Gl/feat/a2a refactor (#3793)

* feat: agent metaclass, refactor a2a to wrappers

* feat: a2a schemas and utils

* chore: move agent class, update imports

* refactor: organize imports to avoid circularity, add a2a to console

* feat: pass response_model through call chain

* feat: add standard openapi spec serialization to tools and structured output

* feat: a2a events

* chore: add a2a to pyproject

* docs: minimal base for learn docs

* fix: adjust a2a conversation flow, allow llm to decide exit until max_retries

* fix: inject agent skills into initial prompt

* fix: format agent card as json in prompt

* refactor: simplify A2A agent prompt formatting and improve skill display

* chore: wide cleanup

* chore: cleanup logic, add auth cache, use json for messages in prompt

* chore: update docs

* fix: doc snippets formatting

* feat: optimize A2A agent card fetching and improve error reporting

* chore: move imports to top of file

* chore: refactor hasattr check

* chore: add httpx-auth, update lockfile

* feat: create base public api

* chore: cleanup modules, add docstrings, types

* fix: exclude extra fields in prompt

* chore: update docs

* tests: update to correct import

* chore: lint for ruff, add missing import

* fix: tweak openai streaming logic for response model

* tests: add reimport for test

* tests: add reimport for test

* fix: don't set a2a attr if not set

* fix: don't set a2a attr if not set

* chore: update cassettes

* tests: fix tests

* fix: use instructor and dont pass response_format for litellm

* chore: consolidate event listeners, add typing

* fix: address race condition in test, update cassettes

* tests: add correct mocks, rerun cassette for json

* tests: update cassette

* chore: regenerate cassette after new run

* fix: make token manager access-safe

* fix: make token manager access-safe

* merge

* chore: update test and cassete for output pydantic

* fix: tweak to disallow deadlock

* chore: linter

* fix: adjust event ordering for threading

* fix: use conditional for batch check

* tests: tweak for emission

* tests: simplify api + event check

* fix: ensure non-function calling llms see json formatted string

* tests: tweak message comparison

* fix: use internal instructor for litellm structure responses

---------

Co-authored-by: Mike Plachta <mike@crewai.com>

lib/crewai/tests/llms/openai/test_openai.py

@@ -482,3 +482,48 @@ def test_openai_get_client_params_no_base_url():
     client_params = llm._get_client_params()
     # When no base_url is provided, it should not be in the params (filtered out as None)
     assert "base_url" not in client_params or client_params.get("base_url") is None
+
+
+def test_openai_streaming_with_response_model():
+    """
+    Test that streaming with response_model works correctly and doesn't call invalid API methods.
+    This test verifies the fix for the bug where streaming with response_model attempted to call
+    self.client.responses.stream() with invalid parameters (input, text_format).
+    """
+    from pydantic import BaseModel
+
+    class TestResponse(BaseModel):
+        """Test response model."""
+
+        answer: str
+        confidence: float
+
+    llm = LLM(model="openai/gpt-4o", stream=True)
+
+    with patch.object(llm.client.chat.completions, "create") as mock_create:
+        mock_chunk1 = MagicMock()
+        mock_chunk1.choices = [
+            MagicMock(delta=MagicMock(content='{"answer": "test", ', tool_calls=None))
+        ]
+
+        mock_chunk2 = MagicMock()
+        mock_chunk2.choices = [
+            MagicMock(
+                delta=MagicMock(content='"confidence": 0.95}', tool_calls=None)
+            )
+        ]
+
+        mock_create.return_value = iter([mock_chunk1, mock_chunk2])
+
+        result = llm.call("Test question", response_model=TestResponse)
+
+        assert result is not None
+        assert isinstance(result, str)
+
+        assert mock_create.called
+        call_kwargs = mock_create.call_args[1]
+        assert call_kwargs["model"] == "gpt-4o"
+        assert call_kwargs["stream"] is True
+
+        assert "input" not in call_kwargs
+        assert "text_format" not in call_kwargs