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>
80 lines
4.9 KiB
JSON
80 lines
4.9 KiB
JSON
[
|
||
{
|
||
"date": "2026-05-05",
|
||
"client": "Riverline Logistics — Nashville Downtown Build-Out",
|
||
"cities": "Nashville",
|
||
"states": "TN",
|
||
"events_total": 5,
|
||
"events_ok": 5,
|
||
"checkpoint_count": 2,
|
||
"model": "gpt-oss:120b",
|
||
"cloud": true,
|
||
"lesson": "When multiple fills are requested for the same city, lock each worker to a single shift in a temporary assignment map before processing the next request. Pre‑select a backup pool from the nearest alternate city (e.g., Murfreesboro, TN) that stays within the 75‑mi bonus radius and reserve those candidates for emergency or misplacement fills. Before confirming any fill, run a quick cross‑check against the map to catch potential double‑bookings, especially for workers who appear in consecutive requests. If a double‑booking is detected, substitute the reserved Murfreesboro candidate to preserve the schedule and bonus eligibility.",
|
||
"checkpoints": [
|
||
{
|
||
"after": "09:00",
|
||
"risk": "double‑booked staff",
|
||
"hint": "Check worker assignments to avoid double‑booking; if additional Shipping Clerks needed, pivot to Murfreesboro, TN (≈35 mi) – still within bonus radius."
|
||
},
|
||
{
|
||
"after": "15:30",
|
||
"risk": "Potential double‑booking conflict for Jamal Ruiz",
|
||
"hint": "If the next shift is Packaging Operator in Nashville, assign a different local candidate—e.g., pull from Murfreesboro (45 mi) to stay within the bonus radius."
|
||
}
|
||
],
|
||
"created_at": "2026-04-21T03:12:02.023Z",
|
||
"file": "2026-05-05_Riverline_Logistics_—_Nashville_Downtown_Build-Out_1776741122023.json"
|
||
},
|
||
{
|
||
"date": "2026-04-25",
|
||
"client": "Riverline Logistics — Nashville Downtown Build-Out",
|
||
"cities": "Nashville",
|
||
"states": "TN",
|
||
"events_total": 5,
|
||
"events_ok": 5,
|
||
"checkpoint_count": 2,
|
||
"model": "gpt-oss:120b",
|
||
"cloud": true,
|
||
"lesson": "When filling several roles in the same city, always cross‑check each candidate’s schedule before confirming a fill and lock the worker ID after every batch (e.g., after the 09:00 baseline fill) to prevent double‑booking. Keep a standby list of qualified alternates (such as Alex Patel for Packaging Operator) within the 75‑mi bonus radius ready to swap in instantly if a conflict arises. If a local conflict can’t be resolved, pre‑identify the nearest fallback city—Murfreesboro, TN—and have its pool size on hand so you can pivot without delay.",
|
||
"checkpoints": [
|
||
{
|
||
"after": "09:00",
|
||
"risk": "Potential double‑booking of staff",
|
||
"hint": "Before assigning next role (e.g., Assembly Tech in Nashville), confirm worker availability; if conflict, pivot to Murfreesboro, TN (≈45 mi) for comparable talent within bonus radius."
|
||
},
|
||
{
|
||
"after": "15:30",
|
||
"risk": "Potential double-booking conflict for Jamal Ruiz",
|
||
"hint": "For next Packaging Operator shift in Nashville, assign a different qualified worker (e.g., use Alex Patel) or pivot to Murfreesboro, TN (≈35 mi) to stay within bonus radius."
|
||
}
|
||
],
|
||
"created_at": "2026-04-21T03:25:17.568Z",
|
||
"file": "2026-04-25_Riverline_Logistics_—_Nashville_Downtown_Build-Out_1776741917568.json"
|
||
},
|
||
{
|
||
"date": "2026-04-22",
|
||
"client": "Riverline Logistics — Nashville Downtown Build-Out",
|
||
"cities": "Nashville",
|
||
"states": "TN",
|
||
"events_total": 5,
|
||
"events_ok": 4,
|
||
"checkpoint_count": 2,
|
||
"model": "gpt-oss:120b",
|
||
"cloud": true,
|
||
"lesson": "Before assigning any worker, cross‑check the current schedule for that individual to prevent double‑booking; for Riverline Logistics, pull Shipping Clerk candidates from Murfreesboro (≈45 mi) first, since the local bonus applies and it avoids overlapping Brenda Hernandez and Rachel Gonzalez. After each fill, run a lightweight JSON schema validator on the executor’s response to catch missing braces or unquoted strings before the system records the placement. If validation fails, abort the fill, log the error, and retry with a corrected payload rather than proceeding to the next event. This two‑step pre‑check eliminates both the double‑booking risk and the recurring JSON‑format error.",
|
||
"checkpoints": [
|
||
{
|
||
"after": "09:00",
|
||
"risk": "Double-booking risk for assigned workers",
|
||
"hint": "Pivot to Shipping Clerk candidates from Murfreesboro, TN (≈45 mi) to stay within bonus radius and avoid double‑booking Brenda Hernandez and Rachel Gonzalez."
|
||
},
|
||
{
|
||
"after": "15:30",
|
||
"risk": "JSON formatting error in executor response",
|
||
"hint": "Validate executor output before sending: ensure JSON object ends with a closing brace and all strings are quoted correctly for Packaging Operator in Nashville, TN."
|
||
}
|
||
],
|
||
"created_at": "2026-04-21T03:17:58.449Z",
|
||
"file": "2026-04-22_Riverline_Logistics_—_Nashville_Downtown_Build-Out_1776741478449.json"
|
||
}
|
||
] |