Lorenze Jay 75b916c85a Lorenze/fix tool call twice (#3495) ...

* test: add test to ensure tool is called only once during crew execution

- Introduced a new test case to validate that the counting_tool is executed exactly once during crew execution.
- Created a CountingTool class to track execution counts and log call history.
- Enhanced the test suite with a YAML cassette for consistent tool behavior verification.

* ensure tool function called only once

* refactor: simplify error handling in CrewStructuredTool

- Removed unnecessary try-except block around the tool function call to streamline execution flow.
- Ensured that the tool function is called directly, improving readability and maintainability.

* linted

* need to ignore for now as we cant infer the complex generic type within pydantic create_model_func

* fix tests

2025-09-10 15:20:21 -07:00

..

test_after_crew_modification.yaml

adding before and after crew

2024-11-18 00:21:36 -03:00

test_after_kickoff_modification.yaml

feat: add official way to use MCP Tools within a CrewBase (#3058)

2025-06-24 15:14:59 -04:00

test_agent_custom_max_iterations.yaml

Feat/individual react agent (#2483)

2025-04-02 08:54:46 -07:00

test_agent_error_on_parsing_tool.yaml

Feat/individual react agent (#2483)

2025-04-02 08:54:46 -07:00

test_agent_execute_task_basic.yaml

drop litellm version to prevent windows issue (#1878)

2025-01-14 13:06:47 -05:00

test_agent_execute_task_with_context.yaml

Bringing support to o1 family back + any models that don't support stop words

2024-09-24 22:18:20 -03:00

test_agent_execute_task_with_custom_llm.yaml

Bringing support to o1 family back + any models that don't support stop words

2024-09-24 22:18:20 -03:00

test_agent_execute_task_with_ollama.yaml

drop litellm version to prevent windows issue (#1878)

2025-01-14 13:06:47 -05:00

test_agent_execute_task_with_tool.yaml

Brandon/eng 266 conversation crew v1 (#1843)

2025-01-06 16:12:43 -05:00

test_agent_execution_with_specific_tools.yaml

Bringing support to o1 family back + any models that don't support stop words

2024-09-24 22:18:20 -03:00

test_agent_execution_with_tools.yaml

Bringing support to o1 family back + any models that don't support stop words

2024-09-24 22:18:20 -03:00

test_agent_execution.yaml

Bringing support to o1 family back + any models that don't support stop words

2024-09-24 22:18:20 -03:00

test_agent_function_calling_llm.yaml

Feat/individual react agent (#2483)

2025-04-02 08:54:46 -07:00

test_agent_knowledege_with_crewai_knowledge.yaml

Fix agent knowledge (#2831)

2025-07-11 13:52:26 -04:00

test_agent_moved_on_after_max_iterations.yaml

Feat/individual react agent (#2483)

2025-04-02 08:54:46 -07:00

test_agent_output_when_guardrail_returns_base_model.yaml

LiteAgent w/ Guardrail (#2982)

2025-06-10 13:32:32 -04:00

test_agent_powered_by_new_o_model_family_that_allows_skipping_tool.yaml

Feat/individual react agent (#2483)

2025-04-02 08:54:46 -07:00

test_agent_powered_by_new_o_model_family_that_uses_tool.yaml

Feat/individual react agent (#2483)

2025-04-02 08:54:46 -07:00

test_agent_remembers_output_format_after_using_tools_too_many_times.yaml

Bringing support to o1 family back + any models that don't support stop words

2024-09-24 22:18:20 -03:00

test_agent_repeated_tool_usage_check_even_with_disabled_cache.yaml

Feat/individual react agent (#2483)

2025-04-02 08:54:46 -07:00

test_agent_repeated_tool_usage.yaml

Feat/individual react agent (#2483)

2025-04-02 08:54:46 -07:00

test_agent_respect_the_max_rpm_set_over_crew_rpm.yaml

Feat/individual react agent (#2483)

2025-04-02 08:54:46 -07:00

test_agent_respect_the_max_rpm_set.yaml

Feat/individual react agent (#2483)

2025-04-02 08:54:46 -07:00

test_agent_step_callback.yaml

Bringing support to o1 family back + any models that don't support stop words

2024-09-24 22:18:20 -03:00

test_agent_usage_metrics_are_captured_for_hierarchical_process.yaml

Lorenze/better tracing events (#3382)

2025-08-26 09:09:46 -07:00

test_agent_use_specific_tasks_output_as_context.yaml

Bringing support to o1 family back + any models that don't support stop words

2024-09-24 22:18:20 -03:00

test_agent_with_knowledge_sources_extensive_role.yaml

feat: implement knowledge retrieval events in Agent (#2727)

2025-05-07 11:55:42 -07:00

test_agent_with_knowledge_sources_generate_search_query.yaml

feat: implement knowledge retrieval events in Agent (#2727)

2025-05-07 11:55:42 -07:00

test_agent_with_knowledge_sources_with_query_limit_and_score_threshold_default.yaml

feat: implement knowledge retrieval events in Agent (#2727)

2025-05-07 11:55:42 -07:00

test_agent_with_knowledge_sources_with_query_limit_and_score_threshold.yaml

feat: implement knowledge retrieval events in Agent (#2727)

2025-05-07 11:55:42 -07:00

test_agent_with_knowledge_sources_works_with_copy.yaml

fix breakage when cloning agent/crew using knowledge_sources and enable custom knowledge_storage (#1927)

2025-01-29 09:37:22 -05:00

test_agent_with_knowledge_sources.yaml

feat: implement knowledge retrieval events in Agent (#2727)

2025-05-07 11:55:42 -07:00

test_agent_with_knowledge_with_no_crewai_knowledge.yaml

Fix agent knowledge (#2831)

2025-07-11 13:52:26 -04:00

test_agent_with_ollama_llama3.yaml

drop litellm version to prevent windows issue (#1878)

2025-01-14 13:06:47 -05:00

test_agent_with_only_crewai_knowledge.yaml

Fix agent knowledge (#2831)

2025-07-11 13:52:26 -04:00

test_agent_without_max_rpm_respects_crew_rpm.yaml

Fixed core invoke loop logic and relevant tests (#1865)

2025-01-09 12:13:02 -05:00

test_agent_without_max_rpm_respet_crew_rpm.yaml

Bringing support to o1 family back + any models that don't support stop words

2024-09-24 22:18:20 -03:00

test_agents_do_not_get_delegation_tools_with_there_is_only_one_agent.yaml

Bringing support to o1 family back + any models that don't support stop words

2024-09-24 22:18:20 -03:00

test_api_calls_throttling.yaml

Bringing support to o1 family back + any models that don't support stop words

2024-09-24 22:18:20 -03:00

test_async_tool_using_decorator_within_flow.yaml

Support async tool executions (#2983)

2025-06-10 12:17:06 -04:00

test_async_tool_using_decorator_within_isolated_crew.yaml

Support async tool executions (#2983)

2025-06-10 12:17:06 -04:00

test_async_tool_using_within_isolated_crew.yaml

Support async tool executions (#2983)

2025-06-10 12:17:06 -04:00

test_async_tool_within_flow.yaml

Support async tool executions (#2983)

2025-06-10 12:17:06 -04:00

test_before_crew_modification.yaml

adding before and after crew

2024-11-18 00:21:36 -03:00

test_before_crew_with_none_input.yaml

adding before and after crew

2024-11-18 00:21:36 -03:00

test_before_kickoff_callback.yaml

fix: properly clone ConditionalTask instances

2025-03-25 16:05:06 -03:00

test_before_kickoff_modification.yaml

feat: enhance CrewBase MCP tools support to allow selecting multiple tools per agent (#3065)

2025-06-25 14:59:55 -04:00

test_before_kickoff_with_none_input.yaml

feat: enhance CrewBase MCP tools support to allow selecting multiple tools per agent (#3065)

2025-06-25 14:59:55 -04:00

test_before_kickoff_without_inputs.yaml

before kickoff breaks if inputs are none. (#1883)

2025-01-14 13:24:03 -05:00

test_cache_hitting_between_agents.yaml

Lorenze/new version 0.140.0 (#3106)

2025-07-02 15:22:18 -07:00

test_cache_hitting.yaml

Bringing support to o1 family back + any models that don't support stop words

2024-09-24 22:18:20 -03:00

test_conditional_task_last_task_when_conditional_is_false.yaml

Bringing support to o1 family back + any models that don't support stop words

2024-09-24 22:18:20 -03:00

test_conditional_task_last_task_when_conditional_is_true.yaml

Bringing support to o1 family back + any models that don't support stop words

2024-09-24 22:18:20 -03:00

test_crew_creation.yaml

Bringing support to o1 family back + any models that don't support stop words

2024-09-24 22:18:20 -03:00

test_crew_does_not_interpolate_without_inputs.yaml

Bringing support to o1 family back + any models that don't support stop words

2024-09-24 22:18:20 -03:00

test_crew_external_memory_save_using_crew_without_memory_flag[save].yaml

Introduce MemoryEvents to monitor their usage (#3098)

2025-07-01 22:50:39 -04:00

test_crew_external_memory_save_using_crew_without_memory_flag[search].yaml

Unblock LLM(stream=True) to work with tools (#2582)

2025-04-17 11:58:52 -04:00

test_crew_external_memory_save_with_memory_flag[save].yaml

Introduce MemoryEvents to monitor their usage (#3098)

2025-07-01 22:50:39 -04:00

test_crew_external_memory_save_with_memory_flag[search].yaml

Introduce MemoryEvents to monitor their usage (#3098)

2025-07-01 22:50:39 -04:00

test_crew_external_memory_save.yaml

Unblock LLM(stream=True) to work with tools (#2582)

2025-04-17 11:58:52 -04:00

test_crew_external_memory_search.yaml

Unblock LLM(stream=True) to work with tools (#2582)

2025-04-17 11:58:52 -04:00

test_crew_function_calling_llm.yaml

Brandon/eng 290 make tool inputs actual objects and not strings (#1868)

2025-01-10 17:16:46 -05:00

test_crew_kickoff_streaming_usage_metrics.yaml

Enhance LLM Streaming Response Handling and Event System (#2266)

2025-03-07 12:54:32 -05:00

test_crew_kickoff_usage_metrics.yaml

Enhance LLM Streaming Response Handling and Event System (#2266)

2025-03-07 12:54:32 -05:00

test_crew_log_file_output.yaml

Bringing support to o1 family back + any models that don't support stop words

2024-09-24 22:18:20 -03:00

test_crew_output_file_end_to_end.yaml

Fix interpolation for output_file in Task (#1803) (#1814)

2024-12-29 01:57:59 -03:00

test_crew_verbose_output.yaml

Lorenze/console printer nice (#3004)

2025-06-14 12:21:46 -07:00

test_crew_with_delegating_agents_should_not_override_agent_tools.yaml

Adding Multimodal Abilities to Crew (#1805)

2024-12-27 17:03:35 -03:00

test_crew_with_delegating_agents_should_not_override_task_tools.yaml

Adding Multimodal Abilities to Crew (#1805)

2024-12-27 17:03:35 -03:00

test_crew_with_delegating_agents.yaml

Adding Multimodal Abilities to Crew (#1805)

2024-12-27 17:03:35 -03:00

test_crew_with_failing_task_guardrails.yaml

improving guardrails

2025-01-04 16:30:20 -03:00

test_crew_with_knowledge_sources_works_with_copy.yaml

fix breakage when cloning agent/crew using knowledge_sources and enable custom knowledge_storage (#1927)

2025-01-29 09:37:22 -05:00

test_custom_converter_cls.yaml

Bringing support to o1 family back + any models that don't support stop words

2024-09-24 22:18:20 -03:00

test_custom_llm_implementation.yaml

Add support for custom LLM implementations (#2277)

2025-03-25 12:39:08 -04:00

test_custom_llm_within_crew.yaml

Add support for custom LLM implementations (#2277)

2025-03-25 12:39:08 -04:00

test_deepseek_r1_with_open_router.yaml

update litellm to support o3-mini and deepseek. Update docs.

2025-02-04 10:58:34 -05:00

test_delegation_is_not_enabled_if_there_are_only_one_agent.yaml

Bringing support to o1 family back + any models that don't support stop words

2024-09-24 22:18:20 -03:00

test_disabled_memory_using_contextual_memory.yaml

Bringing support to o1 family back + any models that don't support stop words

2024-09-24 22:18:20 -03:00

test_disabling_cache_for_agent.yaml

Feat/individual react agent (#2483)

2025-04-02 08:54:46 -07:00

test_do_not_allow_crewai_trigger_context_for_first_task_hierarchical.yaml

Lorenze/better tracing events (#3382)

2025-08-26 09:09:46 -07:00

test_docling_source.yaml

pytest improvements to handle flaky test (#2726)

2025-05-01 15:48:29 -04:00

test_ensure_exchanged_messages_are_propagated_to_external_memory.yaml

feat: include exchanged agent messages into ExternalMemory metadata (#3290)

2025-08-14 09:41:09 -04:00

test_ensure_first_task_allow_crewai_trigger_context_is_false_does_not_inject.yaml

chore: renaming inject_trigger_input to allow_crewai_trigger_context (#3353)

2025-08-18 17:57:21 -04:00

test_first_task_auto_inject_trigger.yaml

Auto inject crewai_trigger_payload (#3351)

2025-08-18 16:36:08 -04:00

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

added gpt-4.1 models and gemini-2.0 and 2.5 pro models (#2609)

2025-04-23 11:20:32 -07:00

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

added gpt-4.1 models and gemini-2.0 and 2.5 pro models (#2609)

2025-04-23 11:20:32 -07:00

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

added gpt-4.1 models and gemini-2.0 and 2.5 pro models (#2609)

2025-04-23 11:20:32 -07:00

test_gemini_models[gemini-gemini-2.5-flash-preview-04-17].yaml

added gpt-4.1 models and gemini-2.0 and 2.5 pro models (#2609)

2025-04-23 11:20:32 -07:00

test_gemini_models[gemini-gemini-2.5-pro-exp-03-25].yaml

added gpt-4.1 models and gemini-2.0 and 2.5 pro models (#2609)

2025-04-23 11:20:32 -07:00

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

Lorenze/tracing v1 (#3279)

2025-08-06 14:05:14 -07:00

test_get_knowledge_search_query.yaml

Lorenze/fix tool call twice (#3495)

2025-09-10 15:20:21 -07:00

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

added gpt-4.1 models and gemini-2.0 and 2.5 pro models (#2609)

2025-04-23 11:20:32 -07:00

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

added gpt-4.1 models and gemini-2.0 and 2.5 pro models (#2609)

2025-04-23 11:20:32 -07:00

test_gpt_4_1[gpt-4.1].yaml

added gpt-4.1 models and gemini-2.0 and 2.5 pro models (#2609)

2025-04-23 11:20:32 -07:00

test_guardrail_emits_events.yaml

Supporting no-code Guardrail creation (#2636)

2025-04-30 10:47:58 -04:00

test_guardrail_is_called_using_callable.yaml

LiteAgent w/ Guardrail (#2982)

2025-06-10 13:32:32 -04:00

test_guardrail_is_called_using_string.yaml

LiteAgent w/ Guardrail (#2982)

2025-06-10 13:32:32 -04:00

test_guardrail_reached_attempt_limit.yaml

LiteAgent w/ Guardrail (#2982)

2025-06-10 13:32:32 -04:00

test_guardrail_when_an_error_occurs.yaml

Supporting no-code Guardrail creation (#2636)

2025-04-30 10:47:58 -04:00

test_handle_context_length_exceeds_limit_cli_no.yaml

Bringing support to o1 family back + any models that don't support stop words

2024-09-24 22:18:20 -03:00

test_handle_context_length_exceeds_limit.yaml

Bringing support to o1 family back + any models that don't support stop words

2024-09-24 22:18:20 -03:00

test_handle_streaming_tool_calls_no_available_functions.yaml

Unblock LLM(stream=True) to work with tools (#2582)

2025-04-17 11:58:52 -04:00

test_handle_streaming_tool_calls_no_tools.yaml

Unblock LLM(stream=True) to work with tools (#2582)

2025-04-17 11:58:52 -04:00

test_handle_streaming_tool_calls_with_error.yaml

feat: log usage tools when called by LLM (#2916)

2025-05-29 14:34:34 -04:00

test_handle_streaming_tool_calls.yaml

Unblock LLM(stream=True) to work with tools (#2582)

2025-04-17 11:58:52 -04:00

test_hierarchical_crew_creation_tasks_with_agents.yaml

Bringing support to o1 family back + any models that don't support stop words

2024-09-24 22:18:20 -03:00

test_hierarchical_crew_creation_tasks_with_async_execution.yaml

Bringing support to o1 family back + any models that don't support stop words

2024-09-24 22:18:20 -03:00

test_hierarchical_crew_creation_tasks_with_sync_last.yaml

Lorenze/better tracing events (#3382)

2025-08-26 09:09:46 -07:00

test_hierarchical_process.yaml

Lorenze/better tracing events (#3382)

2025-08-26 09:09:46 -07:00

test_hierarchical_verbose_false_manager_agent.yaml

Lorenze/better tracing events (#3382)

2025-08-26 09:09:46 -07:00

test_hierarchical_verbose_manager_agent.yaml

Lorenze/better tracing events (#3382)

2025-08-26 09:09:46 -07:00

test_increment_delegations_for_hierarchical_process.yaml

Lorenze/better tracing events (#3382)

2025-08-26 09:09:46 -07:00

test_increment_delegations_for_sequential_process.yaml

Lorenze/better tracing events (#3382)

2025-08-26 09:09:46 -07:00

test_increment_tool_errors.yaml

Lorenze/better tracing events (#3382)

2025-08-26 09:09:46 -07:00

test_inject_date_custom_format.yaml

Add inject_date flag to Agent for automatic date injection (#2870)

2025-05-21 12:58:57 -07:00

test_inject_date.yaml

Add inject_date flag to Agent for automatic date injection (#2870)

2025-05-21 12:58:57 -07:00

test_json_property_without_output_json.yaml

Bringing support to o1 family back + any models that don't support stop words

2024-09-24 22:18:20 -03:00

test_kickoff_for_each_error_handling.yaml

Knowledge (#1567)

2024-11-20 15:40:08 -08:00

test_kickoff_for_each_multiple_inputs.yaml

Bringing support to o1 family back + any models that don't support stop words

2024-09-24 22:18:20 -03:00

test_kickoff_for_each_single_input.yaml

Bringing support to o1 family back + any models that don't support stop words

2024-09-24 22:18:20 -03:00

test_lite_agent_created_with_correct_parameters[False].yaml

KISS: Refactor LiteAgent integration in flows to use Agents instead. … (#2556)

2025-04-09 11:54:45 -07:00

test_lite_agent_created_with_correct_parameters[True].yaml

KISS: Refactor LiteAgent integration in flows to use Agents instead. … (#2556)

2025-04-09 11:54:45 -07:00

test_lite_agent_returns_usage_metrics_async.yaml

KISS: Refactor LiteAgent integration in flows to use Agents instead. … (#2556)

2025-04-09 11:54:45 -07:00

test_lite_agent_returns_usage_metrics.yaml

Feat/individual react agent (#2483)

2025-04-02 08:54:46 -07:00

test_lite_agent_structured_output.yaml

Fix typos in documentation and configuration files (#2712)

2025-05-06 15:07:57 -04:00

test_lite_agent_with_tools.yaml

Feat/individual react agent (#2483)

2025-04-02 08:54:46 -07:00

test_llm_call_when_stop_is_unsupported_when_additional_drop_params_is_provided.yaml

feat: drop unsupported stop parameter for LLM models automatically (#3184)

2025-07-18 13:54:28 -04:00

test_llm_call_when_stop_is_unsupported.yaml

feat: drop unsupported stop parameter for LLM models automatically (#3184)

2025-07-18 13:54:28 -04:00

test_llm_call_with_all_attributes.yaml

Bringing support to o1 family back + any models that don't support stop words

2024-09-24 22:18:20 -03:00

test_llm_call_with_message_list.yaml

Updated calls and added tests to verify (#1953)

2025-01-22 14:36:15 -05:00

test_llm_call_with_ollama_llama3.yaml

drop litellm version to prevent windows issue (#1878)

2025-01-14 13:06:47 -05:00

test_llm_call_with_string_input_and_callbacks.yaml

Updated calls and added tests to verify (#1953)

2025-01-22 14:36:15 -05:00

test_llm_call_with_string_input.yaml

Updated calls and added tests to verify (#1953)

2025-01-22 14:36:15 -05:00

test_llm_call_with_tool_and_message_list.yaml

Updated calls and added tests to verify (#1953)

2025-01-22 14:36:15 -05:00

test_llm_call_with_tool_and_string_input.yaml

Updated calls and added tests to verify (#1953)

2025-01-22 14:36:15 -05:00

test_llm_call.yaml

Bringing support to o1 family back + any models that don't support stop words

2024-09-24 22:18:20 -03:00

test_llm_callback_replacement.yaml

feat: log usage tools when called by LLM (#2916)

2025-05-29 14:34:34 -04:00

test_logging_tool_usage.yaml

Bringing support to o1 family back + any models that don't support stop words

2024-09-24 22:18:20 -03:00

test_long_term_memory_with_memory_flag.yaml

feat: Enhance memory system with isolated memory configuration (#2597)

2025-04-14 15:48:48 -04:00

test_manager_agent_delegating_to_all_agents.yaml

Bringing support to o1 family back + any models that don't support stop words

2024-09-24 22:18:20 -03:00

test_manager_agent_delegating_to_assigned_task_agent.yaml

Bringing support to o1 family back + any models that don't support stop words

2024-09-24 22:18:20 -03:00

test_max_usage_count_is_respected.yaml

Lorenze/max retry defaults tools (#3362)

2025-08-19 10:44:55 -07:00

test_memory_events_are_emitted.yaml

Introduce MemoryEvents to monitor their usage (#3098)

2025-07-01 22:50:39 -04:00

test_multimodal_agent_describing_image_successfully.yaml

test: adding missing test to ensure multimodal content structures

2025-03-26 16:30:17 -03:00

test_multimodal_agent_live_image_analysis.yaml

Adding Multimodal Abilities to Crew (#1805)

2024-12-27 17:03:35 -03:00

test_multiple_before_after_crew.yaml

adding before and after crew

2024-11-18 00:21:36 -03:00

test_multiple_before_after_kickoff.yaml

feat: add official way to use MCP Tools within a CrewBase (#3058)

2025-06-24 15:14:59 -04:00

test_multiple_docling_sources.yaml

pytest improvements to handle flaky test (#2726)

2025-05-01 15:48:29 -04:00

test_no_inject_date.yaml

Add inject_date flag to Agent for automatic date injection (#2870)

2025-05-21 12:58:57 -07:00

test_o3_mini_reasoning_effort_high.yaml

update litellm to support o3-mini and deepseek. Update docs.

2025-02-04 10:58:34 -05:00

test_o3_mini_reasoning_effort_low.yaml

update litellm to support o3-mini and deepseek. Update docs.

2025-02-04 10:58:34 -05:00

test_o3_mini_reasoning_effort_medium.yaml

update litellm to support o3-mini and deepseek. Update docs.

2025-02-04 10:58:34 -05:00

test_output_json_dict_hierarchical.yaml

Lorenze/better tracing events (#3382)

2025-08-26 09:09:46 -07:00

test_output_json_dict_sequential.yaml

Bringing support to o1 family back + any models that don't support stop words

2024-09-24 22:18:20 -03:00

test_output_json_hierarchical.yaml

Lorenze/better tracing events (#3382)

2025-08-26 09:09:46 -07:00

test_output_json_sequential.yaml

Add inject_date flag to Agent for automatic date injection (#2870)

2025-05-21 12:58:57 -07:00

test_output_json_to_another_task.yaml

Bringing support to o1 family back + any models that don't support stop words

2024-09-24 22:18:20 -03:00

test_output_pydantic_hierarchical.yaml

Lorenze/better tracing events (#3382)

2025-08-26 09:09:46 -07:00

test_output_pydantic_sequential.yaml

Bringing support to o1 family back + any models that don't support stop words

2024-09-24 22:18:20 -03:00

test_output_pydantic_to_another_task.yaml

Bringing support to o1 family back + any models that don't support stop words

2024-09-24 22:18:20 -03:00

test_replay_interpolates_inputs_properly.yaml

Bringing support to o1 family back + any models that don't support stop words

2024-09-24 22:18:20 -03:00

test_replay_setup_context.yaml

Bringing support to o1 family back + any models that don't support stop words

2024-09-24 22:18:20 -03:00

test_replay_with_context.yaml

Bringing support to o1 family back + any models that don't support stop words

2024-09-24 22:18:20 -03:00

test_save_task_json_output.yaml

Bringing support to o1 family back + any models that don't support stop words

2024-09-24 22:18:20 -03:00

test_save_task_output.yaml

Bringing support to o1 family back + any models that don't support stop words

2024-09-24 22:18:20 -03:00

test_save_task_pydantic_output.yaml

Bringing support to o1 family back + any models that don't support stop words

2024-09-24 22:18:20 -03:00

test_sequential_async_task_execution_completion.yaml

Bringing support to o1 family back + any models that don't support stop words

2024-09-24 22:18:20 -03:00

test_single_task_with_async_execution.yaml

Bringing support to o1 family back + any models that don't support stop words

2024-09-24 22:18:20 -03:00

test_task_allow_crewai_trigger_context_no_payload.yaml

chore: renaming inject_trigger_input to allow_crewai_trigger_context (#3353)

2025-08-18 17:57:21 -04:00

test_task_allow_crewai_trigger_context.yaml

chore: renaming inject_trigger_input to allow_crewai_trigger_context (#3353)

2025-08-18 17:57:21 -04:00

test_task_execution_times.yaml

[ENG-227] Record task execution timestamps (#1844)

2025-01-03 13:12:13 -05:00

test_task_guardrail_process_output.yaml

Supporting no-code Guardrail creation (#2636)

2025-04-30 10:47:58 -04:00

test_task_interpolation_with_hyphens.yaml

Enhance string interpolation to support hyphens in variable names and… (#2834)

2025-05-14 16:06:07 -07:00

test_task_tools_override_agent_tools.yaml

Brandon/eng 266 conversation crew v1 (#1843)

2025-01-06 16:12:43 -05:00

test_task_with_max_execution_time_exceeded.yaml

Add inject_date flag to Agent for automatic date injection (#2870)

2025-05-21 12:58:57 -07:00

test_task_with_max_execution_time.yaml

Support set max_execution_time to Agent (#2610)

2025-04-17 16:03:00 -04:00

test_task_with_no_arguments.yaml

Lorenze/console printer nice (#3004)

2025-06-14 12:21:46 -07:00

test_task_without_allow_crewai_trigger_context.yaml

chore: renaming inject_trigger_input to allow_crewai_trigger_context (#3353)

2025-08-18 17:57:21 -04:00

test_telemetry_fails_due_connect_timeout.yaml

feat: prevent crash once Telemetry is not available (#2758)

2025-05-05 15:22:32 -04:00

test_tool_result_as_answer_is_the_final_answer_for_the_agent.yaml

Bringing support to o1 family back + any models that don't support stop words

2024-09-24 22:18:20 -03:00

test_tool_usage_information_is_appended_to_agent.yaml

Bringing support to o1 family back + any models that don't support stop words

2024-09-24 22:18:20 -03:00

test_tools_with_custom_caching.yaml

Bringing support to o1 family back + any models that don't support stop words

2024-09-24 22:18:20 -03:00

test_using_contextual_memory_with_long_term_memory.yaml

feat: Enhance memory system with isolated memory configuration (#2597)

2025-04-14 15:48:48 -04:00

test_using_contextual_memory_with_short_term_memory.yaml

feat: Enhance memory system with isolated memory configuration (#2597)

2025-04-14 15:48:48 -04:00

test_using_contextual_memory.yaml

Lorenze/better tracing events (#3382)

2025-08-26 09:09:46 -07:00

test_warning_long_term_memory_without_entity_memory.yaml

feat: Enhance memory system with isolated memory configuration (#2597)

2025-04-14 15:48:48 -04:00

TestAgentEvaluator.test_eval_lite_agent.yaml

Supporting eval single Agent/LiteAgent (#3167)

2025-07-15 09:22:41 -04:00

TestAgentEvaluator.test_eval_specific_agents_from_crew.yaml

Supporting eval single Agent/LiteAgent (#3167)

2025-07-15 09:22:41 -04:00

TestAgentEvaluator.test_evaluate_current_iteration.yaml

Supporting eval single Agent/LiteAgent (#3167)

2025-07-15 09:22:41 -04:00

TestAgentEvaluator.test_failed_evaluation.yaml

Emit events about Agent eval (#3168)

2025-07-16 13:18:59 -04:00

TestTraceListenerSetup.test_batch_manager_finalizes_batch_clears_buffer.yaml

Lorenze/tracing v1 (#3279)

2025-08-06 14:05:14 -07:00

TestTraceListenerSetup.test_events_collection_batch_manager.yaml

Lorenze/tracing v1 (#3279)

2025-08-06 14:05:14 -07:00

TestTraceListenerSetup.test_trace_listener_collects_crew_events.yaml

Lorenze/tracing v1 (#3279)

2025-08-06 14:05:14 -07:00

TestTraceListenerSetup.test_trace_listener_disabled_when_env_false.yaml

Lorenze/tracing v1 (#3279)

2025-08-06 14:05:14 -07:00

TestTraceListenerSetup.test_trace_listener_ephemeral_batch.yaml

Refactor tracing logic to consolidate conditions for enabling tracing… (#3347)

2025-08-18 14:16:51 -07:00

TestTraceListenerSetup.test_trace_listener_setup_correctly_with_tracing_flag.yaml

Lorenze/tracing-improvements-cleanup (#3291)

2025-08-08 13:42:25 -07:00

TestTraceListenerSetup.test_trace_listener_with_authenticated_user.yaml

Refactor tracing logic to consolidate conditions for enabling tracing… (#3347)

2025-08-18 14:16:51 -07:00