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 +1,2 @@
|
||||
{"after_event":"10:30","event_kind":"expansion","ok":true,"model":"gpt-oss:20b","duration_secs":11.218,"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_event":"12:00","event_kind":"emergency","ok":true,"model":"gpt-oss:20b","duration_secs":13.125,"risk":"16:00 double-booking risk","hint":"Verify no worker is assigned twice for 16:00; fix artifact error in scheduling logic."}
|
||||
@@ -0,0 +1,3 @@
|
||||
{"at":"16:00","kind":"baseline_fill","operation":"fill: Assembler x2 in Indianapolis, IN","fills":[{"candidate_id":"W500K-12207","name":"Zachary Taylor"},{"candidate_id":"W500K-49897","name":"Adam D. Watson"}],"turns":3,"duration_secs":26.043,"pool_size":838,"playbook_citations":[],"discovered_pattern":"Across 25 similar past playbooks (25 workers examined) · recurring certifications: OSHA-10 (48%) · archetype mostly: communicator · reliability median 0.80 (range 0.59–1.00)"}
|
||||
{"at":"17:30","kind":"recurring","operation":"fill: Loader x2 in Indianapolis, IN","fills":[{"candidate_id":"W500K-25481","name":"Sharon B. Torres"},{"candidate_id":"W500K-10744","name":"Kimberly Murphy"}],"turns":2,"duration_secs":11.844,"pool_size":620,"playbook_citations":[],"discovered_pattern":"Across 25 similar past playbooks (25 workers examined) · recurring certifications: OSHA-10 (48%) · archetype mostly: communicator · reliability median 0.80 (range 0.59–1.00)"}
|
||||
{"at":"12:00","kind":"emergency","operation":"fill: Loader x4 in Indianapolis, IN","fills":[{"candidate_id":"W500K-11321","name":"Sandra Gray"},{"candidate_id":"W500K-7233","name":"Mark Lopez"},{"candidate_id":"W500K-23191","name":"Helen Z. Cooper"},{"candidate_id":"W500K-26233","name":"Ryan Z. Torres"}],"turns":4,"duration_secs":35.022,"pool_size":431,"playbook_citations":[],"discovered_pattern":"Across 25 similar past playbooks (27 workers examined) · recurring certifications: OSHA-10 (52%) · recurring skills: overhead crane (41%) · archetype mostly: communicator · reliability median 0.80 (range 0.19–1.00)"}
|
||||
@@ -0,0 +1 @@
|
||||
# Client emails — Midway Distribution, 2026-05-05
|
||||
@@ -0,0 +1,8 @@
|
||||
# Cross-day lesson — Midway Distribution, 2026-05-05
|
||||
|
||||
_Generated by `gpt-oss:20b` in 4.5s. Based on 4 events + 2 mid-day checkpoints._
|
||||
|
||||
**
|
||||
Before running an expansion, pre‑fetch local Packer data (or fallback to the nearest city) and validate that the executor returns well‑formed JSON; this prevents the “Missing local Packer data” failure.
|
||||
When an emergency request arrives, immediately cross‑check the 16:00 schedule to ensure no worker is assigned twice, and correct any artifact errors in the scheduling logic that could cause double‑booking.
|
||||
Implement automated checks that flag duplicate assignments and missing data before the agent commits to a fill.
|
||||
@@ -0,0 +1,54 @@
|
||||
[
|
||||
{
|
||||
"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 re‑validate all affected candidate schedules. Pre‑fetch the availability of Sharon Hughes, Gregory T. Roberts, and Dorothy D. Robinson for the remaining slots before assigning them. Ensure the playbook’s `f.reason` is defined and sliced correctly before any assignment to prevent double‑booking. 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": "2026-04-21",
|
||||
"client": "Heritage Foods",
|
||||
"cities": "Indianapolis",
|
||||
"states": "IN",
|
||||
"events_total": 5,
|
||||
"events_ok": 3,
|
||||
"checkpoint_count": 2,
|
||||
"model": "gpt-oss:20b",
|
||||
"cloud": false,
|
||||
"lesson": "** \nBefore starting any expansion or recurring fill, verify the candidate pool size and skill availability; if the pool is unknown or insufficient, postpone the run. For Packer roles, perform a quick tool calibration check and confirm drift thresholds to avoid drift risk. Always cross‑check each candidate’s calendar—especially high‑volume staff like Susan X. Ruiz—to prevent double bookings. Update the booking system to flag conflicts automatically. These steps will reduce failures and keep the schedule on track.",
|
||||
"checkpoints": [
|
||||
{
|
||||
"after": "09:30",
|
||||
"risk": "Packer drift risk in Indianapolis",
|
||||
"hint": "Verify tool calibration and drift thresholds before next Packer expansion in Indianapolis."
|
||||
},
|
||||
{
|
||||
"after": "12:00",
|
||||
"risk": "Susan X. Ruiz double-booked",
|
||||
"hint": "Verify Susan X. Ruiz’s schedule before assigning; ensure no overlapping shifts; update booking system to flag conflicts."
|
||||
}
|
||||
],
|
||||
"created_at": "2026-04-21T01:33:53.135Z",
|
||||
"file": "2026-04-21_Heritage_Foods_1776735233135.json"
|
||||
}
|
||||
]
|
||||
@@ -0,0 +1,83 @@
|
||||
# Scenario retrospective — Midway Distribution, 2026-05-05
|
||||
|
||||
Executor: `qwen3.5:latest` Reviewer: `qwen3:latest` Draft: `qwen2.5:latest` Overview(T3): `gpt-oss:20b`
|
||||
Prior lessons loaded into executor context: **2** (from 2026-04-29, 2026-04-21)
|
||||
|
||||
## Events
|
||||
|
||||
| At | Kind | Role / Count | Pool | Fills | Turns | Dur(s) | Cites | Gaps |
|
||||
|---|---|---|---|---|---|---|---|---|
|
||||
| 16:00 | baseline_fill | Assembler × 2 | 838 | ✓ 2 | 3 | 26.0 | 0 | 2 |
|
||||
| 17:30 | recurring | Loader × 2 | 620 | ✓ 2 | 2 | 11.8 | 0 | 3 |
|
||||
| 10:30 | expansion | Packer × 5 | - | ✗ 0 | 0 | 37.9 | 0 | 1 |
|
||||
| 12:00 | emergency | Loader × 4 | 431 | ✓ 4 | 4 | 35.0 | 0 | 5 |
|
||||
|
||||
## Final roster
|
||||
|
||||
| Worker | Booked | Role | City, ST | Status |
|
||||
|---|---|---|---|---|
|
||||
| undefined Zachary Taylor | 16:00 | Assembler | Indianapolis, IN | confirmed |
|
||||
| undefined Adam D. Watson | 16:00 | Assembler | Indianapolis, IN | confirmed |
|
||||
| undefined Sharon B. Torres | 17:30 | Loader | Indianapolis, IN | confirmed |
|
||||
| undefined Kimberly Murphy | 17:30 | Loader | Indianapolis, IN | confirmed |
|
||||
| undefined Sandra Gray | 12:00 | Loader | Indianapolis, IN | confirmed |
|
||||
| undefined Mark Lopez | 12:00 | Loader | Indianapolis, IN | confirmed |
|
||||
| undefined Helen Z. Cooper | 12:00 | Loader | Indianapolis, IN | confirmed |
|
||||
| undefined Ryan Z. Torres | 12:00 | Loader | Indianapolis, IN | confirmed |
|
||||
|
||||
## Gap signals
|
||||
|
||||
### double_book
|
||||
- **16:00** — undefined Adam D. Watson already booked for 16:00
|
||||
- **17:30** — undefined Sharon B. Torres already booked for 16:00
|
||||
- **17:30** — undefined Kimberly Murphy already booked for 16:00
|
||||
- **12:00** — undefined Sandra Gray already booked for 16:00
|
||||
- **12:00** — undefined Mark Lopez already booked for 16:00
|
||||
- **12:00** — undefined Helen Z. Cooper already booked for 16:00
|
||||
- **12:00** — undefined Ryan Z. Torres already booked for 16:00
|
||||
|
||||
### artifact
|
||||
- **16:00** — undefined is not an object (evaluating 'f.reason.slice')
|
||||
- **17:30** — undefined is not an object (evaluating 'f.reason.slice')
|
||||
- **12:00** — undefined is not an object (evaluating 'f.reason.slice')
|
||||
|
||||
### drift_or_tool
|
||||
- **10:30** — invalid JSON from executor: JSON Parse error: Unable to parse JSON string | raw: {"kind":"plan","steps":["Analyze prior search results: The hybrid_search tool returned 0 SQL matches for 'Indianapolis, IN' despite the filter, indicating the vector reranker is returning irrelevant candidates (Memphis, MO, etc.) because no local Packer data exists in the index.","Action: Execute a
|
||||
|
||||
### fairness
|
||||
- _cross-event_ — Zachary Taylor (undefined) booked 8 times today
|
||||
|
||||
### write_through_audit
|
||||
- _post-run_ — playbook_memory has 1547 entries (ran 4 events, expected ≥ 3 new entries from this run)
|
||||
|
||||
## Workers touched across the week
|
||||
|
||||
8 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 |
|
||||
|---|---|---|---|
|
||||
| 12207 | Zachary Taylor | 16:00 baseline_fill | booked |
|
||||
| 49897 | Adam D. Watson | 16:00 baseline_fill | booked |
|
||||
| W500K-25481 | Sharon B. Torres | 17:30 recurring | booked |
|
||||
| W500K-10744 | Kimberly Murphy | 17:30 recurring | booked |
|
||||
| W500K-11321 | Sandra Gray | 12:00 emergency | booked |
|
||||
| W500K-7233 | Mark Lopez | 12:00 emergency | booked |
|
||||
| W500K-23191 | Helen Z. Cooper | 12:00 emergency | booked |
|
||||
| W500K-26233 | Ryan Z. Torres | 12:00 emergency | booked |
|
||||
|
||||
## Discovered patterns (meta-index)
|
||||
|
||||
What the system identified across semantically-similar past fills as each event ran:
|
||||
|
||||
- **16:00 baseline_fill** (Assembler): Across 25 similar past playbooks (25 workers examined) · recurring certifications: OSHA-10 (48%) · archetype mostly: communicator · reliability median 0.80 (range 0.59–1.00)
|
||||
- **17:30 recurring** (Loader): Across 25 similar past playbooks (25 workers examined) · recurring certifications: OSHA-10 (48%) · archetype mostly: communicator · reliability median 0.80 (range 0.59–1.00)
|
||||
- **10:30 expansion** (Packer): —
|
||||
- **12:00 emergency** (Loader): Across 25 similar past playbooks (27 workers examined) · recurring certifications: OSHA-10 (52%) · recurring skills: overhead crane (41%) · archetype mostly: communicator · reliability median 0.80 (range 0.19–1.00)
|
||||
|
||||
## Narrative
|
||||
|
||||
- 3/4 events reached consensus.
|
||||
- Final roster: 8 bookings across 1 distinct workers.
|
||||
- Workers touched (booked, failed, or otherwise decided): 8.
|
||||
- Playbook citations across the day: 0 (proof the feedback loop fired across events).
|
||||
- Dropped events: 10:30 expansion.
|
||||
@@ -0,0 +1,132 @@
|
||||
[
|
||||
{
|
||||
"event": {
|
||||
"kind": "baseline_fill",
|
||||
"at": "16:00",
|
||||
"role": "Assembler",
|
||||
"count": 2,
|
||||
"city": "Indianapolis",
|
||||
"state": "IN",
|
||||
"shift_start": "16:00 AM"
|
||||
},
|
||||
"ok": true,
|
||||
"fills": [
|
||||
{
|
||||
"candidate_id": "12207",
|
||||
"name": "Zachary Taylor"
|
||||
},
|
||||
{
|
||||
"candidate_id": "49897",
|
||||
"name": "Adam D. Watson"
|
||||
}
|
||||
],
|
||||
"turns": 3,
|
||||
"duration_secs": 26.043,
|
||||
"gap_signals": [
|
||||
"double_book: undefined Adam D. Watson already booked for 16:00",
|
||||
"artifact: undefined is not an object (evaluating 'f.reason.slice')"
|
||||
],
|
||||
"sources_first_score": 0.63550305,
|
||||
"sources_last_score": 0.57368654,
|
||||
"pool_size": 838,
|
||||
"playbook_citations": [],
|
||||
"discovered_pattern": "Across 25 similar past playbooks (25 workers examined) · recurring certifications: OSHA-10 (48%) · archetype mostly: communicator · reliability median 0.80 (range 0.59–1.00)"
|
||||
},
|
||||
{
|
||||
"event": {
|
||||
"kind": "recurring",
|
||||
"at": "17:30",
|
||||
"role": "Loader",
|
||||
"count": 2,
|
||||
"city": "Indianapolis",
|
||||
"state": "IN",
|
||||
"shift_start": "17:30 AM"
|
||||
},
|
||||
"ok": true,
|
||||
"fills": [
|
||||
{
|
||||
"candidate_id": "W500K-25481",
|
||||
"name": "Sharon B. Torres"
|
||||
},
|
||||
{
|
||||
"candidate_id": "W500K-10744",
|
||||
"name": "Kimberly Murphy"
|
||||
}
|
||||
],
|
||||
"turns": 2,
|
||||
"duration_secs": 11.844,
|
||||
"gap_signals": [
|
||||
"double_book: undefined Sharon B. Torres already booked for 16:00",
|
||||
"double_book: undefined Kimberly Murphy already booked for 16:00",
|
||||
"artifact: undefined is not an object (evaluating 'f.reason.slice')"
|
||||
],
|
||||
"sources_first_score": 0.76272166,
|
||||
"sources_last_score": 0.5714574,
|
||||
"pool_size": 620,
|
||||
"playbook_citations": [],
|
||||
"discovered_pattern": "Across 25 similar past playbooks (25 workers examined) · recurring certifications: OSHA-10 (48%) · archetype mostly: communicator · reliability median 0.80 (range 0.59–1.00)"
|
||||
},
|
||||
{
|
||||
"event": {
|
||||
"kind": "expansion",
|
||||
"at": "10:30",
|
||||
"role": "Packer",
|
||||
"count": 5,
|
||||
"city": "Indianapolis",
|
||||
"state": "IN",
|
||||
"shift_start": "10:30 AM"
|
||||
},
|
||||
"ok": false,
|
||||
"fills": [],
|
||||
"turns": 0,
|
||||
"duration_secs": 37.89,
|
||||
"error": "invalid JSON from executor: JSON Parse error: Unable to parse JSON string | raw: {\"kind\":\"plan\",\"steps\":[\"Analyze prior search results: The hybrid_search tool returned 0 SQL matches for 'Indianapolis, IN' despite the filter, indicating the vector reranker is returning irrelevant candidates (Memphis, MO, etc.) because no local Packer data exists in the index.\",\"Action: Execute a ",
|
||||
"gap_signals": [
|
||||
"drift_or_tool: invalid JSON from executor: JSON Parse error: Unable to parse JSON string | raw: {\"kind\":\"plan\",\"steps\":[\"Analyze prior search results: The hybrid_search tool returned 0 SQL matches for 'Indianapolis, IN' despite the filter, indicating the vector reranker is returning irrelevant candidates (Memphis, MO, etc.) because no local Packer data exists in the index.\",\"Action: Execute a "
|
||||
]
|
||||
},
|
||||
{
|
||||
"event": {
|
||||
"kind": "emergency",
|
||||
"at": "12:00",
|
||||
"role": "Loader",
|
||||
"count": 4,
|
||||
"city": "Indianapolis",
|
||||
"state": "IN",
|
||||
"shift_start": "12:00 AM"
|
||||
},
|
||||
"ok": true,
|
||||
"fills": [
|
||||
{
|
||||
"candidate_id": "W500K-11321",
|
||||
"name": "Sandra Gray"
|
||||
},
|
||||
{
|
||||
"candidate_id": "W500K-7233",
|
||||
"name": "Mark Lopez"
|
||||
},
|
||||
{
|
||||
"candidate_id": "W500K-23191",
|
||||
"name": "Helen Z. Cooper"
|
||||
},
|
||||
{
|
||||
"candidate_id": "W500K-26233",
|
||||
"name": "Ryan Z. Torres"
|
||||
}
|
||||
],
|
||||
"turns": 4,
|
||||
"duration_secs": 35.022,
|
||||
"gap_signals": [
|
||||
"double_book: undefined Sandra Gray already booked for 16:00",
|
||||
"double_book: undefined Mark Lopez already booked for 16:00",
|
||||
"double_book: undefined Helen Z. Cooper already booked for 16:00",
|
||||
"double_book: undefined Ryan Z. Torres already booked for 16:00",
|
||||
"artifact: undefined is not an object (evaluating 'f.reason.slice')"
|
||||
],
|
||||
"sources_first_score": 0.61423594,
|
||||
"sources_last_score": 0.5118008,
|
||||
"pool_size": 431,
|
||||
"playbook_citations": [],
|
||||
"discovered_pattern": "Across 25 similar past playbooks (27 workers examined) · recurring certifications: OSHA-10 (52%) · recurring skills: overhead crane (41%) · archetype mostly: communicator · reliability median 0.80 (range 0.19–1.00)"
|
||||
}
|
||||
]
|
||||
@@ -0,0 +1,66 @@
|
||||
[
|
||||
{
|
||||
"name": "Zachary Taylor",
|
||||
"booked_for": "16:00",
|
||||
"role": "Assembler",
|
||||
"city": "Indianapolis",
|
||||
"state": "IN",
|
||||
"status": "confirmed"
|
||||
},
|
||||
{
|
||||
"name": "Adam D. Watson",
|
||||
"booked_for": "16:00",
|
||||
"role": "Assembler",
|
||||
"city": "Indianapolis",
|
||||
"state": "IN",
|
||||
"status": "confirmed"
|
||||
},
|
||||
{
|
||||
"name": "Sharon B. Torres",
|
||||
"booked_for": "17:30",
|
||||
"role": "Loader",
|
||||
"city": "Indianapolis",
|
||||
"state": "IN",
|
||||
"status": "confirmed"
|
||||
},
|
||||
{
|
||||
"name": "Kimberly Murphy",
|
||||
"booked_for": "17:30",
|
||||
"role": "Loader",
|
||||
"city": "Indianapolis",
|
||||
"state": "IN",
|
||||
"status": "confirmed"
|
||||
},
|
||||
{
|
||||
"name": "Sandra Gray",
|
||||
"booked_for": "12:00",
|
||||
"role": "Loader",
|
||||
"city": "Indianapolis",
|
||||
"state": "IN",
|
||||
"status": "confirmed"
|
||||
},
|
||||
{
|
||||
"name": "Mark Lopez",
|
||||
"booked_for": "12:00",
|
||||
"role": "Loader",
|
||||
"city": "Indianapolis",
|
||||
"state": "IN",
|
||||
"status": "confirmed"
|
||||
},
|
||||
{
|
||||
"name": "Helen Z. Cooper",
|
||||
"booked_for": "12:00",
|
||||
"role": "Loader",
|
||||
"city": "Indianapolis",
|
||||
"state": "IN",
|
||||
"status": "confirmed"
|
||||
},
|
||||
{
|
||||
"name": "Ryan Z. Torres",
|
||||
"booked_for": "12:00",
|
||||
"role": "Loader",
|
||||
"city": "Indianapolis",
|
||||
"state": "IN",
|
||||
"status": "confirmed"
|
||||
}
|
||||
]
|
||||
@@ -0,0 +1 @@
|
||||
# SMS drafts — Midway Distribution, 2026-05-05
|
||||
Reference in New Issue
Block a user