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>
3.0 KiB
3.0 KiB
Scenario retrospective — Riverfront Steel, 2026-04-28
Executor: qwen3.5:latest Reviewer: qwen3:latest Draft: qwen2.5:latest Overview(T3): gpt-oss:20b
Prior lessons loaded into executor context: 3 (from 2026-04-26, 2026-04-25, 2026-04-23)
Events
| At | Kind | Role / Count | Pool | Fills | Turns | Dur(s) | Cites | Gaps |
|---|---|---|---|---|---|---|---|---|
| 11:00 | baseline_fill | Assembler × 3 | 876 | ✓ 3 | 3 | 25.9 | 0 | 3 |
| 14:00 | recurring | Material Handler × 1 | 1115 | ✓ 1 | 3 | 15.2 | 0 | 2 |
| 08:30 | misplacement | Packer × 1 | - | ✗ 0 | 0 | 18.9 | 0 | 1 |
Final roster
| Worker | Booked | Role | City, ST | Status |
|---|---|---|---|---|
| undefined Ivan N. Wilson | 11:00 | Assembler | Toledo, OH | no_show |
| undefined Michelle Y. Thompson | 11:00 | Assembler | Toledo, OH | confirmed |
| undefined Paul Peterson | 11:00 | Assembler | Toledo, OH | confirmed |
| undefined Christine R. Jones | 14:00 | Material Handler | Toledo, OH | confirmed |
Gap signals
double_book
- 11:00 — undefined Michelle Y. Thompson already booked for 11:00
- 11:00 — undefined Paul Peterson already booked for 11:00
- 14:00 — undefined Christine R. Jones already booked for 11:00
artifact
- 11:00 — undefined is not an object (evaluating 'f.reason.slice')
- 14:00 — undefined is not an object (evaluating 'f.reason.slice')
drift_or_tool
- 08:30 — aborted — 3 consecutive drift flags
fairness
- cross-event — Ivan N. Wilson (undefined) booked 3 times today
write_through_audit
- post-run — playbook_memory has 1535 entries (ran 3 events, expected ≥ 2 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 |
|---|---|---|---|
| W500K-42601 | Ivan N. Wilson | 11:00 baseline_fill | booked |
| W500K-45498 | Michelle Y. Thompson | 11:00 baseline_fill | booked |
| W500K-11873 | Paul Peterson | 11:00 baseline_fill | booked |
| 34311 | Christine R. Jones | 14:00 recurring | booked |
| undefined | Ivan N. Wilson | 11:00 | no_show |
Discovered patterns (meta-index)
What the system identified across semantically-similar past fills as each event ran:
- 11:00 baseline_fill (Assembler): Across 25 similar past playbooks (21 workers examined) · recurring certifications: OSHA-10 (48%) · archetype mostly: communicator · reliability median 0.82 (range 0.59–1.00)
- 14:00 recurring (Material Handler): Across 25 similar past playbooks (22 workers examined) · recurring certifications: OSHA-10 (45%) · archetype mostly: flexible · reliability median 0.82 (range 0.59–1.00)
- 08:30 misplacement (Packer): —
Narrative
- 2/3 events reached consensus.
- Final roster: 4 bookings across 1 distinct workers.
- Workers touched (booked, failed, or otherwise decided): 5.
- Playbook citations across the day: 0 (proof the feedback loop fired across events).
- Dropped events: 08:30 misplacement.