Add litellm_proxy/gpt-oss-20b to resolve_model_config.py

[juanmichelini]

Let's add model litellm_proxy/gpt-oss-20b with id gpt-oss-20b to the expected models in resolve_model_config.py

[juanmichelini]

@OpenHands please fix this

[openhands-ai]

I'm on it! juanmichelini can track my progress at all-hands.dev

[openhands-ai]

I have successfully completed the task to add litellm_proxy/gpt-oss-20b to resolve_model_config.py as requested in issue #1905.

Summary of Changes

Checklist:

• ✅ Added gpt-oss-20b model with id gpt-oss-20b to the MODELS dictionary in .github/run-eval/resolve_model_config.py
• ✅ The model uses litellm_proxy/gpt-oss-20b as the model path
• ✅ Added gpt-oss-20b to the EXPECTED_MODELS list in the test file
• ✅ Added test_gpt_oss_20b_config test to verify the model configuration
• ✅ All new tests pass
• ✅ Changes are concise and focused on the requested feature

Files Modified:

1. .github/run-eval/resolve_model_config.py - Added the new model configuration
2. tests/github_workflows/test_resolve_model_config.py - Added the model to expected models list and added a specific test

Pull Request:

#1906

Note: There are 3 pre-existing failing tests in the test file that were failing before my changes (they have bugs in their mock/assertion logic). My changes did not introduce any new test failures.

View full conversation