mirror of https://github.com/garrytan/gstack.git
1626d4857b
* fix(plan-devex-review): add missing gstack-review-log step
plan-devex-review carried the EXIT PLAN MODE GATE but never wrote a
review-log entry, so the gate's 'review log was called' check was
structurally unsatisfiable and the Review Readiness Dashboard / GSTACK
REVIEW REPORT had no plan-devex-review data to read. Add a Review Log
section before the dashboard read, logging the devex fields the report
parser already expects (status, scores, product_type, tthw, persona,
competitive_tier, unresolved, commit).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* feat(review): make unresolved-decisions status mandatory in GSTACK REVIEW REPORT
The report's UNRESOLVED line was optional ('omit if empty') and the EXIT
PLAN MODE GATE only checked it 'if applicable', so a plan could ship with
no statement about open decisions at all — a missed ambiguity read
identically to a clean plan. Now every report ends with a mandatory
unresolved-decisions status as its final line: either the exact unbolded
sentinel 'NO UNRESOLVED DECISIONS', or a '**UNRESOLVED DECISIONS:**' block
of bullets. The gate blocks ExitPlanMode unless that final line is present.
generatePlanFileReviewReport: current-review items are listed from context;
prior reviews contribute an aggregate count computed as latest-fresh-row-
per-skill minus the current run (no double-count, dashboard 7-day window).
generateExitPlanModeGate: check #3 is now blocking with no 'if applicable'
escape; bolded sentinel does not satisfy it.
Tests: static guard in gen-skill-docs.test.ts asserts the mandatory status
across all six report consumers and the gate across gate-bearing skills;
skill-e2e-plan.test.ts asserts the written report's final line is the
status (and fixes a stale 'four review rows' -> five-row prompt).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* refactor(review): compress unresolved-status prose to fit parity budget
After merging origin/main (v1.57.3.0), plan-devex-review exceeded the 1.05x
parity ratio vs the v1.53.0.0 baseline. Rather than rebase the baseline,
compressed the new prose to stay under the cap honestly: the report's
unresolved-status block (~32 -> ~9 lines) and the EXIT PLAN MODE GATE's
final-line check (~7 -> ~5 lines), plus the plan-devex-review review-log
step. All load-bearing rules and the exact gate-checkable tokens are
preserved; the static guards in gen-skill-docs.test.ts still pass.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* test: regenerate stale ship golden fixtures (#1909 follow-up)
#1909 (v1.57.3.0) added the always-loaded PR-title-version rule to ship's
template and committed the regenerated ship/SKILL.md, but did not refresh the
three ship golden fixtures, leaving the golden-file regression test red on
main. Regenerate them from current output. The diff is purely #1909 content:
the PR-title invariant line plus a previously-unresolved ${ctx.paths.binDir}
placeholder that current generation correctly resolves. No feature content
from this branch leaks into ship (ship does not consume the review report
resolvers).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix(plan-devex-review): restore TIMESTAMP fill instruction in review-log
Adversarial review caught that compressing the devex review-log block dropped
the TIMESTAMP substitution guidance the three sibling plan-review skills carry.
A literal "timestamp":"TIMESTAMP" parses as JSON but is an unparseable date,
so the Review Readiness Dashboard's 7-day freshness window silently drops the
plan-devex-review row (and the report's prior-review aggregation loses it).
Restore the one-line instruction. Also: the plan-review-report E2E now derives
its last-line check from the report slice, not the whole file, so a mis-placed
report surfaces the real trailing content in the failure message.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* test(parity): rebase parity baseline v1.53.0.0 -> v1.57.7.0
The v1.53 anchor is four minor versions stale. v1.54-v1.57 (ship/plan carving,
carve-guards, AUQ prose fallback, the cross-session decision-log preamble) plus
this branch's mandatory unresolved-decisions status line pushed the three
plan-review skills past the 5% ratchet even after exhaustive compression. The
new baseline captures current UNION sizes (skeleton + sections/*.md, matching
what parity-harness measures) so the per-skill 1.05 ratio keeps catching future
bloat. The frozen v1.44.1 integrity anchor and the v1.47 size-budget baseline
are untouched.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* chore: bump version and changelog (v1.57.7.0)
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
|
||
|---|---|---|
| .. | ||
| app | ||
| host-adapters | ||
| resolvers | ||
| analytics.ts | ||
| archetypes.ts | ||
| brain-cache-spec.ts | ||
| build-app.sh | ||
| build.sh | ||
| capture-baseline.ts | ||
| compare-pr-version.ts | ||
| declared-annotation.ts | ||
| detect-bump.ts | ||
| dev-skill.ts | ||
| discover-skills.ts | ||
| eval-compare.ts | ||
| eval-list.ts | ||
| eval-select.ts | ||
| eval-summary.ts | ||
| eval-watch.ts | ||
| garry-output-comparison.ts | ||
| gen-llms-txt.ts | ||
| gen-skill-docs.ts | ||
| gstack-schema-pack.ts | ||
| host-config-export.ts | ||
| host-config.ts | ||
| jargon-list.json | ||
| models.ts | ||
| one-way-doors.ts | ||
| preflight-agent-sdk.ts | ||
| proactive-suggestions.json | ||
| psychographic-signals.ts | ||
| question-registry.ts | ||
| setup-scc.sh | ||
| skill-check.ts | ||
| slop-diff.ts | ||
| task-emission-schema.ts | ||
| test-free-shards.ts | ||
| update-readme-throughput.ts | ||
| write-version-files.sh | ||