Devin AI c2b151bd30 fix: handle running event loop in A2A sync wrappers (#4671) ...

execute_a2a_delegation() and fetch_agent_card() now use a ThreadPoolExecutor
to run async code in a separate thread when an event loop is already running
(e.g. Jupyter notebooks), instead of raising RuntimeError.

Co-Authored-By: João <joao@crewai.com>

2026-03-02 10:57:07 +00:00

..

a2a

fix: handle running event loop in A2A sync wrappers (#4671)

2026-03-02 10:57:07 +00:00

agents

fix: inject tool errors as observations and resolve name collisions

2026-03-01 00:46:04 -05:00

cassettes

fix: map output_pydantic/output_json to native structured output

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

cli

feat: migrate CLI http client from requests to httpx

2026-02-20 18:21:05 -05:00

config

…

crew

feat: async crew support

2025-12-04 16:53:19 -05:00

events

Fix tool error causing double event scope pop (#4373)

2026-02-04 20:34:08 -03:00

experimental

fix: ensure otel span is closed

2025-12-05 13:23:26 -05:00

hooks

feat: implement before and after tool call hooks in CrewAgentExecutor… (#4287)

2026-01-27 14:56:50 -08:00

knowledge

…

llms

fix: map output_pydantic/output_json to native structured output

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

mcp

Enhance MCP tool resolution and related events (#4580)

2026-02-26 13:59:30 -08:00

memory

feat: update lancedb version and add lance-namespace packages

2026-02-26 15:05:10 -05:00

pipeline

…

project

…

rag

New Unified Memory System (#4420)

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

security

…

storage

New Unified Memory System (#4420)

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

task

feat: async task support (#4024)

2025-12-04 13:34:29 -08:00

telemetry

fix: ensure otel span is closed

2025-12-05 13:23:26 -05:00

tools

fix: validate tool kwargs even when empty to prevent cryptic TypeError (#4611)

2026-02-26 16:18:03 -05:00

tracing

…

utilities

fix: inject tool errors as observations and resolve name collisions

2026-03-01 00:46:04 -05:00

__init__.py

…

test_agent_multimodal.py

feat: native multimodal file handling; openai responses api

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

test_async_human_feedback.py

Adding HITL for Flows (#4143)

2025-12-25 21:04:10 -03:00

test_context.py

Lorenze/imp/native tool calling (#4258)

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

test_crew_multimodal.py

feat: native multimodal file handling; openai responses api

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

test_crew_thread_safety.py

…

test_crew.py

New Unified Memory System (#4420)

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

test_custom_llm.py

…

test_flow_ask.py

Implement user input handling in Flows (#4490)

2026-02-16 18:41:03 -03:00

test_flow_default_override.py

…

test_flow_human_input_integration.py

refactor: extract hitl to provider pattern

2026-02-04 15:40:22 -05:00

test_flow_multimodal.py

feat: native multimodal file handling; openai responses api

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

test_flow_persistence.py

Lorenze/enh decouple executor from crew (#4209)

2026-01-20 21:44:45 -08:00

test_flow_resumability_regression.py

…

test_flow_visualization.py

…

test_flow.py

Fix cyclic flows silently breaking when persistence ID is passed in inputs (#4501)

2026-02-18 03:27:24 -03:00

test_hallucination_guardrail.py

…

test_human_feedback_decorator.py

New Unified Memory System (#4420)

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

test_human_feedback_integration.py

Enhance HITL self-loop functionality in human feedback integration tests (#4493)

2026-02-15 21:54:42 -05:00

test_imports.py

…

test_llm.py

feat: native multimodal file handling; openai responses api

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

test_markdown_task.py

…

test_multimodal_validation.py

…

test_project.py

…

test_streaming_integration.py

…

test_streaming.py

Add call_id to LLM events for correlating requests (#4281)

2026-02-03 10:10:33 -03:00

test_task_guardrails.py

fix: resolve race condition in guardrail event emission test

2026-02-03 09:06:48 -05:00

test_task.py

fix: map output_pydantic/output_json to native structured output

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

utils.py

…