Lorenze Jay a1033e4bfe Fix structured output leaks in tool-calling loops (#5897) ...

* Fix structured output leaks in tool-calling loops

* addressing comments

* drop scripts

* Update Gemini agent tests to include structured output with thoughts and bump model version to 2.5-flash

* merge

* Update Anthropic test cases to use new model and tool structure

- Changed the model from "claude-3-5-haiku-20241022" to "claude-sonnet-4-6" in the test setup.
- Updated the request and response formats in the YAML test cassette to reflect the new tool structure and improved content formatting.
- Adjusted the expected response body to match the new output format from the assistant, including changes in tool usage and response details.
- Increased rate limit values in the response headers for better testing scenarios.

* adjusted bedrock cassettes

* adjusting cassettes for bedrock

* fix test

* Update VCR configuration to use 'host' instead of 'bedrock_host' for request matching

2026-05-27 13:20:53 -07:00

..

a2a

feat: add a2a update mechanisms (poll/stream/push) with handlers, config, and tests

2026-01-07 11:36:36 -05:00

agents

Fix structured output leaks in tool-calling loops (#5897)

2026-05-27 13:20:53 -07:00

events

feat: add event ordering and parent-child hierarchy

2026-01-21 11:12:10 -05:00

experimental/evaluation

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

hooks

Lorenze/feat/plan execute pattern (#4817)

2026-03-15 18:33:17 -07:00

knowledge

fix: ensure token usage recording, validate response model on stream

2025-12-10 20:32:10 -05:00

llms

Fix structured output leaks in tool-calling loops (#5897)

2026-05-27 13:20:53 -07:00

pipeline

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

rag/embeddings

New Unified Memory System (#4420)

2026-02-13 21:34:37 -03:00

telemetry

fix: ensure token usage recording, validate response model on stream

2025-12-10 20:32:10 -05:00

tools

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

tracing

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

utilities

feat: deprecate CrewAgentExecutor, default Crew agents to AgentExecutor (#5745)

2026-05-12 11:22:13 -07:00

test_after_crew_modification.yaml

fix: ensure token usage recording, validate response model on stream

2025-12-10 20:32:10 -05:00

test_after_kickoff_modification.yaml

fix: ensure token usage recording, validate response model on stream

2025-12-10 20:32:10 -05:00

test_agent_usage_metrics_are_captured_for_hierarchical_process.yaml

Lorenze/imp/native tool calling (#4258)

2026-01-22 17:44:03 -08:00

test_agents_do_not_get_delegation_tools_with_there_is_only_one_agent.yaml

Code interpreter sandbox escape (#4791)

2026-03-15 13:18:02 +08:00

test_anthropic_function_calling.yaml

fix: ensure token usage recording, validate response model on stream

2025-12-10 20:32:10 -05:00

test_anthropic_thinking_blocks_preserved_across_turns.yaml

fix: ensure token usage recording, validate response model on stream

2025-12-10 20:32:10 -05:00

test_anthropic_thinking.yaml

fix: ensure token usage recording, validate response model on stream

2025-12-10 20:32:10 -05:00

test_api_calls_throttling.yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

test_before_crew_modification.yaml

fix: ensure token usage recording, validate response model on stream

2025-12-10 20:32:10 -05:00

test_before_crew_with_none_input.yaml

fix: ensure token usage recording, validate response model on stream

2025-12-10 20:32:10 -05:00

test_before_kickoff_callback.yaml

Code interpreter sandbox escape (#4791)

2026-03-15 13:18:02 +08:00

test_before_kickoff_modification.yaml

fix: ensure token usage recording, validate response model on stream

2025-12-10 20:32:10 -05:00

test_before_kickoff_with_none_input.yaml

fix: ensure token usage recording, validate response model on stream

2025-12-10 20:32:10 -05:00

test_before_kickoff_without_inputs.yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

test_cache_hitting_between_agents.yaml

Lorenze/imp/native tool calling (#4258)

2026-01-22 17:44:03 -08:00

test_conditional_task_last_task_when_conditional_is_false.yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

test_conditional_task_last_task_when_conditional_is_true.yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

test_conditional_tasks_result_collection.yaml

Lorenze/feat/plan execute pattern (#4817)

2026-03-15 18:33:17 -07:00

test_crew_creation.yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

test_crew_does_not_interpolate_without_inputs.yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

test_crew_function_calling_llm.yaml

Lorenze/imp/native tool calling (#4258)

2026-01-22 17:44:03 -08:00

test_crew_kickoff_streaming_usage_metrics.yaml

Release/v1.0.0 (#3618)

2025-10-20 14:10:19 -07:00

test_crew_kickoff_usage_metrics.yaml

ci: add slack notification on successful pypi publish

2026-03-13 12:05:52 -04:00

test_crew_log_file_output.yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

test_crew_output_file_end_to_end.yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

test_crew_testing_function.yaml

fix: propagate contextvars across all thread and executor boundaries

2026-03-13 00:32:22 -04:00

test_crew_train_success.yaml

fix: ensure token usage recording, validate response model on stream

2025-12-10 20:32:10 -05:00

test_crew_verbose_output.yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

test_crew_with_delegating_agents_should_not_override_agent_tools.yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

test_crew_with_delegating_agents_should_not_override_task_tools.yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

test_crew_with_delegating_agents.yaml

Code interpreter sandbox escape (#4791)

2026-03-15 13:18:02 +08:00

test_crew_with_failing_task_guardrails.yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

test_crew_with_knowledge_sources_works_with_copy.yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

test_custom_converter_cls.yaml

fix: map output_pydantic/output_json to native structured output

2026-02-25 17:13:34 -05:00

test_custom_llm_implementation.yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

test_custom_llm_within_crew.yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

test_deepseek_r1_with_open_router.yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

test_delegation_is_not_enabled_if_there_are_only_one_agent.yaml

fix: propagate contextvars across all thread and executor boundaries

2026-03-13 00:32:22 -04:00

test_disabled_memory.yaml

New Unified Memory System (#4420)

2026-02-13 21:34:37 -03:00

test_gemini_models[gemini-gemini-2.0-flash-001].yaml

fix: ensure token usage recording, validate response model on stream

2025-12-10 20:32:10 -05:00

test_gemini_models[gemini-gemini-2.0-flash-lite-001].yaml

fix: ensure token usage recording, validate response model on stream

2025-12-10 20:32:10 -05:00

test_gemini_models[gemini-gemini-2.0-flash-thinking-exp-01-21].yaml

fix: ensure token usage recording, validate response model on stream

2025-12-10 20:32:10 -05:00

test_gemini_models[gemini-gemini-3-pro-preview].yaml

fix: ensure token usage recording, validate response model on stream

2025-12-10 20:32:10 -05:00

test_gemma3[gemini-gemma-3-27b-it].yaml

fix: ensure token usage recording, validate response model on stream

2025-12-10 20:32:10 -05:00

test_gpt_4_1[gpt-4.1-mini-2025-04-14].yaml

fix: ensure token usage recording, validate response model on stream

2025-12-10 20:32:10 -05:00

test_gpt_4_1[gpt-4.1-nano-2025-04-14].yaml

fix: ensure token usage recording, validate response model on stream

2025-12-10 20:32:10 -05:00

test_gpt_4_1[gpt-4.1].yaml

fix: ensure token usage recording, validate response model on stream

2025-12-10 20:32:10 -05:00

test_guardrail_emits_events.yaml

fix: map output_pydantic/output_json to native structured output

2026-02-25 17:13:34 -05:00

test_guardrail_when_an_error_occurs.yaml

fix: map output_pydantic/output_json to native structured output

2026-02-25 17:13:34 -05:00

test_handle_context_length_exceeds_limit.yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

test_handle_streaming_tool_calls_no_available_functions.yaml

Release/v1.0.0 (#3618)

2025-10-20 14:10:19 -07:00

test_handle_streaming_tool_calls_no_tools.yaml

Release/v1.0.0 (#3618)

2025-10-20 14:10:19 -07:00

test_handle_streaming_tool_calls_with_error.yaml

Release/v1.0.0 (#3618)

2025-10-20 14:10:19 -07:00

test_handle_streaming_tool_calls.yaml

Release/v1.0.0 (#3618)

2025-10-20 14:10:19 -07:00

test_hierarchical_crew_creation_tasks_with_agents.yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

test_hierarchical_crew_creation_tasks_with_async_execution.yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

test_hierarchical_crew_creation_tasks_with_sync_last.yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

test_hierarchical_process.yaml

fix: propagate contextvars across all thread and executor boundaries

2026-03-13 00:32:22 -04:00

test_hierarchical_verbose_false_manager_agent.yaml

test: re-record hierarchical verbose manager cassette

2026-04-11 02:35:00 +08:00

test_hierarchical_verbose_manager_agent.yaml

ci: add slack notification on successful pypi publish

2026-03-13 12:05:52 -04:00

test_increment_delegations_for_hierarchical_process.yaml

Lorenze/imp/native tool calling (#4258)

2026-01-22 17:44:03 -08:00

test_increment_delegations_for_sequential_process.yaml

Lorenze/imp/native tool calling (#4258)

2026-01-22 17:44:03 -08:00

test_increment_tool_errors.yaml

Lorenze/imp/native tool calling (#4258)

2026-01-22 17:44:03 -08:00

test_inject_date_custom_format.yaml

fix: ensure token usage recording, validate response model on stream

2025-12-10 20:32:10 -05:00

test_inject_date.yaml

fix: ensure token usage recording, validate response model on stream

2025-12-10 20:32:10 -05:00

test_json_property_without_output_json.yaml

fix: map output_pydantic/output_json to native structured output

2026-02-25 17:13:34 -05:00

test_kickoff_for_each_error_handling.yaml

Release/v1.0.0 (#3618)

2025-10-20 14:10:19 -07:00

test_kickoff_for_each_multiple_inputs.yaml

fix: ensure token usage recording, validate response model on stream

2025-12-10 20:32:10 -05:00

test_kickoff_for_each_single_input.yaml

fix: ensure token usage recording, validate response model on stream

2025-12-10 20:32:10 -05:00

test_litellm_auth_error_handling.yaml

fix: ensure token usage recording, validate response model on stream

2025-12-10 20:32:10 -05:00

test_litellm_gpt5_call_succeeds_without_stop_error.yaml

fix: handle GPT-5.x models not supporting the stop API parameter (#5144)

2026-03-30 11:36:51 -04:00

test_llm_call_when_stop_is_unsupported_when_additional_drop_params_is_provided.yaml

fix: ensure token usage recording, validate response model on stream

2025-12-10 20:32:10 -05:00

test_llm_call_when_stop_is_unsupported.yaml

fix: ensure token usage recording, validate response model on stream

2025-12-10 20:32:10 -05:00

test_llm_call_with_error.yaml

fix: ensure token usage recording, validate response model on stream

2025-12-10 20:32:10 -05:00

test_llm_call_with_message_list.yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

test_llm_call_with_string_input_and_callbacks.yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

test_llm_call_with_string_input.yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

test_llm_call_with_tool_and_message_list.yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

test_llm_call_with_tool_and_string_input.yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

test_llm_callback_replacement.yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

test_llm_passes_additional_params.yaml

fix: ensure token usage recording, validate response model on stream

2025-12-10 20:32:10 -05:00

test_manager_agent_delegating_to_all_agents.yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

test_manager_agent_delegating_to_assigned_task_agent.yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

test_manager_agent_with_tools_raises_exception.yaml

tests: cassettes, threading for flow tests

2025-10-21 13:48:21 -04:00

test_manager_agent.yaml

tests: cassettes, threading for flow tests

2025-10-21 13:48:21 -04:00

test_memory_enabled_creates_unified_memory.yaml

fix: propagate contextvars across all thread and executor boundaries

2026-03-13 00:32:22 -04:00

test_memory_events_are_emitted.yaml

fix: ensure token usage recording, validate response model on stream

2025-12-10 20:32:10 -05:00

test_memory_remember_called_after_task.yaml

Code interpreter sandbox escape (#4791)

2026-03-15 13:18:02 +08:00

test_memory_remember_receives_task_content.yaml

New Unified Memory System (#4420)

2026-02-13 21:34:37 -03:00

test_multimodal_agent_describing_image_successfully.yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

test_multimodal_agent_live_image_analysis.yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

test_multiple_before_after_crew.yaml

fix: ensure token usage recording, validate response model on stream

2025-12-10 20:32:10 -05:00

test_multiple_before_after_kickoff.yaml

Lorenze/feat/plan execute pattern (#4817)

2026-03-15 18:33:17 -07:00

test_no_inject_date.yaml

fix: ensure token usage recording, validate response model on stream

2025-12-10 20:32:10 -05:00

test_o3_mini_reasoning_effort_high.yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

test_o3_mini_reasoning_effort_low.yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

test_o3_mini_reasoning_effort_medium.yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

test_output_json_dict_hierarchical.yaml

fix: map output_pydantic/output_json to native structured output

2026-02-25 17:13:34 -05:00

test_output_json_dict_sequential.yaml

fix: map output_pydantic/output_json to native structured output

2026-02-25 17:13:34 -05:00

test_output_json_hierarchical.yaml

fix: map output_pydantic/output_json to native structured output

2026-02-25 17:13:34 -05:00

test_output_json_sequential.yaml

fix: map output_pydantic/output_json to native structured output

2026-02-25 17:13:34 -05:00

test_output_json_to_another_task.yaml

fix: map output_pydantic/output_json to native structured output

2026-02-25 17:13:34 -05:00

test_output_pydantic_hierarchical.yaml

fix: map output_pydantic/output_json to native structured output

2026-02-25 17:13:34 -05:00

test_output_pydantic_sequential.yaml

fix: map output_pydantic/output_json to native structured output

2026-02-25 17:13:34 -05:00

test_output_pydantic_to_another_task.yaml

fix: map output_pydantic/output_json to native structured output

2026-02-25 17:13:34 -05:00

test_replay_interpolates_inputs_properly.yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

test_replay_setup_context.yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

test_replay_with_context_set_to_nullable.yaml

tests: cassettes, threading for flow tests

2025-10-21 13:48:21 -04:00

test_replay_with_context.yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

test_save_task_json_output.yaml

fix: map output_pydantic/output_json to native structured output

2026-02-25 17:13:34 -05:00

test_save_task_output.yaml

fix: map output_pydantic/output_json to native structured output

2026-02-25 17:13:34 -05:00

test_save_task_pydantic_output.yaml

fix: map output_pydantic/output_json to native structured output

2026-02-25 17:13:34 -05:00

test_sequential_async_task_execution_completion.yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

test_sets_flow_context_when_inside_flow.yaml

fix: use contextvars for flow execution context

2026-02-02 11:24:02 -05:00

test_single_task_with_async_execution.yaml

fix: propagate contextvars across all thread and executor boundaries

2026-03-13 00:32:22 -04:00

test_sync_task_execution.yaml

Lorenze/feat/plan execute pattern (#4817)

2026-03-15 18:33:17 -07:00

test_task_execution_times.yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

test_task_guardrail_process_output.yaml

fix: map output_pydantic/output_json to native structured output

2026-02-25 17:13:34 -05:00

test_task_interpolation_with_hyphens.yaml

fix: ensure token usage recording, validate response model on stream

2025-12-10 20:32:10 -05:00

test_task_output_includes_messages.yaml

fix: ensure token usage recording, validate response model on stream

2025-12-10 20:32:10 -05:00

test_task_tools_override_agent_tools.yaml

Code interpreter sandbox escape (#4791)

2026-03-15 13:18:02 +08:00

test_task_tools_preserve_code_execution_tools.yaml

tests: cassettes, threading for flow tests

2025-10-21 13:48:21 -04:00

test_task_with_max_execution_time_exceeded.yaml

Lorenze/imp/native tool calling (#4258)

2026-01-22 17:44:03 -08:00

test_task_with_max_execution_time.yaml

Lorenze/imp/native tool calling (#4258)

2026-01-22 17:44:03 -08:00

test_task_with_no_arguments.yaml

Lorenze/imp/native tool calling (#4258)

2026-01-22 17:44:03 -08:00

test_tools_with_custom_caching.yaml

Lorenze/imp/native tool calling (#4258)

2026-01-22 17:44:03 -08:00

test_usage_info_non_streaming_with_acall_and_stop.yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

test_usage_info_non_streaming_with_acall.yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

test_usage_info_non_streaming_with_call.yaml

Adding usage info in llm.py (#4172)

2026-01-07 10:42:27 -08:00

test_usage_info_streaming_with_acall.yaml

Adding usage info in llm.py (#4172)

2026-01-07 10:42:27 -08:00

test_usage_info_streaming_with_call.yaml

Adding usage info in llm.py (#4172)

2026-01-07 10:42:27 -08:00

test_using_memory_recall_and_save.yaml

Code interpreter sandbox escape (#4791)

2026-03-15 13:18:02 +08:00

test_using_memory_with_remember.yaml

New Unified Memory System (#4420)

2026-02-13 21:34:37 -03:00

test_using_memory.yaml

New Unified Memory System (#4420)

2026-02-13 21:34:37 -03:00

TestAgentMultimodalAnthropic.test_image_file[anthropic-claude-3-5-haiku-20241022].yaml

Lorenze/feat/plan execute pattern (#4817)

2026-03-15 18:33:17 -07:00

TestAgentMultimodalAnthropic.test_mixed_files[anthropic-claude-3-5-haiku-20241022].yaml

Lorenze/feat/plan execute pattern (#4817)

2026-03-15 18:33:17 -07:00

TestAgentMultimodalAnthropic.test_pdf_file[anthropic-claude-3-5-haiku-20241022].yaml

Lorenze/feat/plan execute pattern (#4817)

2026-03-15 18:33:17 -07:00

TestAgentMultimodalAsync.test_async_agent_with_image.yaml

Lorenze/feat/plan execute pattern (#4817)

2026-03-15 18:33:17 -07:00

TestAgentMultimodalFileTypes.test_audio_gemini.yaml

Lorenze/feat/plan execute pattern (#4817)

2026-03-15 18:33:17 -07:00

TestAgentMultimodalFileTypes.test_image_openai.yaml

Lorenze/feat/plan execute pattern (#4817)

2026-03-15 18:33:17 -07:00

TestAgentMultimodalFileTypes.test_pdf_anthropic.yaml

Lorenze/feat/plan execute pattern (#4817)

2026-03-15 18:33:17 -07:00

TestAgentMultimodalFileTypes.test_pdf_openai_responses.yaml

Lorenze/feat/plan execute pattern (#4817)

2026-03-15 18:33:17 -07:00

TestAgentMultimodalFileTypes.test_text_gemini.yaml

Lorenze/feat/plan execute pattern (#4817)

2026-03-15 18:33:17 -07:00

TestAgentMultimodalFileTypes.test_video_gemini.yaml

Lorenze/feat/plan execute pattern (#4817)

2026-03-15 18:33:17 -07:00

TestAgentMultimodalGemini.test_audio_file[gemini-gemini-2.0-flash].yaml

Lorenze/feat/plan execute pattern (#4817)

2026-03-15 18:33:17 -07:00

TestAgentMultimodalGemini.test_audio_file[gemini-gemini-2.5-flash].yaml

Lorenze/feat/plan execute pattern (#4817)

2026-03-15 18:33:17 -07:00

TestAgentMultimodalGemini.test_image_file[gemini-gemini-2.0-flash].yaml

Lorenze/feat/plan execute pattern (#4817)

2026-03-15 18:33:17 -07:00

TestAgentMultimodalGemini.test_image_file[gemini-gemini-2.5-flash].yaml

Lorenze/feat/plan execute pattern (#4817)

2026-03-15 18:33:17 -07:00

TestAgentMultimodalGemini.test_mixed_files[gemini-gemini-2.0-flash].yaml

Lorenze/feat/plan execute pattern (#4817)

2026-03-15 18:33:17 -07:00

TestAgentMultimodalGemini.test_mixed_files[gemini-gemini-2.5-flash].yaml

Lorenze/feat/plan execute pattern (#4817)

2026-03-15 18:33:17 -07:00

TestAgentMultimodalGemini.test_text_file[gemini-gemini-2.0-flash].yaml

Lorenze/feat/plan execute pattern (#4817)

2026-03-15 18:33:17 -07:00

TestAgentMultimodalGemini.test_text_file[gemini-gemini-2.5-flash].yaml

Lorenze/feat/plan execute pattern (#4817)

2026-03-15 18:33:17 -07:00

TestAgentMultimodalGemini.test_video_file[gemini-gemini-2.0-flash].yaml

Lorenze/feat/plan execute pattern (#4817)

2026-03-15 18:33:17 -07:00

TestAgentMultimodalGemini.test_video_file[gemini-gemini-2.5-flash].yaml

Lorenze/feat/plan execute pattern (#4817)

2026-03-15 18:33:17 -07:00

TestAgentMultimodalOpenAI.test_generic_file_image[openai-gpt-4o-mini].yaml

Lorenze/feat/plan execute pattern (#4817)

2026-03-15 18:33:17 -07:00

TestAgentMultimodalOpenAI.test_generic_file_image[openai-gpt-4o].yaml

Lorenze/feat/plan execute pattern (#4817)

2026-03-15 18:33:17 -07:00

TestAgentMultimodalOpenAI.test_generic_file_image[openai-o4-mini].yaml

Lorenze/feat/plan execute pattern (#4817)

2026-03-15 18:33:17 -07:00

TestAgentMultimodalOpenAI.test_image_bytes[openai-gpt-4o-mini].yaml

Lorenze/feat/plan execute pattern (#4817)

2026-03-15 18:33:17 -07:00

TestAgentMultimodalOpenAI.test_image_bytes[openai-gpt-4o].yaml

Lorenze/feat/plan execute pattern (#4817)

2026-03-15 18:33:17 -07:00

TestAgentMultimodalOpenAI.test_image_bytes[openai-o4-mini].yaml

Lorenze/feat/plan execute pattern (#4817)

2026-03-15 18:33:17 -07:00

TestAgentMultimodalOpenAI.test_image_file[openai-gpt-4o-mini].yaml

Lorenze/feat/plan execute pattern (#4817)

2026-03-15 18:33:17 -07:00

TestAgentMultimodalOpenAI.test_image_file[openai-gpt-4o].yaml

Lorenze/feat/plan execute pattern (#4817)

2026-03-15 18:33:17 -07:00

TestAgentMultimodalOpenAI.test_image_file[openai-o4-mini].yaml

Lorenze/feat/plan execute pattern (#4817)

2026-03-15 18:33:17 -07:00

TestAgentMultimodalOpenAIResponses.test_image_file[openai-gpt-4o-mini-responses].yaml

Lorenze/feat/plan execute pattern (#4817)

2026-03-15 18:33:17 -07:00

TestAgentMultimodalOpenAIResponses.test_image_file[openai-o4-mini-responses].yaml

Lorenze/feat/plan execute pattern (#4817)

2026-03-15 18:33:17 -07:00

TestAgentMultimodalOpenAIResponses.test_pdf_file[openai-gpt-4o-mini-responses].yaml

Lorenze/feat/plan execute pattern (#4817)

2026-03-15 18:33:17 -07:00

TestAgentMultimodalOpenAIResponses.test_pdf_file[openai-o4-mini-responses].yaml

Lorenze/feat/plan execute pattern (#4817)

2026-03-15 18:33:17 -07:00

TestCrewMultimodalAnthropic.test_image_file[anthropic-claude-3-5-haiku-20241022].yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

TestCrewMultimodalAnthropic.test_image_file[anthropic-claude-sonnet-4-20250514].yaml

feat: deprecate CrewAgentExecutor, default Crew agents to AgentExecutor (#5745)

2026-05-12 11:22:13 -07:00

TestCrewMultimodalAnthropic.test_mixed_files[anthropic-claude-3-5-haiku-20241022].yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

TestCrewMultimodalAnthropic.test_mixed_files[anthropic-claude-sonnet-4-20250514].yaml

feat: deprecate CrewAgentExecutor, default Crew agents to AgentExecutor (#5745)

2026-05-12 11:22:13 -07:00

TestCrewMultimodalAnthropic.test_pdf_file[anthropic-claude-3-5-haiku-20241022].yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

TestCrewMultimodalAnthropic.test_pdf_file[anthropic-claude-sonnet-4-20250514].yaml

feat: deprecate CrewAgentExecutor, default Crew agents to AgentExecutor (#5745)

2026-05-12 11:22:13 -07:00

TestCrewMultimodalBedrock.test_image_file[bedrock-us.anthropic.claude-sonnet-4-6].yaml

Fix structured output leaks in tool-calling loops (#5897)

2026-05-27 13:20:53 -07:00

TestCrewMultimodalBedrock.test_pdf_file[bedrock-us.anthropic.claude-sonnet-4-6].yaml

Fix structured output leaks in tool-calling loops (#5897)

2026-05-27 13:20:53 -07:00

TestCrewMultimodalFileTypes.test_audio_gemini.yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

TestCrewMultimodalFileTypes.test_image_openai.yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

TestCrewMultimodalFileTypes.test_pdf_anthropic.yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

TestCrewMultimodalFileTypes.test_pdf_openai_responses.yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

TestCrewMultimodalFileTypes.test_text_gemini.yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

TestCrewMultimodalFileTypes.test_video_gemini.yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

TestCrewMultimodalFileUpload.test_image_upload_anthropic.yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

TestCrewMultimodalFileUpload.test_image_upload_openai_responses.yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

TestCrewMultimodalFileUpload.test_pdf_upload_anthropic.yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

TestCrewMultimodalGemini.test_audio_file[gemini-gemini-2.0-flash].yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

TestCrewMultimodalGemini.test_image_file[gemini-gemini-1.5-flash].yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

TestCrewMultimodalGemini.test_image_file[gemini-gemini-2.0-flash].yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

TestCrewMultimodalGemini.test_mixed_files[gemini-gemini-2.0-flash].yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

TestCrewMultimodalGemini.test_text_file[gemini-gemini-2.0-flash].yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

TestCrewMultimodalGemini.test_video_file[gemini-gemini-2.0-flash].yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

TestCrewMultimodalOpenAI.test_generic_file_image[openai-gpt-4.1-mini].yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

TestCrewMultimodalOpenAI.test_generic_file_image[openai-gpt-4o-mini].yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

TestCrewMultimodalOpenAI.test_generic_file_image[openai-gpt-4o].yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

TestCrewMultimodalOpenAI.test_generic_file_image[openai-o4-mini].yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

TestCrewMultimodalOpenAI.test_image_bytes[openai-gpt-4.1-mini].yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

TestCrewMultimodalOpenAI.test_image_bytes[openai-gpt-4o-mini].yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

TestCrewMultimodalOpenAI.test_image_bytes[openai-gpt-4o].yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

TestCrewMultimodalOpenAI.test_image_bytes[openai-o4-mini].yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

TestCrewMultimodalOpenAI.test_image_file[openai-gpt-4.1-mini].yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

TestCrewMultimodalOpenAI.test_image_file[openai-gpt-4o-mini].yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

TestCrewMultimodalOpenAI.test_image_file[openai-gpt-4o].yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

TestCrewMultimodalOpenAI.test_image_file[openai-o4-mini].yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

TestCrewMultimodalOpenAIResponses.test_image_file[openai-gpt-4o-mini-responses].yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

TestCrewMultimodalOpenAIResponses.test_image_file[openai-o4-mini-responses].yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

TestCrewMultimodalOpenAIResponses.test_pdf_file[openai-gpt-4o-mini-responses].yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

TestCrewMultimodalOpenAIResponses.test_pdf_file[openai-o4-mini-responses].yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

TestCrewMultimodalUnsupportedTypes.test_audio_with_anthropic_uses_tool.yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

TestCrewMultimodalUnsupportedTypes.test_video_with_openai_uses_tool.yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

TestFlowMultimodalAnthropic.test_flow_with_image_file.yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

TestFlowMultimodalAnthropic.test_flow_with_pdf_file.yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

TestFlowMultimodalAsync.test_async_flow_with_image.yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

TestFlowMultimodalGemini.test_flow_with_audio_file.yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

TestFlowMultimodalGemini.test_flow_with_image_file.yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

TestFlowMultimodalGemini.test_flow_with_text_file.yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

TestFlowMultimodalGemini.test_flow_with_video_file.yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

TestFlowMultimodalMultiStep.test_flow_with_mixed_files.yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

TestFlowMultimodalMultiStep.test_flow_with_multiple_crews.yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

TestFlowMultimodalOpenAI.test_flow_with_image_bytes.yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

TestFlowMultimodalOpenAI.test_flow_with_image_file.yaml

feat: native multimodal file handling; openai responses api

2026-01-23 15:13:25 -05:00

TestLLMHooksIntegration.test_direct_llm_call_hooks_integration.yaml

fix: ensure token usage recording, validate response model on stream

2025-12-10 20:32:10 -05:00

TestLLMHooksIntegration.test_lite_agent_hooks_integration_with_real_llm.yaml

fix: ensure token usage recording, validate response model on stream

2025-12-10 20:32:10 -05:00

TestStreamingCrewIntegration.test_async_streaming_from_docs.yaml

feat: add streaming result support to flows and crews

2025-11-24 15:43:48 -05:00

TestStreamingCrewIntegration.test_basic_crew_streaming_from_docs.yaml

feat: add streaming result support to flows and crews

2025-11-24 15:43:48 -05:00

TestStreamingCrewIntegration.test_kickoff_for_each_streaming_from_docs.yaml

feat: add streaming result support to flows and crews

2025-11-24 15:43:48 -05:00

TestStreamingCrewIntegration.test_streaming_properties_from_docs.yaml

feat: add streaming result support to flows and crews

2025-11-24 15:43:48 -05:00

TestStreamingCrewIntegration.test_streaming_with_chunk_context_from_docs.yaml

feat: add streaming result support to flows and crews

2025-11-24 15:43:48 -05:00

TestStreamingFlowIntegration.test_async_flow_streaming_from_docs.yaml

feat: add streaming result support to flows and crews

2025-11-24 15:43:48 -05:00

TestStreamingFlowIntegration.test_basic_flow_streaming_from_docs.yaml

feat: add streaming result support to flows and crews

2025-11-24 15:43:48 -05:00