test_executor_model_completes_via_litellm checks the plumbing: a request reaches the executor model through LiteLLM and text comes back. It also asserted that the model obeyed "Reply with exactly one word: pong". On #66's CI, Haiku answered "ping" and the job failed; a re-run passed.
What the model chooses to say isn't what this test is for, so it now asserts non-empty text. Other live tests cover model behaviour, e.g. the capability matrix and the planning and milestone tests.
Passes locally against the live proxy; lint and format clean.
`test_executor_model_completes_via_litellm` checks the plumbing: a request reaches the executor model through LiteLLM and text comes back. It also asserted that the model obeyed "Reply with exactly one word: pong". On #66's CI, Haiku answered "ping" and the job failed; a re-run passed.
What the model chooses to say isn't what this test is for, so it now asserts non-empty text. Other live tests cover model behaviour, e.g. the capability matrix and the planning and milestone tests.
Passes locally against the live proxy; lint and format clean.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
https://claude.ai/code/session_01PPQ14L3LikyefCMFBqEbKE
The test checks that a request reaches the executor model through
LiteLLM and text comes back. It also asserted the model obeyed "Reply
with exactly one word: pong", which Haiku once answered with "ping" and
failed CI on #66. Assert non-empty text instead.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01PPQ14L3LikyefCMFBqEbKE
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
test_executor_model_completes_via_litellmchecks the plumbing: a request reaches the executor model through LiteLLM and text comes back. It also asserted that the model obeyed "Reply with exactly one word: pong". On #66's CI, Haiku answered "ping" and the job failed; a re-run passed.What the model chooses to say isn't what this test is for, so it now asserts non-empty text. Other live tests cover model behaviour, e.g. the capability matrix and the planning and milestone tests.
Passes locally against the live proxy; lint and format clean.
🤖 Generated with Claude Code
https://claude.ai/code/session_01PPQ14L3LikyefCMFBqEbKE