litellm/tests/test_litellm/llms/watsonx
Alexsander Hamir 53e2516ace
fix: make test_watsonx_gpt_oss_prompt_transformation deterministic (#17597)
- Remove network dependency by mocking HuggingFace template fetch
- Use mock template that produces correct format for test validation
- Test now focuses on transformation logic, not network calls
- Fixes flaky test failures due to network timeouts/rate limits

The test verifies that prompt transformation occurs (not simple
concatenation), which doesn't require the actual HuggingFace template.
Mocking makes the test deterministic and faster while still validating
the core behavior.
2025-12-06 08:48:39 -08:00
..
audio_transcription [Bug fix] WatsonX audio transcriptions, don't force content type in request headers (#17546) 2025-12-05 10:56:15 -08:00
__init__.py [Feat] Add audio transcriptions for WatsonX (#17160) 2025-11-26 14:15:49 -08:00
test_watsonx.py fix: make test_watsonx_gpt_oss_prompt_transformation deterministic (#17597) 2025-12-06 08:48:39 -08:00