chore: add real content that was sitting untracked

Surfaced by today's untracked-files audit. None of these are accidents —
multiple are referenced by name in CLAUDE.md and memory files but were
never added.

Categories:
- docs/PHASE_AUDIT_GUIDE.md (106 LOC) — Claude Code phase audit guidance
- ops/systemd/lakehouse-langfuse-bridge.service — Langfuse bridge unit
- package.json — top-level npm manifest
- scripts/e2e_pipeline_check.sh + production_smoke.sh — real test scripts
- reports/kimi/audit-last-week*.md — the "Two reports live" CLAUDE.md cites
- tests/multi-agent/scenarios/ — 44 staffing scenarios (cutover decision A)
- tests/multi-agent/playbooks/ — 102 playbook records
- tests/battery/, tests/agent_test/PRD.md, tests/real-world/* — real tests
- sidecar/sidecar/{lab_ui,pipeline_lab}.py — 888 LOC dev-only UIs that
  remain in service post-sidecar-drop (commit ba928b1 explicitly kept them)

Sensitivity check: scenarios use synthetic company names ("Heritage Foods",
"Cornerstone Fabrication"); audit reports describe code findings only;
no PII or secrets surfaced.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

tests/multi-agent/playbooks/scenario-2026-04-21T02-10-55/report.md

@@ -0,0 +1,72 @@
+# Scenario retrospective — Heritage Foods, 2026-05-09
+
+Executor: `qwen3.5:latest`   Reviewer: `qwen3:latest`   Draft: `qwen2.5:latest`   Overview(T3): `gpt-oss:20b`
+Prior lessons loaded into executor context: **3** (from 2026-05-07, 2026-04-28, 2026-04-26)
+
+## Events
+
+| At | Kind | Role / Count | Pool | Fills | Turns | Dur(s) | Cites | Gaps |
+|---|---|---|---|---|---|---|---|---|
+| 12:00 | baseline_fill | Assembler × 1 | 869 | ✓ 1 | 3 | 21.9 | 1 | 1 |
+| 17:30 | recurring | Welder × 1 | 311 | ✓ 1 | 3 | 15.2 | 0 | 2 |
+| 13:30 | emergency | Material Handler × 2 | 717 | ✓ 2 | 3 | 17.4 | 1 | 3 |
+| 12:00 | misplacement | Receiving Clerk × 1 | - | ✗ 0 | 0 | 25.1 | 0 | 1 |
+
+## Final roster
+
+| Worker | Booked | Role | City, ST | Status |
+|---|---|---|---|---|
+| undefined Amy Q. Lewis | 12:00 | Assembler | Cincinnati, OH | no_show |
+| undefined Betty O. Cruz | 17:30 | Welder | Cincinnati, OH | confirmed |
+| undefined Malik King | 13:30 | Material Handler | Cincinnati, OH | confirmed |
+| undefined Miguel Morris | 13:30 | Material Handler | Cincinnati, OH | confirmed |
+
+## Gap signals
+
+### artifact
+- **12:00** — undefined is not an object (evaluating 'f.reason.slice')
+- **17:30** — undefined is not an object (evaluating 'f.reason.slice')
+- **13:30** — undefined is not an object (evaluating 'f.reason.slice')
+
+### double_book
+- **17:30** — undefined Betty O. Cruz already booked for 12:00
+- **13:30** — undefined Malik King already booked for 12:00
+- **13:30** — undefined Miguel Morris already booked for 12:00
+
+### drift_or_tool
+- **12:00** — aborted — 3 consecutive drift flags
+
+### fairness
+- _cross-event_ — Amy Q. Lewis (undefined) booked 3 times today
+
+### write_through_audit
+- _post-run_ — playbook_memory has 1558 entries (ran 4 events, expected ≥ 3 new entries from this run)
+
+## Workers touched across the week
+
+5 distinct workers made it through to a decision. Every one is accounted for below — no-shows flagged, rebookings noted, everyone visible.
+
+| Worker ID | Name | Events | Outcome |
+|---|---|---|---|
+| 23650 | Amy Q. Lewis | 12:00 baseline_fill | booked |
+| 23232 | Betty O. Cruz | 17:30 recurring | booked |
+| W500K-10726 | Malik King | 13:30 emergency | booked |
+| W500K-2559 | Miguel Morris | 13:30 emergency | booked |
+| undefined | Amy Q. Lewis | 12:00 | no_show |
+
+## Discovered patterns (meta-index)
+
+What the system identified across semantically-similar past fills as each event ran:
+
+- **12:00 baseline_fill** (Assembler): Across 25 similar past playbooks (28 workers examined) · recurring certifications: OSHA-10 (46%) · archetype mostly: communicator · reliability median 0.80 (range 0.19–1.00)
+- **17:30 recurring** (Welder): Across 25 similar past playbooks (28 workers examined) · recurring certifications: OSHA-10 (46%) · archetype mostly: communicator · reliability median 0.80 (range 0.19–1.00)
+- **13:30 emergency** (Material Handler): Across 25 similar past playbooks (30 workers examined) · recurring certifications: OSHA-10 (47%) · archetype mostly: communicator · reliability median 0.79 (range 0.19–1.00)
+- **12:00 misplacement** (Receiving Clerk): —
+
+## Narrative
+
+- 3/4 events reached consensus.
+- Final roster: 4 bookings across 1 distinct workers.
+- Workers touched (booked, failed, or otherwise decided): 5.
+- Playbook citations across the day: 2 (proof the feedback loop fired across events).
+- Dropped events: 12:00 misplacement.