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>
57 lines
3.6 KiB
Markdown
57 lines
3.6 KiB
Markdown
# Scenario retrospective — Riverfront Steel, 2026-04-21
|
||
|
||
Executor: `mistral:latest` Reviewer: `qwen2.5:latest` Draft: `qwen2.5:latest` Overview(T3): `gpt-oss:120b (cloud)`
|
||
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 |
|
||
|---|---|---|---|---|---|---|---|---|
|
||
| 08:00 | baseline_fill | Warehouse Associate × 3 | - | ✗ 0 | 0 | 9.3 | 0 | 1 |
|
||
| 10:30 | recurring | Machine Operator × 2 | - | ✗ 0 | 0 | 7.4 | 0 | 1 |
|
||
| 12:15 | expansion | Forklift Operator × 5 | - | ✗ 0 | 0 | 28.8 | 0 | 1 |
|
||
| 14:00 | emergency | Loader × 4 | - | ✗ 0 | 0 | 3.1 | 0 | 1 |
|
||
| 15:45 | misplacement | Warehouse Associate × 1 | - | ✗ 0 | 0 | 7.4 | 0 | 1 |
|
||
|
||
## Final roster
|
||
|
||
| Worker | Booked | Role | City, ST | Status |
|
||
|---|---|---|---|---|
|
||
|
||
## Gap signals
|
||
|
||
### drift_or_tool
|
||
- **08:00** — invalid JSON from reviewer: JSON Parse error: Unrecognized token '|' | raw: {"kind":"critique","verdict":"continue" | "drift","notes":"Ensure the proposal includes exactly 3 Warehouse Associates from Toledo, OH, and verify at least one candidate through SQL."}
|
||
- **10:30** — invalid JSON from reviewer: JSON Parse error: Unrecognized token '|' | raw: {"kind":"critique","verdict":"continue" | "drift" | "approve_done","notes":"Ensure the SQL verification step includes at least one of the proposed Machine Operators from Toledo, OH with the role 'Machine Operator', and confirm exactly 2 fills are proposed."}
|
||
- **12:15** — invalid JSON from executor: JSON Parse error: Expected ']' | raw: {"kind":"plan","steps":["1. TOOL_CALL sql({'query':"SELECT COUNT(*) FROM workers_500k WHERE role = 'Forklift Operator' AND city = 'Toledo' AND state = 'OH' AND CAST(availability AS DOUBLE) > 0.5 AND CAST(reliability AS DOUBLE) > 0.75"})","2. TOOL_RESULT sql: pool_size=x, where x is the number of wor
|
||
- **14:00** — invalid JSON from executor: JSON Parse error: Invalid escape character ' | raw: {"kind":"plan","steps":["Check JSON payload structure and escape all single quotes",
|
||
"hybrid_search(sql_filter: 'role = \'Loader\' AND city = \'Toledo\' AND state = \'OH\' AND CAST(availability AS DOUBLE) > 0.7', question:'emergency Loader Toledo', index_name:'workers_500k
|
||
- **15:45** — invalid JSON from reviewer: JSON Parse error: Unrecognized token '|' | raw: {"kind":"critique","verdict":"continue" | "drift" | "approve_done","notes":"Ensure the tool calls use parameterized queries and validate the JSON structure. Verify at least one candidate from Toledo, OH with the role 'Warehouse Associate'."}
|
||
|
||
### write_through_audit
|
||
- _post-run_ — playbook_memory has 1214 entries (ran 5 events, expected ≥ 0 new entries from this run)
|
||
|
||
## Workers touched across the week
|
||
|
||
0 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 |
|
||
|---|---|---|---|
|
||
|
||
## Discovered patterns (meta-index)
|
||
|
||
What the system identified across semantically-similar past fills as each event ran:
|
||
|
||
- **08:00 baseline_fill** (Warehouse Associate): —
|
||
- **10:30 recurring** (Machine Operator): —
|
||
- **12:15 expansion** (Forklift Operator): —
|
||
- **14:00 emergency** (Loader): —
|
||
- **15:45 misplacement** (Warehouse Associate): —
|
||
|
||
## Narrative
|
||
|
||
- 0/5 events reached consensus.
|
||
- Final roster: 0 bookings across 0 distinct workers.
|
||
- Workers touched (booked, failed, or otherwise decided): 0.
|
||
- Playbook citations across the day: 0 (proof the feedback loop fired across events).
|
||
- Dropped events: 08:00 baseline_fill, 10:30 recurring, 12:15 expansion, 14:00 emergency, 15:45 misplacement. |