docs(npu): document advisory observability gates

Add operator runbook and link integrated health docs for advisory-only observability, dry-run metrics, and future promotion criteria.
This commit is contained in:
William Valentin
2026-06-06 15:30:31 -07:00
parent 72434c8bc3
commit 22e6ee90d2
2 changed files with 249 additions and 0 deletions
+3
View File
@@ -34,6 +34,7 @@ Scope:
| `scripts/npu-service-health.sh` | Listener / systemd / Docker / health endpoint / single embedding proof. Existing baseline script. |
| `scripts/npu-utilization-digest.py` | Per-service utilization digest with NPU proof per probe, compact text or JSONL output, optional JSONL artifact. |
| `docs/npu-utilization-digest.md` | Per-service digest reference. |
| `docs/npu-advisory-observability-runbook.md` | Dry-run comparison and later promotion criteria for advisory lanes. |
| `tests/test_npu_utilization_digest.py` | Offline unit tests for the digest (no live services required). |
## Integrated workflow
@@ -181,6 +182,8 @@ The integrated workflow intentionally does not:
These remain approval-gated and are tracked on the `npu-maximization` board.
For advisory-lane promotion decisions, pair this live utilization pass with the fixture-only dry-run comparison in `docs/npu-advisory-observability-runbook.md`. The digest can show whether live NPU services are healthy enough to collect evidence; it does not promote advisory outputs into authority. Promotion remains a separate lane-specific approval with explicit scope and rollback.
## Quick reference
```bash