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>
690 B
690 B
Cross-day lesson — Pioneer Assembly, 2026-04-24
Generated by gpt-oss:20b in 3.7s. Based on 1 events + 1 mid-day checkpoints.
**
Before initiating a baseline_fill for a new shift, run a quick tool‑accuracy audit and confirm all clerks have completed the latest training module. Allocate a sufficient pool of clerks and schedule a buffer shift load to avoid gaps; if the pool is empty, the baseline will fail immediately. After the fill, monitor for drift by comparing current performance metrics to the baseline and adjust shift assignments or retrain as needed. This proactive check prevents the “Receiving Clerk Chicago drift risk” and ensures a smooth start to the day.