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>
This commit is contained in:
root
@@ -0,0 +1 @@
|
||||
{"after_event":"14:00","event_kind":"baseline_fill","ok":true,"model":"gpt-oss:20b","duration_secs":15.661,"risk":"Potential JS error in baseline_fill","hint":"Validate f.reason exists for Quality Tech Toledo before calling slice; add null guard to prevent JS error."}
|
||||
@@ -0,0 +1 @@
|
||||
{"at":"14:00","kind":"baseline_fill","operation":"fill: Quality Tech x1 in Toledo, OH","fills":[{"candidate_id":"W500K-45337","name":"Carolyn T. Cox"}],"turns":3,"duration_secs":25.066,"pool_size":701,"playbook_citations":[],"discovered_pattern":"Across 25 similar past playbooks (14 workers examined) · recurring certifications: OSHA-10 (64%) · archetype mostly: flexible · reliability median 0.89 (range 0.59–1.00)"}
|
||||
@@ -0,0 +1 @@
|
||||
# Client emails — Horizon Supply, 2026-04-23
|
||||
@@ -0,0 +1,6 @@
|
||||
# Cross-day lesson — Horizon Supply, 2026-04-23
|
||||
|
||||
_Generated by `gpt-oss:20b` in 4.3s. Based on 1 events + 1 mid-day checkpoints._
|
||||
|
||||
**
|
||||
When executing a `baseline_fill`, always guard against missing `f.reason` before calling `slice`. Add a null check (e.g., `if (f.reason) { … }`) or pre‑fetch the field during data load. Log a warning and skip the slice if `f.reason` is undefined to avoid runtime JS errors and keep the pool count accurate.
|
||||
@@ -0,0 +1,75 @@
|
||||
[
|
||||
{
|
||||
"date": "2026-04-22",
|
||||
"client": "Centennial Packaging",
|
||||
"cities": "Cleveland",
|
||||
"states": "OH",
|
||||
"events_total": 3,
|
||||
"events_ok": 3,
|
||||
"checkpoint_count": 1,
|
||||
"model": "gpt-oss:20b",
|
||||
"cloud": false,
|
||||
"lesson": "** \nBefore running an expansion event, query the current pool for the role and subtract any workers already assigned in earlier shifts; if the remaining pool is less than the requested number, reallocate or reduce the expansion. Implement a pre‑check that flags potential double bookings and forces reassignment of at least one role. Validate all worker references to avoid undefined references in scheduling logic. This prevents overlapping assignments and ensures the pool count remains accurate.",
|
||||
"checkpoints": [
|
||||
{
|
||||
"after": "11:30",
|
||||
"risk": "Double booking risk for Assembler workers",
|
||||
"hint": "Reassign at least one of the five Assembler roles to avoid double booking with the 09:00 shift; review scheduling logic for undefined worker references."
|
||||
}
|
||||
],
|
||||
"created_at": "2026-04-21T01:35:16.915Z",
|
||||
"file": "2026-04-22_Centennial_Packaging_1776735316915.json"
|
||||
},
|
||||
{
|
||||
"date": "2026-04-21",
|
||||
"client": "Riverfront Steel",
|
||||
"cities": "Toledo",
|
||||
"states": "OH",
|
||||
"events_total": 5,
|
||||
"events_ok": 4,
|
||||
"checkpoint_count": 2,
|
||||
"model": "gpt-oss:20b",
|
||||
"cloud": false,
|
||||
"lesson": "** \nBefore launching an expansion, always verify the pool size and certification status for the role; if the pool is unknown or certifications are missing, pre‑fetch the data or secure temporary hires to avoid a fail. For any misplacement or recurring assignment, cross‑check the booking system to confirm that staff such as Patrick Ross are not double‑booked. Maintain a buffer of at least three extra candidates for emergency roles to keep gaps at a minimum. This proactive verification will reduce drift risk and scheduling conflicts in future runs.",
|
||||
"checkpoints": [
|
||||
{
|
||||
"after": "12:15",
|
||||
"risk": "Forklift Operator drift risk in Toledo",
|
||||
"hint": "Verify forklift operator certifications in Toledo; consider temporary hires if drift persists."
|
||||
},
|
||||
{
|
||||
"after": "15:45",
|
||||
"risk": "Double-booking risk for Patrick Ross",
|
||||
"hint": "Verify Patrick Ross’s schedule before assigning; use the booking system to prevent overlapping shifts."
|
||||
}
|
||||
],
|
||||
"created_at": "2026-04-21T01:13:14.575Z",
|
||||
"file": "2026-04-21_Riverfront_Steel_1776733994575.json"
|
||||
},
|
||||
{
|
||||
"date": "2026-04-21",
|
||||
"client": "Riverfront Steel",
|
||||
"cities": "Toledo",
|
||||
"states": "OH",
|
||||
"events_total": 5,
|
||||
"events_ok": 5,
|
||||
"checkpoint_count": 2,
|
||||
"model": "gpt-oss:20b",
|
||||
"cloud": false,
|
||||
"lesson": "** \nBefore assigning any expansion or emergency shift, pull the current availability of all required roles from the central schedule and lock those slots to prevent overlap. For high‑volume roles such as Forklift Operator, confirm no conflict with earlier baseline or recurring bookings. When a misplacement occurs, cross‑check the specific candidate’s calendar (e.g., Patrick Ross) to avoid double‑booking and validate artifact data before re‑assigning. Keep pool counts comfortably above the required number to buffer against last‑minute gaps.",
|
||||
"checkpoints": [
|
||||
{
|
||||
"after": "12:15",
|
||||
"risk": "Forklift Operator double booking risk",
|
||||
"hint": "Verify Toledo forklift operator availability before assigning new shift; avoid overlapping with 08:00 bookings."
|
||||
},
|
||||
{
|
||||
"after": "15:45",
|
||||
"risk": "Potential double-booking of Patrick Ross",
|
||||
"hint": "Check Patrick Ross schedule before assigning to avoid double-booking; verify artifact data integrity for new assignments."
|
||||
}
|
||||
],
|
||||
"created_at": "2026-04-21T01:30:53.606Z",
|
||||
"file": "2026-04-21_Riverfront_Steel_1776735053606.json"
|
||||
}
|
||||
]
|
||||
@@ -0,0 +1,45 @@
|
||||
# Scenario retrospective — Horizon Supply, 2026-04-23
|
||||
|
||||
Executor: `qwen3.5:latest` Reviewer: `qwen3:latest` Draft: `qwen2.5:latest` Overview(T3): `gpt-oss:20b`
|
||||
Prior lessons loaded into executor context: **3** (from 2026-04-22, 2026-04-21, 2026-04-21)
|
||||
|
||||
## Events
|
||||
|
||||
| At | Kind | Role / Count | Pool | Fills | Turns | Dur(s) | Cites | Gaps |
|
||||
|---|---|---|---|---|---|---|---|---|
|
||||
| 14:00 | baseline_fill | Quality Tech × 1 | 701 | ✓ 1 | 3 | 25.1 | 0 | 1 |
|
||||
|
||||
## Final roster
|
||||
|
||||
| Worker | Booked | Role | City, ST | Status |
|
||||
|---|---|---|---|---|
|
||||
| undefined Carolyn T. Cox | 14:00 | Quality Tech | Toledo, OH | confirmed |
|
||||
|
||||
## Gap signals
|
||||
|
||||
### artifact
|
||||
- **14:00** — undefined is not an object (evaluating 'f.reason.slice')
|
||||
|
||||
### write_through_audit
|
||||
- _post-run_ — playbook_memory has 1489 entries (ran 1 events, expected ≥ 1 new entries from this run)
|
||||
|
||||
## Workers touched across the week
|
||||
|
||||
1 distinct workers made it through to a decision. Every one is accounted for below — no-shows flagged, rebookings noted, everyone visible.
|
||||
|
||||
| Worker ID | Name | Events | Outcome |
|
||||
|---|---|---|---|
|
||||
| 45337 | Carolyn T. Cox | 14:00 baseline_fill | booked |
|
||||
|
||||
## Discovered patterns (meta-index)
|
||||
|
||||
What the system identified across semantically-similar past fills as each event ran:
|
||||
|
||||
- **14:00 baseline_fill** (Quality Tech): Across 25 similar past playbooks (14 workers examined) · recurring certifications: OSHA-10 (64%) · archetype mostly: flexible · reliability median 0.89 (range 0.59–1.00)
|
||||
|
||||
## Narrative
|
||||
|
||||
- 1/1 events reached consensus.
|
||||
- Final roster: 1 bookings across 1 distinct workers.
|
||||
- Workers touched (booked, failed, or otherwise decided): 1.
|
||||
- Playbook citations across the day: 0 (proof the feedback loop fired across events).
|
||||
@@ -0,0 +1,30 @@
|
||||
[
|
||||
{
|
||||
"event": {
|
||||
"kind": "baseline_fill",
|
||||
"at": "14:00",
|
||||
"role": "Quality Tech",
|
||||
"count": 1,
|
||||
"city": "Toledo",
|
||||
"state": "OH",
|
||||
"shift_start": "14:00 AM"
|
||||
},
|
||||
"ok": true,
|
||||
"fills": [
|
||||
{
|
||||
"candidate_id": "45337",
|
||||
"name": "Carolyn T. Cox"
|
||||
}
|
||||
],
|
||||
"turns": 3,
|
||||
"duration_secs": 25.066,
|
||||
"gap_signals": [
|
||||
"artifact: undefined is not an object (evaluating 'f.reason.slice')"
|
||||
],
|
||||
"sources_first_score": 0.7026848,
|
||||
"sources_last_score": 0.6469463,
|
||||
"pool_size": 701,
|
||||
"playbook_citations": [],
|
||||
"discovered_pattern": "Across 25 similar past playbooks (14 workers examined) · recurring certifications: OSHA-10 (64%) · archetype mostly: flexible · reliability median 0.89 (range 0.59–1.00)"
|
||||
}
|
||||
]
|
||||
@@ -0,0 +1,10 @@
|
||||
[
|
||||
{
|
||||
"name": "Carolyn T. Cox",
|
||||
"booked_for": "14:00",
|
||||
"role": "Quality Tech",
|
||||
"city": "Toledo",
|
||||
"state": "OH",
|
||||
"status": "confirmed"
|
||||
}
|
||||
]
|
||||
@@ -0,0 +1 @@
|
||||
# SMS drafts — Horizon Supply, 2026-04-23
|
||||
Reference in New Issue
Block a user