Page 2 of 8~245 min topic

Incident response lab

Configure the incident response contract

Types and env contracts make **correctness incident for invalid RAG citations (SEV2)** fail closed before any provider or cluster call.

~35 min this pageSetup

1Learn the idea

Read

Define trusted borders

Implement types or schemas around POST /v1/rag/answer so illegal states are unrepresentable at the boundary. For correctness incident for invalid RAG citations (SEV2), trusted inputs come from sessions, signatures, pinned digests, or workload identity — not from free-form model text. incident commander coordinating mitigate → communicate → verify should be able to read the contract and know which fields are optional, which are enumerated, and which abort the request. Constructors and boot paths must not perform provider side effects; injection points keep tests honest.

Read

Environment and secrets contract

Document required env vars in .env.example with placeholders only. Rotation story belongs later, but the contract already forbids printing secrets and forbids defaulting to fail-open when a dependency is missing. Invariant to encode in types/tests: declare early; preserve evidence; mitigation scoped; no blame in channel. If a config number lacks units, fix the name (timeout_ms, rpm_hard) before writing logic.

Read

Implementation artifact

Read

Evidence freeze: pin index digest, prompt sha, sample request_ids [r_100..r_110]

Read

Fixture kit

Create fixtures for the golden path and for INC-RAG-CIT-2201. Name files after the behavior (429-retry-after.json, cross-tenant.json, empty-citation.json) rather than test1. Each fixture carries expected status/code. This kit is the shared language for validation and failure pages.

Read

Stage depth

Compatibility promise: additive fields may appear only if readers ignore unknowns safely; breaking changes bump a version visible on the wire. For AI payloads, size limits arrive before JSON parse when hostile blobs are a risk. Document how clock skew, idempotency keys, and tracing headers travel through correctness incident for invalid RAG citations (SEV2). If you use feature flags later, the contract already states that flags are not authorization. Link each config knob to a unit and a failure mode (“0 means disabled” vs “0 means divide-by-zero”). A peer reviewing the PR should find INC-RAG-CIT-2201 named in a comment on the adversarial fixture.

Read

Field notes for `incident-response-lab` / `setup-and-contract`

Generate OpenAPI or a typed client only after the hand schema is stable for one fixture round-trip. Record how errors look on the wire — problem+json, envelope, or bare status — and stick to one. Clock sources must be injectable for skew tests. If webhooks appear later, document signature header names now even as TODOs. Keep sample payloads UTF-8 and free of real emails. Add a makefile or npm script that validates schemas without network. In this chapter the product is correctness incident for invalid RAG citations (SEV2), the human stakeholder is incident commander coordinating mitigate → communicate → verify, and the incident id you design against is INC-RAG-CIT-2201. Re-state the oracle in your notes — INC-RAG-CIT-2201: feature flag off in 8m; customer update sent; groundedness restored — and keep the invariant visible: declare early; preserve evidence; mitigation scoped; no blame in channel. Track time_to_declare_m, time_to_mitigate_m, customer_update_sent as the scoreboard. Surface under change control: POST /v1/rag/answer. If you only have forty minutes, finish the fixture for team debugs for an hour without declaring — customers keep seeing wrong policy cites before polishing UI. Promotion language stays ternary: promote, hold, or roll back based on evidence, not hope.

Go deeper

Before you start

Why this matters

For Incident response lab, sketch the request and response shapes that cross POST /v1/rag/answer without naming a framework. Mark which fields are trusted (session, signatures, digests) versus untrusted (user text, model JSON, webhook bodies). If a field can change authorization, it does not belong in model output. Predict one 422/401 you will assert before coding adapters for correctness incident for invalid RAG citations (SEV2).

Check your understanding

Page assessment

Answer from memory. Completion is saved from this evidence, not from opening the next page.

1. Can a newcomer list trusted vs untrusted fields?
2. Does boot avoid external side effects?
3. Are fixtures named after INC-RAG-CIT-2201-class failures?

All responses are required.