dsh-math-modeling-agent 0.2.7 → 0.3.1

package/README.md

@@ -108,7 +108,7 @@ D3 方向/D4 裁决），`run-state.mjs gate` 在每次状态转移前强制校
 安装：
 
 ```bash
-dsh plugin --profile web add github:yohanchen1/MathModelingAgent#v0.2.7
+dsh plugin --profile web add github:yohanchen1/MathModelingAgent#v0.3.1
 dsh --profile web --dump-config   # 检查组合层（应看到 dsh-math-modeling-agent-skills 行）
 dsh web                          # 重启以加载插件
 ```

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "dsh-math-modeling-agent",
-  "version": "0.2.7",
+  "version": "0.3.1",
   "description": "Evidence-driven mathematical modeling and verification skills for DeepSeek Harness",
   "type": "module",
   "files": [

package/skills/math-modeling-agent/SKILL.md

@@ -22,18 +22,18 @@ Return a concise current status, supported claims, unresolved obligations, attem
 ## Default workflow
 
 1. Route the task to Fast, Standard, or High-Assurance using `references/problem-types.md`; ask D1 (task type + assurance mode).
-2. Read available inputs before asking questions; apply the per-subproblem math grill in `references/math-grill.md`; show the D0 restatement and intake digest in the chat.
-3. Create or validate run state with `scripts/run-state.mjs` and follow `references/state-recovery.md`. Gate EVERY transition: `run-state.mjs gate <dir> --to <status> --reason "..."`.
-4. Profile inputs and build the subproblem DAG using `references/data-subproblems.md`.
-5. Register assumptions (per subproblem), claims, and verification obligations from `references/claims-evidence.md`; ask D2 for the subproblem being started.
-6. **Literature research (mandatory, before candidates)**: transition CLAIMS_REGISTERED → RESEARCH, search principles and methods by direction (never contest solutions), write `research/sources.jsonl`, attach a literature column to the candidate matrix, then ask D-R (user endorses/rejects/adds references) and move to CANDIDATES_READY.
-7. Build a baseline and materially different candidates using `references/modeling-methodology.md`; ask D3 (candidate matrix).
-8. Probe tools with `scripts/capability-probe.mjs`; create a run-local Python environment with `scripts/python-environment.mjs` only when computation is required. Announce the tool choice and fallback for the phase (references/tool-policy.md).
-9. Execute, verify, critique, and revise according to `references/workflow.md` and `references/tool-policy.md`; ask D4 after each VERIFY.
+2. Literature research FIRST: transition TRIAGE → RESEARCH, search principles and methods by direction (never contest solutions), write `research/sources.jsonl` + methods matrix, ask D-R (user endorses/rejects/adds).
+3. Show the D0 deep restatement — six sections plus the question-dependency relation — and ask D0; gate SCOPE_FROZEN (requires D0+D1+D-R).
+4. Panorama analysis + data profile (INPUT_PROFILED) with user interaction; global assumptions G-class confirmed via D2-G before CLAIMS_REGISTERED.
+5. Register claims and obligations; build the candidate matrix with literature column (CANDIDATES_READY) and ask D3.
+6. For EACH subproblem: subproblem analysis (reference the panorama, do not re-derive), S-class assumptions via D2-SPi, then ATTEMPT → EXECUTE → VERIFY → subproblem robustness (plan→interact→run) → D4 verdict → REVISE or move to the next subproblem.
+7. Live documents: any discovery that shows an earlier phase was incomplete patches that phase incrementally (revision + stale), never re-running unaffected completed work.
+8. Backtracking depth follows the failure root cause (attempt/verify/direction/assumption/analysis/restatement/research), recorded in failed/issues.md.
+9. Probe tools with `scripts/capability-probe.mjs`; create a run-local Python environment with `scripts/python-environment.mjs` when computation is required; announce the tool choice and fallback.
 10. Dispatch subagents for parallel exploration, blind verification, and audits per `references/subagent-dispatch.md`.
-11. Escalate evidence gaps or stalled directions through `references/research-breakthrough.md`; write wall memos and the failure ledger per `references/run-directory.md`.
-12. Write only incremental attempt and terminal reports defined by `references/report-contract.md`; output the per-round runlog digest in the chat.
-13. Before any terminal transition, run the cleanup gate (references/run-directory.md) and the robustness gate (a PASSED robustness-kind obligation, or scope.robustnessExempt with reason).
+11. Escalate evidence gaps through `references/research-breakthrough.md`; write wall memos and the failure ledger per `references/run-directory.md`.
+12. Write incremental attempt and terminal reports per `references/report-contract.md`; output the per-round runlog digest in the chat.
+13. Before any terminal transition: cleanup gate, ALL required robustness obligations PASS (or robustnessExempt), every subproblem DONE with dependencies satisfied, D4 for the current attempt, report.md present.
 
 ## Invariants
 

package/skills/math-modeling-agent/references/claims-evidence.md

@@ -6,7 +6,9 @@ Store claim ID, exact wording, type, scope/quantifiers, assumptions, risk, verif
 
 ## Assumption record (v2)
 
-Store id, statement, scope (subproblem ids or global), source category, risk, sensitivity plan, validation status, affected claims, status (active/revised/superseded), and revisionHistory [{at, reason, changedTo}]. Allowed source categories are problem, data, theory, verified literature, domain instruction, and modeling simplification.
+Store id, statement, scope ('global' for whole-problem assumptions, or a subproblem id list), source category, risk, sensitivity plan, validation status, affected claims, status (active/revised/superseded), and revisionHistory [{at, reason, changedTo}]. Allowed source categories are problem, data, theory, verified literature, domain instruction, and modeling simplification.
+
+Two classes: G-class (global, confirmed once in the panorama layer via D2-G) and S-class (per subproblem, confirmed via D2-SPi). Claims carry an `assumptions` field listing the assumption ids they depend on; when an assumption is revised, dependent claims are marked stale and must carry post-revision evidence before a terminal state (validate warns otherwise).
 
 Every assumption additionally carries a `basis` field — the evidence chain behind it: `problem-quote` (exact original wording), `data` (evidence id + statistic), `literature` (source id + excerpt location), or `llm-judgment` (explicitly flagged as the LLM's own inference, challengeable in D2).
 

package/skills/math-modeling-agent/references/interaction-protocol.md

@@ -31,7 +31,8 @@ until the user says "可以了". Mathematical modeling is a deep activity;
 | D0 问题重述 | intake complete | the six-section deep restatement below + open clarification questions | accept + no additions |
 | D1 路由 | TRIAGE | task type (prediction/optimization/explanation/proof/…) + assurance mode (Fast/Standard/High-Assurance) | auto-routing result |
 | D-R 文献研究 | CLAIMS_REGISTERED (before CANDIDATES_READY) | the literature list by direction (AI-found); user endorses / rejects / adds their own | accept list |
-| D2 假设确认 | **each subproblem starts** | the assumptions for THIS subproblem, each with statement + basis chain (problem quote / data evidence / literature / LLM-judgment marker) + risk + challengeable point | accept all |
+| D2-G 全局假设确认 | CLAIMS_REGISTERED (全景层) | the GLOBAL assumptions that hold for the whole problem (geometry, data, physical mechanism, numerical basis) — each with basis chain + risk | accept all |
+| D2 子问题假设确认 | **each subproblem starts** | the assumptions for THIS subproblem only (S-class), each with statement + basis chain + risk | accept all |
 | D2' 新假设插问 | mid-subproblem discovery that changes model structure | the new assumption + its effect | record-and-continue |
 | D3 方向选择 | CANDIDATES_READY | candidate matrix with a literature column per direction; user picks or authorizes auto | baseline |
 | D4 结果裁决 | VERIFY done | verdict + evidence digest + key intermediate results (residual/constraint-violation distributions, figure paths) + failure details | verdict-implied |
@@ -46,8 +47,12 @@ until the user says "可以了". Mathematical modeling is a deep activity;
 4. **隐含信息与歧义清单**：numbered; each entry = the LLM's reading + its
    basis + the risk if the reading is wrong. This is the heart of the
    exchange: the user corrects entries here.
-5. **三问数学本质判定**：each sub-question classified (fitting/optimization/
+5. **各子问题数学本质判定**：every sub-question of the problem — however
+   many there are (one or ten) — is classified (fitting/optimization/
    geometric optics/simulation/…), with why.
+5.5 **问间依赖关系**：which sub-questions depend on which (models, data,
+   verified claims reused downstream) — the整体感 guarantee: later questions
+   REFERENCE earlier verified results instead of re-deriving them.
 6. **待澄清问题**：open questions inviting the user to add background,
    correct a reading, or supply their own references — never a yes/no list.
 
@@ -99,6 +104,19 @@ record to real files on disk.
   batch runs may declare `scope.contractExempt: true` — production modeling
   must never set it.
 
+## Phase pace — interactive beats between phases (v2.8)
+
+The exposition is delivered PHASE BY PHASE, never as a firehose. The phase
+sequence is: restatement → analysis → assumptions → modeling → solving →
+verification → robustness → evaluation. Between every two phases there MUST
+be a user interaction point: the completed phase is presented, one line asks
+whether to proceed to the next phase, and the user may interrupt, ask for a
+deeper explanation of any step of the just-finished phase, or contribute
+knowledge. Sensitivity/robustness NEVER follows solving automatically — it
+only starts after the verification phase, the user's go-ahead, and its own
+D-interaction. Within a phase with ≥3 major steps, offer the user one
+interruption opportunity after the first step.
+
 ## L2 display points (MUST show, never ask)
 
 - After every attempt round: the 8-section runlog digest (see report-contract.md).
@@ -127,6 +145,14 @@ record to real files on disk.
   and every downstream claim/obligation that depended on the old assumption is
   marked `stale: true` with the revising assumption id (see claims-evidence.md).
 
+## Live documents (every phase can be refined later)
+
+Every phase artifact is LIVE: problem-brief.md (restatement), analysisLog,
+assumptions, sources.jsonl, methods.md, attempt reports. While solving,
+anything discovered that shows an earlier phase was incomplete is patched
+INCREMENTALLY — revision record + downstream stale marking — without
+re-running completed unaffected work. This is the "解题中不断完善" rule.
+
 ## Rolling documents
 
 - Problem restatement: written once at intake (problem-brief.md); only

package/skills/math-modeling-agent/references/math-grill.md

@@ -17,6 +17,14 @@ Ask one question at a time. Read the problem and attachments first. Ask only que
 10. 假设及依据；11. 任务类型（预测/优化/解释/证明/机制/决策）；12. 误差/精度要求；
 13. 验证标准；14. 最终交付物；15. 风险与失败模式；16. 不适用字段（标注原因）。
 
+## Layered questioning (v0.3)
+
+- **全景层**：global assumptions (G-class) are grilled once — geometry, data
+  quality, physical mechanism, numerical basis; recorded via D2-G before
+  CLAIMS_REGISTERED.
+- **逐问层**：per-subproblem assumptions (S-class) are grilled when the
+  subproblem starts (D2-SPi) — only what is specific to this sub-question.
+
 ## Per-subproblem grilling (v2)
 
 - Grill **one subproblem at a time**. Never demand assumptions for Q2 while Q1 is unsolved.

package/skills/math-modeling-agent/references/report-contract.md

@@ -24,21 +24,73 @@ Do not copy full prior solutions or private reasoning.
 
 State the frozen question, final scientific status, answer/recommendation, verified claims and evidence links, conditional/unresolved claims, assumptions and sensitivity, candidate comparison, data and parameter sources, validation, failure cases, limitations, reproducibility commands, and resume conditions when non-SOLVED.
 
-## Chat display — the runlog digest (MUST output, v2)
+整体感 requirement (v0.3): the terminal report is ONE narrative, not a
+concatenation of sub-question reports — it must show the question-dependency
+chain (which model fed which), the shared global assumptions, and the
+cross-sub-question consistency checks. A reader must be able to see the whole
+problem as one connected argument.
+
+## Chat display — the runlog digest (MUST output, v2.7)
 
 The following is shown DIRECTLY IN THE CHAT, not only on disk.
 
+### Readability standard — write for a human reader, never a bullet list
+
+Every section is an EXPOSITION, not a summary: state WHY the step is taken,
+HOW the reasoning runs (derivation, mechanism, first-principles chain), WHAT
+came out (numbers with units), and HOW it is checked. A reader who knows
+nothing about the problem must be able to follow each section without
+guessing.
+
+Style: step-by-step numbered exposition with plain direct language (this is
+a working document, not a final paper — no paper-style formal phrasing
+required), but with MORE detail than a paper would carry: every parameter
+choice gets its reason, every formula is followed by a plain-language
+explanation of each symbol, every step ends with a transition line
+("这一步保证了…，为下一步…做好准备"), and every conclusion states what it
+would take to be wrong. Minimum expectations per section:
+
+- 问题重述：restate the question in your own words, explaining every
+  parameter's meaning and where it comes from in the problem text.
+- 问题分析：walk the physical/geometric mechanism step by step (e.g. why the
+  nodes move radially, how the focal geometry pins the paraboloid), each
+  step justified by problem text, data, or derivation.
+- 模型假设：for EVERY assumption give the reason it is justified
+  (original wording / data statistic / derivation / literature) and what
+  happens if it fails.
+- 模型建立与求解：write the derivation in full (equations, variable
+  definitions, units, how the equation is solved, numerical method and why
+  it was chosen), not just the final formula.
+- 验证：explain the verification LOGIC for each obligation (what would
+  falsify it, what tolerance is used and why), then the outcome.
+- 鲁棒性：for each perturbation say what was varied, why that parameter,
+  and what would count as a conclusion flip.
+- 评价与改进 / 参考文献：state the comparison criterion and map each
+  reference to the exact method it supports.
+
 ### Intake digest (once, at intake completion) — the six-section deep restatement
 
-【题目要点摘录】problem's own numbers and constraints, quoted
-【背景解读】engineering/physical mechanism
-【数据语义】every attachment column by column (meaning/units/coordinate system/magnitudes)
-【隐含信息与歧义清单】numbered; each = LLM reading + basis + risk (the user corrects entries here)
-【三问数学本质判定】fitting/optimization/geometric optics/… + why
+【题目要点摘录】the problem's own numbers and constraints, quoted, each explained
+【背景解读】engineering/physical mechanism, walked through
+【数据语义】every attachment column by column (meaning/units/coordinate system/magnitudes), with observed statistics
+【隐含信息与歧义清单】numbered; each = LLM reading + derivation/basis + risk (the user corrects entries here)
+【各子问题数学本质判定】every sub-question (any count) classified + why
 【待澄清问题】open questions inviting user background/corrections/references
 
 After the D0 exchange, show the delta applied to problem-brief.md.
 
+### Quality self-check (MUST run before every D4 verdict)
+
+Before presenting a D4 verdict, run the self-check on the current attempt's
+report and show the result in the chat: for each of the eight digest sections,
+confirm whether it answers all four questions — WHY (why this step), HOW
+(how the reasoning runs), WHAT (result with units), CHECK (how it is
+verified, or what would falsify it). Any section failing one of the four is
+flagged as incomplete and the round is NOT presented for verdict until fixed.
+The self-check is a human-facing declaration: the user decides whether the
+exposition is actually sufficient. This is the quality gate; the machine
+gates above only guarantee existence and structure.
+
 ### Per-round digest (after EVERY attempt round)
 
 ```text

package/skills/math-modeling-agent/references/workflow.md

@@ -13,6 +13,12 @@ TRIAGE → SCOPE_FROZEN → INPUT_PROFILED → CLAIMS_REGISTERED → CANDIDATES_
 VERIFY may move to REVISE, RESEARCH, FORK, an independent audit, or one terminal status:
 SOLVED, PARTIAL, CONDITIONAL, INCONCLUSIVE, REFUTED, INFEASIBLE, UNIDENTIFIABLE, BLOCKED, CANCELLED.
 
+## Three-layer flow (v0.3)
+
+- **全景层**（一次建立，贯穿全题）：TRIAGE(读题+D1) → RESEARCH(文献+D-R，前置) → SCOPE_FROZEN(D0 七段重述，含问间依赖) → INPUT_PROFILED(全景分析+数据画像) → CLAIMS_REGISTERED(全局假设 G，D2-G) → CANDIDATES_READY(方法矩阵+D3)。
+- **逐问层**（SPi 循环）：子问题分析 → 子问题假设 Si（D2-SPi）→ ATTEMPT 建模求解 → VERIFY 该问验证 → 该问鲁棒性（扰动计划→交互→执行）→ D4 裁决 → REVISE（本问修订）或进入 SPi+1（reason: "SPi 完成，进入 SPi+1"）。
+- **收束层**：跨问联动检查（终态 gate 校验全部子问题 DONE + 依赖满足）→ 全题鲁棒性汇总 → 终态硬门 → SOLVED + final-report（整体叙事，非拼凑）。
+
 ## Pre-modeling literature research (v2.6, mandatory)
 
 CLAIMS_REGISTERED → RESEARCH → CANDIDATES_READY. Before any candidate is
@@ -37,6 +43,22 @@ scope.robustnessExempt is set with a reason.
 
 - REVISE/RESEARCH reasons MUST reference a decisionStack entry id; the round
   returns to that decision point and tries the next option.
+- Backtracking depth is chosen by the failure root cause (recorded in
+  failed/issues.md):
+
+| Root cause | Depth | Action |
+|---|---|---|
+| IMPLEMENTATION / TOOL | attempt | fix and rerun, no backtrack |
+| VALIDATION | verify | add obligations, re-verify |
+| MODEL (wrong direction) | direction | switch candidate (wall memo) |
+| assumption falsified | assumption | revise assumption (revisionHistory) → dependent claims stale → re-verify |
+| analysis gap | analysis | update analysisLog → re-derive downstream |
+| restatement misunderstanding | restatement | revise problem-brief (re-freeze) |
+| RESEARCH_GAP | research | add sources, switch method |
+
+  Backtracking to assumption/analysis/restatement depth is a CONTENT revision
+  plus downstream re-verification — the state machine does not rewind; the
+  loop is expressed as REVISE cycles and event records.
 - FORK records its fork point; each failed branch writes a wall memo
   (run-directory.md) before the next branch starts. A wrong direction always
   returns to the fork point, never mid-branch.

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

@@ -18,7 +18,8 @@ const FINAL_STATES = ['SOLVED', 'PARTIAL', 'CONDITIONAL', 'INCONCLUSIVE', 'REFUT
 const STATUSES = [...NON_FINAL_STATES, ...FINAL_STATES]
 const STOP_TRANSITIONS = ['BLOCKED', 'CANCELLED']
 const TRANSITIONS = Object.freeze({
-  TRIAGE: ['SCOPE_FROZEN', ...STOP_TRANSITIONS],
+  TRIAGE: ['RESEARCH', 'SCOPE_FROZEN', ...STOP_TRANSITIONS],
+  RESEARCH: ['SCOPE_FROZEN', 'CANDIDATES_READY', ...STOP_TRANSITIONS],
   SCOPE_FROZEN: ['INPUT_PROFILED', ...STOP_TRANSITIONS],
   INPUT_PROFILED: ['CLAIMS_REGISTERED', ...STOP_TRANSITIONS],
   CLAIMS_REGISTERED: ['RESEARCH', 'CANDIDATES_READY', ...STOP_TRANSITIONS],
@@ -27,7 +28,6 @@ const TRANSITIONS = Object.freeze({
   EXECUTE: ['VERIFY', ...STOP_TRANSITIONS],
   VERIFY: ['REVISE', 'RESEARCH', 'FORK', ...FINAL_STATES],
   REVISE: ['ATTEMPT', ...STOP_TRANSITIONS],
-  RESEARCH: ['CANDIDATES_READY', ...STOP_TRANSITIONS],
   FORK: ['ATTEMPT', ...STOP_TRANSITIONS],
 })
 const TASK_ID = /^[a-z0-9]+(?:-[a-z0-9]+)*$/
@@ -440,13 +440,19 @@ function interactionContractViolations(run, ledger, to, reason, subproblem) {
   const violations = []
   const transitional = to !== undefined
   const earlyStop = ['BLOCKED', 'CANCELLED'].includes(run.status)
-  if ((transitional && to === 'SCOPE_FROZEN') || (!transitional && run.status !== 'TRIAGE' && !earlyStop)) {
+  const statusOrder = ['TRIAGE', 'RESEARCH', 'SCOPE_FROZEN', 'INPUT_PROFILED', 'CLAIMS_REGISTERED', 'CANDIDATES_READY', 'ATTEMPT', 'EXECUTE', 'VERIFY', 'REVISE', 'FORK']
+  const reached = (target) => transitional
+    ? to === target
+    : (statusOrder.indexOf(target) <= statusOrder.indexOf(run.status) && !earlyStop)
+  if (reached('SCOPE_FROZEN')) {
     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)')
+    if (!hasDecisionRecord(scope, 'D-R', { allowAuto: false })) violations.push('D-R literature-research interaction record missing (literature survey precedes restatement; auto-authorization is not accepted)')
   }
+  if (reached('CLAIMS_REGISTERED') && !hasDecisionRecord(scope, 'D2-G')) violations.push('D2-G global-assumptions interaction record missing (global assumptions must be confirmed before claims registration)')
+  const candidatesGate = reached('CANDIDATES_READY')
+  if (candidatesGate && !hasDecisionRecord(scope, 'D-R', { allowAuto: false })) violations.push('D-R literature-research interaction record missing (backstop check)')
   const afterCandidates = ['CANDIDATES_READY', 'ATTEMPT', 'EXECUTE', 'VERIFY', 'REVISE', 'FORK', ...FINAL_STATES]
-  const candidatesGate = transitional ? (to === 'CANDIDATES_READY') : (afterCandidates.includes(run.status) && !earlyStop)
-  if (candidatesGate && !hasDecisionRecord(scope, 'D-R', { allowAuto: false })) violations.push('D-R literature-research interaction record missing (pre-modeling literature survey is mandatory; auto-authorization is not accepted)')
   const enteringAttemptFromCandidates = transitional ? (to === 'ATTEMPT' && run.status === 'CANDIDATES_READY') : (run.currentAttempt >= 1)
   if (enteringAttemptFromCandidates) {
     if (transitional && !subproblem) violations.push('ATTEMPT from CANDIDATES_READY requires --subproblem <id>')
@@ -468,8 +474,19 @@ function interactionContractViolations(run, ledger, to, reason, subproblem) {
     : (FINAL_STATES.includes(run.status) && !['BLOCKED', 'CANCELLED'].includes(run.status))
   if (terminalAndExempt) {
     if (scope.robustnessExempt !== true) {
-      const passed = Array.isArray(ledger.obligations) && ledger.obligations.some(o => o && o.kind === 'robustness' && o.status === 'PASS')
-      if (!passed) violations.push('terminal state requires a PASSED robustness-kind obligation (or scope.robustnessExempt: true)')
+      const robos = Array.isArray(ledger.obligations) ? ledger.obligations.filter(o => o && o.kind === 'robustness' && o.required !== false) : []
+      const allPassed = robos.length > 0 && robos.every(o => o.status === 'PASS')
+      if (!allPassed) violations.push(`terminal state requires ALL ${robos.length} required robustness obligations to be PASS (or scope.robustnessExempt: true)`)
+    }
+    const subs = Array.isArray(ledger.subproblems) ? ledger.subproblems : []
+    if (subs.length > 0) {
+      const done = (sp) => sp.status === 'DONE' || sp.status === 'CLOSED'
+      const unfinished = subs.filter(sp => !done(sp))
+      if (unfinished.length > 0) violations.push(`terminal state requires every subproblem DONE (open: ${unfinished.map(sp => sp.id).join(', ')})`)
+      const depGaps = subs.filter(sp => done(sp) && Array.isArray(sp.dependencies) && sp.dependencies.some(dep => {
+        const d = subs.find(x => x.id === dep); return d === undefined || !done(d)
+      }))
+      if (depGaps.length > 0) violations.push(`subproblem dependencies incomplete: ${depGaps.map(sp => sp.id).join(', ')}`)
     }
     if (scope.cleanupPassed !== true) violations.push('terminal state requires scope.cleanupPassed: true (run the cleanup checklist in run-directory.md)')
   }
@@ -574,6 +591,16 @@ async function validateRunUnlocked(root, expectedTaskId) {
         warnings.push(`attempt ${run.currentAttempt} report.md unreadable (runlog digest required)`)
       }
     }
+    for (const assumption of Array.isArray(ledger.assumptions) ? ledger.assumptions : []) {
+      const revised = assumption && (assumption.status === 'revised' || (Array.isArray(assumption.revisionHistory) && assumption.revisionHistory.length > 0))
+      if (!revised) continue
+      for (const claim of Array.isArray(ledger.claims) ? ledger.claims : []) {
+        const depends = claim && Array.isArray(claim.assumptions) && claim.assumptions.includes(assumption.id)
+        if (depends && claim.status === 'VERIFIED' && (!Array.isArray(claim.evidenceIds) || claim.evidenceIds.length === 0)) {
+          warnings.push(`claim ${claim.id} depends on revised assumption ${assumption.id} but has no post-revision evidence`)
+        }
+      }
+    }
   }
   return { valid: diagnostics.length === 0, diagnostics, warnings, run: clone(run) }
 }