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":9.461,"risk":"Receiving Clerk Chicago drift risk","hint":"Verify tool accuracy, retrain clerks, adjust shift load, and monitor drift in next shift."}
|
||||
@@ -0,0 +1 @@
|
||||
# Client emails — Pioneer Assembly, 2026-04-24
|
||||
@@ -0,0 +1,6 @@
|
||||
# Cross-day lesson — Pioneer Assembly, 2026-04-24
|
||||
|
||||
_Generated by `gpt-oss:20b` in 3.7s. Based on 1 events + 1 mid-day checkpoints._
|
||||
|
||||
**
|
||||
Before 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.
|
||||
@@ -0,0 +1,23 @@
|
||||
[
|
||||
{
|
||||
"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 +1,44 @@
|
||||
# Scenario retrospective — Pioneer Assembly, 2026-04-24
|
||||
|
||||
Executor: `qwen3.5:latest` Reviewer: `qwen3:latest` Draft: `qwen2.5:latest` Overview(T3): `gpt-oss:20b`
|
||||
Prior lessons loaded into executor context: **1** (from 2026-04-22)
|
||||
|
||||
## Events
|
||||
|
||||
| At | Kind | Role / Count | Pool | Fills | Turns | Dur(s) | Cites | Gaps |
|
||||
|---|---|---|---|---|---|---|---|---|
|
||||
| 14:00 | baseline_fill | Receiving Clerk × 3 | - | ✗ 0 | 0 | 26.7 | 0 | 1 |
|
||||
|
||||
## Final roster
|
||||
|
||||
| Worker | Booked | Role | City, ST | Status |
|
||||
|---|---|---|---|---|
|
||||
|
||||
## Gap signals
|
||||
|
||||
### drift_or_tool
|
||||
- **14:00** — aborted — 3 consecutive drift flags
|
||||
|
||||
### write_through_audit
|
||||
- _post-run_ — playbook_memory has 1529 entries (ran 1 events, expected ≥ 0 new entries from this run)
|
||||
|
||||
## Workers touched across the week
|
||||
|
||||
0 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 |
|
||||
|---|---|---|---|
|
||||
|
||||
## Discovered patterns (meta-index)
|
||||
|
||||
What the system identified across semantically-similar past fills as each event ran:
|
||||
|
||||
- **14:00 baseline_fill** (Receiving Clerk): —
|
||||
|
||||
## Narrative
|
||||
|
||||
- 0/1 events reached consensus.
|
||||
- Final roster: 0 bookings across 0 distinct workers.
|
||||
- Workers touched (booked, failed, or otherwise decided): 0.
|
||||
- Playbook citations across the day: 0 (proof the feedback loop fired across events).
|
||||
- Dropped events: 14:00 baseline_fill.
|
||||
@@ -0,0 +1,21 @@
|
||||
[
|
||||
{
|
||||
"event": {
|
||||
"kind": "baseline_fill",
|
||||
"at": "14:00",
|
||||
"role": "Receiving Clerk",
|
||||
"count": 3,
|
||||
"city": "Chicago",
|
||||
"state": "IL",
|
||||
"shift_start": "14:00 AM"
|
||||
},
|
||||
"ok": false,
|
||||
"fills": [],
|
||||
"turns": 0,
|
||||
"duration_secs": 26.722,
|
||||
"error": "aborted — 3 consecutive drift flags",
|
||||
"gap_signals": [
|
||||
"drift_or_tool: aborted — 3 consecutive drift flags"
|
||||
]
|
||||
}
|
||||
]
|
||||
@@ -0,0 +1 @@
|
||||
[]
|
||||
@@ -0,0 +1 @@
|
||||
# SMS drafts — Pioneer Assembly, 2026-04-24
|
||||
Reference in New Issue
Block a user