Overview
Sequa is a lightweight snapshot testing library for LLM (Large Language Model) applications. It intercepts, records, and replays HTTP request payloads, allowing developers to mock network latency and API costs during integration testing.
Traditional LLM tests suffer from three main friction points:
- Flakiness: LLM APIs have non-deterministic outputs which can break test expectations randomly.
- Speed: Requests to external LLM providers take anywhere from 1.5s to 5s, ballooning test suite durations.
- Cost: Repeatedly calling commercial APIs in CI/CD environments accumulates significant financial overhead.
The Sequa Solution: Run your test suite once. Sequa records the API response payload into a yaml-structured cassette. On subsequent runs, Sequa intercepts the outbound request, hashes it, matches the cached cassette, and returns the recorded response locally in 12ms without touching the external network.