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
723 B
Markdown
6 lines
723 B
Markdown
# Cross-day lesson — Midway Distribution — Joliet DC Ramp, 2026-04-23
|
||
|
||
_Generated by `gpt-oss:120b` in 5.5s. Based on 4 events + 2 mid-day checkpoints._
|
||
|
||
If an expansion event returns a [ZERO‑SUPPLY] tag (as the Picker role did in Joliet), immediately pivot to the nearest city with likely candidates—Crest Hill, IL (≈10 mi, still within the $3/hr local‑bonus radius). Before running the search, launch a hybrid_search for Pickers in Crest Hill with k=40 and verify that the executor returns valid JSON, then cache that candidate pool for any later fills. Cross‑check candidate IDs across all active events to prevent double‑booking (e.g., Joshua Taylor) before confirming any assignment.
|