feat(npu): add advisory metrics to utilization digest

Roll up confidence, recommendation, authority, fallback, and service-level metrics, including v1 authority-flag handling.
This commit is contained in:
William Valentin
2026-06-06 15:30:31 -07:00
parent dae2a57124
commit 72434c8bc3
3 changed files with 254 additions and 4 deletions
+1 -1
View File
@@ -33,7 +33,7 @@ scripts/npu-utilization-digest.py --format jsonl --no-write
python -m pytest tests/test_npu_utilization_digest.py -q
```
Output shape is intentionally small: service booleans, counts, average probe ms, sysfs deltas, proof flags, fallback warning counts, artifact path, and closed gates. `fallbacks` includes unavailable services, failed/missing proof, and skipped proof-capable smokes such as disabled Whisper/doc-triage probes or GenAI cold-load skips; intentionally health-only RAG/advisory rows are not fallbacks unless unavailable. It does not print raw embeddings, transcripts, OCR text, model completions, request headers, or full upstream JSON.
Output shape is intentionally small: service booleans, request counts by service, average probe ms, sysfs/NPU busy deltas by service, proof flags, fallback totals and per-service fallback counts, confidence distribution, escalation/suppression recommendation counts, authority-safe flag violation totals, artifact path, and closed gates. `fallbacks` includes unavailable services, failed/missing proof, and skipped proof-capable smokes such as disabled Whisper/doc-triage probes or GenAI cold-load skips; intentionally health-only RAG/advisory rows are not fallbacks unless unavailable. It does not print raw embeddings, transcripts, OCR text, model completions, request headers, or full upstream JSON.
Covered rows: