Cover security and operational gates

Separate runtime and operator roles for token+router cost controller for mixed FAQ vs complex research traffic. Runtime may only perform the narrow actions that finance partner capping July LLM spend at $12k needs; operators get audited break-glass with TTL. Encode a negative probe that denies the privilege trick related to router sends long research prompts to mini — quality collapses, retries inflate spend.

Redact prompts/PII at collection. Secrets enter via a manager or workload identity — never source, fixtures, or exception strings. Incident COST-ROUTER-MISCLASS-14 should be impossible if these controls hold. Output allowlists and schema checks stay in force on error paths.

Rehearse the rollback or kill switch timed against a clock. Record actor, reason, prior revision/secret/flag, and verification query. Invariant reminder: simple FAQs route to mini model; monthly forecast alerts at 80% budget.

Abuse cases unique to this lab include the privilege path implied by router sends long research prompts to mini — quality collapses, retries inflate spend. Prove a read-only role cannot mutate. Break-glass tokens expire; leftover tokens fail the drill. Dependency pin/digest story matters when images or models move under you. Document how to rotate the credential that token+router cost controller for mixed FAQ vs complex research traffic uses without a full outage window longer than your dual-run plan. Security evidence is part of ship, not an appendix nobody reads.

List network egress destinations and justify each. Ensure debug endpoints are off by default in the shipping config. Verify that error responses do not echo secrets or raw stack frames to clients. For multi-tenant paths, add a cross-tenant probe fixture. Time the rollback drill twice — once with the author, once with a peer. Store the drill transcript beside the threat notes for the incident id. In this chapter the product is token+router cost controller for mixed FAQ vs complex research traffic, the human stakeholder is finance partner capping July LLM spend at $12k, and the incident id you design against is COST-ROUTER-MISCLASS-14. Re-state the oracle in your notes — replay day shows −32% $ with groundedness drop ≤ 0.01 vs all-frontier baseline — and keep the invariant visible: simple FAQs route to mini model; monthly forecast alerts at 80% budget. Track usd_per_successful_answer and groundedness as the scoreboard. Surface under change control: POST /v1/answer. If you only have forty minutes, finish the fixture for router sends long research prompts to mini — quality collapses, retries inflate spend before polishing UI. Promotion language stays ternary: promote, hold, or roll back based on evidence, not hope.