root 41b0a99ed2 chore: add real content that was sitting untracked
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>
2026-05-02 22:22:10 -05:00

81 lines
4.5 KiB
Markdown
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

# Scenario retrospective — Great Lakes Mfg, 2026-04-21
Executor: `qwen3.5:latest` Reviewer: `qwen3:latest` Draft: `qwen2.5:latest` Overview(T3): `gpt-oss:20b`
Prior lessons loaded into executor context: **3** (from 2026-04-23, 2026-04-22, 2026-04-21)
## Events
| At | Kind | Role / Count | Pool | Fills | Turns | Dur(s) | Cites | Gaps |
|---|---|---|---|---|---|---|---|---|
| 13:00 | baseline_fill | Material Handler × 2 | 1066 | ✓ 2 | 3 | 25.0 | 0 | 2 |
| 14:30 | recurring | Assembler × 2 | 869 | ✓ 2 | 2 | 10.6 | 0 | 3 |
| 10:30 | emergency | Material Handler × 3 | 717 | ✓ 3 | 2 | 11.3 | 0 | 4 |
| 13:30 | misplacement | Shipping Clerk × 1 | 579 | ✓ 1 | 3 | 28.5 | 0 | 2 |
## Final roster
| Worker | Booked | Role | City, ST | Status |
|---|---|---|---|---|
| undefined Jennifer C. Morales | 13:00 | Material Handler | Cincinnati, OH | no_show |
| undefined Christine A. Miller | 13:00 | Material Handler | Cincinnati, OH | confirmed |
| undefined Amy Q. Lewis | 14:30 | Assembler | Cincinnati, OH | confirmed |
| undefined Cynthia R. Anderson | 14:30 | Assembler | Cincinnati, OH | confirmed |
| undefined Malik King | 10:30 | Material Handler | Cincinnati, OH | confirmed |
| undefined Miguel Morris | 10:30 | Material Handler | Cincinnati, OH | confirmed |
| undefined Lauren H. Moore | 10:30 | Material Handler | Cincinnati, OH | confirmed |
| undefined Mei X. Jimenez | 13:30 | Shipping Clerk | Cincinnati, OH | confirmed |
## Gap signals
### double_book
- **13:00** — undefined Christine A. Miller already booked for 13:00
- **14:30** — undefined Amy Q. Lewis already booked for 13:00
- **14:30** — undefined Cynthia R. Anderson already booked for 13:00
- **10:30** — undefined Malik King already booked for 13:00
- **10:30** — undefined Miguel Morris already booked for 13:00
- **10:30** — undefined Lauren H. Moore already booked for 13:00
- **13:30** — undefined Mei X. Jimenez already booked for 13:00
### artifact
- **13:00** — undefined is not an object (evaluating 'f.reason.slice')
- **14:30** — undefined is not an object (evaluating 'f.reason.slice')
- **10:30** — undefined is not an object (evaluating 'f.reason.slice')
- **13:30** — undefined is not an object (evaluating 'f.reason.slice')
### fairness
- _cross-event_ — Jennifer C. Morales (undefined) booked 7 times today
### write_through_audit
- _post-run_ — playbook_memory has 1525 entries (ran 4 events, expected ≥ 4 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 |
|---|---|---|---|
| 33620 | Jennifer C. Morales | 13:00 baseline_fill | booked |
| 26312 | Christine A. Miller | 13:00 baseline_fill | booked |
| W500K-23650 | Amy Q. Lewis | 14:30 recurring | booked |
| W500K-38133 | Cynthia R. Anderson | 14:30 recurring | booked |
| W500K-10726 | Malik King | 10:30 emergency | booked |
| W500K-2559 | Miguel Morris | 10:30 emergency | booked |
| W500K-29283 | Lauren H. Moore | 10:30 emergency | booked |
| 31665 | Mei X. Jimenez | 13:30 misplacement | booked |
| undefined | Jennifer C. Morales | 13:00 | no_show |
## Discovered patterns (meta-index)
What the system identified across semantically-similar past fills as each event ran:
- **13:00 baseline_fill** (Material Handler): Across 25 similar past playbooks (15 workers examined) · recurring certifications: OSHA-10 (60%) · archetype mostly: flexible · reliability median 0.83 (range 0.591.00)
- **14:30 recurring** (Assembler): Across 25 similar past playbooks (15 workers examined) · recurring certifications: OSHA-10 (60%) · archetype mostly: flexible · reliability median 0.83 (range 0.591.00)
- **10:30 emergency** (Material Handler): Across 25 similar past playbooks (17 workers examined) · recurring certifications: OSHA-10 (53%) · recurring skills: 6S (41%) · archetype mostly: communicator · reliability median 0.83 (range 0.591.00)
- **13:30 misplacement** (Shipping Clerk): Across 25 similar past playbooks (17 workers examined) · recurring certifications: OSHA-10 (53%) · recurring skills: 6S (41%) · archetype mostly: communicator · reliability median 0.83 (range 0.591.00)
## Narrative
- 4/4 events reached consensus.
- Final roster: 8 bookings across 1 distinct workers.
- Workers touched (booked, failed, or otherwise decided): 9.
- Playbook citations across the day: 0 (proof the feedback loop fired across events).