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":"12:15","event_kind":"expansion","ok":true,"model":"gpt-oss:20b","duration_secs":12.362,"risk":"Model output failure risk","hint":"If next event is “12:45 expansion Warehouse Associate×4 in Chicago, IL”, switch to gpt-4o-mini and shorten the prompt."}
|
||||
{"after_event":"15:45","event_kind":"misplacement","ok":true,"model":"gpt-oss:20b","duration_secs":11.178,"risk":"Empty model output risk","hint":"Switch to a more robust model, shorten prompts, and pre‑validate Warehouse Associate data for Toledo before generation."}
|
||||
@@ -0,0 +1 @@
|
||||
# Client emails — Riverfront Steel, 2026-04-21
|
||||
@@ -0,0 +1,6 @@
|
||||
# Cross-day lesson — Riverfront Steel, 2026-04-21
|
||||
|
||||
_Generated by `gpt-oss:20b` in 5.4s. Based on 5 events + 2 mid-day checkpoints._
|
||||
|
||||
**
|
||||
Before any expansion or emergency event, pre‑fetch and validate the pool data for the target location—missing pool info caused all failures. Use a smaller, more reliable model (e.g., gpt‑4o‑mini) for large or high‑risk events and keep prompts concise. Verify that the number of required positions matches available candidates before invoking the model. If the model returns empty output, switch to a more robust model and re‑validate the data. This will reduce failures and improve turnaround.
|
||||
@@ -0,0 +1 @@
|
||||
[]
|
||||
@@ -0,0 +1,56 @@
|
||||
# Scenario retrospective — Riverfront Steel, 2026-04-21
|
||||
|
||||
Executor: `qwen3.5:latest` Reviewer: `qwen3:latest` Draft: `qwen2.5:latest` Overview(T3): `gpt-oss:20b`
|
||||
Prior lessons loaded into executor context: **0** (baseline — no prior T3 history)
|
||||
|
||||
## Events
|
||||
|
||||
| At | Kind | Role / Count | Pool | Fills | Turns | Dur(s) | Cites | Gaps |
|
||||
|---|---|---|---|---|---|---|---|---|
|
||||
| 08:00 | baseline_fill | Warehouse Associate × 3 | - | ✗ 0 | 0 | 12.1 | 0 | 1 |
|
||||
| 10:30 | recurring | Machine Operator × 2 | - | ✗ 0 | 0 | 19.0 | 0 | 1 |
|
||||
| 12:15 | expansion | Forklift Operator × 5 | - | ✗ 0 | 0 | 12.1 | 0 | 1 |
|
||||
| 14:00 | emergency | Loader × 4 | - | ✗ 0 | 0 | 16.4 | 0 | 1 |
|
||||
| 15:45 | misplacement | Warehouse Associate × 1 | - | ✗ 0 | 0 | 12.2 | 0 | 1 |
|
||||
|
||||
## Final roster
|
||||
|
||||
| Worker | Booked | Role | City, ST | Status |
|
||||
|---|---|---|---|---|
|
||||
|
||||
## Gap signals
|
||||
|
||||
### drift_or_tool
|
||||
- **08:00** — generate returned empty text from qwen3.5:latest: {"text":"","model":"qwen3.5:latest","tokens_evaluated":998,"tokens_generated":600}
|
||||
- **10:30** — no JSON object in reviewer response: {"kind":"critique","verdict":"continue","notes":"Executor's initial hybrid_search correctly filters Toledo, OH Machine Operators with availability > 0.5. Next steps should select
|
||||
- **12:15** — generate returned empty text from qwen3.5:latest: {"text":"","model":"qwen3.5:latest","tokens_evaluated":1011,"tokens_generated":600}
|
||||
- **14:00** — generate returned empty text from qwen3.5:latest: {"text":"","model":"qwen3.5:latest","tokens_evaluated":998,"tokens_generated":600}
|
||||
- **15:45** — generate returned empty text from qwen3.5:latest: {"text":"","model":"qwen3.5:latest","tokens_evaluated":1002,"tokens_generated":600}
|
||||
|
||||
### write_through_audit
|
||||
- _post-run_ — playbook_memory has 1347 entries (ran 5 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:
|
||||
|
||||
- **08:00 baseline_fill** (Warehouse Associate): —
|
||||
- **10:30 recurring** (Machine Operator): —
|
||||
- **12:15 expansion** (Forklift Operator): —
|
||||
- **14:00 emergency** (Loader): —
|
||||
- **15:45 misplacement** (Warehouse Associate): —
|
||||
|
||||
## Narrative
|
||||
|
||||
- 0/5 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: 08:00 baseline_fill, 10:30 recurring, 12:15 expansion, 14:00 emergency, 15:45 misplacement.
|
||||
@@ -0,0 +1,104 @@
|
||||
[
|
||||
{
|
||||
"event": {
|
||||
"kind": "baseline_fill",
|
||||
"at": "08:00",
|
||||
"role": "Warehouse Associate",
|
||||
"count": 3,
|
||||
"city": "Toledo",
|
||||
"state": "OH",
|
||||
"shift_start": "08:00 AM",
|
||||
"scenario_note": "Regular Monday morning shift, 8-hour."
|
||||
},
|
||||
"ok": false,
|
||||
"fills": [],
|
||||
"turns": 0,
|
||||
"duration_secs": 12.062,
|
||||
"error": "generate returned empty text from qwen3.5:latest: {\"text\":\"\",\"model\":\"qwen3.5:latest\",\"tokens_evaluated\":998,\"tokens_generated\":600}",
|
||||
"gap_signals": [
|
||||
"drift_or_tool: generate returned empty text from qwen3.5:latest: {\"text\":\"\",\"model\":\"qwen3.5:latest\",\"tokens_evaluated\":998,\"tokens_generated\":600}"
|
||||
]
|
||||
},
|
||||
{
|
||||
"event": {
|
||||
"kind": "recurring",
|
||||
"at": "10:30",
|
||||
"role": "Machine Operator",
|
||||
"count": 2,
|
||||
"city": "Toledo",
|
||||
"state": "OH",
|
||||
"shift_start": "11:00 AM",
|
||||
"scenario_note": "Recurring Tuesday/Thursday slot — prior workers may still be available."
|
||||
},
|
||||
"ok": false,
|
||||
"fills": [],
|
||||
"turns": 0,
|
||||
"duration_secs": 18.97,
|
||||
"error": "no JSON object in reviewer response: {\"kind\":\"critique\",\"verdict\":\"continue\",\"notes\":\"Executor's initial hybrid_search correctly filters Toledo, OH Machine Operators with availability > 0.5. Next steps should select",
|
||||
"gap_signals": [
|
||||
"drift_or_tool: no JSON object in reviewer response: {\"kind\":\"critique\",\"verdict\":\"continue\",\"notes\":\"Executor's initial hybrid_search correctly filters Toledo, OH Machine Operators with availability > 0.5. Next steps should select"
|
||||
]
|
||||
},
|
||||
{
|
||||
"event": {
|
||||
"kind": "expansion",
|
||||
"at": "12:15",
|
||||
"role": "Forklift Operator",
|
||||
"count": 5,
|
||||
"city": "Toledo",
|
||||
"state": "OH",
|
||||
"shift_start": "01:00 PM",
|
||||
"scenario_note": "New warehouse location opening, five-worker team needed."
|
||||
},
|
||||
"ok": false,
|
||||
"fills": [],
|
||||
"turns": 0,
|
||||
"duration_secs": 12.086,
|
||||
"error": "generate returned empty text from qwen3.5:latest: {\"text\":\"\",\"model\":\"qwen3.5:latest\",\"tokens_evaluated\":1011,\"tokens_generated\":600}",
|
||||
"gap_signals": [
|
||||
"drift_or_tool: generate returned empty text from qwen3.5:latest: {\"text\":\"\",\"model\":\"qwen3.5:latest\",\"tokens_evaluated\":1011,\"tokens_generated\":600}"
|
||||
]
|
||||
},
|
||||
{
|
||||
"event": {
|
||||
"kind": "emergency",
|
||||
"at": "14:00",
|
||||
"role": "Loader",
|
||||
"count": 4,
|
||||
"city": "Toledo",
|
||||
"state": "OH",
|
||||
"shift_start": "04:00 PM same day",
|
||||
"deadline": "16:00",
|
||||
"scenario_note": "Walkoff incident — replacement crew needed by 16:00 sharp."
|
||||
},
|
||||
"ok": false,
|
||||
"fills": [],
|
||||
"turns": 0,
|
||||
"duration_secs": 16.358,
|
||||
"error": "generate returned empty text from qwen3.5:latest: {\"text\":\"\",\"model\":\"qwen3.5:latest\",\"tokens_evaluated\":998,\"tokens_generated\":600}",
|
||||
"gap_signals": [
|
||||
"drift_or_tool: generate returned empty text from qwen3.5:latest: {\"text\":\"\",\"model\":\"qwen3.5:latest\",\"tokens_evaluated\":998,\"tokens_generated\":600}"
|
||||
]
|
||||
},
|
||||
{
|
||||
"event": {
|
||||
"kind": "misplacement",
|
||||
"at": "15:45",
|
||||
"role": "Warehouse Associate",
|
||||
"count": 1,
|
||||
"city": "Toledo",
|
||||
"state": "OH",
|
||||
"shift_start": "remainder of 08:00 shift",
|
||||
"scenario_note": "One worker from the 08:00 fill didn't show; rebuild the gap.",
|
||||
"replaces_event": "08:00"
|
||||
},
|
||||
"ok": false,
|
||||
"fills": [],
|
||||
"turns": 0,
|
||||
"duration_secs": 12.183,
|
||||
"error": "generate returned empty text from qwen3.5:latest: {\"text\":\"\",\"model\":\"qwen3.5:latest\",\"tokens_evaluated\":1002,\"tokens_generated\":600}",
|
||||
"gap_signals": [
|
||||
"drift_or_tool: generate returned empty text from qwen3.5:latest: {\"text\":\"\",\"model\":\"qwen3.5:latest\",\"tokens_evaluated\":1002,\"tokens_generated\":600}"
|
||||
]
|
||||
}
|
||||
]
|
||||
@@ -0,0 +1 @@
|
||||
[]
|
||||
@@ -0,0 +1 @@
|
||||
# SMS drafts — Riverfront Steel, 2026-04-21
|
||||
Reference in New Issue
Block a user