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

77 lines
3.6 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 — Apex Warehouse, 2026-04-26
Executor: `qwen3.5:latest` Reviewer: `qwen3:latest` Draft: `qwen2.5:latest` Overview(T3): `gpt-oss:20b`
Prior lessons loaded into executor context: **3** (from 2026-04-25, 2026-04-23, 2026-04-23)
## Events
| At | Kind | Role / Count | Pool | Fills | Turns | Dur(s) | Cites | Gaps |
|---|---|---|---|---|---|---|---|---|
| 10:30 | baseline_fill | Receiving Clerk × 1 | - | ✗ 0 | 0 | 24.5 | 0 | 1 |
| 15:30 | recurring | Quality Tech × 2 | 657 | ✓ 2 | 3 | 17.9 | 0 | 2 |
| 14:30 | expansion | Machine Operator × 5 | 600 | ✓ 5 | 2 | 14.3 | 0 | 6 |
## Final roster
| Worker | Booked | Role | City, ST | Status |
|---|---|---|---|---|
| undefined Fatima Parker | 15:30 | Quality Tech | Cleveland, OH | confirmed |
| undefined Shirley H. Davis | 15:30 | Quality Tech | Cleveland, OH | confirmed |
| undefined Anna Rivera | 14:30 | Machine Operator | Cleveland, OH | confirmed |
| undefined Jack K. Ramirez | 14:30 | Machine Operator | Cleveland, OH | confirmed |
| undefined Thomas J. Lewis | 14:30 | Machine Operator | Cleveland, OH | confirmed |
| undefined Brenda A. Cox | 14:30 | Machine Operator | Cleveland, OH | confirmed |
| undefined Lisa O. Diaz | 14:30 | Machine Operator | Cleveland, OH | confirmed |
## Gap signals
### drift_or_tool
- **10:30** — aborted — 3 consecutive drift flags
### double_book
- **15:30** — undefined Shirley H. Davis already booked for 15:30
- **14:30** — undefined Anna Rivera already booked for 15:30
- **14:30** — undefined Jack K. Ramirez already booked for 15:30
- **14:30** — undefined Thomas J. Lewis already booked for 15:30
- **14:30** — undefined Brenda A. Cox already booked for 15:30
- **14:30** — undefined Lisa O. Diaz already booked for 15:30
### artifact
- **15:30** — undefined is not an object (evaluating 'f.reason.slice')
- **14:30** — undefined is not an object (evaluating 'f.reason.slice')
### fairness
- _cross-event_ — Fatima Parker (undefined) booked 7 times today
### write_through_audit
- _post-run_ — playbook_memory has 1533 entries (ran 3 events, expected ≥ 2 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 |
|---|---|---|---|
| 11197 | Fatima Parker | 15:30 recurring | booked |
| 27255 | Shirley H. Davis | 15:30 recurring | booked |
| W500K-8217 | Anna Rivera | 14:30 expansion | booked |
| W500K-39010 | Jack K. Ramirez | 14:30 expansion | booked |
| W500K-29571 | Thomas J. Lewis | 14:30 expansion | booked |
| W500K-33852 | Brenda A. Cox | 14:30 expansion | booked |
| W500K-28588 | Lisa O. Diaz | 14:30 expansion | booked |
## Discovered patterns (meta-index)
What the system identified across semantically-similar past fills as each event ran:
- **10:30 baseline_fill** (Receiving Clerk): —
- **15:30 recurring** (Quality Tech): Across 25 similar past playbooks (20 workers examined) · recurring certifications: OSHA-10 (50%) · archetype mostly: communicator · reliability median 0.83 (range 0.591.00)
- **14:30 expansion** (Machine Operator): Across 25 similar past playbooks (22 workers examined) · recurring certifications: OSHA-10 (45%) · archetype mostly: communicator · reliability median 0.82 (range 0.591.00)
## Narrative
- 2/3 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).
- Dropped events: 10:30 baseline_fill.