baldart 4.24.3 → 4.25.0

package/CHANGELOG.md

@@ -5,6 +5,16 @@ All notable changes to BALDART will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [4.25.0] - 2026-06-11
+
+**`new2`: deterministic per-card review matrix — `balanced` no longer spawns every specialist on every card.** The old fan-out ran code-reviewer + doc-reviewer + qa-sentinel + api-perf-cost-auditor (+ security-reviewer) unconditionally at `balanced`: an api-perf pass on a doc-only card, a doc pass on a pure-code card — 1–3 wasted spawns per card. Each specialist now runs IFF its domain is evidenced by the card's actual surface (`scopeFiles ∪ MAY-EDIT`), computed deterministically in JS (no agent judgement) and audited via a `review-matrix` ledger row per card. **MINOR** (review-behavior capability on the EXPERIMENTAL `new2` surface only; no config key, no change to `/new` — its interactive profiles are untouched; the schema-change propagation rule does not apply).
+
+### Changed
+
+- **`framework/.claude/workflows/new2.js` — relevance-gated `balanced` fan-out.** `touchesCode` → code-reviewer + qa-sentinel; `touchesDocs` (`.md`/`.mdx` or under `paths.docs_dir|references_dir|wiki_dir|prd_dir|design_system`) → doc-reviewer (on a doc-ONLY card it IS the core finder — code-reviewer and qa-sentinel are skipped); `touchesApiData` (superset of the final review's `hasApiDataFiles` regex) → api-perf-cost-auditor; the v4.24.2 `securityRelevant` gate → security-reviewer. Surface = `scopeFiles ∪ MAY-EDIT`, so a DoD-mandated doc the implementer FORGOT to edit still triggers doc-reviewer (it's in MAY-EDIT). **Fail-safes**: `deep` keeps the unconditional full fan-out (Rule C escalation is respected); an empty surface (no evidence) falls back to the full fan-out — absence of evidence is not evidence of absence. `light`/`skip` unchanged.
+- **`new2.js` Phase Final — the F-041 `singleCard`/slim skip is now coverage-gated.** The final review's doc pass is skipped for a single-card batch ONLY when doc-reviewer ACTUALLY ran per-card (`reviewersRun`); otherwise it runs as the missing-doc-update safety net — so gating a per-card specialist off never leaves its domain unreviewed at batch level. This also closes a **latent F-041 hole**: under `light`, doc-reviewer never ran per-card, yet the slim skip still suppressed the final doc pass for single-card batches.
+- **`new2.js` telemetry — `per_card[].reviewers`** records the gated matrix per card, so the A/B spawn accounting can measure exactly what the gating saves.
+
 ## [4.24.3] - 2026-06-10
 
 **`new2`: two follow-ups from the v4.24.2 logic review — epic closure no longer misses deferred cards, and the owner-gated classification reaches the final review.** Both are "parallel location" gaps of earlier fixes (the v4.17.2 meta-lesson): v4.22.1's epic-closure and v4.24.1's owner-gated deferral each missed one site. **PATCH** (bug-fix to the EXPERIMENTAL `new2` surface only; no config key, no change to `/new`).

package/VERSION

@@ -1 +1 @@
-4.24.3
+4.25.0

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

@@ -460,12 +460,40 @@ async function runCard(cardId, cardPath) {
   // v4.18.0 — at `light`, Codex is the SOLE finder (cost-shift off Claude); `code-reviewer` is the
   // fallback when the companion is unavailable. The FP-gate equivalent is preserved downstream: any
   // block routes through resolve(), whose mandatory adversarial judge (new2-resolve F-015, code domain
-  // → code-reviewer) cross-checks the Codex finding before a fix/followup. `balanced`/`deep` unchanged.
+  // → code-reviewer) cross-checks the Codex finding before a fix/followup.
   const codexAvail = !!sharedCtx.codexResolved && !!sharedCtx.codexScriptPath
-  const reviewers = reviewProfile === 'skip' ? []
-    : reviewProfile === 'light' ? (codexAvail ? ['codex'] : ['code-reviewer'])
-    : ['code-reviewer', 'doc-reviewer', 'qa-sentinel', 'api-perf-cost-auditor'].concat(
-        securityRelevant ? ['security-reviewer'] : [])
+  // B6 (v4.25.0) — deterministic per-card review matrix. `balanced` no longer means "every
+  // specialist on every card": each one runs IFF its domain is evidenced by the card's actual
+  // surface (scopeFiles ∪ MAY-EDIT), computed deterministically HERE in JS and audited via a
+  // `review-matrix` ledger row. `deep` keeps the unconditional full fan-out (Rule C assigns it
+  // to high-risk cards — respect the escalation). Coverage holds at batch level: the final
+  // review's doc pass stays the missing-doc-update safety net (its singleCard/slim skip is now
+  // gated on doc-reviewer having ACTUALLY run per-card — see Phase Final), and its api-perf
+  // pass keys on hasApiDataFiles with a regex this matrix supersets — so gating OFF a per-card
+  // specialist never leaves its domain unreviewed.
+  const surface = dedupe((scopeFiles || []).concat(mayEdit || []))
+  const docDirs = [paths.docs_dir, paths.references_dir, paths.wiki_dir, paths.prd_dir, paths.design_system].filter(Boolean)
+  const isDocFile = (f) => /\.(md|mdx)$/i.test(String(f)) || docDirs.some((d) => String(f).includes(String(d)))
+  const touchesDocs = surface.some(isDocFile)
+  const touchesCode = surface.some((f) => !isDocFile(f))
+  // superset of new-final-review's hasApiDataFiles regex — per-card coverage may exceed the
+  // final pass, never lag it.
+  const touchesApiData = surface.some((f) => /api\/|data-model|\.sql$|migrations?\/|server|route|edge|middleware|cron|queue|worker|prisma|drizzle|supabase|schema/i.test(String(f)))
+  const noEvidence = surface.length === 0 // fail-safe: absence of evidence ≠ evidence of absence
+  const FULL_FANOUT = ['code-reviewer', 'doc-reviewer', 'qa-sentinel', 'api-perf-cost-auditor'].concat(securityRelevant ? ['security-reviewer'] : [])
+  let reviewers
+  if (reviewProfile === 'skip') reviewers = []
+  else if (reviewProfile === 'light') reviewers = codexAvail ? ['codex'] : ['code-reviewer']
+  else if (reviewProfile === 'deep' || noEvidence) reviewers = FULL_FANOUT
+  else { // balanced — relevance-gated
+    reviewers = []
+    if (touchesCode) reviewers.push('code-reviewer')
+    if (touchesDocs) reviewers.push('doc-reviewer') // doc-ONLY card: doc-reviewer IS the core finder
+    if (touchesCode) reviewers.push('qa-sentinel')  // skip for doc-only cards — no behavior to QA
+    if (touchesApiData) reviewers.push('api-perf-cost-auditor')
+    if (securityRelevant) reviewers.push('security-reviewer')
+  }
+  if (reviewProfile !== 'skip') g('review-matrix', 'PLANNED', `[${reviewProfile}${noEvidence && reviewProfile === 'balanced' ? '→conservative-full (no surface evidence)' : ''}] ${reviewers.join('+') || '(none)'} · docs:${touchesDocs} code:${touchesCode} api/data:${touchesApiData} sec:${securityRelevant}`)
   const reviewSchema = { type: 'object', required: ['blocks', 'scopeExpansion'], additionalProperties: true,
     properties: { blocks: { type: 'array', items: { type: 'object', additionalProperties: true } }, scopeExpansion: { type: 'array', items: { type: 'object', additionalProperties: true } }, note: { type: 'string' } } }
   let reviewResults = []
@@ -535,7 +563,7 @@ async function runCard(cardId, cardPath) {
     for (const sx of grp) g('scope-expansion', s === 'resolved' ? 'INTEGRATED' : 'FOLLOWUP', sx.evidence || '')
   }
 
-  if (cardBlocked) { await rollbackCard(cardId, mayEdit); return { card: cardId, status: 'followup', gates, commit: '-', scopeFiles, archBaselinePath: `/tmp/arch-baseline-${cardId}.md` } }
+  if (cardBlocked) { await rollbackCard(cardId, mayEdit); return { card: cardId, status: 'followup', gates, commit: '-', scopeFiles, reviewersRun: reviewers, archBaselinePath: `/tmp/arch-baseline-${cardId}.md` } }
 
   // --- Phase 4 — commit (F-023: Haiku + git-status reconcile, never git add -A). ---
   // F-040/H — DONE policy. A card with an OPEN owner-gated/policy-deferred AC commits its code but
@@ -578,6 +606,9 @@ async function runCard(cardId, cardPath) {
     // (A3): an 'unresolved' class means the DoD is genuinely unmet → the card stays IN_PROGRESS.
     deferred: deferredOpen,
     deferredClasses: Array.from(deferredClasses),
+    // B6 — which reviewers ACTUALLY ran (the gated matrix); Phase Final keys its slim/skip
+    // decision on this, and per_card telemetry records it for the A/B spawn accounting.
+    reviewersRun: reviewers,
     scopeFiles, archBaselinePath: `/tmp/arch-baseline-${cardId}.md`, gates,
   }
 }
@@ -675,9 +706,15 @@ if (committed.length && !degraded) {
       firstCardId: firstCard, worktreePath: sharedCtx.worktreePath, baseBranch: TRUNK,
       cardPaths: committed.map((r) => pathById[r.card]).filter(Boolean),
       reviewScopeFiles, archBaselinePaths: allArch, hasApiDataFiles, config: cfg,
-      // F-041 — single-card batch: doc-reviewer + api-perf already ran per-card and there is
-      // NO cross-card conflict to find. Keep only the cross-model Codex pass + qa gates.
-      singleCard: committed.length === 1,
+      // F-041 + B6 — slim the final pass (skip its doc-reviewer) ONLY when doc-reviewer
+      // ACTUALLY ran per-card for this single card. The old unconditional `length === 1` was
+      // built on the premise "doc + api-perf already ran per-card" — false under the gated
+      // review matrix (and it was ALREADY false under `light`, a latent F-041 coverage hole
+      // this closes). When per-card doc review was gated off, the final doc pass is the
+      // missing-doc-update safety net and must run even for a single card. api-perf at the
+      // final pass is independently gated by hasApiDataFiles (regex the per-card matrix
+      // supersets), so its coverage is consistent either way.
+      singleCard: committed.length === 1 && ((committed[0].reviewersRun || []).includes('doc-reviewer')),
     })
   } catch (e) { if (e && isTransient(e)) noteDegraded('outage'); final = null }
 
@@ -840,7 +877,7 @@ function buildTelemetry() {
     // cost — total_tokens via budget.spent() delta; agent_count via counter; wall_clock_s stamped by the SKILL.
     total_tokens: totalTokens,
     agent_count: agentCount,
-    per_card: perCardResults.map((r) => ({ card: r.card, status: r.status, deferred: !!r.deferred, deferredClasses: r.deferredClasses || [], gates: (r.gates || []).length })),
+    per_card: perCardResults.map((r) => ({ card: r.card, status: r.status, deferred: !!r.deferred, deferredClasses: r.deferredClasses || [], reviewers: r.reviewersRun || [], gates: (r.gates || []).length })),
     stats_requested: !!FLAGS.stats,
   }
 }

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "baldart",
-  "version": "4.24.3",
+  "version": "4.25.0",
   "description": "Claude Agent Framework - Reusable framework for coordinating AI agents and humans in software projects",
   "bin": {
     "baldart": "./bin/baldart.js"