# Coordinator Directives

Written **only** by the coordinator (the human's planning session). Agents: read the latest round at session start and after every milestone via `git fetch origin && git show origin/main:plan/DIRECTIVES.md`. The newest round addressed to your lane overrides older rounds and, where in conflict, your lane brief. Never edit this file.

---

## Round 2 — 2026-07-16 — Integration complete; v0.1.0 shipped

**Integration merged to `main` (e5d6b2c) and tagged `v0.1.0`.** M8 (annotation→3D correction +
triangulation) and M9 (keyframed camera paths) are done; README rewritten for v0.1.0. Both
change requests adjudicated and applied (CR-1, CR-2 — additive only; timebase/schema-columns/
pose/API shapes otherwise unchanged).

**Verification (coordinator-run on merged tree):** 101 backend tests pass (up from the 96
floor); two-view stage-corner recovery err **0.00000** (< 0.2); frontend build clean; live
in-browser M8 triangulation (gap 0.21) and M9 path (camera lands exactly on keyframe at t);
M4 sync ~16 ms via deterministic pump. Worktrees removed, debris stash dropped, `frontend/dist`
gitignored.

**One open item for the human (not code-blocking):** the automated browser pane runs
`document.hidden=true`, which throttles `requestAnimationFrame`, so continuous multi-cam
playback sync could only be verified deterministically, not by eye. **Open the app in a normal
focused browser window once** (`python -m festival4d serve` + `cd frontend && npm run dev`) and
confirm the top-right sync panel stays green (<50 ms) during continuous playback.

**Next:** the pipeline is ready for real footage — drop 2–4 overlapping concert clips into
`data/raw/` and run `ingest → sync → reconstruct → events → serve` (see README).

## Round 1 — 2026-07-16 — All lanes merged & verified; integration begins

**Coordinator review result:** foundation + all four lanes are merged to `main` (merge commits `e28dc78` A, `2cad2f7` B, `9d17b47` C; D fast-forwarded earlier at `5c2d7c6`). Independently verified on the merged tree: **96 backend tests pass**, synthetic `ingest → sync` recovers ground-truth offsets exactly (+0 / +1370 / −842 ms, drift 0), `events` finds 3 candidates and degrades gracefully unconfigured, frontend production build clean. Excellent evidence discipline across all lanes — keep it.

**Directives:**

1. **Integration phase starts now** — one agent, branch `integration` from `main`, per `plan/10-integration.md`. Maintain `plan/status/integration.md`.
2. **CR-1 (lane D, test_api.py stub assertion): APPROVED by coordinator.** The edit was a direct consequence of M7 landing and touched no frozen contract file. Integration agent: mark the Decision line in `plan/CHANGE_REQUESTS.md` and confirm the new assertion matches the spec M3 `POST /api/events/detect` response shape (`{result, events}`).
3. **Integration additions to the plan/10-integration.md scope** (small, discovered in review):
   - The shared-worktree collision (see lane A/C status round 0) left a coordinator-stashed debris stash in the main working dir (`git stash list` — "stale lane A/B debris"). After confirming nothing of value remains, drop it, and remove the now-merged worktrees `../festifun-laneA` and `../festifun-laneB` (`git worktree remove`).
   - Lane C's env note: continuous-playback sync was verified deterministically because the automated browser tab was backgrounded. During your full-system pass, verify the M4 sync overlay (<50 ms) once in a real focused browser window.
   - Test count sanity: suite is 96 passed on merge day; it must never drop below that.
4. **Worktree protocol lesson (standing):** integration runs single-agent, so use the main working directory directly on branch `integration`. If parallel agents are ever launched again, each MUST create its own `git worktree` before its first edit — never share a working directory.

## Round 0 — 2026-07-16 — Run order & protocol

**Execution order:**

1. **Now: `foundation` only.** Nothing else starts until foundation merges to `main`. Foundation agent: contracts correctness beats speed — lanes will hard-depend on your API shapes, schema, pose math, and synthetic fixtures.
2. **After foundation merges — start lanes in this priority order** (all four concurrently if capacity allows; if running fewer sessions, start in this order):
   1. **Lane C (viewer)** — longest lane and the earliest validation of the API contract; starts first.
   2. **Lane A (media)** — the core real-footage capability; small surface, should finish early.
   3. **Lane D (events)** — small and fully independent.
   4. **Lane B (recon)** — heaviest external dependency (COLMAP) and the most graceful-degradation slack; safe to start last.
3. **Merge policy:** merge to `main` as soon as your lane's acceptance passes — do not wait for other lanes. Expected finish order: A, D, then C, then B.
4. **After all four merge: `integration`.**

**Standing protocol (all agents):**
- Maintain `plan/status/<your-lane>.md` per `plan/status/TEMPLATE.md` — session start, every milestone, every blocker, before merge. Push status commits to your branch immediately; the coordinator reviews between rounds by reading these files.
- If blocked > 30 minutes on an ambiguity, write the blocker to your status file, push, and move to another task in your lane rather than guessing on a frozen contract.
- Evidence discipline: a checked acceptance box must name the test or the exact command + output that proves it.

*(Future rounds will be appended above this line as the coordinator reviews status files.)*