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>
74 lines
3.7 KiB
Markdown
74 lines
3.7 KiB
Markdown
# Scenario retrospective — Centennial Packaging, 2026-04-22
|
||
|
||
Executor: `qwen3.5:latest` Reviewer: `qwen3:latest` Draft: `qwen2.5:latest` Overview(T3): `gpt-oss:20b`
|
||
Prior lessons loaded into executor context: **3** (from 2026-04-21, 2026-04-21, 2026-04-21)
|
||
|
||
## Events
|
||
|
||
| At | Kind | Role / Count | Pool | Fills | Turns | Dur(s) | Cites | Gaps |
|
||
|---|---|---|---|---|---|---|---|---|
|
||
| 09:00 | baseline_fill | Forklift Operator × 1 | 1176 | ✓ 1 | 4 | 30.5 | 0 | 1 |
|
||
| 09:00 | recurring | Assembler × 1 | 911 | ✓ 1 | 2 | 11.2 | 0 | 2 |
|
||
| 11:30 | expansion | Assembler × 5 | 559 | ✓ 5 | 2 | 12.7 | 0 | 6 |
|
||
|
||
## Final roster
|
||
|
||
| Worker | Booked | Role | City, ST | Status |
|
||
|---|---|---|---|---|
|
||
| undefined Amanda Edwards | 09:00 | Forklift Operator | Cleveland, OH | confirmed |
|
||
| undefined Betty K. Bennett | 09:00 | Assembler | Cleveland, OH | confirmed |
|
||
| undefined Zachary Davis | 11:30 | Assembler | Cleveland, OH | confirmed |
|
||
| undefined Nicholas K. Hill | 11:30 | Assembler | Cleveland, OH | confirmed |
|
||
| undefined Susan U. Carter | 11:30 | Assembler | Cleveland, OH | confirmed |
|
||
| undefined Kevin K. Mendoza | 11:30 | Assembler | Cleveland, OH | confirmed |
|
||
| undefined Miguel Z. Hall | 11:30 | Assembler | Cleveland, OH | confirmed |
|
||
|
||
## Gap signals
|
||
|
||
### artifact
|
||
- **09:00** — undefined is not an object (evaluating 'f.reason.slice')
|
||
- **09:00** — undefined is not an object (evaluating 'f.reason.slice')
|
||
- **11:30** — undefined is not an object (evaluating 'f.reason.slice')
|
||
|
||
### double_book
|
||
- **09:00** — undefined Betty K. Bennett already booked for 09:00
|
||
- **11:30** — undefined Zachary Davis already booked for 09:00
|
||
- **11:30** — undefined Nicholas K. Hill already booked for 09:00
|
||
- **11:30** — undefined Susan U. Carter already booked for 09:00
|
||
- **11:30** — undefined Kevin K. Mendoza already booked for 09:00
|
||
- **11:30** — undefined Miguel Z. Hall already booked for 09:00
|
||
|
||
### fairness
|
||
- _cross-event_ — Amanda Edwards (undefined) booked 7 times today
|
||
|
||
### write_through_audit
|
||
- _post-run_ — playbook_memory has 1488 entries (ran 3 events, expected ≥ 3 new entries from this run)
|
||
|
||
## Workers touched across the week
|
||
|
||
7 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 |
|
||
|---|---|---|---|
|
||
| 9810 | Amanda Edwards | 09:00 baseline_fill | booked |
|
||
| W500K-35240 | Betty K. Bennett | 09:00 recurring | booked |
|
||
| W500K-8211 | Zachary Davis | 11:30 expansion | booked |
|
||
| W500K-46732 | Nicholas K. Hill | 11:30 expansion | booked |
|
||
| W500K-23030 | Susan U. Carter | 11:30 expansion | booked |
|
||
| W500K-15922 | Kevin K. Mendoza | 11:30 expansion | booked |
|
||
| W500K-27715 | Miguel Z. Hall | 11:30 expansion | booked |
|
||
|
||
## Discovered patterns (meta-index)
|
||
|
||
What the system identified across semantically-similar past fills as each event ran:
|
||
|
||
- **09:00 baseline_fill** (Forklift Operator): Across 25 similar past playbooks (13 workers examined) · recurring certifications: OSHA-10 (69%) · archetype mostly: communicator · reliability median 0.89 (range 0.59–1.00)
|
||
- **09:00 recurring** (Assembler): Across 25 similar past playbooks (14 workers examined) · recurring certifications: OSHA-10 (64%) · archetype mostly: communicator · reliability median 0.89 (range 0.59–1.00)
|
||
- **11:30 expansion** (Assembler): Across 25 similar past playbooks (15 workers examined) · recurring certifications: OSHA-10 (60%) · archetype mostly: communicator · reliability median 0.83 (range 0.59–1.00)
|
||
|
||
## Narrative
|
||
|
||
- 3/3 events reached consensus.
|
||
- Final roster: 7 bookings across 1 distinct workers.
|
||
- Workers touched (booked, failed, or otherwise decided): 7.
|
||
- Playbook citations across the day: 0 (proof the feedback loop fired across events). |