root 41b0a99ed2 chore: add real content that was sitting untracked
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>
2026-05-02 22:22:10 -05:00

80 lines
4.9 KiB
JSON
Raw Permalink Blame History

This file contains invisible Unicode characters

This file contains invisible Unicode characters that are indistinguishable to humans but may be processed differently by a computer. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

[
{
"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. Preselect a backup pool from the nearest alternate city (e.g., Murfreesboro,TN) that stays within the 75mi bonus radius and reserve those candidates for emergency or misplacement fills. Before confirming any fill, run a quick crosscheck against the map to catch potential doublebookings, especially for workers who appear in consecutive requests. If a doublebooking is detected, substitute the reserved Murfreesboro candidate to preserve the schedule and bonus eligibility.",
"checkpoints": [
{
"after": "09:00",
"risk": "doublebooked staff",
"hint": "Check worker assignments to avoid doublebooking; if additional Shipping Clerks needed, pivot to Murfreesboro, TN (≈35mi) still within bonus radius."
},
{
"after": "15:30",
"risk": "Potential doublebooking conflict for Jamal Ruiz",
"hint": "If the next shift is Packaging Operator in Nashville, assign a different local candidate—e.g., pull from Murfreesboro (45mi) 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": "2026-05-01",
"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 target the same city, the pools “turns” metric can mask imminent doublebooking; always crossreference each candidates current assignment before confirming a new fill. Preload a secondary candidate list from the nearest bonuseligible city (e.g., Murfreesboro,TN35mi) for every role that has already been placed twice in Nashville. If a worker appears in the “cites” count for a role more than once, automatically switch that fill to the Murfreesboro list to preserve the local $4/hr bonus and avoid conflicts. Finally, log each assignments turn number and gap count in a shared spreadsheet so the next shift can spot repeat usage at a glance.",
"checkpoints": [
{
"after": "09:00",
"risk": "double-booking workers",
"hint": "Pivot next role to Murfreesboro, TN (35mi) to stay within bonus radius and avoid reusing Brenda Hernandez or Rachel Gonzalez."
},
{
"after": "15:30",
"risk": "Potential doublebooking conflict for Jamal Ruiz",
"hint": "Use alternative Packaging Operator from Murfreesboro, TN (≈35mi) to avoid doublebooking Jamal Ruiz."
}
],
"created_at": "2026-04-21T03:40:05.328Z",
"file": "2026-05-01_Riverline_Logistics_—_Nashville_Downtown_Build-Out_1776742805328.json"
},
{
"date": "2026-04-28",
"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": "Before confirming any fill, crosscheck the schedule for each role and flag workers already booked for another shift; pull replacements from the nearest qualified city within the 75mi radius (e.g., Murfreesboro for Shipping Clerks and Packaging Operators) before finalizing the assignment. Maintain a live list of unassigned workers per role in adjacent cities and prioritize those when a doublebooking risk appears. If a worker is flagged as doublebooked (e.g., JamalRuiz), immediately replace them with a local alternate rather than reassigning the same individual. Finally, refresh the systems “available pool” cache after each fill to keep turn counts accurate and eliminate gaps.",
"checkpoints": [
{
"after": "09:00",
"risk": "Double-booking risk for scheduled workers",
"hint": "Select two unassigned Shipping Clerks from Murfreesboro, TN (≈35mi) for the next shift to avoid doublebooking the Nashville staff."
},
{
"after": "15:30",
"risk": "Double-booked worker Jamal Ruiz causing conflict",
"hint": "Pivot to a Packaging Operator from Murfreesboro, TN (≈45mi) within bonus radius, avoid doublebooking Jamal Ruiz."
}
],
"created_at": "2026-04-21T03:32:44.857Z",
"file": "2026-04-28_Riverline_Logistics_—_Nashville_Downtown_Build-Out_1776742364857.json"
}
]