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>
81 lines
4.1 KiB
Markdown
81 lines
4.1 KiB
Markdown
# Scenario retrospective — Midway Distribution — Joliet DC Ramp, 2026-05-02
|
||
|
||
Executor: `kimi-k2.5` Reviewer: `qwen3:latest` Draft: `qwen2.5:latest` Overview(T3): `disabled`
|
||
Prior lessons loaded into executor context: **3** (from 2026-05-10, 2026-05-02, 2026-05-01)
|
||
|
||
## Events
|
||
|
||
| At | Kind | Role / Count | Pool | Fills | Turns | Dur(s) | Cites | Gaps |
|
||
|---|---|---|---|---|---|---|---|---|
|
||
| 07:00 | baseline_fill | Warehouse Associate × 5 | 821 | ✓ 5 | 4 | 23.6 | 9 | 4 |
|
||
| 10:00 | recurring | Forklift Operator × 3 | 1178 | ✓ 3 | 4 | 26.2 | 16 | 3 |
|
||
| 12:30 | expansion | Picker × 4 | - | ✗ 0 | 0 | 27.9 | 0 | 1 |
|
||
| 15:00 | misplacement | Forklift Operator × 1 | 1178 | ✓ 1 | 4 | 37.2 | 17 | 1 |
|
||
|
||
## Final roster
|
||
|
||
| Worker | Booked | Role | City, ST | Status |
|
||
|---|---|---|---|---|
|
||
| undefined Nathan Y. Miller | 07:00 | Warehouse Associate | Joliet, IL | no_show |
|
||
| undefined Emily E. Powell | 07:00 | Warehouse Associate | Joliet, IL | confirmed |
|
||
| undefined Andre Davis | 07:00 | Warehouse Associate | Joliet, IL | confirmed |
|
||
| undefined Kelly L. Nelson | 07:00 | Warehouse Associate | Joliet, IL | confirmed |
|
||
| undefined Mary H. King | 07:00 | Warehouse Associate | Joliet, IL | confirmed |
|
||
| undefined Joshua Taylor | 10:00 | Forklift Operator | Joliet, IL | confirmed |
|
||
| undefined Joyce D. Reyes | 10:00 | Forklift Operator | Joliet, IL | confirmed |
|
||
| undefined Lauren F. Adams | 10:00 | Forklift Operator | Joliet, IL | confirmed |
|
||
| undefined Joshua Taylor | 15:00 | Forklift Operator | Joliet, IL | confirmed |
|
||
|
||
## Gap signals
|
||
|
||
### double_book
|
||
- **07:00** — undefined Emily E. Powell already booked for 07:00
|
||
- **07:00** — undefined Andre Davis already booked for 07:00
|
||
- **07:00** — undefined Kelly L. Nelson already booked for 07:00
|
||
- **07:00** — undefined Mary H. King already booked for 07:00
|
||
- **10:00** — undefined Joshua Taylor already booked for 07:00
|
||
- **10:00** — undefined Joyce D. Reyes already booked for 07:00
|
||
- **10:00** — undefined Lauren F. Adams already booked for 07:00
|
||
- **15:00** — undefined Joshua Taylor already booked for 07:00
|
||
|
||
### drift_or_tool
|
||
- **12:30** — aborted — 3 consecutive drift flags
|
||
|
||
### fairness
|
||
- _cross-event_ — Nathan Y. Miller (undefined) booked 8 times today
|
||
|
||
### write_through_audit
|
||
- _post-run_ — playbook_memory has 1927 entries (ran 4 events, expected ≥ 3 new entries from this run)
|
||
|
||
## Workers touched across the week
|
||
|
||
9 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-16430 | Nathan Y. Miller | 07:00 baseline_fill | booked |
|
||
| W500K-23612 | Emily E. Powell | 07:00 baseline_fill | booked |
|
||
| W500K-2245 | Andre Davis | 07:00 baseline_fill | booked |
|
||
| W500K-23801 | Kelly L. Nelson | 07:00 baseline_fill | booked |
|
||
| W500K-37707 | Mary H. King | 07:00 baseline_fill | booked |
|
||
| W500K-2372 | Joshua Taylor | 10:00 recurring + 15:00 misplacement | booked |
|
||
| W500K-41031 | Joyce D. Reyes | 10:00 recurring | booked |
|
||
| W500K-46701 | Lauren F. Adams | 10:00 recurring | booked |
|
||
| undefined | Nathan Y. Miller | 07:00 | no_show |
|
||
|
||
## Discovered patterns (meta-index)
|
||
|
||
What the system identified across semantically-similar past fills as each event ran:
|
||
|
||
- **07:00 baseline_fill** (Warehouse Associate): Across 25 similar past playbooks (18 workers examined) · archetype mostly: communicator · reliability median 0.80 (range 0.34–1.00)
|
||
- **10:00 recurring** (Forklift Operator): Across 25 similar past playbooks (18 workers examined) · archetype mostly: communicator · reliability median 0.80 (range 0.34–1.00)
|
||
- **12:30 expansion** (Picker): —
|
||
- **15:00 misplacement** (Forklift Operator): Across 25 similar past playbooks (18 workers examined) · archetype mostly: communicator · reliability median 0.80 (range 0.34–1.00)
|
||
|
||
## Narrative
|
||
|
||
- 3/4 events reached consensus.
|
||
- Final roster: 9 bookings across 1 distinct workers.
|
||
- Workers touched (booked, failed, or otherwise decided): 9.
|
||
- Playbook citations across the day: 42 (proof the feedback loop fired across events).
|
||
- Dropped events: 12:30 expansion. |