Build the first working local chat adapter

Code the narrow path that serves legal analyst summarizing NDAs that must not leave the laptop by default: accept → authorize/normalize → call dependency → validate → record. Keep stages named so a trace can show which boundary passed. Success must emit evidence useful to local_share ≥ 0.8 and cloud_fallback_with_pii == 0, not only a 200 with prose. Predict the observable for POST http://127.0.0.1:11434/api/generate before running: local llama3.2:3b answers fixture brief at ≥ 25 tok/s; fallback path logs reason=local_timeout.

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 Ollama-backed local router with policy-controlled cloud fallback — resist adding unrelated features mid-path.

For Local model lab, paste the CLI/HTTP transcript beside your prediction for POST http://127.0.0.1:11434/api/generate. If the oracle is unmet (local llama3.2:3b answers fixture brief at ≥ 25 tok/s; fallback path logs reason=local_timeout), 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 LOCAL-FALLBACK-PII-03.

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 local_share ≥ 0.8 and cloud_fallback_with_pii == 0. 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 legal analyst summarizing NDAs that must not leave the laptop by default 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 Ollama-backed local router with policy-controlled cloud fallback, the human stakeholder is legal analyst summarizing NDAs that must not leave the laptop by default, and the incident id you design against is LOCAL-FALLBACK-PII-03. Re-state the oracle in your notes — local llama3.2:3b answers fixture brief at ≥ 25 tok/s; fallback path logs reason=local_timeout — and keep the invariant visible: cloud fallback requires explicit policy flag + redaction pass; local p95 ≤ 6s for 512 tokens. Track local_share ≥ 0.8 and cloud_fallback_with_pii == 0 as the scoreboard. Surface under change control: POST http://127.0.0.1:11434/api/generate. If you only have forty minutes, finish the fixture for fallback silently ships full NDA text to cloud when Ollama is down before polishing UI. Promotion language stays ternary: promote, hold, or roll back based on evidence, not hope.