coder / coder/internal

AIBridge integration tests

Open
#1,037 0 comments 0 reactions 0 assignees View on GitHub
Dominant language
No language data
Stars
3
Forks
0
PR merge metrics
No merged PRs in 30d

Description

Currently we have some mocked integration tests, but they don't catch errors/incompatibilities from the real upstream.

We should add some tests that don't run in CI (to avoid flakes) but can be run manually with a real anthropic or openai API key.

These tests would try injected and non-injected tool calls with a real agent like claude code. We could run it multiple times if it doesn't give the expected output to hopefully minimize flakes.

Contributor guide

No contributing guide indexed for this repository

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.