b981fddfaa
Fixes #18282 This PR fixes two issues with Gemini context window error handling: 1. **Pattern matching for Gemini 2.0 Flash**: The previous pattern 'input token count exceeds the maximum number of tokens allowed' doesn't match Gemini 2.0 Flash errors which include dynamic token counts like '(2800010)' in the message. Split into shorter patterns that work with both formats. 2. **Add context window check to Gemini block**: The is_error_str_context_window_exceeded() check was only called for OpenAI-compatible providers, not for Gemini/Vertex AI. Added the check to the Gemini-specific error handling block. Test cases added for both Gemini 2.0 Flash and 2.5/3 error formats. |
||
|---|---|---|
| .. | ||
| a2a_protocol | ||
| caching | ||
| completion_extras | ||
| containers | ||
| enterprise | ||
| experimental_mcp_client | ||
| google_genai | ||
| images | ||
| integrations | ||
| interactions | ||
| litellm_core_utils | ||
| llms | ||
| passthrough | ||
| proxy | ||
| responses | ||
| router_strategy | ||
| router_utils | ||
| secret_managers | ||
| types | ||
| vector_stores | ||
| __init__.py | ||
| conftest.py | ||
| log.txt | ||
| readme.md | ||
| test_acompletion_session_reuse_e2e.py | ||
| test_add_deployment_no_master_key.py | ||
| test_aembedding_session_reuse_e2e.py | ||
| test_azure_video_router.py | ||
| test_claude_haiku_4_5_config.py | ||
| test_constants.py | ||
| test_container_router.py | ||
| test_cost_calculation_log_level.py | ||
| test_cost_calculator.py | ||
| test_exception_mapping_request_attribute.py | ||
| test_filter_out_litellm_params.py | ||
| test_groq_streaming_encoding.py | ||
| test_lazy_imports.py | ||
| test_logging.py | ||
| test_lowest_latency_zero_tokens.py | ||
| test_main.py | ||
| test_nested_drop_params.py | ||
| test_redis.py | ||
| test_responses_id_security.py | ||
| test_router_google_genai.py | ||
| test_router.py | ||
| test_shared_session_integration.py | ||
| test_system_message_format_bug.py | ||
| test_utils.py | ||
| test_uuid_helper.py | ||
| test_video_generation.py | ||
Testing for litellm/
This directory 1:1 maps the the litellm/ directory, and can only contain mocked tests.
The point of this is to:
- Increase test coverage of
litellm/ - Make it easy for contributors to add tests for the
litellm/package and easily run tests without needing LLM API keys.
File name conventions
litellm/proxy/test_caching_routes.pymaps tolitellm/proxy/caching_routes.pytest_<filename>.pymaps tolitellm/<filename>.py