mirror of
https://github.com/garrytan/gstack.git
synced 2026-05-02 03:35:09 +02:00
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>
57 lines
3.1 KiB
TypeScript
57 lines
3.1 KiB
TypeScript
/**
|
|
* RESOLVERS record — maps {{PLACEHOLDER}} names to generator functions.
|
|
* Each resolver takes a TemplateContext and returns the replacement string.
|
|
*/
|
|
|
|
import type { TemplateContext } from './types';
|
|
|
|
// Domain modules
|
|
import { generatePreamble } from './preamble';
|
|
import { generateTestFailureTriage } from './preamble';
|
|
import { generateCommandReference, generateSnapshotFlags, generateBrowseSetup } from './browse';
|
|
import { generateDesignMethodology, generateDesignHardRules, generateDesignOutsideVoices, generateDesignReviewLite, generateDesignSketch, generateDesignSetup, generateDesignMockup, generateDesignShotgunLoop } from './design';
|
|
import { generateTestBootstrap, generateTestCoverageAuditPlan, generateTestCoverageAuditShip, generateTestCoverageAuditReview } from './testing';
|
|
import { generateReviewDashboard, generatePlanFileReviewReport, generateSpecReviewLoop, generateBenefitsFrom, generateCodexSecondOpinion, generateAdversarialStep, generateCodexPlanReview, generatePlanCompletionAuditShip, generatePlanCompletionAuditReview, generatePlanVerificationExec } from './review';
|
|
import { generateSlugEval, generateSlugSetup, generateBaseBranchDetect, generateDeployBootstrap, generateQAMethodology, generateCoAuthorTrailer } from './utility';
|
|
import { generateLearningsSearch, generateLearningsLog } from './learnings';
|
|
import { generateConfidenceCalibration } from './confidence';
|
|
|
|
export const RESOLVERS: Record<string, (ctx: TemplateContext) => string> = {
|
|
SLUG_EVAL: generateSlugEval,
|
|
SLUG_SETUP: generateSlugSetup,
|
|
COMMAND_REFERENCE: generateCommandReference,
|
|
SNAPSHOT_FLAGS: generateSnapshotFlags,
|
|
PREAMBLE: generatePreamble,
|
|
BROWSE_SETUP: generateBrowseSetup,
|
|
BASE_BRANCH_DETECT: generateBaseBranchDetect,
|
|
QA_METHODOLOGY: generateQAMethodology,
|
|
DESIGN_METHODOLOGY: generateDesignMethodology,
|
|
DESIGN_HARD_RULES: generateDesignHardRules,
|
|
DESIGN_OUTSIDE_VOICES: generateDesignOutsideVoices,
|
|
DESIGN_REVIEW_LITE: generateDesignReviewLite,
|
|
REVIEW_DASHBOARD: generateReviewDashboard,
|
|
PLAN_FILE_REVIEW_REPORT: generatePlanFileReviewReport,
|
|
TEST_BOOTSTRAP: generateTestBootstrap,
|
|
TEST_COVERAGE_AUDIT_PLAN: generateTestCoverageAuditPlan,
|
|
TEST_COVERAGE_AUDIT_SHIP: generateTestCoverageAuditShip,
|
|
TEST_COVERAGE_AUDIT_REVIEW: generateTestCoverageAuditReview,
|
|
TEST_FAILURE_TRIAGE: generateTestFailureTriage,
|
|
SPEC_REVIEW_LOOP: generateSpecReviewLoop,
|
|
DESIGN_SKETCH: generateDesignSketch,
|
|
DESIGN_SETUP: generateDesignSetup,
|
|
DESIGN_MOCKUP: generateDesignMockup,
|
|
DESIGN_SHOTGUN_LOOP: generateDesignShotgunLoop,
|
|
BENEFITS_FROM: generateBenefitsFrom,
|
|
CODEX_SECOND_OPINION: generateCodexSecondOpinion,
|
|
ADVERSARIAL_STEP: generateAdversarialStep,
|
|
DEPLOY_BOOTSTRAP: generateDeployBootstrap,
|
|
CODEX_PLAN_REVIEW: generateCodexPlanReview,
|
|
PLAN_COMPLETION_AUDIT_SHIP: generatePlanCompletionAuditShip,
|
|
PLAN_COMPLETION_AUDIT_REVIEW: generatePlanCompletionAuditReview,
|
|
PLAN_VERIFICATION_EXEC: generatePlanVerificationExec,
|
|
CO_AUTHOR_TRAILER: generateCoAuthorTrailer,
|
|
LEARNINGS_SEARCH: generateLearningsSearch,
|
|
LEARNINGS_LOG: generateLearningsLog,
|
|
CONFIDENCE_CALIBRATION: generateConfidenceCalibration,
|
|
};
|