adafac1117
These params were silently dropped for Chat Completions because they were missing from the supported params whitelist. Also adds prompt_cache_retention to the Responses API TypedDict and fixes misleading cache_control comments in OpenAI prompt caching docs. |
||
|---|---|---|
| .. | ||
| audio.md | ||
| batching.md | ||
| computer_use.md | ||
| document_understanding.md | ||
| drop_params.md | ||
| function_call.md | ||
| http_handler_config.md | ||
| image_generation_chat.md | ||
| input.md | ||
| json_mode.md | ||
| knowledgebase.md | ||
| message_sanitization.md | ||
| message_trimming.md | ||
| mock_requests.md | ||
| model_alias.md | ||
| multiple_deployments.md | ||
| output.md | ||
| predict_outputs.md | ||
| prefix.md | ||
| prompt_caching.md | ||
| prompt_formatting.md | ||
| provider_specific_params.md | ||
| reliable_completions.md | ||
| shared_session.md | ||
| stream.md | ||
| token_usage.md | ||
| usage.md | ||
| vision.md | ||
| web_fetch.md | ||
| web_search.md | ||