dsh-vibe-math 2.4.1 → 2.6.0

package/vibe-math-v3//345/256/236/347/216/260/346/226/271/346/241/210.md

@@ -146,11 +146,11 @@ VibeMath/                                   # 工作区级
        ├─ tasks.json                        # 验证任务等
        ├─ plans.json                        # 当前待执行计划队列
        ├─ index.json                        # 锚点扫描重建的机器索引（调度唯一读取面）
-       ├─ verifier_accuracy.json            # 验证器历史准确率
+       ├─ verifier_accuracy.json            # 验证器投票记录（审计轨迹；不参与加权，见 §9 裁决）
        ├─ method_log.json                   # 方法库操作日志（上报/沉淀/晋升）
        ├─ formal.json                       # 【新】形式化记录（records/todo/libRuns，按对象 id）
        ├─ process_epoch.json                # 进程纪元（断点续跑判据）
-       └─ project.lock                      # 会话级项目锁（防并发写冲突）
+       └─ project_lock.json                 # 会话级项目锁（租约；运行中每 10s 续租，夺取需显式 override）
 ```
 
 **路径职责**：`Problems/` 问题清单类、`Progress/` progress 类、`Propos/` 结论/命题类、`Methods/` 理论发明类、`Formal/`（项目内）与 `Formal/{Lib,Proved}`（工作区级，见 §11.1）Lean 形式化类、`Verified/` 绝对可信类（含 `Verified/Lean/` 归档证明）、`Reliable/` 可信参考、`Notes/` 自由记录、`Logs/` 审计、`State/` 机器状态——**不同类型，不同路径**（需求 1）。
@@ -398,7 +398,7 @@ VibeMath/                                   # 工作区级
 - **目标对象**：单个命题 / 命题+证明或证伪 / 问题+解法，从 md 读取（锚点 + 正文全文）；
 - **独立审查**：≥3 个验证器各自独立输出 `{Result ∈ [0,1], Reason}`（判定 1 需完整证明，判定 0 需严谨证伪，否则取中间值）；独立前互不通气；
 - **辩论（交流群）**：轮流发言，回应他人、可改变立场（须说明理由）；上限 `debateMaxRounds`；全部一致（全 1 或全 0）即终止；
-- **裁决**：`verdictMode` —— `flat`（均衡）/ `forced`（按历史准确率+严谨性加权）/ `manual`（人工）；中间结果回写证明/证伪列表与对应概率。
+- **裁决**：`verdictMode` —— `flat`（均衡：分歧时 0.5）/ `forced`（强制裁决：对每票**等权取均值**——严格 1/0 是唯一"绝对投票"语义，其影响通过数值本身拉向端点；**不按"历史准确率"加权**，因为那只是"与本批裁决的一致度"，没有后续真值可纠正它）/ `manual`（人工）；中间结果回写证明/证伪列表与对应概率。**最小票数**：一个对象至少要有 `max(2, verifierCount)` 票才能裁决（`allReported` 同时要求"已派出的验证器数达到预期"且"本轮全部回报"），单票绝不结论。
 
 ### 8.2 v3 默认修复 v2 审计发现的缺陷
 

package/vibe-math-v4/agent.cordis.yml

@@ -61,7 +61,7 @@
       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.
@@ -71,14 +71,28 @@
           (execute / archive / list the reuse library). Residents use them too; they work in every mode.
         - 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|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|resume|pause|abort|status|report|message <to|all> <content>|meeting|members|add|remove|set).
+        - 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|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 —
       is experiential reference. A proposition / method / theory only reaches Verified/ when
       ALL residents unanimously agree true (or all agree false); otherwise it stays in its
-      library with a probability estimate.
+      library with a probability estimate. Closure rule (identical across the presets): the framework
+      writes the Verified/ card — a resident's own claim never does — and what counts as a vote is
+      stated once in the VOTE CONTRACT below.
+
+      VOTE CONTRACT: a verification vote is a probability of truth in [0,1], but only an EXACT
+      1 (absolutely true) and an EXACT 0 (absolutely false) count as a vote. Anything strictly
+      between (0.9, 0.95, 0.5 …) is an ABSTENTION carrying that probability estimate: the run
+      does NOT conclude, and the group's MEAN probability is written back to the object's card
+      so it stays in its library with a probability. The same absoluteness applies to the
+      meeting stop-vote: every resident on the roster must answer `voteSolved:true` — one
+      abstention keeps the run alive.
 
       LEAN FORMAL VERIFICATION (formalVerify, a tunable parameter):
         - 'off' (default, no extra requirement) | 'encourage' (the residents decide by implementation
@@ -143,7 +157,7 @@
       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.
@@ -153,14 +167,28 @@
           (execute / archive / list the reuse library). Residents use them too; they work in every mode.
         - 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|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|resume|pause|abort|status|report|message <to|all> <content>|meeting|members|add|remove|set).
+        - 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|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 —
       is experiential reference. A proposition / method / theory only reaches Verified/ when
       ALL residents unanimously agree true (or all agree false); otherwise it stays in its
-      library with a probability estimate.
+      library with a probability estimate. Closure rule (identical across the presets): the framework
+      writes the Verified/ card — a resident's own claim never does — and what counts as a vote is
+      stated once in the VOTE CONTRACT below.
+
+      VOTE CONTRACT: a verification vote is a probability of truth in [0,1], but only an EXACT
+      1 (absolutely true) and an EXACT 0 (absolutely false) count as a vote. Anything strictly
+      between (0.9, 0.95, 0.5 …) is an ABSTENTION carrying that probability estimate: the run
+      does NOT conclude, and the group's MEAN probability is written back to the object's card
+      so it stays in its library with a probability. The same absoluteness applies to the
+      meeting stop-vote: every resident on the roster must answer `voteSolved:true` — one
+      abstention keeps the run alive.
 
       LEAN FORMAL VERIFICATION (formalVerify, a tunable parameter):
         - 'off' (default, no extra requirement) | 'encourage' (the residents decide by implementation