baldart 4.2.1 → 4.2.2
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/CHANGELOG.md +10 -0
- package/VERSION +1 -1
- package/framework/.claude/skills/new/SKILL.md +54 -26
- package/package.json +1 -1
package/CHANGELOG.md
CHANGED
|
@@ -5,6 +5,16 @@ All notable changes to BALDART will be documented in this file.
|
|
|
5
5
|
The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
|
|
6
6
|
and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
|
|
7
7
|
|
|
8
|
+
## [4.2.2] - 2026-06-03
|
|
9
|
+
|
|
10
|
+
**`/new` Phase 0 stops blocking on framework-owned noise: telemetry-only dirty trees and `baldart update`/subtree commits are auto-ignored.** Every batch tripped its own Phase 0 gates: (1) the dirty-tree gate fired on `${paths.metrics}/archive/batch-tracker-*.md` + `skill-runs.jsonl` + `sessions/` — telemetry that Phase 8 writes *after* the merge and never commits, so the next batch always saw a "dirty" tree and forced a stash/commit decision; (2) the divergence gate fired on `.framework/` subtree commits + the `[CHORE] baldart update …` chore, treating expected framework-management divergence as the FEAT-0006 orphan-commit pattern and forcing a push/cherry-pick decision. Both gates now **partition the working tree / the ahead-commits before prompting** and surface only genuine in-progress user work. The FEAT-0006 protection is intact — real orphan commits and real uncommitted work still gate. **PATCH** (bugfix to an existing gate's classification; no new agent/skill/template, no `baldart.config.yml` key — `paths.metrics` already exists).
|
|
11
|
+
|
|
12
|
+
> **Why.** Phase 0 exists because of a real incident (FEAT-0006: an unpushed orphan commit + diverged trunk caused data loss), so the gates can't be removed. But they were classifying *framework-generated artifacts as if they were user state* — the skill's own Phase 8 telemetry and the `baldart update` subtree commits — and raising a non-decision to the user on every single `/new` run. The fix is surgical classification, not relaxation: the dirty-tree gate filters paths under `$METRICS` (resolved from `paths.metrics`) and gates only on the remainder; the divergence gate reclassifies each ahead commit (subtree merge into `.framework/`, `baldart update`/`add` chore, or `.framework/`-only diff) as framework-management and counts only genuine unpushed commits. Phase 6c's batch-close assertion gets the same reclassification so the noise doesn't re-appear at the end. `/prd` and `/nw` were already lean (read-only pre-flight, branch from `origin/$TRUNK`) and needed no change. Aligns with the standing "respect explicit user intent — no silent confirmation gates for non-decisions" principle.
|
|
13
|
+
|
|
14
|
+
### Changed
|
|
15
|
+
|
|
16
|
+
- **`framework/.claude/skills/new/SKILL.md`** — Phase 0 step 0 now resolves `$METRICS` (`paths.metrics`, default `docs/metrics`). Step 3 (dirty-tree gate) partitions `git status --porcelain`, dropping framework telemetry under `$METRICS`; gates only on `$USER_DIRTY`, otherwise logs `Dirty: framework-telemetry-only (auto-ignored)` and proceeds with no `AskUserQuestion`. Step 4 (divergence gate) and Phase 6c step 4 (batch-close divergence assertion) reclassify ahead commits, count only `$GENUINE_AHEAD`, auto-ignore `$FW_SKIPPED` framework-management commits, and branch on `$BEHIND`/`$GENUINE_AHEAD`. Step 5 log template extended with the two new auto-ignored states.
|
|
17
|
+
|
|
8
18
|
## [4.2.1] - 2026-06-03
|
|
9
19
|
|
|
10
20
|
**`/prd` pre-dev audit: `code-reviewer` swapped for `plan-auditor` (card grounding) in the `check-audit` team.** The Step 6 pre-development audit ran `code-reviewer` on backlog `.yml` cards — but `code-reviewer` is built around a *diff* (scope = `git diff --name-only`, diff-simulation pass, completion-report cross-check, line-range/`repro_steps` findings schema, `PASS/FAIL/NEEDS_REWORK` verdict), none of which applies before any code exists. The audit had to re-purpose it with an ad-hoc mandate and override its native output format. `plan-auditor` is the agent purpose-built for this surface (native `.yml` INPUT TYPE DETECTION + BACKLOG CARD ATTACK SURFACE + native `[Target: <field>]` tagging + project memory), so it now fills that slot. **PATCH** (refinement of an existing capability — swaps which already-shipped agent audits cards; no new agent/skill/template, no `baldart.config.yml` key).
|
package/VERSION
CHANGED
|
@@ -1 +1 @@
|
|
|
1
|
-
4.2.
|
|
1
|
+
4.2.2
|
|
@@ -141,6 +141,7 @@ Trunk branch: [resolved git.trunk_branch — Phase 0 step 0 populates]
|
|
|
141
141
|
0. **Feature gate + config resolution (BLOCKING)** — before anything else:
|
|
142
142
|
- Read `features.has_backlog` from `baldart.config.yml`. If it is `false` (or the key is absent and the user confirms there is no backlog), this skill REFUSES to run: print "`/new` operates on backlog cards and requires `features.has_backlog: true` — run `npx baldart configure` to enable." and HALT. Do NOT proceed to step 1.
|
|
143
143
|
- Resolve `$TRUNK` = `git.trunk_branch` from `baldart.config.yml`. **When the key is absent** (consumer updated to ≥4.0.0 without re-running `configure`), do NOT hard-assume `develop` — autodetect the repo's real default branch exactly as worktree-manager does, so `/new` and `nw` agree on the base: `git -C "$MAIN" symbolic-ref --quiet refs/remotes/origin/HEAD` (strip `refs/remotes/origin/`), else the first existing local branch among `develop` / `main` / `master`. A `main`-trunk repo defaulted to `develop` here would diverge from the worktree base `nw` picks and break every `git diff "$TRUNK...HEAD"` gate. Only HALT ("Trunk branch unresolved — run `npx baldart configure`") if nothing resolves. Persist the resolved value as `Trunk branch:` in the tracker `## Worktree` section. **Every later Phase 0 / Phase 6c bash snippet that references the integration trunk MUST use `$TRUNK`, never a baked-in `develop`.** Begin every later consumer with a guard: if `$TRUNK` is empty → HALT with "Trunk branch unresolved — re-read `git.trunk_branch` from the tracker".
|
|
144
|
+
- Resolve `$METRICS` = `paths.metrics` from `baldart.config.yml` (default `docs/metrics`). This is the framework-owned telemetry directory written by Phase 8 (tracker archive, `skill-runs.jsonl`, `sessions/`). The dirty-tree gate (step 3) reads `$METRICS` to recognise — and never surface — its own telemetry output. Persist it as `Metrics dir:` in the tracker `## Worktree` section.
|
|
144
145
|
|
|
145
146
|
1. **Resolve `$MAIN`** — the absolute path of the main repo (not a worktree). If `/new` was invoked from inside a worktree, walk up to the parent repo via `git rev-parse --show-superproject-working-tree` or `git worktree list` until you find the non-worktree root. Persist as `Main repo:` in the tracker `## Worktree` section. **Write `$MAIN` to the tracker the moment it is computed** — every later consumer (Phase 6c, Phase 6b) MUST re-read it from the tracker and HALT with "`$MAIN` absent from tracker" if the field is missing or empty, never silently use an undefined `$MAIN` (it does not survive context compaction).
|
|
146
147
|
|
|
@@ -149,11 +150,20 @@ Trunk branch: [resolved git.trunk_branch — Phase 0 step 0 populates]
|
|
|
149
150
|
git -C "$MAIN" fetch origin --quiet
|
|
150
151
|
```
|
|
151
152
|
|
|
152
|
-
3. **Dirty-tree gate (BLOCKING)** — capture the working tree state of the main repo:
|
|
153
|
+
3. **Dirty-tree gate (BLOCKING — framework telemetry is auto-ignored, never surfaced)** — capture the working tree state of the main repo, then **partition it** so the gate fires only on genuine in-progress user work:
|
|
153
154
|
```bash
|
|
154
|
-
git -C "$MAIN" status --porcelain
|
|
155
|
-
|
|
156
|
-
|
|
155
|
+
PORCELAIN="$(git -C "$MAIN" status --porcelain)"
|
|
156
|
+
# Drop framework-owned telemetry THIS skill writes in Phase 8 (tracker archive,
|
|
157
|
+
# skill-runs.jsonl, sessions/) and never commits. Porcelain lines are "XY path";
|
|
158
|
+
# paths with special chars are quoted. $METRICS resolved in step 0 (e.g. docs/metrics).
|
|
159
|
+
USER_DIRTY="$(printf '%s\n' "$PORCELAIN" \
|
|
160
|
+
| grep -vE "^.{3}\"?${METRICS}/" \
|
|
161
|
+
| grep -vE "^.{3}\"?${METRICS}\"?$" \
|
|
162
|
+
| grep -v '^[[:space:]]*$')"
|
|
163
|
+
```
|
|
164
|
+
**Why**: Phase 8 copies the batch tracker into `$METRICS/archive/` and appends to `$METRICS/skill-runs.jsonl` *after* the merge, and never commits them. If those untracked telemetry files tripped this gate, **every batch would block on the previous batch's metrics** — a self-inflicted loop. They are not user work and the user is never asked about them.
|
|
165
|
+
- If `$PORCELAIN` is non-empty but `$USER_DIRTY` is **empty** (only telemetry under `$METRICS` is dirty) → do **NOT** gate. Write `Dirty: framework-telemetry-only (auto-ignored)` to the tracker and proceed to step 4. No `AskUserQuestion`.
|
|
166
|
+
- If `$USER_DIRTY` is **non-empty** (genuine uncommitted user work) → invoke `AskUserQuestion`:
|
|
157
167
|
- Question: `"Main repo ($MAIN) ha modifiche non committate prima di partire con la batch. Come procedo?"`
|
|
158
168
|
- Options (max 4):
|
|
159
169
|
1. **"Stash automatico (restore in Phase 6c)"** — `$MAIN` is the main checkout (NOT a worktree), so a stash here is safe. Run `git -C "$MAIN" stash push -u -m "baldart-new-phase0-<FIRST-CARD-ID>-<timestamp>"` and write the **stash MESSAGE label** (`baldart-new-phase0-<FIRST-CARD-ID>-<timestamp>`) to the tracker under `## Workspace Snapshot: <message-label> (created <timestamp>)`. Phase 6c resolves the stash by this message — NEVER by a positional `stash@{N}`, because other stashes pushed during the batch (on the main checkout) would shift the index. Do NOT record `stash@{0}`.
|
|
@@ -163,23 +173,40 @@ Trunk branch: [resolved git.trunk_branch — Phase 0 step 0 populates]
|
|
|
163
173
|
|
|
164
174
|
Do NOT silently proceed. Do NOT auto-stash without the user picking option 1.
|
|
165
175
|
|
|
166
|
-
4. **Divergence gate (BLOCKING)** — compare local `$TRUNK` against `origin/$TRUNK` (the trunk resolved in step 0):
|
|
176
|
+
4. **Divergence gate (BLOCKING — framework-management commits do NOT count as orphan commits)** — compare local `$TRUNK` against `origin/$TRUNK` (the trunk resolved in step 0):
|
|
167
177
|
```bash
|
|
168
|
-
git -C "$MAIN" rev-list --left-right --count "origin/$TRUNK...$TRUNK"
|
|
178
|
+
read BEHIND AHEAD <<< "$(git -C "$MAIN" rev-list --left-right --count "origin/$TRUNK...$TRUNK")"
|
|
169
179
|
```
|
|
170
|
-
|
|
171
|
-
|
|
172
|
-
|
|
173
|
-
|
|
174
|
-
-
|
|
180
|
+
`$BEHIND` / `$AHEAD` are the raw counts. Before branching, **reclassify the ahead commits**: commits produced by `baldart update`/`baldart add` (subtree merges into `.framework/`, the `[CHORE] baldart update …` commit, and the regenerated overlay files they carry) are *expected* divergence, not the FEAT-0006 orphan-commit pattern. Count only **genuine** unpushed commits:
|
|
181
|
+
```bash
|
|
182
|
+
GENUINE_AHEAD=0; GENUINE_LIST=""; FW_SKIPPED=0
|
|
183
|
+
for sha in $(git -C "$MAIN" rev-list "origin/$TRUNK..$TRUNK"); do
|
|
184
|
+
subj="$(git -C "$MAIN" log -1 --format=%s "$sha")"
|
|
185
|
+
# subtree merge (e.g. "Merge commit '…' as '.framework'") or baldart update/add chore
|
|
186
|
+
if printf '%s' "$subj" | grep -qE "as '\.framework'" || printf '%s' "$subj" | grep -qiE "baldart (update|add)"; then
|
|
187
|
+
FW_SKIPPED=$((FW_SKIPPED+1)); continue
|
|
188
|
+
fi
|
|
189
|
+
# touches ONLY files under .framework/ ? (empty file list = merge commit, handled above)
|
|
190
|
+
files="$(git -C "$MAIN" show --pretty=format: --name-only "$sha" | grep -v '^$')"
|
|
191
|
+
if [ -n "$files" ] && ! printf '%s\n' "$files" | grep -qvE '^\.framework/'; then
|
|
192
|
+
FW_SKIPPED=$((FW_SKIPPED+1)); continue
|
|
193
|
+
fi
|
|
194
|
+
GENUINE_AHEAD=$((GENUINE_AHEAD+1)); GENUINE_LIST="$GENUINE_LIST $sha"
|
|
195
|
+
done
|
|
196
|
+
```
|
|
197
|
+
`$FW_SKIPPED` framework-management commits are auto-ignored (log them — see below). Branch on `$BEHIND` and the **genuine** ahead count `$GENUINE_AHEAD` (NOT the raw `$AHEAD`):
|
|
198
|
+
|
|
199
|
+
- **`BEHIND=0` and `GENUINE_AHEAD=0`** — synchronized for `/new`'s purposes. If `$FW_SKIPPED > 0`, write `Divergence: $FW_SKIPPED framework-management commits ahead (auto-ignored — baldart update/subtree)` to the tracker. **No `AskUserQuestion`.** Proceed to step 5.
|
|
200
|
+
- **`BEHIND>0` and `GENUINE_AHEAD=0`** (only behind) — invoke `AskUserQuestion`:
|
|
201
|
+
- Question: `"Local $TRUNK è behind origin/$TRUNK di $BEHIND commit. Come procedo?"`
|
|
175
202
|
- Options: `[Fast-forward pull adesso]` / `[Procedi senza pull]` / `[Abort]`.
|
|
176
203
|
- On `Fast-forward pull adesso`: if `$MAIN` HEAD == `$TRUNK`, run `git -C "$MAIN" pull --ff-only origin "$TRUNK"`; otherwise log "main HEAD is `<branch>` — fetch already updated `refs/remotes/origin/$TRUNK`, local `$TRUNK` ref will be reconciled in Phase 6c".
|
|
177
|
-
- **`0
|
|
178
|
-
- Question: `"Local $TRUNK è ahead di origin/$TRUNK di
|
|
179
|
-
- Show the
|
|
204
|
+
- **`BEHIND=0` and `GENUINE_AHEAD>0`** (genuine UNPUSHED LOCAL COMMITS, this is the FEAT-0006 pattern) — invoke `AskUserQuestion`:
|
|
205
|
+
- Question: `"Local $TRUNK è ahead di origin/$TRUNK di $GENUINE_AHEAD commit locali non pushati (esclusi $FW_SKIPPED commit di gestione framework). Cosa faccio?"`
|
|
206
|
+
- Show **only the genuine** commits inline: `git -C "$MAIN" show -s --oneline $GENUINE_LIST`.
|
|
180
207
|
- Options: `[Push adesso (git push origin $TRUNK)]` / `[Cherry-pick a parte e continua]` / `[Lascia così e procedi (lo gestisco io)]` / `[Abort]`.
|
|
181
|
-
- **`
|
|
182
|
-
- Question: `"Local $TRUNK è diverged da origin/$TRUNK:
|
|
208
|
+
- **`BEHIND>0` and `GENUINE_AHEAD>0`** (diverged both ways) — invoke `AskUserQuestion`:
|
|
209
|
+
- Question: `"Local $TRUNK è diverged da origin/$TRUNK: $BEHIND behind, $GENUINE_AHEAD genuine ahead. Servono entrambe le riconciliazioni. Come procedo?"`
|
|
183
210
|
- Options: `[Rebase local $TRUNK su origin/$TRUNK]` / `[Mostrami i commit e fammi decidere]` / `[Abort]`.
|
|
184
211
|
|
|
185
212
|
5. **Log and proceed** — write to the tracker:
|
|
@@ -188,8 +215,8 @@ Trunk branch: [resolved git.trunk_branch — Phase 0 step 0 populates]
|
|
|
188
215
|
Status: PASS
|
|
189
216
|
Main repo: $MAIN
|
|
190
217
|
Trunk branch: $TRUNK
|
|
191
|
-
Dirty: <none | stashed: <message-label> | user-override>
|
|
192
|
-
Divergence (local…origin/$TRUNK): <0\t0 | resolved: ff-pull | resolved: pushed | user-deferred>
|
|
218
|
+
Dirty: <none | framework-telemetry-only (auto-ignored) | stashed: <message-label> | user-override>
|
|
219
|
+
Divergence (local…origin/$TRUNK): <0\t0 | framework-mgmt-only (auto-ignored: $FW_SKIPPED) | resolved: ff-pull | resolved: pushed | user-deferred>
|
|
193
220
|
Completed: <timestamp>
|
|
194
221
|
```
|
|
195
222
|
If any step ended in HALT, set `Status: HALT` and stop — do NOT continue to `## Pre-flight (once)`.
|
|
@@ -1868,18 +1895,19 @@ The most common failure mode is leaving cards IN_PROGRESS after merge. This crea
|
|
|
1868
1895
|
|
|
1869
1896
|
4. **Divergence assertion (BLOCKING — this catches the FEAT-0006 orphan-commit pattern)**. `$MAIN` and `$TRUNK` are read from the tracker (`## Worktree` section); HALT if either is absent/empty.
|
|
1870
1897
|
```bash
|
|
1871
|
-
git -C "$MAIN" rev-list --left-right --count "origin/$TRUNK...$TRUNK"
|
|
1898
|
+
read BEHIND AHEAD <<< "$(git -C "$MAIN" rev-list --left-right --count "origin/$TRUNK...$TRUNK")"
|
|
1872
1899
|
```
|
|
1873
|
-
|
|
1874
|
-
-
|
|
1875
|
-
|
|
1900
|
+
Compute `$GENUINE_AHEAD` / `$GENUINE_LIST` / `$FW_SKIPPED` with the **exact same reclassification loop as Phase 0 step 4** (framework-management commits — subtree merges into `.framework/`, `baldart update`/`add` chores, `.framework/`-only commits — are auto-ignored, NOT orphan commits). Then branch on `$BEHIND` and `$GENUINE_AHEAD`:
|
|
1901
|
+
- **`BEHIND=0` and `GENUINE_AHEAD=0`** — synchronized. If `$FW_SKIPPED > 0`, log `Divergence: $FW_SKIPPED framework-management commits ahead (auto-ignored)` and proceed. No `AskUserQuestion`.
|
|
1902
|
+
- **Ahead only (`GENUINE_AHEAD > 0`, genuine unpushed commits)** — invoke `AskUserQuestion`:
|
|
1903
|
+
- Question: `"Local $TRUNK ha $GENUINE_AHEAD commit genuini non pushati su origin/$TRUNK al termine del batch (esclusi $FW_SKIPPED di gestione framework). Lista: <git show -s --oneline $GENUINE_LIST>. Cosa faccio?"`
|
|
1876
1904
|
- Options: `[Push adesso (git push origin $TRUNK)]` / `[Cherry-pick selettivo su origin/$TRUNK]` / `[Reset --hard origin/$TRUNK (richiede conferma esplicita, DISTRUTTIVO)]` / `[Halt con stato preservato]`.
|
|
1877
1905
|
- On `Reset --hard origin/$TRUNK` re-ask `AskUserQuestion` to confirm: `"Confermi reset --hard? I commit <list> verranno persi se non pushati altrove."` Solo dopo conferma esplicita esegui il reset.
|
|
1878
|
-
- **Behind only (
|
|
1879
|
-
- Question: `"Local $TRUNK è behind origin/$TRUNK di
|
|
1906
|
+
- **Behind only (`BEHIND > 0`, `GENUINE_AHEAD=0`)** — invoke `AskUserQuestion`:
|
|
1907
|
+
- Question: `"Local $TRUNK è behind origin/$TRUNK di $BEHIND commit (qualcuno ha pushato durante il batch). Faccio ff-pull adesso?"`
|
|
1880
1908
|
- Options: `[Fast-forward pull]` / `[Lascia behind (lo gestisco io)]`.
|
|
1881
|
-
- **Diverged both ways** — invoke `AskUserQuestion`:
|
|
1882
|
-
- Question: `"Local $TRUNK è diverged (
|
|
1909
|
+
- **Diverged both ways (`BEHIND > 0` and `GENUINE_AHEAD > 0`)** — invoke `AskUserQuestion`:
|
|
1910
|
+
- Question: `"Local $TRUNK è diverged ($BEHIND behind, $GENUINE_AHEAD genuine ahead). Servono entrambe le riconciliazioni. Come procedo?"`
|
|
1883
1911
|
- Options: `[Rebase local $TRUNK su origin/$TRUNK]` / `[Mostrami i commit locali e decidiamo]` / `[Halt]`.
|
|
1884
1912
|
|
|
1885
1913
|
5. **Restore Phase 0 stash (if any)** — read the tracker for `## Workspace Snapshot: <message-label>`:
|