Build the first working claim-with-citation path

Code the narrow path that serves analyst compiling a brief on bike-share policy from a fixed corpus: accept → authorize/normalize → call dependency → validate → record. Keep stages named so a trace can show which boundary passed. Success must emit evidence useful to claim_citation_coverage and fabricated_id_rate, not only a 200 with prose. Predict the observable for POST /v1/research/brief before running: brief on fixture corpus: ≥ 0.95 claims cited; fabricated ID rate 0.

Drive the path with recording fakes or local stubs. Assert call order and arguments. Idempotency keys or stable ids should keep retries from duplicating costly work where the product requires it. Product under test remains citation-first research assistant that maps every claim to evidence IDs — resist adding unrelated features mid-path.

For Capstone: research bot with citations, paste the CLI/HTTP transcript beside your prediction for POST /v1/research/brief. If the oracle is unmet (brief on fixture corpus: ≥ 0.95 claims cited; fabricated ID rate 0), stop and debug this page; do not compensate with prompt folktales. Re-run once after a clean process start to catch hidden global state that would invalidate CAP-RESEARCH-FAKE-ID-3.

Performance sketch: measure local p95 for the fake-backed path so later regressions are obvious. Keep concurrency modest until failure-handling proves limits. Log a single structured event per success with request id, revision, and the evidence field behind claim_citation_coverage and fabricated_id_rate. Avoid hidden global caches in the happy path unless the lab is about caching — and even then key by tenant. If the path calls a model, pin model id in config and echo it in the response for auditability. Remember analyst compiling a brief on bike-share policy from a fixed corpus experiences wall-clock time, not your debugger’s single-step comfort.

Prefer explicit function names over a single god-object handleRequest. Thread a correlation id from ingress to the last log line. When streaming, define what partial failure means before coding. Snapshot one successful response body in fixtures after redaction. If the path writes to a queue, assert message attributes in the fake. Stop adding retries on this page; that is the next concern. In this chapter the product is citation-first research assistant that maps every claim to evidence IDs, the human stakeholder is analyst compiling a brief on bike-share policy from a fixed corpus, and the incident id you design against is CAP-RESEARCH-FAKE-ID-3. Re-state the oracle in your notes — brief on fixture corpus: ≥ 0.95 claims cited; fabricated ID rate 0 — and keep the invariant visible: claim without evidence → abstain or drop claim; no orphan sentences. Track claim_citation_coverage and fabricated_id_rate as the scoreboard. Surface under change control: POST /v1/research/brief. If you only have forty minutes, finish the fixture for model invents kb://minutes-2099 citation before polishing UI. Promotion language stays ternary: promote, hold, or roll back based on evidence, not hope.