dsh-vibe-math 2.4.0 → 2.5.0

package/README.en.md

@@ -9,10 +9,10 @@ English | [中文](README.md)
 > A set of **agent presets** running inside **DeepSeek Harness** (`vibe-math-v2` / `vibe-math-v3` / `vibe-math-v4` / `vibe-math-v5`),
 > which use multi-agent collaboration to automatically solve mathematical problems and perform multi-agent cross-verification of the conclusions. All four presets share the foundational capabilities of "**checkpoint resume**,
 > **mid-run manual intervention**, **progress reporting**, and **natural-language driving**", but adopt four generations of different solving architectures:
-> **💡 `vibe-math-v2` and `vibe-math-v3` are recommended at the same level** — both are mature, usable, actively maintained recommended architectures; choose according to your actual needs (see "How to choose" below); `vibe-math-v4` is the "resident self-organizing collaborative research" architecture, and `vibe-math-v5` is the latest "institute system" (both are experimental).
+> **💡 All four architectures are peers** — `vibe-math-v2` and `vibe-math-v3` are the **classic** architectures (mature, usable, actively maintained); `vibe-math-v4` is the "resident self-organizing collaborative research" architecture and `vibe-math-v5` is the latest "institute system" (both labelled experimental); choose according to your actual needs (see "How to choose" below).
 >
-> - **`vibe-math-v2` (probability-driven · JSON data layer) ✅ Recommended**: `qs.json` problem list + `Propos/` proposition library + probability-driven scheduling + code heuristic scheduling;
-> - **`vibe-math-v3` (third generation · paper-style md + planner agent + method library) ✅ Recommended**: all knowledge is stored and extended in **Markdown paper/research-report form** (`Problems/` problem list + dependencies + source motivation, `Progress/` research log, `Propos/` proposition library, `Methods/` general theory invention library, `Verified/` absolutely trustworthy); before scheduling, the **planner agent** autonomously draws up a plan for the next N steps; theories/frameworks/tools/methods/ideas invented during solving are distilled by the **Method Keeper** into a reusable method system (as in inventing group theory or functional analysis).
+> - **`vibe-math-v2` (probability-driven · JSON data layer) · classic**: `qs.json` problem list + `Propos/` proposition library + probability-driven scheduling + code heuristic scheduling;
+> - **`vibe-math-v3` (third generation · paper-style md + planner agent + method library) · classic**: all knowledge is stored and extended in **Markdown paper/research-report form** (`Problems/` problem list + dependencies + source motivation, `Progress/` research log, `Propos/` proposition library, `Methods/` general theory invention library, `Verified/` absolutely trustworthy); before scheduling, the **planner agent** autonomously draws up a plan for the next N steps; theories/frameworks/tools/methods/ideas invented during solving are distilled by the **Method Keeper** into a reusable method system (as in inventing group theory or functional analysis).
 > - **`vibe-math-v4` (fourth generation · resident self-organizing collaborative research) 🧪 Experimental**: a group of **persistent resident subagents** **leave messages for one another + hold meetings**, and autonomously decide all task arrangements (no central scheduler); each accumulates its own progress/proposition/method/subproblem libraries and consults the others; verification is written to `Verified/` **only when all residents agree (true or false)**, otherwise it remains in the library with a probability attached; when the context reaches a threshold it automatically `/compact`s; it stops only when all agree that the original problem has been solved.
 > - **`vibe-math-v5` (fifth generation · institute system) 🧪 Experimental · Latest**: upgrades the residents into an **institute** — **academicians** (leaders / the organizing and coordinating center, responsible for decomposition and **assignment**, setting priorities, chairing meetings, and supervising progress) + **resident researchers** (with voting rights, able to autonomously hire/fire their own temp workers) + **temp workers** (no voting rights); it has a **public charter**, **group chat and meetings**, a **compare-and-set task board**, and **real firing**; a boolean agreement of **≥ m votes** is required to write to `Verified/` (opposing votes block, abstentions are not counted, and if the threshold is not met it remains in the library with an average probability attached); state is written to the **hardened JSON file** `State/<institute>.v5state.json` under the institute directory (serial writes, a mandatory load before read) — **never into the host session log** — at zero token cost.
 
@@ -31,13 +31,13 @@ After installing this plugin package (or manually copying the presets), **four**
 > (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 (probability-driven · JSON data layer) · classic
 
 ![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 (paper-style md + planner agent + methods library) · classic
 
 ![Vibe Math V3 architecture diagram](示例图/框架图-v3-en.svg)
 
@@ -79,7 +79,7 @@ flowchart TB
     subgraph FW["⚙️ Framework vibe-v5 —— only a medium (middleware), never assigns tasks"]
         M["Message relay · meetings/debates · task board CAS+DAG<br/>m-vote consensus verification · context and liveness · roster and hiring · scheduler"]
     end
-    PROJ["💾 State/&lt;institute&gt;.v5state.json (hardened JSON, authoritative)<br/>11 kinds of events · pure fold applyV5Event · serial writes · recovery = load before read"]
+    PROJ["💾 State/&lt;institute&gt;.v5state.json (hardened JSON, authoritative)<br/>12 kinds of events · pure fold applyV5Event · serial writes · recovery = load before read"]
     FS["📁 Members/&lt;id&gt;/* · Shared/* · Verified/ · Problems/"]
     RULE{{"Truth gate: Boolean unanimity and Boolean votes ≥ m = min(quorumCap, number of registered voting members)"}}
     OFF <-->|"vibe_v5_* / /v5 commands　↔　status / report"| M
@@ -349,7 +349,7 @@ dsh plugin --profile <your profile> add dsh-vibe-math
 dsh plugin --profile <your profile> add github:ChongCyrus/Vibe-Mathematics
 ```
 
-Then start a new session and pick **Vibe Math V3** (v3, **primary recommendation**), **Vibe Math V2** (v2, **primary recommendation**), **Vibe Math V4** (v4, resident self-organization) or **Vibe Math V5** (v5, institute system) in the preset picker — v2 and v3 are equally primary recommendations, choose according to your actual needs (see "How to choose").
+Then start a new session and pick **Vibe Math V2** (v2, classic), **Vibe Math V3** (v3, classic), **Vibe Math V4** (v4, resident self-organization) or **Vibe Math V5** (v5, institute system) in the preset picker — the four architectures are peers, choose according to your actual needs (see "How to choose").
 **The two DSH generations land in different places, and this package adapts to both**:
 
 - **DSH ≥ 0.1.7 (current)**: agent presets are declared as composition rows. This package declares all four presets in `cordis.patch.yml` (each row hands that preset's full plugin list to the host's `agentPresets` service), and **writes nothing into `~/.dsh/.agent-presets/`** — that directory has not been read since 0.1.7.
@@ -384,7 +384,7 @@ Then start a new session and select **"Vibe Math V2"** / **"Vibe Math V3"** / **
 
 ## 🧭 How to choose among the four presets
 
-> **💡 `vibe-math-v2` and `vibe-math-v3` are equally primary recommendations; choose according to your actual needs:**
+> **💡 All four architectures are peers; choose according to your actual needs:**
 >
 > - **Choose `vibe-math-v2` (probability-driven · JSON data layer)** if you:
 >   - prefer **structured JSON data** (`qs.json` / `Propos/<category>_Propos.json` / `Verified/` cards), convenient for programmatic retrieval and further processing;
@@ -402,14 +402,14 @@ Then start a new session and select **"Vibe Math V2"** / **"Vibe Math V3"** / **
 > - **Choose `vibe-math-v5` (institute system)** if you want:
 >   - **organized self-organization** — like a real research institute, with a **leader (academician)** responsible for decomposition, assignment, prioritization, chairing meetings and supervising progress, but **judgment still belongs to each individual**;
 >   - a **roster that can grow or shrink** — resident researchers + temp workers who can be **autonomously hired/dismissed** (temp workers have no voting rights, suitable for chores such as checking, trial computation and material organization);
->   - an **adjustable consistency threshold** — `m = min(quorumCap, number of voting members)` boolean-consistent votes settle the matter (easier to converge than "unanimity", while **opposing votes still block**, so a minority will not be drowned out by abstentions);
+>   - an **adjustable consistency threshold** — `m = min(quorumCap, number of voting members)` boolean-consistent votes settle the matter (because an opposing vote blocks, the effective threshold is still "every Boolean vote points the same way"; it differs only when fewer than `m` members cast a Boolean vote);
 >   - **zero-token-cost state persistence** — the institute state is written to a hardened JSON file under the institute directory and does not consume member context budget.
 >
-> **⚠️ `vibe-math-v2` and `vibe-math-v3` are mature primary architectures; `vibe-math-v4` and `vibe-math-v5` are experimental architectures,** all are selectable; the old `vibe-math-v1` has been removed (this package contains only v2/v3/v4/v5).
+> **⚠️ `vibe-math-v2` and `vibe-math-v3` are the classic architectures; `vibe-math-v4` and `vibe-math-v5` are experimental architectures,** all four are peers and all are selectable; the old `vibe-math-v1` has been removed (this package contains only v2/v3/v4/v5).
 
-| | **v2 (probability-driven · primary)** | **v3 (paper-style md · primary)** | **v4 (resident self-organization · experimental)** | **v5 (institute system · experimental)** |
+| | **v2 (probability-driven · classic)** | **v3 (paper-style md · classic)** | **v4 (resident self-organization · experimental)** | **v5 (institute system · experimental)** |
 |---|---|---|---|---|
-| Positioning | **Primary** (JSON data layer) | **Primary** (third generation) | **Experimental** (fourth generation) | **Experimental** (fifth generation) |
+| Positioning | **Classic** (JSON data layer) | **Classic** (third generation) | **Experimental** (fourth generation) | **Experimental** (fifth generation) |
 | Core idea | Probability-driven: `qs.json` problems + `Propos/` proposition library, scheduled by "correctness probability / value" | **Paper-style md knowledge base + planner agent scheduling + general theory invention library** | **Persistent resident subagents self-organizing**: message each other + meetings decide all tasks, no central scheduling | **Institute**: the academician organizes and assigns, members research on their own; a conclusion requires **≥ m boolean-consistent votes**; temp workers can be hired as needed |
 | Data | `qs/qs.json` + `Propos/<category>_Propos.json` + `Reliable/` | `Problems/` + `Progress/` + `Propos/` + `Methods/` (all md, soft-spec anchors + free narration) + `Verified/` | `Problems/` + `Progress|Propos|Methods|Subproblems/<id>/` **owned by resident id** + `Shared/` (meetings/task board/debate) + `Verified/` | Same member-owned layout as v4, plus `Institutes.md` (roster mirror); **the authoritative state is `State/<institute>.v5state.json`**, and the other files are only mirrors and workspaces |
 | Roles | explorer → per-direction solver → verifier | **planner (planner agent)** → explorer → per-direction solver → verifier → **method-keeper (method organization agent)** | **N resident researchers** (continuable), no fixed roles | **academician acad** (leader) + **resident researcher r-n** (with voting rights) + **temp worker t-n** (no voting rights, hireable and dismissible) + institute office (does not research and does not vote) |
@@ -420,12 +420,12 @@ Then start a new session and select **"Vibe Math V2"** / **"Vibe Math V3"** / **
 | Ad hoc capabilities | Automatic promotion of proposition "value/criticality" to the problem list; `reportMode file/push/both`; `priorityAdjust` | **Method library accumulation loop** (`methods_used`/`new_inventions` → Method Keeper); **plan approval gate/method promotion gate**; **project lock**; follow-up problem "source and motivation" as a first-class citizen | **Residents accumulate individually + read each other**; **unanimous verification**; **add/close residents at any time, intervene by message**; **checkpoint resume** | All v4 capabilities, plus: **real hiring/dismissal** (releases sub-sessions, reclaims tasks); **compare-and-set task board + dependency DAG**; **strict mutual exclusion between meetings and verification**; **roster mirror and conclusion records**; **zero-token-cost state** |
 
 All four support: checkpoint resume (`vibe_math_resume` / `vibe_v4_resume` / `vibe_v5_resume`), manual intervention and pause/resume,
-per-project isolation, subagent permission control, and natural-language driving. **v2 and v3 are both equally primary recommendations** — choose v2 if you prefer structured JSON data and deterministic scheduling,
+per-project isolation, subagent permission control, and natural-language driving. **All four architectures are peers** — choose v2 if you prefer structured JSON data and deterministic scheduling,
 choose v3 if you prefer paper-style md, the planner agent and the theory invention library; v4 is fully self-organizing resident collaborative research, and v5 is an institute system with "a leader + a roster that can grow or shrink + an adjustable threshold".
 
 ---
 
-## 🧠 Architecture and Division of Labor (v3 · third generation) ✅ recommended
+## 🧠 Architecture and Division of Labor (v3 · third generation) · classic
 
 The framework = **one main agent (assistant) + one code scheduler + one planner agent + six kinds of subagents**.
 
@@ -460,7 +460,7 @@ For the complete v5 architecture (including member lifecycle, one-round timeline
 
 ## 📁 Directory Structure
 
-### v2 (probability-driven · recommended)
+### v2 (probability-driven · classic)
 
 ```
 <session workspace>/VibeMath/
@@ -477,7 +477,7 @@ For the complete v5 architecture (including member lifecycle, one-round timeline
    └─ VibeMath_State/                  # scheduler-private persistent state (for checkpoint resume)
 ```
 
-### v3 (paper-style md + planner agent + method library) ✅ recommended
+### v3 (paper-style md + planner agent + method library) · classic
 
 ```
 <session workspace>/VibeMath/
@@ -651,11 +651,11 @@ The main agent runs `vibe_math_status` and reports in plain language: the number
 **Step 3 — Tune parameters by conversation (optional)**
 
 ```
-I want it to use weighted voting, with the concurrency limit set to 6.
+I want it to use forced verdict mode, with the concurrency limit set to 6.
 ```
 
-The main agent `vibe_math_set_params {"verdictMode":"weighted-vote","maxParallelThreshold":6}`,
-and asks you whether to `vibe_math_save_settings` to save them.
+The main agent `vibe_math_set_params {"verdictMode":"forced","maxParallelThreshold":6}`,
+and asks you whether to `vibe_math_save_settings` to save them. (`verdictMode` accepts only `flat|forced`; any other value is **not an error** — it is silently reverted to that architecture's default, `flat` in v2 and `forced` in v3.)
 
 **Step 4 — Intervene midway (optional)**
 
@@ -694,7 +694,7 @@ The main agent `vibe_math_status`: in `qs/qs.json`, `q1` has been written back w
 
 ## ⚙️ Parameter quick reference
 
-### v2 (probability-driven · main recommendation) defaults
+### v2 (probability-driven · classic) defaults
 
 | Parameter | Default | Description |
 |---|---|---|
@@ -704,7 +704,7 @@ The main agent `vibe_math_status`: in `qs/qs.json`, `q1` has been written back w
 | `directionsPerSolver` | 1 | Total number of directions visible to each solver prompt (1 = only its own direction, no mutual interference; N>1 = its own plus summaries of up to N-1 other active directions) |
 | `verifierCount` | 3 | Number of independent verifiers per verification target |
 | `debateMaxRounds` | 5 | Maximum number of rounds of verification debate (chat group) |
-| `verdictMode` | `flat` | `flat` = balanced mechanism (inconsistency judged 0.5) / `forced` = forced verdict (historical accuracy + rigor weighting) |
+| `verdictMode` | `flat` | `flat` = the **equal-weight mean** of the probabilities the verifiers report (an inconsistency is no longer judged 0.5) / `forced` = forced verdict (weighted by historical accuracy + rigor; accuracy is tracked per model and scored only when the object later receives a boolean verdict) |
 | `reportMode` | `file` | `file` = write a report file / `push` = push a report to the main agent / `both` |
 | `promoteValueThreshold` | 0.7 | A proposition in Propos with "value/criticality" ≥ this value and undecided (0,1) is automatically added to qs.json |
 | `priorityAdjust` | `none` | `none` / `deadend-deprioritize` (deprioritize all dead ends) / `survival-map` (recompute by survival rate) |
@@ -732,12 +732,12 @@ Added/adjusted on top of all v2 parameters:
 
 | Parameter | Default | Description |
 |---|---|---|
-| `verdictMode` | `forced` | v3 first makes a **near-consensus determination** (all results on the same side with a mean ≥0.85/≤0.15 takes the mean), otherwise `forced` = weighted by historical accuracy + rigor / `flat` = balanced (0.5). Fixes the v2 flat problem of misjudging "0.9 vs 1" as 0.5 |
+| `verdictMode` | `forced` | v3 first makes a **near-consensus determination** (all results on the same side with a mean ≥0.85/≤0.15 takes the mean) — this runs BEFORE the mode, so 0.9 vs 1 yields ≈0.95 in either mode; otherwise `forced` takes the **equal-weight mean** of the reported probabilities (no accuracy weighting; strict 1/0 still act as absolute votes), while `flat` rules `0.5` (a disagreement is undecided) |
 | `planningHorizon` | 3 | Maximum number of actions in one plan by the planner agent ("the next n times") |
 | `plannerEnabled` | true | false = fully use the built-in heuristic scheduling (planner agent disabled) |
 | `plannerProvider` / `plannerModel` | empty | Planner agent model route (empty = inherit the root agent) |
 | `plannerPersona` | empty | Persona/requirements injected at the start of the planner agent prompt |
-| `planMinIntervalMs` | 30000 | Minimum interval between two planning calls (milliseconds); ignored when the system is idle and there is work |
+| `planMinIntervalMs` | 30000 | Minimum interval between two planning calls (milliseconds); it applies to **every** planning call (empty plans included, and "idle but still work" — the idle bypass is gone) |
 | `plannerMaxFails` | 3 | The planner agent reaching this number of consecutive failures → automatic degradation to heuristics |
 | `methodKeepIntervalMs` | 0 | Method Keeper periodic consolidation interval (0 = event-driven) |
 | `methodKeepEvery` | 5 | Trigger one consolidation every N accumulated inventions/new propositions awaiting sedimentation |
@@ -825,8 +825,8 @@ 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 all suites in parallel in ≈1.9 min; the probe scripts ≈2.6 min; every runner prints its elapsed time/speedup for choosing a strategy next time)
-- **Static prompt-surface consistency (persona ↔ tool registry ↔ slash command hint/usage)**: [`audit-persona-surface.test.mjs`](tests/audit-persona-surface.test.mjs) (197 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"
+- **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"
 - **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
@@ -840,16 +840,16 @@ Common controls: `vibe_v5_configure` (configure first) → `vibe_v5_start` (star
 - **(DSH ≤ 0.1.6, the directory form)** The installer has **versioned auto-update**: on every DSH start it compares the package version against the record in `<presetRoot>/.vibe-math-installed.json` — **as soon as the version changes (or on the first run of an older installation with no record) it replaces the managed files wholesale, regardless of whether they were modified**; replaced hand-edited originals are first backed up to `<presetRoot>/.vibe-math-backup/<old version>/<preset>/` and listed in the log. Within the same version it **rewrites no files at all** (restarting DSH will not rewrite the presets, nor disturb the generation index it records by mtime), and missing files are restored at any time. To force a full reinstall: delete those four preset directories and restart DSH.
   On DSH ≥ 0.1.7 the installer **writes none of these directories** (the composition rows of the "Installation" section above supply the presets); at startup it only logs that leftover copies can safely be deleted.
 - **On DSH ≤ 0.1.6 these four directories are owned by the installer**: deleting any file in them or the whole directory only leads to it being restored on the next DSH start (which is exactly why the "force a full reinstall" above works). On DSH ≥ 0.1.7 they are neither read nor written any more, so you can simply delete them; to get rid of them entirely, uninstall this package (`dsh plugin --profile <your profile> remove dsh-vibe-math`).
-- A `flat` verdict directly rules `0.5` when the debate is inconsistent (high-confidence disagreement such as 0.9 vs 1 is also misjudged as 0.5 — **v3 has fixed this with the near-consensus rule**); `forced` weights by historical accuracy + confidence.
+- A `flat` verdict takes the **equal-weight mean** of the probabilities the verifiers report when the debate is inconsistent (it is no longer judged `0.5`; the early problem of misjudging a high-confidence disagreement such as 0.9 vs 1 as 0.5 is fixed in v2/v3); `forced` is weighted by historical accuracy + rigor, and accuracy is scored only when the object later receives a boolean verdict.
 - Problems/propositions with `never` priority are **never scheduled**, and do not block strict termination (they count as voluntarily abstaining).
 - The four preset files are mutually independent and can coexist; only one preset can be selected in a given session at a time.
 
 **v3**:
 - **Soft specification rather than zero specification**: the md knowledge base only enforces the 4–7 anchor lines at the head of an object (`- ID/类型/状态/概率/优先级/依赖/...`) and the entry title line (`### 解法/证明/证伪 N｜标题｜概率X｜状态Y`), so that the scheduler can index reliably; the body is entirely free paper-style prose, and the scheduler never parses the body. Manually editing the anchors may cause index drift (the scheduler keeps the last valid index and warns).
-- **The planning agent is an enhancement, not a requirement**: when `plannerEnabled=false` or the planning agent fails repeatedly (`plannerMaxFails`), it automatically falls back to v2-style heuristic scheduling; the `planMinIntervalMs` cooldown takes effect while subagents are in flight (when the system is idle and there is work, it plans immediately).
+- **The planning agent is an enhancement, not a requirement**: when `plannerEnabled=false` or the planning agent fails repeatedly (`plannerMaxFails`), it automatically falls back to v2-style heuristic scheduling; the `planMinIntervalMs` cooldown applies to **every** planning call — empty plans and "idle but still work" included (idleness no longer bypasses the cooldown, which is exactly what amplified the planner's per-tick spinning).
 - **Trust tiers in the method library**: a method card's `可信断言` may only link IDs that have entered `Verified/`; all other content of a method entry (including unverified strategies/intuitions/heuristics) is treated as **empirical reference** and must not be cited as a theorem.
 - **Project lock**: only one session may schedule a given project at a time (starting a second session reports "occupied by session X"); the lock is released automatically on pause/termination/when everything is resolved.
-- **Near-consensus verdicts**: when all verifier results fall on the same side and the mean is ≥0.85/≤0.15, the mean is taken (e.g. 0.9 vs 1 → 0.95); otherwise `forced` weighting / `flat` rules 0.5 — this fixes the problem in v2 where conclusions that were "mathematically correct but formally flawed" were misjudged as uncertain.
+- **Near-consensus verdicts**: when all verifier results fall on the same side and the mean is ≥0.85/≤0.15, the mean is taken (e.g. 0.9 vs 1 → 0.95); otherwise `forced` takes the **equal-weight mean** of the votes and `flat` rules `0.5` — this fixes the problem in v2 where conclusions that were "mathematically correct but formally flawed" were misjudged as uncertain.
 
 **v5**:
 - **The framework never assigns tasks**: this is a hard design boundary, not a feature that has yet to be implemented. The creation and allocation of tasks belong to **institute self-governance**
@@ -857,7 +857,7 @@ Common controls: `vibe_v5_configure` (configure first) → `vibe_v5_start` (star
 - **`≥ m` agreement ≠ mathematically proved**: the quorum only guarantees that "a consistent judgment has been reached within the institute", not that the conclusion is really correct.
   The depth of truth-seeking rests on the members' own derivations and the paper trail in the debate records; objects that do not reach quorum are **kept in the library with their average probability attached** and are not forcibly ruled true or false.
 - **The consistency quorum is not "majority rule"**: any single opposing boolean vote blocks a conclusion, and abstention helps neither truth nor falsehood.
-  To converge more easily, lower `quorumCap` or reduce the number of members with voting rights; for stricter behavior, switch to `quorumMode: "all-unanimous"`.
+  Under this rule (`m = min(quorumCap, number of voting members)`) **as soon as anyone casts a Boolean vote, the threshold is effectively "every Boolean vote points the same way"**: lowering `quorumCap` only lowers how many Boolean votes are required (`m`) and does **not** make convergence easier; for stricter behavior, switch to `quorumMode: "all-unanimous"` (which does not even allow abstentions).
 - **A member whose round never ends will not be forcibly released** (the same boundary as v4): the heartbeat re-arms it every time,
   so the scheduler will not freeze permanently; when manual intervention is needed, use `vibe_v5_fire` (temp worker) or have the institute office add or remove positions.
 - **Meetings and verification are strictly mutually exclusive**: while one is in progress, the other queues/is held. Therefore "concluding an object on the spot in a meeting" first queues,

package/README.md

@@ -9,10 +9,10 @@
 > 运行在 **DeepSeek Harness** 内的一组 **agent preset**（`vibe-math-v2` / `vibe-math-v3` / `vibe-math-v4` / `vibe-math-v5`），
 > 用多代理协作自动求解数学问题并对结论做多代理交叉验证。四个预设共享「**断点续跑**、
 > **中途人工干预**、**进度汇报**、**自然语言驱动**」底座能力，但采用四代不同的求解架构：
-> **💡 `vibe-math-v2` 与 `vibe-math-v3` 同级主推**——两者都是成熟可用、正在维护的主推架构，根据你的实际需求自行选择（详见下方「怎么选」）；`vibe-math-v4` 是「常驻自组织合作研究」架构，`vibe-math-v5` 是最新的「研究所体系」（两者均为实验性）。
+> **💡 四个架构同级**——`vibe-math-v2` 与 `vibe-math-v3` 是**经典**架构（成熟可用、持续维护），`vibe-math-v4` 是「常驻自组织合作研究」架构、`vibe-math-v5` 是最新的「研究所体系」（两者均标注为实验性）；根据你的实际需求自行选择（详见下方「怎么选」）。
 >
-> - **`vibe-math-v2`（概率驱动 · JSON 数据层）✅ 主推**：`qs.json` 问题清单 + `Propos/` 命题库 + 概率驱动调度 + 代码启发式调度；
-> - **`vibe-math-v3`（第三代 · 论文式 md + 规划代理 + 方法库）✅ 主推**：全部知识以 **Markdown 论文/研究报告式** 存储与续写（`Problems/` 问题清单+依赖+来源动机、`Progress/` 研究日志、`Propos/` 命题库、`Methods/` 通用理论发明库、`Verified/` 绝对可信）；调度前由**规划代理**自主制定接下来 N 步计划；解决过程中发明的理论/框架/工具/方法/思想由 **Method Keeper** 沉淀为可复用方法体系（如发明群论、泛函分析那样）。
+> - **`vibe-math-v2`（概率驱动 · JSON 数据层）· 经典**：`qs.json` 问题清单 + `Propos/` 命题库 + 概率驱动调度 + 代码启发式调度；
+> - **`vibe-math-v3`（第三代 · 论文式 md + 规划代理 + 方法库）· 经典**：全部知识以 **Markdown 论文/研究报告式** 存储与续写（`Problems/` 问题清单+依赖+来源动机、`Progress/` 研究日志、`Propos/` 命题库、`Methods/` 通用理论发明库、`Verified/` 绝对可信）；调度前由**规划代理**自主制定接下来 N 步计划；解决过程中发明的理论/框架/工具/方法/思想由 **Method Keeper** 沉淀为可复用方法体系（如发明群论、泛函分析那样）。
 > - **`vibe-math-v4`（第四代 · 常驻自组织合作研究）🧪 实验性**：一组**持久化常驻子代理**互相**留言 + 开会**，自主决定一切任务安排（无中央调度）；各自沉淀进度/命题/方法/子问题库并互相查阅；验证**仅当全体常驻一致（真 或 假）**才写入 `Verified/`，否则留库附概率；上下文达阈值自动 `/compact`；仅当全体一致认为原问题已解决才停止。
 > - **`vibe-math-v5`（第五代 · 研究所体系）🧪 实验性 · 最新**：把常驻升级为一座**研究所**——**院士**（领头人 / 组织与协调中心，负责拆解与**分派**、定优先级、主持会议、督导进度）+ **常驻研究员**（有表决权，可自主雇佣/解雇自己的临时工）+ **临时工**（无表决权）；有**公共规章**、**群聊与会议**、**compare-and-set 任务板**、**真实解雇**；**≥ m 票布尔一致**才写入 `Verified/`（反向票阻塞、弃权不计票、未达门槛留库附平均概率）；状态存于研究所目录下的**加固 JSON** `State/<研究所>.v5state.json`（串行写、读前必 load），**不写入宿主会话日志**，零 token 成本。
 
@@ -30,13 +30,13 @@
 > （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
+### Vibe Math V2（概率驱动 · JSON 数据层）· 经典
 
 ![Vibe Math V2 架构图](示例图/框架图-v2.png)
 
 **一句话流水线**：`qs.json` 按优先级取问题 → Explorer 拆方向（全死路则重派生）→ 每方向一个 Solver 多轮迭代（引理进 `Propos/`、解法回 `qs.json`，概率均 <1）→ 调度器选 r（命题 / 命题+证明·证伪 / 问题+解法）派 ≥3 验证器独立审查→辩论→裁决 → 概率=1 自动收口（问题 solved、命题 1/0，优先级置 `never`）；全程状态落盘，`resume` 断点续跑，`reportMode` 可 file/push/both 汇报。
 
-### Vibe Math V3（论文式 md + 规划代理 + 方法库）✅ 主推
+### Vibe Math V3（论文式 md + 规划代理 + 方法库）· 经典
 
 ![Vibe Math V3 架构图](示例图/框架图-v3.png)
 
@@ -79,7 +79,7 @@ flowchart TB
     subgraph FW["⚙️ 框架 vibe-v5 —— 只是媒介（middleware），绝不指派任务"]
         M["消息中继 · 会议/辩论 · 任务板 CAS+DAG<br/>m 票共识验证 · 上下文与活性 · 编制与雇佣 · 调度器"]
     end
-    PROJ["💾 State/&lt;研究所&gt;.v5state.json（加固 JSON 权威源）<br/>11 类事件 · 纯折叠 applyV5Event · 串行写 · 恢复=读前必 load"]
+    PROJ["💾 State/&lt;研究所&gt;.v5state.json（加固 JSON 权威源）<br/>12 类事件 · 纯折叠 applyV5Event · 串行写 · 恢复=读前必 load"]
     FS["📁 Members/&lt;id&gt;/* · Shared/* · Verified/ · Problems/"]
     RULE{{"求真门槛：布尔一致 且 布尔票 ≥ m = min(quorumCap, 在册有表决权人数)"}}
     OFF <-->|"vibe_v5_* / /v5 命令　↔　status / report"| M
@@ -349,7 +349,7 @@ dsh plugin --profile <你的 profile> add dsh-vibe-math
 dsh plugin --profile <你的 profile> add github:ChongCyrus/Vibe-Mathematics
 ```
 
-之后新建会话，预设选择器里选择 **Vibe Math V3**（v3，**主推**）、**Vibe Math V2**（v2，**主推**）、**Vibe Math V4**（v4，常驻自组织）或 **Vibe Math V5**（v5，研究所体系）即可——v2 与 v3 同级主推，按实际需求自选（见「怎么选」）。
+之后新建会话，预设选择器里选择 **Vibe Math V2**（v2，经典）、**Vibe Math V3**（v3，经典）、**Vibe Math V4**（v4，常驻自组织）或 **Vibe Math V5**（v5，研究所体系）即可——四个架构同级，按实际需求自选（见「怎么选」）。
 **两个 DSH 世代的落点不同，本包自动适配**：
 
 - **DSH ≥ 0.1.7（当前）**：agent preset 由组合行声明。本包在 `cordis.patch.yml` 里声明四个 preset（每行把该 preset 的完整插件清单交给宿主的 `agentPresets` 服务注册），**不往 `~/.dsh/.agent-presets/` 写任何东西**——该目录自 0.1.7 起不再被读取。
@@ -378,13 +378,13 @@ dsh plugin --profile <你的 profile> add github:ChongCyrus/Vibe-Mathematics
 - **DSH STORE 兼容声明**：`package.json` 的 `dsh.compatibility.dshReleases` 对每个完整 DSH 版本逐项声明 `compatible` / `incompatible` / `unknown`（当前声明 `0.1.2-alpha.4` … `0.2.0-rc.2` 共 11 个版本为 `compatible`，实测目标为 `0.2.0-rc.2`）；`engines.dsh` 为 `>=0.1.2-alpha.4 <0.1.3-0 || >=0.1.3-alpha.2 <0.1.5-0 || >=0.1.5-alpha.1 <0.1.6-0 || >=0.1.6-alpha.1 <0.1.7-0 || >=0.1.7-alpha.1 <0.2.0-0 || >=0.2.0-alpha.1 <0.3.0-0`；`engines.node` 为 `^22.19.0 || >=24.0.0`。
   另外声明了 `peerDependencies`（`@deepseek-ai/dsh-base`，并标为 optional）：DSH ≥ 0.1.7 会用**宿主自己的版本**去比对插件声明的 peer 范围，不满足时**跳过整个 bundle 并给出明确提示**，而不是挂上一个跑不通的预设。
 - **运行时自检（版本 + 形态 + 能力）**：安装器（bundle 插件）每次启动时：**① 按优先级探测 DSH 版本**——`DSH_VERSION` 环境变量 → `pluginManager` 服务的 bundle 列表（`@deepseek-ai/dsh-base` 的版本即宿主版本，0.1.7+）→ `@deepseek-ai/dsh-app-boot` 导出的 `getDshRuntimeVersion()`（0.2.0+ 的公开 API）→ `@deepseek-ai/dsh/package.json`（全局 0.1.x 安装），日志会写明**来源**；探测到且未被 `dshReleases` 声明为 `compatible` 时给出明确提示。**② 判断 preset 形态**：从 loader 入口树里是否挂了 `@deepseek-ai/dsh-agent-preset`（或其 registry）判断本宿主是"组合行"还是"目录"，据此决定是否同步 `~/.dsh/.agent-presets/`——新宿主上会跳过并在日志里说明旧目录可安全删除。**③ 能力自检**（真正的挂载门槛）：`subagents`/`agents`/`tools`/`commands`/`fs` 为**必需**（缺失即 warning），`subprocess`/`sandboxPolicy`/`compaction` 为**可选**（缺失只提示"功能会静默降级"），另含 `fs.resolve` 返回形状检测与 subagent `agentOptions`/`toolFilter` capability 检测。preset 挂载失败时先看 DSH 日志里的自检 warning。
-- **升级路径**：DSH 升级后无需重装本包；升级本包用 `dsh plugin --profile <你的 profile> add dsh-vibe-math@latest`（`dsh plugin` 的 `--profile` 是必填项；用 `add` 而不是 `update`，因为 profile 里可能把版本钉成精确值，那时 `update` 不会跨过去），重启 DSH 后安装器会把四个 preset 的受管文件整体更新到新版本（改过的文件同样被替换，原文先进 `<presetRoot>/.vibe-math-backup/`；见上文「安装」说明）。
+- **升级路径**：DSH 升级后无需重装本包；升级本包用 `dsh plugin --profile <你的 profile> add dsh-vibe-math@latest`（`dsh plugin` 的 `--profile` 是必填项；用 `add` 而不是 `update`，因为 profile 里可能把版本钉成精确值，那时 `update` 不会跨过去），重启 DSH 后（DSH ≤ 0.1.6 的目录形式下）安装器会把四个 preset 的受管文件整体更新到新版本（改过的文件同样被替换，原文先进 `<presetRoot>/.vibe-math-backup/`；DSH ≥ 0.1.7 的 preset 来自组合行，安装器不写任何文件）——见上文「安装」说明。
 
 ---
 
 ## 🧭 四个预设怎么选
 
-> **💡 `vibe-math-v2` 与 `vibe-math-v3` 同级主推，按你的实际需求自行选择：**
+> **💡 四个架构同级，按你的实际需求自行选择：**
 >
 > - **选 `vibe-math-v2`（概率驱动 · JSON 数据层）**，如果你：
 >   - 偏好**结构化 JSON 数据**（`qs.json` / `Propos/<分类>_Propos.json` / `Verified/` 卡），方便程序化检索与二次加工；
@@ -402,14 +402,14 @@ dsh plugin --profile <你的 profile> add github:ChongCyrus/Vibe-Mathematics
 > - **选 `vibe-math-v5`（研究所体系）**，如果你想要：
 >   - **有组织的自组织**——现实研究所那样有**领头人（院士）**负责拆解、分派、定优先级、主持会议、督导进度，但**判断仍归每个人自己**；
 >   - **可增减的编制**——常驻研究员 + 可**自主雇佣/解雇**的临时工（临时工无表决权，适合处理核对、试算、资料整理等杂活）；
->   - **可调的一致性门槛**——`m = min(quorumCap, 有表决权人数)` 票布尔一致即定论（比"全体一致"更容易收敛，同时**反向票仍然阻塞**，少数派不会被弃权淹没）；
+>   - **可调的一致性门槛**——`m = min(quorumCap, 有表决权人数)` 票布尔一致即定论（因为反向票阻塞，实际门槛仍是"全部布尔票同向"；只有投出布尔票的人少于 `m` 时才不同）；
 >   - **零 token 成本的状态持久化**——研究所状态写在研究所目录下的加固 JSON 里，不占成员上下文预算。
 >
-> **⚠️ `vibe-math-v2` 与 `vibe-math-v3` 是成熟主推架构；`vibe-math-v4`、`vibe-math-v5` 是实验性架构，** 均可选择；老 `vibe-math-v1` 已被移除（本包仅含 v2/v3/v4/v5）。
+> **⚠️ `vibe-math-v2` 与 `vibe-math-v3` 是经典架构；`vibe-math-v4`、`vibe-math-v5` 是实验性架构，** 四者同级、均可选择；老 `vibe-math-v1` 已被移除（本包仅含 v2/v3/v4/v5）。
 
-| | **v2（概率驱动 · 主推）** | **v3（论文式 md · 主推）** | **v4（常驻自组织 · 实验）** | **v5（研究所体系 · 实验）** |
+| | **v2（概率驱动 · 经典）** | **v3（论文式 md · 经典）** | **v4（常驻自组织 · 实验）** | **v5（研究所体系 · 实验）** |
 |---|---|---|---|---|
-| 定位 | **主推**（JSON 数据层） | **主推**（第三代） | **实验性**（第四代） | **实验性**（第五代） |
+| 定位 | **经典**（JSON 数据层） | **经典**（第三代） | **实验性**（第四代） | **实验性**（第五代） |
 | 核心思想 | 概率驱动：`qs.json` 问题 + `Propos/` 命题库，按「正确概率 / 价值」调度 | **论文式 md 知识库 + 规划代理调度 + 通用理论发明库** | **持久化常驻子代理自组织**：互相留言 + 开会决定一切任务，无中央调度 | **研究所**：院士做组织与分派，成员各自研究；**≥ m 票布尔一致**才定论；临时工可按需雇入 |
 | 数据 | `qs/qs.json` + `Propos/<分类>_Propos.json` + `Reliable/` | `Problems/` + `Progress/` + `Propos/` + `Methods/`（全部 md，软规范锚点 + 自由叙述）+ `Verified/` | `Problems/` + **按常驻 id 归属**的 `Progress|Propos|Methods|Subproblems/<id>/` + `Shared/`（会议/任务板/辩论）+ `Verified/` | 同 v4 的按成员归属布局，另加 `Institutes.md`（编制镜像）；**权威状态在 `State/<研究所>.v5state.json`**，其余文件只是镜像与工作区 |
 | 角色 | explorer → 逐方向 solver → verifier | **planner（规划代理）** → explorer → 逐方向 solver → verifier → **method-keeper（方法整理代理）** | **N 个常驻研究者**（continuable），无固定角色 | **院士 acad**（领头人）+ **常驻研究员 r-n**（有表决权）+ **临时工 t-n**（无表决权，可雇可解雇）+ 所办（不研究不投票） |
@@ -420,12 +420,12 @@ dsh plugin --profile <你的 profile> add github:ChongCyrus/Vibe-Mathematics
 | 特设能力 | 命题「价值/关键性」自动晋升问题清单；`reportMode file/push/both`；`priorityAdjust` | **方法库沉淀循环**（`methods_used`/`new_inventions` → Method Keeper）；**计划审批门/方法晋升门**；**项目锁**；后生问题「来源与动机」一等公民 | **常驻各自沉淀 + 互相阅读**；**全体一致验证**；**随时增开/关闭常驻、留言干预**；**断点续跑** | v4 的全部能力，另加：**真实雇佣/解雇**（释放子会话、收回任务）；**compare-and-set 任务板 + 依赖 DAG**；**会议与验证严格互斥**；**编制镜像与结题记录**；**状态零 token 成本** |
 
 四者都支持：断点续跑（`vibe_math_resume` / `vibe_v4_resume` / `vibe_v5_resume`）、人工干预与暂停恢复、
-按项目隔离、子代理权限调控、自然语言驱动。**v2 与 v3 均为同级主推**——偏好结构化 JSON 数据与确定性调度选 v2，
+按项目隔离、子代理权限调控、自然语言驱动。**四个架构同级**——偏好结构化 JSON 数据与确定性调度选 v2，
 偏好论文式 md、规划代理与理论发明库选 v3；v4 是完全自组织的常驻合作研究，v5 是"有领头人 + 可增减编制 + 可调门槛"的研究所体系。
 
 ---
 
-## 🧠 架构与分工（v3 · 第三代）✅ 主推
+## 🧠 架构与分工（v3 · 第三代）· 经典
 
 框架 = **一个主代理（助手）+ 一个代码调度器 + 一个规划代理 + 六类子代理**。
 
@@ -461,7 +461,7 @@ v5 的完整架构（含成员生命周期、一轮时序、共识状态机、
 
 ## 📁 目录结构
 
-### v2（概率驱动 · 主推）
+### v2（概率驱动 · 经典）
 
 ```
 <会话工作区>/VibeMath/
@@ -478,7 +478,7 @@ v5 的完整架构（含成员生命周期、一轮时序、共识状态机、
    └─ VibeMath_State/                  # 调度器私有持久状态（断点恢复用）
 ```
 
-### v3（论文式 md + 规划代理 + 方法库）✅ 主推
+### v3（论文式 md + 规划代理 + 方法库）· 经典
 
 ```
 <会话工作区>/VibeMath/
@@ -652,11 +652,11 @@ v5 的完整架构（含成员生命周期、一轮时序、共识状态机、
 **Step 3 — 问答式调参（可选）**
 
 ```
-我想让它用加权投票，并发数设成 6。
+我想让它用强制裁决模式（forced）跑，并发数设成 6。
 ```
 
-主代理 `vibe_math_set_params {"verdictMode":"weighted-vote","maxParallelThreshold":6}`，
-并问你是否 `vibe_math_save_settings` 保存。
+主代理 `vibe_math_set_params {"verdictMode":"forced","maxParallelThreshold":6}`，
+并问你是否 `vibe_math_save_settings` 保存。（`verdictMode` 只接受 `flat|forced`；写其它值**不报错**，会被静默回退成该架构的默认值——v2 是 `flat`、v3 是 `forced`。）
 
 **Step 4 — 中途干预（可选）**
 
@@ -695,7 +695,7 @@ v5 的完整架构（含成员生命周期、一轮时序、共识状态机、
 
 ## ⚙️ 参数速查表
 
-### v2（概率驱动 · 主推）默认值
+### v2（概率驱动 · 经典）默认值
 
 | 参数 | 默认 | 说明 |
 |---|---|---|
@@ -705,7 +705,7 @@ v5 的完整架构（含成员生命周期、一轮时序、共识状态机、
 | `directionsPerSolver` | 1 | 每个 solver 提示词可见的方向总数（1 = 只看自己方向、互不干扰；N>1 = 自己 + 最多 N-1 个其他活跃方向摘要） |
 | `verifierCount` | 3 | 每个验证对象的独立验证器数量 |
 | `debateMaxRounds` | 5 | 验证辩论（交流群）最大轮数 |
-| `verdictMode` | `flat` | `flat` = 均衡机制（不一致判 0.5）/ `forced` = 强制裁决（历史准确率+严谨性加权） |
+| `verdictMode` | `flat` | `flat` = 取各验证者报告概率的**等权平均**（不一致时不再一律判 0.5）/ `forced` = 强制裁决（按历史准确率+严谨性加权；准确率按模型追踪，且只在对象此后获得布尔裁决时计分） |
 | `reportMode` | `file` | `file` = 写报告文件 / `push` = 推送主代理汇报 / `both` |
 | `promoteValueThreshold` | 0.7 | Propos 中「价值/关键性」≥ 该值且未决(0,1) 的命题自动加入 qs.json |
 | `priorityAdjust` | `none` | `none` / `deadend-deprioritize`（全死路降优先级）/ `survival-map`（按存活率重算） |
@@ -733,12 +733,12 @@ v5 的完整架构（含成员生命周期、一轮时序、共识状态机、
 
 | 参数 | 默认 | 说明 |
 |---|---|---|
-| `verdictMode` | `forced` | v3 先做**近共识判定**（全部结果同侧且均值 ≥0.85/≤0.15 取均值），否则 `forced`=按历史准确率+严谨性加权 / `flat`=均衡（0.5）。修复了 v2 flat 把"0.9 vs 1"误判成 0.5 的问题 |
+| `verdictMode` | `forced` | v3 先做**近共识判定**（全部结果同侧且均值 ≥0.85/≤0.15 取均值）——这一步先于模式生效，所以 0.9 vs 1 在两种模式下都得到 ≈0.95；否则 `forced` 取各验证者概率的**等权平均**（不再按准确率加权；严格的 1/0 仍以绝对票生效），`flat` 则判 `0.5`（不一致即不确定） |
 | `planningHorizon` | 3 | 规划代理一次计划的最多动作数（"接下来 n 次"） |
 | `plannerEnabled` | true | false = 完全走内置启发式调度（规划代理禁用） |
 | `plannerProvider` / `plannerModel` | 空 | 规划代理模型路由（空 = 继承根代理） |
 | `plannerPersona` | 空 | 注入规划代理提示词开头的人格/要求 |
-| `planMinIntervalMs` | 30000 | 两次规划调用的最小间隔（毫秒）；系统空闲且有工作时忽略 |
+| `planMinIntervalMs` | 30000 | 两次规划调用的最小间隔（毫秒）；对**每一次**规划调用都生效（含空计划、含"空闲但仍有工作"，不再有空闲绕过） |
 | `plannerMaxFails` | 3 | 规划代理连续失败达此值 → 自动降级启发式 |
 | `methodKeepIntervalMs` | 0 | Method Keeper 定时整理间隔（0 = 事件驱动） |
 | `methodKeepEvery` | 5 | 每积累 N 个待沉淀发明/新命题触发一次整理 |
@@ -826,8 +826,8 @@ 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 ≈1.9 min；探针脚本 ≈2.6 min；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)（197 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"
+- **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"
 - **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
@@ -841,16 +841,16 @@ v5 的完整架构（含成员生命周期、一轮时序、共识状态机、
 - **（DSH ≤ 0.1.6 的目录形式）** 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：删除那四个 preset 目录后重启 DSH。
   在 DSH ≥ 0.1.7 上安装器**不写这些目录**（预设由上文「安装」里的组合行提供），启动时只会提示旧副本可安全删除。
 - **在 DSH ≤ 0.1.6 上，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）。在 DSH ≥ 0.1.7 上它们不再被读取、也不再被写入，直接删掉即可；想彻底不要本包的预设，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。
+- `flat` 裁决在辩论不一致时取各验证者概率的**等权平均**（不再直接判 `0.5`；早期把高置信分歧 0.9 vs 1 误判为 0.5 的问题已在 v2/v3 修复）；`forced` 按历史准确率+严谨性加权，且准确率只在对象此后获得布尔裁决时计分。
 - `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）。
 - 四个 preset 文件互相独立、可共存；同一会话同时只能选一个预设。
 
 **v3**：
 - **软规范而非零规范**：md 知识库只强制对象头部的 4~7 行锚点（`- ID/类型/状态/概率/优先级/依赖/...`）与条目标题行（`### 解法/证明/证伪 N｜标题｜概率X｜状态Y`），供调度器可靠索引；正文完全自由论文式叙述，调度器从不解析正文。手工编辑锚点可能导致索引漂移（调度器会保留上次有效索引并告警）。
-- **规划代理是增强而非必需**：`plannerEnabled=false` 或规划代理连续失败（`plannerMaxFails`）时自动回退 v2 式启发式调度；`planMinIntervalMs` 冷却在有在途子代理时生效（系统空闲时有工作则立即规划）。
+- **规划代理是增强而非必需**：`plannerEnabled=false` 或规划代理连续失败（`plannerMaxFails`）时自动回退 v2 式启发式调度；`planMinIntervalMs` 冷却对**每一次**规划调用生效——包括空计划和"空闲但仍有工作"的情形（空闲不再绕过冷却，那正是规划代理每 tick 空转的放大器）。
 - **方法库可信分层**：方法卡的 `可信断言` 只允许链接已进 `Verified/` 的 ID；方法条目的其余内容（含未验证的策略/直觉/启发式）一律视为**经验参考**，不得当定理引用。
 - **项目锁**：同一项目同一时刻只允许一个会话调度（第二个会话启动会提示"被会话 X 占用"）；锁在暂停/终止/全部解决时自动释放。
-- **近共识裁决**：全部验证器结果同侧且均值 ≥0.85/≤0.15 时取均值（如 0.9 vs 1 → 0.95），否则 `forced` 加权 / `flat` 判 0.5——修复了 v2 中"数学上正确但形式有瑕疵"的结论被误判为不确定的问题。
+- **近共识裁决**：全部验证器结果同侧且均值 ≥0.85/≤0.15 时取均值（如 0.9 vs 1 → 0.95），否则 `forced` 取各票的**等权平均**、`flat` 判 `0.5`——修复了 v2 中"数学上正确但形式有瑕疵"的结论被误判为不确定的问题。
 
 **v5**：
 - **框架绝不指派任务**：这是设计上的硬边界，不是尚未实现的功能。任务的产生与分配属于**所内自治**
@@ -858,7 +858,8 @@ v5 的完整架构（含成员生命周期、一轮时序、共识状态机、
 - **`≥ m` 一致 ≠ 数学上已证明**：门槛只保证"所内达成了一致判断"，不保证结论真的正确。
   求真的纵深靠成员自己的推导与辩论录留痕；未达门槛的对象会**留库附平均概率**，不会被强行判真判假。
 - **一致性门槛不是"少数服从多数"**：任何一张反向布尔票都阻塞定论，弃权既不帮真也不帮假。
-  要更容易收敛就调低 `quorumCap` 或减少有表决权人数；要更严格可切 `quorumMode: "all-unanimous"`。
+  因此在本口径下（`m = min(quorumCap, 有表决权人数)`）**只要有人投布尔票，门槛就等于"全部布尔票同向"**：
+  调低 `quorumCap` 只是把"至少几张布尔票"降到 `m`，**不会让收敛更容易**；要更严格可切 `quorumMode: "all-unanimous"`（它连弃权都不允许）。
 - **一个回合永不结束的成员不会被强行释放**（与 v4 同一边界）：心跳每次都会重新武装，
   所以调度器不会永久冻结；需要人工介入时用 `vibe_v5_fire`（临时工）或所办增删编制。
 - **会议与验证严格互斥**：一方进行中，另一方排队/暂存。因此"在会议上当场定论一个对象"会先排队，

package/SECURITY.md

@@ -0,0 +1,56 @@
+# Security Policy
+
+## Supported versions
+
+Security fixes are released for the latest published line. The previous line receives security fixes
+only for the DSH host versions it was built against.
+
+| Version | Supported | Notes |
+|---|---|---|
+| 2.4.x (latest) | ✅ | Current line — DSH 0.1.2-alpha.4 … 0.2.0-rc.2 |
+| 2.3.x | ⚠️ security fixes only | Superseded by 2.4.x, which also covers DSH ≤ 0.1.6; **cannot run on DSH 0.2.x** |
+| ≤ 2.2.x | ❌ | Please upgrade |
+
+## Reporting a vulnerability
+
+Please **do not** open a public issue for a security problem. Use GitHub's private vulnerability
+reporting on this repository (Security → Report a vulnerability), or contact the maintainer through
+the profile linked from <https://github.com/ChongCyrus/Vibe-Mathematics>.
+
+Please include: the affected version and DSH host version, a minimal reproduction, the impact you
+believe it has, and whether you are willing to be credited.
+
+We aim to acknowledge a report within 7 days and to ship a fix or a documented mitigation within 30
+days for anything rated high or critical. If the report turns out to concern the DSH host itself
+rather than this package, we will say so and point you at the right project.
+
+## What this package does (and what it does not)
+
+Knowing the design makes reports much easier to triage:
+
+- **What it is.** `dsh-vibe-math` is a DeepSeek Harness plugin bundle. It ships four agent presets
+  (v2/v3/v4/v5) and an installer. It runs **inside** the DSH host process with whatever permissions
+  the user granted that host — it does not add privileges of its own.
+- **No dynamic code execution.** The package contains no `eval` and no `new Function`. Its behaviour
+  is fixed at install time; nothing in a session can inject code into it.
+- **Filesystem.** The presets read and write only inside the session workspace (the project directory
+  that DSH hands to the session) — `VibeMath/…` — through the host's `fs` service, so the host's
+  sandbox policy applies there. The **installer** additionally syncs preset files for hosts it does
+  not detect as using composition rows (the DSH ≤ 0.1.6 directory line) into the legacy
+  `<DSH_HOME>/.agent-presets/` directory (default `~/.dsh/.agent-presets/`), including its
+  `.vibe-math-installed.json` state file and `.vibe-math-backup/` copies of replaced files. That sync
+  uses Node's own `fs` **inside the host process**, not the host `fs` service, so only the host's
+  OS-level sandbox applies to it.
+- **No network, no credentials, no telemetry.** The package itself makes no outbound requests and
+  reads no secrets or tokens. Model traffic, if any, is the host's own LLM service.
+- **Subprocesses.** The Lean toolchain and shell helpers are invoked only when a preset tool is
+  actually called, through the host's `subprocess` service under the host's sandbox policy.
+- **Prompts are data.** The preset prompts, corpora and documentation are inert text shipped with
+  the package; the repository's own suites verify that model-facing text matches the implementation.
+
+## Verifying what you install
+
+- Published tarballs: `npm view dsh-vibe-math dist.shasum dist.integrity`
+- The release gate the maintainer runs before publishing lives outside this repository (it re-runs every
+  guard, the packaging checks, and the plugin-catalog compliance scan); the artifact hashes above are
+  the verifiable output of a release.