Sequa – Deterministic AI Testing ⭐

Version updated for https://github.com/thetechnoadvisor/sequa to version v0.7.0.

  • This action is used across all versions by ? repositories.

Action Type

This is a Composite action.

Go to the GitHub Marketplace to find the latest changes.

Action Summary

Sequa records AI executions once and replays them locally, reducing test run time, API costs, and dependency on internet connectivity. It supports multiple frameworks like OpenAI, Anthropic, LangChain, and LangGraph, offering features such as deterministic testing, phase 2 AI regression testing engine, and searchable AI executions & instant replay capabilities.

What’s Changed

  • feat: implement regression testing mode and add utility for result comparison (bce5243)
  • feat: upgrade the pyproject version (5af1386)
  • feat: implement pytest plugin for LLM testing with marker support and CI/CD integration (fbda344)
  • chore: update readme.md (34cbfb7)
  • feat: update version (10eea22)
  • feat: update demo.ipynb with git like cassette search and replay debugging engine (0d0937b)
  • feat: implement new search module (cc44592)
  • Update ci cd (6c6e8aa)
  • feat: implement interactive benchmark demos and automate CI/CD pipeline with release tagging (977d704)
  • feat: add Sequa dashboard web interface and implement new video script and comparison demos (8d8a166)