Instrument tokens/sec and fallback reasons

Instrument Ollama-backed local router with policy-controlled cloud fallback so legal analyst summarizing NDAs that must not leave the laptop by default can answer: demand, errors, latency/age, saturation. Emit fields needed by local_share ≥ 0.8 and cloud_fallback_with_pii == 0 with bounded labels. Sample successful high-volume traces; keep errors and rollout transitions denser within policy.

Define at least one alert that would fire for LOCAL-FALLBACK-PII-03, with a for/pending window that survives deploy blips. Missing scrape or missing revision labels must not look like health. Include a trace/log example id format you will actually search.

Add a unit/integration check that metrics increment on the happy path and on the fallback silently ships full NDA text to cloud when Ollama is down branch. Store machine-readable output in CI artifacts when practical.

Cardinality discipline: tenant and revision are usually enough; raw question text is not a label. Exemplars or trace links beat screenshots alone when debugging LOCAL-FALLBACK-PII-03. Define who owns alert fatigue review. If you export to a vendor, record retention and access. Synthetic probes should use non-sensitive fixtures and still exercise POST http://127.0.0.1:11434/api/generate. Practice the query you will type at 2am once, while calm.

Document the exact PromQL or log query in the runbook stub for this service. Verify histograms have buckets around your SLO target. Add a canary synthetic check that exercises the oracle path every few minutes in staging. Confirm that PII redaction happens before export. Track build/version as a label on the golden signals. Delete noisy debug logs before they become accidental product dependencies. In this chapter the product is Ollama-backed local router with policy-controlled cloud fallback, the human stakeholder is legal analyst summarizing NDAs that must not leave the laptop by default, and the incident id you design against is LOCAL-FALLBACK-PII-03. Re-state the oracle in your notes — local llama3.2:3b answers fixture brief at ≥ 25 tok/s; fallback path logs reason=local_timeout — and keep the invariant visible: cloud fallback requires explicit policy flag + redaction pass; local p95 ≤ 6s for 512 tokens. Track local_share ≥ 0.8 and cloud_fallback_with_pii == 0 as the scoreboard. Surface under change control: POST http://127.0.0.1:11434/api/generate. If you only have forty minutes, finish the fixture for fallback silently ships full NDA text to cloud when Ollama is down before polishing UI. Promotion language stays ternary: promote, hold, or roll back based on evidence, not hope.