41b0a99ed2
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>
5.8 KiB
5.8 KiB
Scenario retrospective — Pioneer Assembly — Indianapolis Plant Expansion, 2026-05-03
Executor: kimi-k2.5 Reviewer: qwen3:latest Draft: qwen2.5:latest Overview(T3): disabled
Prior lessons loaded into executor context: 3 (from 2026-05-05, 2026-05-03, 2026-04-30)
Events
| At | Kind | Role / Count | Pool | Fills | Turns | Dur(s) | Cites | Gaps |
|---|---|---|---|---|---|---|---|---|
| 07:30 | baseline_fill | Assembler × 6 | 838 | ✓ 6 | 4 | 29.4 | 19 | 5 |
| 09:30 | recurring | Quality Tech × 2 | - | ✗ 0 | 0 | 21.9 | 0 | 1 |
| 11:00 | expansion | Machine Operator × 5 | 597 | ✓ 5 | 4 | 22.0 | 18 | 5 |
| 14:00 | emergency | Machine Operator × 3 | 657 | ✓ 3 | 4 | 22.3 | 19 | 3 |
| 16:00 | misplacement | Assembler × 1 | 838 | ✓ 1 | 4 | 21.3 | 20 | 1 |
Final roster
| Worker | Booked | Role | City, ST | Status |
|---|---|---|---|---|
| undefined Adam D. Watson | 07:30 | Assembler | Indianapolis, IN | no_show |
| undefined Jacob E. Bailey | 07:30 | Assembler | Indianapolis, IN | confirmed |
| undefined Andre C. Brooks | 07:30 | Assembler | Indianapolis, IN | confirmed |
| undefined Jeffrey Walker | 07:30 | Assembler | Indianapolis, IN | confirmed |
| undefined James S. Castillo | 07:30 | Assembler | Indianapolis, IN | confirmed |
| undefined Lauren F. Moore | 07:30 | Assembler | Indianapolis, IN | confirmed |
| undefined Alexander R. Evans | 11:00 | Machine Operator | Indianapolis, IN | confirmed |
| undefined Angela U. Ward | 11:00 | Machine Operator | Indianapolis, IN | confirmed |
| undefined Alexander P. Turner | 11:00 | Machine Operator | Indianapolis, IN | confirmed |
| undefined Christina Watson | 11:00 | Machine Operator | Indianapolis, IN | confirmed |
| undefined Amy S. Jenkins | 11:00 | Machine Operator | Indianapolis, IN | confirmed |
| undefined Alexander R. Evans | 14:00 | Machine Operator | Indianapolis, IN | confirmed |
| undefined Alexander P. Turner | 14:00 | Machine Operator | Indianapolis, IN | confirmed |
| undefined Angela U. Ward | 14:00 | Machine Operator | Indianapolis, IN | confirmed |
| undefined Adam D. Watson | 16:00 | Assembler | Indianapolis, IN | confirmed |
Gap signals
double_book
- 07:30 — undefined Jacob E. Bailey already booked for 07:30
- 07:30 — undefined Andre C. Brooks already booked for 07:30
- 07:30 — undefined Jeffrey Walker already booked for 07:30
- 07:30 — undefined James S. Castillo already booked for 07:30
- 07:30 — undefined Lauren F. Moore already booked for 07:30
- 11:00 — undefined Alexander R. Evans already booked for 07:30
- 11:00 — undefined Angela U. Ward already booked for 07:30
- 11:00 — undefined Alexander P. Turner already booked for 07:30
- 11:00 — undefined Christina Watson already booked for 07:30
- 11:00 — undefined Amy S. Jenkins already booked for 07:30
- 14:00 — undefined Alexander R. Evans already booked for 07:30
- 14:00 — undefined Alexander P. Turner already booked for 07:30
- 14:00 — undefined Angela U. Ward already booked for 07:30
- 16:00 — undefined Adam D. Watson already booked for 07:30
drift_or_tool
- 09:30 — executor returned unexpected shape: {"kind":"sql","args":{"query":"SELECT worker_id, name, role, city, state, availability, reliability, skills FROM workers_500k WHERE worker_id = 41658"},"rationale":"Verify second candidate Frank G. Ro
fairness
- cross-event — Adam D. Watson (undefined) booked 14 times today
write_through_audit
- post-run — playbook_memory has 1931 entries (ran 5 events, expected ≥ 4 new entries from this run)
Workers touched across the week
12 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 |
|---|---|---|---|
| W500K-49897 | Adam D. Watson | 07:30 baseline_fill + 16:00 misplacement | booked |
| W500K-24626 | Jacob E. Bailey | 07:30 baseline_fill | booked |
| W500K-45788 | Andre C. Brooks | 07:30 baseline_fill | booked |
| W500K-7814 | Jeffrey Walker | 07:30 baseline_fill | booked |
| W500K-47104 | James S. Castillo | 07:30 baseline_fill | booked |
| W500K-41683 | Lauren F. Moore | 07:30 baseline_fill | booked |
| W500K-34233 | Alexander R. Evans | 11:00 expansion + 14:00 emergency | booked |
| W500K-23524 | Angela U. Ward | 11:00 expansion + 14:00 emergency | booked |
| W500K-23467 | Alexander P. Turner | 11:00 expansion + 14:00 emergency | booked |
| W500K-6479 | Christina Watson | 11:00 expansion | booked |
| W500K-18400 | Amy S. Jenkins | 11:00 expansion | booked |
| undefined | Adam D. Watson | 07:30 | no_show |
Discovered patterns (meta-index)
What the system identified across semantically-similar past fills as each event ran:
- 07:30 baseline_fill (Assembler): Across 25 similar past playbooks (17 workers examined) · recurring certifications: Forklift (47%) · archetype mostly: communicator · reliability median 0.81 (range 0.34–1.00)
- 09:30 recurring (Quality Tech): —
- 11:00 expansion (Machine Operator): Across 25 similar past playbooks (18 workers examined) · archetype mostly: communicator · reliability median 0.80 (range 0.34–1.00)
- 14:00 emergency (Machine Operator): Across 25 similar past playbooks (18 workers examined) · archetype mostly: communicator · reliability median 0.80 (range 0.34–1.00)
- 16:00 misplacement (Assembler): Across 25 similar past playbooks (17 workers examined) · recurring certifications: Forklift (47%) · archetype mostly: reliable · reliability median 0.81 (range 0.34–1.00)
Narrative
- 4/5 events reached consensus.
- Final roster: 15 bookings across 1 distinct workers.
- Workers touched (booked, failed, or otherwise decided): 12.
- Playbook citations across the day: 76 (proof the feedback loop fired across events).
- Dropped events: 09:30 recurring.