Validate outputs and schemas

Add executable validation at the trust boundaries of token+router cost controller for mixed FAQ vs complex research traffic. Reject unknown fields where they matter, bound string sizes, and coerce only after auth/signature checks when raw bytes are security-relevant. Invariant under test: simple FAQs route to mini model; monthly forecast alerts at 80% budget. A TypeScript type or Python annotation is not runtime validation — pair them with parsers.

Automate the fixtures from setup, including a recreation of COST-ROUTER-MISCLASS-14. Assert both the visible error and the absence of side effects (no provider call, no queue write, no flag flip). Where metrics matter, assert label enums stay bounded.

Document which failures are client mistakes (4xx) versus operator/config mistakes (5xx/503). Oracle still stands: replay day shows −32% $ with groundedness drop ≤ 0.01 vs all-frontier baseline. Validation should make accidental “success with empty body” impossible for finance partner capping July LLM spend at $12k.

Property ideas: shuffled field order, Unicode edges, maximum-length strings, and replayed timestamps. Where money, identity, or citations matter, assertion messages should cite the field name. Do not snapshot entire provider payloads in tests; assert semantically. If validation fails open “to keep the demo working,” you have inverted the lab. Tie at least one CI job to the COST-ROUTER-MISCLASS-14 fixture so main cannot regress silently. Re-read simple FAQs route to mini model; monthly forecast alerts at 80% budget after each new parser — convenience helpers love to bypass it.

Table-drive status codes and error codes so reviewers see coverage at a glance. Include a Unicode normalization case if user text is accepted. Verify that oversized bodies fail before CPU-heavy work. Where digests or versions are pinned, assert mismatch behavior. Keep golden files small enough to read in review. CI should fail on skipped tests that mark the incident fixture as xfail without a ticket link. 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.