dsh-math-modeling-agent 0.2.8 → 0.4.1

package/skills/math-modeling-agent/scripts/distribution-parity.mjs

@@ -0,0 +1,123 @@
+import { createHash } from 'node:crypto'
+import { lstat, readFile, readdir, realpath } from 'node:fs/promises'
+import { isAbsolute, join, relative, resolve, sep } from 'node:path'
+import { fileURLToPath } from 'node:url'
+
+const MAX_FILES = 10_000
+const MAX_FILE_BYTES = 20 * 1024 * 1024
+const MAX_TOTAL_BYTES = 100 * 1024 * 1024
+const MAX_DEPTH = 32
+
+function normalizeRelative(path) {
+  return path.split(sep).join('/')
+}
+
+function assertInside(root, path) {
+  const relativePath = relative(root, path)
+  if (isAbsolute(relativePath) || relativePath === '..' || relativePath.startsWith('..' + sep)) {
+    throw new Error('distribution entry escapes package root: ' + path)
+  }
+}
+
+async function collectFiles(root, entries, { allowMissing = false } = {}) {
+  const realRoot = await realpath(root)
+  const files = new Map()
+  let totalBytes = 0
+
+  const visit = async (path, depth) => {
+    if (depth > MAX_DEPTH) throw new Error('distribution tree exceeds maximum depth: ' + path)
+    let information
+    try {
+      information = await lstat(path)
+    } catch (error) {
+      if (allowMissing && error?.code === 'ENOENT') return
+      throw error
+    }
+    if (information.isSymbolicLink()) throw new Error('symbolic link is not allowed in distribution: ' + path)
+    const realPath = await realpath(path)
+    assertInside(realRoot, realPath)
+    if (information.isDirectory()) {
+      for (const entry of await readdir(path)) await visit(join(path, entry), depth + 1)
+      return
+    }
+    if (!information.isFile()) return
+    if (information.size > MAX_FILE_BYTES) throw new Error('distribution file exceeds maximum size: ' + path)
+    totalBytes += information.size
+    if (totalBytes > MAX_TOTAL_BYTES) throw new Error('distribution tree exceeds maximum size')
+    if (files.size >= MAX_FILES) throw new Error('distribution tree exceeds maximum file count')
+    const relativePath = normalizeRelative(relative(root, path))
+    const digest = createHash('sha256').update(await readFile(path)).digest('hex')
+    files.set(relativePath, digest)
+  }
+
+  for (const entry of entries) {
+    if (typeof entry !== 'string' || !entry.trim()) throw new Error('package files entries must be non-empty strings')
+    const path = resolve(root, entry)
+    assertInside(root, path)
+    await visit(path, 0)
+  }
+  return files
+}
+
+/** Compare the allowlisted package files of a source and distribution root. */
+export async function compareDistribution(sourceRoot, candidateRoot) {
+  const source = resolve(sourceRoot)
+  const candidate = resolve(candidateRoot)
+  const manifest = JSON.parse(await readFile(join(source, 'package.json'), 'utf8'))
+  if (!Array.isArray(manifest.files) || manifest.files.length === 0) {
+    throw new Error('source package.json must declare a non-empty files allowlist')
+  }
+  const entries = [...new Set(['package.json', ...manifest.files])]
+  const expected = await collectFiles(source, entries)
+  const actual = await collectFiles(candidate, entries, { allowMissing: true })
+  const missing = [...expected.keys()].filter(path => !actual.has(path)).sort()
+  const extra = [...actual.keys()].filter(path => !expected.has(path)).sort()
+  const mismatched = [...expected.keys()]
+    .filter(path => actual.has(path) && actual.get(path) !== expected.get(path))
+    .sort()
+  const metadataMismatches = []
+  try {
+    const candidateManifest = JSON.parse(await readFile(join(candidate, 'package.json'), 'utf8'))
+    for (const key of ['name', 'version']) {
+      if (candidateManifest[key] !== manifest[key]) {
+        metadataMismatches.push(`${key}: expected ${manifest[key]}, received ${candidateManifest[key]}`)
+      }
+    }
+  } catch (error) {
+    metadataMismatches.push('package.json: ' + (error instanceof Error ? error.message : String(error)))
+  }
+  return {
+    ok: missing.length === 0 && extra.length === 0 && mismatched.length === 0 && metadataMismatches.length === 0,
+    sourceRoot: source,
+    candidateRoot: candidate,
+    expectedFileCount: expected.size,
+    candidateFileCount: actual.size,
+    missing,
+    extra,
+    mismatched,
+    metadataMismatches,
+  }
+}
+
+function parseArguments(argv) {
+  if (argv.length !== 2 || argv.some(value => !value || value.startsWith('-'))) {
+    throw new Error('usage: node distribution-parity.mjs <source-root> <candidate-root>')
+  }
+  return { sourceRoot: argv[0], candidateRoot: argv[1] }
+}
+
+export async function main(argv = process.argv.slice(2)) {
+  try {
+    const { sourceRoot, candidateRoot } = parseArguments(argv)
+    const result = await compareDistribution(sourceRoot, candidateRoot)
+    console.log(JSON.stringify(result, null, 2))
+    return result.ok ? 0 : 1
+  } catch (error) {
+    console.error(error instanceof Error ? error.message : String(error))
+    return 2
+  }
+}
+
+if (process.argv[1] !== undefined && fileURLToPath(import.meta.url) === resolve(process.argv[1])) {
+  process.exitCode = await main()
+}

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) }
 }