mirror of
https://github.com/BerriAI/litellm.git
synced 2026-10-29 06:33:28 +00:00
c29a4f56a3
* fix(gemini)!: honor supports_sampling_params on the Gemini and Vertex path and flag Gemini 3.6 Flash, 3.5 Flash-Lite and later Google ignores temperature, top_p and top_k on Gemini 3.6 Flash, Gemini 3.5 Flash-Lite and every later Gemini release, and says a later generation will return 400 for them. The model map now carries supports_sampling_params: false on those rows, and the Gemini and Vertex transformation reads the flag the way the Anthropic and Bedrock paths already do, dropping the params under drop_params and otherwise raising the client-side 400 that names drop_params BREAKING CHANGE: a request that sends temperature, top_p or top_k to a flagged Gemini model without drop_params now gets a 400 instead of a 200 whose sampling params Google silently ignored Fixes #47015 * fix(gemini): gate the passed-through top_k where the request body is built and keep allowed_openai_params working top_k is a provider-specific kwarg that never reaches the OpenAI param mapping, so the flag has to be applied while the Gemini request body is built, the same boundary Anthropic uses. The mapping now skips a flagged sampling param instead of raising, because the shared unsupported-param check already returns the 400 that names drop_params, and a param the caller lists in allowed_openai_params is forwarded verbatim as that 400 promises * fix(gemini): filter top_k out of the generation config instead of mutating optional_params * test(gemini): type the sampling-flag twin test and keep its locals out of the loop body * fix(vertex_ai): reject or drop sampling params on batch rows for flagged Gemini models The batch JSONL wrapper calls map_openai_params directly and skips get_optional_params, so a flagged model's temperature, top_p and top_k vanished from the uploaded row with no 400. Batch rows now get the same contract as a real-time call: a 400 naming drop_params, or the knobs dropped when litellm.drop_params is on * fix(vertex_ai): ignore null sampling knobs on batch rows for flagged Gemini models A batch row carrying temperature: null, top_p: null or top_k: null means no override, the same as on a real-time call, so the row is no longer refused with a 400 and the null knobs are simply not forwarded |
||
|---|---|---|
| .. | ||
| a2a | ||
| aiml | ||
| aiohttp_openai | ||
| anthropic | ||
| apiserpent | ||
| aws_polly | ||
| azure | ||
| azure_ai | ||
| base_llm | ||
| baseten | ||
| bedrock | ||
| bedrock_mantle | ||
| black_forest_labs | ||
| brave | ||
| bytez | ||
| cerebras | ||
| chat | ||
| chatgpt | ||
| clarifai | ||
| claude_code | ||
| cloudflare | ||
| codex | ||
| cohere | ||
| cometapi | ||
| compactifai | ||
| crusoe | ||
| custom_httpx | ||
| dashscope | ||
| databricks | ||
| dataforseo | ||
| datarobot | ||
| deepagents | ||
| deepgram | ||
| deepinfra | ||
| deepseek | ||
| docker_model_runner | ||
| duckduckgo | ||
| e2b | ||
| edenai | ||
| elevenlabs | ||
| exa_ai | ||
| fal_ai | ||
| fastcrw | ||
| featherless_ai | ||
| firecrawl | ||
| fireworks_ai | ||
| friendliai | ||
| gdc | ||
| gemini | ||
| gigachat | ||
| github_copilot | ||
| google_pse | ||
| gradient_ai | ||
| groq | ||
| heroku | ||
| hosted_vllm | ||
| huggingface | ||
| hyperbolic | ||
| inception | ||
| infinity | ||
| jina_ai | ||
| lambda_ai | ||
| langflow | ||
| langgraph | ||
| laya | ||
| lemonade | ||
| linkup | ||
| litellm_proxy | ||
| llamafile | ||
| lm_studio | ||
| manus | ||
| meta | ||
| meta_llama | ||
| microsoft_365_copilot | ||
| milvus | ||
| minimax | ||
| mistral | ||
| modelscope | ||
| mongodb | ||
| moonshot | ||
| nadir | ||
| nebius | ||
| neosantara | ||
| nimble | ||
| nlp_cloud | ||
| novita | ||
| nscale | ||
| nvidia_nim | ||
| nvidia_riva | ||
| oci | ||
| ocr | ||
| ollama | ||
| oobabooga | ||
| openai | ||
| openai_like | ||
| opencode | ||
| openrouter | ||
| opensandbox | ||
| ovhcloud | ||
| parallel_ai | ||
| parasail | ||
| pass_through | ||
| perplexity | ||
| pg_vector | ||
| pi | ||
| publicai | ||
| ragflow | ||
| recraft | ||
| reducto | ||
| replicate | ||
| runwayml | ||
| s3_vectors | ||
| sagemaker | ||
| sail | ||
| sambanova | ||
| sap | ||
| scaledown | ||
| scaleway | ||
| searchapi | ||
| searxng | ||
| serper | ||
| snowflake | ||
| soniox | ||
| stability | ||
| strands_decider | ||
| tavily | ||
| tencent | ||
| tinyfish | ||
| together_ai | ||
| tool_loop | ||
| topaz | ||
| triton | ||
| v0 | ||
| valkey | ||
| vercel_ai_gateway | ||
| vertex_ai | ||
| vllm | ||
| volcengine | ||
| voyage | ||
| wandb | ||
| watsonx | ||
| xai | ||
| xinference | ||
| you_com | ||
| zai | ||
| __init__.py | ||
| test_cache_control_and_reasoning.py | ||
| test_custom_llm.py | ||
| test_file_content_block.py | ||
| test_file_search_responses.py | ||
| test_lifecycle_fix.py | ||
| test_oss_decision.py | ||
| test_polling_url_origin_match.py | ||
| test_predibase_transformation.py | ||