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>
7 lines
700 B
Markdown
7 lines
700 B
Markdown
# Cross-day lesson — Riverfront Steel, 2026-04-21
|
||
|
||
_Generated by `gpt-oss:20b` in 6.0s. Based on 5 events + 2 mid-day checkpoints._
|
||
|
||
**
|
||
Before assigning any shift, pull the current schedule for every worker in the pool and flag any overlapping assignments. Use a single source of truth for shift times and enforce a lock on a worker’s calendar during the assignment process. Verify that the reason field is populated for every placement to avoid artifact errors, especially for high‑volume roles like Loader and Forklift Operator. After each event, update the pool and turns counts to keep the risk model accurate. This prevents double‑booking and ensures data integrity across all events.
|