openai-agents-python/tests/models
Kazuhiro Sera d5287b741d
fix: align model defaults with TS SDK (#6064)
* Align GPT-5 and newer model defaults with TypeScript

* Preserve explicit request settings when applying model defaults
2026-11-17 21:40:15 +00:00
..
__init__.py Docs and tests for litellm (#561) 2025-04-21 16:59:01 -04:00
test_agent_registration.py feat: consistently accept typed objects and dictionaries for SDK configuration (#3917) 2026-07-24 08:04:45 +09:00
test_anthropic_thinking_blocks.py fix(extensions): preserve thinking blocks for replay (#4157) 2026-08-04 00:13:13 +00:00
test_any_llm_model.py fix: align model defaults with TS SDK (#6064) 2026-11-17 21:40:15 +00:00
test_chatcompletions_stream_eof.py fix: reject premature Chat Completions stream EOF (#5211) 2026-09-27 22:37:02 -07:00
test_deepseek_reasoning_content.py fix: #2155 DeepSeek reasoning_content missing in tool call messages (#2328) 2026-01-19 10:25:44 +09:00
test_default_models.py fix: align model defaults with TS SDK (#6064) 2026-11-17 21:40:15 +00:00
test_extended_thinking_message_order.py fix(litellm): avoid duplicating content and signed thinking blocks across parallel tool-call splits (#3215) 2026-05-09 12:52:11 +09:00
test_gemini_thought_signatures.py test: improve coverage and organize test layout (#3085) 2026-05-02 15:40:54 +09:00
test_gemini_thought_signatures_stream.py test: improve coverage and organize test layout (#3085) 2026-05-02 15:40:54 +09:00
test_generation_metadata.py fix(core/extensions): respect sensitive trace capture for model metadata (#5129) 2026-09-21 13:59:06 +09:00
test_gpt6_chat_tool_defaults.py fix: align model defaults with TS SDK (#6064) 2026-11-17 21:40:15 +00:00
test_kwargs_functionality.py fix: trace offered tools on Chat Completions generation spans (#5635) 2026-11-09 06:05:37 +00:00
test_litellm_chatcompletions_stream.py fix(deps): bump openai from 3.29.0 to 3.48.0 (#6054) 2026-11-17 06:58:58 -08:00
test_litellm_content_filter.py fix(litellm): surface content-filter refusals instead of an empty turn (#3769) 2026-07-11 00:52:45 +00:00
test_litellm_extra_body.py fix: align model defaults with TS SDK (#6064) 2026-11-17 21:40:15 +00:00
test_litellm_logging_patch.py fix: #2291 silence LiteLLM serializer warnings in streaming (opt-in) (#2295) 2026-01-12 10:26:12 +09:00
test_litellm_logprobs.py feat(models): preserve raw usage payloads (#4279) 2026-08-07 19:24:39 +09:00
test_litellm_usage_requests.py fix: normalize nullable token counts in remaining provider paths (#5260) 2026-09-30 14:58:23 -07:00
test_litellm_user_agent.py Allow headers override instead of just ua (#1787) 2025-09-23 10:50:02 -04:00
test_map.py fix(core): close all MultiProvider children after failures (#4438) 2026-08-16 07:58:08 +09:00
test_model_payload_iterators.py test: improve coverage and organize test layout (#3085) 2026-05-02 15:40:54 +09:00
test_model_retry.py fix: preserve usage from failed and incomplete Responses calls (#6046) 2026-11-16 22:46:54 +00:00
test_openai_chatcompletions.py fix: trace offered tools on Chat Completions generation spans (#5635) 2026-11-09 06:05:37 +00:00
test_openai_chatcompletions_converter.py fix: replay ID-less assistant output in Chat Completions sessions (#5419) 2026-10-26 21:43:43 +00:00
test_openai_chatcompletions_stream.py fix(deps): bump openai from 3.29.0 to 3.48.0 (#6054) 2026-11-17 06:58:58 -08:00
test_openai_client_utils.py test: improve coverage and organize test layout (#3085) 2026-05-02 15:40:54 +09:00
test_openai_responses.py fix: align model defaults with TS SDK (#6064) 2026-11-17 21:40:15 +00:00
test_openai_responses_converter.py fix(core): select built-in shell and apply_patch tools by their own type (#4952) 2026-09-25 14:44:41 -07:00
test_openai_retry_helpers.py feat: support OpenAI Python 3 and HTTPX2 (#4380) 2026-08-13 12:09:43 +09:00
test_reasoning_content.py fix: reject premature Chat Completions stream EOF (#5211) 2026-09-27 22:37:02 -07:00
test_reasoning_content_replay_hook.py feat: #2669 add opt-in reasoning content replay for chat completion models (#2670) 2026-03-20 16:20:36 +09:00
test_remove_openai_responses_api_incompatible_fields.py fix(models): strip placeholder item IDs without provider_data on the Responses path (#4266) 2026-08-07 16:32:23 +09:00
test_responses_stream_diagnostics.py fix: improve missing stream completion diagnostics (#5457) 2026-10-30 20:13:59 +00:00
test_responses_websocket_session.py feat: consistently accept typed objects and dictionaries for SDK configuration (#3917) 2026-07-24 08:04:45 +09:00
test_trace_config.py fix(core/extensions): respect sensitive trace capture for model metadata (#5129) 2026-09-21 13:59:06 +09:00