Canary and operate load testing

From a fresh clone/directory, run the commands that prove find saturation knee near 180 RPS; beyond that queue depth explodes. A second person plays capacity planner before Black Friday traffic 3× baseline and follows your script without coaching. The demo includes limitations: what k6 streaming load test for chat completion gateway still will not do.

Bundle: contract snippet, passing tests, metric snapshot for saturation_rps, p95_ttft_ms, test_usd, security negative probe, rollback note, owner name. Reference LOAD-FALSE-GREEN-33 as the drill you rehearsed. If any item is missing, the ship gate fails even if the happy path dazzles.

For Load testing lab, name the human who gets paged, the review date for thresholds, and the condition that triggers reevaluation. Endpoint POST /v1/chat/completions (stream) remains the production surface you operate for k6 streaming load test for chat completion gateway — not a slide. Keep LOAD-FALSE-GREEN-33 in the handoff template so the next owner inherits the drill.

After the peer demo, schedule the next threshold review date. File a short changelog that mentions LOAD-FALSE-GREEN-33 and the control that addresses it. Archive the evidence pack where your team already stores launch records. Resist rewriting everything “for real production” in one weekend — operate this slice until the metrics bore you, then widen. Final self-check: if telemetry vanished, would you still know to hold? If yes, you learned the operating posture this lane teaches.

Trim the demo script until every command is necessary. Record a peer signature line: name, date UTC, pass/fail. File known limitations as bullets, not apologies. Link the evidence pack from the README. Schedule the next game day on a calendar, even if it is solo. Archive the branch tag or release digest you actually shipped. In this chapter the product is k6 streaming load test for chat completion gateway, the human stakeholder is capacity planner before Black Friday traffic 3× baseline, and the incident id you design against is LOAD-FALSE-GREEN-33. Re-state the oracle in your notes — find saturation knee near 180 RPS; beyond that queue depth explodes — and keep the invariant visible: abort if error_rate > 1% or p95_ttft > 1.5s; test cost ≤ $50. Track saturation_rps, p95_ttft_ms, test_usd as the scoreboard. Surface under change control: POST /v1/chat/completions (stream). If you only have forty minutes, finish the fixture for load generator retries hide server shedding — false green before polishing UI. Promotion language stays ternary: promote, hold, or roll back based on evidence, not hope.