949d90887d
Update CLAUDE.md, .claude/CLAUDE.md, README.md, CHANGELOG.md to reference new paths: decisions.md, progress/, release-notes.md, unified findings.md. Fix branch name reference (dexter_changes -> hib_changes). Rewrite TODO.md with grouped categories (Multi-Machine, Multi-Agent, Security, Reliability).
1.8 KiB
1.8 KiB
Agent Orchestrator — TODO
Multi-Machine (v3.1)
- Real-world relay testing — TLS added, code complete in bridges/stores. Needs 2-machine test to verify relay + RemoteManager end-to-end. Multi-machine UI not yet surfaced in v3 ProjectBox.
- Certificate pinning — TLS encryption works. Pin relay cert hash in RemoteManager to prevent MITM. Planned for v3.1.
Multi-Agent (v3.1)
- Agent Teams real-world testing — Subagent delegation prompt +
CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1env injection done. Needs real multi-agent session to verify Manager spawns child agents via SDK teams.
Security (v3.2)
- Plugin sandbox migration — Current
new Function()sandbox has escape vectors (prototype walking,arguments.callee.constructor). Migrate to Web Worker isolation for true process-level sandboxing.
Reliability
- Soak test — Run 4-hour soak with 6+ agents across 3+ projects. Monitor: memory growth, SQLite WAL size, xterm.js instance count, sidecar supervisor restarts.
Completed
- E2E fixture + judge hardening | Done: 2026-03-12
- LLM judge refactor + E2E docs | Done: 2026-03-12
- v3 Hardening Sprint (TLS, WAL, Landlock, plugin tests, Phase C E2E) | Done: 2026-03-12
- v3 Production Readiness — all 13 tribunal items | Done: 2026-03-12
- Unified test runner + testing gate rule | Done: 2026-03-12
- E2E Phase B + 27 test fixes | Done: 2026-03-12
- Reviewer agent role | Done: 2026-03-12
- Auto-wake Manager scheduler | Done: 2026-03-12
- Dashboard metrics panel | Done: 2026-03-12
- Branded types (GroupId, AgentId, SessionId, ProjectId) | Done: 2026-03-11
- Regression tests + sidecar env security | Done: 2026-03-11
- Integration fix (btmsg column, camelCase, PlantUML, Tauri 2.x assets) | Done: 2026-03-11