baldart 4.52.4 → 4.53.1

package/framework/.claude/workflows/new-final-review.js

@@ -54,6 +54,7 @@ const FINDING = {
     evidence: { type: 'string', description: 'exact file:line + code quote' },
     minimal_fix_direction: { type: 'string' },
     domain: { enum: ['doc', 'security', 'migration', 'code', 'perf', 'test'], description: 'Domain-Override routing bucket' },
+    requires_action: { type: 'boolean', description: 'false = a VERIFIED observation that needs NO change anywhere (concern cleared / safe-as-is / advisory) — recorded for audit, NEVER routed to a writer. Omit (⇒ actionable) when a concrete edit is needed. If a change is needed but not by you (out of scope), keep true and say so in minimal_fix_direction (it surfaces as residual).' },
   },
 }
 const FINDINGS_SCHEMA = {
@@ -157,16 +158,19 @@ const codexPrompt =
   `Return codexAvailable:false ONLY if $REVIEW_FILE ends up containing "CODEX_NOT_FOUND" or stays empty after the FULL 10-minute window — NEVER because a single Bash call returned slowly. The script's existence is already verified, so a premature false here is a bug, not a capability gap.\n\n` +
   `${scopeBrief}\n\n${baselineBrief}\n\n` +
   `For each finding return: finding_id, title, severity (BLOCKER|HIGH|MEDIUM|LOW), confidence (0-100), evidence (exact file:line + code quote), minimal_fix_direction, and domain (doc|security|migration|code|perf|test). ` +
-  `Run the mandatory false-positive check on every finding and suppress the unconvincing ones (your findings are treated as already FP-validated). Set codexAvailable:true when the review ran.`
+  `Run the mandatory false-positive check on every finding and suppress the unconvincing ones (your findings are treated as already FP-validated). ` +
+  `Then the actionability check: an observation you have VERIFIED needs NO change anywhere (the fix direction would be "no fix required" / "acceptable as-is" / "verified non-issue") is not work — set requires_action:false on it (it is recorded but never sent to a fixer), or simply do not emit it. Emit requires_action true/omitted ONLY when a concrete edit is needed. Set codexAvailable:true when the review ran.`
 
 const docPrompt =
   `Cross-card documentation + SSOT-registry review over the batch diff, per ${protocolRef} Step F.3 (doc-reviewer row). Check doc consistency, ssot-registry completeness, and invariants across the changed files.\n\n${scopeBrief}\n\n${baselineBrief}\n\n` +
-  `You OWN the doc domain end-to-end: run the mandatory false-positive check on every finding yourself and SUPPRESS the unconvincing ones — your surviving findings are treated as already validated and are NOT re-judged by another agent (a generic code-reviewer judging prose would be cross-domain). Flag only a finding you genuinely cannot resolve as confidence < 80.\n\n` +
+  `You OWN the doc domain end-to-end: run the mandatory false-positive check on every finding yourself and SUPPRESS the unconvincing ones — your surviving findings are treated as already validated and are NOT re-judged by another agent (a generic code-reviewer judging prose would be cross-domain). ` +
+  `Then the actionability check: an observation you VERIFIED needs NO change (the fix direction would be "no fix required" / "already accurate") is not work — set requires_action:false (recorded, never sent to a fixer), or do not emit it. Flag only a finding you genuinely cannot resolve as confidence < 80.\n\n` +
   `Return findings (domain almost always "doc"). Use the finding schema fields.`
 
 const apiPrompt =
   `API / data-model / performance / cost defect review over the batch diff, per ${protocolRef} Step F.3 (api-perf-cost-auditor row). Look for unbounded reads, N+1, missing pagination, contract drift, and cost regressions.\n\n${scopeBrief}\n\n${baselineBrief}\n\n` +
-  `You OWN the api/perf/data domain end-to-end: run the mandatory false-positive check on every finding yourself and SUPPRESS the unconvincing ones — your surviving findings are treated as already validated and are NOT re-judged by another agent. Flag only a finding you genuinely cannot resolve as confidence < 80.\n\n` +
+  `You OWN the api/perf/data domain end-to-end: run the mandatory false-positive check on every finding yourself and SUPPRESS the unconvincing ones — your surviving findings are treated as already validated and are NOT re-judged by another agent. ` +
+  `Then the actionability check: an observation you VERIFIED needs NO change (the fix direction would be "no fix required" / "acceptable as-is" / "optional") is not work — set requires_action:false (recorded, never sent to a fixer), or do not emit it. Flag only a finding you genuinely cannot resolve as confidence < 80.\n\n` +
   `Return findings with domain in {code, perf, migration, security}. Use the finding schema fields.`
 
 const qaPrompt =
@@ -238,7 +242,7 @@ for (const item of reviewResults) {
 if (!codexRan) {
   codexEngine = 'code-reviewer (fallback)'
   const fb = await agent(
-    `Codex was unavailable for the batch final review. Run the FULL code review yourself over the batch diff, per ${protocolRef} Step F.3.\n\n${scopeBrief}\n\n${baselineBrief}\n\nReturn findings using the schema fields, with a self false-positive check applied.`,
+    `Codex was unavailable for the batch final review. Run the FULL code review yourself over the batch diff, per ${protocolRef} Step F.3.\n\n${scopeBrief}\n\n${baselineBrief}\n\nReturn findings using the schema fields, with a self false-positive check applied. An observation you VERIFIED needs NO change (fix direction "no fix required" / "acceptable as-is") is not work — set requires_action:false (recorded, never sent to a fixer), or do not emit it.`,
     { label: 'code-reviewer (fallback)', phase: 'Review', agentType: 'code-reviewer', schema: FINDINGS_SCHEMA }
   )
   // the fallback code-reviewer IS the primary code-review engine here and applied its own FP
@@ -247,6 +251,12 @@ if (!codexRan) {
   if (fb && Array.isArray(fb.findings)) raw.push(...fb.findings.map((f) => ({ ...f, source: 'code-reviewer', preValidated: true })))
 }
 
+// Globally-unique finding_id at the fan-in (parity with new-card-review.js). Finders number F###
+// INDEPENDENTLY → a Codex F003 and a doc F003 collide; downstream telemetry/routing (new2 ledger,
+// the skill's F.5 partition) keys on finding_id, so a collision conflates them. Prefix source +
+// running index → uniqueness without losing the human-readable id.
+raw.forEach((f, i) => { f.finding_id = `${f.source || 'src'}#${i}:${f.finding_id || ('F' + i)}` })
+
 // ───────────────────────────────────────────────────────────────────────────
 // Phase Verify (F.4) — specialist-owned validation (NOT a generic code-reviewer re-judge).
 //   Each domain specialist owns its lane end-to-end: it FP-checks its OWN findings in the
@@ -292,20 +302,31 @@ async function verifyFinding(f) {
   return { ...f, classification: (v && v.classification) || 'NEEDS_MANUAL_CONFIRMATION' }
 }
 
-// ---- Result: drop FALSE_POSITIVE, keep VERIFIED + NEEDS_MANUAL (F.4 step 9) --
-const findings = classified.filter((f) => f.classification !== 'FALSE_POSITIVE')
+// ---- Result: drop FALSE_POSITIVE, segregate no-action, keep actionable VERIFIED + NEEDS_MANUAL --
+// Actionability gate (parity with new-card-review.js): a VERIFIED finding needing NO change must NOT
+// reach the skill's F.5 writer partition. Honoured ONLY for MED/LOW — BLOCKER/HIGH always actionable.
+// No silent drop: no-action findings are returned separately (noActionFindings) + counted, so the
+// skill can log them; only the actionable set flows into `findings` (what F.5 routes to writers).
+const NO_ACTION_RE = /(^|[.\s(])(no\s+(fix|change|action)\s+(is\s+)?(required|needed)|none\s+(needed|required)|not\s+a\s+(defect|bug|correctness\s+bug)|acceptable\s+as[-\s]is|verified\s+(safe|non[-\s]issue)|no\s+action\s+(needed|required))([.\s,;)]|$)/i
+const isNoAction = (f) => f.classification === 'VERIFIED' && (f.severity !== 'BLOCKER' && f.severity !== 'HIGH') &&
+  (f.requires_action === false || NO_ACTION_RE.test(String(f.minimal_fix_direction || '')))
+const noActionFindings = classified.filter(isNoAction)
+const noActionSet = new Set(noActionFindings)
+const findings = classified.filter((f) => f.classification !== 'FALSE_POSITIVE' && !noActionSet.has(f))
+for (const f of noActionFindings) log(`Final review: no-action finding recorded (not routed to a writer): [${f.finding_id}] ${f.severity} ${f.domain} — ${f.title} (${f.requires_action === false ? 'requires_action:false' : 'no-action-inferred'})`)
 const summary = {
   total: raw.length,
   verified: classified.filter((f) => f.classification === 'VERIFIED').length,
+  noAction: noActionFindings.length,
   falsePositive: classified.filter((f) => f.classification === 'FALSE_POSITIVE').length,
   needsManual: classified.filter((f) => f.classification === 'NEEDS_MANUAL_CONFIRMATION').length,
   blockers: classified.filter((f) => f.classification === 'VERIFIED' && f.severity === 'BLOCKER').length,
   highs: classified.filter((f) => f.classification === 'VERIFIED' && f.severity === 'HIGH').length,
   failingGates: gateTable.filter((g) => g.status === 'FAIL').map((g) => g.gate),
 }
-log(`Final review done: ${summary.verified} verified (${summary.blockers} BLOCKER / ${summary.highs} HIGH), ${summary.needsManual} needs-manual, ${summary.failingGates.length} failing gate(s). Engine: ${codexEngine}.`)
+log(`Final review done: ${summary.verified} verified (${summary.blockers} BLOCKER / ${summary.highs} HIGH), ${summary.noAction} no-action (recorded), ${summary.needsManual} needs-manual, ${summary.failingGates.length} failing gate(s). Engine: ${codexEngine}.`)
 
-return { codexEngine, findings, gateTable, summary }
+return { codexEngine, findings, noActionFindings, gateTable, summary }
 
 function emptySummary() {
   return { total: 0, verified: 0, falsePositive: 0, needsManual: 0, blockers: 0, highs: 0, failingGates: [] }

package/framework/.claude/workflows/new2.js

@@ -268,7 +268,7 @@ try {
       `ROLE BOUNDARY (specialization integrity): you are the OPS/GIT agent. You NEVER edit source or doc files — any needed content change belongs to the coder specialist; report it instead.\n\n` +
       `DETERMINISTIC GATE POLICIES (NO user prompts):\n` +
       `• G1 dirty-tree (main repo ${MAIN}): partition framework-managed noise exactly as setup.md step 3 ($METRICS=${METRICS}, .baldart/generated|state.json|skill-conflicts.json — NOT overlays/). Genuine user work → auto-stash 'baldart-new2-${firstCard}' (main checkout) and record the label. Never commit/abort/prompt.\n` +
-      `• Worktree (setup.md step 4): create ONE code worktree off ${TRUNK}; install deps; assign a port; run the baseline (tsc+lint+build). Copy the gitignored env artifacts in stack.env_files (resolved: ${JSON.stringify(ENV_FILES)}) — FILES via \`cp\` (plain cp, dereferences symlinks; never cp -P), DIRS via \`cp -r\`; a missing FILE → WARN (never abort). Do NOT add .env.example (tracked → already in the checkout) and do NOT bulk-copy untracked files from the main repo (avoids stray backlog cards in the worktree). Use the git-authoritative idempotency pre-check. E2: baseline FAILS → do NOT fix it yourself (role boundary — the coder specialist repairs it); return baseline:'fail' + a baselineLog precise enough for a coder to act (failing command, error excerpt, suspect files). Wrap the build in \`timeout 600 <build-cmd>\` (10 min); if killed, return baseline:'timeout' + the partial log. On baseline PASS, VERIFY the worktree on disk and return EVIDENCE (not just a flag): set worktreeVerified:true ONLY after running \`git -C ${MAIN} worktree list --porcelain\` (the worktree path MUST appear in the output) AND \`test -d <wt>/node_modules\` AND confirming the branch; put the LITERAL stdout into worktreeEvidence{ worktreeListPorcelain, artifactsLs:\`ls -la <wt>/node_modules <wt>/.next 2>/dev/null | head\`, baselineLogTail }. The workflow string-matches this evidence — NEVER report worktreeVerified:true without actually running the commands.\n` +
+      `• Worktree (setup.md step 4): the ENTIRE build sequence (worktree add → install → env copy → port → registry → baseline) is the SSOT script \`scripts/setup-worktree.sh\` — the SAME script /nw and classic /new run. Do NOT hand-roll the bash (a re-authored copy is the duplication CLAUDE.md forbids, and the script cannot fabricate a baseline or stall). Resolve the branch from the lead/parent card's git_strategy.branch (fallback feat/<PARENT-ID|lead>-<slug>) + a kebab slug, then derive the git-authoritative idempotency pre-check (existing worktree for the branch → reset the half-built orphan before running, never re-create into a fail-loud collision). Resolve the script: \`SETUP_SH="$(ls .framework/framework/.claude/skills/worktree-manager/scripts/setup-worktree.sh .claude/skills/worktree-manager/scripts/setup-worktree.sh 2>/dev/null | head -1)"\`. Run it (foreground — you ARE the background context here): \`bash "$SETUP_SH" --main ${MAIN} --trunk ${TRUNK} --branch <branch> --slug <slug> --cards "${cardIds.join(',')}" --group-parent "<PARENT|>" --env-files "${ENV_FILES.join(',')}" --manifest /tmp/new2-wt-${firstCard}.txt\`. It installs non-interactively, copies stack.env_files (FILES plain cp / DIRS cp -R / missing FILE → WARN, never abort; never .env.example, never bulk-copy untracked), allocates a locked port, writes the registry, and runs the baseline under timeout 600 (tsc/lint report-but-continue, build STOP-on-fail). Read the manifest block (status/baseline/worktree_path/port/created_at/baseline_log): map baseline → your baseline field (pass|fail|timeout) and baseline_log → baselineLog. E2: a \`baseline:fail\`/\`status:error\` build break is NOT yours to fix (role boundary — the coder repairs it); just return it precisely. Then, INDEPENDENTLY of the manifest, VERIFY the worktree on disk and return EVIDENCE (the workflow E2.5 gate string-matches it, never the script's word): set worktreeVerified:true ONLY after running \`git -C ${MAIN} worktree list --porcelain\` (the worktree path MUST appear) AND \`test -d <wt>/node_modules\` AND confirming the branch; put the LITERAL stdout into worktreeEvidence{ worktreeListPorcelain, artifactsLs:\`ls -la <wt>/node_modules <wt>/.next 2>/dev/null | head\`, baselineLogTail }. If the script is ABSENT (older subtree), fall back to running the sequence inline per setup.md step 4 prose. NEVER report worktreeVerified:true without actually running the verify commands.\n` +
       codexResolveBullet +
       g3Bullet +
       `• G4 card-field validation (setup.md 1b/1c): card missing requirements/acceptance_criteria/files_likely_touched → EXCLUDE (excluded[] + reason). Never HALT for one bad card.\n` +

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "baldart",
-  "version": "4.52.4",
+  "version": "4.53.1",
   "description": "Claude Agent Framework - Reusable framework for coordinating AI agents and humans in software projects",
   "bin": {
     "baldart": "./bin/baldart.js"