dsh-vibe-math 2.3.15 → 2.3.16

package/README.en.md

@@ -22,30 +22,32 @@ After installing this plugin package (or manually copying the presets), **four**
 
 ## 🧩 Architecture Diagrams (v2 + v3 + v4 + v5)
 
-> Static architecture diagrams; for the complete process description see [docs/架构图.md](docs/架构图.md) (v2 in detail) and
-> [vibe-math-v5/架构图.md](vibe-math-v5/架构图.md) (the full set of v5 detail diagrams);
-> editable generation scripts: [v2](docs/generate_framework_diagram_v2.py) / [v3](docs/generate_framework_diagram_v3.py) (matplotlib → PNG),
+> Static architecture diagrams; for the complete process description see [the v1-era architecture notes](docs/架构图.md) (historical: the layout changed from v2 on) and
+> [the v5 detail diagrams](vibe-math-v5/架构图.md) (the full set of v5 detail diagrams);
+> editable generation scripts: the Chinese v2/v3 posters come from the matplotlib scripts
+> [v2](docs/generate_framework_diagram_v2.py) / [v3](docs/generate_framework_diagram_v3.py) (matplotlib → PNG); the English v2/v3 diagrams come from the
+> zero-dependency Node scripts [v2-en](docs/generate_framework_diagram_v2_en.mjs) / [v3-en](docs/generate_framework_diagram_v3_en.mjs) (→ **SVG**);
 > [v4](docs/generate_framework_diagram_v4.mjs) / [v5](docs/generate_framework_diagram_v5.mjs)
-> (zero-dependency Node → **SVG**, `node docs/generate_framework_diagram_v4.mjs`).
+> (zero-dependency Node → **SVG**, `node docs/generate_framework_diagram_v4.mjs`; add `--lang=en` for `示例图/框架图-v4-en.svg`).
 > SVG is used from v4 onward: plain text, diff-friendly, crisp at any zoom; when PNG is needed, screenshot with a headless browser (the command is at the top of the generation script).
 
 ### Vibe Math V2 (probability-driven · JSON data layer) ✅ Recommended
 
-![Vibe Math V2 architecture diagram](示例图/框架图-v2.png)
+![Vibe Math V2 architecture diagram](示例图/框架图-v2-en.svg)
 
 **One-sentence pipeline**: `qs.json` takes problems by priority → Explorer splits out directions (if all are dead ends, re-derive) → one Solver per direction iterates over multiple rounds (lemmas go into `Propos/`, solutions go back to `qs.json`, all probabilities <1) → the scheduler picks r (proposition / proposition+proof·disproof / problem+solution) and dispatches ≥3 verifiers for independent review → debate → ruling → at probability=1 it automatically closes out (problem solved, proposition 1/0, priority set to `never`); state is written to disk throughout, `resume` continues from the checkpoint, and `reportMode` can report by file/push/both.
 
 ### Vibe Math V3 (paper-style md + planner agent + methods library) ✅ Recommended
 
-![Vibe Math V3 architecture diagram](示例图/框架图-v3.png)
+![Vibe Math V3 architecture diagram](示例图/框架图-v3-en.svg)
 
 **One-sentence pipeline**: all knowledge is stored and continued as **Markdown papers/research reports** (`Problems/` problem list including dependencies and the source motivation of follow-up problems, `Progress/` research log continued by direction and by round, `Propos/` proposition library, `Methods/` general theory invention library, `Verified/` absolutely trustworthy) → before scheduling, the scheduler builds a state brief and calls the **planner agent**; the planner agent lays out the next N steps in one go (spawn solver/verifier/explorer/method-keeper, interrupt, promote, wait), which are executed after code validation (actions exceeding the concurrency limit are queued and consumed across ticks; a planning failure automatically falls back to the v2-style heuristic) → verifiers review independently → debate → **near-consensus ruling** (if on the same side and the mean is ≥0.85/≤0.15, take the mean, fixing v2's flat misjudgment) → at probability=1 it closes out and generates a `Verified/` card → the solver's `methods_used`/`new_inventions` reports are distilled/refined into the methods library by the **Method Keeper** (which can form system hierarchies and be reused across projects).
 
 ### Vibe Math V4 (resident self-organizing collaborative research) 🧪 Experimental
 
-![Vibe Math V4 architecture diagram](示例图/框架图-v4.svg)
+![Vibe Math V4 architecture diagram](示例图/框架图-v4-en.svg)
 
-> The SVG above is generated by a zero-dependency script: `node docs/generate_framework_diagram_v4.mjs` (pure Node, no Python/matplotlib dependency;
+> The SVG above is generated by a zero-dependency script: `node docs/generate_framework_diagram_v4.mjs --lang=en` (pure Node, no Python/matplotlib dependency;
 > generation estimates text width, and any line overflowing its container raises a warning and exits with code 1).
 
 **One-sentence pipeline**: initially N **resident subagents** are created (continuable, persistent context) which first brainstorm on their own and produce initial insights/directions → after that **all task arrangements are decided autonomously by them leaving messages for each other + holding collective meetings** (the framework only provides the message bus/meetings/task board/artifact persistence, and **never assigns tasks**); each resident persists valuable artifacts into **its own** `Progress/<id>/`, `Propos/<id>/`, `Methods/<id>/`, `Subproblems/<id>/` libraries according to **degree of value / planned motivation and use / its own probability estimate**, and they **can read each other's**; verification is initiated by **their own deliberation**, and only when **all residents agree (true or false)** is it written to `Verified/`, otherwise it stays in the library with a probability attached; when a resident's context reaches a threshold (66% by default) it automatically `/compact`s; they stop **only when all of them agree that the original problem is solved**; residents can be manually intervened with/added/shut down at any time, and checkpoint resume is supported.
@@ -60,11 +62,11 @@ After installing this plugin package (or manually copying the presets), **four**
 **One-sentence positioning**: upgrade v4's "a group of residents messaging each other" into an **institute** — with three classes of staff: **academician** (leader), **resident researcher**, and **temp worker**; with the institute's **public charter**; with **group chat and meetings**; with **autonomous hiring/firing**; and where
 **any conclusion must be given a Boolean probability of 1 or 0 unanimously by at least m voting members before it can be written to `Verified/`**.
 
-![Vibe Math V5 architecture diagram](示例图/框架图-v5.svg)
+![Vibe Math V5 architecture diagram](示例图/框架图-v5-en.svg)
 
 > Image sources and all detail diagrams (member lifecycle, one-round sequence, consensus state machine, meeting flow, scheduling priority, state folding,
-> prompt composition, task board, authority matrix): [`vibe-math-v5/架构图.md`](vibe-math-v5/架构图.md).
-> The SVG above is generated by a zero-dependency script: `node docs/generate_framework_diagram_v5.mjs`.
+> prompt composition, task board, authority matrix): [the v5 detail diagrams](vibe-math-v5/架构图.md).
+> The SVG above is generated by a zero-dependency script: `node docs/generate_framework_diagram_v5.mjs --lang=en`.
 
 ```mermaid
 flowchart TB
@@ -146,7 +148,7 @@ session log, from which `applyV5Event` purely folds out the state. Therefore
 - **Recovery takes the same code path**: both cross-process restarts and resume after an in-process abort are covered by DSH's checkpoint/restore;
 - the whole class of problems caused by v4's direct writes to `State/*.json` — "corrupted silent overwrite / concurrent lost writes / stale cross-process snapshots" — is eliminated by construction.
 
-If the host has no `sessionProjections` service, v5 automatically falls back to hardened JSON (`State/<研究所>.v5state.json`, the same fold,
+If the host has no `sessionProjections` service, v5 automatically falls back to hardened JSON (`State/<institute>.v5state.json`, the same fold,
 serial writes, and a mandatory load before read), and the installer's startup self-check reports this degradation. Files outside the projection (member output libraries, group chat, meeting minutes,
 debate records, roster mirror, task board mirror) are all **human-readable artifacts**, and breaking them by hand does not damage the institute.
 
@@ -159,18 +161,18 @@ and the **receipt contract**. Every field in the receipt contract that the frame
 (temp workers have no `verdict`/`hire`/`fire`; non-academicians have no `assign`/`prioritize`/`nudge`/`convene_meeting`).
 
 The framework treats "the text a member reads" as a product to be guaranteed: identity is **passed explicitly and never guessed**; a member is **written to the roster first, and only then** are its onboarding
-prompts constructed; the charter snapshot is frozen at onboarding, and a session rebuild is framed as `【会话重建】` rather than "just onboarded"; no academician narrative appears when there is no academician;
+prompts constructed; the charter snapshot is frozen at onboarding, and a session rebuild is framed as the literal marker `【会话重建 —— <role> <id>】` ("session rebuild") rather than "just onboarded"; no academician narrative appears when there is no academician;
 message headers are labeled by **true origin** (institute office assignment ≠ academician assignment; supervision ≠ assignment); framework feedback has its own sender,
 and **only one message is delivered per prompt**.
 
 #### Directory Structure (Institute)
 
 ```
-<会话工作区>/VibeMath/Projects/<项目>/Institutes/<研究所>/
+<session workspace>/VibeMath/Projects/<project>/Institutes/<institute>/
 ├─ Institutes.md                 # roster mirror (human-readable snapshot, do not edit by hand)
 ├─ Problems/<id>.md              # original problem
 ├─ Problems/conclusion.md        # conclusion record
-├─ Members/<代号>/
+├─ Members/<codename>/
 │   ├─ Progress/progress.md      # research log (the main basis for restoring state after compaction)
 │   ├─ Propos/<id>.md            # proposition
 │   ├─ Methods/<id>.md           # method / theory / tool
@@ -203,8 +205,8 @@ and **only one message is delivered per prompt**.
 - **No npm experimental package is introduced**: v5 is a single `.js` file within the preset, with zero dependencies.
 - **Meetings and verification are strictly mutually exclusive** (queued in both directions).
 
-See [`vibe-math-v5/实现方案.md`](vibe-math-v5/实现方案.md) (written specification) and
-[`vibe-math-v5/架构图.md`](vibe-math-v5/架构图.md) (all detail diagrams).
+See [the v5 specification](vibe-math-v5/实现方案.md) (written specification) and
+[the v5 detail diagrams](vibe-math-v5/架构图.md) (all detail diagrams).
 
 ---
 
@@ -449,8 +451,8 @@ The framework = **one main agent (assistant) + one code scheduler + one planner
 | Roster | resident, can be spawned/closed | **can grow and shrink**: resident researchers are hired with the institute office's approval; temp workers are hired and fired autonomously by academicians/researchers |
 | State | `State/*.json` written directly | **session-log host-only projection cells** (zero token cost, handled by DSH checkpoint/restore) |
 
-For the complete v5 architecture (including member lifecycle, one-round timeline, consensus state machine, meeting flow, scheduling priority, state folding, prompt composition, task board, authority matrix), see [`vibe-math-v5/架构图.md`](vibe-math-v5/架构图.md); for the textual specification see
-[`vibe-math-v5/实现方案.md`](vibe-math-v5/实现方案.md).
+For the complete v5 architecture (including member lifecycle, one-round timeline, consensus state machine, meeting flow, scheduling priority, state folding, prompt composition, task board, authority matrix), see [the v5 detail diagrams](vibe-math-v5/架构图.md); for the textual specification see
+[the v5 specification](vibe-math-v5/实现方案.md).
 
 ---
 
@@ -479,6 +481,7 @@ For the complete v5 architecture (including member lifecycle, one-round timeline
 ```
 <session workspace>/VibeMath/
 ├─ Methods/                            # [global] cross-project general theory invention library (v3, promoted from project level)
+├─ Formal/                             # object formalization workspace: Lib/ (reusable definitions) and Proved/ (proved lemmas)
 ├─ current.<session id>.json               # current project per session (parallel sessions do not overwrite each other)
 ├─ vibe_math_setting.json             # (optional, global fallback) default parameters JSONC, with comments
 └─ Projects/<project>/
@@ -545,13 +548,13 @@ and citations must be marked "unverified"; ④ entry into the library must state
 Because the main agent has built-in usage instructions, you **can simply speak in plain language**:
 
 ```
-帮我用 Vibe Math 证明 √2 是无理数。
+Use Vibe Math to prove that √2 is irrational.
 ```
 
 The main agent will automatically: `vibe_math_add_problem` to add the problem → `vibe_math_start` to start it → after that you can ask it for progress at any time.
 
 ```
-现在进展怎么样了？
+How is it going so far?
 ```
 
 The main agent will automatically call `vibe_math_status` / `vibe_math_report` and report the results back to you in plain language.
@@ -594,19 +597,19 @@ The main agent's role is to be your "translator". You only need to describe the
 
 | What you say | What the main agent does |
 |---|---|
-| “求解 / 证明 XXX” | `add_problem` + `start`, then report |
-| “现在进度怎么样 / 有哪些代理在跑” | `status` / `report` / `list_agents` and summarize |
-| “暂停 / 终止求解” | `pause` / `abort` |
-| “切到人工模式，我要逐步把关” | `set_mode manual`, then remind you with `list_decisions` whenever there is a decision |
-| “给 q1 的某个求解方向换个思路（比如改成构造性证明）” | `list_agents` to find the childId → `message_agent` to inject new instructions |
-| “中断某个卡住的子代理” | `interrupt_agent` |
+| “Solve / prove XXX” | `add_problem` + `start`, then report |
+| “What is the progress now / which agents are running?” | `status` / `report` / `list_agents` and summarize |
+| “Pause / abort the proof” | `pause` / `abort` |
+| “Switch to manual mode; I want to review each step” | `set_mode manual`, then remind you with `list_decisions` whenever there is a decision |
+| “Give one of q1's directions a new angle (e.g. turn it into a constructive proof)” | `list_agents` to find the childId → `message_agent` to inject new instructions |
+| “Interrupt a stuck subagent” | `interrupt_agent` |
 
 ### 2. Q&A-style parameter configuration (/vibe setup)
 
 You do not even need to remember parameter names. Say:
 
 ```
-帮我配置一下参数。
+Help me configure the parameters.
 ```
 
 The main agent will call `vibe_math_setup` to get the full parameter schema (each item includes a **description / options / suggestion / current value**),
@@ -620,7 +623,7 @@ You can also just run the command: `/vibe setup` (view the schema) → tell the
 - **Generate a template**: `/vibe template` (generated into the workspace) or `/vibe template project` (generated into the current project) —
   it produces a JSON template **with `//` comments and an item-by-item Chinese description**; after you edit it by hand, restart/resume to take effect.
 - **Save current values**: `/vibe save` writes the currently effective parameters back to that file.
-- **The only persistent source**: that file is the **only persistence layer** for parameters (project level takes precedence → when missing, fall back to the global `<工作区>/VibeMath/vibe_math_setting.json` → built-in defaults).
+- **The only persistent source**: that file is the **only persistence layer** for parameters (project level takes precedence → when missing, fall back to the global `<workspace>/VibeMath/vibe_math_setting.json` → built-in defaults).
   `vibe_math_set_params` / `set_mode` **write back immediately** to the project-level file and persist, so no manual save is needed.
 
 ---
@@ -630,16 +633,16 @@ You can also just run the command: `/vibe setup` (view the schema) → tell the
 **Step 1 — Start with one sentence**
 
 ```
-帮我用 Vibe Math 证明：√2 是无理数。
+Use Vibe Math to prove: √2 is irrational.
 ```
 
-The main agent runs `vibe_math_add_problem {"id":"q1","description":"证明：√2 是无理数。","priority":0}`
+The main agent runs `vibe_math_add_problem {"id":"q1","description":"Prove that √2 is irrational.","priority":0}`
 then runs `vibe_math_start`, and then tells you “started”.
 
 **Step 2 — Ask about progress**
 
 ```
-进展如何？
+How is the progress?
 ```
 
 The main agent runs `vibe_math_status` and reports in plain language: the number of currently active subagents, the units being verified, whether there are pending decisions, and so on.
@@ -647,7 +650,7 @@ The main agent runs `vibe_math_status` and reports in plain language: the number
 **Step 3 — Tune parameters by conversation (optional)**
 
 ```
-我想让它用加权投票，并发数设成 6。
+I want it to use weighted voting, with the concurrency limit set to 6.
 ```
 
 The main agent `vibe_math_set_params {"verdictMode":"weighted-vote","maxParallelThreshold":6}`,
@@ -656,7 +659,7 @@ and asks you whether to `vibe_math_save_settings` to save them.
 **Step 4 — Intervene midway (optional)**
 
 ```
-切到人工模式，我要在每个关键节点把关。
+Switch to manual mode; I want to check every key step.
 ```
 
 The main agent `vibe_math_set_mode {"mode":"manual"}`. Afterwards, at every key node it runs `vibe_math_list_decisions`
@@ -665,13 +668,13 @@ to get the decisions, explains them to you, and waits for you to `vibe_math_deci
 **Step 5 — Wrap up**
 
 ```
-结束了吗？结论是什么？
+Is it finished? What is the conclusion?
 ```
 
-The main agent `vibe_math_status`: in `qs.csv`, `q1` has been written back as `solved`, and the solution file is in `Verified/` and named
-`q1-的解法_<唯一标识>.csv`.
+The main agent `vibe_math_status`: in `qs/qs.json`, `q1` has been written back with `已解决 = true` (`已解决` = solved) and its solution carries `正确概率 = 1` (`正确概率` = correctness probability); the resolved fact is indexed in
+`Verified/<category>_Verified.json`.
 
-> The corresponding wrap-up in v2 is: `q1.已解决 = true` in `qs.json`, its solution `正确概率 = 1`, and the related proposition enters `Verified/`.
+> v2 writes no CSV at all: solved problems live in `qs/qs.json`, and `Verified/<category>_Verified.json` is the resolved-fact index (a solution with `正确概率 = 1` closes its problem; a proof or disproof with `正确概率 = 1` sets the proposition estimate to `1`/`0`).
 
 ---
 
@@ -813,10 +816,10 @@ Common controls: `vibe_v5_configure` (configure first) → `vibe_v5_start` (star
 
 ## 📚 Specification documents
 
-- **v2 (probability-driven)**: [`vibe-math-v2/实现方案.md`](vibe-math-v2/实现方案.md)
-- **v3 (paper-style md + planning agent + method library)**: [`vibe-math-v3/实现方案.md`](vibe-math-v3/实现方案.md)
-- **v4 (resident self-organization)**: [`vibe-math-v4/实现方案.md`](vibe-math-v4/实现方案.md)
-- **v5 (institute system)**: [`vibe-math-v5/实现方案.md`](vibe-math-v5/实现方案.md) (text specification) · [`vibe-math-v5/架构图.md`](vibe-math-v5/架构图.md) (the full set of architecture diagrams)
+- **v2 (probability-driven)**: [the v2 specification](vibe-math-v2/实现方案.md)
+- **v3 (paper-style md + planning agent + method library)**: [the v3 specification](vibe-math-v3/实现方案.md)
+- **v4 (resident self-organization)**: [the v4 specification](vibe-math-v4/实现方案.md)
+- **v5 (institute system)**: [the v5 specification](vibe-math-v5/实现方案.md) (text specification) · [the v5 detail diagrams](vibe-math-v5/架构图.md) (the full set of architecture diagrams)
 - **v5 prompts and interaction corpus**: [`prompt-corpus-v5/prompt-corpus-v5.md`](prompt-corpus-v5/prompt-corpus-v5.md) (the verbatim text of every prompt the framework actually emits, so you can manually review whether identity/positions/interaction signatures are correct)
 - **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)

package/README.md

@@ -1,6 +1,6 @@
 # Vibe Mathematics — 多代理数学问题求解与验证框架（四架构）
-
-[English](README.en.md) | 中文
+
+[English](README.en.md) | 中文
 
 [![npm](https://img.shields.io/npm/v/dsh-vibe-math)](https://www.npmjs.com/package/dsh-vibe-math)
 [![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](https://opensource.org/licenses/MIT)
@@ -22,11 +22,12 @@
 
 ## 🧩 架构图（v2 + v3 + v4 + v5）
 
-> 静态架构图；完整流程说明见 [docs/架构图.md](docs/架构图.md)（v2 详解）与
+> 静态架构图；完整流程说明见 [docs/架构图.md](docs/架构图.md)（v1 历史架构图；v2 起目录布局已变更）与
 > [vibe-math-v5/架构图.md](vibe-math-v5/架构图.md)（v5 全套细节图）；
-> 可编辑生成脚本：[v2](docs/generate_framework_diagram_v2.py) / [v3](docs/generate_framework_diagram_v3.py)（matplotlib → PNG）、
+> 可编辑生成脚本：中文 v2/v3 海报由 matplotlib 脚本生成 [v2](docs/generate_framework_diagram_v2.py) / [v3](docs/generate_framework_diagram_v3.py)（matplotlib → PNG）；
+> 英文版 v2/v3 由零依赖 Node 脚本生成 [v2-en](docs/generate_framework_diagram_v2_en.mjs) / [v3-en](docs/generate_framework_diagram_v3_en.mjs)（→ **SVG**）；
 > [v4](docs/generate_framework_diagram_v4.mjs) / [v5](docs/generate_framework_diagram_v5.mjs)
-> （零依赖 Node → **SVG**，`node docs/generate_framework_diagram_v4.mjs`）。
+> （零依赖 Node → **SVG**，`node docs/generate_framework_diagram_v4.mjs`，加 `--lang=en` 生成英文版 `示例图/框架图-v4-en.svg`）。
 > v4 起改用 SVG：纯文本、diff 友好、任意缩放不糊；需要 PNG 时用无头浏览器截图（命令见生成脚本头部）。
 
 ### Vibe Math V2（概率驱动 · JSON 数据层）✅ 主推
@@ -481,6 +482,7 @@ v5 的完整架构（含成员生命周期、一轮时序、共识状态机、
 ```
 <会话工作区>/VibeMath/
 ├─ Methods/                            # 【全局】跨项目通用理论发明库（v3，晋升自项目级）
+├─ Formal/                             # 对象形式化工作文件：Lib/（可复用定义）与 Proved/（已证引理）
 ├─ current.<会话id>.json               # 每会话当前项目（多会话并行互不覆盖）
 ├─ vibe_math_setting.json             # （可选，全局回退）默认参数 JSONC，含注释
 └─ Projects/<项目>/
@@ -670,10 +672,10 @@ v5 的完整架构（含成员生命周期、一轮时序、共识状态机、
 结束了吗？结论是什么？
 ```
 
-主代理 `vibe_math_status`：`qs.csv` 里 `q1` 已回写 `solved`，解法文件在 `Verified/` 里并被命名为
-`q1-的解法_<唯一标识>.csv`。
+主代理 `vibe_math_status`：`qs/qs.json` 里 `q1` 已回写 `已解决 = true`，其解法 `正确概率 = 1`；定论事实进入
+`Verified/<分类>_Verified.json`。
 
-> v2 对应的收尾是：`qs.json` 中 `q1.已解决 = true`，其解法 `正确概率 = 1`，相关命题进入 `Verified/`。
+> v2 不写 CSV：已解决问题就在 `qs/qs.json` 里，`Verified/<分类>_Verified.json` 是定论事实索引（解法 `正确概率 = 1` → 问题收口；证明/证伪 `正确概率 = 1` → 命题布尔估计 = 1/0）。
 
 ---
 
@@ -835,7 +837,7 @@ v5 的完整架构（含成员生命周期、一轮时序、共识状态机、
 ## ⚠️ 已知边界（有意简化）
 
 **v2**：
-- 安装器带**版本化自动更新**：每次 DSH 启动时对比包版本与 `<presetRoot>/.vibe-math-installed.json` 记录——**版本一变（或无记录的老安装首次运行）就整体替换受管文件，不看它是否被改过**；被替换的手改原文先备份到 `<presetRoot>/.vibe-math-backup/<旧版本>/<preset>/` 并在日志里列出。同一个版本内**不重写任何文件**（重启 DSH 不会改写 preset、也不会扰动它按 mtime 记的生成代际），缺失文件随时补回。想强制全量重装：删除 `~/.dsh/.agent-presets/vibe-math-v2`、`vibe-math-v3`、`vibe-math-v4` 与 `vibe-math-v5` 目录后重启 DSH。
+- 安装器带**版本化自动更新**：每次 DSH 启动时对比包版本与 `<presetRoot>/.vibe-math-installed.json` 记录——**版本一变（或无记录的老安装首次运行）就整体替换受管文件，不看它是否被改过**；被替换的手改原文先备份到 `<presetRoot>/.vibe-math-backup/<旧版本>/<preset>/` 并在日志里列出。同一个版本内**不重写任何文件**（重启 DSH 不会改写 preset、也不会扰动它按 mtime 记的生成代际），缺失文件随时补回。想强制全量重装：删除 `~/.dsh/.agent-presets/vibe-math-v2`、`vibe-math-v3`、`vibe-math-v4` 与 `vibe-math-v5` 目录后重启 DSH。
 - **这四个目录由安装器负责**：删掉其中任一文件或整个目录，只会在下次启动 DSH 时被补回（这正是上面"强制全量重装"可行的原因）。想彻底不要它们，就卸载本包（`dsh plugin --profile <你的 profile> remove dsh-vibe-math`）。
 - `flat` 裁决在辩论不一致时直接判 `0.5`（高置信分歧如 0.9 vs 1 也会被误判 0.5——**v3 已用近共识规则修复**）；`forced` 按历史准确率+置信度加权。
 - `never` 优先级的问题/命题**永不调度**，且不阻塞严格终止（视为主动弃权）。

package/docs/AUDIT-CHECKLIST.md

@@ -320,46 +320,65 @@ provider **直接拒绝**。于是"提示词/规格/状态表都写着这个参
 
 - 缺陷要分**类**："这一整类此前没有审计维度"比"修了 N 个 bug"更重要。
 - 假绿/假红必须单独说明：**审计本身失效**是最严重的发现。
-- 每条结论都要给出**可复核的证据**（真实日志片段、语料原文、可重跑的命令与结果）。
-
----
-
-## 6. 发布说明（Release Notes / GitHub Release）格式
-
-**中英双语、先中文后英文，只写"给用户看的信息"。** 工程过程（探针结果、断言条数、事故复盘、行号与
-内部编号）属于 `_oneoff/audit-findings-*.md` 台账与提交信息，**不进**发布说明。
-
-固定骨架（只有版本号、标题与正文随版本变，**节名不变**）：
-
-```markdown
-# dsh-vibe-math <版本> — 发布说明（中文）
-
-> 上一版：<版本>。<一句话：这一版是干什么的、是否影响行为。>
-
-## 概览
-## 变更
-## 兼容性
-## 升级
-
----
-
-# dsh-vibe-math <版本> — Release Notes (English)
-
-> Previous: <version>. <One sentence: what this release is and whether behaviour changes.>
-
-## Overview
-## Changes
-## Compatibility
-## Upgrade
-```
-
-- [ ] 两个 H1 都在；**英文那份的 H1 必须含 `English`**（发布门禁阶段 1c 会检查）；
-- [ ] 中文部分 ≥ 150 个汉字（门禁同阶段检查），英文部分不得残留未翻译段落；
-- [ ] 每条变更都回答"**对使用者有什么影响**"——不写内部编号、探针名、断言条数；
-- [ ] 「兼容性」明确回答：四套预设的字节/行为是否变化、参数与工具面是否变化；
-- [ ] 「升级」给出可直接复制的命令（`npm i dsh-vibe-math@latest`；若 profile 里把版本钉死了，
-      写出对应的 `dsh plugin --profile <name> add dsh-vibe-math@latest`）；
-- [ ] **发布前把草稿交给用户确认**（在对话里展示全文，或用提问工具）；用户同意或给出修改意见后再发布；
-- [ ] GitHub Release 的正文 = 这份文件本身（`gh release create --notes-file <该文件>`），标题中英并列。
-
----
+- 每条结论都要给出**可复核的证据**（真实日志片段、语料原文、可重跑的命令与结果）。
+
+---
+
+## 6. 发布说明（Release Notes / GitHub Release）格式
+
+**中英双语、先中文后英文，只写"给用户看的信息"。** 工程过程（探针结果、断言条数、事故复盘、行号与
+内部编号）属于 `_oneoff/audit-findings-*.md` 台账与提交信息，**不进**发布说明。
+
+固定骨架（只有版本号、标题与正文随版本变，**节名不变**）：
+
+```markdown
+# dsh-vibe-math <版本> — 发布说明（中文）
+
+> 上一版：<版本>。<一句话：这一版是干什么的、是否影响行为。>
+
+## 概览
+## 变更
+## 兼容性
+## 升级
+
+---
+
+# dsh-vibe-math <版本> — Release Notes (English)
+
+> Previous: <version>. <One sentence: what this release is and whether behaviour changes.>
+
+## Overview
+## Changes
+## Compatibility
+## Upgrade
+```
+
+- [ ] 两个 H1 都在；**英文那份的 H1 必须含 `English`**（发布门禁阶段 1c 会检查）；
+- [ ] 中文部分 ≥ 150 个汉字（门禁同阶段检查），英文部分不得残留未翻译段落；
+- [ ] 每条变更都回答"**对使用者有什么影响**"——不写内部编号、探针名、断言条数；
+- [ ] 「兼容性」明确回答：四套预设的字节/行为是否变化、参数与工具面是否变化；
+- [ ] 「升级」给出可直接复制的命令（`npm i dsh-vibe-math@latest`；若 profile 里把版本钉死了，
+      写出对应的 `dsh plugin --profile <name> add dsh-vibe-math@latest`）；
+- [ ] **发布前把草稿交给用户确认**（在对话里展示全文，或用提问工具）；用户同意或给出修改意见后再发布；
+- [ ] GitHub Release 的正文 = 这份文件本身（`gh release create --notes-file <该文件>`），标题中英并列。
+
+---
+
+## 7. 中英双语 README 与英文版架构图（2.3.16 起）
+
+- **默认语言**：`README.md` 为中文（默认、GitHub 首屏），`README.en.md` 为英文；两文顶部各有一行切换器
+  （中文版 `[English](README.en.md) | 中文`，英文版 `English | [中文](README.md)`）。不建 `README.zh.md`。
+- **结构同构**：标题层级序列、表格行数、代码块数、图片数量、本地链接集合必须一一对应；
+  唯一允许的差异是四张架构图各自指向 `-en` 版本（按序号配对校验）。
+- **文件与产物名不翻译**：真实目录/文件名（`示例图/…`、`docs/架构图.md`、`Verified/命题/`、`Logs/报告.md`）、
+  真实 JSON 键（`已解决`、`正确概率`）、真实格式锚点（`- ID/类型/状态/概率/…`、`### 解法/证明/证伪 N｜标题｜概率X｜状态Y`）、
+  会话重建标记 `【会话重建 —— <role> <id>】`、v2/v3 真实 md 字段名（`可信断言`、`上级体系`、`子方法`）**保持原样**，
+  首次出现处可加括注；除此以外的正文必须是英文（`tests/audit-readme-bilingual.test.mjs` 的 CJK 预算兜底）。
+- **架构图**：四张英文图 `示例图/框架图-v{2,3,4,5}-en.svg` 只被 `README.en.md` 引用，中文图不受影响；
+  v4/v5 用现有零依赖生成器加 `--lang=en`（`docs/generate_framework_diagram_v4.mjs`），
+  v2/v3 用独立的零依赖 Node 生成器 `docs/generate_framework_diagram_v{2,3}_en.mjs`（中文 v2/v3 海报仍由 matplotlib 脚本产出）。
+  英文图内只允许保留上述"真实字面量"的中文，`tests/audit-diagram-assets.test.mjs` 按图核 CJK 预算。
+- **历史文档必须标注适用范围**：描述旧版本布局的文档（如 v1 时期的 `docs/架构图.md`）要在开头写明它描述的是哪一版，
+  不能在被 README 当作"当前详解"引用时静默误导（`qs.csv`、`Pending_Verification/` 等 v1 名称在 v2 起已不存在）。
+
+---