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>
4.1 KiB
4.1 KiB
Scenario retrospective — Riverfront Steel, 2026-05-07
Executor: qwen3.5:latest Reviewer: qwen3:latest Draft: qwen2.5:latest Overview(T3): gpt-oss:20b
Prior lessons loaded into executor context: 3 (from 2026-04-28, 2026-04-26, 2026-04-25)
Events
| At | Kind | Role / Count | Pool | Fills | Turns | Dur(s) | Cites | Gaps |
|---|---|---|---|---|---|---|---|---|
| 12:00 | baseline_fill | Quality Tech × 3 | 692 | ✓ 3 | 3 | 24.1 | 1 | 3 |
| 09:30 | recurring | Machine Operator × 1 | 974 | ✓ 1 | 4 | 22.2 | 0 | 2 |
| 17:30 | emergency | Assembler × 3 | - | ✗ 0 | 0 | 17.4 | 0 | 1 |
| 15:30 | misplacement | Material Handler × 1 | 1118 | ✓ 1 | 2 | 17.2 | 0 | 2 |
Final roster
| Worker | Booked | Role | City, ST | Status |
|---|---|---|---|---|
| undefined Heather Martin | 12:00 | Quality Tech | Columbus, OH | no_show |
| undefined Alexander P. Brown | 12:00 | Quality Tech | Columbus, OH | confirmed |
| undefined Brenda Rivera | 12:00 | Quality Tech | Columbus, OH | confirmed |
| undefined Anthony Jimenez | 09:30 | Machine Operator | Columbus, OH | confirmed |
| undefined Jack Kim | 15:30 | Material Handler | Columbus, OH | confirmed |
Gap signals
double_book
- 12:00 — undefined Alexander P. Brown already booked for 12:00
- 12:00 — undefined Brenda Rivera already booked for 12:00
- 09:30 — undefined Anthony Jimenez already booked for 12:00
- 15:30 — undefined Jack Kim already booked for 12:00
artifact
- 12:00 — undefined is not an object (evaluating 'f.reason.slice')
- 09:30 — undefined is not an object (evaluating 'f.reason.slice')
- 15:30 — undefined is not an object (evaluating 'f.reason.slice')
drift_or_tool
- 17:30 — invalid JSON from executor: JSON Parse error: Unable to parse JSON string | raw: {"kind":"tool_call","tool":"hybrid_search","args":{"index_name":"workers_500k_v1","sql_filter":"role = 'Assembler' AND city = 'Columbus' AND state = 'OH' AND CAST(availability AS DOUBLE) > 0.7","question":"emergency Assembler Columbus OH","k":15},"rationale":"Execute hybrid_search FIRST as per canon
fairness
- cross-event — Heather Martin (undefined) booked 4 times today
write_through_audit
- post-run — playbook_memory has 1553 entries (ran 4 events, expected ≥ 3 new entries from this run)
Workers touched across the week
6 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-12576 | Heather Martin | 12:00 baseline_fill | booked |
| W500K-36259 | Alexander P. Brown | 12:00 baseline_fill | booked |
| W500K-7305 | Brenda Rivera | 12:00 baseline_fill | booked |
| 3223 | Anthony Jimenez | 09:30 recurring | booked |
| W500K-2115 | Jack Kim | 15:30 misplacement | booked |
| undefined | Heather Martin | 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 (Quality Tech): Across 25 similar past playbooks (30 workers examined) · recurring certifications: OSHA-10 (53%) · recurring skills: overhead crane (43%) · archetype mostly: communicator · reliability median 0.80 (range 0.19–1.00)
- 09:30 recurring (Machine Operator): Across 25 similar past playbooks (30 workers examined) · recurring certifications: OSHA-10 (53%) · recurring skills: overhead crane (43%) · archetype mostly: communicator · reliability median 0.80 (range 0.19–1.00)
- 17:30 emergency (Assembler): —
- 15:30 misplacement (Material Handler): Across 25 similar past playbooks (30 workers examined) · recurring certifications: OSHA-10 (53%) · recurring skills: overhead crane (40%) · archetype mostly: communicator · reliability median 0.79 (range 0.19–1.00)
Narrative
- 3/4 events reached consensus.
- Final roster: 5 bookings across 1 distinct workers.
- Workers touched (booked, failed, or otherwise decided): 6.
- Playbook citations across the day: 1 (proof the feedback loop fired across events).
- Dropped events: 17:30 emergency.