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>
6 lines
855 B
Markdown
6 lines
855 B
Markdown
# Cross-day lesson — Riverfront Steel, 2026-04-21
|
||
|
||
_Generated by `gpt-oss:120b` in 7.7s. Based on 5 events + 2 mid-day checkpoints._
|
||
|
||
Before each batch, generate the JSON payload for every role‑city‑state request, run it through a JSON linter, and verify that all brackets are closed and the role, city, and state values are properly quoted. Keep a pre‑cached list of at least one qualified candidate for each common position (Warehouse Associate, Machine Operator, Forklift Operator, Loader) in Toledo, OH, and insert that candidate into the payload before calling the tool. After building the plan, re‑validate the entire JSON schema; if any formatting error is detected, correct it immediately rather than proceeding to the next event. This ensures the pool isn’t empty and prevents JSON‑format failures that halt the workflow.
|