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
2026-05-02 22:22:10 -05:00
co-authored by Claude Opus 4.7
parent 6e34ef7baf
commit 41b0a99ed2
788 changed files with 107142 additions and 0 deletions
@@ -0,0 +1 @@
{"after_event":"10:00","event_kind":"expansion","ok":true,"model":"gpt-oss:20b","duration_secs":21.86,"risk":"Double booking of scheduled workers","hint":"Verify each worker's schedule before assigning to 15:00; handle artifact errors by ensuring f.reason exists."}
@@ -0,0 +1,2 @@
{"at":"15:00","kind":"baseline_fill","operation":"fill: Shipping Clerk x1 in Chicago, IL","fills":[{"candidate_id":"W500K-47824","name":"Kyle K. Lee"}],"turns":3,"duration_secs":21.681,"pool_size":610,"playbook_citations":[],"discovered_pattern":"Across 25 similar past playbooks (27 workers examined) · recurring certifications: OSHA-10 (48%) · archetype mostly: communicator · reliability median 0.80 (range 0.59–1.00)"}
{"at":"10:00","kind":"expansion","operation":"fill: Warehouse Associate x2 in Chicago, IL","fills":[{"candidate_id":"W500K-46109","name":"Terrence L. Hernandez"},{"candidate_id":"W500K-15079","name":"Samuel Z. Allen"}],"turns":2,"duration_secs":11.175,"pool_size":479,"playbook_citations":[],"discovered_pattern":"Across 25 similar past playbooks (28 workers examined) · recurring certifications: OSHA-10 (50%) · archetype mostly: communicator · reliability median 0.80 (range 0.59–1.00)"}
@@ -0,0 +1 @@
# Client emails — Northland Logistics, 2026-05-01
@@ -0,0 +1,6 @@
# Cross-day lesson — Northland Logistics, 2026-05-01
_Generated by `gpt-oss:20b` in 5.4s. Based on 2 events + 1 mid-day checkpoints._
**
Before assigning the 15:00 baseline_fill, pre‑fetch the list of workers already allocated at 10:00 and cross‑check each candidate’s schedule to avoid double booking. Verify that every worker’s artifact includes a valid `f.reason` before finalizing the assignment. This ensures overlapping shifts are caught early and reduces rework.
@@ -0,0 +1,44 @@
[
{
"date": "2026-04-24",
"client": "Pioneer Assembly",
"cities": "Chicago",
"states": "IL",
"events_total": 1,
"events_ok": 0,
"checkpoint_count": 1,
"model": "gpt-oss:20b",
"cloud": false,
"lesson": "** \nBefore initiating a baseline_fill for a new shift, run a quick tool‑accuracy audit and confirm all clerks have completed the latest training module. Allocate a sufficient pool of clerks and schedule a buffer shift load to avoid gaps; if the pool is empty, the baseline will fail immediately. After the fill, monitor for drift by comparing current performance metrics to the baseline and adjust shift assignments or retrain as needed. This proactive check prevents the “Receiving Clerk Chicago drift risk” and ensures a smooth start to the day.",
"checkpoints": [
{
"after": "14:00",
"risk": "Receiving Clerk Chicago drift risk",
"hint": "Verify tool accuracy, retrain clerks, adjust shift load, and monitor drift in next shift."
}
],
"created_at": "2026-04-21T01:45:42.165Z",
"file": "2026-04-24_Pioneer_Assembly_1776735942165.json"
},
{
"date": "2026-04-22",
"client": "Parallel Machining",
"cities": "Joliet",
"states": "IL",
"events_total": 2,
"events_ok": 1,
"checkpoint_count": 1,
"model": "gpt-oss:20b",
"cloud": false,
"lesson": "** \nBefore any recurring Packer run in Joliet, verify tool calibration and review recent drift logs; if drift risk is detected, postpone the run until recalibration and refresher training are completed. Pre‑fetch updated pool data to avoid missing values that could cause failures. Log the calibration status and training completion in the system to trigger automatic risk alerts. If a run fails, immediately flag the drift risk and schedule corrective action before the next cycle.",
"checkpoints": [
{
"after": "09:30",
"risk": "Joliet Packer drift risk",
"hint": "Recalibrate tools, review drift logs, and schedule refresher training for Packer in Joliet."
}
],
"created_at": "2026-04-21T01:43:31.053Z",
"file": "2026-04-22_Parallel_Machining_1776735811053.json"
}
]
@@ -0,0 +1,59 @@
# Scenario retrospective — Northland Logistics, 2026-05-01
Executor: `qwen3.5:latest` Reviewer: `qwen3:latest` Draft: `qwen2.5:latest` Overview(T3): `gpt-oss:20b`
Prior lessons loaded into executor context: **2** (from 2026-04-24, 2026-04-22)
## Events
| At | Kind | Role / Count | Pool | Fills | Turns | Dur(s) | Cites | Gaps |
|---|---|---|---|---|---|---|---|---|
| 15:00 | baseline_fill | Shipping Clerk × 1 | 610 | ✓ 1 | 3 | 21.7 | 0 | 1 |
| 10:00 | expansion | Warehouse Associate × 2 | 479 | ✓ 2 | 2 | 11.2 | 0 | 3 |
## Final roster
| Worker | Booked | Role | City, ST | Status |
|---|---|---|---|---|
| undefined Kyle K. Lee | 15:00 | Shipping Clerk | Chicago, IL | confirmed |
| undefined Terrence L. Hernandez | 10:00 | Warehouse Associate | Chicago, IL | confirmed |
| undefined Samuel Z. Allen | 10:00 | Warehouse Associate | Chicago, IL | confirmed |
## Gap signals
### artifact
- **15:00** — undefined is not an object (evaluating 'f.reason.slice')
- **10:00** — undefined is not an object (evaluating 'f.reason.slice')
### double_book
- **10:00** — undefined Terrence L. Hernandez already booked for 15:00
- **10:00** — undefined Samuel Z. Allen already booked for 15:00
### fairness
- _cross-event_ — Kyle K. Lee (undefined) booked 3 times today
### write_through_audit
- _post-run_ — playbook_memory has 1541 entries (ran 2 events, expected ≥ 2 new entries from this run)
## Workers touched across the week
3 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 |
|---|---|---|---|
| 47824 | Kyle K. Lee | 15:00 baseline_fill | booked |
| W500K-46109 | Terrence L. Hernandez | 10:00 expansion | booked |
| W500K-15079 | Samuel Z. Allen | 10:00 expansion | booked |
## Discovered patterns (meta-index)
What the system identified across semantically-similar past fills as each event ran:
- **15:00 baseline_fill** (Shipping Clerk): Across 25 similar past playbooks (27 workers examined) · recurring certifications: OSHA-10 (48%) · archetype mostly: communicator · reliability median 0.80 (range 0.59–1.00)
- **10:00 expansion** (Warehouse Associate): Across 25 similar past playbooks (28 workers examined) · recurring certifications: OSHA-10 (50%) · archetype mostly: communicator · reliability median 0.80 (range 0.59–1.00)
## Narrative
- 2/2 events reached consensus.
- Final roster: 3 bookings across 1 distinct workers.
- Workers touched (booked, failed, or otherwise decided): 3.
- Playbook citations across the day: 0 (proof the feedback loop fired across events).
@@ -0,0 +1,64 @@
[
{
"event": {
"kind": "baseline_fill",
"at": "15:00",
"role": "Shipping Clerk",
"count": 1,
"city": "Chicago",
"state": "IL",
"shift_start": "15:00 AM"
},
"ok": true,
"fills": [
{
"candidate_id": "47824",
"name": "Kyle K. Lee"
}
],
"turns": 3,
"duration_secs": 21.681,
"gap_signals": [
"artifact: undefined is not an object (evaluating 'f.reason.slice')"
],
"sources_first_score": 0.5990598,
"sources_last_score": 0.50957674,
"pool_size": 610,
"playbook_citations": [],
"discovered_pattern": "Across 25 similar past playbooks (27 workers examined) · recurring certifications: OSHA-10 (48%) · archetype mostly: communicator · reliability median 0.80 (range 0.59–1.00)"
},
{
"event": {
"kind": "expansion",
"at": "10:00",
"role": "Warehouse Associate",
"count": 2,
"city": "Chicago",
"state": "IL",
"shift_start": "10:00 AM"
},
"ok": true,
"fills": [
{
"candidate_id": "W500K-46109",
"name": "Terrence L. Hernandez"
},
{
"candidate_id": "W500K-15079",
"name": "Samuel Z. Allen"
}
],
"turns": 2,
"duration_secs": 11.175,
"gap_signals": [
"double_book: undefined Terrence L. Hernandez already booked for 15:00",
"double_book: undefined Samuel Z. Allen already booked for 15:00",
"artifact: undefined is not an object (evaluating 'f.reason.slice')"
],
"sources_first_score": 0.6175976,
"sources_last_score": 0.51133966,
"pool_size": 479,
"playbook_citations": [],
"discovered_pattern": "Across 25 similar past playbooks (28 workers examined) · recurring certifications: OSHA-10 (50%) · archetype mostly: communicator · reliability median 0.80 (range 0.59–1.00)"
}
]
@@ -0,0 +1,26 @@
[
{
"name": "Kyle K. Lee",
"booked_for": "15:00",
"role": "Shipping Clerk",
"city": "Chicago",
"state": "IL",
"status": "confirmed"
},
{
"name": "Terrence L. Hernandez",
"booked_for": "10:00",
"role": "Warehouse Associate",
"city": "Chicago",
"state": "IL",
"status": "confirmed"
},
{
"name": "Samuel Z. Allen",
"booked_for": "10:00",
"role": "Warehouse Associate",
"city": "Chicago",
"state": "IL",
"status": "confirmed"
}
]
@@ -0,0 +1 @@
# SMS drafts — Northland Logistics, 2026-05-01