dsh-vibe-math 2.4.1 → 2.6.0

package/vibe-math-v2//345/256/236/347/216/260/346/226/271/346/241/210.md

@@ -125,6 +125,11 @@
    - 记 `p_{q-tmp}` 为对 `q_sub` 的某种回答/答案的**临时假设**（**命题类对象**）；
    - 把**临时问题 `q_sub`** 与**「判断下述命题是否成立：`p_{q-tmp}`」**两个问题一起加入 `qs.json`（两者的概述、定义必须完整——所涉及的对象、依赖、环境、背景等一律给出完整定义，避免断章取义）；
    - 将 `p_{q-tmp}` 作为命题对象写入 `Propos/`（布尔估计记 `0.5`，`progress` 标注“临时假设 · 依赖 `q_sub`”）；若该假设被证伪，则依赖它的主线结论需重新审视；
+      - 依赖关系**必须落库**：处在某条在力假设之下的引理会带上 `依赖假设` 字段（`vibe_math_list_propositions`
+        与验证提示词都会显示它），假设被证伪时依赖它的结论被标记 `依赖假设已证伪` 并重新进入验证候选；
+      - “判断下述命题是否成立：p_{q-tmp}”这个问题**自带一条种子解法**（就是"该假设成立"这一候选回答，概率 `0.5`，
+        不是定论）。没有它，验证候选集里永远没有属于这个问题的对象（裸 `p-tmp-*` 命题被显式跳过），
+        于是 `p_{q-tmp}` 永远停在 `0.5`、判断问题永不收口、终止规则不可达；
    - 在当前线程中，**临时假设 `p_{q-tmp}` 成立**，继续推进主线；
    - 后续所得命题/结论中**凡依赖该假设的**，必须把假设作为前提显式写出，形如「若 `p_{q-tmp}` 成立，则：...」（概述、定义完整，不断章取义）。
 4. **终止条件（进入 `END` 状态）**：
@@ -171,14 +176,25 @@
 
 3. **共识判定与强制裁决**  
    - 若达到最大轮数后仍未一致，则按预设参数采用以下方式之一：
-     - 均衡机制：直接判定为 `0.5`；
-     - 强制裁决机制：基于各代理历史准确率与本次推理严谨性评分（系统动态评估），综合计算得到 `r` 的判定结果（介于 `(0,1)`）。
+     - 均衡机制（`verdictMode='flat'`）：取各评审**自报概率的均值**（只有精确的 `1`/`0` 才是绝对真/假，
+       `0<Result<1` 是"它为真的概率"；不再把高置信分歧折叠成固定的 `0.5`）；
+     - 强制裁决机制（`verdictMode='forced'`）：按验证者的历史准确率与布尔票置信度加权求平均，得到
+       `(0,1)` 内的判定结果。准确率按**稳定身份**（`provider/model`）记，且只在对象**后来**取得布尔
+       定论时回溯计分——按一次性的子代理 id 记（恒 `0.5`）或拿本次聚合值给同一批评审打分都是自指的。
+   - 无论哪种机制，中段结果（`0<r<1`）都**不是**定论：对象重新变为可验证（冷却期后重新入选），
+     绝不把中段结果当成绝对真/假来写卡片或收口。
+   - 每次裁定需要**至少 2 名独立评审**：票数不足时先补派，补不足就搁置该对象等冷却期后重试，
+     绝不退化成单票结论。为保证"另一个对象也凑得齐 2 票"，单个验证对象同时占用的评审槽位不超过
+     `maxParallelThreshold - 2`（容量宽裕时就是 `verifierCount`）。
 
 4. **更新数据**  
    - 若 `r` 为单个命题，则记 `a = r`；若 `r` 为“命题+证明/证伪”或“问题+解法”，则记 `a` 为 `r` 中的那个证明/证伪/解法。
-   - 若判定结果为 `0`：更新 `a` 的正确概率为 `0`，并将完整证伪过程记录到证伪列表；
+   - 若判定对象是**命题本身**且结果为 `0`：更新 `a` 的布尔估计为 `0`，并将完整证伪过程记录到证伪列表（概率 `1`）；
+   - 若判定对象是**某一条证明/证伪**且结果为 `0`：那只表示**这一条过程无效**（`a` 的正确概率记 `0`、`已验`），
+     **不是**"命题为假"——绝不因此向对侧列表伪造一条概率 `1` 的反条目，也绝不改写命题的布尔估计。
+     伪否定会经由收口规则变成一张"已验证·假"的卡片，那正是这条规则要避免的（与 `defect` 同类事故）。
    - 若判定结果为 `1`：更新 `a` 的正确概率为 `1`，并将完整证明过程记录到证明列表；
-   - 若判定结果介于 `0` 和 `1` 之间：更新 `a` 的正确概率为该结果，并分别向证明、证伪列表添加根据辩论得出的尽可能正确的过程/支撑信息及相应概率。
+   - 若判定结果介于 `0` 和 `1` 之间：更新 `a` 的正确概率为该结果，并分别向证明、证伪列表添加根据辩论得出的尽可能正确的过程/支撑信息及相应概率；对象在冷却期后重新进入验证候选（中段值不是定论）。
    - 辩论全程发言记录存入 `Verification_logs/` 对应日志，便于复盘与审计。
 
 ---

package/vibe-math-v3/agent.cordis.yml

@@ -38,7 +38,8 @@
       - vibe_math_add_problem {id, description, priority, dependencies?} — add a problem (creates Problems/<id>.md).
       - vibe_math_add_proposition {id, 概述, 概率, 优先级, 价值/关键性, 分类} — add a proposition (Propos/<分类>/<id>.md).
       - vibe_math_list_propositions — list the proposition knowledge base.
-      - vibe_math_start / vibe_math_resume — start / resume the scheduler (resume = continue after checkpoint/restart).
+      - vibe_math_start / vibe_math_resume — start / resume the scheduler (resume = continue after checkpoint/restart);
+        both accept override=true to take the project lock over from another session (only after you verified that session is gone).
       - vibe_math_status / vibe_math_report — read status / full progress report (report writes Progress_Logs/report.json + Logs/报告.md).
       - vibe_math_pause / vibe_math_abort — pause / abort.
       - vibe_math_set_mode {mode: manual|auto} — switch manual / auto (manual gates: 计划审批 / 裁决 / 方法晋升).
@@ -46,12 +47,16 @@
         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.
       - vibe_math_method_add / vibe_math_method_list — manually add / list method cards (Methods/ + global).
-      - vibe_math_lock_status — project lock occupancy.
+      - vibe_math_lock_status — project lock occupancy (the lock is a renewed lease: while a session is running it never expires; taking it over needs override=true, or happens automatically once the owner's lease has clearly expired after a crash).
+        Only ONE session may run a project: a second session is refused with PROJECT_LOCKED instead of silently writing the same knowledge base in parallel.
       - 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.
       - vibe_math_list_agents / vibe_math_message_agent / vibe_math_interrupt_agent — inspect / steer / interrupt subagents.
@@ -59,14 +64,20 @@
         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 (/vibe start|resume|pause|abort|status|report|mode
-      <auto|manual>|setup|save|add <id> <desc>|add-proposition <id> <概述>|list-propositions|methods|index|plan|lock|...).
+      A /vibe slash command mirrors the main controls (/vibe start [override]|resume [override]|pause|abort|status|report|mode
+      <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
       (the scheduler writes Verified/问题/<id>.md); a proposition reaches 已验证·真/假 when a 证明/证伪
-      entry reaches 概率 = 1 (Verified/命题/<id>.md); Propos propositions with 价值/关键性 ≥
-      promoteValueThreshold auto-promote into Problems/ as "判断下述命题是否成立：<命题>" (verification
+      entry reaches 概率 = 1 (Verified/命题/<id>.md).
+      Closure rule (identical across the presets): those 概率 = 1 values are written ONLY by the scheduler,
+      after ≥2 independent verifier agents settle the object (a lone reviewer can never conclude; see
+      minVotes), and Verified/ is written by that same scheduler path — a self-reported 1 is never a
+      conclusion. Propos propositions whose 价值/关键性 ≥
+      promoteValueThreshold (write that anchor on the proposition card, or report it as lemmas[].价值/关键性 in
+      vibe_math_sync_meta — default 0.5 never promotes) and that are still undecided
+      auto-promote into Problems/ as "判断下述命题是否成立：<命题>" (verification
       results sync back to the source proposition); a solver-reported sub-question q_sub registers THREE
       objects (q_sub problem + judge problem + p-tmp temporary-assumption proposition) with full 来源与动机.
 
@@ -112,7 +123,8 @@
       - vibe_math_add_problem {id, description, priority, dependencies?} — add a problem (creates Problems/<id>.md).
       - vibe_math_add_proposition {id, 概述, 概率, 优先级, 价值/关键性, 分类} — add a proposition (Propos/<分类>/<id>.md).
       - vibe_math_list_propositions — list the proposition knowledge base.
-      - vibe_math_start / vibe_math_resume — start / resume the scheduler (resume = continue after checkpoint/restart).
+      - vibe_math_start / vibe_math_resume — start / resume the scheduler (resume = continue after checkpoint/restart);
+        both accept override=true to take the project lock over from another session (only after you verified that session is gone).
       - vibe_math_status / vibe_math_report — read status / full progress report (report writes Progress_Logs/report.json + Logs/报告.md).
       - vibe_math_pause / vibe_math_abort — pause / abort.
       - vibe_math_set_mode {mode: manual|auto} — switch manual / auto (manual gates: 计划审批 / 裁决 / 方法晋升).
@@ -120,12 +132,16 @@
         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.
       - vibe_math_method_add / vibe_math_method_list — manually add / list method cards (Methods/ + global).
-      - vibe_math_lock_status — project lock occupancy.
+      - vibe_math_lock_status — project lock occupancy (the lock is a renewed lease: while a session is running it never expires; taking it over needs override=true, or happens automatically once the owner's lease has clearly expired after a crash).
+        Only ONE session may run a project: a second session is refused with PROJECT_LOCKED instead of silently writing the same knowledge base in parallel.
       - 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.
       - vibe_math_list_agents / vibe_math_message_agent / vibe_math_interrupt_agent — inspect / steer / interrupt subagents.
@@ -133,14 +149,20 @@
         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 (/vibe start|resume|pause|abort|status|report|mode
-      <auto|manual>|setup|save|add <id> <desc>|add-proposition <id> <概述>|list-propositions|methods|index|plan|lock|...).
+      A /vibe slash command mirrors the main controls (/vibe start [override]|resume [override]|pause|abort|status|report|mode
+      <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
       (the scheduler writes Verified/问题/<id>.md); a proposition reaches 已验证·真/假 when a 证明/证伪
-      entry reaches 概率 = 1 (Verified/命题/<id>.md); Propos propositions with 价值/关键性 ≥
-      promoteValueThreshold auto-promote into Problems/ as "判断下述命题是否成立：<命题>" (verification
+      entry reaches 概率 = 1 (Verified/命题/<id>.md).
+      Closure rule (identical across the presets): those 概率 = 1 values are written ONLY by the scheduler,
+      after ≥2 independent verifier agents settle the object (a lone reviewer can never conclude; see
+      minVotes), and Verified/ is written by that same scheduler path — a self-reported 1 is never a
+      conclusion. Propos propositions whose 价值/关键性 ≥
+      promoteValueThreshold (write that anchor on the proposition card, or report it as lemmas[].价值/关键性 in
+      vibe_math_sync_meta — default 0.5 never promotes) and that are still undecided
+      auto-promote into Problems/ as "判断下述命题是否成立：<命题>" (verification
       results sync back to the source proposition); a solver-reported sub-question q_sub registers THREE
       objects (q_sub problem + judge problem + p-tmp temporary-assumption proposition) with full 来源与动机.