径经同一个 `Paper/` 构造器，只写这个目录内，不污染 `Verified/`、`State/`）。
+
+| 文件 | 何时出现 |
+|---|---|
+| `paper.md` | `paperFormat` 含 `md`（`both`/`md`） |
+| `paper.tex` | `paperFormat` 含 `tex`（`both`/`tex`） |
+| `paper.pdf` | 仅在编译器**真的跑通**时出现 |
+| `paper.meta.json` | 总是：参数、触发原因、运行 id、`finalizedAt`、编译状态与引擎、v5 的咨询计数等 |
+| `paper.log.md` | 总是：谁写了什么、谁提了什么意见、如何采纳（人读审计链） |
+
+宿主 fs 只支持**文本写**（没有 `writeBytes`），所以 `paper.pdf` **只能由编译器子进程**在论文目录内产生，
+插件只做存在性校验，绝不自己写二进制，也**绝不覆盖已存在的 pdf**。
+
+## 6. 论文骨架（四套一致，9 节）
+
+1. 标题、作者（预设名 + 运行/研究所标识）、日期、摘要（原问题 + 主要结论）
+2. 引言与问题背景（原问题的完整陈述）
+3. **原问题的完整解法**（最终答案 + 完整推理链）
+4. **已检验通过的命题**（逐条列出，含判定为真的估计值与证据来源）
+5. **已解决的子问题 / 中间成果**
+6. **创造或发现的有价值之物**：方法、理论、思想、有价值经验、数学理解
+7. **规律总结**（从上述条目归纳出的可复用规律）
+8. 讨论、局限与展望
+9. 附录：证据与文件索引（`Verified/`、`Logs/`、关键卡片路径）
+
+写法要求：只写有证据支撑的内容；**未决 / 被否证的条目必须显式标注**；不得编造。
+
+## 7. 写作流程
+
+**v2 / v3（单作者）**：派遣一名专职「论文撰写」子代理，输入 = 汇总材料（命题 / 子问题 / 成果 /
+规律线索 + 证据索引），产出 = 完整 md 正文（含 tex 用的结构标记）；插件负责落盘 md/tex 与编译。
+
+**v4 / v5（团队合写）**：
+
+1. 各自写自己负责的部分（v4：各 resident 写自己库里的内容；v5：各常驻研究员/院士写自己负责的部分）；
+2. **合并**（去重、统一术语、统一符号）；
+3. **互检/审稿**：至少一轮交叉审阅（每人审他人的部分，指出问题并优化）；
+4. **定稿**：定稿代表按 `paperEditor` 梳理成最终稿；
+5. **一致认同**才定稿：所有参与成员明确表示"可交付"；有反对则继续迭代（有轮次上限，超限记警告并把分歧写进附录）。
+
+定稿代表：
+
+- **v4**：`paperEditor` 默认 `office`（= 会话根 / 人类侧；`facilitator` 不在编制里、没有 LLM，不能当作作者），
+  另可选 `resident:<id>`。指定的 resident 已离职时**降级到 office** 并在 `paper.meta.json` 与 `paper.log.md` 记明。
+- **v5**：`paperEditor` 默认 `academician` —— 这是**无人值守也能完成**的路径（所办是根会话，没有唤醒路径，
+  自动收口触发必须用院士）。`office` 只在手动 `/v5 paper editor=office` 时可用，并且
+  **所办必须先与全所交流、商讨、优化、审查**：至少 1 条所办消息（`vibe_v5_message`）**且**至少 1 次会议
+  （`vibe_v5_meeting`），结论写进定稿说明，然后调用 `vibe_v5_finalize_paper`。
+  两个计数记在 `paper.meta.json`；缺一即 `V5_PAPER_CONSULT_REQUIRED`（不是静默跳过）。
+
+## 8. LaTeX 检测、编译与降级
+
+- **检测**走 `subprocess.resolveExecutable`：`paperLatexCommand` 非空时**只用它**（不猜）；
+  空则按语言探测 —— 中文 `xelatex` → `latexmk` → `pdflatex` → `lualatex` → `tectonic`
+  （xelatex 对 CJK 开箱可用），英文 `pdflatex` 优先，其余同理。
+- **编译**在论文目录内执行、`-interaction=nonstopmode`、跑两遍（`latexmk`/`tectonic` 用各自参数）。
+- **先修复、后降级**（有收敛上限）：换引擎重试 → `nonstopmode` 重跑 → 换最小模板
+  （`ctexart` / `article`）再试一次；到达上限就**保留 tex+md**，`paper.meta.json` 记
+  `compile: 'failed'`（或未检测到时的 `'not-detected'`），**警告 + 上报**，但**不阻塞定稿**、
+  **不抛错**、**不覆盖已有 pdf**，也绝不改写论文内容。
+- `paperFormat=md` 时根本不产出 tex，编译直接 `skipped`，不得产生"缺 tex 无法编译"的警告。
+- tex 模板：中文 `ctexart`（xelatex），英文 `article`；只用常见宏包（`amsmath`、`amssymb`、`amsthm`、
+  `geometry`、`hyperref`、`longtable`、`booktabs`）；转义所有 `_ % & # $ { } ~ ^ \`。
+- 记录：规格确认时本机**没有任何 LaTeX 引擎**，所以真机走的是"未检测到 → 只交 tex+md"分支；
+  编译成功 / 修复后成功 / 持续失败三条路径由守卫里的**假编译器**覆盖（见 §10）。
+
+## 9. 幂等与可审计
+
+- 幂等键 = **run id + `finalizedAt` + 逐产物存在性检查**（不使用多文件稳定哈希）；
+  重复触发只补写缺失产物，`force` 才重写。
+- v2 的收口判据含 `agentRegistry=={}` ⇒ 撰写子代理被排除在收口判据之外（§3）；v3 在触发前已释放项目锁，
+  因此论文落盘要**原子 + 幂等**（可加 paper 作用域锁），避免两个会话写同一棵树。
+- 每次触发、每次派遣、每次编译、每次降级都追加 `paper.log.md`，并在活动日志里留一条。
+
+## 10. 守卫与验证要求
+
+每条不变式都要有断言，且要么有灵敏度探针证明它会变红，要么在探针里写明为什么不可达：
+
+- 参数默认值 / schema 存在性 / 非法值回退；五个（v4/v5 六个）参数同时出现在工具 schema 与帮助文本里；
+- 触发判定的正负用例：未收口不触发、收口触发、`finalPaper=false` 不触发、重复触发幂等；
+- 内容生成：假 LLM/假成员回应驱动，断言 md/tex 两版产出、9 节骨架齐全、证据索引存在、未决项被标注；
+- 编译分支：假编译器覆盖"成功 → pdf""失败 → 修复后成功""持续失败 → 降级 + 警告"三条路径；
+  真机无 LaTeX 时断言走"未检测到"分支且不报错；
+- 路径与越权：只写 `Paper/<id>/` 内、id 归一化（防路径逃逸）、与 `Verified/`/`State/` 不互相污染；
+- 命令：`/vN paper` 的参数覆盖、`force` 与非法参数 `kind:'error'`；
+- 团队流程（v4/v5）：断言"各部分 → 合并 → 互审 → 定稿"的消息序列；`paperEditor` 两种取值都可用；
+  v5 选 `office` 时**确有**交流与会议记录（负用例：未咨询就定稿必须被拒），未达成一致认同时不定稿。
+
+现有守卫：`tests/v4-final-paper.test.mjs`（v4 团队流程与产物）、`tests/e2e-v5-round2.test.mjs`
+（v5 的手动/自动路径与所办咨询门）、`tests/v2-fix-probes.test.mjs` / `tests/v3-fix-probes.test.mjs`
+（v2/v3 的收口派遣与降级）、`tests/audit-persona-sensitivity.mjs`（提示词面必须随新命令/工具更新）。
+
+## 11. 纪律
+
+- 写域按预设切分，同一文件只有一个写者；实现者**不提交**（由 Lead 统一提交并跑门禁）。
+- **不得编造论文内容**：论文只整理已有证据，未决/被否证的条目显式标注。
+- 成本纪律：只跑本预设相关套件 + 自建聚焦探针；全量 `run-tests`、`audit-formal-sensitivity`、
+  `e2e-v4-fixes` 等慢脚本留给轮末门禁（见 `docs/test-timing.md`）。