mirror of
https://github.com/garrytan/gstack.git
synced 2026-07-07 16:48:01 +02:00
feat: GStack Learns — per-project self-learning infrastructure (v0.13.4.0) (#622)
* feat: learnings + confidence resolvers — cross-skill memory infrastructure Three new resolvers for the self-learning system: - LEARNINGS_SEARCH: tells skills to load prior learnings before analysis - LEARNINGS_LOG: tells skills to capture discoveries after completing work - CONFIDENCE_CALIBRATION: adds 1-10 confidence scoring to all review findings Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * feat: learnings bin scripts — append-only JSONL read/write gstack-learnings-log: validates JSON, auto-injects timestamp, appends to ~/.gstack/projects/$SLUG/learnings.jsonl. Append-only (no mutation). gstack-learnings-search: reads/filters/dedupes learnings with confidence decay (observed/inferred lose 1pt/30d), cross-project discovery, and "latest winner" resolution per key+type. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * feat: learnings count in preamble output Every skill now prints "LEARNINGS: N entries loaded" during preamble, making the compounding loop visible to the user. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * feat: integrate learnings + confidence into 9 skill templates Add {{LEARNINGS_SEARCH}}, {{LEARNINGS_LOG}}, and {{CONFIDENCE_CALIBRATION}} placeholders to review, ship, plan-eng-review, plan-ceo-review, office-hours, investigate, retro, and cso templates. Regenerated all SKILL.md files. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * feat: /learn skill — manage project learnings New skill for reviewing, searching, pruning, and exporting what gstack has learned across sessions. Commands: /learn, /learn search, /learn prune, /learn export, /learn stats, /learn add. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * docs: self-learning roadmap — 5-release design doc Covers: R1 GStack Learns (v0.14), R2 Review Army (v0.15), R3 Smart Ceremony (v0.16), R4 /autoship (v0.17), R5 Studio (v0.18). Inspired by Compound Engineering, adapted to GStack's architecture. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * test: learnings bin script unit tests — 13 tests, free Tests gstack-learnings-log (valid/invalid JSON, timestamp injection, append-only) and gstack-learnings-search (dedup, type/query/limit filters, confidence decay, user-stated no-decay, malformed JSONL skip). Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * chore: bump version and changelog (v0.13.4.0) Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * test: learnings resolver + bin script edge case tests — 21 new tests, free Adds gen-skill-docs coverage for LEARNINGS_SEARCH, LEARNINGS_LOG, and CONFIDENCE_CALIBRATION resolvers. Adds bin script edge cases: timestamp preservation, special characters, files array, sort order, type grouping, combined filtering, missing fields, confidence floor at 0. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix: sync package.json version with VERSION file (0.13.4.0) Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * chore: gitignore .factory/ — generated output, not source Same pattern as .claude/skills/ and .agents/. These SKILL.md files are generated from .tmpl templates by gen:skill-docs --host factory. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * test: /learn E2E — seed 3 learnings, verify agent surfaces them Seeds N+1 query pattern, stale cache pitfall, and rubocop preference into learnings.jsonl, then runs /learn and checks that at least 2/3 appear in the agent's output. Gate tier, ~$0.25/run. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Garry Tan
@@ -2123,3 +2123,113 @@ describe('codex commands must not use inline $(git rev-parse --show-toplevel) fo
|
||||
expect(violations).toEqual([]);
|
||||
});
|
||||
});
|
||||
|
||||
// ─── Learnings + Confidence Resolver Tests ─────────────────────
|
||||
|
||||
describe('LEARNINGS_SEARCH resolver', () => {
|
||||
const SEARCH_SKILLS = ['review', 'ship', 'plan-eng-review', 'investigate', 'office-hours', 'plan-ceo-review'];
|
||||
|
||||
for (const skill of SEARCH_SKILLS) {
|
||||
test(`${skill} generated SKILL.md contains learnings search`, () => {
|
||||
const content = fs.readFileSync(path.join(ROOT, skill, 'SKILL.md'), 'utf-8');
|
||||
expect(content).toContain('Prior Learnings');
|
||||
expect(content).toContain('gstack-learnings-search');
|
||||
});
|
||||
}
|
||||
|
||||
test('learnings search includes cross-project config check', () => {
|
||||
const content = fs.readFileSync(path.join(ROOT, 'review', 'SKILL.md'), 'utf-8');
|
||||
expect(content).toContain('cross_project_learnings');
|
||||
expect(content).toContain('--cross-project');
|
||||
});
|
||||
|
||||
test('learnings search includes AskUserQuestion for first-time cross-project opt-in', () => {
|
||||
const content = fs.readFileSync(path.join(ROOT, 'review', 'SKILL.md'), 'utf-8');
|
||||
expect(content).toContain('Enable cross-project learnings');
|
||||
expect(content).toContain('project-scoped only');
|
||||
});
|
||||
|
||||
test('learnings search mentions prior learning applied display format', () => {
|
||||
const content = fs.readFileSync(path.join(ROOT, 'review', 'SKILL.md'), 'utf-8');
|
||||
expect(content).toContain('Prior learning applied');
|
||||
});
|
||||
});
|
||||
|
||||
describe('LEARNINGS_LOG resolver', () => {
|
||||
const LOG_SKILLS = ['review', 'retro', 'investigate'];
|
||||
|
||||
for (const skill of LOG_SKILLS) {
|
||||
test(`${skill} generated SKILL.md contains learnings log`, () => {
|
||||
const content = fs.readFileSync(path.join(ROOT, skill, 'SKILL.md'), 'utf-8');
|
||||
expect(content).toContain('Capture Learnings');
|
||||
expect(content).toContain('gstack-learnings-log');
|
||||
});
|
||||
}
|
||||
|
||||
test('learnings log documents all type values', () => {
|
||||
const content = fs.readFileSync(path.join(ROOT, 'review', 'SKILL.md'), 'utf-8');
|
||||
for (const type of ['pattern', 'pitfall', 'preference', 'architecture', 'tool']) {
|
||||
expect(content).toContain(type);
|
||||
}
|
||||
});
|
||||
|
||||
test('learnings log documents all source values', () => {
|
||||
const content = fs.readFileSync(path.join(ROOT, 'review', 'SKILL.md'), 'utf-8');
|
||||
for (const source of ['observed', 'user-stated', 'inferred', 'cross-model']) {
|
||||
expect(content).toContain(source);
|
||||
}
|
||||
});
|
||||
|
||||
test('learnings log includes files field for staleness detection', () => {
|
||||
const content = fs.readFileSync(path.join(ROOT, 'review', 'SKILL.md'), 'utf-8');
|
||||
expect(content).toContain('"files"');
|
||||
expect(content).toContain('staleness detection');
|
||||
});
|
||||
});
|
||||
|
||||
describe('CONFIDENCE_CALIBRATION resolver', () => {
|
||||
const CONFIDENCE_SKILLS = ['review', 'ship', 'plan-eng-review', 'cso'];
|
||||
|
||||
for (const skill of CONFIDENCE_SKILLS) {
|
||||
test(`${skill} generated SKILL.md contains confidence calibration`, () => {
|
||||
const content = fs.readFileSync(path.join(ROOT, skill, 'SKILL.md'), 'utf-8');
|
||||
expect(content).toContain('Confidence Calibration');
|
||||
expect(content).toContain('confidence score');
|
||||
});
|
||||
}
|
||||
|
||||
test('confidence calibration includes scoring rubric with all tiers', () => {
|
||||
const content = fs.readFileSync(path.join(ROOT, 'review', 'SKILL.md'), 'utf-8');
|
||||
expect(content).toContain('9-10');
|
||||
expect(content).toContain('7-8');
|
||||
expect(content).toContain('5-6');
|
||||
expect(content).toContain('3-4');
|
||||
expect(content).toContain('1-2');
|
||||
});
|
||||
|
||||
test('confidence calibration includes display rules', () => {
|
||||
const content = fs.readFileSync(path.join(ROOT, 'review', 'SKILL.md'), 'utf-8');
|
||||
expect(content).toContain('Show normally');
|
||||
expect(content).toContain('Suppress from main report');
|
||||
});
|
||||
|
||||
test('confidence calibration includes finding format example', () => {
|
||||
const content = fs.readFileSync(path.join(ROOT, 'review', 'SKILL.md'), 'utf-8');
|
||||
expect(content).toContain('[P1] (confidence:');
|
||||
expect(content).toContain('SQL injection');
|
||||
});
|
||||
|
||||
test('confidence calibration includes calibration learning feedback loop', () => {
|
||||
const content = fs.readFileSync(path.join(ROOT, 'review', 'SKILL.md'), 'utf-8');
|
||||
expect(content).toContain('calibration event');
|
||||
expect(content).toContain('Log the corrected pattern');
|
||||
});
|
||||
|
||||
test('skills without confidence calibration do NOT contain it', () => {
|
||||
// office-hours and retro do NOT use confidence calibration
|
||||
for (const skill of ['office-hours', 'retro']) {
|
||||
const content = fs.readFileSync(path.join(ROOT, skill, 'SKILL.md'), 'utf-8');
|
||||
expect(content).not.toContain('## Confidence Calibration');
|
||||
}
|
||||
});
|
||||
});
|
||||
|
||||
Reference in New Issue
Block a user