baldart 4.42.0 → 4.43.1

package/CHANGELOG.md

@@ -5,6 +5,29 @@ 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).
 
+## [4.43.1] - 2026-06-15
+
+**The npm publish workflow is now race-safe: pushing several `v*.*.*` tags close together can no longer leave `latest` on a lower version.** Publishing v4.41.0/4.42.0/4.43.0 together exposed the bug — the three tag-push workflow runs executed in **parallel**, and `npm publish` (with no explicit dist-tag) points `latest` at whichever version finishes **last chronologically**, not the highest. Real outcome: `latest` landed on **4.42.0**, so `npx baldart` installed a non-latest version (fixed by hand with `npm dist-tag add baldart@4.43.0 latest`). This release closes the race two ways: (1) a workflow-level **`concurrency` group** (`group: publish-npm`, `cancel-in-progress: false`) serializes all publish runs so they never race on the dist-tag and a publish is never cancelled; (2) a new final step **reconciles `latest` to the highest published version** — it computes the max stable semver across `npm view baldart versions` (unioned with the just-published `VERSION` to survive registry propagation lag, numeric per-segment compare so `4.10.0 > 4.9.0`) and repoints `latest` only when it has drifted. Because the runs are serialized, the last run always leaves `latest` on the maximum regardless of push order. The existing "Verify tag matches VERSION" guard is untouched. **PATCH** (CI/release-machinery bugfix, no change to installed surface or `baldart.config.yml` ⇒ schema-change propagation rule N/A).
+
+### Fixed
+
+- **`.github/workflows/publish-npm.yml` — race-safe `latest` dist-tag.** Added a `concurrency` group to serialize parallel tag-push publish runs, and a `Reconcile 'latest' dist-tag to highest published version` step that repoints `latest` at `max(npm view baldart versions ∪ VERSION)` via a self-contained numeric semver comparator (no `semver` dependency), only when `latest` drifts. Fixes `latest` landing on a lower version when multiple tags are pushed close together.
+
+### Changed
+
+- **`MAINTAINING.md` — release protocol note** that pushing multiple tags at once is now safe (since v4.43.1) and why.
+
+## [4.43.0] - 2026-06-15
+
+**The classic `/new` team-mode director stops bloating its own context by legitimately running the review cluster inline — the delegation gate is hardened to the same no-discretion enforcement the sequential path already carries.** A real run analysis (the same FEAT-0028/0029 investigation that produced v4.42.0) found the dominant orchestrator-context driver in team mode is NOT the review token volume (that already runs out-of-context in the `new-card-review` workflow) but the **director's turn count**: the team-mode delegation gate `D.1.6` was labelled "opt-in, additive" with a soft `IF available → delegate`, while the sequential path (`review-cycle.md` Phase 2.5x) carries a strict **MECHANICAL · NO discretion · MUST delegate · GATE VIOLATION if inline** clause. That asymmetry let a director legitimately run the chattiest sub-steps (the per-card Codex loop + per-card Simplify fan-out) inline, re-reading a growing prefix every turn. This release ports the strong clause verbatim into `D.1.6`, plus two pure-distillation fixes (batch the D.1.5 per-card diffs to `/tmp` and read only the compact summary; the same diffs-to-disk discipline on the sequential path for symmetry). Also lands the one **safe** survivor of the deferred worktree-prose cleanup: the `/nw` code-mode now **auto-appends** `.worktrees/` to `.gitignore` (idempotent + WARN) instead of leaving a programmatic `/new` run to create a git-tracked worktree. An adversarial review refuted the rest of that cleanup and a separate review-gate proposal (per-card AC-conformance gate + a second relevance-gating layer) as net-negative/regressive — both deferred. **MINOR** (FIX A changes which path runs by default in team mode — an observable behavior change; no removed surface, no new `baldart.config.yml` key ⇒ schema-change propagation rule N/A).
+
+### Changed
+
+- **`framework/.claude/skills/new/references/team-mode.md` — `D.1.6` delegation gate hardened** (`v4.34.0 → enforcement hardened`). The "opt-in, additive" framing is replaced with the verbatim no-discretion clause from `review-cycle.md` Phase 2.5x ("MECHANICAL, BINARY decision — you have NO discretion … the factors that feel like reasons to run inline are NOT inputs to this gate"), plus the twin telemetry log `D.1.6: GATE VIOLATION — ran inline despite Workflow available + new-card-review.js linked + non-trivial group`. Forces the cluster out of the director's context whenever the `Workflow` tool + `new-card-review.js` are present and the group is non-trivial.
+- **`framework/.claude/skills/new/references/team-mode.md` — D.1.5 diff batching (context economy).** The per-card effective-profile computation is now an explicit ONE-bash pass that writes each card's diff to `/tmp/diff-<CARD-ID>.txt` and derives `source|non-source` + doc-touch + the Step-A trigger count there; only the compact per-card summary + `--name-only` lists enter the director's context, never the raw diffs.
+- **`framework/.claude/skills/new/references/review-cycle.md` — sequential-path symmetry.** Phase 2.5x input-building writes the card's diff to `/tmp/diff-<CARD-ID>.txt` once and derives both the Step-A grep and `scopeFiles` from it (same diffs-to-disk discipline as team-mode, so the two paths stay symmetric).
+- **`framework/.claude/skills/worktree-manager/SKILL.md` — `/nw` code-mode `.gitignore` auto-heal.** When `.worktrees/` is not ignored, the code-mode path now auto-appends it (idempotent) and WARNs, instead of either silently creating a git-tracked worktree or hard-aborting (`exit 1`) on a non-attended `/new` run. (nw-docs keeps its interactive `exit 1` — that path is human-driven.)
+
 ## [4.42.0] - 2026-06-15
 
 **The `/new` worktree-setup can no longer pass on a fabricated baseline: the orchestrator now verifies the worktree on disk instead of trusting the subagent's self-report, and the setup subagent moves off `haiku`.** A real `/new` run reproduced **2/2** a silent failure — the background **worktree-setup** subagent (on `haiku`) returned a well-formed block reporting `baseline: pass` in ~6s **with no worktree on disk**: it pattern-matched the expected output instead of running the multi-step `/nw` skill, and the orchestrator trusted it because the baseline gate only ever checked the *returned* field, never the disk. This release closes both halves: (1) the worktree-setup subagent moves **`haiku → sonnet`** (running `/nw` via the Skill tool is a sustained tool-execution chain a too-weak model fabricates rather than executes); (2) a new **worktree integrity gate** (`setup.md §6a`) verifies the worktree with **orchestrator Bash** — `git worktree list --porcelain` + `test -d` + branch + `node_modules` — which a subagent cannot fabricate, and routes any failure to a **non-circular fallback chain** (`subagent → inline /nw → HALT`, no loop, with a build `timeout`). `new2`'s pre-flight gets the parallel mitigation (it cannot run Bash, so it returns non-falsifiable evidence the workflow string-matches — explicitly declared structurally weaker). Separately, the card-baseline validator is now **dependency-free**: it parsed cards with `js-yaml`, absent from the framework payload, so `require('js-yaml')` failed in consumers and silently disabled card-baseline validation (1b-iii) — replaced with a node-core `parseCardYaml`. **MINOR** (additive integrity gate + a behavior change to the worktree subagent model + a dependency-removing bugfix; no removed surface, the `/nw` `{path,branch,port}` contract is unchanged, and no new `baldart.config.yml` key ⇒ schema-change propagation rule N/A).

package/VERSION

@@ -1 +1 @@
-4.42.0
+4.43.1

package/framework/.claude/skills/new/references/review-cycle.md

@@ -37,7 +37,7 @@ so it surfaces in telemetry.
     `skip`/`light` ⇒ `qaTier:"light"` (qa-sentinel deferred to Final), `deep` **or any Phase 3.7 Step-A
     high-risk trigger on this card's diff** ⇒ `qaTier:"full"`). Compute the **Step-A detector**
     (`references/codex-gate.md` Step A) once here — it also tells the workflow's Codex pass the depth.
-  - `scopeFiles` ← this card's committed diff (`git diff --name-only "$TRUNK...HEAD"`, fallback `HEAD~1..HEAD`).
+  - `scopeFiles` ← this card's committed diff (`git diff --name-only "$TRUNK...HEAD"`, fallback `HEAD~1..HEAD`). **Diffs to disk (context economy, v4.43.0):** write the card's full diff to `/tmp/diff-<CARD-ID>.txt` once and derive BOTH the Step-A grep (above) and this `--name-only` list from it — never read the raw diff inline (mirrors the team-mode D.1.5 batching discipline, so the two paths stay symmetric).
   - `editableFiles` ← this card's **File Ownership Map** entries (the coder's write scope; `setup.md` step 3b).
   - `archBaselinePath` ← `/tmp/arch-baseline-<CARD-ID>.md` (persisted at `implement.md` step 5b).
   - `hasSecurityFiles` ← any `scopeFiles` path matches `paths.high_risk_modules`.

package/framework/.claude/skills/new/references/team-mode.md

@@ -162,12 +162,23 @@ After ALL agents in the group complete successfully:
    - **Sub-classify `TRIVIAL_CARDS` ⊆ `LIGHT_CARDS`** = cards that are `IS_TRIVIAL` on the committed diff (§ "Trivial-card fast-lane": `review_profile == skip` AND 0 Step-A triggers AND **non-source diff**). These are the LIGHT cards that have nothing for `code-reviewer` to review. (A `skip` card whose diff DID touch a source file is in `LIGHT_CARDS` but NOT `TRIVIAL_CARDS` — the guard keeps it on the code-review path.)
    - **Sub-classify `DOC_DEFER_CARDS`** (since v4.7.0, for #2 doc deferral) = cards with `review_profile == light` whose committed diff touches **NO documentation file** (no `.md`, no path under `${paths.references_dir}`, no data-model/ssot/api doc). Their per-card doc-review is deferred to the Final F.3 doc-reviewer. (Trivial cards, and any card whose diff touches a doc file, are NOT in this set — doc-review stays relevant for them.)
    - Log: `## D.1.5 Effective Profiles\n<CARD-ID>: profile=<floor> triggers=<n> diff=<source|non-source> → effective=<light|full> (<LIGHT_CARDS|FULL_CARDS>)<, TRIVIAL / DOC_DEFER if applicable>` per card. This single computation is the SSOT for D.2 (doc-reviewer scoping), D.3b/D.3c (already skipped for trivial), and D.4b (inclusion + per-card Codex profile: `light` cards → `/codexreview` `light`, `full` cards → `full`) — do NOT recompute it downstream.
+   - **Batching (context economy, v4.43.0):** compute the whole group in ONE bash pass, not N inline round-trips — write each card's committed diff to `/tmp/diff-<CARD-ID>.txt`, and in the SAME script derive per-card `source|non-source`, doc-file touch, and the Step-A trigger count (grep over the `/tmp` file). Read only the compact per-card summary (the `## D.1.5 Effective Profiles` log above) + the `--name-only` lists into context — **never the raw diffs inline** (§ "Context economy" — diffs to disk; same discipline D.3b already uses for its scope diff).
 
-1.6. **D.1.6 — Review-cluster workflow delegation gate (v4.34.0 — opt-in, additive)** — The group's
+1.6. **D.1.6 — Review-cluster workflow delegation gate (v4.34.0; enforcement hardened v4.43.0)** — The group's
    code-review cluster — **D.3b Simplify + D.4 QA + D.4b Codex** (per-card discovery) **and their fix
    application** — runs ONCE per wave OUTSIDE this orchestrator's context when delegated to a dynamic
    workflow. This is the single biggest context-economy win in team mode (the D.4b per-card Codex loop +
-   the D.3b per-card Simplify fan-out are the chattiest sub-steps).
+   the D.3b per-card Simplify fan-out are the chattiest sub-steps — running them inline is precisely what
+   bloats the director's context window across the wave).
+   **This is a MECHANICAL, BINARY decision — you have NO discretion** (same enforcement as the sequential
+   path, `references/review-cycle.md` § "Phase 2.5x — Branch"): if the delegation conditions below hold you
+   **MUST** delegate. The factors that feel like reasons to "just run it inline" — a single-card wave, a
+   small/well-scoped diff, "the context-economy benefit is marginal here", "a workflow once degenerated on
+   this project" (that concerns the `new2` whole-batch host — a *different* workflow), "inline is safer / I
+   have full control" — are **NOT inputs to this gate** and **MUST NOT** override it. The inline D.2→D.6
+   fallback exists **only** for installs where the `Workflow` tool is genuinely absent (the ELSE branch
+   below), never as a judgment-call alternative. If you run inline while the delegation conditions were met,
+   that is a **gate violation**: log `D.1.6: GATE VIOLATION — ran inline despite Workflow available + new-card-review.js linked + non-trivial group` so it surfaces in telemetry.
 
    - **IF** the `Workflow` tool is available **AND** `.claude/workflows/new-card-review.js` is present →
      **delegate the cluster for the whole group in ONE call.** First run **D.3a (AC-Closure Gate)** for

package/framework/.claude/skills/worktree-manager/SKILL.md

@@ -423,6 +423,16 @@ Supports three modes:
 # persist both onto the registry entry created in step 6 (R6). Every later step
 # reads them from the registry with a presence guard — never from in-context state.
 MAIN="$(git rev-parse --show-toplevel)"
+# .gitignore safety (auto-heal, NON-blocking — code-mode differs from nw-docs, which
+# hard-aborts). Without `.worktrees/` ignored the worktree is git-tracked and `git status`
+# on the main repo explodes. The programmatic /new path is NON-attended, so we MUST NOT
+# `exit 1` here (it would break a batch that today completes dirty-but-successful); instead
+# auto-append the line (idempotent, lossless — owning a one-line .gitignore edit is
+# framework-legitimate) and WARN. The grep guard means we append at most once.
+if [ ! -f "$MAIN/.gitignore" ] || ! grep -qE '^\.worktrees/?$' "$MAIN/.gitignore"; then
+  printf '\n.worktrees/\n' >> "$MAIN/.gitignore"
+  echo "WARN: appended '.worktrees/' to $MAIN/.gitignore (was missing — the worktree would otherwise be git-tracked)." >&2
+fi
 # Prefer git.trunk_branch; autodetect the repo's real default branch if the
 # config key is absent (consumer updated to >=4.0.0 without re-running
 # `configure`). Same fallback as nw-docs — never hard-fail on a resolvable repo.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "baldart",
-  "version": "4.42.0",
+  "version": "4.43.1",
   "description": "Claude Agent Framework - Reusable framework for coordinating AI agents and humans in software projects",
   "bin": {
     "baldart": "./bin/baldart.js"