dsh-math-modeling-agent 0.2.0 → 0.2.1

package/README.md

@@ -81,14 +81,20 @@ NOT_CHECKED → DERIVED → EXECUTED → VERIFIED → INDEPENDENTLY_VERIFIED →
 默认运行目录 `math-modeling-runs/<task-id>/`：
 
 ```text
-run.json            # 原子状态快照
-ledger.json         # 范围、假设、主张、义务、子问题、候选、issue
-events.jsonl        # 追加式转移日志
-attempts/<n>/       # 每轮报告与产物
-research/  walls/   # 文献检索 / 放弃方向的突破备忘录
+run.json  ledger.json  events.jsonl   # 原子状态 + 契约（interactions/decisionStack）+ 日志
+problem-brief.md  inputs.json         # 冻结的问题重述 + 输入清单
+attempts/<n>/                         # 每轮：report.md + code/ + data/ + plots/ + _drafts/
+failed/directions/<id>/               # 方向级失败：wall memo + 代码 + 放弃理由
+failed/code-drafts/<attempt>-<name>/  # 实现级失败：bug 版/超时版/弃用版（不删除）
+failed/issues.md                      # 失败账本（DATA/TOOL/IMPLEMENTATION/MODEL/VALIDATION/EVIDENCE/RESEARCH_GAP）
+research/  walls/                     # 文献检索 / 突破备忘录
 reproducibility.json  final-report.md
 ```
 
+v0.2.0 起：每个会改变模型结构的决策在对话中交互确认并写入 ledger（D0 重述/D1 路由/
+D2 子问题假设/D3 方向/D4 裁决），`run-state.mjs gate` 在每次状态转移前强制校验；
+终态前强制鲁棒性敏感度分析；失败尝试按类归档到独立目录。
+
 崩溃恢复：跨进程互斥锁 + stale 锁与 reclaim guard 回收 + Windows 共享冲突重试；已完成且输入未变的工作不重跑；任何失败都保留最佳候选与原始产物。
 
 ## MCM / ICM 终审（audit Skill）
@@ -100,7 +106,7 @@ reproducibility.json  final-report.md
 安装：
 
 ```bash
-dsh plugin --profile web add github:yohanchen1/MathModelingAgent#v0.2.0
+dsh plugin --profile web add github:yohanchen1/MathModelingAgent#v0.2.1
 dsh --profile web --dump-config   # 检查组合层
 dsh web                          # 然后重启
 ```

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "dsh-math-modeling-agent",
-  "version": "0.2.0",
+  "version": "0.2.1",
   "description": "Evidence-driven mathematical modeling and verification skills for DeepSeek Harness",
   "type": "module",
   "files": [

package/skills/math-modeling-agent/examples/minimal-run/README.md

@@ -1,4 +1,4 @@
-# Minimal Run Example
+# Minimal Run Example (v2)
 
 Problem: solve 2x + 3 = 11.
 
@@ -11,4 +11,10 @@ Evidence E-002: substitution 2(4) + 3 = 11.
 
 Status: SOLVED.
 
+v2 interaction records (ledger.scope.interactions): D0 restatement (auto), D1 routing
+(algebra / Fast), D2 assumptions (none beyond the equation), D3 direction
+(direct inverse), D4 verdict (user accepted). scope.robustnessExempt = true —
+a pure algebraic equation has no perturbable parameters, so the robustness
+gate is exempted with that reason. decisionStack holds the D3 entry.
+
 No Python, Lean, Wolfram, research directory, or empty artifact directory is required.

package/skills/math-modeling-agent/examples/resumed-run/README.md

@@ -7,7 +7,9 @@ Resume sequence:
 1. run `node scripts/run-state.mjs validate <run-root>`;
 2. run `node scripts/run-state.mjs recover <run-root>`;
 3. confirm C-003 remains the best candidate;
-4. rerun only the incomplete verifier;
-5. append a new evidence-linked transition.
+4. run `node scripts/run-state.mjs gate <run-root> --to REVISE --reason "回退到 D3-SP1：..."` (the reason must reference the decisionStack entry);
+5. rerun only the incomplete verifier;
+6. append a new evidence-linked transition (the CLI enforces the gate).
 
-Previously hash-stable Python outputs are not recomputed.
+Previously hash-stable Python outputs are not recomputed. Interaction records,
+the decision stack, and the failure ledger survive the crash unchanged.

package/skills/math-modeling-agent/scripts/run-state.mjs

@@ -421,17 +421,27 @@ function decisionStackIds(scope) {
     ? scope.decisionStack.filter(entry => entry && typeof entry.id === 'string').map(entry => entry.id)
     : []
 }
-function interactionContractViolations(run, ledger, to, reason) {
+/** D2 records carry the subproblem id(s) they cover: {decisionPoint:'D2', scope:['SP1'], ...} */
+function hasSubproblemD2(scope, subproblem) {
+  if (!subproblem || !Array.isArray(scope?.interactions)) return true
+  return scope.interactions.some(entry => entry && entry.decisionPoint === 'D2' &&
+    (Array.isArray(entry.scope) ? entry.scope.includes(subproblem) : entry.subproblem === subproblem))
+}
+function interactionContractViolations(run, ledger, to, reason, subproblem) {
   if (ledger.schemaVersion !== SCHEMA_VERSION) return []
   const scope = ledger.scope ?? {}
   const violations = []
   const transitional = to !== undefined
   const earlyStop = ['BLOCKED', 'CANCELLED'].includes(run.status)
   if ((transitional && to === 'SCOPE_FROZEN') || (!transitional && run.status !== 'TRIAGE' && !earlyStop)) {
+    if (!hasDecisionRecord(scope, 'D0')) violations.push('D0 restatement interaction record missing (ledger.scope.interactions)')
     if (!hasDecisionRecord(scope, 'D1')) violations.push('D1 routing interaction record missing (ledger.scope.interactions)')
   }
   const enteringAttemptFromCandidates = transitional ? (to === 'ATTEMPT' && run.status === 'CANDIDATES_READY') : (run.currentAttempt >= 1)
-  if (enteringAttemptFromCandidates && !hasDecisionRecord(scope, 'D3')) violations.push('D3 direction-selection interaction record missing')
+  if (enteringAttemptFromCandidates) {
+    if (!hasDecisionRecord(scope, 'D3')) violations.push('D3 direction-selection interaction record missing')
+    if (transitional && !hasSubproblemD2(scope, subproblem)) violations.push(`D2 assumption interaction record missing for subproblem ${subproblem} (run the gate with --subproblem <id>)`)
+  }
   const enteringTerminalFromVerify = transitional
     ? (FINAL_STATES.includes(to) && run.status === 'VERIFY')
     : (FINAL_STATES.includes(run.status) && !['BLOCKED', 'CANCELLED'].includes(run.status))
@@ -539,6 +549,17 @@ async function validateRunUnlocked(root, expectedTaskId) {
     for (const violation of interactionContractViolations(run, ledger, undefined, undefined)) {
       warnings.push(`interaction contract: ${violation}`)
     }
+    if (run.currentAttempt >= 1) {
+      const reportPath = join(root, 'attempts', String(run.currentAttempt), 'report.md')
+      try {
+        const reportText = await readFile(reportPath, 'utf8')
+        for (const section of ['问题重述', '问题分析', '模型假设', '模型建立与求解', '验证', '鲁棒性', '评价与改进', '参考文献']) {
+          if (!reportText.includes(section)) warnings.push(`attempt ${run.currentAttempt} report.md missing runlog digest section: ${section}`)
+        }
+      } catch {
+        warnings.push(`attempt ${run.currentAttempt} report.md unreadable (runlog digest required)`)
+      }
+    }
   }
   return { valid: diagnostics.length === 0, diagnostics, warnings, run: clone(run) }
 }
@@ -552,12 +573,12 @@ export async function validateRun(root, expectedTaskId, runtime = {}) {
  * mutating anything. The agent workflow must call this before `transition`;
  * the CLI `transition` command enforces it internally unless --skip-gate.
  */
-export async function gateTransition(root, { to, reason }, runtime = {}) {
+export async function gateTransition(root, { to, reason, subproblem }, runtime = {}) {
   return withLock(root, MUTATION_LOCK_FILE, 'gate', async () => {
     const p = paths(root)
     const run = await readJson(p.run)
     const ledger = await readJson(p.ledger)
-    const violations = interactionContractViolations(run, ledger, to, reason)
+    const violations = interactionContractViolations(run, ledger, to, reason, subproblem)
     return { allowed: violations.length === 0, violations, status: run.status }
   }, runtime)
 }
@@ -603,13 +624,13 @@ async function cli(argv) {
   const options = parseOptions(rest)
   if (command === 'init') return initRun(root, { taskId: options['task-id'], mode: options.mode ?? 'standard' })
   if (command === 'gate') {
-    const result = await gateTransition(root, { to: options.to, reason: options.reason })
+    const result = await gateTransition(root, { to: options.to, reason: options.reason, subproblem: options.subproblem })
     if (!result.allowed) process.exitCode = 1
     return result
   }
   if (command === 'transition') {
     if (options['skip-gate'] !== 'true') {
-      const gate = await gateTransition(root, { to: options.to, reason: options.reason })
+      const gate = await gateTransition(root, { to: options.to, reason: options.reason, subproblem: options.subproblem })
       if (!gate.allowed) {
         process.exitCode = 1
         return { error: `interaction contract violated: ${gate.violations.join('; ')}`, gate }