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
4.3 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": "Midway Distribution",
"cities": "Indianapolis",
"states": "IN",
"events_total": 4,
"events_ok": 3,
"checkpoint_count": 2,
"model": "gpt-oss:20b",
"cloud": false,
"lesson": "** \nBefore running an expansion, prefetch local Packer data (or fallback to the nearest city) and validate that the executor returns wellformed JSON; this prevents the “Missing local Packer data” failure. \nWhen an emergency request arrives, immediately crosscheck the 16:00 schedule to ensure no worker is assigned twice, and correct any artifact errors in the scheduling logic that could cause doublebooking. \nImplement automated checks that flag duplicate assignments and missing data before the agent commits to a fill.",
"checkpoints": [
{
"after": "10:30",
"risk": "Missing local Packer data",
"hint": "Add Indianapolis Packer records to the index or fallback to nearest city; verify executor returns valid JSON before execution."
},
{
"after": "12:00",
"risk": "16:00 double-booking risk",
"hint": "Verify no worker is assigned twice for 16:00; fix artifact error in scheduling logic."
}
],
"created_at": "2026-04-21T02:04:50.585Z",
"file": "2026-05-05_Midway_Distribution_1776737090585.json"
},
{
"date": "2026-04-29",
"client": "Northland Logistics",
"cities": "Indianapolis",
"states": "IN",
"events_total": 4,
"events_ok": 4,
"checkpoint_count": 2,
"model": "gpt-oss:20b",
"cloud": false,
"lesson": "** \nAfter an emergency or misplacement event, immediately revalidate all affected candidate schedules. Prefetch the availability of Sharon Hughes, Gregory T. Roberts, and Dorothy D. Robinson for the remaining slots before assigning them. Ensure the playbooks `f.reason` is defined and sliced correctly before any assignment to prevent doublebooking. This step eliminates the risk flagged in the checkpoints.",
"checkpoints": [
{
"after": "10:00",
"risk": "Double booking risk: Sharon, Gregory",
"hint": "Confirm Sharon Hughes and Gregory T. Roberts are not booked at 14:00, and review the f.reason.slice error in the playbook."
},
{
"after": "14:30",
"risk": "Dorothy D. Robinson double-book",
"hint": "Verify Dorothy D. Robinson's schedule, avoid double-booking, and confirm f.reason is defined before assignment."
}
],
"created_at": "2026-04-21T01:54:16.942Z",
"file": "2026-04-29_Northland_Logistics_1776736456942.json"
},
{
"date": "2026-04-24",
"client": "Pioneer Assembly — Indianapolis Plant Expansion",
"cities": "Indianapolis",
"states": "IN",
"events_total": 5,
"events_ok": 5,
"checkpoint_count": 2,
"model": "gpt-oss:120b",
"cloud": true,
"lesson": "Before scheduling any shift, generate a temporary roster that flags workers already assigned to earlier events that day and exclude them from subsequent fills. For Machine Operator and Assembler roles in Indianapolis, prepull the required headcount from the Muncie,IN pool (≈5055mi) to stay within the $5/hr localbonus radius and ensure fresh candidates. Keep a running list of used IDs (e.g., Christina Watson, Zachary Taylor) and crossreference it at each new fill to eliminate doublebooking. If the Indianapolis pool runs low, automatically switch to Muncie rather than reusing local staff.",
"checkpoints": [
{
"after": "11:00",
"risk": "Potential doublebooking of already scheduled workers",
"hint": "For the next role, pull Machine Operators from Muncie, IN (≈50mi) to stay within the bonus radius and avoid reusing Christina Watson, Amy S. Jenkins, Alexander R. Evans, Angela U. Ward, or Nathan N. Roberts."
},
{
"after": "16:00",
"risk": "Doublebooking risk for Zachary Taylor",
"hint": "For the next Assembler shift in Indianapolis, assign a different qualified worker or pivot to Muncie, IN (≈55mi) to stay within bonus radius and avoid doublebooking Zachary Taylor."
}
],
"created_at": "2026-04-21T03:22:46.841Z",
"file": "2026-04-24_Pioneer_Assembly_—_Indianapolis_Plant_Expansion_1776741766841.json"
}
]