feat: recursive self-improvement — operational learning + full skill wiring (v0.13.8.0)#647
Open
feat: recursive self-improvement — operational learning + full skill wiring (v0.13.8.0)#647
Conversation
…-improvement slot Contributor mode never fired in 18 days of heavy use (required manual opt-in via gstack-config, gated behind _CONTRIB=true, wrote disconnected markdown). Removes: generateContributorMode(), _CONTRIB bash var, 2 E2E tests, touchfile entry, doc references. Cleans up skip-lists in plan-ceo-review, autoplan, review resolver, and document-release templates. The operational self-improvement system (next commit) replaces this slot with automatic learning capture that requires no opt-in. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Adds universal operational learning capture to the preamble completion protocol. At the end of every skill session, the agent reflects on CLI failures, wrong approaches, and project quirks, logging them as type "operational" to the learnings JSONL. Future sessions surface these automatically. - generateCompletionStatus(ctx) now includes operational capture section - Preamble bash shows top 3 learnings inline when count > 5 - New "operational" type in generateLearningsLog alongside pattern/pitfall/etc - Updated unit tests + operational seed entry in learnings E2E Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Adds LEARNINGS_SEARCH and/or LEARNINGS_LOG to 10 skill templates that produce reusable insights but were previously disconnected from the learning system: - office-hours, plan-ceo-review, plan-eng-review: add LOG (had SEARCH) - plan-design-review: add both SEARCH + LOG (had neither) - design-review, design-consultation, cso, qa, qa-only: add both - retro: add SEARCH (had LOG) 13 skills now fully participate in the learning loop (read + write). Every review, QA, investigation, and design session both consults prior learnings and contributes new ones. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Validates the write path: agent encounters a CLI failure, logs an operational learning to JSONL via gstack-learnings-log. Replaces the removed contributor-mode E2E test. Setup: temp git repo, copy bin scripts, set GSTACK_HOME. Prompt: simulated npm test failure needing --experimental-vm-modules. Assert: learnings.jsonl exists with type=operational entry. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
…rdcoded The test seeded learnings at projects/test-project/ but gstack-slug computes the slug from basename(workDir) when no git remote exists. The agent's search looked at the wrong path and found nothing. Fix: compute slug the same way gstack-slug does (basename + sanitize) and seed the learnings there. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
…eviews # Conflicts: # SKILL.md # autoplan/SKILL.md # benchmark/SKILL.md # browse/SKILL.md # canary/SKILL.md # codex/SKILL.md # connect-chrome/SKILL.md # cso/SKILL.md # design-consultation/SKILL.md # design-review/SKILL.md # design-shotgun/SKILL.md # document-release/SKILL.md # investigate/SKILL.md # land-and-deploy/SKILL.md # learn/SKILL.md # office-hours/SKILL.md # plan-ceo-review/SKILL.md # plan-design-review/SKILL.md # plan-eng-review/SKILL.md # qa-only/SKILL.md # qa/SKILL.md # retro/SKILL.md # review/SKILL.md # scripts/resolvers/preamble.ts # setup-browser-cookies/SKILL.md # setup-deploy/SKILL.md # ship/SKILL.md
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
E2E Evals: ✅ PASS61/61 tests passed | $5.85 total cost | 12 parallel runners
12x ubicloud-standard-2 (Docker: pre-baked toolchain + deps) | wall clock ≈ slowest suite |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
gstack now learns from its own operational failures and wires learnings into every insight-producing skill.
Operational self-improvement (universal)
gstack-learnings-logwith newoperationaltypeFull learning loop (13 skills wired)
Dead code removal
E2E test fixes
operational-learninggate-tier E2E test validates the write pathlearnings-showslug mismatch (seeded at hardcoded path, but gstack-slug computed different path)Test Coverage
All new code paths have test coverage.
gen-skill-docs.test.tsvalidates operational self-improvement in preamble output + operational type in LEARNINGS_LOGoperational-learning(PASS, $0.05, 13s) validates write pathlearnings-show(PASS, $0.13, 42s) validates read path with all 4 types including operationalPre-Landing Review
Pre-Landing Review: No issues found. Template/resolver changes only.
Reviews
Test plan
🤖 Generated with Claude Code