Files

Claude 6045077144 refactor: Phase 1/4/6 — doc cleanup, config fix, token optimization

Phase 1 — Documentation cleanup:
- Slim README 303→93 lines (remove duplicated architecture, config tables)
- Slim CLAUDE.md 267→80 lines (remove project layout, env vars, CI section)
- Slim AGENTS.md 342→72 lines (remove duplicated patterns, running locally)
- Delete MEMORY.md, WORKSET_PLAN.md, WORKSET_PLAN_PHASE2.md (session docs)
- Archive PLAN.md, IMPLEMENTATION_SUMMARY.md to docs/
- Move QUALITY_ANALYSIS.md, QUALITY_REVIEW_REPORT.md to docs/
- Move apply_security_fixes.py, activate_self_tdd.sh to scripts/

Phase 4 — Config & build cleanup:
- Fix wheel build: add 11 missing modules to pyproject.toml include list
- Add pytest markers (unit, integration, dashboard, swarm, slow)
- Add data/self_modify_reports/ and .handoff/ to .gitignore

Phase 6 — Token optimization:
- Add docstrings to 15 __init__.py files that were empty
- Create __init__.py for events/, memory/, upgrades/ modules

Root markdown: 87KB → ~18KB (79% reduction)

https://claude.ai/code/session_019oMFNvD8uSGSSmBMGkBfQN

2026-02-26 21:03:15 +00:00

2.4 KiB

Raw Blame History

AGENTS.md — Timmy Time Development Standards for AI Agents

Read CLAUDE.md for architecture patterns and conventions.

Non-Negotiable Rules

Tests must stay green. Run make test before committing.
No cloud dependencies. All AI computation runs on localhost.
No new top-level files without purpose. Don't litter the root directory.
Follow existing patterns — singletons, graceful degradation, pydantic-settings.
Security defaults: Never hard-code secrets.
XSS prevention: Never use innerHTML with untrusted content.

Agent Roster

Build Tier

Local (Ollama) — Primary workhorse. Free. Unrestricted. Best for: everything, iterative dev, Docker swarm workers.

Kimi (Moonshot) — Paid. Large-context feature drops, new subsystems, persona agents. Avoid: touching CI/pyproject.toml, adding cloud calls, removing tests.

DeepSeek — Near-free. Second-opinion generation, large refactors (R1 for hard problems). Avoid: bypassing review tier for security modules.

Review Tier

Claude (Anthropic) — Architecture, tests, docs, CI/CD, PR review. Avoid: large one-shot feature dumps.

Gemini (Google) — Docs, frontend polish, boilerplate, diff summaries. Avoid: security modules, Python business logic without Claude review.

Manus AI — Security audits, coverage gaps, L402 validation. Avoid: large refactors, new features, prompt changes.

Docker Agents

Container agents poll the coordinator's HTTP API (not in-memory SwarmComms):

GET  /internal/tasks    → list tasks open for bidding
POST /internal/bids     → submit a bid

COORDINATOR_URL=http://dashboard:8000 is set by docker-compose.

make docker-build       # build image
make docker-up          # start dashboard
make docker-agent       # add a worker

File Conventions

Pattern	Convention
New route	`src/dashboard/routes/<name>.py` + register in `app.py`
New template	`src/dashboard/templates/<name>.html` extends `base.html`
New subsystem	`src/<name>/` with `__init__.py`
New test	`tests/test_<module>.py`
Secrets	Via `config.settings` + startup warning if default
DB files	Project root or `data/` — never in `src/`

Roadmap

v2.0 Exodus (in progress): Swarm + L402 + Voice + Marketplace + Hands v3.0 Revelation (planned): Lightning treasury + .app bundle + federation

2.4 KiB Raw Blame History