mirror of
https://github.com/garrytan/gstack.git
synced 2026-05-02 03:35:09 +02:00
Garry Tan
ae0a9ad195
* 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>
60 lines
3.7 KiB
JSON
60 lines
3.7 KiB
JSON
{
|
|
"name": "gstack",
|
|
"version": "0.13.6.0",
|
|
"description": "Garry's Stack — Claude Code skills + fast headless browser. One repo, one install, entire AI engineering workflow.",
|
|
"license": "MIT",
|
|
"type": "module",
|
|
"bin": {
|
|
"browse": "./browse/dist/browse"
|
|
},
|
|
"scripts": {
|
|
"build": "bun run gen:skill-docs --host all; bun build --compile browse/src/cli.ts --outfile browse/dist/browse && bun build --compile browse/src/find-browse.ts --outfile browse/dist/find-browse && bun build --compile design/src/cli.ts --outfile design/dist/design && bun build --compile bin/gstack-global-discover.ts --outfile bin/gstack-global-discover && bash browse/scripts/build-node-server.sh && git rev-parse HEAD > browse/dist/.version && git rev-parse HEAD > design/dist/.version && rm -f .*.bun-build || true",
|
|
"dev:design": "bun run design/src/cli.ts",
|
|
"gen:skill-docs": "bun run scripts/gen-skill-docs.ts",
|
|
"dev": "bun run browse/src/cli.ts",
|
|
"server": "bun run browse/src/server.ts",
|
|
"test": "bun test browse/test/ test/ --ignore 'test/skill-e2e-*.test.ts' --ignore test/skill-llm-eval.test.ts --ignore test/skill-routing-e2e.test.ts --ignore test/codex-e2e.test.ts --ignore test/gemini-e2e.test.ts",
|
|
"test:evals": "EVALS=1 bun test --retry 2 --concurrent --max-concurrency ${EVALS_CONCURRENCY:-15} test/skill-llm-eval.test.ts test/skill-e2e-*.test.ts test/skill-routing-e2e.test.ts test/codex-e2e.test.ts test/gemini-e2e.test.ts",
|
|
"test:evals:all": "EVALS=1 EVALS_ALL=1 bun test --retry 2 --concurrent --max-concurrency ${EVALS_CONCURRENCY:-15} test/skill-llm-eval.test.ts test/skill-e2e-*.test.ts test/skill-routing-e2e.test.ts test/codex-e2e.test.ts test/gemini-e2e.test.ts",
|
|
"test:e2e": "EVALS=1 bun test --retry 2 --concurrent --max-concurrency ${EVALS_CONCURRENCY:-15} test/skill-e2e-*.test.ts test/skill-routing-e2e.test.ts test/codex-e2e.test.ts test/gemini-e2e.test.ts",
|
|
"test:e2e:all": "EVALS=1 EVALS_ALL=1 bun test --retry 2 --concurrent --max-concurrency ${EVALS_CONCURRENCY:-15} test/skill-e2e-*.test.ts test/skill-routing-e2e.test.ts test/codex-e2e.test.ts test/gemini-e2e.test.ts",
|
|
"test:gate": "EVALS=1 EVALS_TIER=gate bun test --retry 2 --concurrent --max-concurrency ${EVALS_CONCURRENCY:-15} test/skill-llm-eval.test.ts test/skill-e2e-*.test.ts test/skill-routing-e2e.test.ts test/codex-e2e.test.ts test/gemini-e2e.test.ts",
|
|
"test:periodic": "EVALS=1 EVALS_TIER=periodic EVALS_ALL=1 bun test --retry 2 --concurrent --max-concurrency ${EVALS_CONCURRENCY:-15} test/skill-e2e-*.test.ts test/skill-routing-e2e.test.ts test/codex-e2e.test.ts test/gemini-e2e.test.ts",
|
|
"test:codex": "EVALS=1 bun test test/codex-e2e.test.ts",
|
|
"test:codex:all": "EVALS=1 EVALS_ALL=1 bun test test/codex-e2e.test.ts",
|
|
"test:gemini": "EVALS=1 bun test test/gemini-e2e.test.ts",
|
|
"test:gemini:all": "EVALS=1 EVALS_ALL=1 bun test test/gemini-e2e.test.ts",
|
|
"skill:check": "bun run scripts/skill-check.ts",
|
|
"dev:skill": "bun run scripts/dev-skill.ts",
|
|
"start": "bun run browse/src/server.ts",
|
|
"eval:list": "bun run scripts/eval-list.ts",
|
|
"eval:compare": "bun run scripts/eval-compare.ts",
|
|
"eval:summary": "bun run scripts/eval-summary.ts",
|
|
"eval:watch": "bun run scripts/eval-watch.ts",
|
|
"eval:select": "bun run scripts/eval-select.ts",
|
|
"analytics": "bun run scripts/analytics.ts",
|
|
"test:audit": "bun test test/audit-compliance.test.ts"
|
|
},
|
|
"dependencies": {
|
|
"diff": "^7.0.0",
|
|
"playwright": "^1.58.2",
|
|
"puppeteer-core": "^24.40.0"
|
|
},
|
|
"engines": {
|
|
"bun": ">=1.0.0"
|
|
},
|
|
"keywords": [
|
|
"browser",
|
|
"automation",
|
|
"playwright",
|
|
"headless",
|
|
"cli",
|
|
"claude",
|
|
"ai-agent",
|
|
"devtools"
|
|
],
|
|
"devDependencies": {
|
|
"@anthropic-ai/sdk": "^0.78.0"
|
|
}
|
|
}
|