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
parent 6e34ef7baf
commit 41b0a99ed2
788 changed files with 107142 additions and 0 deletions
@@ -0,0 +1,59 @@
+# Scenario retrospective — Parallel Machining, 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: **0** (baseline — no prior T3 history)
+
+## Events
+
+| At | Kind | Role / Count | Pool | Fills | Turns | Dur(s) | Cites | Gaps |
+|---|---|---|---|---|---|---|---|---|
+| 10:00 | baseline_fill | Machine Operator × 2 | 987 | ✓ 2 | 3 | 22.9 | 1 | 2 |
+| 09:30 | recurring | Packer × 2 | - | ✗ 0 | 0 | 19.9 | 0 | 1 |
+
+## Final roster
+
+| Worker | Booked | Role | City, ST | Status |
+|---|---|---|---|---|
+| undefined Priya Parker | 10:00 | Machine Operator | Joliet, IL | confirmed |
+| undefined Omar F. Wright | 10:00 | Machine Operator | Joliet, IL | confirmed |
+
+## Gap signals
+
+### double_book
+- **10:00** — undefined Omar F. Wright already booked for 10:00
+
+### artifact
+- **10:00** — undefined is not an object (evaluating 'f.reason.slice')
+
+### drift_or_tool
+- **09:30** — aborted — 3 consecutive drift flags
+
+### fairness
+- _cross-event_ — Priya Parker (undefined) booked 2 times today
+
+### write_through_audit
+- _post-run_ — playbook_memory has 1526 entries (ran 2 events, expected ≥ 1 new entries from this run)
+
+## Workers touched across the week
+
+2 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 |
+|---|---|---|---|
+| 4383 | Priya Parker | 10:00 baseline_fill | booked |
+| 36405 | Omar F. Wright | 10:00 baseline_fill | booked |
+
+## Discovered patterns (meta-index)
+
+What the system identified across semantically-similar past fills as each event ran:
+
+- **10:00 baseline_fill** (Machine Operator): 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 0.59–1.00)
+- **09:30 recurring** (Packer): —
+
+## Narrative
+
+- 1/2 events reached consensus.
+- Final roster: 2 bookings across 1 distinct workers.
+- Workers touched (booked, failed, or otherwise decided): 2.
+- Playbook citations across the day: 1 (proof the feedback loop fired across events).
+- Dropped events: 09:30 recurring.