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>
646 B
646 B
Cross-day lesson — Riverfront Steel, 2026-04-21
Generated by gpt-oss:20b in 5.4s. Based on 5 events + 2 mid-day checkpoints.
**
Before any expansion or emergency event, pre‑fetch and validate the pool data for the target location—missing pool info caused all failures. Use a smaller, more reliable model (e.g., gpt‑4o‑mini) for large or high‑risk events and keep prompts concise. Verify that the number of required positions matches available candidates before invoking the model. If the model returns empty output, switch to a more robust model and re‑validate the data. This will reduce failures and improve turnaround.