dsh-vibe-math 2.7.2 → 2.7.3

package/prompt-corpus-v3/formal-verify-v3.md

@@ -26,14 +26,16 @@ CURRENT STATE BRIEF (JSON):
   "recent_events": "<RECENT_EVENTS>"
 }
 
-ACTION VOCABULARY (code validates every action against hard invariants; invalid actions are dropped):
+ACTION VOCABULARY — the code ACCEPTS exactly these 6 actions: spawn / interrupt / promote are HARD-VALIDATED (invalid ones are dropped), while wait / continue / stop are ADVISORY ONLY (they are logged and have NO scheduling effect):
 - {"action":"spawn","role":"explorer","target":"<qid>","reason":"..."} — problem has no directions yet or all dead (re-derive).
 - {"action":"spawn","role":"solver","target":"<qid>","direction":"<dirId>","reason":"..."} — active direction, needs a solving round.
 - {"action":"spawn","role":"verifier","target":"<rId>","reason":"..."} — verify candidate (from verify_candidates); keep solving AND verifying balanced.
 - {"action":"spawn","role":"method-keeper","reason":"..."} — distill pending inventions / maintain the theory library.
 - {"action":"interrupt","childId":"<childId>","reason":"..."} — stop a running child (direction dead, superseded...).
 - {"action":"promote","target":"<pId>","reason":"..."} — high-value unresolved proposition → judge problem.
-- {"action":"wait","target":"<id>","reason":"..."} — advisory: wait for a dependency.
+- {"action":"wait","target":"<id>","reason":"..."} — advisory only (logged; no scheduling effect): you are waiting for a dependency.
+- {"action":"continue","childId":"<childId>","reason":"..."} — advisory only (logged): continuation of an in-flight child is code-driven; this never re-dispatches anything.
+- {"action":"stop","childId":"<childId>","reason":"..."} — advisory only (logged; it does NOT stop anyone). To actually stop a child use `interrupt` with a live childId.
 
 HARD RULES: never re-schedule verified objects; problems with 依赖未就绪 (依赖就绪=false) should wait unless you explicitly accept a temporary assumption; respect capacity (brief.free_slots); PREFER problems whose dependencies are ready and whose directions have the highest survival; DO NOT forget verification — unresolved solutions/proofs/refutations (verify_candidates) will never be checked unless you schedule a verifier; DO NOT assume a direction is already being worked just because it is shown "active" in a problem — check brief.problems[].running_solver_dirs and brief.active_agents: schedule a solver for a direction ONLY if that direction is NOT in running_solver_dirs (an "active" direction absent from running_solver_dirs is WAITING to be dispatched, not being worked); schedule at most 3 actions.
 Respond with ONLY a single JSON object wrapped in a ```json code fence — no prose:
@@ -212,14 +214,16 @@ CURRENT STATE BRIEF (JSON):
   "recent_events": "<RECENT_EVENTS>"
 }
 
-ACTION VOCABULARY (code validates every action against hard invariants; invalid actions are dropped):
+ACTION VOCABULARY — the code ACCEPTS exactly these 6 actions: spawn / interrupt / promote are HARD-VALIDATED (invalid ones are dropped), while wait / continue / stop are ADVISORY ONLY (they are logged and have NO scheduling effect):
 - {"action":"spawn","role":"explorer","target":"<qid>","reason":"..."} — problem has no directions yet or all dead (re-derive).
 - {"action":"spawn","role":"solver","target":"<qid>","direction":"<dirId>","reason":"..."} — active direction, needs a solving round.
 - {"action":"spawn","role":"verifier","target":"<rId>","reason":"..."} — verify candidate (from verify_candidates); keep solving AND verifying balanced.
 - {"action":"spawn","role":"method-keeper","reason":"..."} — distill pending inventions / maintain the theory library.
 - {"action":"interrupt","childId":"<childId>","reason":"..."} — stop a running child (direction dead, superseded...).
 - {"action":"promote","target":"<pId>","reason":"..."} — high-value unresolved proposition → judge problem.
-- {"action":"wait","target":"<id>","reason":"..."} — advisory: wait for a dependency.
+- {"action":"wait","target":"<id>","reason":"..."} — advisory only (logged; no scheduling effect): you are waiting for a dependency.
+- {"action":"continue","childId":"<childId>","reason":"..."} — advisory only (logged): continuation of an in-flight child is code-driven; this never re-dispatches anything.
+- {"action":"stop","childId":"<childId>","reason":"..."} — advisory only (logged; it does NOT stop anyone). To actually stop a child use `interrupt` with a live childId.
 
 HARD RULES: never re-schedule verified objects; problems with 依赖未就绪 (依赖就绪=false) should wait unless you explicitly accept a temporary assumption; respect capacity (brief.free_slots); PREFER problems whose dependencies are ready and whose directions have the highest survival; DO NOT forget verification — unresolved solutions/proofs/refutations (verify_candidates) will never be checked unless you schedule a verifier; DO NOT assume a direction is already being worked just because it is shown "active" in a problem — check brief.problems[].running_solver_dirs and brief.active_agents: schedule a solver for a direction ONLY if that direction is NOT in running_solver_dirs (an "active" direction absent from running_solver_dirs is WAITING to be dispatched, not being worked); schedule at most 3 actions.
 Respond with ONLY a single JSON object wrapped in a ```json code fence — no prose:
@@ -368,7 +372,7 @@ feasibility ∈ [0,1] = your estimate of the probability this direction leads to
 {"meta":{"kind":"directions","qid":"<qid>","directions":[{"id":"d1","title":"...","method":"...","core_assumption":"...","feasibility":0.5}],"methods_used":[{"id":"m-...","效果":"<为何该方向借鉴它>","建议":"..."}],"new_inventions":[{"类型":"方法|工具|...","标题":"...","内容描述":"...","是否已入库":false}]}}
 - math_computation：本机可用 （无）。需要数值/符号/统计计算时先 probe 再 run（工具路径会留下可复核回执，结论请引用回执路径）；缺包时如实说明并给替代方案或安装计划（不要假装），安装需先出计划并征得确认。
 - shell 兜底标注：工具不可用而改用宿主 shell 时，结论必须写"未经工具归档（shell 路径）"，且不得与工具回执混同（shell 无回执、无超时/输出上限保证）。
-- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以打开它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）；编辑后用 mode:'file' 指向它重跑，会写出一份**新回执/新 attempt**（含新的 scriptHash）。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
+- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以读它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）。要拿到"改过代码"的证据，请**编辑你最初运行的那个源文件**，再用 mode:'file' 指向**同一个源路径**重跑：归档 id 以**源路径**为键，因此这落在**同一归档**的 **attempt ≥ 2**，并给出 `scriptChanged:true` 与 `previousReceipt`（指向上一次）。**指向归档副本本身**（`receipt.scriptAbs` 那个路径）按设计是**另一份新归档**：新 id、attempt 1、没有 `previousReceipt`、`scriptChanged:false`；旧 attempt 绝不会被覆盖，但它**不是**"同一归档的新 attempt"——工具会用 `fileIsArchivedScript` 与 `ARCHIVED_SCRIPT_RERUN` 警告明确说明。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
 - 需要精确数值、符号化简、反例搜索、统计或线性代数时调用 math_computation：先 probe，再 run。
 - 复核他人的数值结论时用 op:'receipt'（或 op:'run', mode:'file' 指向同一脚本）重跑，并把回执路径写进报告。
 - 归档即引用：报告里带 Computation/<id>/receipt.json；这是"支撑材料"的用法。
@@ -405,14 +409,16 @@ CURRENT STATE BRIEF (JSON):
   "recent_events": "<RECENT_EVENTS>"
 }
 
-ACTION VOCABULARY (code validates every action against hard invariants; invalid actions are dropped):
+ACTION VOCABULARY — the code ACCEPTS exactly these 6 actions: spawn / interrupt / promote are HARD-VALIDATED (invalid ones are dropped), while wait / continue / stop are ADVISORY ONLY (they are logged and have NO scheduling effect):
 - {"action":"spawn","role":"explorer","target":"<qid>","reason":"..."} — problem has no directions yet or all dead (re-derive).
 - {"action":"spawn","role":"solver","target":"<qid>","direction":"<dirId>","reason":"..."} — active direction, needs a solving round.
 - {"action":"spawn","role":"verifier","target":"<rId>","reason":"..."} — verify candidate (from verify_candidates); keep solving AND verifying balanced.
 - {"action":"spawn","role":"method-keeper","reason":"..."} — distill pending inventions / maintain the theory library.
 - {"action":"interrupt","childId":"<childId>","reason":"..."} — stop a running child (direction dead, superseded...).
 - {"action":"promote","target":"<pId>","reason":"..."} — high-value unresolved proposition → judge problem.
-- {"action":"wait","target":"<id>","reason":"..."} — advisory: wait for a dependency.
+- {"action":"wait","target":"<id>","reason":"..."} — advisory only (logged; no scheduling effect): you are waiting for a dependency.
+- {"action":"continue","childId":"<childId>","reason":"..."} — advisory only (logged): continuation of an in-flight child is code-driven; this never re-dispatches anything.
+- {"action":"stop","childId":"<childId>","reason":"..."} — advisory only (logged; it does NOT stop anyone). To actually stop a child use `interrupt` with a live childId.
 
 HARD RULES: never re-schedule verified objects; problems with 依赖未就绪 (依赖就绪=false) should wait unless you explicitly accept a temporary assumption; respect capacity (brief.free_slots); PREFER problems whose dependencies are ready and whose directions have the highest survival; DO NOT forget verification — unresolved solutions/proofs/refutations (verify_candidates) will never be checked unless you schedule a verifier; DO NOT assume a direction is already being worked just because it is shown "active" in a problem — check brief.problems[].running_solver_dirs and brief.active_agents: schedule a solver for a direction ONLY if that direction is NOT in running_solver_dirs (an "active" direction absent from running_solver_dirs is WAITING to be dispatched, not being worked); schedule at most 3 actions.
 Respond with ONLY a single JSON object wrapped in a ```json code fence — no prose:
@@ -463,7 +469,7 @@ feasibility ∈ [0,1] = your estimate of the probability this direction leads to
 {"meta":{"kind":"directions","qid":"<qid>","directions":[{"id":"d1","title":"...","method":"...","core_assumption":"...","feasibility":0.5}],"methods_used":[{"id":"m-...","效果":"<为何该方向借鉴它>","建议":"..."}],"new_inventions":[{"类型":"方法|工具|...","标题":"...","内容描述":"...","是否已入库":false}]}}
 - math_computation：本机可用 （无）。需要数值/符号/统计计算时先 probe 再 run（工具路径会留下可复核回执，结论请引用回执路径）；缺包时如实说明并给替代方案或安装计划（不要假装），安装需先出计划并征得确认。
 - shell 兜底标注：工具不可用而改用宿主 shell 时，结论必须写"未经工具归档（shell 路径）"，且不得与工具回执混同（shell 无回执、无超时/输出上限保证）。
-- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以打开它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）；编辑后用 mode:'file' 指向它重跑，会写出一份**新回执/新 attempt**（含新的 scriptHash）。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
+- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以读它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）。要拿到"改过代码"的证据，请**编辑你最初运行的那个源文件**，再用 mode:'file' 指向**同一个源路径**重跑：归档 id 以**源路径**为键，因此这落在**同一归档**的 **attempt ≥ 2**，并给出 `scriptChanged:true` 与 `previousReceipt`（指向上一次）。**指向归档副本本身**（`receipt.scriptAbs` 那个路径）按设计是**另一份新归档**：新 id、attempt 1、没有 `previousReceipt`、`scriptChanged:false`；旧 attempt 绝不会被覆盖，但它**不是**"同一归档的新 attempt"——工具会用 `fileIsArchivedScript` 与 `ARCHIVED_SCRIPT_RERUN` 警告明确说明。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
 - 需要精确数值、符号化简、反例搜索、统计或线性代数时调用 math_computation：先 probe，再 run。
 - 复核他人的数值结论时用 op:'receipt'（或 op:'run', mode:'file' 指向同一脚本）重跑，并把回执路径写进报告。
 - 归档即引用：报告里带 Computation/<id>/receipt.json；这是"支撑材料"的用法。
@@ -500,14 +506,16 @@ CURRENT STATE BRIEF (JSON):
   "recent_events": "<RECENT_EVENTS>"
 }
 
-ACTION VOCABULARY (code validates every action against hard invariants; invalid actions are dropped):
+ACTION VOCABULARY — the code ACCEPTS exactly these 6 actions: spawn / interrupt / promote are HARD-VALIDATED (invalid ones are dropped), while wait / continue / stop are ADVISORY ONLY (they are logged and have NO scheduling effect):
 - {"action":"spawn","role":"explorer","target":"<qid>","reason":"..."} — problem has no directions yet or all dead (re-derive).
 - {"action":"spawn","role":"solver","target":"<qid>","direction":"<dirId>","reason":"..."} — active direction, needs a solving round.
 - {"action":"spawn","role":"verifier","target":"<rId>","reason":"..."} — verify candidate (from verify_candidates); keep solving AND verifying balanced.
 - {"action":"spawn","role":"method-keeper","reason":"..."} — distill pending inventions / maintain the theory library.
 - {"action":"interrupt","childId":"<childId>","reason":"..."} — stop a running child (direction dead, superseded...).
 - {"action":"promote","target":"<pId>","reason":"..."} — high-value unresolved proposition → judge problem.
-- {"action":"wait","target":"<id>","reason":"..."} — advisory: wait for a dependency.
+- {"action":"wait","target":"<id>","reason":"..."} — advisory only (logged; no scheduling effect): you are waiting for a dependency.
+- {"action":"continue","childId":"<childId>","reason":"..."} — advisory only (logged): continuation of an in-flight child is code-driven; this never re-dispatches anything.
+- {"action":"stop","childId":"<childId>","reason":"..."} — advisory only (logged; it does NOT stop anyone). To actually stop a child use `interrupt` with a live childId.
 
 HARD RULES: never re-schedule verified objects; problems with 依赖未就绪 (依赖就绪=false) should wait unless you explicitly accept a temporary assumption; respect capacity (brief.free_slots); PREFER problems whose dependencies are ready and whose directions have the highest survival; DO NOT forget verification — unresolved solutions/proofs/refutations (verify_candidates) will never be checked unless you schedule a verifier; DO NOT assume a direction is already being worked just because it is shown "active" in a problem — check brief.problems[].running_solver_dirs and brief.active_agents: schedule a solver for a direction ONLY if that direction is NOT in running_solver_dirs (an "active" direction absent from running_solver_dirs is WAITING to be dispatched, not being worked); schedule at most 3 actions.
 Respond with ONLY a single JSON object wrapped in a ```json code fence — no prose:
@@ -589,7 +597,7 @@ CHANNEL B (your file tools are unavailable): put the content you would have writ
 区分规则：methods_used 只能填**已存在的方法卡 ID**（m-…，来自 AVAILABLE METHODS 列表）——引用你自己刚想出的新方法/新技巧不属于 methods_used，请如实填入 new_inventions（它会由 Method Keeper 蒸馏建卡）；不要把方法名/标题当 id 填进 methods_used。
 - math_computation：本机可用 （无）。需要数值/符号/统计计算时先 probe 再 run（工具路径会留下可复核回执，结论请引用回执路径）；缺包时如实说明并给替代方案或安装计划（不要假装），安装需先出计划并征得确认。
 - shell 兜底标注：工具不可用而改用宿主 shell 时，结论必须写"未经工具归档（shell 路径）"，且不得与工具回执混同（shell 无回执、无超时/输出上限保证）。
-- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以打开它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）；编辑后用 mode:'file' 指向它重跑，会写出一份**新回执/新 attempt**（含新的 scriptHash）。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
+- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以读它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）。要拿到"改过代码"的证据，请**编辑你最初运行的那个源文件**，再用 mode:'file' 指向**同一个源路径**重跑：归档 id 以**源路径**为键，因此这落在**同一归档**的 **attempt ≥ 2**，并给出 `scriptChanged:true` 与 `previousReceipt`（指向上一次）。**指向归档副本本身**（`receipt.scriptAbs` 那个路径）按设计是**另一份新归档**：新 id、attempt 1、没有 `previousReceipt`、`scriptChanged:false`；旧 attempt 绝不会被覆盖，但它**不是**"同一归档的新 attempt"——工具会用 `fileIsArchivedScript` 与 `ARCHIVED_SCRIPT_RERUN` 警告明确说明。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
 - 需要精确数值、符号化简、反例搜索、统计或线性代数时调用 math_computation：先 probe，再 run。
 - 复核他人的数值结论时用 op:'receipt'（或 op:'run', mode:'file' 指向同一脚本）重跑，并把回执路径写进报告。
 - 归档即引用：报告里带 Computation/<id>/receipt.json；这是"支撑材料"的用法。
@@ -684,7 +692,7 @@ CHANNEL B (your file tools are unavailable): put the content you would have writ
 区分规则：methods_used 只能填**已存在的方法卡 ID**（m-…，来自 AVAILABLE METHODS 列表）——引用你自己刚想出的新方法/新技巧不属于 methods_used，请如实填入 new_inventions（它会由 Method Keeper 蒸馏建卡）；不要把方法名/标题当 id 填进 methods_used。
 - math_computation：本机可用 （无）。需要数值/符号/统计计算时先 probe 再 run（工具路径会留下可复核回执，结论请引用回执路径）；缺包时如实说明并给替代方案或安装计划（不要假装），安装需先出计划并征得确认。
 - shell 兜底标注：工具不可用而改用宿主 shell 时，结论必须写"未经工具归档（shell 路径）"，且不得与工具回执混同（shell 无回执、无超时/输出上限保证）。
-- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以打开它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）；编辑后用 mode:'file' 指向它重跑，会写出一份**新回执/新 attempt**（含新的 scriptHash）。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
+- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以读它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）。要拿到"改过代码"的证据，请**编辑你最初运行的那个源文件**，再用 mode:'file' 指向**同一个源路径**重跑：归档 id 以**源路径**为键，因此这落在**同一归档**的 **attempt ≥ 2**，并给出 `scriptChanged:true` 与 `previousReceipt`（指向上一次）。**指向归档副本本身**（`receipt.scriptAbs` 那个路径）按设计是**另一份新归档**：新 id、attempt 1、没有 `previousReceipt`、`scriptChanged:false`；旧 attempt 绝不会被覆盖，但它**不是**"同一归档的新 attempt"——工具会用 `fileIsArchivedScript` 与 `ARCHIVED_SCRIPT_RERUN` 警告明确说明。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
 - 需要精确数值、符号化简、反例搜索、统计或线性代数时调用 math_computation：先 probe，再 run。
 - 复核他人的数值结论时用 op:'receipt'（或 op:'run', mode:'file' 指向同一脚本）重跑，并把回执路径写进报告。
 - 归档即引用：报告里带 Computation/<id>/receipt.json；这是"支撑材料"的用法。
@@ -745,7 +753,7 @@ For each pending invention decide: create a NEW method card, or fold it into an
 
 - math_computation：本机可用 （无）。需要数值/符号/统计计算时先 probe 再 run（工具路径会留下可复核回执，结论请引用回执路径）；缺包时如实说明并给替代方案或安装计划（不要假装），安装需先出计划并征得确认。
 - shell 兜底标注：工具不可用而改用宿主 shell 时，结论必须写"未经工具归档（shell 路径）"，且不得与工具回执混同（shell 无回执、无超时/输出上限保证）。
-- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以打开它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）；编辑后用 mode:'file' 指向它重跑，会写出一份**新回执/新 attempt**（含新的 scriptHash）。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
+- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以读它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）。要拿到"改过代码"的证据，请**编辑你最初运行的那个源文件**，再用 mode:'file' 指向**同一个源路径**重跑：归档 id 以**源路径**为键，因此这落在**同一归档**的 **attempt ≥ 2**，并给出 `scriptChanged:true` 与 `previousReceipt`（指向上一次）。**指向归档副本本身**（`receipt.scriptAbs` 那个路径）按设计是**另一份新归档**：新 id、attempt 1、没有 `previousReceipt`、`scriptChanged:false`；旧 attempt 绝不会被覆盖，但它**不是**"同一归档的新 attempt"——工具会用 `fileIsArchivedScript` 与 `ARCHIVED_SCRIPT_RERUN` 警告明确说明。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
 - 需要精确数值、符号化简、反例搜索、统计或线性代数时调用 math_computation：先 probe，再 run。
 - 复核他人的数值结论时用 op:'receipt'（或 op:'run', mode:'file' 指向同一脚本）重跑，并把回执路径写进报告。
 - 归档即引用：报告里带 Computation/<id>/receipt.json；这是"支撑材料"的用法。
@@ -760,7 +768,7 @@ For each pending invention decide: create a NEW method card, or fold it into an
   · 编译默认走后台队列（leanAsync=true）：入队后你可以继续工作；用 vibe_math_lean_job（可 waitMs 等结果）或下一轮提示里的【形式化结果】行看结果。**在作业落地为通过之前，不得把该对象当成已通过。**
 【方法沉淀 × Lean 形式化】除了方法卡，你沉淀的每个可复用对象 / 定义 / 假设都应当归档到全局 Lean 库（vibe_math_lean_archive kind='def'），已成立的引理归档到 Proved/（kind='lemma'）；归档时**连同定义与陈述一起写清**，方便后续直接 import。
 OUTPUT CONTRACT — pick ONE channel. Write method cards into Markdown; only the created IDs, which cards were used, and improvements cross the machine reply.
-CHANNEL A (recommended, you can write files): write each method card into `Methods/<m-id>.md` (`# 方法｜标题` + `- 标题/ID/类型/状态/可信断言/适用场景` + `## 核心内容`/`## 应用记录`/`## 改进历史`), then reply ONLY this metadata:
+CHANNEL A (recommended, you can write files): write each method card into `Methods/<m-id>.md` — the `<m-id>` in the FILE NAME must be EXACTLY the id you list in `created`（调度器按 `created` 里的 id 去 `Methods/<id>.md` 找卡；不一致会被当成"已沉淀"而实际没有卡）(`# 方法｜标题` + `- 标题/ID/类型/状态/可信断言/适用场景` + `## 核心内容`/`## 应用记录`/`## 改进历史`), then reply ONLY this metadata:
 {"meta":{"kind":"methods","used":[{"id":"m-...","效果":"...","建议":"..."}],"created":["m-xxx"],"improvements":[{"id":"m-...","改进内容":"...","原因":"..."}]}}
 CHANNEL B (your file tools are unavailable): put the method-card content into __writes and carry the same meta:
 {"__writes":[{"path":"Methods/<m-id>.md","content":"<# 方法｜标题 + 锚点 + ## 核心内容... 完整卡面>"}],"meta":{"kind":"methods","used":[...],"created":["m-xxx"],"improvements":[...]}}
@@ -786,14 +794,16 @@ CURRENT STATE BRIEF (JSON):
   "recent_events": "<RECENT_EVENTS>"
 }
 
-ACTION VOCABULARY (code validates every action against hard invariants; invalid actions are dropped):
+ACTION VOCABULARY — the code ACCEPTS exactly these 6 actions: spawn / interrupt / promote are HARD-VALIDATED (invalid ones are dropped), while wait / continue / stop are ADVISORY ONLY (they are logged and have NO scheduling effect):
 - {"action":"spawn","role":"explorer","target":"<qid>","reason":"..."} — problem has no directions yet or all dead (re-derive).
 - {"action":"spawn","role":"solver","target":"<qid>","direction":"<dirId>","reason":"..."} — active direction, needs a solving round.
 - {"action":"spawn","role":"verifier","target":"<rId>","reason":"..."} — verify candidate (from verify_candidates); keep solving AND verifying balanced.
 - {"action":"spawn","role":"method-keeper","reason":"..."} — distill pending inventions / maintain the theory library.
 - {"action":"interrupt","childId":"<childId>","reason":"..."} — stop a running child (direction dead, superseded...).
 - {"action":"promote","target":"<pId>","reason":"..."} — high-value unresolved proposition → judge problem.
-- {"action":"wait","target":"<id>","reason":"..."} — advisory: wait for a dependency.
+- {"action":"wait","target":"<id>","reason":"..."} — advisory only (logged; no scheduling effect): you are waiting for a dependency.
+- {"action":"continue","childId":"<childId>","reason":"..."} — advisory only (logged): continuation of an in-flight child is code-driven; this never re-dispatches anything.
+- {"action":"stop","childId":"<childId>","reason":"..."} — advisory only (logged; it does NOT stop anyone). To actually stop a child use `interrupt` with a live childId.
 
 HARD RULES: never re-schedule verified objects; problems with 依赖未就绪 (依赖就绪=false) should wait unless you explicitly accept a temporary assumption; respect capacity (brief.free_slots); PREFER problems whose dependencies are ready and whose directions have the highest survival; DO NOT forget verification — unresolved solutions/proofs/refutations (verify_candidates) will never be checked unless you schedule a verifier; DO NOT assume a direction is already being worked just because it is shown "active" in a problem — check brief.problems[].running_solver_dirs and brief.active_agents: schedule a solver for a direction ONLY if that direction is NOT in running_solver_dirs (an "active" direction absent from running_solver_dirs is WAITING to be dispatched, not being worked); schedule at most 3 actions.
 Respond with ONLY a single JSON object wrapped in a ```json code fence — no prose:
@@ -860,7 +870,7 @@ Citations: facts may only be cited from Verified/ (or Propos/ 状态: 已验证
   · 宿主没有 Lean 工具链（LEAN_NOT_FOUND）或宿主不提供 subprocess 服务（NO_SUBPROCESS）时：把代码写下来归档，并在回执的 note 里写明"宿主无 Lean 工具链"——这算显式阻塞原因，定论门禁可以据此放行。
 - math_computation：本机可用 （无）。需要数值/符号/统计计算时先 probe 再 run（工具路径会留下可复核回执，结论请引用回执路径）；缺包时如实说明并给替代方案或安装计划（不要假装），安装需先出计划并征得确认。
 - shell 兜底标注：工具不可用而改用宿主 shell 时，结论必须写"未经工具归档（shell 路径）"，且不得与工具回执混同（shell 无回执、无超时/输出上限保证）。
-- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以打开它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）；编辑后用 mode:'file' 指向它重跑，会写出一份**新回执/新 attempt**（含新的 scriptHash）。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
+- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以读它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）。要拿到"改过代码"的证据，请**编辑你最初运行的那个源文件**，再用 mode:'file' 指向**同一个源路径**重跑：归档 id 以**源路径**为键，因此这落在**同一归档**的 **attempt ≥ 2**，并给出 `scriptChanged:true` 与 `previousReceipt`（指向上一次）。**指向归档副本本身**（`receipt.scriptAbs` 那个路径）按设计是**另一份新归档**：新 id、attempt 1、没有 `previousReceipt`、`scriptChanged:false`；旧 attempt 绝不会被覆盖，但它**不是**"同一归档的新 attempt"——工具会用 `fileIsArchivedScript` 与 `ARCHIVED_SCRIPT_RERUN` 警告明确说明。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
 - 需要精确数值、符号化简、反例搜索、统计或线性代数时调用 math_computation：先 probe，再 run。
 - 复核他人的数值结论时用 op:'receipt'（或 op:'run', mode:'file' 指向同一脚本）重跑，并把回执路径写进报告。
 - 归档即引用：报告里带 Computation/<id>/receipt.json；这是"支撑材料"的用法。
@@ -933,7 +943,7 @@ Citations: facts may only be cited from Verified/ (or Propos/ 状态: 已验证
   · 宿主没有 Lean 工具链（LEAN_NOT_FOUND）或宿主不提供 subprocess 服务（NO_SUBPROCESS）时：把代码写下来归档，并在回执的 note 里写明"宿主无 Lean 工具链"——这算显式阻塞原因，定论门禁可以据此放行。
 - math_computation：本机可用 （无）。需要数值/符号/统计计算时先 probe 再 run（工具路径会留下可复核回执，结论请引用回执路径）；缺包时如实说明并给替代方案或安装计划（不要假装），安装需先出计划并征得确认。
 - shell 兜底标注：工具不可用而改用宿主 shell 时，结论必须写"未经工具归档（shell 路径）"，且不得与工具回执混同（shell 无回执、无超时/输出上限保证）。
-- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以打开它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）；编辑后用 mode:'file' 指向它重跑，会写出一份**新回执/新 attempt**（含新的 scriptHash）。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
+- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以读它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）。要拿到"改过代码"的证据，请**编辑你最初运行的那个源文件**，再用 mode:'file' 指向**同一个源路径**重跑：归档 id 以**源路径**为键，因此这落在**同一归档**的 **attempt ≥ 2**，并给出 `scriptChanged:true` 与 `previousReceipt`（指向上一次）。**指向归档副本本身**（`receipt.scriptAbs` 那个路径）按设计是**另一份新归档**：新 id、attempt 1、没有 `previousReceipt`、`scriptChanged:false`；旧 attempt 绝不会被覆盖，但它**不是**"同一归档的新 attempt"——工具会用 `fileIsArchivedScript` 与 `ARCHIVED_SCRIPT_RERUN` 警告明确说明。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
 - 需要精确数值、符号化简、反例搜索、统计或线性代数时调用 math_computation：先 probe，再 run。
 - 复核他人的数值结论时用 op:'receipt'（或 op:'run', mode:'file' 指向同一脚本）重跑，并把回执路径写进报告。
 - 归档即引用：报告里带 Computation/<id>/receipt.json；这是"支撑材料"的用法。
@@ -1007,7 +1017,7 @@ Reason is MANDATORY and MUST be non-empty; an empty-Reason result (esp. a bare 0
   · 宿主没有 Lean 工具链（LEAN_NOT_FOUND）或宿主不提供 subprocess 服务（NO_SUBPROCESS）时：把代码写下来归档，并在回执的 note 里写明"宿主无 Lean 工具链"——这算显式阻塞原因，定论门禁可以据此放行。
 - math_computation：本机可用 （无）。需要数值/符号/统计计算时先 probe 再 run（工具路径会留下可复核回执，结论请引用回执路径）；缺包时如实说明并给替代方案或安装计划（不要假装），安装需先出计划并征得确认。
 - shell 兜底标注：工具不可用而改用宿主 shell 时，结论必须写"未经工具归档（shell 路径）"，且不得与工具回执混同（shell 无回执、无超时/输出上限保证）。
-- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以打开它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）；编辑后用 mode:'file' 指向它重跑，会写出一份**新回执/新 attempt**（含新的 scriptHash）。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
+- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以读它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）。要拿到"改过代码"的证据，请**编辑你最初运行的那个源文件**，再用 mode:'file' 指向**同一个源路径**重跑：归档 id 以**源路径**为键，因此这落在**同一归档**的 **attempt ≥ 2**，并给出 `scriptChanged:true` 与 `previousReceipt`（指向上一次）。**指向归档副本本身**（`receipt.scriptAbs` 那个路径）按设计是**另一份新归档**：新 id、attempt 1、没有 `previousReceipt`、`scriptChanged:false`；旧 attempt 绝不会被覆盖，但它**不是**"同一归档的新 attempt"——工具会用 `fileIsArchivedScript` 与 `ARCHIVED_SCRIPT_RERUN` 警告明确说明。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
 - 需要精确数值、符号化简、反例搜索、统计或线性代数时调用 math_computation：先 probe，再 run。
 - 复核他人的数值结论时用 op:'receipt'（或 op:'run', mode:'file' 指向同一脚本）重跑，并把回执路径写进报告。
 - 归档即引用：报告里带 Computation/<id>/receipt.json；这是"支撑材料"的用法。
@@ -1081,7 +1091,7 @@ Reason is MANDATORY and MUST be non-empty; an empty-Reason result (esp. a bare 0
   · 宿主没有 Lean 工具链（LEAN_NOT_FOUND）或宿主不提供 subprocess 服务（NO_SUBPROCESS）时：把代码写下来归档，并在回执的 note 里写明"宿主无 Lean 工具链"——这算显式阻塞原因，定论门禁可以据此放行。
 - math_computation：本机可用 （无）。需要数值/符号/统计计算时先 probe 再 run（工具路径会留下可复核回执，结论请引用回执路径）；缺包时如实说明并给替代方案或安装计划（不要假装），安装需先出计划并征得确认。
 - shell 兜底标注：工具不可用而改用宿主 shell 时，结论必须写"未经工具归档（shell 路径）"，且不得与工具回执混同（shell 无回执、无超时/输出上限保证）。
-- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以打开它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）；编辑后用 mode:'file' 指向它重跑，会写出一份**新回执/新 attempt**（含新的 scriptHash）。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
+- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以读它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）。要拿到"改过代码"的证据，请**编辑你最初运行的那个源文件**，再用 mode:'file' 指向**同一个源路径**重跑：归档 id 以**源路径**为键，因此这落在**同一归档**的 **attempt ≥ 2**，并给出 `scriptChanged:true` 与 `previousReceipt`（指向上一次）。**指向归档副本本身**（`receipt.scriptAbs` 那个路径）按设计是**另一份新归档**：新 id、attempt 1、没有 `previousReceipt`、`scriptChanged:false`；旧 attempt 绝不会被覆盖，但它**不是**"同一归档的新 attempt"——工具会用 `fileIsArchivedScript` 与 `ARCHIVED_SCRIPT_RERUN` 警告明确说明。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
 - 需要精确数值、符号化简、反例搜索、统计或线性代数时调用 math_computation：先 probe，再 run。
 - 复核他人的数值结论时用 op:'receipt'（或 op:'run', mode:'file' 指向同一脚本）重跑，并把回执路径写进报告。
 - 归档即引用：报告里带 Computation/<id>/receipt.json；这是"支撑材料"的用法。
@@ -1114,14 +1124,16 @@ CURRENT STATE BRIEF (JSON):
   "recent_events": "<RECENT_EVENTS>"
 }
 
-ACTION VOCABULARY (code validates every action against hard invariants; invalid actions are dropped):
+ACTION VOCABULARY — the code ACCEPTS exactly these 6 actions: spawn / interrupt / promote are HARD-VALIDATED (invalid ones are dropped), while wait / continue / stop are ADVISORY ONLY (they are logged and have NO scheduling effect):
 - {"action":"spawn","role":"explorer","target":"<qid>","reason":"..."} — problem has no directions yet or all dead (re-derive).
 - {"action":"spawn","role":"solver","target":"<qid>","direction":"<dirId>","reason":"..."} — active direction, needs a solving round.
 - {"action":"spawn","role":"verifier","target":"<rId>","reason":"..."} — verify candidate (from verify_candidates); keep solving AND verifying balanced.
 - {"action":"spawn","role":"method-keeper","reason":"..."} — distill pending inventions / maintain the theory library.
 - {"action":"interrupt","childId":"<childId>","reason":"..."} — stop a running child (direction dead, superseded...).
 - {"action":"promote","target":"<pId>","reason":"..."} — high-value unresolved proposition → judge problem.
-- {"action":"wait","target":"<id>","reason":"..."} — advisory: wait for a dependency.
+- {"action":"wait","target":"<id>","reason":"..."} — advisory only (logged; no scheduling effect): you are waiting for a dependency.
+- {"action":"continue","childId":"<childId>","reason":"..."} — advisory only (logged): continuation of an in-flight child is code-driven; this never re-dispatches anything.
+- {"action":"stop","childId":"<childId>","reason":"..."} — advisory only (logged; it does NOT stop anyone). To actually stop a child use `interrupt` with a live childId.
 
 HARD RULES: never re-schedule verified objects; problems with 依赖未就绪 (依赖就绪=false) should wait unless you explicitly accept a temporary assumption; respect capacity (brief.free_slots); PREFER problems whose dependencies are ready and whose directions have the highest survival; DO NOT forget verification — unresolved solutions/proofs/refutations (verify_candidates) will never be checked unless you schedule a verifier; DO NOT assume a direction is already being worked just because it is shown "active" in a problem — check brief.problems[].running_solver_dirs and brief.active_agents: schedule a solver for a direction ONLY if that direction is NOT in running_solver_dirs (an "active" direction absent from running_solver_dirs is WAITING to be dispatched, not being worked); schedule at most 3 actions.
 Respond with ONLY a single JSON object wrapped in a ```json code fence — no prose:
@@ -1203,14 +1215,16 @@ CURRENT STATE BRIEF (JSON):
   "recent_events": "<RECENT_EVENTS>"
 }
 
-ACTION VOCABULARY (code validates every action against hard invariants; invalid actions are dropped):
+ACTION VOCABULARY — the code ACCEPTS exactly these 6 actions: spawn / interrupt / promote are HARD-VALIDATED (invalid ones are dropped), while wait / continue / stop are ADVISORY ONLY (they are logged and have NO scheduling effect):
 - {"action":"spawn","role":"explorer","target":"<qid>","reason":"..."} — problem has no directions yet or all dead (re-derive).
 - {"action":"spawn","role":"solver","target":"<qid>","direction":"<dirId>","reason":"..."} — active direction, needs a solving round.
 - {"action":"spawn","role":"verifier","target":"<rId>","reason":"..."} — verify candidate (from verify_candidates); keep solving AND verifying balanced.
 - {"action":"spawn","role":"method-keeper","reason":"..."} — distill pending inventions / maintain the theory library.
 - {"action":"interrupt","childId":"<childId>","reason":"..."} — stop a running child (direction dead, superseded...).
 - {"action":"promote","target":"<pId>","reason":"..."} — high-value unresolved proposition → judge problem.
-- {"action":"wait","target":"<id>","reason":"..."} — advisory: wait for a dependency.
+- {"action":"wait","target":"<id>","reason":"..."} — advisory only (logged; no scheduling effect): you are waiting for a dependency.
+- {"action":"continue","childId":"<childId>","reason":"..."} — advisory only (logged): continuation of an in-flight child is code-driven; this never re-dispatches anything.
+- {"action":"stop","childId":"<childId>","reason":"..."} — advisory only (logged; it does NOT stop anyone). To actually stop a child use `interrupt` with a live childId.
 
 HARD RULES: never re-schedule verified objects; problems with 依赖未就绪 (依赖就绪=false) should wait unless you explicitly accept a temporary assumption; respect capacity (brief.free_slots); PREFER problems whose dependencies are ready and whose directions have the highest survival; DO NOT forget verification — unresolved solutions/proofs/refutations (verify_candidates) will never be checked unless you schedule a verifier; DO NOT assume a direction is already being worked just because it is shown "active" in a problem — check brief.problems[].running_solver_dirs and brief.active_agents: schedule a solver for a direction ONLY if that direction is NOT in running_solver_dirs (an "active" direction absent from running_solver_dirs is WAITING to be dispatched, not being worked); schedule at most 3 actions.
 Respond with ONLY a single JSON object wrapped in a ```json code fence — no prose:
@@ -1277,7 +1291,7 @@ Citations: facts may only be cited from Verified/ (or Propos/ 状态: 已验证
   · 宿主没有 Lean 工具链（LEAN_NOT_FOUND）或宿主不提供 subprocess 服务（NO_SUBPROCESS）时：把代码写下来归档，并在回执的 note 里写明"宿主无 Lean 工具链"——这算显式阻塞原因，定论门禁可以据此放行。
 - math_computation：本机可用 （无）。需要数值/符号/统计计算时先 probe 再 run（工具路径会留下可复核回执，结论请引用回执路径）；缺包时如实说明并给替代方案或安装计划（不要假装），安装需先出计划并征得确认。
 - shell 兜底标注：工具不可用而改用宿主 shell 时，结论必须写"未经工具归档（shell 路径）"，且不得与工具回执混同（shell 无回执、无超时/输出上限保证）。
-- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以打开它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）；编辑后用 mode:'file' 指向它重跑，会写出一份**新回执/新 attempt**（含新的 scriptHash）。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
+- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以读它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）。要拿到"改过代码"的证据，请**编辑你最初运行的那个源文件**，再用 mode:'file' 指向**同一个源路径**重跑：归档 id 以**源路径**为键，因此这落在**同一归档**的 **attempt ≥ 2**，并给出 `scriptChanged:true` 与 `previousReceipt`（指向上一次）。**指向归档副本本身**（`receipt.scriptAbs` 那个路径）按设计是**另一份新归档**：新 id、attempt 1、没有 `previousReceipt`、`scriptChanged:false`；旧 attempt 绝不会被覆盖，但它**不是**"同一归档的新 attempt"——工具会用 `fileIsArchivedScript` 与 `ARCHIVED_SCRIPT_RERUN` 警告明确说明。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
 - 需要精确数值、符号化简、反例搜索、统计或线性代数时调用 math_computation：先 probe，再 run。
 - 复核他人的数值结论时用 op:'receipt'（或 op:'run', mode:'file' 指向同一脚本）重跑，并把回执路径写进报告。
 - 归档即引用：报告里带 Computation/<id>/receipt.json；这是"支撑材料"的用法。
@@ -1350,7 +1364,7 @@ Citations: facts may only be cited from Verified/ (or Propos/ 状态: 已验证
   · 宿主没有 Lean 工具链（LEAN_NOT_FOUND）或宿主不提供 subprocess 服务（NO_SUBPROCESS）时：把代码写下来归档，并在回执的 note 里写明"宿主无 Lean 工具链"——这算显式阻塞原因，定论门禁可以据此放行。
 - math_computation：本机可用 （无）。需要数值/符号/统计计算时先 probe 再 run（工具路径会留下可复核回执，结论请引用回执路径）；缺包时如实说明并给替代方案或安装计划（不要假装），安装需先出计划并征得确认。
 - shell 兜底标注：工具不可用而改用宿主 shell 时，结论必须写"未经工具归档（shell 路径）"，且不得与工具回执混同（shell 无回执、无超时/输出上限保证）。
-- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以打开它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）；编辑后用 mode:'file' 指向它重跑，会写出一份**新回执/新 attempt**（含新的 scriptHash）。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
+- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以读它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）。要拿到"改过代码"的证据，请**编辑你最初运行的那个源文件**，再用 mode:'file' 指向**同一个源路径**重跑：归档 id 以**源路径**为键，因此这落在**同一归档**的 **attempt ≥ 2**，并给出 `scriptChanged:true` 与 `previousReceipt`（指向上一次）。**指向归档副本本身**（`receipt.scriptAbs` 那个路径）按设计是**另一份新归档**：新 id、attempt 1、没有 `previousReceipt`、`scriptChanged:false`；旧 attempt 绝不会被覆盖，但它**不是**"同一归档的新 attempt"——工具会用 `fileIsArchivedScript` 与 `ARCHIVED_SCRIPT_RERUN` 警告明确说明。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
 - 需要精确数值、符号化简、反例搜索、统计或线性代数时调用 math_computation：先 probe，再 run。
 - 复核他人的数值结论时用 op:'receipt'（或 op:'run', mode:'file' 指向同一脚本）重跑，并把回执路径写进报告。
 - 归档即引用：报告里带 Computation/<id>/receipt.json；这是"支撑材料"的用法。
@@ -1383,14 +1397,16 @@ CURRENT STATE BRIEF (JSON):
   "recent_events": "<RECENT_EVENTS>"
 }
 
-ACTION VOCABULARY (code validates every action against hard invariants; invalid actions are dropped):
+ACTION VOCABULARY — the code ACCEPTS exactly these 6 actions: spawn / interrupt / promote are HARD-VALIDATED (invalid ones are dropped), while wait / continue / stop are ADVISORY ONLY (they are logged and have NO scheduling effect):
 - {"action":"spawn","role":"explorer","target":"<qid>","reason":"..."} — problem has no directions yet or all dead (re-derive).
 - {"action":"spawn","role":"solver","target":"<qid>","direction":"<dirId>","reason":"..."} — active direction, needs a solving round.
 - {"action":"spawn","role":"verifier","target":"<rId>","reason":"..."} — verify candidate (from verify_candidates); keep solving AND verifying balanced.
 - {"action":"spawn","role":"method-keeper","reason":"..."} — distill pending inventions / maintain the theory library.
 - {"action":"interrupt","childId":"<childId>","reason":"..."} — stop a running child (direction dead, superseded...).
 - {"action":"promote","target":"<pId>","reason":"..."} — high-value unresolved proposition → judge problem.
-- {"action":"wait","target":"<id>","reason":"..."} — advisory: wait for a dependency.
+- {"action":"wait","target":"<id>","reason":"..."} — advisory only (logged; no scheduling effect): you are waiting for a dependency.
+- {"action":"continue","childId":"<childId>","reason":"..."} — advisory only (logged): continuation of an in-flight child is code-driven; this never re-dispatches anything.
+- {"action":"stop","childId":"<childId>","reason":"..."} — advisory only (logged; it does NOT stop anyone). To actually stop a child use `interrupt` with a live childId.
 
 HARD RULES: never re-schedule verified objects; problems with 依赖未就绪 (依赖就绪=false) should wait unless you explicitly accept a temporary assumption; respect capacity (brief.free_slots); PREFER problems whose dependencies are ready and whose directions have the highest survival; DO NOT forget verification — unresolved solutions/proofs/refutations (verify_candidates) will never be checked unless you schedule a verifier; DO NOT assume a direction is already being worked just because it is shown "active" in a problem — check brief.problems[].running_solver_dirs and brief.active_agents: schedule a solver for a direction ONLY if that direction is NOT in running_solver_dirs (an "active" direction absent from running_solver_dirs is WAITING to be dispatched, not being worked); schedule at most 3 actions.
 Respond with ONLY a single JSON object wrapped in a ```json code fence — no prose:
@@ -1457,7 +1473,7 @@ Citations: facts may only be cited from Verified/ (or Propos/ 状态: 已验证
   · 宿主没有 Lean 工具链（LEAN_NOT_FOUND）或宿主不提供 subprocess 服务（NO_SUBPROCESS）时：把代码写下来归档，并在回执的 note 里写明"宿主无 Lean 工具链"——这算显式阻塞原因，定论门禁可以据此放行。
 - math_computation：本机可用 （无）。需要数值/符号/统计计算时先 probe 再 run（工具路径会留下可复核回执，结论请引用回执路径）；缺包时如实说明并给替代方案或安装计划（不要假装），安装需先出计划并征得确认。
 - shell 兜底标注：工具不可用而改用宿主 shell 时，结论必须写"未经工具归档（shell 路径）"，且不得与工具回执混同（shell 无回执、无超时/输出上限保证）。
-- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以打开它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）；编辑后用 mode:'file' 指向它重跑，会写出一份**新回执/新 attempt**（含新的 scriptHash）。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
+- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以读它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）。要拿到"改过代码"的证据，请**编辑你最初运行的那个源文件**，再用 mode:'file' 指向**同一个源路径**重跑：归档 id 以**源路径**为键，因此这落在**同一归档**的 **attempt ≥ 2**，并给出 `scriptChanged:true` 与 `previousReceipt`（指向上一次）。**指向归档副本本身**（`receipt.scriptAbs` 那个路径）按设计是**另一份新归档**：新 id、attempt 1、没有 `previousReceipt`、`scriptChanged:false`；旧 attempt 绝不会被覆盖，但它**不是**"同一归档的新 attempt"——工具会用 `fileIsArchivedScript` 与 `ARCHIVED_SCRIPT_RERUN` 警告明确说明。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
 - 需要精确数值、符号化简、反例搜索、统计或线性代数时调用 math_computation：先 probe，再 run。
 - 复核他人的数值结论时用 op:'receipt'（或 op:'run', mode:'file' 指向同一脚本）重跑，并把回执路径写进报告。
 - 归档即引用：报告里带 Computation/<id>/receipt.json；这是"支撑材料"的用法。
@@ -1530,7 +1546,7 @@ Citations: facts may only be cited from Verified/ (or Propos/ 状态: 已验证
   · 宿主没有 Lean 工具链（LEAN_NOT_FOUND）或宿主不提供 subprocess 服务（NO_SUBPROCESS）时：把代码写下来归档，并在回执的 note 里写明"宿主无 Lean 工具链"——这算显式阻塞原因，定论门禁可以据此放行。
 - math_computation：本机可用 （无）。需要数值/符号/统计计算时先 probe 再 run（工具路径会留下可复核回执，结论请引用回执路径）；缺包时如实说明并给替代方案或安装计划（不要假装），安装需先出计划并征得确认。
 - shell 兜底标注：工具不可用而改用宿主 shell 时，结论必须写"未经工具归档（shell 路径）"，且不得与工具回执混同（shell 无回执、无超时/输出上限保证）。
-- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以打开它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）；编辑后用 mode:'file' 指向它重跑，会写出一份**新回执/新 attempt**（含新的 scriptHash）。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
+- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以读它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）。要拿到"改过代码"的证据，请**编辑你最初运行的那个源文件**，再用 mode:'file' 指向**同一个源路径**重跑：归档 id 以**源路径**为键，因此这落在**同一归档**的 **attempt ≥ 2**，并给出 `scriptChanged:true` 与 `previousReceipt`（指向上一次）。**指向归档副本本身**（`receipt.scriptAbs` 那个路径）按设计是**另一份新归档**：新 id、attempt 1、没有 `previousReceipt`、`scriptChanged:false`；旧 attempt 绝不会被覆盖，但它**不是**"同一归档的新 attempt"——工具会用 `fileIsArchivedScript` 与 `ARCHIVED_SCRIPT_RERUN` 警告明确说明。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
 - 需要精确数值、符号化简、反例搜索、统计或线性代数时调用 math_computation：先 probe，再 run。
 - 复核他人的数值结论时用 op:'receipt'（或 op:'run', mode:'file' 指向同一脚本）重跑，并把回执路径写进报告。
 - 归档即引用：报告里带 Computation/<id>/receipt.json；这是"支撑材料"的用法。
@@ -1563,14 +1579,16 @@ CURRENT STATE BRIEF (JSON):
   "recent_events": "<RECENT_EVENTS>"
 }
 
-ACTION VOCABULARY (code validates every action against hard invariants; invalid actions are dropped):
+ACTION VOCABULARY — the code ACCEPTS exactly these 6 actions: spawn / interrupt / promote are HARD-VALIDATED (invalid ones are dropped), while wait / continue / stop are ADVISORY ONLY (they are logged and have NO scheduling effect):
 - {"action":"spawn","role":"explorer","target":"<qid>","reason":"..."} — problem has no directions yet or all dead (re-derive).
 - {"action":"spawn","role":"solver","target":"<qid>","direction":"<dirId>","reason":"..."} — active direction, needs a solving round.
 - {"action":"spawn","role":"verifier","target":"<rId>","reason":"..."} — verify candidate (from verify_candidates); keep solving AND verifying balanced.
 - {"action":"spawn","role":"method-keeper","reason":"..."} — distill pending inventions / maintain the theory library.
 - {"action":"interrupt","childId":"<childId>","reason":"..."} — stop a running child (direction dead, superseded...).
 - {"action":"promote","target":"<pId>","reason":"..."} — high-value unresolved proposition → judge problem.
-- {"action":"wait","target":"<id>","reason":"..."} — advisory: wait for a dependency.
+- {"action":"wait","target":"<id>","reason":"..."} — advisory only (logged; no scheduling effect): you are waiting for a dependency.
+- {"action":"continue","childId":"<childId>","reason":"..."} — advisory only (logged): continuation of an in-flight child is code-driven; this never re-dispatches anything.
+- {"action":"stop","childId":"<childId>","reason":"..."} — advisory only (logged; it does NOT stop anyone). To actually stop a child use `interrupt` with a live childId.
 
 HARD RULES: never re-schedule verified objects; problems with 依赖未就绪 (依赖就绪=false) should wait unless you explicitly accept a temporary assumption; respect capacity (brief.free_slots); PREFER problems whose dependencies are ready and whose directions have the highest survival; DO NOT forget verification — unresolved solutions/proofs/refutations (verify_candidates) will never be checked unless you schedule a verifier; DO NOT assume a direction is already being worked just because it is shown "active" in a problem — check brief.problems[].running_solver_dirs and brief.active_agents: schedule a solver for a direction ONLY if that direction is NOT in running_solver_dirs (an "active" direction absent from running_solver_dirs is WAITING to be dispatched, not being worked); schedule at most 3 actions.
 Respond with ONLY a single JSON object wrapped in a ```json code fence — no prose:
@@ -1637,7 +1655,7 @@ Citations: facts may only be cited from Verified/ (or Propos/ 状态: 已验证
   · 宿主没有 Lean 工具链（LEAN_NOT_FOUND）或宿主不提供 subprocess 服务（NO_SUBPROCESS）时：把代码写下来归档，并在回执的 note 里写明"宿主无 Lean 工具链"——这算显式阻塞原因，定论门禁可以据此放行。
 - math_computation：本机可用 （无）。需要数值/符号/统计计算时先 probe 再 run（工具路径会留下可复核回执，结论请引用回执路径）；缺包时如实说明并给替代方案或安装计划（不要假装），安装需先出计划并征得确认。
 - shell 兜底标注：工具不可用而改用宿主 shell 时，结论必须写"未经工具归档（shell 路径）"，且不得与工具回执混同（shell 无回执、无超时/输出上限保证）。
-- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以打开它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）；编辑后用 mode:'file' 指向它重跑，会写出一份**新回执/新 attempt**（含新的 scriptHash）。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
+- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以读它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）。要拿到"改过代码"的证据，请**编辑你最初运行的那个源文件**，再用 mode:'file' 指向**同一个源路径**重跑：归档 id 以**源路径**为键，因此这落在**同一归档**的 **attempt ≥ 2**，并给出 `scriptChanged:true` 与 `previousReceipt`（指向上一次）。**指向归档副本本身**（`receipt.scriptAbs` 那个路径）按设计是**另一份新归档**：新 id、attempt 1、没有 `previousReceipt`、`scriptChanged:false`；旧 attempt 绝不会被覆盖，但它**不是**"同一归档的新 attempt"——工具会用 `fileIsArchivedScript` 与 `ARCHIVED_SCRIPT_RERUN` 警告明确说明。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
 - 需要精确数值、符号化简、反例搜索、统计或线性代数时调用 math_computation：先 probe，再 run。
 - 复核他人的数值结论时用 op:'receipt'（或 op:'run', mode:'file' 指向同一脚本）重跑，并把回执路径写进报告。
 - 归档即引用：报告里带 Computation/<id>/receipt.json；这是"支撑材料"的用法。
@@ -1710,7 +1728,7 @@ Citations: facts may only be cited from Verified/ (or Propos/ 状态: 已验证
   · 宿主没有 Lean 工具链（LEAN_NOT_FOUND）或宿主不提供 subprocess 服务（NO_SUBPROCESS）时：把代码写下来归档，并在回执的 note 里写明"宿主无 Lean 工具链"——这算显式阻塞原因，定论门禁可以据此放行。
 - math_computation：本机可用 （无）。需要数值/符号/统计计算时先 probe 再 run（工具路径会留下可复核回执，结论请引用回执路径）；缺包时如实说明并给替代方案或安装计划（不要假装），安装需先出计划并征得确认。
 - shell 兜底标注：工具不可用而改用宿主 shell 时，结论必须写"未经工具归档（shell 路径）"，且不得与工具回执混同（shell 无回执、无超时/输出上限保证）。
-- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以打开它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）；编辑后用 mode:'file' 指向它重跑，会写出一份**新回执/新 attempt**（含新的 scriptHash）。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
+- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以读它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）。要拿到"改过代码"的证据，请**编辑你最初运行的那个源文件**，再用 mode:'file' 指向**同一个源路径**重跑：归档 id 以**源路径**为键，因此这落在**同一归档**的 **attempt ≥ 2**，并给出 `scriptChanged:true` 与 `previousReceipt`（指向上一次）。**指向归档副本本身**（`receipt.scriptAbs` 那个路径）按设计是**另一份新归档**：新 id、attempt 1、没有 `previousReceipt`、`scriptChanged:false`；旧 attempt 绝不会被覆盖，但它**不是**"同一归档的新 attempt"——工具会用 `fileIsArchivedScript` 与 `ARCHIVED_SCRIPT_RERUN` 警告明确说明。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
 - 需要精确数值、符号化简、反例搜索、统计或线性代数时调用 math_computation：先 probe，再 run。
 - 复核他人的数值结论时用 op:'receipt'（或 op:'run', mode:'file' 指向同一脚本）重跑，并把回执路径写进报告。
 - 归档即引用：报告里带 Computation/<id>/receipt.json；这是"支撑材料"的用法。
@@ -1783,7 +1801,7 @@ Citations: facts may only be cited from Verified/ (or Propos/ 状态: 已验证
   · 宿主没有 Lean 工具链（LEAN_NOT_FOUND）或宿主不提供 subprocess 服务（NO_SUBPROCESS）时：把代码写下来归档，并在回执的 note 里写明"宿主无 Lean 工具链"——这算显式阻塞原因，定论门禁可以据此放行。
 - math_computation：本机可用 （无）。需要数值/符号/统计计算时先 probe 再 run（工具路径会留下可复核回执，结论请引用回执路径）；缺包时如实说明并给替代方案或安装计划（不要假装），安装需先出计划并征得确认。
 - shell 兜底标注：工具不可用而改用宿主 shell 时，结论必须写"未经工具归档（shell 路径）"，且不得与工具回执混同（shell 无回执、无超时/输出上限保证）。
-- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以打开它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）；编辑后用 mode:'file' 指向它重跑，会写出一份**新回执/新 attempt**（含新的 scriptHash）。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
+- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以读它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）。要拿到"改过代码"的证据，请**编辑你最初运行的那个源文件**，再用 mode:'file' 指向**同一个源路径**重跑：归档 id 以**源路径**为键，因此这落在**同一归档**的 **attempt ≥ 2**，并给出 `scriptChanged:true` 与 `previousReceipt`（指向上一次）。**指向归档副本本身**（`receipt.scriptAbs` 那个路径）按设计是**另一份新归档**：新 id、attempt 1、没有 `previousReceipt`、`scriptChanged:false`；旧 attempt 绝不会被覆盖，但它**不是**"同一归档的新 attempt"——工具会用 `fileIsArchivedScript` 与 `ARCHIVED_SCRIPT_RERUN` 警告明确说明。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
 - 需要精确数值、符号化简、反例搜索、统计或线性代数时调用 math_computation：先 probe，再 run。
 - 复核他人的数值结论时用 op:'receipt'（或 op:'run', mode:'file' 指向同一脚本）重跑，并把回执路径写进报告。
 - 归档即引用：报告里带 Computation/<id>/receipt.json；这是"支撑材料"的用法。
@@ -1856,7 +1874,7 @@ Citations: facts may only be cited from Verified/ (or Propos/ 状态: 已验证
   · 宿主没有 Lean 工具链（LEAN_NOT_FOUND）或宿主不提供 subprocess 服务（NO_SUBPROCESS）时：把代码写下来归档，并在回执的 note 里写明"宿主无 Lean 工具链"——这算显式阻塞原因，定论门禁可以据此放行。
 - math_computation：本机可用 （无）。需要数值/符号/统计计算时先 probe 再 run（工具路径会留下可复核回执，结论请引用回执路径）；缺包时如实说明并给替代方案或安装计划（不要假装），安装需先出计划并征得确认。
 - shell 兜底标注：工具不可用而改用宿主 shell 时，结论必须写"未经工具归档（shell 路径）"，且不得与工具回执混同（shell 无回执、无超时/输出上限保证）。
-- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以打开它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）；编辑后用 mode:'file' 指向它重跑，会写出一份**新回执/新 attempt**（含新的 scriptHash）。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
+- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以读它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）。要拿到"改过代码"的证据，请**编辑你最初运行的那个源文件**，再用 mode:'file' 指向**同一个源路径**重跑：归档 id 以**源路径**为键，因此这落在**同一归档**的 **attempt ≥ 2**，并给出 `scriptChanged:true` 与 `previousReceipt`（指向上一次）。**指向归档副本本身**（`receipt.scriptAbs` 那个路径）按设计是**另一份新归档**：新 id、attempt 1、没有 `previousReceipt`、`scriptChanged:false`；旧 attempt 绝不会被覆盖，但它**不是**"同一归档的新 attempt"——工具会用 `fileIsArchivedScript` 与 `ARCHIVED_SCRIPT_RERUN` 警告明确说明。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
 - 需要精确数值、符号化简、反例搜索、统计或线性代数时调用 math_computation：先 probe，再 run。
 - 复核他人的数值结论时用 op:'receipt'（或 op:'run', mode:'file' 指向同一脚本）重跑，并把回执路径写进报告。
 - 归档即引用：报告里带 Computation/<id>/receipt.json；这是"支撑材料"的用法。
@@ -1889,14 +1907,16 @@ CURRENT STATE BRIEF (JSON):
   "recent_events": "<RECENT_EVENTS>"
 }
 
-ACTION VOCABULARY (code validates every action against hard invariants; invalid actions are dropped):
+ACTION VOCABULARY — the code ACCEPTS exactly these 6 actions: spawn / interrupt / promote are HARD-VALIDATED (invalid ones are dropped), while wait / continue / stop are ADVISORY ONLY (they are logged and have NO scheduling effect):
 - {"action":"spawn","role":"explorer","target":"<qid>","reason":"..."} — problem has no directions yet or all dead (re-derive).
 - {"action":"spawn","role":"solver","target":"<qid>","direction":"<dirId>","reason":"..."} — active direction, needs a solving round.
 - {"action":"spawn","role":"verifier","target":"<rId>","reason":"..."} — verify candidate (from verify_candidates); keep solving AND verifying balanced.
 - {"action":"spawn","role":"method-keeper","reason":"..."} — distill pending inventions / maintain the theory library.
 - {"action":"interrupt","childId":"<childId>","reason":"..."} — stop a running child (direction dead, superseded...).
 - {"action":"promote","target":"<pId>","reason":"..."} — high-value unresolved proposition → judge problem.
-- {"action":"wait","target":"<id>","reason":"..."} — advisory: wait for a dependency.
+- {"action":"wait","target":"<id>","reason":"..."} — advisory only (logged; no scheduling effect): you are waiting for a dependency.
+- {"action":"continue","childId":"<childId>","reason":"..."} — advisory only (logged): continuation of an in-flight child is code-driven; this never re-dispatches anything.
+- {"action":"stop","childId":"<childId>","reason":"..."} — advisory only (logged; it does NOT stop anyone). To actually stop a child use `interrupt` with a live childId.
 
 HARD RULES: never re-schedule verified objects; problems with 依赖未就绪 (依赖就绪=false) should wait unless you explicitly accept a temporary assumption; respect capacity (brief.free_slots); PREFER problems whose dependencies are ready and whose directions have the highest survival; DO NOT forget verification — unresolved solutions/proofs/refutations (verify_candidates) will never be checked unless you schedule a verifier; DO NOT assume a direction is already being worked just because it is shown "active" in a problem — check brief.problems[].running_solver_dirs and brief.active_agents: schedule a solver for a direction ONLY if that direction is NOT in running_solver_dirs (an "active" direction absent from running_solver_dirs is WAITING to be dispatched, not being worked); schedule at most 3 actions.
 Respond with ONLY a single JSON object wrapped in a ```json code fence — no prose:
@@ -1961,7 +1981,7 @@ Citations: facts may only be cited from Verified/ (or Propos/ 状态: 已验证
   ▸ 只有当你**独立于这份 Lean 代码**也能确定命题为假时，才投 0，并在 Reason 里写清独立理由。
 - math_computation：本机可用 （无）。需要数值/符号/统计计算时先 probe 再 run（工具路径会留下可复核回执，结论请引用回执路径）；缺包时如实说明并给替代方案或安装计划（不要假装），安装需先出计划并征得确认。
 - shell 兜底标注：工具不可用而改用宿主 shell 时，结论必须写"未经工具归档（shell 路径）"，且不得与工具回执混同（shell 无回执、无超时/输出上限保证）。
-- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以打开它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）；编辑后用 mode:'file' 指向它重跑，会写出一份**新回执/新 attempt**（含新的 scriptHash）。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
+- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以读它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）。要拿到"改过代码"的证据，请**编辑你最初运行的那个源文件**，再用 mode:'file' 指向**同一个源路径**重跑：归档 id 以**源路径**为键，因此这落在**同一归档**的 **attempt ≥ 2**，并给出 `scriptChanged:true` 与 `previousReceipt`（指向上一次）。**指向归档副本本身**（`receipt.scriptAbs` 那个路径）按设计是**另一份新归档**：新 id、attempt 1、没有 `previousReceipt`、`scriptChanged:false`；旧 attempt 绝不会被覆盖，但它**不是**"同一归档的新 attempt"——工具会用 `fileIsArchivedScript` 与 `ARCHIVED_SCRIPT_RERUN` 警告明确说明。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
 - 需要精确数值、符号化简、反例搜索、统计或线性代数时调用 math_computation：先 probe，再 run。
 - 复核他人的数值结论时用 op:'receipt'（或 op:'run', mode:'file' 指向同一脚本）重跑，并把回执路径写进报告。
 - 归档即引用：报告里带 Computation/<id>/receipt.json；这是"支撑材料"的用法。
@@ -2032,7 +2052,7 @@ Citations: facts may only be cited from Verified/ (or Propos/ 状态: 已验证
   ▸ 只有当你**独立于这份 Lean 代码**也能确定命题为假时，才投 0，并在 Reason 里写清独立理由。
 - math_computation：本机可用 （无）。需要数值/符号/统计计算时先 probe 再 run（工具路径会留下可复核回执，结论请引用回执路径）；缺包时如实说明并给替代方案或安装计划（不要假装），安装需先出计划并征得确认。
 - shell 兜底标注：工具不可用而改用宿主 shell 时，结论必须写"未经工具归档（shell 路径）"，且不得与工具回执混同（shell 无回执、无超时/输出上限保证）。
-- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以打开它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）；编辑后用 mode:'file' 指向它重跑，会写出一份**新回执/新 attempt**（含新的 scriptHash）。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
+- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以读它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）。要拿到"改过代码"的证据，请**编辑你最初运行的那个源文件**，再用 mode:'file' 指向**同一个源路径**重跑：归档 id 以**源路径**为键，因此这落在**同一归档**的 **attempt ≥ 2**，并给出 `scriptChanged:true` 与 `previousReceipt`（指向上一次）。**指向归档副本本身**（`receipt.scriptAbs` 那个路径）按设计是**另一份新归档**：新 id、attempt 1、没有 `previousReceipt`、`scriptChanged:false`；旧 attempt 绝不会被覆盖，但它**不是**"同一归档的新 attempt"——工具会用 `fileIsArchivedScript` 与 `ARCHIVED_SCRIPT_RERUN` 警告明确说明。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
 - 需要精确数值、符号化简、反例搜索、统计或线性代数时调用 math_computation：先 probe，再 run。
 - 复核他人的数值结论时用 op:'receipt'（或 op:'run', mode:'file' 指向同一脚本）重跑，并把回执路径写进报告。
 - 归档即引用：报告里带 Computation/<id>/receipt.json；这是"支撑材料"的用法。
@@ -2105,7 +2125,7 @@ Citations: facts may only be cited from Verified/ (or Propos/ 状态: 已验证
   · 宿主没有 Lean 工具链（LEAN_NOT_FOUND）或宿主不提供 subprocess 服务（NO_SUBPROCESS）时：把代码写下来归档，并在回执的 note 里写明"宿主无 Lean 工具链"——这算显式阻塞原因，定论门禁可以据此放行。
 - math_computation：本机可用 （无）。需要数值/符号/统计计算时先 probe 再 run（工具路径会留下可复核回执，结论请引用回执路径）；缺包时如实说明并给替代方案或安装计划（不要假装），安装需先出计划并征得确认。
 - shell 兜底标注：工具不可用而改用宿主 shell 时，结论必须写"未经工具归档（shell 路径）"，且不得与工具回执混同（shell 无回执、无超时/输出上限保证）。
-- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以打开它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）；编辑后用 mode:'file' 指向它重跑，会写出一份**新回执/新 attempt**（含新的 scriptHash）。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
+- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以读它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）。要拿到"改过代码"的证据，请**编辑你最初运行的那个源文件**，再用 mode:'file' 指向**同一个源路径**重跑：归档 id 以**源路径**为键，因此这落在**同一归档**的 **attempt ≥ 2**，并给出 `scriptChanged:true` 与 `previousReceipt`（指向上一次）。**指向归档副本本身**（`receipt.scriptAbs` 那个路径）按设计是**另一份新归档**：新 id、attempt 1、没有 `previousReceipt`、`scriptChanged:false`；旧 attempt 绝不会被覆盖，但它**不是**"同一归档的新 attempt"——工具会用 `fileIsArchivedScript` 与 `ARCHIVED_SCRIPT_RERUN` 警告明确说明。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
 - 需要精确数值、符号化简、反例搜索、统计或线性代数时调用 math_computation：先 probe，再 run。
 - 复核他人的数值结论时用 op:'receipt'（或 op:'run', mode:'file' 指向同一脚本）重跑，并把回执路径写进报告。
 - 归档即引用：报告里带 Computation/<id>/receipt.json；这是"支撑材料"的用法。
@@ -2178,7 +2198,7 @@ Citations: facts may only be cited from Verified/ (or Propos/ 状态: 已验证
   · 宿主没有 Lean 工具链（LEAN_NOT_FOUND）或宿主不提供 subprocess 服务（NO_SUBPROCESS）时：把代码写下来归档，并在回执的 note 里写明"宿主无 Lean 工具链"——这算显式阻塞原因，定论门禁可以据此放行。
 - math_computation：本机可用 （无）。需要数值/符号/统计计算时先 probe 再 run（工具路径会留下可复核回执，结论请引用回执路径）；缺包时如实说明并给替代方案或安装计划（不要假装），安装需先出计划并征得确认。
 - shell 兜底标注：工具不可用而改用宿主 shell 时，结论必须写"未经工具归档（shell 路径）"，且不得与工具回执混同（shell 无回执、无超时/输出上限保证）。
-- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以打开它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）；编辑后用 mode:'file' 指向它重跑，会写出一份**新回执/新 attempt**（含新的 scriptHash）。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
+- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以读它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）。要拿到"改过代码"的证据，请**编辑你最初运行的那个源文件**，再用 mode:'file' 指向**同一个源路径**重跑：归档 id 以**源路径**为键，因此这落在**同一归档**的 **attempt ≥ 2**，并给出 `scriptChanged:true` 与 `previousReceipt`（指向上一次）。**指向归档副本本身**（`receipt.scriptAbs` 那个路径）按设计是**另一份新归档**：新 id、attempt 1、没有 `previousReceipt`、`scriptChanged:false`；旧 attempt 绝不会被覆盖，但它**不是**"同一归档的新 attempt"——工具会用 `fileIsArchivedScript` 与 `ARCHIVED_SCRIPT_RERUN` 警告明确说明。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
 - 需要精确数值、符号化简、反例搜索、统计或线性代数时调用 math_computation：先 probe，再 run。
 - 复核他人的数值结论时用 op:'receipt'（或 op:'run', mode:'file' 指向同一脚本）重跑，并把回执路径写进报告。
 - 归档即引用：报告里带 Computation/<id>/receipt.json；这是"支撑材料"的用法。
@@ -2211,14 +2231,16 @@ CURRENT STATE BRIEF (JSON):
   "recent_events": "<RECENT_EVENTS>"
 }
 
-ACTION VOCABULARY (code validates every action against hard invariants; invalid actions are dropped):
+ACTION VOCABULARY — the code ACCEPTS exactly these 6 actions: spawn / interrupt / promote are HARD-VALIDATED (invalid ones are dropped), while wait / continue / stop are ADVISORY ONLY (they are logged and have NO scheduling effect):
 - {"action":"spawn","role":"explorer","target":"<qid>","reason":"..."} — problem has no directions yet or all dead (re-derive).
 - {"action":"spawn","role":"solver","target":"<qid>","direction":"<dirId>","reason":"..."} — active direction, needs a solving round.
 - {"action":"spawn","role":"verifier","target":"<rId>","reason":"..."} — verify candidate (from verify_candidates); keep solving AND verifying balanced.
 - {"action":"spawn","role":"method-keeper","reason":"..."} — distill pending inventions / maintain the theory library.
 - {"action":"interrupt","childId":"<childId>","reason":"..."} — stop a running child (direction dead, superseded...).
 - {"action":"promote","target":"<pId>","reason":"..."} — high-value unresolved proposition → judge problem.
-- {"action":"wait","target":"<id>","reason":"..."} — advisory: wait for a dependency.
+- {"action":"wait","target":"<id>","reason":"..."} — advisory only (logged; no scheduling effect): you are waiting for a dependency.
+- {"action":"continue","childId":"<childId>","reason":"..."} — advisory only (logged): continuation of an in-flight child is code-driven; this never re-dispatches anything.
+- {"action":"stop","childId":"<childId>","reason":"..."} — advisory only (logged; it does NOT stop anyone). To actually stop a child use `interrupt` with a live childId.
 
 HARD RULES: never re-schedule verified objects; problems with 依赖未就绪 (依赖就绪=false) should wait unless you explicitly accept a temporary assumption; respect capacity (brief.free_slots); PREFER problems whose dependencies are ready and whose directions have the highest survival; DO NOT forget verification — unresolved solutions/proofs/refutations (verify_candidates) will never be checked unless you schedule a verifier; DO NOT assume a direction is already being worked just because it is shown "active" in a problem — check brief.problems[].running_solver_dirs and brief.active_agents: schedule a solver for a direction ONLY if that direction is NOT in running_solver_dirs (an "active" direction absent from running_solver_dirs is WAITING to be dispatched, not being worked); schedule at most 3 actions.
 Respond with ONLY a single JSON object wrapped in a ```json code fence — no prose:
@@ -2275,7 +2297,7 @@ Citations: facts may only be cited from Verified/ (or Propos/ 状态: 已验证
     请复核这个判断是否成立；若你认为其实可以形式化，请指出来并动手做。
 - math_computation：本机可用 （无）。需要数值/符号/统计计算时先 probe 再 run（工具路径会留下可复核回执，结论请引用回执路径）；缺包时如实说明并给替代方案或安装计划（不要假装），安装需先出计划并征得确认。
 - shell 兜底标注：工具不可用而改用宿主 shell 时，结论必须写"未经工具归档（shell 路径）"，且不得与工具回执混同（shell 无回执、无超时/输出上限保证）。
-- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以打开它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）；编辑后用 mode:'file' 指向它重跑，会写出一份**新回执/新 attempt**（含新的 scriptHash）。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
+- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以读它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）。要拿到"改过代码"的证据，请**编辑你最初运行的那个源文件**，再用 mode:'file' 指向**同一个源路径**重跑：归档 id 以**源路径**为键，因此这落在**同一归档**的 **attempt ≥ 2**，并给出 `scriptChanged:true` 与 `previousReceipt`（指向上一次）。**指向归档副本本身**（`receipt.scriptAbs` 那个路径）按设计是**另一份新归档**：新 id、attempt 1、没有 `previousReceipt`、`scriptChanged:false`；旧 attempt 绝不会被覆盖，但它**不是**"同一归档的新 attempt"——工具会用 `fileIsArchivedScript` 与 `ARCHIVED_SCRIPT_RERUN` 警告明确说明。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
 - 需要精确数值、符号化简、反例搜索、统计或线性代数时调用 math_computation：先 probe，再 run。
 - 复核他人的数值结论时用 op:'receipt'（或 op:'run', mode:'file' 指向同一脚本）重跑，并把回执路径写进报告。
 - 归档即引用：报告里带 Computation/<id>/receipt.json；这是"支撑材料"的用法。
@@ -2338,7 +2360,7 @@ Citations: facts may only be cited from Verified/ (or Propos/ 状态: 已验证
     请复核这个判断是否成立；若你认为其实可以形式化，请指出来并动手做。
 - math_computation：本机可用 （无）。需要数值/符号/统计计算时先 probe 再 run（工具路径会留下可复核回执，结论请引用回执路径）；缺包时如实说明并给替代方案或安装计划（不要假装），安装需先出计划并征得确认。
 - shell 兜底标注：工具不可用而改用宿主 shell 时，结论必须写"未经工具归档（shell 路径）"，且不得与工具回执混同（shell 无回执、无超时/输出上限保证）。
-- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以打开它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）；编辑后用 mode:'file' 指向它重跑，会写出一份**新回执/新 attempt**（含新的 scriptHash）。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
+- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以读它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）。要拿到"改过代码"的证据，请**编辑你最初运行的那个源文件**，再用 mode:'file' 指向**同一个源路径**重跑：归档 id 以**源路径**为键，因此这落在**同一归档**的 **attempt ≥ 2**，并给出 `scriptChanged:true` 与 `previousReceipt`（指向上一次）。**指向归档副本本身**（`receipt.scriptAbs` 那个路径）按设计是**另一份新归档**：新 id、attempt 1、没有 `previousReceipt`、`scriptChanged:false`；旧 attempt 绝不会被覆盖，但它**不是**"同一归档的新 attempt"——工具会用 `fileIsArchivedScript` 与 `ARCHIVED_SCRIPT_RERUN` 警告明确说明。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
 - 需要精确数值、符号化简、反例搜索、统计或线性代数时调用 math_computation：先 probe，再 run。
 - 复核他人的数值结论时用 op:'receipt'（或 op:'run', mode:'file' 指向同一脚本）重跑，并把回执路径写进报告。
 - 归档即引用：报告里带 Computation/<id>/receipt.json；这是"支撑材料"的用法。
@@ -2411,7 +2433,7 @@ Citations: facts may only be cited from Verified/ (or Propos/ 状态: 已验证
   · 宿主没有 Lean 工具链（LEAN_NOT_FOUND）或宿主不提供 subprocess 服务（NO_SUBPROCESS）时：把代码写下来归档，并在回执的 note 里写明"宿主无 Lean 工具链"——这算显式阻塞原因，定论门禁可以据此放行。
 - math_computation：本机可用 （无）。需要数值/符号/统计计算时先 probe 再 run（工具路径会留下可复核回执，结论请引用回执路径）；缺包时如实说明并给替代方案或安装计划（不要假装），安装需先出计划并征得确认。
 - shell 兜底标注：工具不可用而改用宿主 shell 时，结论必须写"未经工具归档（shell 路径）"，且不得与工具回执混同（shell 无回执、无超时/输出上限保证）。
-- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以打开它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）；编辑后用 mode:'file' 指向它重跑，会写出一份**新回执/新 attempt**（含新的 scriptHash）。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
+- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以读它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）。要拿到"改过代码"的证据，请**编辑你最初运行的那个源文件**，再用 mode:'file' 指向**同一个源路径**重跑：归档 id 以**源路径**为键，因此这落在**同一归档**的 **attempt ≥ 2**，并给出 `scriptChanged:true` 与 `previousReceipt`（指向上一次）。**指向归档副本本身**（`receipt.scriptAbs` 那个路径）按设计是**另一份新归档**：新 id、attempt 1、没有 `previousReceipt`、`scriptChanged:false`；旧 attempt 绝不会被覆盖，但它**不是**"同一归档的新 attempt"——工具会用 `fileIsArchivedScript` 与 `ARCHIVED_SCRIPT_RERUN` 警告明确说明。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
 - 需要精确数值、符号化简、反例搜索、统计或线性代数时调用 math_computation：先 probe，再 run。
 - 复核他人的数值结论时用 op:'receipt'（或 op:'run', mode:'file' 指向同一脚本）重跑，并把回执路径写进报告。
 - 归档即引用：报告里带 Computation/<id>/receipt.json；这是"支撑材料"的用法。
@@ -2484,7 +2506,7 @@ Citations: facts may only be cited from Verified/ (or Propos/ 状态: 已验证
   · 宿主没有 Lean 工具链（LEAN_NOT_FOUND）或宿主不提供 subprocess 服务（NO_SUBPROCESS）时：把代码写下来归档，并在回执的 note 里写明"宿主无 Lean 工具链"——这算显式阻塞原因，定论门禁可以据此放行。
 - math_computation：本机可用 （无）。需要数值/符号/统计计算时先 probe 再 run（工具路径会留下可复核回执，结论请引用回执路径）；缺包时如实说明并给替代方案或安装计划（不要假装），安装需先出计划并征得确认。
 - shell 兜底标注：工具不可用而改用宿主 shell 时，结论必须写"未经工具归档（shell 路径）"，且不得与工具回执混同（shell 无回执、无超时/输出上限保证）。
-- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以打开它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）；编辑后用 mode:'file' 指向它重跑，会写出一份**新回执/新 attempt**（含新的 scriptHash）。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
+- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以读它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）。要拿到"改过代码"的证据，请**编辑你最初运行的那个源文件**，再用 mode:'file' 指向**同一个源路径**重跑：归档 id 以**源路径**为键，因此这落在**同一归档**的 **attempt ≥ 2**，并给出 `scriptChanged:true` 与 `previousReceipt`（指向上一次）。**指向归档副本本身**（`receipt.scriptAbs` 那个路径）按设计是**另一份新归档**：新 id、attempt 1、没有 `previousReceipt`、`scriptChanged:false`；旧 attempt 绝不会被覆盖，但它**不是**"同一归档的新 attempt"——工具会用 `fileIsArchivedScript` 与 `ARCHIVED_SCRIPT_RERUN` 警告明确说明。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
 - 需要精确数值、符号化简、反例搜索、统计或线性代数时调用 math_computation：先 probe，再 run。
 - 复核他人的数值结论时用 op:'receipt'（或 op:'run', mode:'file' 指向同一脚本）重跑，并把回执路径写进报告。
 - 归档即引用：报告里带 Computation/<id>/receipt.json；这是"支撑材料"的用法。
@@ -2517,14 +2539,16 @@ CURRENT STATE BRIEF (JSON):
   "recent_events": "<RECENT_EVENTS>"
 }
 
-ACTION VOCABULARY (code validates every action against hard invariants; invalid actions are dropped):
+ACTION VOCABULARY — the code ACCEPTS exactly these 6 actions: spawn / interrupt / promote are HARD-VALIDATED (invalid ones are dropped), while wait / continue / stop are ADVISORY ONLY (they are logged and have NO scheduling effect):
 - {"action":"spawn","role":"explorer","target":"<qid>","reason":"..."} — problem has no directions yet or all dead (re-derive).
 - {"action":"spawn","role":"solver","target":"<qid>","direction":"<dirId>","reason":"..."} — active direction, needs a solving round.
 - {"action":"spawn","role":"verifier","target":"<rId>","reason":"..."} — verify candidate (from verify_candidates); keep solving AND verifying balanced.
 - {"action":"spawn","role":"method-keeper","reason":"..."} — distill pending inventions / maintain the theory library.
 - {"action":"interrupt","childId":"<childId>","reason":"..."} — stop a running child (direction dead, superseded...).
 - {"action":"promote","target":"<pId>","reason":"..."} — high-value unresolved proposition → judge problem.
-- {"action":"wait","target":"<id>","reason":"..."} — advisory: wait for a dependency.
+- {"action":"wait","target":"<id>","reason":"..."} — advisory only (logged; no scheduling effect): you are waiting for a dependency.
+- {"action":"continue","childId":"<childId>","reason":"..."} — advisory only (logged): continuation of an in-flight child is code-driven; this never re-dispatches anything.
+- {"action":"stop","childId":"<childId>","reason":"..."} — advisory only (logged; it does NOT stop anyone). To actually stop a child use `interrupt` with a live childId.
 
 HARD RULES: never re-schedule verified objects; problems with 依赖未就绪 (依赖就绪=false) should wait unless you explicitly accept a temporary assumption; respect capacity (brief.free_slots); PREFER problems whose dependencies are ready and whose directions have the highest survival; DO NOT forget verification — unresolved solutions/proofs/refutations (verify_candidates) will never be checked unless you schedule a verifier; DO NOT assume a direction is already being worked just because it is shown "active" in a problem — check brief.problems[].running_solver_dirs and brief.active_agents: schedule a solver for a direction ONLY if that direction is NOT in running_solver_dirs (an "active" direction absent from running_solver_dirs is WAITING to be dispatched, not being worked); schedule at most 3 actions.
 Respond with ONLY a single JSON object wrapped in a ```json code fence — no prose:
@@ -2591,7 +2615,7 @@ Citations: facts may only be cited from Verified/ (or Propos/ 状态: 已验证
   · 宿主没有 Lean 工具链（LEAN_NOT_FOUND）或宿主不提供 subprocess 服务（NO_SUBPROCESS）时：把代码写下来归档，并在回执的 note 里写明"宿主无 Lean 工具链"——这算显式阻塞原因，定论门禁可以据此放行。
 - math_computation：本机可用 （无）。需要数值/符号/统计计算时先 probe 再 run（工具路径会留下可复核回执，结论请引用回执路径）；缺包时如实说明并给替代方案或安装计划（不要假装），安装需先出计划并征得确认。
 - shell 兜底标注：工具不可用而改用宿主 shell 时，结论必须写"未经工具归档（shell 路径）"，且不得与工具回执混同（shell 无回执、无超时/输出上限保证）。
-- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以打开它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）；编辑后用 mode:'file' 指向它重跑，会写出一份**新回执/新 attempt**（含新的 scriptHash）。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
+- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以读它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）。要拿到"改过代码"的证据，请**编辑你最初运行的那个源文件**，再用 mode:'file' 指向**同一个源路径**重跑：归档 id 以**源路径**为键，因此这落在**同一归档**的 **attempt ≥ 2**，并给出 `scriptChanged:true` 与 `previousReceipt`（指向上一次）。**指向归档副本本身**（`receipt.scriptAbs` 那个路径）按设计是**另一份新归档**：新 id、attempt 1、没有 `previousReceipt`、`scriptChanged:false`；旧 attempt 绝不会被覆盖，但它**不是**"同一归档的新 attempt"——工具会用 `fileIsArchivedScript` 与 `ARCHIVED_SCRIPT_RERUN` 警告明确说明。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
 - 需要精确数值、符号化简、反例搜索、统计或线性代数时调用 math_computation：先 probe，再 run。
 - 复核他人的数值结论时用 op:'receipt'（或 op:'run', mode:'file' 指向同一脚本）重跑，并把回执路径写进报告。
 - 归档即引用：报告里带 Computation/<id>/receipt.json；这是"支撑材料"的用法。
@@ -2664,7 +2688,7 @@ Citations: facts may only be cited from Verified/ (or Propos/ 状态: 已验证
   · 宿主没有 Lean 工具链（LEAN_NOT_FOUND）或宿主不提供 subprocess 服务（NO_SUBPROCESS）时：把代码写下来归档，并在回执的 note 里写明"宿主无 Lean 工具链"——这算显式阻塞原因，定论门禁可以据此放行。
 - math_computation：本机可用 （无）。需要数值/符号/统计计算时先 probe 再 run（工具路径会留下可复核回执，结论请引用回执路径）；缺包时如实说明并给替代方案或安装计划（不要假装），安装需先出计划并征得确认。
 - shell 兜底标注：工具不可用而改用宿主 shell 时，结论必须写"未经工具归档（shell 路径）"，且不得与工具回执混同（shell 无回执、无超时/输出上限保证）。
-- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以打开它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）；编辑后用 mode:'file' 指向它重跑，会写出一份**新回执/新 attempt**（含新的 scriptHash）。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
+- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以读它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）。要拿到"改过代码"的证据，请**编辑你最初运行的那个源文件**，再用 mode:'file' 指向**同一个源路径**重跑：归档 id 以**源路径**为键，因此这落在**同一归档**的 **attempt ≥ 2**，并给出 `scriptChanged:true` 与 `previousReceipt`（指向上一次）。**指向归档副本本身**（`receipt.scriptAbs` 那个路径）按设计是**另一份新归档**：新 id、attempt 1、没有 `previousReceipt`、`scriptChanged:false`；旧 attempt 绝不会被覆盖，但它**不是**"同一归档的新 attempt"——工具会用 `fileIsArchivedScript` 与 `ARCHIVED_SCRIPT_RERUN` 警告明确说明。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
 - 需要精确数值、符号化简、反例搜索、统计或线性代数时调用 math_computation：先 probe，再 run。
 - 复核他人的数值结论时用 op:'receipt'（或 op:'run', mode:'file' 指向同一脚本）重跑，并把回执路径写进报告。
 - 归档即引用：报告里带 Computation/<id>/receipt.json；这是"支撑材料"的用法。
@@ -2752,14 +2776,16 @@ CURRENT STATE BRIEF (JSON):
   "recent_events": "<RECENT_EVENTS>"
 }
 
-ACTION VOCABULARY (code validates every action against hard invariants; invalid actions are dropped):
+ACTION VOCABULARY — the code ACCEPTS exactly these 6 actions: spawn / interrupt / promote are HARD-VALIDATED (invalid ones are dropped), while wait / continue / stop are ADVISORY ONLY (they are logged and have NO scheduling effect):
 - {"action":"spawn","role":"explorer","target":"<qid>","reason":"..."} — problem has no directions yet or all dead (re-derive).
 - {"action":"spawn","role":"solver","target":"<qid>","direction":"<dirId>","reason":"..."} — active direction, needs a solving round.
 - {"action":"spawn","role":"verifier","target":"<rId>","reason":"..."} — verify candidate (from verify_candidates); keep solving AND verifying balanced.
 - {"action":"spawn","role":"method-keeper","reason":"..."} — distill pending inventions / maintain the theory library.
 - {"action":"interrupt","childId":"<childId>","reason":"..."} — stop a running child (direction dead, superseded...).
 - {"action":"promote","target":"<pId>","reason":"..."} — high-value unresolved proposition → judge problem.
-- {"action":"wait","target":"<id>","reason":"..."} — advisory: wait for a dependency.
+- {"action":"wait","target":"<id>","reason":"..."} — advisory only (logged; no scheduling effect): you are waiting for a dependency.
+- {"action":"continue","childId":"<childId>","reason":"..."} — advisory only (logged): continuation of an in-flight child is code-driven; this never re-dispatches anything.
+- {"action":"stop","childId":"<childId>","reason":"..."} — advisory only (logged; it does NOT stop anyone). To actually stop a child use `interrupt` with a live childId.
 
 HARD RULES: never re-schedule verified objects; problems with 依赖未就绪 (依赖就绪=false) should wait unless you explicitly accept a temporary assumption; respect capacity (brief.free_slots); PREFER problems whose dependencies are ready and whose directions have the highest survival; DO NOT forget verification — unresolved solutions/proofs/refutations (verify_candidates) will never be checked unless you schedule a verifier; DO NOT assume a direction is already being worked just because it is shown "active" in a problem — check brief.problems[].running_solver_dirs and brief.active_agents: schedule a solver for a direction ONLY if that direction is NOT in running_solver_dirs (an "active" direction absent from running_solver_dirs is WAITING to be dispatched, not being worked); schedule at most 3 actions.
 Respond with ONLY a single JSON object wrapped in a ```json code fence — no prose:
@@ -2826,7 +2852,7 @@ Citations: facts may only be cited from Verified/ (or Propos/ 状态: 已验证
   · 宿主没有 Lean 工具链（LEAN_NOT_FOUND）或宿主不提供 subprocess 服务（NO_SUBPROCESS）时：把代码写下来归档，并在回执的 note 里写明"宿主无 Lean 工具链"——这算显式阻塞原因，定论门禁可以据此放行。
 - math_computation：本机可用 （无）。需要数值/符号/统计计算时先 probe 再 run（工具路径会留下可复核回执，结论请引用回执路径）；缺包时如实说明并给替代方案或安装计划（不要假装），安装需先出计划并征得确认。
 - shell 兜底标注：工具不可用而改用宿主 shell 时，结论必须写"未经工具归档（shell 路径）"，且不得与工具回执混同（shell 无回执、无超时/输出上限保证）。
-- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以打开它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）；编辑后用 mode:'file' 指向它重跑，会写出一份**新回执/新 attempt**（含新的 scriptHash）。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
+- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以读它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）。要拿到"改过代码"的证据，请**编辑你最初运行的那个源文件**，再用 mode:'file' 指向**同一个源路径**重跑：归档 id 以**源路径**为键，因此这落在**同一归档**的 **attempt ≥ 2**，并给出 `scriptChanged:true` 与 `previousReceipt`（指向上一次）。**指向归档副本本身**（`receipt.scriptAbs` 那个路径）按设计是**另一份新归档**：新 id、attempt 1、没有 `previousReceipt`、`scriptChanged:false`；旧 attempt 绝不会被覆盖，但它**不是**"同一归档的新 attempt"——工具会用 `fileIsArchivedScript` 与 `ARCHIVED_SCRIPT_RERUN` 警告明确说明。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
 - 需要精确数值、符号化简、反例搜索、统计或线性代数时调用 math_computation：先 probe，再 run。
 - 复核他人的数值结论时用 op:'receipt'（或 op:'run', mode:'file' 指向同一脚本）重跑，并把回执路径写进报告。
 - 归档即引用：报告里带 Computation/<id>/receipt.json；这是"支撑材料"的用法。
@@ -2899,7 +2925,7 @@ Citations: facts may only be cited from Verified/ (or Propos/ 状态: 已验证
   · 宿主没有 Lean 工具链（LEAN_NOT_FOUND）或宿主不提供 subprocess 服务（NO_SUBPROCESS）时：把代码写下来归档，并在回执的 note 里写明"宿主无 Lean 工具链"——这算显式阻塞原因，定论门禁可以据此放行。
 - math_computation：本机可用 （无）。需要数值/符号/统计计算时先 probe 再 run（工具路径会留下可复核回执，结论请引用回执路径）；缺包时如实说明并给替代方案或安装计划（不要假装），安装需先出计划并征得确认。
 - shell 兜底标注：工具不可用而改用宿主 shell 时，结论必须写"未经工具归档（shell 路径）"，且不得与工具回执混同（shell 无回执、无超时/输出上限保证）。
-- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以打开它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）；编辑后用 mode:'file' 指向它重跑，会写出一份**新回执/新 attempt**（含新的 scriptHash）。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
+- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以读它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）。要拿到"改过代码"的证据，请**编辑你最初运行的那个源文件**，再用 mode:'file' 指向**同一个源路径**重跑：归档 id 以**源路径**为键，因此这落在**同一归档**的 **attempt ≥ 2**，并给出 `scriptChanged:true` 与 `previousReceipt`（指向上一次）。**指向归档副本本身**（`receipt.scriptAbs` 那个路径）按设计是**另一份新归档**：新 id、attempt 1、没有 `previousReceipt`、`scriptChanged:false`；旧 attempt 绝不会被覆盖，但它**不是**"同一归档的新 attempt"——工具会用 `fileIsArchivedScript` 与 `ARCHIVED_SCRIPT_RERUN` 警告明确说明。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
 - 需要精确数值、符号化简、反例搜索、统计或线性代数时调用 math_computation：先 probe，再 run。
 - 复核他人的数值结论时用 op:'receipt'（或 op:'run', mode:'file' 指向同一脚本）重跑，并把回执路径写进报告。
 - 归档即引用：报告里带 Computation/<id>/receipt.json；这是"支撑材料"的用法。
@@ -2932,14 +2958,16 @@ CURRENT STATE BRIEF (JSON):
   "recent_events": "<RECENT_EVENTS>"
 }
 
-ACTION VOCABULARY (code validates every action against hard invariants; invalid actions are dropped):
+ACTION VOCABULARY — the code ACCEPTS exactly these 6 actions: spawn / interrupt / promote are HARD-VALIDATED (invalid ones are dropped), while wait / continue / stop are ADVISORY ONLY (they are logged and have NO scheduling effect):
 - {"action":"spawn","role":"explorer","target":"<qid>","reason":"..."} — problem has no directions yet or all dead (re-derive).
 - {"action":"spawn","role":"solver","target":"<qid>","direction":"<dirId>","reason":"..."} — active direction, needs a solving round.
 - {"action":"spawn","role":"verifier","target":"<rId>","reason":"..."} — verify candidate (from verify_candidates); keep solving AND verifying balanced.
 - {"action":"spawn","role":"method-keeper","reason":"..."} — distill pending inventions / maintain the theory library.
 - {"action":"interrupt","childId":"<childId>","reason":"..."} — stop a running child (direction dead, superseded...).
 - {"action":"promote","target":"<pId>","reason":"..."} — high-value unresolved proposition → judge problem.
-- {"action":"wait","target":"<id>","reason":"..."} — advisory: wait for a dependency.
+- {"action":"wait","target":"<id>","reason":"..."} — advisory only (logged; no scheduling effect): you are waiting for a dependency.
+- {"action":"continue","childId":"<childId>","reason":"..."} — advisory only (logged): continuation of an in-flight child is code-driven; this never re-dispatches anything.
+- {"action":"stop","childId":"<childId>","reason":"..."} — advisory only (logged; it does NOT stop anyone). To actually stop a child use `interrupt` with a live childId.
 
 HARD RULES: never re-schedule verified objects; problems with 依赖未就绪 (依赖就绪=false) should wait unless you explicitly accept a temporary assumption; respect capacity (brief.free_slots); PREFER problems whose dependencies are ready and whose directions have the highest survival; DO NOT forget verification — unresolved solutions/proofs/refutations (verify_candidates) will never be checked unless you schedule a verifier; DO NOT assume a direction is already being worked just because it is shown "active" in a problem — check brief.problems[].running_solver_dirs and brief.active_agents: schedule a solver for a direction ONLY if that direction is NOT in running_solver_dirs (an "active" direction absent from running_solver_dirs is WAITING to be dispatched, not being worked); schedule at most 3 actions.
 Respond with ONLY a single JSON object wrapped in a ```json code fence — no prose:
@@ -3006,7 +3034,7 @@ Citations: facts may only be cited from Verified/ (or Propos/ 状态: 已验证
   · 宿主没有 Lean 工具链（LEAN_NOT_FOUND）或宿主不提供 subprocess 服务（NO_SUBPROCESS）时：把代码写下来归档，并在回执的 note 里写明"宿主无 Lean 工具链"——这算显式阻塞原因，定论门禁可以据此放行。
 - math_computation：本机可用 （无）。需要数值/符号/统计计算时先 probe 再 run（工具路径会留下可复核回执，结论请引用回执路径）；缺包时如实说明并给替代方案或安装计划（不要假装），安装需先出计划并征得确认。
 - shell 兜底标注：工具不可用而改用宿主 shell 时，结论必须写"未经工具归档（shell 路径）"，且不得与工具回执混同（shell 无回执、无超时/输出上限保证）。
-- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以打开它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）；编辑后用 mode:'file' 指向它重跑，会写出一份**新回执/新 attempt**（含新的 scriptHash）。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
+- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以读它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）。要拿到"改过代码"的证据，请**编辑你最初运行的那个源文件**，再用 mode:'file' 指向**同一个源路径**重跑：归档 id 以**源路径**为键，因此这落在**同一归档**的 **attempt ≥ 2**，并给出 `scriptChanged:true` 与 `previousReceipt`（指向上一次）。**指向归档副本本身**（`receipt.scriptAbs` 那个路径）按设计是**另一份新归档**：新 id、attempt 1、没有 `previousReceipt`、`scriptChanged:false`；旧 attempt 绝不会被覆盖，但它**不是**"同一归档的新 attempt"——工具会用 `fileIsArchivedScript` 与 `ARCHIVED_SCRIPT_RERUN` 警告明确说明。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
 - 需要精确数值、符号化简、反例搜索、统计或线性代数时调用 math_computation：先 probe，再 run。
 - 复核他人的数值结论时用 op:'receipt'（或 op:'run', mode:'file' 指向同一脚本）重跑，并把回执路径写进报告。
 - 归档即引用：报告里带 Computation/<id>/receipt.json；这是"支撑材料"的用法。
@@ -3079,7 +3107,7 @@ Citations: facts may only be cited from Verified/ (or Propos/ 状态: 已验证
   · 宿主没有 Lean 工具链（LEAN_NOT_FOUND）或宿主不提供 subprocess 服务（NO_SUBPROCESS）时：把代码写下来归档，并在回执的 note 里写明"宿主无 Lean 工具链"——这算显式阻塞原因，定论门禁可以据此放行。
 - math_computation：本机可用 （无）。需要数值/符号/统计计算时先 probe 再 run（工具路径会留下可复核回执，结论请引用回执路径）；缺包时如实说明并给替代方案或安装计划（不要假装），安装需先出计划并征得确认。
 - shell 兜底标注：工具不可用而改用宿主 shell 时，结论必须写"未经工具归档（shell 路径）"，且不得与工具回执混同（shell 无回执、无超时/输出上限保证）。
-- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以打开它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）；编辑后用 mode:'file' 指向它重跑，会写出一份**新回执/新 attempt**（含新的 scriptHash）。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
+- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以读它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）。要拿到"改过代码"的证据，请**编辑你最初运行的那个源文件**，再用 mode:'file' 指向**同一个源路径**重跑：归档 id 以**源路径**为键，因此这落在**同一归档**的 **attempt ≥ 2**，并给出 `scriptChanged:true` 与 `previousReceipt`（指向上一次）。**指向归档副本本身**（`receipt.scriptAbs` 那个路径）按设计是**另一份新归档**：新 id、attempt 1、没有 `previousReceipt`、`scriptChanged:false`；旧 attempt 绝不会被覆盖，但它**不是**"同一归档的新 attempt"——工具会用 `fileIsArchivedScript` 与 `ARCHIVED_SCRIPT_RERUN` 警告明确说明。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
 - 需要精确数值、符号化简、反例搜索、统计或线性代数时调用 math_computation：先 probe，再 run。
 - 复核他人的数值结论时用 op:'receipt'（或 op:'run', mode:'file' 指向同一脚本）重跑，并把回执路径写进报告。
 - 归档即引用：报告里带 Computation/<id>/receipt.json；这是"支撑材料"的用法。
@@ -3112,14 +3140,16 @@ CURRENT STATE BRIEF (JSON):
   "recent_events": "<RECENT_EVENTS>"
 }
 
-ACTION VOCABULARY (code validates every action against hard invariants; invalid actions are dropped):
+ACTION VOCABULARY — the code ACCEPTS exactly these 6 actions: spawn / interrupt / promote are HARD-VALIDATED (invalid ones are dropped), while wait / continue / stop are ADVISORY ONLY (they are logged and have NO scheduling effect):
 - {"action":"spawn","role":"explorer","target":"<qid>","reason":"..."} — problem has no directions yet or all dead (re-derive).
 - {"action":"spawn","role":"solver","target":"<qid>","direction":"<dirId>","reason":"..."} — active direction, needs a solving round.
 - {"action":"spawn","role":"verifier","target":"<rId>","reason":"..."} — verify candidate (from verify_candidates); keep solving AND verifying balanced.
 - {"action":"spawn","role":"method-keeper","reason":"..."} — distill pending inventions / maintain the theory library.
 - {"action":"interrupt","childId":"<childId>","reason":"..."} — stop a running child (direction dead, superseded...).
 - {"action":"promote","target":"<pId>","reason":"..."} — high-value unresolved proposition → judge problem.
-- {"action":"wait","target":"<id>","reason":"..."} — advisory: wait for a dependency.
+- {"action":"wait","target":"<id>","reason":"..."} — advisory only (logged; no scheduling effect): you are waiting for a dependency.
+- {"action":"continue","childId":"<childId>","reason":"..."} — advisory only (logged): continuation of an in-flight child is code-driven; this never re-dispatches anything.
+- {"action":"stop","childId":"<childId>","reason":"..."} — advisory only (logged; it does NOT stop anyone). To actually stop a child use `interrupt` with a live childId.
 
 HARD RULES: never re-schedule verified objects; problems with 依赖未就绪 (依赖就绪=false) should wait unless you explicitly accept a temporary assumption; respect capacity (brief.free_slots); PREFER problems whose dependencies are ready and whose directions have the highest survival; DO NOT forget verification — unresolved solutions/proofs/refutations (verify_candidates) will never be checked unless you schedule a verifier; DO NOT assume a direction is already being worked just because it is shown "active" in a problem — check brief.problems[].running_solver_dirs and brief.active_agents: schedule a solver for a direction ONLY if that direction is NOT in running_solver_dirs (an "active" direction absent from running_solver_dirs is WAITING to be dispatched, not being worked); schedule at most 3 actions.
 Respond with ONLY a single JSON object wrapped in a ```json code fence — no prose:
@@ -3184,7 +3214,7 @@ Citations: facts may only be cited from Verified/ (or Propos/ 状态: 已验证
   ▸ 只有当你**独立于这份 Lean 代码**也能确定命题为假时，才投 0，并在 Reason 里写清独立理由。
 - math_computation：本机可用 （无）。需要数值/符号/统计计算时先 probe 再 run（工具路径会留下可复核回执，结论请引用回执路径）；缺包时如实说明并给替代方案或安装计划（不要假装），安装需先出计划并征得确认。
 - shell 兜底标注：工具不可用而改用宿主 shell 时，结论必须写"未经工具归档（shell 路径）"，且不得与工具回执混同（shell 无回执、无超时/输出上限保证）。
-- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以打开它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）；编辑后用 mode:'file' 指向它重跑，会写出一份**新回执/新 attempt**（含新的 scriptHash）。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
+- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以读它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）。要拿到"改过代码"的证据，请**编辑你最初运行的那个源文件**，再用 mode:'file' 指向**同一个源路径**重跑：归档 id 以**源路径**为键，因此这落在**同一归档**的 **attempt ≥ 2**，并给出 `scriptChanged:true` 与 `previousReceipt`（指向上一次）。**指向归档副本本身**（`receipt.scriptAbs` 那个路径）按设计是**另一份新归档**：新 id、attempt 1、没有 `previousReceipt`、`scriptChanged:false`；旧 attempt 绝不会被覆盖，但它**不是**"同一归档的新 attempt"——工具会用 `fileIsArchivedScript` 与 `ARCHIVED_SCRIPT_RERUN` 警告明确说明。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
 - 需要精确数值、符号化简、反例搜索、统计或线性代数时调用 math_computation：先 probe，再 run。
 - 复核他人的数值结论时用 op:'receipt'（或 op:'run', mode:'file' 指向同一脚本）重跑，并把回执路径写进报告。
 - 归档即引用：报告里带 Computation/<id>/receipt.json；这是"支撑材料"的用法。
@@ -3255,7 +3285,7 @@ Citations: facts may only be cited from Verified/ (or Propos/ 状态: 已验证
   ▸ 只有当你**独立于这份 Lean 代码**也能确定命题为假时，才投 0，并在 Reason 里写清独立理由。
 - math_computation：本机可用 （无）。需要数值/符号/统计计算时先 probe 再 run（工具路径会留下可复核回执，结论请引用回执路径）；缺包时如实说明并给替代方案或安装计划（不要假装），安装需先出计划并征得确认。
 - shell 兜底标注：工具不可用而改用宿主 shell 时，结论必须写"未经工具归档（shell 路径）"，且不得与工具回执混同（shell 无回执、无超时/输出上限保证）。
-- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以打开它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）；编辑后用 mode:'file' 指向它重跑，会写出一份**新回执/新 attempt**（含新的 scriptHash）。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
+- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以读它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）。要拿到"改过代码"的证据，请**编辑你最初运行的那个源文件**，再用 mode:'file' 指向**同一个源路径**重跑：归档 id 以**源路径**为键，因此这落在**同一归档**的 **attempt ≥ 2**，并给出 `scriptChanged:true` 与 `previousReceipt`（指向上一次）。**指向归档副本本身**（`receipt.scriptAbs` 那个路径）按设计是**另一份新归档**：新 id、attempt 1、没有 `previousReceipt`、`scriptChanged:false`；旧 attempt 绝不会被覆盖，但它**不是**"同一归档的新 attempt"——工具会用 `fileIsArchivedScript` 与 `ARCHIVED_SCRIPT_RERUN` 警告明确说明。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
 - 需要精确数值、符号化简、反例搜索、统计或线性代数时调用 math_computation：先 probe，再 run。
 - 复核他人的数值结论时用 op:'receipt'（或 op:'run', mode:'file' 指向同一脚本）重跑，并把回执路径写进报告。
 - 归档即引用：报告里带 Computation/<id>/receipt.json；这是"支撑材料"的用法。
@@ -3288,14 +3318,16 @@ CURRENT STATE BRIEF (JSON):
   "recent_events": "<RECENT_EVENTS>"
 }
 
-ACTION VOCABULARY (code validates every action against hard invariants; invalid actions are dropped):
+ACTION VOCABULARY — the code ACCEPTS exactly these 6 actions: spawn / interrupt / promote are HARD-VALIDATED (invalid ones are dropped), while wait / continue / stop are ADVISORY ONLY (they are logged and have NO scheduling effect):
 - {"action":"spawn","role":"explorer","target":"<qid>","reason":"..."} — problem has no directions yet or all dead (re-derive).
 - {"action":"spawn","role":"solver","target":"<qid>","direction":"<dirId>","reason":"..."} — active direction, needs a solving round.
 - {"action":"spawn","role":"verifier","target":"<rId>","reason":"..."} — verify candidate (from verify_candidates); keep solving AND verifying balanced.
 - {"action":"spawn","role":"method-keeper","reason":"..."} — distill pending inventions / maintain the theory library.
 - {"action":"interrupt","childId":"<childId>","reason":"..."} — stop a running child (direction dead, superseded...).
 - {"action":"promote","target":"<pId>","reason":"..."} — high-value unresolved proposition → judge problem.
-- {"action":"wait","target":"<id>","reason":"..."} — advisory: wait for a dependency.
+- {"action":"wait","target":"<id>","reason":"..."} — advisory only (logged; no scheduling effect): you are waiting for a dependency.
+- {"action":"continue","childId":"<childId>","reason":"..."} — advisory only (logged): continuation of an in-flight child is code-driven; this never re-dispatches anything.
+- {"action":"stop","childId":"<childId>","reason":"..."} — advisory only (logged; it does NOT stop anyone). To actually stop a child use `interrupt` with a live childId.
 
 HARD RULES: never re-schedule verified objects; problems with 依赖未就绪 (依赖就绪=false) should wait unless you explicitly accept a temporary assumption; respect capacity (brief.free_slots); PREFER problems whose dependencies are ready and whose directions have the highest survival; DO NOT forget verification — unresolved solutions/proofs/refutations (verify_candidates) will never be checked unless you schedule a verifier; DO NOT assume a direction is already being worked just because it is shown "active" in a problem — check brief.problems[].running_solver_dirs and brief.active_agents: schedule a solver for a direction ONLY if that direction is NOT in running_solver_dirs (an "active" direction absent from running_solver_dirs is WAITING to be dispatched, not being worked); schedule at most 3 actions.
 Respond with ONLY a single JSON object wrapped in a ```json code fence — no prose:
@@ -3360,7 +3392,7 @@ Citations: facts may only be cited from Verified/ (or Propos/ 状态: 已验证
   ▸ 只有当你**独立于这份 Lean 代码**也能确定命题为假时，才投 0，并在 Reason 里写清独立理由。
 - math_computation：本机可用 （无）。需要数值/符号/统计计算时先 probe 再 run（工具路径会留下可复核回执，结论请引用回执路径）；缺包时如实说明并给替代方案或安装计划（不要假装），安装需先出计划并征得确认。
 - shell 兜底标注：工具不可用而改用宿主 shell 时，结论必须写"未经工具归档（shell 路径）"，且不得与工具回执混同（shell 无回执、无超时/输出上限保证）。
-- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以打开它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）；编辑后用 mode:'file' 指向它重跑，会写出一份**新回执/新 attempt**（含新的 scriptHash）。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
+- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以读它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）。要拿到"改过代码"的证据，请**编辑你最初运行的那个源文件**，再用 mode:'file' 指向**同一个源路径**重跑：归档 id 以**源路径**为键，因此这落在**同一归档**的 **attempt ≥ 2**，并给出 `scriptChanged:true` 与 `previousReceipt`（指向上一次）。**指向归档副本本身**（`receipt.scriptAbs` 那个路径）按设计是**另一份新归档**：新 id、attempt 1、没有 `previousReceipt`、`scriptChanged:false`；旧 attempt 绝不会被覆盖，但它**不是**"同一归档的新 attempt"——工具会用 `fileIsArchivedScript` 与 `ARCHIVED_SCRIPT_RERUN` 警告明确说明。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
 - 需要精确数值、符号化简、反例搜索、统计或线性代数时调用 math_computation：先 probe，再 run。
 - 复核他人的数值结论时用 op:'receipt'（或 op:'run', mode:'file' 指向同一脚本）重跑，并把回执路径写进报告。
 - 归档即引用：报告里带 Computation/<id>/receipt.json；这是"支撑材料"的用法。
@@ -3431,7 +3463,7 @@ Citations: facts may only be cited from Verified/ (or Propos/ 状态: 已验证
   ▸ 只有当你**独立于这份 Lean 代码**也能确定命题为假时，才投 0，并在 Reason 里写清独立理由。
 - math_computation：本机可用 （无）。需要数值/符号/统计计算时先 probe 再 run（工具路径会留下可复核回执，结论请引用回执路径）；缺包时如实说明并给替代方案或安装计划（不要假装），安装需先出计划并征得确认。
 - shell 兜底标注：工具不可用而改用宿主 shell 时，结论必须写"未经工具归档（shell 路径）"，且不得与工具回执混同（shell 无回执、无超时/输出上限保证）。
-- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以打开它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）；编辑后用 mode:'file' 指向它重跑，会写出一份**新回执/新 attempt**（含新的 scriptHash）。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
+- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以读它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）。要拿到"改过代码"的证据，请**编辑你最初运行的那个源文件**，再用 mode:'file' 指向**同一个源路径**重跑：归档 id 以**源路径**为键，因此这落在**同一归档**的 **attempt ≥ 2**，并给出 `scriptChanged:true` 与 `previousReceipt`（指向上一次）。**指向归档副本本身**（`receipt.scriptAbs` 那个路径）按设计是**另一份新归档**：新 id、attempt 1、没有 `previousReceipt`、`scriptChanged:false`；旧 attempt 绝不会被覆盖，但它**不是**"同一归档的新 attempt"——工具会用 `fileIsArchivedScript` 与 `ARCHIVED_SCRIPT_RERUN` 警告明确说明。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
 - 需要精确数值、符号化简、反例搜索、统计或线性代数时调用 math_computation：先 probe，再 run。
 - 复核他人的数值结论时用 op:'receipt'（或 op:'run', mode:'file' 指向同一脚本）重跑，并把回执路径写进报告。
 - 归档即引用：报告里带 Computation/<id>/receipt.json；这是"支撑材料"的用法。
@@ -3523,14 +3555,16 @@ CURRENT STATE BRIEF (JSON):
   "recent_events": "<RECENT_EVENTS>"
 }
 
-ACTION VOCABULARY (code validates every action against hard invariants; invalid actions are dropped):
+ACTION VOCABULARY — the code ACCEPTS exactly these 6 actions: spawn / interrupt / promote are HARD-VALIDATED (invalid ones are dropped), while wait / continue / stop are ADVISORY ONLY (they are logged and have NO scheduling effect):
 - {"action":"spawn","role":"explorer","target":"<qid>","reason":"..."} — problem has no directions yet or all dead (re-derive).
 - {"action":"spawn","role":"solver","target":"<qid>","direction":"<dirId>","reason":"..."} — active direction, needs a solving round.
 - {"action":"spawn","role":"verifier","target":"<rId>","reason":"..."} — verify candidate (from verify_candidates); keep solving AND verifying balanced.
 - {"action":"spawn","role":"method-keeper","reason":"..."} — distill pending inventions / maintain the theory library.
 - {"action":"interrupt","childId":"<childId>","reason":"..."} — stop a running child (direction dead, superseded...).
 - {"action":"promote","target":"<pId>","reason":"..."} — high-value unresolved proposition → judge problem.
-- {"action":"wait","target":"<id>","reason":"..."} — advisory: wait for a dependency.
+- {"action":"wait","target":"<id>","reason":"..."} — advisory only (logged; no scheduling effect): you are waiting for a dependency.
+- {"action":"continue","childId":"<childId>","reason":"..."} — advisory only (logged): continuation of an in-flight child is code-driven; this never re-dispatches anything.
+- {"action":"stop","childId":"<childId>","reason":"..."} — advisory only (logged; it does NOT stop anyone). To actually stop a child use `interrupt` with a live childId.
 
 HARD RULES: never re-schedule verified objects; problems with 依赖未就绪 (依赖就绪=false) should wait unless you explicitly accept a temporary assumption; respect capacity (brief.free_slots); PREFER problems whose dependencies are ready and whose directions have the highest survival; DO NOT forget verification — unresolved solutions/proofs/refutations (verify_candidates) will never be checked unless you schedule a verifier; DO NOT assume a direction is already being worked just because it is shown "active" in a problem — check brief.problems[].running_solver_dirs and brief.active_agents: schedule a solver for a direction ONLY if that direction is NOT in running_solver_dirs (an "active" direction absent from running_solver_dirs is WAITING to be dispatched, not being worked); schedule at most 3 actions.
 Respond with ONLY a single JSON object wrapped in a ```json code fence — no prose:
@@ -3587,7 +3621,7 @@ Citations: facts may only be cited from Verified/ (or Propos/ 状态: 已验证
     请复核这个判断是否成立；若你认为其实可以形式化，请指出来并动手做。
 - math_computation：本机可用 （无）。需要数值/符号/统计计算时先 probe 再 run（工具路径会留下可复核回执，结论请引用回执路径）；缺包时如实说明并给替代方案或安装计划（不要假装），安装需先出计划并征得确认。
 - shell 兜底标注：工具不可用而改用宿主 shell 时，结论必须写"未经工具归档（shell 路径）"，且不得与工具回执混同（shell 无回执、无超时/输出上限保证）。
-- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以打开它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）；编辑后用 mode:'file' 指向它重跑，会写出一份**新回执/新 attempt**（含新的 scriptHash）。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
+- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以读它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）。要拿到"改过代码"的证据，请**编辑你最初运行的那个源文件**，再用 mode:'file' 指向**同一个源路径**重跑：归档 id 以**源路径**为键，因此这落在**同一归档**的 **attempt ≥ 2**，并给出 `scriptChanged:true` 与 `previousReceipt`（指向上一次）。**指向归档副本本身**（`receipt.scriptAbs` 那个路径）按设计是**另一份新归档**：新 id、attempt 1、没有 `previousReceipt`、`scriptChanged:false`；旧 attempt 绝不会被覆盖，但它**不是**"同一归档的新 attempt"——工具会用 `fileIsArchivedScript` 与 `ARCHIVED_SCRIPT_RERUN` 警告明确说明。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
 - 需要精确数值、符号化简、反例搜索、统计或线性代数时调用 math_computation：先 probe，再 run。
 - 复核他人的数值结论时用 op:'receipt'（或 op:'run', mode:'file' 指向同一脚本）重跑，并把回执路径写进报告。
 - 归档即引用：报告里带 Computation/<id>/receipt.json；这是"支撑材料"的用法。
@@ -3650,7 +3684,7 @@ Citations: facts may only be cited from Verified/ (or Propos/ 状态: 已验证
     请复核这个判断是否成立；若你认为其实可以形式化，请指出来并动手做。
 - math_computation：本机可用 （无）。需要数值/符号/统计计算时先 probe 再 run（工具路径会留下可复核回执，结论请引用回执路径）；缺包时如实说明并给替代方案或安装计划（不要假装），安装需先出计划并征得确认。
 - shell 兜底标注：工具不可用而改用宿主 shell 时，结论必须写"未经工具归档（shell 路径）"，且不得与工具回执混同（shell 无回执、无超时/输出上限保证）。
-- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以打开它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）；编辑后用 mode:'file' 指向它重跑，会写出一份**新回执/新 attempt**（含新的 scriptHash）。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
+- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以读它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）。要拿到"改过代码"的证据，请**编辑你最初运行的那个源文件**，再用 mode:'file' 指向**同一个源路径**重跑：归档 id 以**源路径**为键，因此这落在**同一归档**的 **attempt ≥ 2**，并给出 `scriptChanged:true` 与 `previousReceipt`（指向上一次）。**指向归档副本本身**（`receipt.scriptAbs` 那个路径）按设计是**另一份新归档**：新 id、attempt 1、没有 `previousReceipt`、`scriptChanged:false`；旧 attempt 绝不会被覆盖，但它**不是**"同一归档的新 attempt"——工具会用 `fileIsArchivedScript` 与 `ARCHIVED_SCRIPT_RERUN` 警告明确说明。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
 - 需要精确数值、符号化简、反例搜索、统计或线性代数时调用 math_computation：先 probe，再 run。
 - 复核他人的数值结论时用 op:'receipt'（或 op:'run', mode:'file' 指向同一脚本）重跑，并把回执路径写进报告。
 - 归档即引用：报告里带 Computation/<id>/receipt.json；这是"支撑材料"的用法。
@@ -3683,14 +3717,16 @@ CURRENT STATE BRIEF (JSON):
   "recent_events": "<RECENT_EVENTS>"
 }
 
-ACTION VOCABULARY (code validates every action against hard invariants; invalid actions are dropped):
+ACTION VOCABULARY — the code ACCEPTS exactly these 6 actions: spawn / interrupt / promote are HARD-VALIDATED (invalid ones are dropped), while wait / continue / stop are ADVISORY ONLY (they are logged and have NO scheduling effect):
 - {"action":"spawn","role":"explorer","target":"<qid>","reason":"..."} — problem has no directions yet or all dead (re-derive).
 - {"action":"spawn","role":"solver","target":"<qid>","direction":"<dirId>","reason":"..."} — active direction, needs a solving round.
 - {"action":"spawn","role":"verifier","target":"<rId>","reason":"..."} — verify candidate (from verify_candidates); keep solving AND verifying balanced.
 - {"action":"spawn","role":"method-keeper","reason":"..."} — distill pending inventions / maintain the theory library.
 - {"action":"interrupt","childId":"<childId>","reason":"..."} — stop a running child (direction dead, superseded...).
 - {"action":"promote","target":"<pId>","reason":"..."} — high-value unresolved proposition → judge problem.
-- {"action":"wait","target":"<id>","reason":"..."} — advisory: wait for a dependency.
+- {"action":"wait","target":"<id>","reason":"..."} — advisory only (logged; no scheduling effect): you are waiting for a dependency.
+- {"action":"continue","childId":"<childId>","reason":"..."} — advisory only (logged): continuation of an in-flight child is code-driven; this never re-dispatches anything.
+- {"action":"stop","childId":"<childId>","reason":"..."} — advisory only (logged; it does NOT stop anyone). To actually stop a child use `interrupt` with a live childId.
 
 HARD RULES: never re-schedule verified objects; problems with 依赖未就绪 (依赖就绪=false) should wait unless you explicitly accept a temporary assumption; respect capacity (brief.free_slots); PREFER problems whose dependencies are ready and whose directions have the highest survival; DO NOT forget verification — unresolved solutions/proofs/refutations (verify_candidates) will never be checked unless you schedule a verifier; DO NOT assume a direction is already being worked just because it is shown "active" in a problem — check brief.problems[].running_solver_dirs and brief.active_agents: schedule a solver for a direction ONLY if that direction is NOT in running_solver_dirs (an "active" direction absent from running_solver_dirs is WAITING to be dispatched, not being worked); schedule at most 3 actions.
 Respond with ONLY a single JSON object wrapped in a ```json code fence — no prose:
@@ -3755,7 +3791,7 @@ Citations: facts may only be cited from Verified/ (or Propos/ 状态: 已验证
   ▸ 只有当你**独立于这份 Lean 代码**也能确定命题为假时，才投 0，并在 Reason 里写清独立理由。
 - math_computation：本机可用 （无）。需要数值/符号/统计计算时先 probe 再 run（工具路径会留下可复核回执，结论请引用回执路径）；缺包时如实说明并给替代方案或安装计划（不要假装），安装需先出计划并征得确认。
 - shell 兜底标注：工具不可用而改用宿主 shell 时，结论必须写"未经工具归档（shell 路径）"，且不得与工具回执混同（shell 无回执、无超时/输出上限保证）。
-- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以打开它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）；编辑后用 mode:'file' 指向它重跑，会写出一份**新回执/新 attempt**（含新的 scriptHash）。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
+- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以读它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）。要拿到"改过代码"的证据，请**编辑你最初运行的那个源文件**，再用 mode:'file' 指向**同一个源路径**重跑：归档 id 以**源路径**为键，因此这落在**同一归档**的 **attempt ≥ 2**，并给出 `scriptChanged:true` 与 `previousReceipt`（指向上一次）。**指向归档副本本身**（`receipt.scriptAbs` 那个路径）按设计是**另一份新归档**：新 id、attempt 1、没有 `previousReceipt`、`scriptChanged:false`；旧 attempt 绝不会被覆盖，但它**不是**"同一归档的新 attempt"——工具会用 `fileIsArchivedScript` 与 `ARCHIVED_SCRIPT_RERUN` 警告明确说明。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
 - 需要精确数值、符号化简、反例搜索、统计或线性代数时调用 math_computation：先 probe，再 run。
 - 复核他人的数值结论时用 op:'receipt'（或 op:'run', mode:'file' 指向同一脚本）重跑，并把回执路径写进报告。
 - 归档即引用：报告里带 Computation/<id>/receipt.json；这是"支撑材料"的用法。
@@ -3826,7 +3862,7 @@ Citations: facts may only be cited from Verified/ (or Propos/ 状态: 已验证
   ▸ 只有当你**独立于这份 Lean 代码**也能确定命题为假时，才投 0，并在 Reason 里写清独立理由。
 - math_computation：本机可用 （无）。需要数值/符号/统计计算时先 probe 再 run（工具路径会留下可复核回执，结论请引用回执路径）；缺包时如实说明并给替代方案或安装计划（不要假装），安装需先出计划并征得确认。
 - shell 兜底标注：工具不可用而改用宿主 shell 时，结论必须写"未经工具归档（shell 路径）"，且不得与工具回执混同（shell 无回执、无超时/输出上限保证）。
-- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以打开它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）；编辑后用 mode:'file' 指向它重跑，会写出一份**新回执/新 attempt**（含新的 scriptHash）。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
+- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以读它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）。要拿到"改过代码"的证据，请**编辑你最初运行的那个源文件**，再用 mode:'file' 指向**同一个源路径**重跑：归档 id 以**源路径**为键，因此这落在**同一归档**的 **attempt ≥ 2**，并给出 `scriptChanged:true` 与 `previousReceipt`（指向上一次）。**指向归档副本本身**（`receipt.scriptAbs` 那个路径）按设计是**另一份新归档**：新 id、attempt 1、没有 `previousReceipt`、`scriptChanged:false`；旧 attempt 绝不会被覆盖，但它**不是**"同一归档的新 attempt"——工具会用 `fileIsArchivedScript` 与 `ARCHIVED_SCRIPT_RERUN` 警告明确说明。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
 - 需要精确数值、符号化简、反例搜索、统计或线性代数时调用 math_computation：先 probe，再 run。
 - 复核他人的数值结论时用 op:'receipt'（或 op:'run', mode:'file' 指向同一脚本）重跑，并把回执路径写进报告。
 - 归档即引用：报告里带 Computation/<id>/receipt.json；这是"支撑材料"的用法。
@@ -3916,14 +3952,16 @@ CURRENT STATE BRIEF (JSON):
   "recent_events": "<RECENT_EVENTS>"
 }
 
-ACTION VOCABULARY (code validates every action against hard invariants; invalid actions are dropped):
+ACTION VOCABULARY — the code ACCEPTS exactly these 6 actions: spawn / interrupt / promote are HARD-VALIDATED (invalid ones are dropped), while wait / continue / stop are ADVISORY ONLY (they are logged and have NO scheduling effect):
 - {"action":"spawn","role":"explorer","target":"<qid>","reason":"..."} — problem has no directions yet or all dead (re-derive).
 - {"action":"spawn","role":"solver","target":"<qid>","direction":"<dirId>","reason":"..."} — active direction, needs a solving round.
 - {"action":"spawn","role":"verifier","target":"<rId>","reason":"..."} — verify candidate (from verify_candidates); keep solving AND verifying balanced.
 - {"action":"spawn","role":"method-keeper","reason":"..."} — distill pending inventions / maintain the theory library.
 - {"action":"interrupt","childId":"<childId>","reason":"..."} — stop a running child (direction dead, superseded...).
 - {"action":"promote","target":"<pId>","reason":"..."} — high-value unresolved proposition → judge problem.
-- {"action":"wait","target":"<id>","reason":"..."} — advisory: wait for a dependency.
+- {"action":"wait","target":"<id>","reason":"..."} — advisory only (logged; no scheduling effect): you are waiting for a dependency.
+- {"action":"continue","childId":"<childId>","reason":"..."} — advisory only (logged): continuation of an in-flight child is code-driven; this never re-dispatches anything.
+- {"action":"stop","childId":"<childId>","reason":"..."} — advisory only (logged; it does NOT stop anyone). To actually stop a child use `interrupt` with a live childId.
 
 HARD RULES: never re-schedule verified objects; problems with 依赖未就绪 (依赖就绪=false) should wait unless you explicitly accept a temporary assumption; respect capacity (brief.free_slots); PREFER problems whose dependencies are ready and whose directions have the highest survival; DO NOT forget verification — unresolved solutions/proofs/refutations (verify_candidates) will never be checked unless you schedule a verifier; DO NOT assume a direction is already being worked just because it is shown "active" in a problem — check brief.problems[].running_solver_dirs and brief.active_agents: schedule a solver for a direction ONLY if that direction is NOT in running_solver_dirs (an "active" direction absent from running_solver_dirs is WAITING to be dispatched, not being worked); schedule at most 3 actions.
 Respond with ONLY a single JSON object wrapped in a ```json code fence — no prose:
@@ -3988,7 +4026,7 @@ Citations: facts may only be cited from Verified/ (or Propos/ 状态: 已验证
   ▸ 只有当你**独立于这份 Lean 代码**也能确定命题为假时，才投 0，并在 Reason 里写清独立理由。
 - math_computation：本机可用 （无）。需要数值/符号/统计计算时先 probe 再 run（工具路径会留下可复核回执，结论请引用回执路径）；缺包时如实说明并给替代方案或安装计划（不要假装），安装需先出计划并征得确认。
 - shell 兜底标注：工具不可用而改用宿主 shell 时，结论必须写"未经工具归档（shell 路径）"，且不得与工具回执混同（shell 无回执、无超时/输出上限保证）。
-- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以打开它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）；编辑后用 mode:'file' 指向它重跑，会写出一份**新回执/新 attempt**（含新的 scriptHash）。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
+- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以读它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）。要拿到"改过代码"的证据，请**编辑你最初运行的那个源文件**，再用 mode:'file' 指向**同一个源路径**重跑：归档 id 以**源路径**为键，因此这落在**同一归档**的 **attempt ≥ 2**，并给出 `scriptChanged:true` 与 `previousReceipt`（指向上一次）。**指向归档副本本身**（`receipt.scriptAbs` 那个路径）按设计是**另一份新归档**：新 id、attempt 1、没有 `previousReceipt`、`scriptChanged:false`；旧 attempt 绝不会被覆盖，但它**不是**"同一归档的新 attempt"——工具会用 `fileIsArchivedScript` 与 `ARCHIVED_SCRIPT_RERUN` 警告明确说明。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
 - 需要精确数值、符号化简、反例搜索、统计或线性代数时调用 math_computation：先 probe，再 run。
 - 复核他人的数值结论时用 op:'receipt'（或 op:'run', mode:'file' 指向同一脚本）重跑，并把回执路径写进报告。
 - 归档即引用：报告里带 Computation/<id>/receipt.json；这是"支撑材料"的用法。
@@ -4059,7 +4097,7 @@ Citations: facts may only be cited from Verified/ (or Propos/ 状态: 已验证
   ▸ 只有当你**独立于这份 Lean 代码**也能确定命题为假时，才投 0，并在 Reason 里写清独立理由。
 - math_computation：本机可用 （无）。需要数值/符号/统计计算时先 probe 再 run（工具路径会留下可复核回执，结论请引用回执路径）；缺包时如实说明并给替代方案或安装计划（不要假装），安装需先出计划并征得确认。
 - shell 兜底标注：工具不可用而改用宿主 shell 时，结论必须写"未经工具归档（shell 路径）"，且不得与工具回执混同（shell 无回执、无超时/输出上限保证）。
-- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以打开它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）；编辑后用 mode:'file' 指向它重跑，会写出一份**新回执/新 attempt**（含新的 scriptHash）。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
+- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以读它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）。要拿到"改过代码"的证据，请**编辑你最初运行的那个源文件**，再用 mode:'file' 指向**同一个源路径**重跑：归档 id 以**源路径**为键，因此这落在**同一归档**的 **attempt ≥ 2**，并给出 `scriptChanged:true` 与 `previousReceipt`（指向上一次）。**指向归档副本本身**（`receipt.scriptAbs` 那个路径）按设计是**另一份新归档**：新 id、attempt 1、没有 `previousReceipt`、`scriptChanged:false`；旧 attempt 绝不会被覆盖，但它**不是**"同一归档的新 attempt"——工具会用 `fileIsArchivedScript` 与 `ARCHIVED_SCRIPT_RERUN` 警告明确说明。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
 - 需要精确数值、符号化简、反例搜索、统计或线性代数时调用 math_computation：先 probe，再 run。
 - 复核他人的数值结论时用 op:'receipt'（或 op:'run', mode:'file' 指向同一脚本）重跑，并把回执路径写进报告。
 - 归档即引用：报告里带 Computation/<id>/receipt.json；这是"支撑材料"的用法。
@@ -4151,14 +4189,16 @@ CURRENT STATE BRIEF (JSON):
   "recent_events": "<RECENT_EVENTS>"
 }
 
-ACTION VOCABULARY (code validates every action against hard invariants; invalid actions are dropped):
+ACTION VOCABULARY — the code ACCEPTS exactly these 6 actions: spawn / interrupt / promote are HARD-VALIDATED (invalid ones are dropped), while wait / continue / stop are ADVISORY ONLY (they are logged and have NO scheduling effect):
 - {"action":"spawn","role":"explorer","target":"<qid>","reason":"..."} — problem has no directions yet or all dead (re-derive).
 - {"action":"spawn","role":"solver","target":"<qid>","direction":"<dirId>","reason":"..."} — active direction, needs a solving round.
 - {"action":"spawn","role":"verifier","target":"<rId>","reason":"..."} — verify candidate (from verify_candidates); keep solving AND verifying balanced.
 - {"action":"spawn","role":"method-keeper","reason":"..."} — distill pending inventions / maintain the theory library.
 - {"action":"interrupt","childId":"<childId>","reason":"..."} — stop a running child (direction dead, superseded...).
 - {"action":"promote","target":"<pId>","reason":"..."} — high-value unresolved proposition → judge problem.
-- {"action":"wait","target":"<id>","reason":"..."} — advisory: wait for a dependency.
+- {"action":"wait","target":"<id>","reason":"..."} — advisory only (logged; no scheduling effect): you are waiting for a dependency.
+- {"action":"continue","childId":"<childId>","reason":"..."} — advisory only (logged): continuation of an in-flight child is code-driven; this never re-dispatches anything.
+- {"action":"stop","childId":"<childId>","reason":"..."} — advisory only (logged; it does NOT stop anyone). To actually stop a child use `interrupt` with a live childId.
 
 HARD RULES: never re-schedule verified objects; problems with 依赖未就绪 (依赖就绪=false) should wait unless you explicitly accept a temporary assumption; respect capacity (brief.free_slots); PREFER problems whose dependencies are ready and whose directions have the highest survival; DO NOT forget verification — unresolved solutions/proofs/refutations (verify_candidates) will never be checked unless you schedule a verifier; DO NOT assume a direction is already being worked just because it is shown "active" in a problem — check brief.problems[].running_solver_dirs and brief.active_agents: schedule a solver for a direction ONLY if that direction is NOT in running_solver_dirs (an "active" direction absent from running_solver_dirs is WAITING to be dispatched, not being worked); schedule at most 3 actions.
 Respond with ONLY a single JSON object wrapped in a ```json code fence — no prose:
@@ -4209,7 +4249,7 @@ feasibility ∈ [0,1] = your estimate of the probability this direction leads to
 {"meta":{"kind":"directions","qid":"<qid>","directions":[{"id":"d1","title":"...","method":"...","core_assumption":"...","feasibility":0.5}],"methods_used":[{"id":"m-...","效果":"<为何该方向借鉴它>","建议":"..."}],"new_inventions":[{"类型":"方法|工具|...","标题":"...","内容描述":"...","是否已入库":false}]}}
 - math_computation：本机可用 （无）。需要数值/符号/统计计算时先 probe 再 run（工具路径会留下可复核回执，结论请引用回执路径）；缺包时如实说明并给替代方案或安装计划（不要假装），安装需先出计划并征得确认。
 - shell 兜底标注：工具不可用而改用宿主 shell 时，结论必须写"未经工具归档（shell 路径）"，且不得与工具回执混同（shell 无回执、无超时/输出上限保证）。
-- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以打开它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）；编辑后用 mode:'file' 指向它重跑，会写出一份**新回执/新 attempt**（含新的 scriptHash）。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
+- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以读它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）。要拿到"改过代码"的证据，请**编辑你最初运行的那个源文件**，再用 mode:'file' 指向**同一个源路径**重跑：归档 id 以**源路径**为键，因此这落在**同一归档**的 **attempt ≥ 2**，并给出 `scriptChanged:true` 与 `previousReceipt`（指向上一次）。**指向归档副本本身**（`receipt.scriptAbs` 那个路径）按设计是**另一份新归档**：新 id、attempt 1、没有 `previousReceipt`、`scriptChanged:false`；旧 attempt 绝不会被覆盖，但它**不是**"同一归档的新 attempt"——工具会用 `fileIsArchivedScript` 与 `ARCHIVED_SCRIPT_RERUN` 警告明确说明。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
 - 需要精确数值、符号化简、反例搜索、统计或线性代数时调用 math_computation：先 probe，再 run。
 - 复核他人的数值结论时用 op:'receipt'（或 op:'run', mode:'file' 指向同一脚本）重跑，并把回执路径写进报告。
 - 归档即引用：报告里带 Computation/<id>/receipt.json；这是"支撑材料"的用法。
@@ -4270,7 +4310,7 @@ feasibility ∈ [0,1] = your estimate of the probability this direction leads to
 {"meta":{"kind":"directions","qid":"<qid>","directions":[{"id":"d1","title":"...","method":"...","core_assumption":"...","feasibility":0.5}],"methods_used":[{"id":"m-...","效果":"<为何该方向借鉴它>","建议":"..."}],"new_inventions":[{"类型":"方法|工具|...","标题":"...","内容描述":"...","是否已入库":false}]}}
 - math_computation：本机可用 （无）。需要数值/符号/统计计算时先 probe 再 run（工具路径会留下可复核回执，结论请引用回执路径）；缺包时如实说明并给替代方案或安装计划（不要假装），安装需先出计划并征得确认。
 - shell 兜底标注：工具不可用而改用宿主 shell 时，结论必须写"未经工具归档（shell 路径）"，且不得与工具回执混同（shell 无回执、无超时/输出上限保证）。
-- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以打开它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）；编辑后用 mode:'file' 指向它重跑，会写出一份**新回执/新 attempt**（含新的 scriptHash）。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
+- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以读它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）。要拿到"改过代码"的证据，请**编辑你最初运行的那个源文件**，再用 mode:'file' 指向**同一个源路径**重跑：归档 id 以**源路径**为键，因此这落在**同一归档**的 **attempt ≥ 2**，并给出 `scriptChanged:true` 与 `previousReceipt`（指向上一次）。**指向归档副本本身**（`receipt.scriptAbs` 那个路径）按设计是**另一份新归档**：新 id、attempt 1、没有 `previousReceipt`、`scriptChanged:false`；旧 attempt 绝不会被覆盖，但它**不是**"同一归档的新 attempt"——工具会用 `fileIsArchivedScript` 与 `ARCHIVED_SCRIPT_RERUN` 警告明确说明。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
 - 需要精确数值、符号化简、反例搜索、统计或线性代数时调用 math_computation：先 probe，再 run。
 - 复核他人的数值结论时用 op:'receipt'（或 op:'run', mode:'file' 指向同一脚本）重跑，并把回执路径写进报告。
 - 归档即引用：报告里带 Computation/<id>/receipt.json；这是"支撑材料"的用法。
@@ -4331,7 +4371,7 @@ feasibility ∈ [0,1] = your estimate of the probability this direction leads to
 {"meta":{"kind":"directions","qid":"<qid>","directions":[{"id":"d1","title":"...","method":"...","core_assumption":"...","feasibility":0.5}],"methods_used":[{"id":"m-...","效果":"<为何该方向借鉴它>","建议":"..."}],"new_inventions":[{"类型":"方法|工具|...","标题":"...","内容描述":"...","是否已入库":false}]}}
 - math_computation：本机可用 （无）。需要数值/符号/统计计算时先 probe 再 run（工具路径会留下可复核回执，结论请引用回执路径）；缺包时如实说明并给替代方案或安装计划（不要假装），安装需先出计划并征得确认。
 - shell 兜底标注：工具不可用而改用宿主 shell 时，结论必须写"未经工具归档（shell 路径）"，且不得与工具回执混同（shell 无回执、无超时/输出上限保证）。
-- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以打开它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）；编辑后用 mode:'file' 指向它重跑，会写出一份**新回执/新 attempt**（含新的 scriptHash）。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
+- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以读它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）。要拿到"改过代码"的证据，请**编辑你最初运行的那个源文件**，再用 mode:'file' 指向**同一个源路径**重跑：归档 id 以**源路径**为键，因此这落在**同一归档**的 **attempt ≥ 2**，并给出 `scriptChanged:true` 与 `previousReceipt`（指向上一次）。**指向归档副本本身**（`receipt.scriptAbs` 那个路径）按设计是**另一份新归档**：新 id、attempt 1、没有 `previousReceipt`、`scriptChanged:false`；旧 attempt 绝不会被覆盖，但它**不是**"同一归档的新 attempt"——工具会用 `fileIsArchivedScript` 与 `ARCHIVED_SCRIPT_RERUN` 警告明确说明。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
 - 需要精确数值、符号化简、反例搜索、统计或线性代数时调用 math_computation：先 probe，再 run。
 - 复核他人的数值结论时用 op:'receipt'（或 op:'run', mode:'file' 指向同一脚本）重跑，并把回执路径写进报告。
 - 归档即引用：报告里带 Computation/<id>/receipt.json；这是"支撑材料"的用法。
@@ -4368,14 +4408,16 @@ CURRENT STATE BRIEF (JSON):
   "recent_events": "<RECENT_EVENTS>"
 }
 
-ACTION VOCABULARY (code validates every action against hard invariants; invalid actions are dropped):
+ACTION VOCABULARY — the code ACCEPTS exactly these 6 actions: spawn / interrupt / promote are HARD-VALIDATED (invalid ones are dropped), while wait / continue / stop are ADVISORY ONLY (they are logged and have NO scheduling effect):
 - {"action":"spawn","role":"explorer","target":"<qid>","reason":"..."} — problem has no directions yet or all dead (re-derive).
 - {"action":"spawn","role":"solver","target":"<qid>","direction":"<dirId>","reason":"..."} — active direction, needs a solving round.
 - {"action":"spawn","role":"verifier","target":"<rId>","reason":"..."} — verify candidate (from verify_candidates); keep solving AND verifying balanced.
 - {"action":"spawn","role":"method-keeper","reason":"..."} — distill pending inventions / maintain the theory library.
 - {"action":"interrupt","childId":"<childId>","reason":"..."} — stop a running child (direction dead, superseded...).
 - {"action":"promote","target":"<pId>","reason":"..."} — high-value unresolved proposition → judge problem.
-- {"action":"wait","target":"<id>","reason":"..."} — advisory: wait for a dependency.
+- {"action":"wait","target":"<id>","reason":"..."} — advisory only (logged; no scheduling effect): you are waiting for a dependency.
+- {"action":"continue","childId":"<childId>","reason":"..."} — advisory only (logged): continuation of an in-flight child is code-driven; this never re-dispatches anything.
+- {"action":"stop","childId":"<childId>","reason":"..."} — advisory only (logged; it does NOT stop anyone). To actually stop a child use `interrupt` with a live childId.
 
 HARD RULES: never re-schedule verified objects; problems with 依赖未就绪 (依赖就绪=false) should wait unless you explicitly accept a temporary assumption; respect capacity (brief.free_slots); PREFER problems whose dependencies are ready and whose directions have the highest survival; DO NOT forget verification — unresolved solutions/proofs/refutations (verify_candidates) will never be checked unless you schedule a verifier; DO NOT assume a direction is already being worked just because it is shown "active" in a problem — check brief.problems[].running_solver_dirs and brief.active_agents: schedule a solver for a direction ONLY if that direction is NOT in running_solver_dirs (an "active" direction absent from running_solver_dirs is WAITING to be dispatched, not being worked); schedule at most 3 actions.
 Respond with ONLY a single JSON object wrapped in a ```json code fence — no prose:
@@ -4457,7 +4499,7 @@ CHANNEL B (your file tools are unavailable): put the content you would have writ
 区分规则：methods_used 只能填**已存在的方法卡 ID**（m-…，来自 AVAILABLE METHODS 列表）——引用你自己刚想出的新方法/新技巧不属于 methods_used，请如实填入 new_inventions（它会由 Method Keeper 蒸馏建卡）；不要把方法名/标题当 id 填进 methods_used。
 - math_computation：本机可用 （无）。需要数值/符号/统计计算时先 probe 再 run（工具路径会留下可复核回执，结论请引用回执路径）；缺包时如实说明并给替代方案或安装计划（不要假装），安装需先出计划并征得确认。
 - shell 兜底标注：工具不可用而改用宿主 shell 时，结论必须写"未经工具归档（shell 路径）"，且不得与工具回执混同（shell 无回执、无超时/输出上限保证）。
-- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以打开它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）；编辑后用 mode:'file' 指向它重跑，会写出一份**新回执/新 attempt**（含新的 scriptHash）。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
+- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以读它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）。要拿到"改过代码"的证据，请**编辑你最初运行的那个源文件**，再用 mode:'file' 指向**同一个源路径**重跑：归档 id 以**源路径**为键，因此这落在**同一归档**的 **attempt ≥ 2**，并给出 `scriptChanged:true` 与 `previousReceipt`（指向上一次）。**指向归档副本本身**（`receipt.scriptAbs` 那个路径）按设计是**另一份新归档**：新 id、attempt 1、没有 `previousReceipt`、`scriptChanged:false`；旧 attempt 绝不会被覆盖，但它**不是**"同一归档的新 attempt"——工具会用 `fileIsArchivedScript` 与 `ARCHIVED_SCRIPT_RERUN` 警告明确说明。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
 - 需要精确数值、符号化简、反例搜索、统计或线性代数时调用 math_computation：先 probe，再 run。
 - 复核他人的数值结论时用 op:'receipt'（或 op:'run', mode:'file' 指向同一脚本）重跑，并把回执路径写进报告。
 - 归档即引用：报告里带 Computation/<id>/receipt.json；这是"支撑材料"的用法。
@@ -4494,14 +4536,16 @@ CURRENT STATE BRIEF (JSON):
   "recent_events": "<RECENT_EVENTS>"
 }
 
-ACTION VOCABULARY (code validates every action against hard invariants; invalid actions are dropped):
+ACTION VOCABULARY — the code ACCEPTS exactly these 6 actions: spawn / interrupt / promote are HARD-VALIDATED (invalid ones are dropped), while wait / continue / stop are ADVISORY ONLY (they are logged and have NO scheduling effect):
 - {"action":"spawn","role":"explorer","target":"<qid>","reason":"..."} — problem has no directions yet or all dead (re-derive).
 - {"action":"spawn","role":"solver","target":"<qid>","direction":"<dirId>","reason":"..."} — active direction, needs a solving round.
 - {"action":"spawn","role":"verifier","target":"<rId>","reason":"..."} — verify candidate (from verify_candidates); keep solving AND verifying balanced.
 - {"action":"spawn","role":"method-keeper","reason":"..."} — distill pending inventions / maintain the theory library.
 - {"action":"interrupt","childId":"<childId>","reason":"..."} — stop a running child (direction dead, superseded...).
 - {"action":"promote","target":"<pId>","reason":"..."} — high-value unresolved proposition → judge problem.
-- {"action":"wait","target":"<id>","reason":"..."} — advisory: wait for a dependency.
+- {"action":"wait","target":"<id>","reason":"..."} — advisory only (logged; no scheduling effect): you are waiting for a dependency.
+- {"action":"continue","childId":"<childId>","reason":"..."} — advisory only (logged): continuation of an in-flight child is code-driven; this never re-dispatches anything.
+- {"action":"stop","childId":"<childId>","reason":"..."} — advisory only (logged; it does NOT stop anyone). To actually stop a child use `interrupt` with a live childId.
 
 HARD RULES: never re-schedule verified objects; problems with 依赖未就绪 (依赖就绪=false) should wait unless you explicitly accept a temporary assumption; respect capacity (brief.free_slots); PREFER problems whose dependencies are ready and whose directions have the highest survival; DO NOT forget verification — unresolved solutions/proofs/refutations (verify_candidates) will never be checked unless you schedule a verifier; DO NOT assume a direction is already being worked just because it is shown "active" in a problem — check brief.problems[].running_solver_dirs and brief.active_agents: schedule a solver for a direction ONLY if that direction is NOT in running_solver_dirs (an "active" direction absent from running_solver_dirs is WAITING to be dispatched, not being worked); schedule at most 3 actions.
 Respond with ONLY a single JSON object wrapped in a ```json code fence — no prose:
@@ -4566,7 +4610,7 @@ Citations: facts may only be cited from Verified/ (or Propos/ 状态: 已验证
   ▸ 只有当你**独立于这份 Lean 代码**也能确定命题为假时，才投 0，并在 Reason 里写清独立理由。
 - math_computation：本机可用 （无）。需要数值/符号/统计计算时先 probe 再 run（工具路径会留下可复核回执，结论请引用回执路径）；缺包时如实说明并给替代方案或安装计划（不要假装），安装需先出计划并征得确认。
 - shell 兜底标注：工具不可用而改用宿主 shell 时，结论必须写"未经工具归档（shell 路径）"，且不得与工具回执混同（shell 无回执、无超时/输出上限保证）。
-- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以打开它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）；编辑后用 mode:'file' 指向它重跑，会写出一份**新回执/新 attempt**（含新的 scriptHash）。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
+- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以读它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）。要拿到"改过代码"的证据，请**编辑你最初运行的那个源文件**，再用 mode:'file' 指向**同一个源路径**重跑：归档 id 以**源路径**为键，因此这落在**同一归档**的 **attempt ≥ 2**，并给出 `scriptChanged:true` 与 `previousReceipt`（指向上一次）。**指向归档副本本身**（`receipt.scriptAbs` 那个路径）按设计是**另一份新归档**：新 id、attempt 1、没有 `previousReceipt`、`scriptChanged:false`；旧 attempt 绝不会被覆盖，但它**不是**"同一归档的新 attempt"——工具会用 `fileIsArchivedScript` 与 `ARCHIVED_SCRIPT_RERUN` 警告明确说明。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
 - 需要精确数值、符号化简、反例搜索、统计或线性代数时调用 math_computation：先 probe，再 run。
 - 复核他人的数值结论时用 op:'receipt'（或 op:'run', mode:'file' 指向同一脚本）重跑，并把回执路径写进报告。
 - 归档即引用：报告里带 Computation/<id>/receipt.json；这是"支撑材料"的用法。
@@ -4637,7 +4681,7 @@ Citations: facts may only be cited from Verified/ (or Propos/ 状态: 已验证
   ▸ 只有当你**独立于这份 Lean 代码**也能确定命题为假时，才投 0，并在 Reason 里写清独立理由。
 - math_computation：本机可用 （无）。需要数值/符号/统计计算时先 probe 再 run（工具路径会留下可复核回执，结论请引用回执路径）；缺包时如实说明并给替代方案或安装计划（不要假装），安装需先出计划并征得确认。
 - shell 兜底标注：工具不可用而改用宿主 shell 时，结论必须写"未经工具归档（shell 路径）"，且不得与工具回执混同（shell 无回执、无超时/输出上限保证）。
-- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以打开它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）；编辑后用 mode:'file' 指向它重跑，会写出一份**新回执/新 attempt**（含新的 scriptHash）。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
+- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以读它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）。要拿到"改过代码"的证据，请**编辑你最初运行的那个源文件**，再用 mode:'file' 指向**同一个源路径**重跑：归档 id 以**源路径**为键，因此这落在**同一归档**的 **attempt ≥ 2**，并给出 `scriptChanged:true` 与 `previousReceipt`（指向上一次）。**指向归档副本本身**（`receipt.scriptAbs` 那个路径）按设计是**另一份新归档**：新 id、attempt 1、没有 `previousReceipt`、`scriptChanged:false`；旧 attempt 绝不会被覆盖，但它**不是**"同一归档的新 attempt"——工具会用 `fileIsArchivedScript` 与 `ARCHIVED_SCRIPT_RERUN` 警告明确说明。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
 - 需要精确数值、符号化简、反例搜索、统计或线性代数时调用 math_computation：先 probe，再 run。
 - 复核他人的数值结论时用 op:'receipt'（或 op:'run', mode:'file' 指向同一脚本）重跑，并把回执路径写进报告。
 - 归档即引用：报告里带 Computation/<id>/receipt.json；这是"支撑材料"的用法。
@@ -4709,7 +4753,7 @@ Reason is MANDATORY and MUST be non-empty; an empty-Reason result (esp. a bare 0
   ▸ 只有当你**独立于这份 Lean 代码**也能确定命题为假时，才投 0，并在 Reason 里写清独立理由。
 - math_computation：本机可用 （无）。需要数值/符号/统计计算时先 probe 再 run（工具路径会留下可复核回执，结论请引用回执路径）；缺包时如实说明并给替代方案或安装计划（不要假装），安装需先出计划并征得确认。
 - shell 兜底标注：工具不可用而改用宿主 shell 时，结论必须写"未经工具归档（shell 路径）"，且不得与工具回执混同（shell 无回执、无超时/输出上限保证）。
-- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以打开它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）；编辑后用 mode:'file' 指向它重跑，会写出一份**新回执/新 attempt**（含新的 scriptHash）。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
+- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以读它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）。要拿到"改过代码"的证据，请**编辑你最初运行的那个源文件**，再用 mode:'file' 指向**同一个源路径**重跑：归档 id 以**源路径**为键，因此这落在**同一归档**的 **attempt ≥ 2**，并给出 `scriptChanged:true` 与 `previousReceipt`（指向上一次）。**指向归档副本本身**（`receipt.scriptAbs` 那个路径）按设计是**另一份新归档**：新 id、attempt 1、没有 `previousReceipt`、`scriptChanged:false`；旧 attempt 绝不会被覆盖，但它**不是**"同一归档的新 attempt"——工具会用 `fileIsArchivedScript` 与 `ARCHIVED_SCRIPT_RERUN` 警告明确说明。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
 - 需要精确数值、符号化简、反例搜索、统计或线性代数时调用 math_computation：先 probe，再 run。
 - 复核他人的数值结论时用 op:'receipt'（或 op:'run', mode:'file' 指向同一脚本）重跑，并把回执路径写进报告。
 - 归档即引用：报告里带 Computation/<id>/receipt.json；这是"支撑材料"的用法。
@@ -4781,7 +4825,7 @@ Reason is MANDATORY and MUST be non-empty; an empty-Reason result (esp. a bare 0
   ▸ 只有当你**独立于这份 Lean 代码**也能确定命题为假时，才投 0，并在 Reason 里写清独立理由。
 - math_computation：本机可用 （无）。需要数值/符号/统计计算时先 probe 再 run（工具路径会留下可复核回执，结论请引用回执路径）；缺包时如实说明并给替代方案或安装计划（不要假装），安装需先出计划并征得确认。
 - shell 兜底标注：工具不可用而改用宿主 shell 时，结论必须写"未经工具归档（shell 路径）"，且不得与工具回执混同（shell 无回执、无超时/输出上限保证）。
-- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以打开它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）；编辑后用 mode:'file' 指向它重跑，会写出一份**新回执/新 attempt**（含新的 scriptHash）。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
+- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以读它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）。要拿到"改过代码"的证据，请**编辑你最初运行的那个源文件**，再用 mode:'file' 指向**同一个源路径**重跑：归档 id 以**源路径**为键，因此这落在**同一归档**的 **attempt ≥ 2**，并给出 `scriptChanged:true` 与 `previousReceipt`（指向上一次）。**指向归档副本本身**（`receipt.scriptAbs` 那个路径）按设计是**另一份新归档**：新 id、attempt 1、没有 `previousReceipt`、`scriptChanged:false`；旧 attempt 绝不会被覆盖，但它**不是**"同一归档的新 attempt"——工具会用 `fileIsArchivedScript` 与 `ARCHIVED_SCRIPT_RERUN` 警告明确说明。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
 - 需要精确数值、符号化简、反例搜索、统计或线性代数时调用 math_computation：先 probe，再 run。
 - 复核他人的数值结论时用 op:'receipt'（或 op:'run', mode:'file' 指向同一脚本）重跑，并把回执路径写进报告。
 - 归档即引用：报告里带 Computation/<id>/receipt.json；这是"支撑材料"的用法。
@@ -4814,14 +4858,16 @@ CURRENT STATE BRIEF (JSON):
   "recent_events": "<RECENT_EVENTS>"
 }
 
-ACTION VOCABULARY (code validates every action against hard invariants; invalid actions are dropped):
+ACTION VOCABULARY — the code ACCEPTS exactly these 6 actions: spawn / interrupt / promote are HARD-VALIDATED (invalid ones are dropped), while wait / continue / stop are ADVISORY ONLY (they are logged and have NO scheduling effect):
 - {"action":"spawn","role":"explorer","target":"<qid>","reason":"..."} — problem has no directions yet or all dead (re-derive).
 - {"action":"spawn","role":"solver","target":"<qid>","direction":"<dirId>","reason":"..."} — active direction, needs a solving round.
 - {"action":"spawn","role":"verifier","target":"<rId>","reason":"..."} — verify candidate (from verify_candidates); keep solving AND verifying balanced.
 - {"action":"spawn","role":"method-keeper","reason":"..."} — distill pending inventions / maintain the theory library.
 - {"action":"interrupt","childId":"<childId>","reason":"..."} — stop a running child (direction dead, superseded...).
 - {"action":"promote","target":"<pId>","reason":"..."} — high-value unresolved proposition → judge problem.
-- {"action":"wait","target":"<id>","reason":"..."} — advisory: wait for a dependency.
+- {"action":"wait","target":"<id>","reason":"..."} — advisory only (logged; no scheduling effect): you are waiting for a dependency.
+- {"action":"continue","childId":"<childId>","reason":"..."} — advisory only (logged): continuation of an in-flight child is code-driven; this never re-dispatches anything.
+- {"action":"stop","childId":"<childId>","reason":"..."} — advisory only (logged; it does NOT stop anyone). To actually stop a child use `interrupt` with a live childId.
 
 HARD RULES: never re-schedule verified objects; problems with 依赖未就绪 (依赖就绪=false) should wait unless you explicitly accept a temporary assumption; respect capacity (brief.free_slots); PREFER problems whose dependencies are ready and whose directions have the highest survival; DO NOT forget verification — unresolved solutions/proofs/refutations (verify_candidates) will never be checked unless you schedule a verifier; DO NOT assume a direction is already being worked just because it is shown "active" in a problem — check brief.problems[].running_solver_dirs and brief.active_agents: schedule a solver for a direction ONLY if that direction is NOT in running_solver_dirs (an "active" direction absent from running_solver_dirs is WAITING to be dispatched, not being worked); schedule at most 3 actions.
 Respond with ONLY a single JSON object wrapped in a ```json code fence — no prose:
@@ -4886,7 +4932,7 @@ Citations: facts may only be cited from Verified/ (or Propos/ 状态: 已验证
   ▸ 只有当你**独立于这份 Lean 代码**也能确定命题为假时，才投 0，并在 Reason 里写清独立理由。
 - math_computation：本机可用 （无）。需要数值/符号/统计计算时先 probe 再 run（工具路径会留下可复核回执，结论请引用回执路径）；缺包时如实说明并给替代方案或安装计划（不要假装），安装需先出计划并征得确认。
 - shell 兜底标注：工具不可用而改用宿主 shell 时，结论必须写"未经工具归档（shell 路径）"，且不得与工具回执混同（shell 无回执、无超时/输出上限保证）。
-- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以打开它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）；编辑后用 mode:'file' 指向它重跑，会写出一份**新回执/新 attempt**（含新的 scriptHash）。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
+- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以读它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）。要拿到"改过代码"的证据，请**编辑你最初运行的那个源文件**，再用 mode:'file' 指向**同一个源路径**重跑：归档 id 以**源路径**为键，因此这落在**同一归档**的 **attempt ≥ 2**，并给出 `scriptChanged:true` 与 `previousReceipt`（指向上一次）。**指向归档副本本身**（`receipt.scriptAbs` 那个路径）按设计是**另一份新归档**：新 id、attempt 1、没有 `previousReceipt`、`scriptChanged:false`；旧 attempt 绝不会被覆盖，但它**不是**"同一归档的新 attempt"——工具会用 `fileIsArchivedScript` 与 `ARCHIVED_SCRIPT_RERUN` 警告明确说明。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
 - 需要精确数值、符号化简、反例搜索、统计或线性代数时调用 math_computation：先 probe，再 run。
 - 复核他人的数值结论时用 op:'receipt'（或 op:'run', mode:'file' 指向同一脚本）重跑，并把回执路径写进报告。
 - 归档即引用：报告里带 Computation/<id>/receipt.json；这是"支撑材料"的用法。
@@ -4957,7 +5003,7 @@ Citations: facts may only be cited from Verified/ (or Propos/ 状态: 已验证
   ▸ 只有当你**独立于这份 Lean 代码**也能确定命题为假时，才投 0，并在 Reason 里写清独立理由。
 - math_computation：本机可用 （无）。需要数值/符号/统计计算时先 probe 再 run（工具路径会留下可复核回执，结论请引用回执路径）；缺包时如实说明并给替代方案或安装计划（不要假装），安装需先出计划并征得确认。
 - shell 兜底标注：工具不可用而改用宿主 shell 时，结论必须写"未经工具归档（shell 路径）"，且不得与工具回执混同（shell 无回执、无超时/输出上限保证）。
-- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以打开它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）；编辑后用 mode:'file' 指向它重跑，会写出一份**新回执/新 attempt**（含新的 scriptHash）。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
+- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以读它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）。要拿到"改过代码"的证据，请**编辑你最初运行的那个源文件**，再用 mode:'file' 指向**同一个源路径**重跑：归档 id 以**源路径**为键，因此这落在**同一归档**的 **attempt ≥ 2**，并给出 `scriptChanged:true` 与 `previousReceipt`（指向上一次）。**指向归档副本本身**（`receipt.scriptAbs` 那个路径）按设计是**另一份新归档**：新 id、attempt 1、没有 `previousReceipt`、`scriptChanged:false`；旧 attempt 绝不会被覆盖，但它**不是**"同一归档的新 attempt"——工具会用 `fileIsArchivedScript` 与 `ARCHIVED_SCRIPT_RERUN` 警告明确说明。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
 - 需要精确数值、符号化简、反例搜索、统计或线性代数时调用 math_computation：先 probe，再 run。
 - 复核他人的数值结论时用 op:'receipt'（或 op:'run', mode:'file' 指向同一脚本）重跑，并把回执路径写进报告。
 - 归档即引用：报告里带 Computation/<id>/receipt.json；这是"支撑材料"的用法。
@@ -4990,14 +5036,16 @@ CURRENT STATE BRIEF (JSON):
   "recent_events": "<RECENT_EVENTS>"
 }
 
-ACTION VOCABULARY (code validates every action against hard invariants; invalid actions are dropped):
+ACTION VOCABULARY — the code ACCEPTS exactly these 6 actions: spawn / interrupt / promote are HARD-VALIDATED (invalid ones are dropped), while wait / continue / stop are ADVISORY ONLY (they are logged and have NO scheduling effect):
 - {"action":"spawn","role":"explorer","target":"<qid>","reason":"..."} — problem has no directions yet or all dead (re-derive).
 - {"action":"spawn","role":"solver","target":"<qid>","direction":"<dirId>","reason":"..."} — active direction, needs a solving round.
 - {"action":"spawn","role":"verifier","target":"<rId>","reason":"..."} — verify candidate (from verify_candidates); keep solving AND verifying balanced.
 - {"action":"spawn","role":"method-keeper","reason":"..."} — distill pending inventions / maintain the theory library.
 - {"action":"interrupt","childId":"<childId>","reason":"..."} — stop a running child (direction dead, superseded...).
 - {"action":"promote","target":"<pId>","reason":"..."} — high-value unresolved proposition → judge problem.
-- {"action":"wait","target":"<id>","reason":"..."} — advisory: wait for a dependency.
+- {"action":"wait","target":"<id>","reason":"..."} — advisory only (logged; no scheduling effect): you are waiting for a dependency.
+- {"action":"continue","childId":"<childId>","reason":"..."} — advisory only (logged): continuation of an in-flight child is code-driven; this never re-dispatches anything.
+- {"action":"stop","childId":"<childId>","reason":"..."} — advisory only (logged; it does NOT stop anyone). To actually stop a child use `interrupt` with a live childId.
 
 HARD RULES: never re-schedule verified objects; problems with 依赖未就绪 (依赖就绪=false) should wait unless you explicitly accept a temporary assumption; respect capacity (brief.free_slots); PREFER problems whose dependencies are ready and whose directions have the highest survival; DO NOT forget verification — unresolved solutions/proofs/refutations (verify_candidates) will never be checked unless you schedule a verifier; DO NOT assume a direction is already being worked just because it is shown "active" in a problem — check brief.problems[].running_solver_dirs and brief.active_agents: schedule a solver for a direction ONLY if that direction is NOT in running_solver_dirs (an "active" direction absent from running_solver_dirs is WAITING to be dispatched, not being worked); schedule at most 3 actions.
 Respond with ONLY a single JSON object wrapped in a ```json code fence — no prose:
@@ -5054,7 +5102,7 @@ Citations: facts may only be cited from Verified/ (or Propos/ 状态: 已验证
     请复核这个判断是否成立；若你认为其实可以形式化，请指出来并动手做。
 - math_computation：本机可用 （无）。需要数值/符号/统计计算时先 probe 再 run（工具路径会留下可复核回执，结论请引用回执路径）；缺包时如实说明并给替代方案或安装计划（不要假装），安装需先出计划并征得确认。
 - shell 兜底标注：工具不可用而改用宿主 shell 时，结论必须写"未经工具归档（shell 路径）"，且不得与工具回执混同（shell 无回执、无超时/输出上限保证）。
-- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以打开它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）；编辑后用 mode:'file' 指向它重跑，会写出一份**新回执/新 attempt**（含新的 scriptHash）。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
+- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以读它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）。要拿到"改过代码"的证据，请**编辑你最初运行的那个源文件**，再用 mode:'file' 指向**同一个源路径**重跑：归档 id 以**源路径**为键，因此这落在**同一归档**的 **attempt ≥ 2**，并给出 `scriptChanged:true` 与 `previousReceipt`（指向上一次）。**指向归档副本本身**（`receipt.scriptAbs` 那个路径）按设计是**另一份新归档**：新 id、attempt 1、没有 `previousReceipt`、`scriptChanged:false`；旧 attempt 绝不会被覆盖，但它**不是**"同一归档的新 attempt"——工具会用 `fileIsArchivedScript` 与 `ARCHIVED_SCRIPT_RERUN` 警告明确说明。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
 - 需要精确数值、符号化简、反例搜索、统计或线性代数时调用 math_computation：先 probe，再 run。
 - 复核他人的数值结论时用 op:'receipt'（或 op:'run', mode:'file' 指向同一脚本）重跑，并把回执路径写进报告。
 - 归档即引用：报告里带 Computation/<id>/receipt.json；这是"支撑材料"的用法。
@@ -5117,7 +5165,7 @@ Citations: facts may only be cited from Verified/ (or Propos/ 状态: 已验证
     请复核这个判断是否成立；若你认为其实可以形式化，请指出来并动手做。
 - math_computation：本机可用 （无）。需要数值/符号/统计计算时先 probe 再 run（工具路径会留下可复核回执，结论请引用回执路径）；缺包时如实说明并给替代方案或安装计划（不要假装），安装需先出计划并征得确认。
 - shell 兜底标注：工具不可用而改用宿主 shell 时，结论必须写"未经工具归档（shell 路径）"，且不得与工具回执混同（shell 无回执、无超时/输出上限保证）。
-- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以打开它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）；编辑后用 mode:'file' 指向它重跑，会写出一份**新回执/新 attempt**（含新的 scriptHash）。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
+- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以读它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）。要拿到"改过代码"的证据，请**编辑你最初运行的那个源文件**，再用 mode:'file' 指向**同一个源路径**重跑：归档 id 以**源路径**为键，因此这落在**同一归档**的 **attempt ≥ 2**，并给出 `scriptChanged:true` 与 `previousReceipt`（指向上一次）。**指向归档副本本身**（`receipt.scriptAbs` 那个路径）按设计是**另一份新归档**：新 id、attempt 1、没有 `previousReceipt`、`scriptChanged:false`；旧 attempt 绝不会被覆盖，但它**不是**"同一归档的新 attempt"——工具会用 `fileIsArchivedScript` 与 `ARCHIVED_SCRIPT_RERUN` 警告明确说明。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
 - 需要精确数值、符号化简、反例搜索、统计或线性代数时调用 math_computation：先 probe，再 run。
 - 复核他人的数值结论时用 op:'receipt'（或 op:'run', mode:'file' 指向同一脚本）重跑，并把回执路径写进报告。
 - 归档即引用：报告里带 Computation/<id>/receipt.json；这是"支撑材料"的用法。
@@ -5174,7 +5222,7 @@ feasibility ∈ [0,1] = your estimate of the probability this direction leads to
 {"meta":{"kind":"directions","qid":"<qid>","directions":[{"id":"d1","title":"...","method":"...","core_assumption":"...","feasibility":0.5}],"methods_used":[{"id":"m-...","效果":"<为何该方向借鉴它>","建议":"..."}],"new_inventions":[{"类型":"方法|工具|...","标题":"...","内容描述":"...","是否已入库":false}]}}
 - math_computation：本机可用 （无）。需要数值/符号/统计计算时先 probe 再 run（工具路径会留下可复核回执，结论请引用回执路径）；缺包时如实说明并给替代方案或安装计划（不要假装），安装需先出计划并征得确认。
 - shell 兜底标注：工具不可用而改用宿主 shell 时，结论必须写"未经工具归档（shell 路径）"，且不得与工具回执混同（shell 无回执、无超时/输出上限保证）。
-- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以打开它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）；编辑后用 mode:'file' 指向它重跑，会写出一份**新回执/新 attempt**（含新的 scriptHash）。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
+- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以读它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）。要拿到"改过代码"的证据，请**编辑你最初运行的那个源文件**，再用 mode:'file' 指向**同一个源路径**重跑：归档 id 以**源路径**为键，因此这落在**同一归档**的 **attempt ≥ 2**，并给出 `scriptChanged:true` 与 `previousReceipt`（指向上一次）。**指向归档副本本身**（`receipt.scriptAbs` 那个路径）按设计是**另一份新归档**：新 id、attempt 1、没有 `previousReceipt`、`scriptChanged:false`；旧 attempt 绝不会被覆盖，但它**不是**"同一归档的新 attempt"——工具会用 `fileIsArchivedScript` 与 `ARCHIVED_SCRIPT_RERUN` 警告明确说明。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
 - 需要精确数值、符号化简、反例搜索、统计或线性代数时调用 math_computation：先 probe，再 run。
 - 复核他人的数值结论时用 op:'receipt'（或 op:'run', mode:'file' 指向同一脚本）重跑，并把回执路径写进报告。
 - 归档即引用：报告里带 Computation/<id>/receipt.json；这是"支撑材料"的用法。
@@ -5211,14 +5259,16 @@ CURRENT STATE BRIEF (JSON):
   "recent_events": "<RECENT_EVENTS>"
 }
 
-ACTION VOCABULARY (code validates every action against hard invariants; invalid actions are dropped):
+ACTION VOCABULARY — the code ACCEPTS exactly these 6 actions: spawn / interrupt / promote are HARD-VALIDATED (invalid ones are dropped), while wait / continue / stop are ADVISORY ONLY (they are logged and have NO scheduling effect):
 - {"action":"spawn","role":"explorer","target":"<qid>","reason":"..."} — problem has no directions yet or all dead (re-derive).
 - {"action":"spawn","role":"solver","target":"<qid>","direction":"<dirId>","reason":"..."} — active direction, needs a solving round.
 - {"action":"spawn","role":"verifier","target":"<rId>","reason":"..."} — verify candidate (from verify_candidates); keep solving AND verifying balanced.
 - {"action":"spawn","role":"method-keeper","reason":"..."} — distill pending inventions / maintain the theory library.
 - {"action":"interrupt","childId":"<childId>","reason":"..."} — stop a running child (direction dead, superseded...).
 - {"action":"promote","target":"<pId>","reason":"..."} — high-value unresolved proposition → judge problem.
-- {"action":"wait","target":"<id>","reason":"..."} — advisory: wait for a dependency.
+- {"action":"wait","target":"<id>","reason":"..."} — advisory only (logged; no scheduling effect): you are waiting for a dependency.
+- {"action":"continue","childId":"<childId>","reason":"..."} — advisory only (logged): continuation of an in-flight child is code-driven; this never re-dispatches anything.
+- {"action":"stop","childId":"<childId>","reason":"..."} — advisory only (logged; it does NOT stop anyone). To actually stop a child use `interrupt` with a live childId.
 
 HARD RULES: never re-schedule verified objects; problems with 依赖未就绪 (依赖就绪=false) should wait unless you explicitly accept a temporary assumption; respect capacity (brief.free_slots); PREFER problems whose dependencies are ready and whose directions have the highest survival; DO NOT forget verification — unresolved solutions/proofs/refutations (verify_candidates) will never be checked unless you schedule a verifier; DO NOT assume a direction is already being worked just because it is shown "active" in a problem — check brief.problems[].running_solver_dirs and brief.active_agents: schedule a solver for a direction ONLY if that direction is NOT in running_solver_dirs (an "active" direction absent from running_solver_dirs is WAITING to be dispatched, not being worked); schedule at most 3 actions.
 Respond with ONLY a single JSON object wrapped in a ```json code fence — no prose:
@@ -5269,7 +5319,7 @@ feasibility ∈ [0,1] = your estimate of the probability this direction leads to
 {"meta":{"kind":"directions","qid":"<qid>","directions":[{"id":"d1","title":"...","method":"...","core_assumption":"...","feasibility":0.5}],"methods_used":[{"id":"m-...","效果":"<为何该方向借鉴它>","建议":"..."}],"new_inventions":[{"类型":"方法|工具|...","标题":"...","内容描述":"...","是否已入库":false}]}}
 - math_computation：本机可用 （无）。需要数值/符号/统计计算时先 probe 再 run（工具路径会留下可复核回执，结论请引用回执路径）；缺包时如实说明并给替代方案或安装计划（不要假装），安装需先出计划并征得确认。
 - shell 兜底标注：工具不可用而改用宿主 shell 时，结论必须写"未经工具归档（shell 路径）"，且不得与工具回执混同（shell 无回执、无超时/输出上限保证）。
-- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以打开它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）；编辑后用 mode:'file' 指向它重跑，会写出一份**新回执/新 attempt**（含新的 scriptHash）。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
+- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以读它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）。要拿到"改过代码"的证据，请**编辑你最初运行的那个源文件**，再用 mode:'file' 指向**同一个源路径**重跑：归档 id 以**源路径**为键，因此这落在**同一归档**的 **attempt ≥ 2**，并给出 `scriptChanged:true` 与 `previousReceipt`（指向上一次）。**指向归档副本本身**（`receipt.scriptAbs` 那个路径）按设计是**另一份新归档**：新 id、attempt 1、没有 `previousReceipt`、`scriptChanged:false`；旧 attempt 绝不会被覆盖，但它**不是**"同一归档的新 attempt"——工具会用 `fileIsArchivedScript` 与 `ARCHIVED_SCRIPT_RERUN` 警告明确说明。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
 - 需要精确数值、符号化简、反例搜索、统计或线性代数时调用 math_computation：先 probe，再 run。
 - 复核他人的数值结论时用 op:'receipt'（或 op:'run', mode:'file' 指向同一脚本）重跑，并把回执路径写进报告。
 - 归档即引用：报告里带 Computation/<id>/receipt.json；这是"支撑材料"的用法。
@@ -5306,14 +5356,16 @@ CURRENT STATE BRIEF (JSON):
   "recent_events": "<RECENT_EVENTS>"
 }
 
-ACTION VOCABULARY (code validates every action against hard invariants; invalid actions are dropped):
+ACTION VOCABULARY — the code ACCEPTS exactly these 6 actions: spawn / interrupt / promote are HARD-VALIDATED (invalid ones are dropped), while wait / continue / stop are ADVISORY ONLY (they are logged and have NO scheduling effect):
 - {"action":"spawn","role":"explorer","target":"<qid>","reason":"..."} — problem has no directions yet or all dead (re-derive).
 - {"action":"spawn","role":"solver","target":"<qid>","direction":"<dirId>","reason":"..."} — active direction, needs a solving round.
 - {"action":"spawn","role":"verifier","target":"<rId>","reason":"..."} — verify candidate (from verify_candidates); keep solving AND verifying balanced.
 - {"action":"spawn","role":"method-keeper","reason":"..."} — distill pending inventions / maintain the theory library.
 - {"action":"interrupt","childId":"<childId>","reason":"..."} — stop a running child (direction dead, superseded...).
 - {"action":"promote","target":"<pId>","reason":"..."} — high-value unresolved proposition → judge problem.
-- {"action":"wait","target":"<id>","reason":"..."} — advisory: wait for a dependency.
+- {"action":"wait","target":"<id>","reason":"..."} — advisory only (logged; no scheduling effect): you are waiting for a dependency.
+- {"action":"continue","childId":"<childId>","reason":"..."} — advisory only (logged): continuation of an in-flight child is code-driven; this never re-dispatches anything.
+- {"action":"stop","childId":"<childId>","reason":"..."} — advisory only (logged; it does NOT stop anyone). To actually stop a child use `interrupt` with a live childId.
 
 HARD RULES: never re-schedule verified objects; problems with 依赖未就绪 (依赖就绪=false) should wait unless you explicitly accept a temporary assumption; respect capacity (brief.free_slots); PREFER problems whose dependencies are ready and whose directions have the highest survival; DO NOT forget verification — unresolved solutions/proofs/refutations (verify_candidates) will never be checked unless you schedule a verifier; DO NOT assume a direction is already being worked just because it is shown "active" in a problem — check brief.problems[].running_solver_dirs and brief.active_agents: schedule a solver for a direction ONLY if that direction is NOT in running_solver_dirs (an "active" direction absent from running_solver_dirs is WAITING to be dispatched, not being worked); schedule at most 3 actions.
 Respond with ONLY a single JSON object wrapped in a ```json code fence — no prose:
@@ -5364,7 +5416,7 @@ feasibility ∈ [0,1] = your estimate of the probability this direction leads to
 {"meta":{"kind":"directions","qid":"<qid>","directions":[{"id":"d1","title":"...","method":"...","core_assumption":"...","feasibility":0.5}],"methods_used":[{"id":"m-...","效果":"<为何该方向借鉴它>","建议":"..."}],"new_inventions":[{"类型":"方法|工具|...","标题":"...","内容描述":"...","是否已入库":false}]}}
 - math_computation：本机可用 （无）。需要数值/符号/统计计算时先 probe 再 run（工具路径会留下可复核回执，结论请引用回执路径）；缺包时如实说明并给替代方案或安装计划（不要假装），安装需先出计划并征得确认。
 - shell 兜底标注：工具不可用而改用宿主 shell 时，结论必须写"未经工具归档（shell 路径）"，且不得与工具回执混同（shell 无回执、无超时/输出上限保证）。
-- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以打开它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）；编辑后用 mode:'file' 指向它重跑，会写出一份**新回执/新 attempt**（含新的 scriptHash）。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
+- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以读它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）。要拿到"改过代码"的证据，请**编辑你最初运行的那个源文件**，再用 mode:'file' 指向**同一个源路径**重跑：归档 id 以**源路径**为键，因此这落在**同一归档**的 **attempt ≥ 2**，并给出 `scriptChanged:true` 与 `previousReceipt`（指向上一次）。**指向归档副本本身**（`receipt.scriptAbs` 那个路径）按设计是**另一份新归档**：新 id、attempt 1、没有 `previousReceipt`、`scriptChanged:false`；旧 attempt 绝不会被覆盖，但它**不是**"同一归档的新 attempt"——工具会用 `fileIsArchivedScript` 与 `ARCHIVED_SCRIPT_RERUN` 警告明确说明。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
 - 需要精确数值、符号化简、反例搜索、统计或线性代数时调用 math_computation：先 probe，再 run。
 - 复核他人的数值结论时用 op:'receipt'（或 op:'run', mode:'file' 指向同一脚本）重跑，并把回执路径写进报告。
 - 归档即引用：报告里带 Computation/<id>/receipt.json；这是"支撑材料"的用法。
@@ -5395,14 +5447,16 @@ CURRENT STATE BRIEF (JSON):
   "recent_events": "<RECENT_EVENTS>"
 }
 
-ACTION VOCABULARY (code validates every action against hard invariants; invalid actions are dropped):
+ACTION VOCABULARY — the code ACCEPTS exactly these 6 actions: spawn / interrupt / promote are HARD-VALIDATED (invalid ones are dropped), while wait / continue / stop are ADVISORY ONLY (they are logged and have NO scheduling effect):
 - {"action":"spawn","role":"explorer","target":"<qid>","reason":"..."} — problem has no directions yet or all dead (re-derive).
 - {"action":"spawn","role":"solver","target":"<qid>","direction":"<dirId>","reason":"..."} — active direction, needs a solving round.
 - {"action":"spawn","role":"verifier","target":"<rId>","reason":"..."} — verify candidate (from verify_candidates); keep solving AND verifying balanced.
 - {"action":"spawn","role":"method-keeper","reason":"..."} — distill pending inventions / maintain the theory library.
 - {"action":"interrupt","childId":"<childId>","reason":"..."} — stop a running child (direction dead, superseded...).
 - {"action":"promote","target":"<pId>","reason":"..."} — high-value unresolved proposition → judge problem.
-- {"action":"wait","target":"<id>","reason":"..."} — advisory: wait for a dependency.
+- {"action":"wait","target":"<id>","reason":"..."} — advisory only (logged; no scheduling effect): you are waiting for a dependency.
+- {"action":"continue","childId":"<childId>","reason":"..."} — advisory only (logged): continuation of an in-flight child is code-driven; this never re-dispatches anything.
+- {"action":"stop","childId":"<childId>","reason":"..."} — advisory only (logged; it does NOT stop anyone). To actually stop a child use `interrupt` with a live childId.
 
 HARD RULES: never re-schedule verified objects; problems with 依赖未就绪 (依赖就绪=false) should wait unless you explicitly accept a temporary assumption; respect capacity (brief.free_slots); PREFER problems whose dependencies are ready and whose directions have the highest survival; DO NOT forget verification — unresolved solutions/proofs/refutations (verify_candidates) will never be checked unless you schedule a verifier; DO NOT assume a direction is already being worked just because it is shown "active" in a problem — check brief.problems[].running_solver_dirs and brief.active_agents: schedule a solver for a direction ONLY if that direction is NOT in running_solver_dirs (an "active" direction absent from running_solver_dirs is WAITING to be dispatched, not being worked); schedule at most 3 actions.
 Respond with ONLY a single JSON object wrapped in a ```json code fence — no prose:
@@ -5453,7 +5507,7 @@ feasibility ∈ [0,1] = your estimate of the probability this direction leads to
 {"meta":{"kind":"directions","qid":"<qid>","directions":[{"id":"d1","title":"...","method":"...","core_assumption":"...","feasibility":0.5}],"methods_used":[{"id":"m-...","效果":"<为何该方向借鉴它>","建议":"..."}],"new_inventions":[{"类型":"方法|工具|...","标题":"...","内容描述":"...","是否已入库":false}]}}
 - math_computation：本机可用 （无）。需要数值/符号/统计计算时先 probe 再 run（工具路径会留下可复核回执，结论请引用回执路径）；缺包时如实说明并给替代方案或安装计划（不要假装），安装需先出计划并征得确认。
 - shell 兜底标注：工具不可用而改用宿主 shell 时，结论必须写"未经工具归档（shell 路径）"，且不得与工具回执混同（shell 无回执、无超时/输出上限保证）。
-- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以打开它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）；编辑后用 mode:'file' 指向它重跑，会写出一份**新回执/新 attempt**（含新的 scriptHash）。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
+- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以读它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）。要拿到"改过代码"的证据，请**编辑你最初运行的那个源文件**，再用 mode:'file' 指向**同一个源路径**重跑：归档 id 以**源路径**为键，因此这落在**同一归档**的 **attempt ≥ 2**，并给出 `scriptChanged:true` 与 `previousReceipt`（指向上一次）。**指向归档副本本身**（`receipt.scriptAbs` 那个路径）按设计是**另一份新归档**：新 id、attempt 1、没有 `previousReceipt`、`scriptChanged:false`；旧 attempt 绝不会被覆盖，但它**不是**"同一归档的新 attempt"——工具会用 `fileIsArchivedScript` 与 `ARCHIVED_SCRIPT_RERUN` 警告明确说明。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
 - 需要精确数值、符号化简、反例搜索、统计或线性代数时调用 math_computation：先 probe，再 run。
 - 复核他人的数值结论时用 op:'receipt'（或 op:'run', mode:'file' 指向同一脚本）重跑，并把回执路径写进报告。
 - 归档即引用：报告里带 Computation/<id>/receipt.json；这是"支撑材料"的用法。
@@ -5489,14 +5543,16 @@ CURRENT STATE BRIEF (JSON):
   "recent_events": "<RECENT_EVENTS>"
 }
 
-ACTION VOCABULARY (code validates every action against hard invariants; invalid actions are dropped):
+ACTION VOCABULARY — the code ACCEPTS exactly these 6 actions: spawn / interrupt / promote are HARD-VALIDATED (invalid ones are dropped), while wait / continue / stop are ADVISORY ONLY (they are logged and have NO scheduling effect):
 - {"action":"spawn","role":"explorer","target":"<qid>","reason":"..."} — problem has no directions yet or all dead (re-derive).
 - {"action":"spawn","role":"solver","target":"<qid>","direction":"<dirId>","reason":"..."} — active direction, needs a solving round.
 - {"action":"spawn","role":"verifier","target":"<rId>","reason":"..."} — verify candidate (from verify_candidates); keep solving AND verifying balanced.
 - {"action":"spawn","role":"method-keeper","reason":"..."} — distill pending inventions / maintain the theory library.
 - {"action":"interrupt","childId":"<childId>","reason":"..."} — stop a running child (direction dead, superseded...).
 - {"action":"promote","target":"<pId>","reason":"..."} — high-value unresolved proposition → judge problem.
-- {"action":"wait","target":"<id>","reason":"..."} — advisory: wait for a dependency.
+- {"action":"wait","target":"<id>","reason":"..."} — advisory only (logged; no scheduling effect): you are waiting for a dependency.
+- {"action":"continue","childId":"<childId>","reason":"..."} — advisory only (logged): continuation of an in-flight child is code-driven; this never re-dispatches anything.
+- {"action":"stop","childId":"<childId>","reason":"..."} — advisory only (logged; it does NOT stop anyone). To actually stop a child use `interrupt` with a live childId.
 
 HARD RULES: never re-schedule verified objects; problems with 依赖未就绪 (依赖就绪=false) should wait unless you explicitly accept a temporary assumption; respect capacity (brief.free_slots); PREFER problems whose dependencies are ready and whose directions have the highest survival; DO NOT forget verification — unresolved solutions/proofs/refutations (verify_candidates) will never be checked unless you schedule a verifier; DO NOT assume a direction is already being worked just because it is shown "active" in a problem — check brief.problems[].running_solver_dirs and brief.active_agents: schedule a solver for a direction ONLY if that direction is NOT in running_solver_dirs (an "active" direction absent from running_solver_dirs is WAITING to be dispatched, not being worked); schedule at most 3 actions.
 Respond with ONLY a single JSON object wrapped in a ```json code fence — no prose:
@@ -5547,7 +5603,7 @@ feasibility ∈ [0,1] = your estimate of the probability this direction leads to
 {"meta":{"kind":"directions","qid":"<qid>","directions":[{"id":"d1","title":"...","method":"...","core_assumption":"...","feasibility":0.5}],"methods_used":[{"id":"m-...","效果":"<为何该方向借鉴它>","建议":"..."}],"new_inventions":[{"类型":"方法|工具|...","标题":"...","内容描述":"...","是否已入库":false}]}}
 - math_computation：本机可用 （无）。需要数值/符号/统计计算时先 probe 再 run（工具路径会留下可复核回执，结论请引用回执路径）；缺包时如实说明并给替代方案或安装计划（不要假装），安装需先出计划并征得确认。
 - shell 兜底标注：工具不可用而改用宿主 shell 时，结论必须写"未经工具归档（shell 路径）"，且不得与工具回执混同（shell 无回执、无超时/输出上限保证）。
-- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以打开它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）；编辑后用 mode:'file' 指向它重跑，会写出一份**新回执/新 attempt**（含新的 scriptHash）。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
+- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以读它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）。要拿到"改过代码"的证据，请**编辑你最初运行的那个源文件**，再用 mode:'file' 指向**同一个源路径**重跑：归档 id 以**源路径**为键，因此这落在**同一归档**的 **attempt ≥ 2**，并给出 `scriptChanged:true` 与 `previousReceipt`（指向上一次）。**指向归档副本本身**（`receipt.scriptAbs` 那个路径）按设计是**另一份新归档**：新 id、attempt 1、没有 `previousReceipt`、`scriptChanged:false`；旧 attempt 绝不会被覆盖，但它**不是**"同一归档的新 attempt"——工具会用 `fileIsArchivedScript` 与 `ARCHIVED_SCRIPT_RERUN` 警告明确说明。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
 - 需要精确数值、符号化简、反例搜索、统计或线性代数时调用 math_computation：先 probe，再 run。
 - 复核他人的数值结论时用 op:'receipt'（或 op:'run', mode:'file' 指向同一脚本）重跑，并把回执路径写进报告。
 - 归档即引用：报告里带 Computation/<id>/receipt.json；这是"支撑材料"的用法。
@@ -5583,14 +5639,16 @@ CURRENT STATE BRIEF (JSON):
   "recent_events": "<RECENT_EVENTS>"
 }
 
-ACTION VOCABULARY (code validates every action against hard invariants; invalid actions are dropped):
+ACTION VOCABULARY — the code ACCEPTS exactly these 6 actions: spawn / interrupt / promote are HARD-VALIDATED (invalid ones are dropped), while wait / continue / stop are ADVISORY ONLY (they are logged and have NO scheduling effect):
 - {"action":"spawn","role":"explorer","target":"<qid>","reason":"..."} — problem has no directions yet or all dead (re-derive).
 - {"action":"spawn","role":"solver","target":"<qid>","direction":"<dirId>","reason":"..."} — active direction, needs a solving round.
 - {"action":"spawn","role":"verifier","target":"<rId>","reason":"..."} — verify candidate (from verify_candidates); keep solving AND verifying balanced.
 - {"action":"spawn","role":"method-keeper","reason":"..."} — distill pending inventions / maintain the theory library.
 - {"action":"interrupt","childId":"<childId>","reason":"..."} — stop a running child (direction dead, superseded...).
 - {"action":"promote","target":"<pId>","reason":"..."} — high-value unresolved proposition → judge problem.
-- {"action":"wait","target":"<id>","reason":"..."} — advisory: wait for a dependency.
+- {"action":"wait","target":"<id>","reason":"..."} — advisory only (logged; no scheduling effect): you are waiting for a dependency.
+- {"action":"continue","childId":"<childId>","reason":"..."} — advisory only (logged): continuation of an in-flight child is code-driven; this never re-dispatches anything.
+- {"action":"stop","childId":"<childId>","reason":"..."} — advisory only (logged; it does NOT stop anyone). To actually stop a child use `interrupt` with a live childId.
 
 HARD RULES: never re-schedule verified objects; problems with 依赖未就绪 (依赖就绪=false) should wait unless you explicitly accept a temporary assumption; respect capacity (brief.free_slots); PREFER problems whose dependencies are ready and whose directions have the highest survival; DO NOT forget verification — unresolved solutions/proofs/refutations (verify_candidates) will never be checked unless you schedule a verifier; DO NOT assume a direction is already being worked just because it is shown "active" in a problem — check brief.problems[].running_solver_dirs and brief.active_agents: schedule a solver for a direction ONLY if that direction is NOT in running_solver_dirs (an "active" direction absent from running_solver_dirs is WAITING to be dispatched, not being worked); schedule at most 3 actions.
 Respond with ONLY a single JSON object wrapped in a ```json code fence — no prose:
@@ -5672,7 +5730,7 @@ CHANNEL B (your file tools are unavailable): put the content you would have writ
 区分规则：methods_used 只能填**已存在的方法卡 ID**（m-…，来自 AVAILABLE METHODS 列表）——引用你自己刚想出的新方法/新技巧不属于 methods_used，请如实填入 new_inventions（它会由 Method Keeper 蒸馏建卡）；不要把方法名/标题当 id 填进 methods_used。
 - math_computation：本机可用 （无）。需要数值/符号/统计计算时先 probe 再 run（工具路径会留下可复核回执，结论请引用回执路径）；缺包时如实说明并给替代方案或安装计划（不要假装），安装需先出计划并征得确认。
 - shell 兜底标注：工具不可用而改用宿主 shell 时，结论必须写"未经工具归档（shell 路径）"，且不得与工具回执混同（shell 无回执、无超时/输出上限保证）。
-- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以打开它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）；编辑后用 mode:'file' 指向它重跑，会写出一份**新回执/新 attempt**（含新的 scriptHash）。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
+- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以读它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）。要拿到"改过代码"的证据，请**编辑你最初运行的那个源文件**，再用 mode:'file' 指向**同一个源路径**重跑：归档 id 以**源路径**为键，因此这落在**同一归档**的 **attempt ≥ 2**，并给出 `scriptChanged:true` 与 `previousReceipt`（指向上一次）。**指向归档副本本身**（`receipt.scriptAbs` 那个路径）按设计是**另一份新归档**：新 id、attempt 1、没有 `previousReceipt`、`scriptChanged:false`；旧 attempt 绝不会被覆盖，但它**不是**"同一归档的新 attempt"——工具会用 `fileIsArchivedScript` 与 `ARCHIVED_SCRIPT_RERUN` 警告明确说明。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
 - 需要精确数值、符号化简、反例搜索、统计或线性代数时调用 math_computation：先 probe，再 run。
 - 复核他人的数值结论时用 op:'receipt'（或 op:'run', mode:'file' 指向同一脚本）重跑，并把回执路径写进报告。
 - 归档即引用：报告里带 Computation/<id>/receipt.json；这是"支撑材料"的用法。
@@ -5708,14 +5766,16 @@ CURRENT STATE BRIEF (JSON):
   "recent_events": "<RECENT_EVENTS>"
 }
 
-ACTION VOCABULARY (code validates every action against hard invariants; invalid actions are dropped):
+ACTION VOCABULARY — the code ACCEPTS exactly these 6 actions: spawn / interrupt / promote are HARD-VALIDATED (invalid ones are dropped), while wait / continue / stop are ADVISORY ONLY (they are logged and have NO scheduling effect):
 - {"action":"spawn","role":"explorer","target":"<qid>","reason":"..."} — problem has no directions yet or all dead (re-derive).
 - {"action":"spawn","role":"solver","target":"<qid>","direction":"<dirId>","reason":"..."} — active direction, needs a solving round.
 - {"action":"spawn","role":"verifier","target":"<rId>","reason":"..."} — verify candidate (from verify_candidates); keep solving AND verifying balanced.
 - {"action":"spawn","role":"method-keeper","reason":"..."} — distill pending inventions / maintain the theory library.
 - {"action":"interrupt","childId":"<childId>","reason":"..."} — stop a running child (direction dead, superseded...).
 - {"action":"promote","target":"<pId>","reason":"..."} — high-value unresolved proposition → judge problem.
-- {"action":"wait","target":"<id>","reason":"..."} — advisory: wait for a dependency.
+- {"action":"wait","target":"<id>","reason":"..."} — advisory only (logged; no scheduling effect): you are waiting for a dependency.
+- {"action":"continue","childId":"<childId>","reason":"..."} — advisory only (logged): continuation of an in-flight child is code-driven; this never re-dispatches anything.
+- {"action":"stop","childId":"<childId>","reason":"..."} — advisory only (logged; it does NOT stop anyone). To actually stop a child use `interrupt` with a live childId.
 
 HARD RULES: never re-schedule verified objects; problems with 依赖未就绪 (依赖就绪=false) should wait unless you explicitly accept a temporary assumption; respect capacity (brief.free_slots); PREFER problems whose dependencies are ready and whose directions have the highest survival; DO NOT forget verification — unresolved solutions/proofs/refutations (verify_candidates) will never be checked unless you schedule a verifier; DO NOT assume a direction is already being worked just because it is shown "active" in a problem — check brief.problems[].running_solver_dirs and brief.active_agents: schedule a solver for a direction ONLY if that direction is NOT in running_solver_dirs (an "active" direction absent from running_solver_dirs is WAITING to be dispatched, not being worked); schedule at most 3 actions.
 Respond with ONLY a single JSON object wrapped in a ```json code fence — no prose:
@@ -5769,7 +5829,7 @@ feasibility ∈ [0,1]. Respond with ONLY a single JSON object in a ```json code
 {"meta":{"kind":"directions","qid":"<qid>","directions":[{"id":"d1","title":"...","method":"...","core_assumption":"...","feasibility":0.5}],"methods_used":[{"id":"m-...","效果":"...","建议":"..."}],"new_inventions":[{"类型":"方法|工具|...","标题":"...","内容描述":"...","是否已入库":false}]}}
 - math_computation：本机可用 （无）。需要数值/符号/统计计算时先 probe 再 run（工具路径会留下可复核回执，结论请引用回执路径）；缺包时如实说明并给替代方案或安装计划（不要假装），安装需先出计划并征得确认。
 - shell 兜底标注：工具不可用而改用宿主 shell 时，结论必须写"未经工具归档（shell 路径）"，且不得与工具回执混同（shell 无回执、无超时/输出上限保证）。
-- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以打开它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）；编辑后用 mode:'file' 指向它重跑，会写出一份**新回执/新 attempt**（含新的 scriptHash）。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
+- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以读它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）。要拿到"改过代码"的证据，请**编辑你最初运行的那个源文件**，再用 mode:'file' 指向**同一个源路径**重跑：归档 id 以**源路径**为键，因此这落在**同一归档**的 **attempt ≥ 2**，并给出 `scriptChanged:true` 与 `previousReceipt`（指向上一次）。**指向归档副本本身**（`receipt.scriptAbs` 那个路径）按设计是**另一份新归档**：新 id、attempt 1、没有 `previousReceipt`、`scriptChanged:false`；旧 attempt 绝不会被覆盖，但它**不是**"同一归档的新 attempt"——工具会用 `fileIsArchivedScript` 与 `ARCHIVED_SCRIPT_RERUN` 警告明确说明。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
 - 需要精确数值、符号化简、反例搜索、统计或线性代数时调用 math_computation：先 probe，再 run。
 - 复核他人的数值结论时用 op:'receipt'（或 op:'run', mode:'file' 指向同一脚本）重跑，并把回执路径写进报告。
 - 归档即引用：报告里带 Computation/<id>/receipt.json；这是"支撑材料"的用法。
@@ -5829,7 +5889,7 @@ For each pending invention decide: create a NEW method card, or fold it into an
 
 - math_computation：本机可用 （无）。需要数值/符号/统计计算时先 probe 再 run（工具路径会留下可复核回执，结论请引用回执路径）；缺包时如实说明并给替代方案或安装计划（不要假装），安装需先出计划并征得确认。
 - shell 兜底标注：工具不可用而改用宿主 shell 时，结论必须写"未经工具归档（shell 路径）"，且不得与工具回执混同（shell 无回执、无超时/输出上限保证）。
-- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以打开它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）；编辑后用 mode:'file' 指向它重跑，会写出一份**新回执/新 attempt**（含新的 scriptHash）。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
+- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以读它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）。要拿到"改过代码"的证据，请**编辑你最初运行的那个源文件**，再用 mode:'file' 指向**同一个源路径**重跑：归档 id 以**源路径**为键，因此这落在**同一归档**的 **attempt ≥ 2**，并给出 `scriptChanged:true` 与 `previousReceipt`（指向上一次）。**指向归档副本本身**（`receipt.scriptAbs` 那个路径）按设计是**另一份新归档**：新 id、attempt 1、没有 `previousReceipt`、`scriptChanged:false`；旧 attempt 绝不会被覆盖，但它**不是**"同一归档的新 attempt"——工具会用 `fileIsArchivedScript` 与 `ARCHIVED_SCRIPT_RERUN` 警告明确说明。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
 - 需要精确数值、符号化简、反例搜索、统计或线性代数时调用 math_computation：先 probe，再 run。
 - 复核他人的数值结论时用 op:'receipt'（或 op:'run', mode:'file' 指向同一脚本）重跑，并把回执路径写进报告。
 - 归档即引用：报告里带 Computation/<id>/receipt.json；这是"支撑材料"的用法。
@@ -5842,7 +5902,7 @@ For each pending invention decide: create a NEW method card, or fold it into an
   · **先 vibe_math_lean_lib 查再决定是否重写**：vibe_math_lean_lib 列出现成定义/引理，vibe_math_lean_read 可取回归档原文逐字复用；复用已归档内容用 `import Formal.Lib.<name>` / `import Formal.Proved.<name>`（模块根 = <VIBEMATH>，框架已把它加进编译搜索路径）。
   · **没把握就记 blocked**（vibe_math_lean_archive kind='blocked' note=…，或回执 formal 的 blocked）：把难点写清楚，别用形式化掩盖不确定。
   · 编译默认走后台队列（leanAsync=true）：入队后你可以继续工作；用 vibe_math_lean_job（可 waitMs 等结果）或下一轮提示里的【形式化结果】行看结果。**在作业落地为通过之前，不得把该对象当成已通过。**OUTPUT CONTRACT — pick ONE channel. Write method cards into Markdown; only the created IDs, which cards were used, and improvements cross the machine reply.
-CHANNEL A (recommended, you can write files): write each method card into `Methods/<m-id>.md` (`# 方法｜标题` + `- 标题/ID/类型/状态/可信断言/适用场景` + `## 核心内容`/`## 应用记录`/`## 改进历史`), then reply ONLY this metadata:
+CHANNEL A (recommended, you can write files): write each method card into `Methods/<m-id>.md` — the `<m-id>` in the FILE NAME must be EXACTLY the id you list in `created`（调度器按 `created` 里的 id 去 `Methods/<id>.md` 找卡；不一致会被当成"已沉淀"而实际没有卡）(`# 方法｜标题` + `- 标题/ID/类型/状态/可信断言/适用场景` + `## 核心内容`/`## 应用记录`/`## 改进历史`), then reply ONLY this metadata:
 {"meta":{"kind":"methods","used":[{"id":"m-...","效果":"...","建议":"..."}],"created":["m-xxx"],"improvements":[{"id":"m-...","改进内容":"...","原因":"..."}]}}
 CHANNEL B (your file tools are unavailable): put the method-card content into __writes and carry the same meta:
 {"__writes":[{"path":"Methods/<m-id>.md","content":"<# 方法｜标题 + 锚点 + ## 核心内容... 完整卡面>"}],"meta":{"kind":"methods","used":[...],"created":["m-xxx"],"improvements":[...]}}
@@ -5892,7 +5952,7 @@ feasibility ∈ [0,1] = your estimate of the probability this direction leads to
 {"meta":{"kind":"directions","qid":"<qid>","directions":[{"id":"d1","title":"...","method":"...","core_assumption":"...","feasibility":0.5}],"methods_used":[{"id":"m-...","效果":"<为何该方向借鉴它>","建议":"..."}],"new_inventions":[{"类型":"方法|工具|...","标题":"...","内容描述":"...","是否已入库":false}]}}
 - math_computation：本机可用 （无）。需要数值/符号/统计计算时先 probe 再 run（工具路径会留下可复核回执，结论请引用回执路径）；缺包时如实说明并给替代方案或安装计划（不要假装），安装需先出计划并征得确认。
 - shell 兜底标注：工具不可用而改用宿主 shell 时，结论必须写"未经工具归档（shell 路径）"，且不得与工具回执混同（shell 无回执、无超时/输出上限保证）。
-- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以打开它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）；编辑后用 mode:'file' 指向它重跑，会写出一份**新回执/新 attempt**（含新的 scriptHash）。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
+- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以读它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）。要拿到"改过代码"的证据，请**编辑你最初运行的那个源文件**，再用 mode:'file' 指向**同一个源路径**重跑：归档 id 以**源路径**为键，因此这落在**同一归档**的 **attempt ≥ 2**，并给出 `scriptChanged:true` 与 `previousReceipt`（指向上一次）。**指向归档副本本身**（`receipt.scriptAbs` 那个路径）按设计是**另一份新归档**：新 id、attempt 1、没有 `previousReceipt`、`scriptChanged:false`；旧 attempt 绝不会被覆盖，但它**不是**"同一归档的新 attempt"——工具会用 `fileIsArchivedScript` 与 `ARCHIVED_SCRIPT_RERUN` 警告明确说明。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
 - 需要精确数值、符号化简、反例搜索、统计或线性代数时调用 math_computation：先 probe，再 run。
 - 复核他人的数值结论时用 op:'receipt'（或 op:'run', mode:'file' 指向同一脚本）重跑，并把回执路径写进报告。
 - 归档即引用：报告里带 Computation/<id>/receipt.json；这是"支撑材料"的用法。
@@ -5923,14 +5983,16 @@ CURRENT STATE BRIEF (JSON):
   "recent_events": "<RECENT_EVENTS>"
 }
 
-ACTION VOCABULARY (code validates every action against hard invariants; invalid actions are dropped):
+ACTION VOCABULARY — the code ACCEPTS exactly these 6 actions: spawn / interrupt / promote are HARD-VALIDATED (invalid ones are dropped), while wait / continue / stop are ADVISORY ONLY (they are logged and have NO scheduling effect):
 - {"action":"spawn","role":"explorer","target":"<qid>","reason":"..."} — problem has no directions yet or all dead (re-derive).
 - {"action":"spawn","role":"solver","target":"<qid>","direction":"<dirId>","reason":"..."} — active direction, needs a solving round.
 - {"action":"spawn","role":"verifier","target":"<rId>","reason":"..."} — verify candidate (from verify_candidates); keep solving AND verifying balanced.
 - {"action":"spawn","role":"method-keeper","reason":"..."} — distill pending inventions / maintain the theory library.
 - {"action":"interrupt","childId":"<childId>","reason":"..."} — stop a running child (direction dead, superseded...).
 - {"action":"promote","target":"<pId>","reason":"..."} — high-value unresolved proposition → judge problem.
-- {"action":"wait","target":"<id>","reason":"..."} — advisory: wait for a dependency.
+- {"action":"wait","target":"<id>","reason":"..."} — advisory only (logged; no scheduling effect): you are waiting for a dependency.
+- {"action":"continue","childId":"<childId>","reason":"..."} — advisory only (logged): continuation of an in-flight child is code-driven; this never re-dispatches anything.
+- {"action":"stop","childId":"<childId>","reason":"..."} — advisory only (logged; it does NOT stop anyone). To actually stop a child use `interrupt` with a live childId.
 
 HARD RULES: never re-schedule verified objects; problems with 依赖未就绪 (依赖就绪=false) should wait unless you explicitly accept a temporary assumption; respect capacity (brief.free_slots); PREFER problems whose dependencies are ready and whose directions have the highest survival; DO NOT forget verification — unresolved solutions/proofs/refutations (verify_candidates) will never be checked unless you schedule a verifier; DO NOT assume a direction is already being worked just because it is shown "active" in a problem — check brief.problems[].running_solver_dirs and brief.active_agents: schedule a solver for a direction ONLY if that direction is NOT in running_solver_dirs (an "active" direction absent from running_solver_dirs is WAITING to be dispatched, not being worked); schedule at most 3 actions.
 Respond with ONLY a single JSON object wrapped in a ```json code fence — no prose:
@@ -6012,7 +6074,7 @@ CHANNEL B (your file tools are unavailable): put the content you would have writ
 区分规则：methods_used 只能填**已存在的方法卡 ID**（m-…，来自 AVAILABLE METHODS 列表）——引用你自己刚想出的新方法/新技巧不属于 methods_used，请如实填入 new_inventions（它会由 Method Keeper 蒸馏建卡）；不要把方法名/标题当 id 填进 methods_used。
 - math_computation：本机可用 （无）。需要数值/符号/统计计算时先 probe 再 run（工具路径会留下可复核回执，结论请引用回执路径）；缺包时如实说明并给替代方案或安装计划（不要假装），安装需先出计划并征得确认。
 - shell 兜底标注：工具不可用而改用宿主 shell 时，结论必须写"未经工具归档（shell 路径）"，且不得与工具回执混同（shell 无回执、无超时/输出上限保证）。
-- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以打开它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）；编辑后用 mode:'file' 指向它重跑，会写出一份**新回执/新 attempt**（含新的 scriptHash）。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
+- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以读它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）。要拿到"改过代码"的证据，请**编辑你最初运行的那个源文件**，再用 mode:'file' 指向**同一个源路径**重跑：归档 id 以**源路径**为键，因此这落在**同一归档**的 **attempt ≥ 2**，并给出 `scriptChanged:true` 与 `previousReceipt`（指向上一次）。**指向归档副本本身**（`receipt.scriptAbs` 那个路径）按设计是**另一份新归档**：新 id、attempt 1、没有 `previousReceipt`、`scriptChanged:false`；旧 attempt 绝不会被覆盖，但它**不是**"同一归档的新 attempt"——工具会用 `fileIsArchivedScript` 与 `ARCHIVED_SCRIPT_RERUN` 警告明确说明。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
 - 需要精确数值、符号化简、反例搜索、统计或线性代数时调用 math_computation：先 probe，再 run。
 - 复核他人的数值结论时用 op:'receipt'（或 op:'run', mode:'file' 指向同一脚本）重跑，并把回执路径写进报告。
 - 归档即引用：报告里带 Computation/<id>/receipt.json；这是"支撑材料"的用法。
@@ -6043,14 +6105,16 @@ CURRENT STATE BRIEF (JSON):
   "recent_events": "<RECENT_EVENTS>"
 }
 
-ACTION VOCABULARY (code validates every action against hard invariants; invalid actions are dropped):
+ACTION VOCABULARY — the code ACCEPTS exactly these 6 actions: spawn / interrupt / promote are HARD-VALIDATED (invalid ones are dropped), while wait / continue / stop are ADVISORY ONLY (they are logged and have NO scheduling effect):
 - {"action":"spawn","role":"explorer","target":"<qid>","reason":"..."} — problem has no directions yet or all dead (re-derive).
 - {"action":"spawn","role":"solver","target":"<qid>","direction":"<dirId>","reason":"..."} — active direction, needs a solving round.
 - {"action":"spawn","role":"verifier","target":"<rId>","reason":"..."} — verify candidate (from verify_candidates); keep solving AND verifying balanced.
 - {"action":"spawn","role":"method-keeper","reason":"..."} — distill pending inventions / maintain the theory library.
 - {"action":"interrupt","childId":"<childId>","reason":"..."} — stop a running child (direction dead, superseded...).
 - {"action":"promote","target":"<pId>","reason":"..."} — high-value unresolved proposition → judge problem.
-- {"action":"wait","target":"<id>","reason":"..."} — advisory: wait for a dependency.
+- {"action":"wait","target":"<id>","reason":"..."} — advisory only (logged; no scheduling effect): you are waiting for a dependency.
+- {"action":"continue","childId":"<childId>","reason":"..."} — advisory only (logged): continuation of an in-flight child is code-driven; this never re-dispatches anything.
+- {"action":"stop","childId":"<childId>","reason":"..."} — advisory only (logged; it does NOT stop anyone). To actually stop a child use `interrupt` with a live childId.
 
 HARD RULES: never re-schedule verified objects; problems with 依赖未就绪 (依赖就绪=false) should wait unless you explicitly accept a temporary assumption; respect capacity (brief.free_slots); PREFER problems whose dependencies are ready and whose directions have the highest survival; DO NOT forget verification — unresolved solutions/proofs/refutations (verify_candidates) will never be checked unless you schedule a verifier; DO NOT assume a direction is already being worked just because it is shown "active" in a problem — check brief.problems[].running_solver_dirs and brief.active_agents: schedule a solver for a direction ONLY if that direction is NOT in running_solver_dirs (an "active" direction absent from running_solver_dirs is WAITING to be dispatched, not being worked); schedule at most 3 actions.
 Respond with ONLY a single JSON object wrapped in a ```json code fence — no prose:
@@ -6104,7 +6168,7 @@ feasibility ∈ [0,1]. Respond with ONLY a single JSON object in a ```json code
 {"meta":{"kind":"directions","qid":"<qid>","directions":[{"id":"d1","title":"...","method":"...","core_assumption":"...","feasibility":0.5}],"methods_used":[{"id":"m-...","效果":"...","建议":"..."}],"new_inventions":[{"类型":"方法|工具|...","标题":"...","内容描述":"...","是否已入库":false}]}}
 - math_computation：本机可用 （无）。需要数值/符号/统计计算时先 probe 再 run（工具路径会留下可复核回执，结论请引用回执路径）；缺包时如实说明并给替代方案或安装计划（不要假装），安装需先出计划并征得确认。
 - shell 兜底标注：工具不可用而改用宿主 shell 时，结论必须写"未经工具归档（shell 路径）"，且不得与工具回执混同（shell 无回执、无超时/输出上限保证）。
-- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以打开它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）；编辑后用 mode:'file' 指向它重跑，会写出一份**新回执/新 attempt**（含新的 scriptHash）。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
+- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以读它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）。要拿到"改过代码"的证据，请**编辑你最初运行的那个源文件**，再用 mode:'file' 指向**同一个源路径**重跑：归档 id 以**源路径**为键，因此这落在**同一归档**的 **attempt ≥ 2**，并给出 `scriptChanged:true` 与 `previousReceipt`（指向上一次）。**指向归档副本本身**（`receipt.scriptAbs` 那个路径）按设计是**另一份新归档**：新 id、attempt 1、没有 `previousReceipt`、`scriptChanged:false`；旧 attempt 绝不会被覆盖，但它**不是**"同一归档的新 attempt"——工具会用 `fileIsArchivedScript` 与 `ARCHIVED_SCRIPT_RERUN` 警告明确说明。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
 - 需要精确数值、符号化简、反例搜索、统计或线性代数时调用 math_computation：先 probe，再 run。
 - 复核他人的数值结论时用 op:'receipt'（或 op:'run', mode:'file' 指向同一脚本）重跑，并把回执路径写进报告。
 - 归档即引用：报告里带 Computation/<id>/receipt.json；这是"支撑材料"的用法。
@@ -6159,7 +6223,7 @@ For each pending invention decide: create a NEW method card, or fold it into an
 
 - math_computation：本机可用 （无）。需要数值/符号/统计计算时先 probe 再 run（工具路径会留下可复核回执，结论请引用回执路径）；缺包时如实说明并给替代方案或安装计划（不要假装），安装需先出计划并征得确认。
 - shell 兜底标注：工具不可用而改用宿主 shell 时，结论必须写"未经工具归档（shell 路径）"，且不得与工具回执混同（shell 无回执、无超时/输出上限保证）。
-- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以打开它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）；编辑后用 mode:'file' 指向它重跑，会写出一份**新回执/新 attempt**（含新的 scriptHash）。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
+- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以读它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）。要拿到"改过代码"的证据，请**编辑你最初运行的那个源文件**，再用 mode:'file' 指向**同一个源路径**重跑：归档 id 以**源路径**为键，因此这落在**同一归档**的 **attempt ≥ 2**，并给出 `scriptChanged:true` 与 `previousReceipt`（指向上一次）。**指向归档副本本身**（`receipt.scriptAbs` 那个路径）按设计是**另一份新归档**：新 id、attempt 1、没有 `previousReceipt`、`scriptChanged:false`；旧 attempt 绝不会被覆盖，但它**不是**"同一归档的新 attempt"——工具会用 `fileIsArchivedScript` 与 `ARCHIVED_SCRIPT_RERUN` 警告明确说明。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
 - 需要精确数值、符号化简、反例搜索、统计或线性代数时调用 math_computation：先 probe，再 run。
 - 复核他人的数值结论时用 op:'receipt'（或 op:'run', mode:'file' 指向同一脚本）重跑，并把回执路径写进报告。
 - 归档即引用：报告里带 Computation/<id>/receipt.json；这是"支撑材料"的用法。
@@ -6169,7 +6233,7 @@ For each pending invention decide: create a NEW method card, or fold it into an
 
 【方法沉淀 × Lean 形式化】除了方法卡，你沉淀的每个可复用对象 / 定义 / 假设都应当归档到全局 Lean 库（vibe_math_lean_archive kind='def'），已成立的引理归档到 Proved/（kind='lemma'）；归档时**连同定义与陈述一起写清**，方便后续直接 import。
 OUTPUT CONTRACT — pick ONE channel. Write method cards into Markdown; only the created IDs, which cards were used, and improvements cross the machine reply.
-CHANNEL A (recommended, you can write files): write each method card into `Methods/<m-id>.md` (`# 方法｜标题` + `- 标题/ID/类型/状态/可信断言/适用场景` + `## 核心内容`/`## 应用记录`/`## 改进历史`), then reply ONLY this metadata:
+CHANNEL A (recommended, you can write files): write each method card into `Methods/<m-id>.md` — the `<m-id>` in the FILE NAME must be EXACTLY the id you list in `created`（调度器按 `created` 里的 id 去 `Methods/<id>.md` 找卡；不一致会被当成"已沉淀"而实际没有卡）(`# 方法｜标题` + `- 标题/ID/类型/状态/可信断言/适用场景` + `## 核心内容`/`## 应用记录`/`## 改进历史`), then reply ONLY this metadata:
 {"meta":{"kind":"methods","used":[{"id":"m-...","效果":"...","建议":"..."}],"created":["m-xxx"],"improvements":[{"id":"m-...","改进内容":"...","原因":"..."}]}}
 CHANNEL B (your file tools are unavailable): put the method-card content into __writes and carry the same meta:
 {"__writes":[{"path":"Methods/<m-id>.md","content":"<# 方法｜标题 + 锚点 + ## 核心内容... 完整卡面>"}],"meta":{"kind":"methods","used":[...],"created":["m-xxx"],"improvements":[...]}}
@@ -6219,7 +6283,7 @@ feasibility ∈ [0,1] = your estimate of the probability this direction leads to
 {"meta":{"kind":"directions","qid":"<qid>","directions":[{"id":"d1","title":"...","method":"...","core_assumption":"...","feasibility":0.5}],"methods_used":[{"id":"m-...","效果":"<为何该方向借鉴它>","建议":"..."}],"new_inventions":[{"类型":"方法|工具|...","标题":"...","内容描述":"...","是否已入库":false}]}}
 - math_computation：本机可用 （无）。需要数值/符号/统计计算时先 probe 再 run（工具路径会留下可复核回执，结论请引用回执路径）；缺包时如实说明并给替代方案或安装计划（不要假装），安装需先出计划并征得确认。
 - shell 兜底标注：工具不可用而改用宿主 shell 时，结论必须写"未经工具归档（shell 路径）"，且不得与工具回执混同（shell 无回执、无超时/输出上限保证）。
-- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以打开它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）；编辑后用 mode:'file' 指向它重跑，会写出一份**新回执/新 attempt**（含新的 scriptHash）。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
+- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以读它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）。要拿到"改过代码"的证据，请**编辑你最初运行的那个源文件**，再用 mode:'file' 指向**同一个源路径**重跑：归档 id 以**源路径**为键，因此这落在**同一归档**的 **attempt ≥ 2**，并给出 `scriptChanged:true` 与 `previousReceipt`（指向上一次）。**指向归档副本本身**（`receipt.scriptAbs` 那个路径）按设计是**另一份新归档**：新 id、attempt 1、没有 `previousReceipt`、`scriptChanged:false`；旧 attempt 绝不会被覆盖，但它**不是**"同一归档的新 attempt"——工具会用 `fileIsArchivedScript` 与 `ARCHIVED_SCRIPT_RERUN` 警告明确说明。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
 - 需要精确数值、符号化简、反例搜索、统计或线性代数时调用 math_computation：先 probe，再 run。
 - 复核他人的数值结论时用 op:'receipt'（或 op:'run', mode:'file' 指向同一脚本）重跑，并把回执路径写进报告。
 - 归档即引用：报告里带 Computation/<id>/receipt.json；这是"支撑材料"的用法。
@@ -6250,14 +6314,16 @@ CURRENT STATE BRIEF (JSON):
   "recent_events": "<RECENT_EVENTS>"
 }
 
-ACTION VOCABULARY (code validates every action against hard invariants; invalid actions are dropped):
+ACTION VOCABULARY — the code ACCEPTS exactly these 6 actions: spawn / interrupt / promote are HARD-VALIDATED (invalid ones are dropped), while wait / continue / stop are ADVISORY ONLY (they are logged and have NO scheduling effect):
 - {"action":"spawn","role":"explorer","target":"<qid>","reason":"..."} — problem has no directions yet or all dead (re-derive).
 - {"action":"spawn","role":"solver","target":"<qid>","direction":"<dirId>","reason":"..."} — active direction, needs a solving round.
 - {"action":"spawn","role":"verifier","target":"<rId>","reason":"..."} — verify candidate (from verify_candidates); keep solving AND verifying balanced.
 - {"action":"spawn","role":"method-keeper","reason":"..."} — distill pending inventions / maintain the theory library.
 - {"action":"interrupt","childId":"<childId>","reason":"..."} — stop a running child (direction dead, superseded...).
 - {"action":"promote","target":"<pId>","reason":"..."} — high-value unresolved proposition → judge problem.
-- {"action":"wait","target":"<id>","reason":"..."} — advisory: wait for a dependency.
+- {"action":"wait","target":"<id>","reason":"..."} — advisory only (logged; no scheduling effect): you are waiting for a dependency.
+- {"action":"continue","childId":"<childId>","reason":"..."} — advisory only (logged): continuation of an in-flight child is code-driven; this never re-dispatches anything.
+- {"action":"stop","childId":"<childId>","reason":"..."} — advisory only (logged; it does NOT stop anyone). To actually stop a child use `interrupt` with a live childId.
 
 HARD RULES: never re-schedule verified objects; problems with 依赖未就绪 (依赖就绪=false) should wait unless you explicitly accept a temporary assumption; respect capacity (brief.free_slots); PREFER problems whose dependencies are ready and whose directions have the highest survival; DO NOT forget verification — unresolved solutions/proofs/refutations (verify_candidates) will never be checked unless you schedule a verifier; DO NOT assume a direction is already being worked just because it is shown "active" in a problem — check brief.problems[].running_solver_dirs and brief.active_agents: schedule a solver for a direction ONLY if that direction is NOT in running_solver_dirs (an "active" direction absent from running_solver_dirs is WAITING to be dispatched, not being worked); schedule at most 3 actions.
 Respond with ONLY a single JSON object wrapped in a ```json code fence — no prose:
@@ -6339,7 +6405,7 @@ CHANNEL B (your file tools are unavailable): put the content you would have writ
 区分规则：methods_used 只能填**已存在的方法卡 ID**（m-…，来自 AVAILABLE METHODS 列表）——引用你自己刚想出的新方法/新技巧不属于 methods_used，请如实填入 new_inventions（它会由 Method Keeper 蒸馏建卡）；不要把方法名/标题当 id 填进 methods_used。
 - math_computation：本机可用 （无）。需要数值/符号/统计计算时先 probe 再 run（工具路径会留下可复核回执，结论请引用回执路径）；缺包时如实说明并给替代方案或安装计划（不要假装），安装需先出计划并征得确认。
 - shell 兜底标注：工具不可用而改用宿主 shell 时，结论必须写"未经工具归档（shell 路径）"，且不得与工具回执混同（shell 无回执、无超时/输出上限保证）。
-- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以打开它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）；编辑后用 mode:'file' 指向它重跑，会写出一份**新回执/新 attempt**（含新的 scriptHash）。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
+- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以读它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）。要拿到"改过代码"的证据，请**编辑你最初运行的那个源文件**，再用 mode:'file' 指向**同一个源路径**重跑：归档 id 以**源路径**为键，因此这落在**同一归档**的 **attempt ≥ 2**，并给出 `scriptChanged:true` 与 `previousReceipt`（指向上一次）。**指向归档副本本身**（`receipt.scriptAbs` 那个路径）按设计是**另一份新归档**：新 id、attempt 1、没有 `previousReceipt`、`scriptChanged:false`；旧 attempt 绝不会被覆盖，但它**不是**"同一归档的新 attempt"——工具会用 `fileIsArchivedScript` 与 `ARCHIVED_SCRIPT_RERUN` 警告明确说明。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
 - 需要精确数值、符号化简、反例搜索、统计或线性代数时调用 math_computation：先 probe，再 run。
 - 复核他人的数值结论时用 op:'receipt'（或 op:'run', mode:'file' 指向同一脚本）重跑，并把回执路径写进报告。
 - 归档即引用：报告里带 Computation/<id>/receipt.json；这是"支撑材料"的用法。
@@ -6370,14 +6436,16 @@ CURRENT STATE BRIEF (JSON):
   "recent_events": "<RECENT_EVENTS>"
 }
 
-ACTION VOCABULARY (code validates every action against hard invariants; invalid actions are dropped):
+ACTION VOCABULARY — the code ACCEPTS exactly these 6 actions: spawn / interrupt / promote are HARD-VALIDATED (invalid ones are dropped), while wait / continue / stop are ADVISORY ONLY (they are logged and have NO scheduling effect):
 - {"action":"spawn","role":"explorer","target":"<qid>","reason":"..."} — problem has no directions yet or all dead (re-derive).
 - {"action":"spawn","role":"solver","target":"<qid>","direction":"<dirId>","reason":"..."} — active direction, needs a solving round.
 - {"action":"spawn","role":"verifier","target":"<rId>","reason":"..."} — verify candidate (from verify_candidates); keep solving AND verifying balanced.
 - {"action":"spawn","role":"method-keeper","reason":"..."} — distill pending inventions / maintain the theory library.
 - {"action":"interrupt","childId":"<childId>","reason":"..."} — stop a running child (direction dead, superseded...).
 - {"action":"promote","target":"<pId>","reason":"..."} — high-value unresolved proposition → judge problem.
-- {"action":"wait","target":"<id>","reason":"..."} — advisory: wait for a dependency.
+- {"action":"wait","target":"<id>","reason":"..."} — advisory only (logged; no scheduling effect): you are waiting for a dependency.
+- {"action":"continue","childId":"<childId>","reason":"..."} — advisory only (logged): continuation of an in-flight child is code-driven; this never re-dispatches anything.
+- {"action":"stop","childId":"<childId>","reason":"..."} — advisory only (logged; it does NOT stop anyone). To actually stop a child use `interrupt` with a live childId.
 
 HARD RULES: never re-schedule verified objects; problems with 依赖未就绪 (依赖就绪=false) should wait unless you explicitly accept a temporary assumption; respect capacity (brief.free_slots); PREFER problems whose dependencies are ready and whose directions have the highest survival; DO NOT forget verification — unresolved solutions/proofs/refutations (verify_candidates) will never be checked unless you schedule a verifier; DO NOT assume a direction is already being worked just because it is shown "active" in a problem — check brief.problems[].running_solver_dirs and brief.active_agents: schedule a solver for a direction ONLY if that direction is NOT in running_solver_dirs (an "active" direction absent from running_solver_dirs is WAITING to be dispatched, not being worked); schedule at most 3 actions.
 Respond with ONLY a single JSON object wrapped in a ```json code fence — no prose:
@@ -6431,7 +6499,7 @@ feasibility ∈ [0,1]. Respond with ONLY a single JSON object in a ```json code
 {"meta":{"kind":"directions","qid":"<qid>","directions":[{"id":"d1","title":"...","method":"...","core_assumption":"...","feasibility":0.5}],"methods_used":[{"id":"m-...","效果":"...","建议":"..."}],"new_inventions":[{"类型":"方法|工具|...","标题":"...","内容描述":"...","是否已入库":false}]}}
 - math_computation：本机可用 （无）。需要数值/符号/统计计算时先 probe 再 run（工具路径会留下可复核回执，结论请引用回执路径）；缺包时如实说明并给替代方案或安装计划（不要假装），安装需先出计划并征得确认。
 - shell 兜底标注：工具不可用而改用宿主 shell 时，结论必须写"未经工具归档（shell 路径）"，且不得与工具回执混同（shell 无回执、无超时/输出上限保证）。
-- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以打开它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）；编辑后用 mode:'file' 指向它重跑，会写出一份**新回执/新 attempt**（含新的 scriptHash）。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
+- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以读它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）。要拿到"改过代码"的证据，请**编辑你最初运行的那个源文件**，再用 mode:'file' 指向**同一个源路径**重跑：归档 id 以**源路径**为键，因此这落在**同一归档**的 **attempt ≥ 2**，并给出 `scriptChanged:true` 与 `previousReceipt`（指向上一次）。**指向归档副本本身**（`receipt.scriptAbs` 那个路径）按设计是**另一份新归档**：新 id、attempt 1、没有 `previousReceipt`、`scriptChanged:false`；旧 attempt 绝不会被覆盖，但它**不是**"同一归档的新 attempt"——工具会用 `fileIsArchivedScript` 与 `ARCHIVED_SCRIPT_RERUN` 警告明确说明。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
 - 需要精确数值、符号化简、反例搜索、统计或线性代数时调用 math_computation：先 probe，再 run。
 - 复核他人的数值结论时用 op:'receipt'（或 op:'run', mode:'file' 指向同一脚本）重跑，并把回执路径写进报告。
 - 归档即引用：报告里带 Computation/<id>/receipt.json；这是"支撑材料"的用法。
@@ -6504,7 +6572,7 @@ Citations: facts may only be cited from Verified/ (or Propos/ 状态: 已验证
   · 宿主没有 Lean 工具链（LEAN_NOT_FOUND）或宿主不提供 subprocess 服务（NO_SUBPROCESS）时：把代码写下来归档，并在回执的 note 里写明"宿主无 Lean 工具链"——这算显式阻塞原因，定论门禁可以据此放行。
 - math_computation：本机可用 （无）。需要数值/符号/统计计算时先 probe 再 run（工具路径会留下可复核回执，结论请引用回执路径）；缺包时如实说明并给替代方案或安装计划（不要假装），安装需先出计划并征得确认。
 - shell 兜底标注：工具不可用而改用宿主 shell 时，结论必须写"未经工具归档（shell 路径）"，且不得与工具回执混同（shell 无回执、无超时/输出上限保证）。
-- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以打开它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）；编辑后用 mode:'file' 指向它重跑，会写出一份**新回执/新 attempt**（含新的 scriptHash）。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
+- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以读它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）。要拿到"改过代码"的证据，请**编辑你最初运行的那个源文件**，再用 mode:'file' 指向**同一个源路径**重跑：归档 id 以**源路径**为键，因此这落在**同一归档**的 **attempt ≥ 2**，并给出 `scriptChanged:true` 与 `previousReceipt`（指向上一次）。**指向归档副本本身**（`receipt.scriptAbs` 那个路径）按设计是**另一份新归档**：新 id、attempt 1、没有 `previousReceipt`、`scriptChanged:false`；旧 attempt 绝不会被覆盖，但它**不是**"同一归档的新 attempt"——工具会用 `fileIsArchivedScript` 与 `ARCHIVED_SCRIPT_RERUN` 警告明确说明。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
 - 需要精确数值、符号化简、反例搜索、统计或线性代数时调用 math_computation：先 probe，再 run。
 - 复核他人的数值结论时用 op:'receipt'（或 op:'run', mode:'file' 指向同一脚本）重跑，并把回执路径写进报告。
 - 归档即引用：报告里带 Computation/<id>/receipt.json；这是"支撑材料"的用法。
@@ -6579,7 +6647,7 @@ Citations: facts may only be cited from Verified/ (or Propos/ 状态: 已验证
   · 宿主没有 Lean 工具链（LEAN_NOT_FOUND）或宿主不提供 subprocess 服务（NO_SUBPROCESS）时：把代码写下来归档，并在回执的 note 里写明"宿主无 Lean 工具链"——这算显式阻塞原因，定论门禁可以据此放行。
 - math_computation：本机可用 （无）。需要数值/符号/统计计算时先 probe 再 run（工具路径会留下可复核回执，结论请引用回执路径）；缺包时如实说明并给替代方案或安装计划（不要假装），安装需先出计划并征得确认。
 - shell 兜底标注：工具不可用而改用宿主 shell 时，结论必须写"未经工具归档（shell 路径）"，且不得与工具回执混同（shell 无回执、无超时/输出上限保证）。
-- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以打开它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）；编辑后用 mode:'file' 指向它重跑，会写出一份**新回执/新 attempt**（含新的 scriptHash）。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
+- 归档→编辑→重跑：mode:'code' 的脚本原件在回执的 scriptPath（Computation/<id>/script.<ext>，**相对项目根**）；**成员的文件工具是按会话 cwd 解析的**，所以读它要用**绝对路径** `receipt.scriptAbs`，或把 `receipt.cwd` 与 `receipt.scriptPath` 拼起来（回执两个字段都有）。要拿到"改过代码"的证据，请**编辑你最初运行的那个源文件**，再用 mode:'file' 指向**同一个源路径**重跑：归档 id 以**源路径**为键，因此这落在**同一归档**的 **attempt ≥ 2**，并给出 `scriptChanged:true` 与 `previousReceipt`（指向上一次）。**指向归档副本本身**（`receipt.scriptAbs` 那个路径）按设计是**另一份新归档**：新 id、attempt 1、没有 `previousReceipt`、`scriptChanged:false`；旧 attempt 绝不会被覆盖，但它**不是**"同一归档的新 attempt"——工具会用 `fileIsArchivedScript` 与 `ARCHIVED_SCRIPT_RERUN` 警告明确说明。**旧回执对修改后的代码无效**——报告里必须引用与当前代码哈希一致的那份回执；工具会在 scriptChanged / scriptChangedDuringRun 为 true 时显式告警。
 - 需要精确数值、符号化简、反例搜索、统计或线性代数时调用 math_computation：先 probe，再 run。
 - 复核他人的数值结论时用 op:'receipt'（或 op:'run', mode:'file' 指向同一脚本）重跑，并把回执路径写进报告。
 - 归档即引用：报告里带 Computation/<id>/receipt.json；这是"支撑材料"的用法。
@@ -6612,14 +6680,16 @@ CURRENT STATE BRIEF (JSON):
   "recent_events": "<RECENT_EVENTS>"
 }
 
-ACTION VOCABULARY (code validates every action against hard invariants; invalid actions are dropped):
+ACTION VOCABULARY — the code ACCEPTS exactly these 6 actions: spawn / interrupt / promote are HARD-VALIDATED (invalid ones are dropped), while wait / continue / stop are ADVISORY ONLY (they are logged and have NO scheduling effect):
 - {"action":"spawn","role":"explorer","target":"<qid>","reason":"..."} — problem has no directions yet or all dead (re-derive).
 - {"action":"spawn","role":"solver","target":"<qid>","direction":"<dirId>","reason":"..."} — active direction, needs a solving round.
 - {"action":"spawn","role":"verifier","target":"<rId>","reason":"..."} — verify candidate (from verify_candidates); keep solving AND verifying balanced.
 - {"action":"spawn","role":"method-keeper","reason":"..."} — distill pending inventions / maintain the theory library.
 - {"action":"interrupt","childId":"<childId>","reason":"..."} — stop a running child (direction dead, superseded...).
 - {"action":"promote","target":"<pId>","reason":"..."} — high-value unresolved proposition → judge problem.
-- {"action":"wait","target":"<id>","reason":"..."} — advisory: wait for a dependency.
+- {"action":"wait","target":"<id>","reason":"..."} — advisory only (logged; no scheduling effect): you are waiting for a dependency.
+- {"action":"continue","childId":"<childId>","reason":"..."} — advisory only (logged): continuation of an in-flight child is code-driven; this never re-dispatches anything.
+- {"action":"stop","childId":"<childId>","reason":"..."} — advisory only (logged; it does NOT stop anyone). To actually stop a child use `interrupt` with a live childId.
 
 HARD RULES: never re-schedule verified objects; problems with 依赖未就绪 (依赖就绪=false) should wait unless you explicitly accept a temporary assumption; respect capacity (brief.free_slots); PREFER problems whose dependencies are ready and whose directions have the highest survival; DO NOT forget verification — unresolved solutions/proofs/refutations (verify_candidates) will never be checked unless you schedule a verifier; DO NOT assume a direction is already being worked just because it is shown "active" in a problem — check brief.problems[].running_solver_dirs and brief.active_agents: schedule a solver for a direction ONLY if that direction is NOT in running_solver_dirs (an "active" direction absent from running_solver_dirs is WAITING to be dispatched, not being worked); schedule at most 3 actions.
 Respond with ONLY a single JSON object wrapped in a ```json code fence — no prose: