Add observability and tests

Instrument OpenTelemetry traces across retrieve → rerank → generate for support answers so on-call engineer debugging a slow groundedness miss can answer: demand, errors, latency/age, saturation. Emit fields needed by trace_completeness ≥ 0.99 and p95_end_to_end_ms ≤ 2500 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 TRACE-ORPHAN-441, 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 missing parent context → orphan spans, cannot join retrieve to answer 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 TRACE-ORPHAN-441. 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/answer. 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 OpenTelemetry traces across retrieve → rerank → generate for support answers, the human stakeholder is on-call engineer debugging a slow groundedness miss, and the incident id you design against is TRACE-ORPHAN-441. Re-state the oracle in your notes — fixture question produces 3 child spans; total latency attributes sum within 5% of root — and keep the invariant visible: every span carries trace_id + redacted attrs; prompts sampled ≤ 1%. Track trace_completeness ≥ 0.99 and p95_end_to_end_ms ≤ 2500 as the scoreboard. Surface under change control: POST /v1/support/answer. If you only have forty minutes, finish the fixture for missing parent context → orphan spans, cannot join retrieve to answer before polishing UI. Promotion language stays ternary: promote, hold, or roll back based on evidence, not hope.