fix: map output_pydantic/output_json to native structured output

* fix: map output_pydantic/output_json to native structured output

* test: add crew+tools+structured output integration test for Gemini

* fix: re-record stale cassette for test_crew_testing_function

* fix: re-record remaining stale cassettes for native structured output

* fix: enable native structured output for lite agent and fix mypy errors

Author: greysonlalonde

lib/crewai/src/crewai/agent/core.py

@@ -864,7 +864,11 @@ def create_agent_executor(
                 respect_context_window=self.respect_context_window,
                 request_within_rpm_limit=rpm_limit_fn,
                 callbacks=[TokenCalcHandler(self._token_process)],
-                response_model=task.response_model if task else None,
+                response_model=(
+                    task.response_model or task.output_pydantic or task.output_json
+                )
+                if task
+                else None,
             )
 
     def _update_executor_parameters(
@@ -893,7 +897,11 @@ def _update_executor_parameters(
         self.agent_executor.stop = stop_words
         self.agent_executor.tools_names = get_tool_names(tools)
         self.agent_executor.tools_description = render_text_description_and_args(tools)
-        self.agent_executor.response_model = task.response_model if task else None
+        self.agent_executor.response_model = (
+            (task.response_model or task.output_pydantic or task.output_json)
+            if task
+            else None
+        )
 
         self.agent_executor.tools_handler = self.tools_handler
         self.agent_executor.request_within_rpm_limit = rpm_limit_fn
@@ -1712,7 +1720,8 @@ def _prepare_kickoff(
 
             existing_names = {sanitize_tool_name(t.name) for t in raw_tools}
             raw_tools.extend(
-                mt for mt in create_memory_tools(agent_memory)
+                mt
+                for mt in create_memory_tools(agent_memory)
                 if sanitize_tool_name(mt.name) not in existing_names
             )
 
@@ -1937,14 +1946,15 @@ def _save_kickoff_to_memory(
             if isinstance(messages, str):
                 input_str = messages
             else:
-                input_str = "\n".join(
-                    str(msg.get("content", "")) for msg in messages if msg.get("content")
-                ) or "User request"
-            raw = (
-                f"Input: {input_str}\n"
-                f"Agent: {self.role}\n"
-                f"Result: {output_text}"
-            )
+                input_str = (
+                    "\n".join(
+                        str(msg.get("content", ""))
+                        for msg in messages
+                        if msg.get("content")
+                    )
+                    or "User request"
+                )
+            raw = f"Input: {input_str}\nAgent: {self.role}\nResult: {output_text}"
             extracted = agent_memory.extract_memories(raw)
             if extracted:
                 agent_memory.remember_many(extracted)

lib/crewai/src/crewai/lite_agent.py

@@ -2,10 +2,10 @@
 
 import asyncio
 from collections.abc import Callable
-import time
 from functools import wraps
 import inspect
 import json
+import time
 from types import MethodType
 from typing import (
     TYPE_CHECKING,
@@ -49,15 +49,20 @@
     LiteAgentExecutionErrorEvent,
     LiteAgentExecutionStartedEvent,
 )
+from crewai.events.types.logging_events import AgentLogsExecutionEvent
 from crewai.events.types.memory_events import (
     MemoryRetrievalCompletedEvent,
     MemoryRetrievalFailedEvent,
     MemoryRetrievalStartedEvent,
 )
-from crewai.events.types.logging_events import AgentLogsExecutionEvent
 from crewai.flow.flow_trackable import FlowTrackable
 from crewai.hooks.llm_hooks import get_after_llm_call_hooks, get_before_llm_call_hooks
-from crewai.hooks.types import AfterLLMCallHookType, BeforeLLMCallHookType
+from crewai.hooks.types import (
+    AfterLLMCallHookCallable,
+    AfterLLMCallHookType,
+    BeforeLLMCallHookCallable,
+    BeforeLLMCallHookType,
+)
 from crewai.lite_agent_output import LiteAgentOutput
 from crewai.llm import LLM
 from crewai.llms.base_llm import BaseLLM
@@ -270,11 +275,11 @@ class LiteAgent(FlowTrackable, BaseModel):
     _guardrail: GuardrailCallable | None = PrivateAttr(default=None)
     _guardrail_retry_count: int = PrivateAttr(default=0)
     _callbacks: list[TokenCalcHandler] = PrivateAttr(default_factory=list)
-    _before_llm_call_hooks: list[BeforeLLMCallHookType] = PrivateAttr(
-        default_factory=get_before_llm_call_hooks
+    _before_llm_call_hooks: list[BeforeLLMCallHookType | BeforeLLMCallHookCallable] = (
+        PrivateAttr(default_factory=get_before_llm_call_hooks)
     )
-    _after_llm_call_hooks: list[AfterLLMCallHookType] = PrivateAttr(
-        default_factory=get_after_llm_call_hooks
+    _after_llm_call_hooks: list[AfterLLMCallHookType | AfterLLMCallHookCallable] = (
+        PrivateAttr(default_factory=get_after_llm_call_hooks)
     )
     _memory: Any = PrivateAttr(default=None)
 
@@ -440,12 +445,16 @@ def _original_role(self) -> str:
         return self.role
 
     @property
-    def before_llm_call_hooks(self) -> list[BeforeLLMCallHookType]:
+    def before_llm_call_hooks(
+        self,
+    ) -> list[BeforeLLMCallHookType | BeforeLLMCallHookCallable]:
         """Get the before_llm_call hooks for this agent."""
         return self._before_llm_call_hooks
 
     @property
-    def after_llm_call_hooks(self) -> list[AfterLLMCallHookType]:
+    def after_llm_call_hooks(
+        self,
+    ) -> list[AfterLLMCallHookType | AfterLLMCallHookCallable]:
         """Get the after_llm_call hooks for this agent."""
         return self._after_llm_call_hooks
 
@@ -482,11 +491,12 @@ def kickoff(
         # Inject memory tools once if memory is configured (mirrors Agent._prepare_kickoff)
         if self._memory is not None:
             from crewai.tools.memory_tools import create_memory_tools
-            from crewai.utilities.agent_utils import sanitize_tool_name
+            from crewai.utilities.string_utils import sanitize_tool_name
 
             existing_names = {sanitize_tool_name(t.name) for t in self._parsed_tools}
             memory_tools = [
-                mt for mt in create_memory_tools(self._memory)
+                mt
+                for mt in create_memory_tools(self._memory)
                 if sanitize_tool_name(mt.name) not in existing_names
             ]
             if memory_tools:
@@ -565,9 +575,10 @@ def _inject_memory_context(self) -> None:
             if memory_block:
                 formatted = self.i18n.slice("memory").format(memory=memory_block)
                 if self._messages and self._messages[0].get("role") == "system":
-                    self._messages[0]["content"] = (
-                        self._messages[0].get("content", "") + "\n\n" + formatted
-                    )
+                    existing_content = self._messages[0].get("content", "")
+                    if not isinstance(existing_content, str):
+                        existing_content = ""
+                    self._messages[0]["content"] = existing_content + "\n\n" + formatted
             crewai_event_bus.emit(
                 self,
                 event=MemoryRetrievalCompletedEvent(
@@ -593,11 +604,7 @@ def _save_to_memory(self, output_text: str) -> None:
             return
         input_str = self._get_last_user_content() or "User request"
         try:
-            raw = (
-                f"Input: {input_str}\n"
-                f"Agent: {self.role}\n"
-                f"Result: {output_text}"
-            )
+            raw = f"Input: {input_str}\nAgent: {self.role}\nResult: {output_text}"
             extracted = self._memory.extract_memories(raw)
             if extracted:
                 self._memory.remember_many(extracted, agent_role=self.role)
@@ -622,13 +629,20 @@ def _execute_core(
         )
 
         # Execute the agent using invoke loop
-        agent_finish = self._invoke_loop()
+        active_response_format = response_format or self.response_format
+        agent_finish = self._invoke_loop(response_model=active_response_format)
         if self._memory is not None:
-            self._save_to_memory(agent_finish.output)
+            output_text = (
+                agent_finish.output.model_dump_json()
+                if isinstance(agent_finish.output, BaseModel)
+                else agent_finish.output
+            )
+            self._save_to_memory(output_text)
         formatted_result: BaseModel | None = None
 
-        active_response_format = response_format or self.response_format
-        if active_response_format:
+        if isinstance(agent_finish.output, BaseModel):
+            formatted_result = agent_finish.output
+        elif active_response_format:
             try:
                 model_schema = generate_model_description(active_response_format)
                 schema = json.dumps(model_schema, indent=2)
@@ -660,8 +674,13 @@ def _execute_core(
             usage_metrics = self._token_process.get_summary()
 
         # Create output
+        raw_output = (
+            agent_finish.output.model_dump_json()
+            if isinstance(agent_finish.output, BaseModel)
+            else agent_finish.output
+        )
         output = LiteAgentOutput(
-            raw=agent_finish.output,
+            raw=raw_output,
             pydantic=formatted_result,
             agent_role=self.role,
             usage_metrics=usage_metrics.model_dump() if usage_metrics else None,
@@ -838,10 +857,15 @@ def _format_messages(
 
         return formatted_messages
 
-    def _invoke_loop(self) -> AgentFinish:
+    def _invoke_loop(
+        self, response_model: type[BaseModel] | None = None
+    ) -> AgentFinish:
         """
         Run the agent's thought process until it reaches a conclusion or max iterations.
 
+        Args:
+            response_model: Optional Pydantic model for native structured output.
+
         Returns:
             AgentFinish: The final result of the agent execution.
         """
@@ -870,12 +894,19 @@ def _invoke_loop(self) -> AgentFinish:
                         printer=self._printer,
                         from_agent=self,
                         executor_context=self,
+                        response_model=response_model,
                         verbose=self.verbose,
                     )
 
                 except Exception as e:
                     raise e
 
+                if isinstance(answer, BaseModel):
+                    formatted_answer = AgentFinish(
+                        thought="", output=answer, text=answer.model_dump_json()
+                    )
+                    break
+
                 formatted_answer = process_llm_response(
                     cast(str, answer), self.use_stop_words
                 )
@@ -901,7 +932,7 @@ def _invoke_loop(self) -> AgentFinish:
                     )
 
                 self._append_message(formatted_answer.text, role="assistant")
-            except OutputParserError as e:  # noqa: PERF203
+            except OutputParserError as e:
                 if self.verbose:
                     self._printer.print(
                         content="Failed to parse LLM output. Retrying...",

lib/crewai/src/crewai/llms/providers/gemini/completion.py

@@ -894,7 +894,7 @@ def _process_response_with_tools(
         content = self._extract_text_from_response(response)
 
         effective_response_model = None if self.tools else response_model
-        if not effective_response_model:
+        if not response_model:
             content = self._apply_stop_words(content)
 
         return self._finalize_completion_response(

lib/crewai/src/crewai/task.py

@@ -586,16 +586,29 @@ async def _aexecute_core(
 
             self._post_agent_execution(agent)
 
-            if not self._guardrails and not self._guardrail:
+            if isinstance(result, BaseModel):
+                raw = result.model_dump_json()
+                if self.output_pydantic:
+                    pydantic_output = result
+                    json_output = None
+                elif self.output_json:
+                    pydantic_output = None
+                    json_output = result.model_dump()
+                else:
+                    pydantic_output = None
+                    json_output = None
+            elif not self._guardrails and not self._guardrail:
+                raw = result
                 pydantic_output, json_output = self._export_output(result)
             else:
+                raw = result
                 pydantic_output, json_output = None, None
 
             task_output = TaskOutput(
                 name=self.name or self.description,
                 description=self.description,
                 expected_output=self.expected_output,
-                raw=result,
+                raw=raw,
                 pydantic=pydantic_output,
                 json_dict=json_output,
                 agent=agent.role,
@@ -687,16 +700,29 @@ def _execute_core(
 
             self._post_agent_execution(agent)
 
-            if not self._guardrails and not self._guardrail:
+            if isinstance(result, BaseModel):
+                raw = result.model_dump_json()
+                if self.output_pydantic:
+                    pydantic_output = result
+                    json_output = None
+                elif self.output_json:
+                    pydantic_output = None
+                    json_output = result.model_dump()
+                else:
+                    pydantic_output = None
+                    json_output = None
+            elif not self._guardrails and not self._guardrail:
+                raw = result
                 pydantic_output, json_output = self._export_output(result)
             else:
+                raw = result
                 pydantic_output, json_output = None, None
 
             task_output = TaskOutput(
                 name=self.name or self.description,
                 description=self.description,
                 expected_output=self.expected_output,
-                raw=result,
+                raw=raw,
                 pydantic=pydantic_output,
                 json_dict=json_output,
                 agent=agent.role,