Instrument metrics and rollout decisions

Instrument support API: versioned policy retrieval + scoped order tool + cited answer or escalate so customer asking where order A12 is without leaking other customers' orders can answer: demand, errors, latency/age, saturation. Emit fields needed by unauthorized_tool_calls == 0 and citation_rate ≥ 0.9 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 CAP-SUPPORT-TOOL-09, 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 model passes attacker order_id and tool executes 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 CAP-SUPPORT-TOOL-09. 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 /v1/support/turn. 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 support API: versioned policy retrieval + scoped order tool + cited answer or escalate, the human stakeholder is customer asking where order A12 is without leaking other customers' orders, and the incident id you design against is CAP-SUPPORT-TOOL-09. Re-state the oracle in your notes — order lookup returns status+policy cite; cross-customer order_id → deny+escalate — and keep the invariant visible: tool args bind to session customer_id; refunds never auto-executed. Track unauthorized_tool_calls == 0 and citation_rate ≥ 0.9 as the scoreboard. Surface under change control: POST /v1/support/turn. If you only have forty minutes, finish the fixture for model passes attacker order_id and tool executes before polishing UI. Promotion language stays ternary: promote, hold, or roll back based on evidence, not hope.