mirror of https://github.com/garrytan/gstack.git
54a50e4b67
PR review feedback on #1071: - Dropped the data-model exception + JSONField bullets from plan-ceo-review entirely. CEO review should stay high-level on "right-sized diff"; data-model pushback belongs to plan-eng-review, which already carries the full checklist. plan-ceo-review/SKILL.md(.tmpl) are now byte-identical to origin/main. - Trimmed both remaining plan-eng-review bullets (data-model exception, JSONField) to single-sentence terseness, matching the style of sibling preferences instead of reading like a paragraph. - Removed cognitive patterns 11-13 (normalize-first, SRP-for-models, structure-beats-blobs) from the numbered "Cognitive Patterns" list — they were more tactical/lower-level than the rest of that list (Larson, McKinley, Conway-style instincts), and duplicated what the Data Model Review now covers operationally. Renumbered 14-18 down to 11-15. - Promoted the Data Model Review Checklist from a "####" subsection tacked onto Architecture Review to its own "### Data model review" section with its own AskUserQuestion/STOP gate, matching Architecture/Code Quality/Test/Performance as a peer rather than an afterthought. Did not renumber the existing 1-4 sections (Architecture/Code Quality/Test/ Performance) since those numbers are referenced elsewhere (carve-guards.ts, the main SKILL.md.tmpl's section-order prose). Updated test/skill-validation.test.ts's static guardrails to match: removed the plan-ceo-review assertions (nothing left to guard there), removed the three now-deleted cognitive-pattern assertions, updated the contiguity check from 1-18 to 1-15, and updated the checklist-subsection test to check for the new "### Data model review" heading. Tightened test/helpers/carve-guards.ts budgets back down now that content shrank: plan-ceo-review reverted fully to its original 90_000/1.08 (content is byte-identical to baseline again); plan-eng-review tightened from 70_000/1.15 to 67_500/1.13 (down from the prior over-generous bump, though not fully back to the original 67_000/no-ratio since the trimmed bullets are still a small net addition). bun test test/skill-validation.test.ts test/parity-suite.test.ts test/touchfiles.test.ts test/gen-skill-docs.test.ts — all pass. |
||
|---|---|---|
| .. | ||
| providers | ||
| agent-sdk-runner.ts | ||
| auq-sdk-capture.ts | ||
| benchmark-judge.ts | ||
| benchmark-runner.ts | ||
| budget-override.test.ts | ||
| budget-override.ts | ||
| capture-parity-baseline.test.ts | ||
| capture-parity-baseline.ts | ||
| carve-guard-checks.ts | ||
| carve-guards.ts | ||
| claude-pty-runner.ts | ||
| claude-pty-runner.unit.test.ts | ||
| codex-session-runner.ts | ||
| e2e-helpers.test.ts | ||
| e2e-helpers.ts | ||
| eval-store.test.ts | ||
| eval-store.ts | ||
| gemini-session-runner.test.ts | ||
| gemini-session-runner.ts | ||
| hermetic-env.test.ts | ||
| hermetic-env.ts | ||
| llm-judge.ts | ||
| observability.test.ts | ||
| parity-harness.ts | ||
| pricing.ts | ||
| required-reads.ts | ||
| secret-sink-harness.ts | ||
| session-runner.test.ts | ||
| session-runner.ts | ||
| skill-parser.ts | ||
| tool-map.ts | ||
| touchfiles.ts | ||
| transcript-section-logger.ts | ||