Skip to content

docs: add task #0043 — agent-to-agent CONTRIBUTING.md#46

Merged
fazxes merged 1 commit intomainfrom
docs/contributing-task
Apr 5, 2026
Merged

docs: add task #0043 — agent-to-agent CONTRIBUTING.md#46
fazxes merged 1 commit intomainfrom
docs/contributing-task

Conversation

@fazxes
Copy link
Copy Markdown
Member

@fazxes fazxes commented Apr 5, 2026

Summary

  • Adds task docs: use git worktree when daemon is running #43: create a CONTRIBUTING.md designed as an agent-to-agent collaboration protocol
  • The guide will be built by the daemon, for agents — not a standard human contributing guide
  • Covers both the resident daemon's perspective and external contributing agents

Context

Task #40 was overwritten by the daemon's own follow-up tasks. This is #43 to avoid collision.

@fazxes fazxes merged commit 7969ccc into main Apr 5, 2026
2 checks passed
fazxes added a commit that referenced this pull request Apr 5, 2026
5-agent audit identified task selection as mesa-optimization: agent
optimizes session success over project progress. 5 more agents audited
the fix and found 7 issues, all resolved.

Phase 1 — Prompt fixes:
- Remove "smaller in scope" incentive from evolve-auto.md
- Queue order authoritative, handoff advisory
- "Tasks I Did NOT Pick and Why" in every handoff
- Tracker delta required in session reports
- Staleness multiplier (5+ sessions = 2x priority)
- All-integration-tasks edge case handled

Phase 2 — Task queue:
- environment: internal | integration tags
- blocked_reason subtypes: environment, dependency, design
- .next-id for atomic task ID allocation
- archive/ for done tasks (daemon auto-archives)
- Tagged #12, #28, #29 blocked-environment
- Fixed #43 broken frontmatter (duplicate of #40)

Phase 3 — Overseer avoidance detection:
- 6 new checks: stale tasks, cherry-picking, stuck integration,
  weak blocks, max attempts, skip accountability

Learnings index:
- INDEX.md with categorized one-line summaries (31/31 matched)
- Agent reads index, opens files only when relevant
- Updated CLAUDE.md, evolve.md Step 1 and Step 6l

Meta layer vision (8 new tasks #46-#53):
- #46 Healer — between-session trend observer
- #47 Multi-agent PR review panel
- #48 Human escalation (gh issue create + webhook)
- #49 Self-evaluation loop against real repos
- #50 Prompt self-refinement via strategist
- #51 Cross-session cost intelligence
- #52 Codebase world model (MODULE_MAP.md)
- #53 Agent generates its own tasks across all dimensions

Also: OPERATIONS.md stale task queue + --squash example fixed
@fazxes fazxes deleted the docs/contributing-task branch April 5, 2026 04:36
fazxes added a commit that referenced this pull request Apr 5, 2026
Add a lightweight agent call between sessions in the builder daemon that
observes system health, identifies patterns and trends, and creates
follow-up tasks. The healer reads the last handoff, session index, task
queue, vision tracker, and learnings to spot problems that no single
builder session would catch.

- docs/prompt/healer.md: self-contained healer prompt
- docs/healer/log.md: observation journal
- scripts/daemon.sh: healer call between housekeeping and builder
- scripts/lib-agent.sh: persist_healer_changes() for branch+PR+merge
  of healer outputs, healer.md added to PROMPT_GUARD_FILES
- 9 new tests validating healer infrastructure wiring
- Task #46 done. 659 tests passing.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant