fix: preserve full LLM config across HITL resume for non-OpenAI providers (#4970)

When a flow with @human_feedback(llm=create_llm()) pauses for HITL and
later resumes:

1. The LLM object was being serialized to just a model string via
   _serialize_llm_for_context() (e.g. 'gemini/gemini-3.1-flash-lite-preview')
2. On resume, resume_async() was creating LLM(model=string) with NO
   credentials, project, location, safety_settings, or client_params
3. OpenAI worked by accident (OPENAI_API_KEY from env), but Gemini with
   service accounts broke

This fix:
- Stashes the live LLM object on the wrapper as _hf_llm attribute
- On resume, looks up the method and retrieves the live LLM if available
- Falls back to the serialized string for backward compatibility
- Preserves _hf_llm through FlowMethod wrapper decorators

Co-authored-by: Joao Moura <joao@crewai.com>
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>

docs/docs.json

@@ -115,6 +115,13 @@
                           "en/guides/flows/mastering-flow-state"
                         ]
                       },
+                      {
+                        "group": "Tools",
+                        "icon": "wrench",
+                        "pages": [
+                          "en/guides/tools/publish-custom-tools"
+                        ]
+                      },
                       {
                         "group": "Coding Tools",
                         "icon": "terminal",
@@ -575,6 +582,13 @@
                           "en/guides/flows/mastering-flow-state"
                         ]
                       },
+                      {
+                        "group": "Tools",
+                        "icon": "wrench",
+                        "pages": [
+                          "en/guides/tools/publish-custom-tools"
+                        ]
+                      },
                       {
                         "group": "Coding Tools",
                         "icon": "terminal",
@@ -1035,6 +1049,13 @@
                           "en/guides/flows/mastering-flow-state"
                         ]
                       },
+                      {
+                        "group": "Tools",
+                        "icon": "wrench",
+                        "pages": [
+                          "en/guides/tools/publish-custom-tools"
+                        ]
+                      },
                       {
                         "group": "Coding Tools",
                         "icon": "terminal",
@@ -1525,6 +1546,20 @@
                           "pt-BR/guides/flows/mastering-flow-state"
                         ]
                       },
+                      {
+                        "group": "Ferramentas",
+                        "icon": "wrench",
+                        "pages": [
+                          "pt-BR/guides/tools/publish-custom-tools"
+                        ]
+                      },
+                      {
+                        "group": "Ferramentas de Codificação",
+                        "icon": "terminal",
+                        "pages": [
+                          "pt-BR/guides/coding-tools/agents-md"
+                        ]
+                      },
                       {
                         "group": "Avançado",
                         "icon": "gear",
@@ -1964,6 +1999,20 @@
                           "pt-BR/guides/flows/mastering-flow-state"
                         ]
                       },
+                      {
+                        "group": "Ferramentas",
+                        "icon": "wrench",
+                        "pages": [
+                          "pt-BR/guides/tools/publish-custom-tools"
+                        ]
+                      },
+                      {
+                        "group": "Ferramentas de Codificação",
+                        "icon": "terminal",
+                        "pages": [
+                          "pt-BR/guides/coding-tools/agents-md"
+                        ]
+                      },
                       {
                         "group": "Avançado",
                         "icon": "gear",
@@ -2403,6 +2452,20 @@
                           "pt-BR/guides/flows/mastering-flow-state"
                         ]
                       },
+                      {
+                        "group": "Ferramentas",
+                        "icon": "wrench",
+                        "pages": [
+                          "pt-BR/guides/tools/publish-custom-tools"
+                        ]
+                      },
+                      {
+                        "group": "Ferramentas de Codificação",
+                        "icon": "terminal",
+                        "pages": [
+                          "pt-BR/guides/coding-tools/agents-md"
+                        ]
+                      },
                       {
                         "group": "Avançado",
                         "icon": "gear",
@@ -2872,6 +2935,20 @@
                           "ko/guides/flows/mastering-flow-state"
                         ]
                       },
+                      {
+                        "group": "도구",
+                        "icon": "wrench",
+                        "pages": [
+                          "ko/guides/tools/publish-custom-tools"
+                        ]
+                      },
+                      {
+                        "group": "코딩 도구",
+                        "icon": "terminal",
+                        "pages": [
+                          "ko/guides/coding-tools/agents-md"
+                        ]
+                      },
                       {
                         "group": "고급",
                         "icon": "gear",
@@ -3323,6 +3400,20 @@
                           "ko/guides/flows/mastering-flow-state"
                         ]
                       },
+                      {
+                        "group": "도구",
+                        "icon": "wrench",
+                        "pages": [
+                          "ko/guides/tools/publish-custom-tools"
+                        ]
+                      },
+                      {
+                        "group": "코딩 도구",
+                        "icon": "terminal",
+                        "pages": [
+                          "ko/guides/coding-tools/agents-md"
+                        ]
+                      },
                       {
                         "group": "고급",
                         "icon": "gear",
@@ -3774,6 +3865,20 @@
                           "ko/guides/flows/mastering-flow-state"
                         ]
                       },
+                      {
+                        "group": "도구",
+                        "icon": "wrench",
+                        "pages": [
+                          "ko/guides/tools/publish-custom-tools"
+                        ]
+                      },
+                      {
+                        "group": "코딩 도구",
+                        "icon": "terminal",
+                        "pages": [
+                          "ko/guides/coding-tools/agents-md"
+                        ]
+                      },
                       {
                         "group": "고급",
                         "icon": "gear",

docs/en/concepts/event-listener.mdx

@@ -196,12 +196,19 @@ CrewAI provides a wide range of events that you can listen for:
 - **CrewTrainStartedEvent**: Emitted when a Crew starts training
 - **CrewTrainCompletedEvent**: Emitted when a Crew completes training
 - **CrewTrainFailedEvent**: Emitted when a Crew fails to complete training
+- **CrewTestResultEvent**: Emitted when a Crew test result is available. Contains the quality score, execution duration, and model used.
 
 ### Agent Events
 
 - **AgentExecutionStartedEvent**: Emitted when an Agent starts executing a task
 - **AgentExecutionCompletedEvent**: Emitted when an Agent completes executing a task
 - **AgentExecutionErrorEvent**: Emitted when an Agent encounters an error during execution
+- **LiteAgentExecutionStartedEvent**: Emitted when a LiteAgent starts executing. Contains the agent info, tools, and messages.
+- **LiteAgentExecutionCompletedEvent**: Emitted when a LiteAgent completes execution. Contains the agent info and output.
+- **LiteAgentExecutionErrorEvent**: Emitted when a LiteAgent encounters an error during execution. Contains the agent info and error message.
+- **AgentEvaluationStartedEvent**: Emitted when an agent evaluation starts. Contains the agent ID, agent role, optional task ID, and iteration number.
+- **AgentEvaluationCompletedEvent**: Emitted when an agent evaluation completes. Contains the agent ID, agent role, optional task ID, iteration number, metric category, and score.
+- **AgentEvaluationFailedEvent**: Emitted when an agent evaluation fails. Contains the agent ID, agent role, optional task ID, iteration number, and error message.
 
 ### Task Events
 
@@ -242,16 +249,26 @@ CrewAI provides a wide range of events that you can listen for:
 
 - **LLMGuardrailStartedEvent**: Emitted when a guardrail validation starts. Contains details about the guardrail being applied and retry count.
 - **LLMGuardrailCompletedEvent**: Emitted when a guardrail validation completes. Contains details about validation success/failure, results, and error messages if any.
+- **LLMGuardrailFailedEvent**: Emitted when a guardrail validation fails. Contains the error message and retry count.
 
 ### Flow Events
 
 - **FlowCreatedEvent**: Emitted when a Flow is created
 - **FlowStartedEvent**: Emitted when a Flow starts execution
 - **FlowFinishedEvent**: Emitted when a Flow completes execution
+- **FlowPausedEvent**: Emitted when a Flow is paused waiting for human feedback. Contains the flow name, flow ID, method name, current state, message shown when requesting feedback, and optional list of possible outcomes for routing.
 - **FlowPlotEvent**: Emitted when a Flow is plotted
 - **MethodExecutionStartedEvent**: Emitted when a Flow method starts execution
 - **MethodExecutionFinishedEvent**: Emitted when a Flow method completes execution
 - **MethodExecutionFailedEvent**: Emitted when a Flow method fails to complete execution
+- **MethodExecutionPausedEvent**: Emitted when a Flow method is paused waiting for human feedback. Contains the flow name, method name, current state, flow ID, message shown when requesting feedback, and optional list of possible outcomes for routing.
+
+### Human In The Loop Events
+
+- **FlowInputRequestedEvent**: Emitted when a Flow requests user input via `Flow.ask()`. Contains the flow name, method name, the question or prompt being shown to the user, and optional metadata (e.g., user ID, channel, session context).
+- **FlowInputReceivedEvent**: Emitted when user input is received after `Flow.ask()`. Contains the flow name, method name, the original question, the user's response (or `None` if timed out), optional request metadata, and optional response metadata from the provider (e.g., who responded, thread ID, timestamps).
+- **HumanFeedbackRequestedEvent**: Emitted when a `@human_feedback` decorated method requires input from a human reviewer. Contains the flow name, method name, the method output shown to the human for review, the message displayed when requesting feedback, and optional list of possible outcomes for routing.
+- **HumanFeedbackReceivedEvent**: Emitted when a human provides feedback in response to a `@human_feedback` decorated method. Contains the flow name, method name, the raw text feedback provided by the human, and the collapsed outcome string (if emit was specified).
 
 ### LLM Events
 
@@ -259,6 +276,7 @@ CrewAI provides a wide range of events that you can listen for:
 - **LLMCallCompletedEvent**: Emitted when an LLM call completes
 - **LLMCallFailedEvent**: Emitted when an LLM call fails
 - **LLMStreamChunkEvent**: Emitted for each chunk received during streaming LLM responses
+- **LLMThinkingChunkEvent**: Emitted when a thinking/reasoning chunk is received from a thinking model. Contains the chunk text and optional response ID.
 
 ### Memory Events
 
@@ -270,6 +288,79 @@ CrewAI provides a wide range of events that you can listen for:
 - **MemorySaveFailedEvent**: Emitted when a memory save operation fails. Contains the value, metadata, agent role, and error message.
 - **MemoryRetrievalStartedEvent**: Emitted when memory retrieval for a task prompt starts. Contains the optional task ID.
 - **MemoryRetrievalCompletedEvent**: Emitted when memory retrieval for a task prompt completes successfully. Contains the task ID, memory content, and retrieval execution time.
+- **MemoryRetrievalFailedEvent**: Emitted when memory retrieval for a task prompt fails. Contains the optional task ID and error message.
+
+### Reasoning Events
+
+- **AgentReasoningStartedEvent**: Emitted when an agent starts reasoning about a task. Contains the agent role, task ID, and attempt number.
+- **AgentReasoningCompletedEvent**: Emitted when an agent finishes its reasoning process. Contains the agent role, task ID, the plan produced, and whether the agent is ready to proceed.
+- **AgentReasoningFailedEvent**: Emitted when the reasoning process fails. Contains the agent role, task ID, and error message.
+
+### Observation Events
+
+- **StepObservationStartedEvent**: Emitted when the Planner begins observing a step's result. Fires after every step execution, before the observation LLM call. Contains the agent role, step number, and step description.
+- **StepObservationCompletedEvent**: Emitted when the Planner finishes observing a step's result. Contains whether the step completed successfully, key information learned, whether the remaining plan is still valid, whether a full replan is needed, and suggested refinements.
+- **StepObservationFailedEvent**: Emitted when the observation LLM call itself fails. The system defaults to continuing the plan. Contains the error message.
+- **PlanRefinementEvent**: Emitted when the Planner refines upcoming step descriptions without a full replan. Contains the number of refined steps and the refinements applied.
+- **PlanReplanTriggeredEvent**: Emitted when the Planner triggers a full replan because the remaining plan was deemed fundamentally wrong. Contains the replan reason, replan count, and number of completed steps preserved.
+- **GoalAchievedEarlyEvent**: Emitted when the Planner detects the goal was achieved early and remaining steps will be skipped. Contains the number of steps remaining and steps completed.
+
+### A2A (Agent-to-Agent) Events
+
+#### Delegation Events
+
+- **A2ADelegationStartedEvent**: Emitted when A2A delegation starts. Contains the endpoint URL, task description, agent ID, context ID, whether it's multiturn, turn number, agent card metadata, protocol version, provider info, and optional skill ID.
+- **A2ADelegationCompletedEvent**: Emitted when A2A delegation completes. Contains the completion status (`completed`, `input_required`, `failed`, etc.), result, error message, context ID, and agent card metadata.
+- **A2AParallelDelegationStartedEvent**: Emitted when parallel delegation to multiple A2A agents begins. Contains the list of endpoints and the task description.
+- **A2AParallelDelegationCompletedEvent**: Emitted when parallel delegation to multiple A2A agents completes. Contains the list of endpoints, success count, failure count, and results summary.
+
+#### Conversation Events
+
+- **A2AConversationStartedEvent**: Emitted once at the beginning of a multiturn A2A conversation, before the first message exchange. Contains the agent ID, endpoint, context ID, agent card metadata, protocol version, and provider info.
+- **A2AMessageSentEvent**: Emitted when a message is sent to the A2A agent. Contains the message content, turn number, context ID, message ID, and whether it's multiturn.
+- **A2AResponseReceivedEvent**: Emitted when a response is received from the A2A agent. Contains the response content, turn number, context ID, message ID, status, and whether it's the final response.
+- **A2AConversationCompletedEvent**: Emitted once at the end of a multiturn A2A conversation. Contains the final status (`completed` or `failed`), final result, error message, context ID, and total number of turns.
+
+#### Streaming Events
+
+- **A2AStreamingStartedEvent**: Emitted when streaming mode begins for A2A delegation. Contains the task ID, context ID, endpoint, turn number, and whether it's multiturn.
+- **A2AStreamingChunkEvent**: Emitted when a streaming chunk is received. Contains the chunk text, chunk index, whether it's the final chunk, task ID, context ID, and turn number.
+
+#### Polling & Push Notification Events
+
+- **A2APollingStartedEvent**: Emitted when polling mode begins for A2A delegation. Contains the task ID, context ID, polling interval in seconds, and endpoint.
+- **A2APollingStatusEvent**: Emitted on each polling iteration. Contains the task ID, context ID, current task state, elapsed seconds, and poll count.
+- **A2APushNotificationRegisteredEvent**: Emitted when a push notification callback is registered. Contains the task ID, context ID, callback URL, and endpoint.
+- **A2APushNotificationReceivedEvent**: Emitted when a push notification is received from the remote A2A agent. Contains the task ID, context ID, and current state.
+- **A2APushNotificationSentEvent**: Emitted when a push notification is sent to a callback URL. Contains the task ID, context ID, callback URL, state, whether delivery succeeded, and optional error message.
+- **A2APushNotificationTimeoutEvent**: Emitted when push notification wait times out. Contains the task ID, context ID, and timeout duration in seconds.
+
+#### Connection & Authentication Events
+
+- **A2AAgentCardFetchedEvent**: Emitted when an agent card is successfully fetched. Contains the endpoint, agent name, agent card metadata, protocol version, provider info, whether it was cached, and fetch time in milliseconds.
+- **A2AAuthenticationFailedEvent**: Emitted when authentication to an A2A agent fails. Contains the endpoint, auth type attempted (e.g., `bearer`, `oauth2`, `api_key`), error message, and HTTP status code.
+- **A2AConnectionErrorEvent**: Emitted when a connection error occurs during A2A communication. Contains the endpoint, error message, error type (e.g., `timeout`, `connection_refused`, `dns_error`), HTTP status code, and the operation being attempted.
+- **A2ATransportNegotiatedEvent**: Emitted when transport protocol is negotiated with an A2A agent. Contains the negotiated transport, negotiated URL, selection source (`client_preferred`, `server_preferred`, `fallback`), and client/server supported transports.
+- **A2AContentTypeNegotiatedEvent**: Emitted when content types are negotiated with an A2A agent. Contains the client/server input/output modes, negotiated input/output modes, and whether negotiation succeeded.
+
+#### Artifact Events
+
+- **A2AArtifactReceivedEvent**: Emitted when an artifact is received from a remote A2A agent. Contains the task ID, artifact ID, artifact name, description, MIME type, size in bytes, and whether content should be appended.
+
+#### Server Task Events
+
+- **A2AServerTaskStartedEvent**: Emitted when an A2A server task execution starts. Contains the task ID and context ID.
+- **A2AServerTaskCompletedEvent**: Emitted when an A2A server task execution completes. Contains the task ID, context ID, and result.
+- **A2AServerTaskCanceledEvent**: Emitted when an A2A server task execution is canceled. Contains the task ID and context ID.
+- **A2AServerTaskFailedEvent**: Emitted when an A2A server task execution fails. Contains the task ID, context ID, and error message.
+
+#### Context Lifecycle Events
+
+- **A2AContextCreatedEvent**: Emitted when an A2A context is created. Contexts group related tasks in a conversation or workflow. Contains the context ID and creation timestamp.
+- **A2AContextExpiredEvent**: Emitted when an A2A context expires due to TTL. Contains the context ID, creation timestamp, age in seconds, and task count.
+- **A2AContextIdleEvent**: Emitted when an A2A context becomes idle (no activity for the configured threshold). Contains the context ID, idle time in seconds, and task count.
+- **A2AContextCompletedEvent**: Emitted when all tasks in an A2A context complete. Contains the context ID, total tasks, and duration in seconds.
+- **A2AContextPrunedEvent**: Emitted when an A2A context is pruned (deleted). Contains the context ID, task count, and age in seconds.
 
 ## Event Handler Structure
 

docs/en/guides/tools/publish-custom-tools.mdx

@@ -0,0 +1,244 @@
+---
+title: Publish Custom Tools
+description: How to build, package, and publish your own CrewAI-compatible tools to PyPI so any CrewAI user can install and use them.
+icon: box-open
+mode: "wide"
+---
+
+## Overview
+
+CrewAI's tool system is designed to be extended. If you've built a tool that could benefit others, you can package it as a standalone Python library, publish it to PyPI, and make it available to any CrewAI user — no PR to the CrewAI repo required.
+
+This guide walks through the full process: implementing the tools contract, structuring your package, and publishing to PyPI.
+
+<Note type="info" title="Not looking to publish?">
+If you just need a custom tool for your own project, see the [Create Custom Tools](/en/learn/create-custom-tools) guide instead.
+</Note>
+
+## The Tools Contract
+
+Every CrewAI tool must satisfy one of two interfaces:
+
+### Option 1: Subclass `BaseTool`
+
+Subclass `crewai.tools.BaseTool` and implement the `_run` method. Define `name`, `description`, and optionally an `args_schema` for input validation.
+
+```python
+from crewai.tools import BaseTool
+from pydantic import BaseModel, Field
+
+
+class GeolocateInput(BaseModel):
+    """Input schema for GeolocateTool."""
+    address: str = Field(..., description="The street address to geolocate.")
+
+
+class GeolocateTool(BaseTool):
+    name: str = "Geolocate"
+    description: str = "Converts a street address into latitude/longitude coordinates."
+    args_schema: type[BaseModel] = GeolocateInput
+
+    def _run(self, address: str) -> str:
+        # Your implementation here
+        return f"40.7128, -74.0060"
+```
+
+### Option 2: Use the `@tool` Decorator
+
+For simpler tools, the `@tool` decorator turns a function into a CrewAI tool. The function **must** have a docstring (used as the tool description) and type annotations.
+
+```python
+from crewai.tools import tool
+
+
+@tool("Geolocate")
+def geolocate(address: str) -> str:
+    """Converts a street address into latitude/longitude coordinates."""
+    return "40.7128, -74.0060"
+```
+
+### Key Requirements
+
+Regardless of which approach you use, your tool must:
+
+- Have a **`name`** — a short, descriptive identifier.
+- Have a **`description`** — tells the agent when and how to use the tool. This directly affects how well agents use your tool, so be clear and specific.
+- Implement **`_run`** (BaseTool) or provide a **function body** (@tool) — the synchronous execution logic.
+- Use **type annotations** on all parameters and return values.
+- Return a **string** result (or something that can be meaningfully converted to one).
+
+### Optional: Async Support
+
+If your tool performs I/O-bound work, implement `_arun` for async execution:
+
+```python
+class GeolocateTool(BaseTool):
+    name: str = "Geolocate"
+    description: str = "Converts a street address into latitude/longitude coordinates."
+
+    def _run(self, address: str) -> str:
+        # Sync implementation
+        ...
+
+    async def _arun(self, address: str) -> str:
+        # Async implementation
+        ...
+```
+
+### Optional: Input Validation with `args_schema`
+
+Define a Pydantic model as your `args_schema` to get automatic input validation and clear error messages. If you don't provide one, CrewAI will infer it from your `_run` method's signature.
+
+```python
+from pydantic import BaseModel, Field
+
+
+class TranslateInput(BaseModel):
+    """Input schema for TranslateTool."""
+    text: str = Field(..., description="The text to translate.")
+    target_language: str = Field(
+        default="en",
+        description="ISO 639-1 language code for the target language.",
+    )
+```
+
+Explicit schemas are recommended for published tools — they produce better agent behavior and clearer documentation for your users.
+
+### Optional: Environment Variables
+
+If your tool requires API keys or other configuration, declare them with `env_vars` so users know what to set:
+
+```python
+from crewai.tools import BaseTool, EnvVar
+
+
+class GeolocateTool(BaseTool):
+    name: str = "Geolocate"
+    description: str = "Converts a street address into latitude/longitude coordinates."
+    env_vars: list[EnvVar] = [
+        EnvVar(
+            name="GEOCODING_API_KEY",
+            description="API key for the geocoding service.",
+            required=True,
+        ),
+    ]
+
+    def _run(self, address: str) -> str:
+        ...
+```
+
+## Package Structure
+
+Structure your project as a standard Python package. Here's a recommended layout:
+
+```
+crewai-geolocate/
+├── pyproject.toml
+├── LICENSE
+├── README.md
+└── src/
+    └── crewai_geolocate/
+        ├── __init__.py
+        └── tools.py
+```
+
+### `pyproject.toml`
+
+```toml
+[project]
+name = "crewai-geolocate"
+version = "0.1.0"
+description = "A CrewAI tool for geolocating street addresses."
+requires-python = ">=3.10"
+dependencies = [
+    "crewai",
+]
+
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+```
+
+Declare `crewai` as a dependency so users get a compatible version automatically.
+
+### `__init__.py`
+
+Re-export your tool classes so users can import them directly:
+
+```python
+from crewai_geolocate.tools import GeolocateTool
+
+__all__ = ["GeolocateTool"]
+```
+
+### Naming Conventions
+
+- **Package name**: Use the prefix `crewai-` (e.g., `crewai-geolocate`). This makes your tool discoverable when users search PyPI.
+- **Module name**: Use underscores (e.g., `crewai_geolocate`).
+- **Tool class name**: Use PascalCase ending in `Tool` (e.g., `GeolocateTool`).
+
+## Testing Your Tool
+
+Before publishing, verify your tool works within a crew:
+
+```python
+from crewai import Agent, Crew, Task
+from crewai_geolocate import GeolocateTool
+
+agent = Agent(
+    role="Location Analyst",
+    goal="Find coordinates for given addresses.",
+    backstory="An expert in geospatial data.",
+    tools=[GeolocateTool()],
+)
+
+task = Task(
+    description="Find the coordinates of 1600 Pennsylvania Avenue, Washington, DC.",
+    expected_output="The latitude and longitude of the address.",
+    agent=agent,
+)
+
+crew = Crew(agents=[agent], tasks=[task])
+result = crew.kickoff()
+print(result)
+```
+
+## Publishing to PyPI
+
+Once your tool is tested and ready:
+
+```bash
+# Build the package
+uv build
+
+# Publish to PyPI
+uv publish
+```
+
+If this is your first time publishing, you'll need a [PyPI account](https://pypi.org/account/register/) and an [API token](https://pypi.org/help/#apitoken).
+
+### After Publishing
+
+Users can install your tool with:
+
+```bash
+pip install crewai-geolocate
+```
+
+Or with uv:
+
+```bash
+uv add crewai-geolocate
+```
+
+Then use it in their crews:
+
+```python
+from crewai_geolocate import GeolocateTool
+
+agent = Agent(
+    role="Location Analyst",
+    tools=[GeolocateTool()],
+    # ...
+)
+```

docs/en/learn/create-custom-tools.mdx

@@ -11,6 +11,10 @@ This guide provides detailed instructions on creating custom tools for the CrewA
 incorporating the latest functionalities such as tool delegation, error handling, and dynamic tool calling. It also highlights the importance of collaboration tools,
 enabling agents to perform a wide range of actions.
 
+<Tip>
+  **Want to publish your tool for the community?** If you're building a tool that others could benefit from, check out the [Publish Custom Tools](/en/guides/tools/publish-custom-tools) guide to learn how to package and distribute your tool on PyPI.
+</Tip>
+
 ### Subclassing `BaseTool`
 
 To create a personalized tool, inherit from `BaseTool` and define the necessary attributes, including the `args_schema` for input validation, and the `_run` method.

docs/ko/concepts/event-listener.mdx

@@ -195,12 +195,19 @@ CrewAI는 여러분이 청취할 수 있는 다양한 이벤트를 제공합니
 - **CrewTrainStartedEvent**: Crew가 훈련을 시작할 때 발생
 - **CrewTrainCompletedEvent**: Crew가 훈련을 완료할 때 발생
 - **CrewTrainFailedEvent**: Crew가 훈련을 완료하지 못할 때 발생
+- **CrewTestResultEvent**: Crew 테스트 결과가 사용 가능할 때 발생합니다. 품질 점수, 실행 시간, 사용된 모델을 포함합니다.
 
 ### 에이전트 이벤트
 
 - **AgentExecutionStartedEvent**: 에이전트가 작업 실행을 시작할 때 발생함
 - **AgentExecutionCompletedEvent**: 에이전트가 작업 실행을 완료할 때 발생함
 - **AgentExecutionErrorEvent**: 에이전트가 실행 도중 오류를 만날 때 발생함
+- **LiteAgentExecutionStartedEvent**: LiteAgent가 실행을 시작할 때 발생합니다. 에이전트 정보, 도구, 메시지를 포함합니다.
+- **LiteAgentExecutionCompletedEvent**: LiteAgent가 실행을 완료할 때 발생합니다. 에이전트 정보와 출력을 포함합니다.
+- **LiteAgentExecutionErrorEvent**: LiteAgent가 실행 중 오류를 만날 때 발생합니다. 에이전트 정보와 오류 메시지를 포함합니다.
+- **AgentEvaluationStartedEvent**: 에이전트 평가가 시작될 때 발생합니다. 에이전트 ID, 에이전트 역할, 선택적 태스크 ID, 반복 횟수를 포함합니다.
+- **AgentEvaluationCompletedEvent**: 에이전트 평가가 완료될 때 발생합니다. 에이전트 ID, 에이전트 역할, 선택적 태스크 ID, 반복 횟수, 메트릭 카테고리, 점수를 포함합니다.
+- **AgentEvaluationFailedEvent**: 에이전트 평가가 실패할 때 발생합니다. 에이전트 ID, 에이전트 역할, 선택적 태스크 ID, 반복 횟수, 오류 메시지를 포함합니다.
 
 ### 작업 이벤트
 
@@ -218,6 +225,16 @@ CrewAI는 여러분이 청취할 수 있는 다양한 이벤트를 제공합니
 - **ToolExecutionErrorEvent**: 도구 실행 중 오류가 발생할 때 발생함
 - **ToolSelectionErrorEvent**: 도구 선택 시 오류가 발생할 때 발생함
 
+### MCP 이벤트
+
+- **MCPConnectionStartedEvent**: MCP 서버 연결을 시작할 때 발생합니다. 서버 이름, URL, 전송 유형, 연결 시간 초과, 재연결 시도 여부를 포함합니다.
+- **MCPConnectionCompletedEvent**: MCP 서버에 성공적으로 연결될 때 발생합니다. 서버 이름, 연결 시간(밀리초), 재연결 여부를 포함합니다.
+- **MCPConnectionFailedEvent**: MCP 서버 연결이 실패할 때 발생합니다. 서버 이름, 오류 메시지, 오류 유형(`timeout`, `authentication`, `network` 등)을 포함합니다.
+- **MCPToolExecutionStartedEvent**: MCP 도구 실행을 시작할 때 발생합니다. 서버 이름, 도구 이름, 도구 인수를 포함합니다.
+- **MCPToolExecutionCompletedEvent**: MCP 도구 실행이 성공적으로 완료될 때 발생합니다. 서버 이름, 도구 이름, 결과, 실행 시간(밀리초)을 포함합니다.
+- **MCPToolExecutionFailedEvent**: MCP 도구 실행이 실패할 때 발생합니다. 서버 이름, 도구 이름, 오류 메시지, 오류 유형(`timeout`, `validation`, `server_error` 등)을 포함합니다.
+- **MCPConfigFetchFailedEvent**: MCP 서버 구성을 가져오는 데 실패할 때 발생합니다(예: 계정에서 MCP가 연결되지 않았거나, API 오류, 구성을 가져온 후 연결 실패). slug, 오류 메시지, 오류 유형(`not_connected`, `api_error`, `connection_failed`)을 포함합니다.
+
 ### 지식 이벤트
 
 - **KnowledgeRetrievalStartedEvent**: 지식 검색이 시작될 때 발생
@@ -231,16 +248,26 @@ CrewAI는 여러분이 청취할 수 있는 다양한 이벤트를 제공합니
 
 - **LLMGuardrailStartedEvent**: 가드레일 검증이 시작될 때 발생합니다. 적용되는 가드레일에 대한 세부 정보와 재시도 횟수를 포함합니다.
 - **LLMGuardrailCompletedEvent**: 가드레일 검증이 완료될 때 발생합니다. 검증의 성공/실패, 결과 및 오류 메시지(있는 경우)에 대한 세부 정보를 포함합니다.
+- **LLMGuardrailFailedEvent**: 가드레일 검증이 실패할 때 발생합니다. 오류 메시지와 재시도 횟수를 포함합니다.
 
 ### Flow 이벤트
 
 - **FlowCreatedEvent**: Flow가 생성될 때 발생
 - **FlowStartedEvent**: Flow가 실행을 시작할 때 발생
 - **FlowFinishedEvent**: Flow가 실행을 완료할 때 발생
+- **FlowPausedEvent**: 사람의 피드백을 기다리며 Flow가 일시 중지될 때 발생합니다. Flow 이름, Flow ID, 메서드 이름, 현재 상태, 피드백 요청 시 표시되는 메시지, 라우팅을 위한 선택적 결과 목록을 포함합니다.
 - **FlowPlotEvent**: Flow가 플롯될 때 발생
 - **MethodExecutionStartedEvent**: Flow 메서드가 실행을 시작할 때 발생
 - **MethodExecutionFinishedEvent**: Flow 메서드가 실행을 완료할 때 발생
 - **MethodExecutionFailedEvent**: Flow 메서드가 실행을 완료하지 못할 때 발생
+- **MethodExecutionPausedEvent**: 사람의 피드백을 기다리며 Flow 메서드가 일시 중지될 때 발생합니다. Flow 이름, 메서드 이름, 현재 상태, Flow ID, 피드백 요청 시 표시되는 메시지, 라우팅을 위한 선택적 결과 목록을 포함합니다.
+
+### Human In The Loop 이벤트
+
+- **FlowInputRequestedEvent**: `Flow.ask()`를 통해 Flow가 사용자 입력을 요청할 때 발생합니다. Flow 이름, 메서드 이름, 사용자에게 표시되는 질문 또는 프롬프트, 선택적 메타데이터(예: 사용자 ID, 채널, 세션 컨텍스트)를 포함합니다.
+- **FlowInputReceivedEvent**: `Flow.ask()` 이후 사용자 입력이 수신될 때 발생합니다. Flow 이름, 메서드 이름, 원래 질문, 사용자의 응답(시간 초과 시 `None`), 선택적 요청 메타데이터, 프로바이더의 선택적 응답 메타데이터(예: 응답자, 스레드 ID, 타임스탬프)를 포함합니다.
+- **HumanFeedbackRequestedEvent**: `@human_feedback` 데코레이터가 적용된 메서드가 사람 리뷰어의 입력을 필요로 할 때 발생합니다. Flow 이름, 메서드 이름, 사람에게 검토를 위해 표시되는 메서드 출력, 피드백 요청 시 표시되는 메시지, 라우팅을 위한 선택적 결과 목록을 포함합니다.
+- **HumanFeedbackReceivedEvent**: `@human_feedback` 데코레이터가 적용된 메서드에 대해 사람이 피드백을 제공할 때 발생합니다. Flow 이름, 메서드 이름, 사람이 제공한 원본 텍스트 피드백, 축약된 결과 문자열(emit이 지정된 경우)을 포함합니다.
 
 ### LLM 이벤트
 
@@ -248,6 +275,7 @@ CrewAI는 여러분이 청취할 수 있는 다양한 이벤트를 제공합니
 - **LLMCallCompletedEvent**: LLM 호출이 완료될 때 발생
 - **LLMCallFailedEvent**: LLM 호출이 실패할 때 발생
 - **LLMStreamChunkEvent**: 스트리밍 LLM 응답 중 각 청크를 받을 때마다 발생
+- **LLMThinkingChunkEvent**: thinking 모델에서 사고/추론 청크가 수신될 때 발생합니다. 청크 텍스트와 선택적 응답 ID를 포함합니다.
 
 ### 메모리 이벤트
 
@@ -259,6 +287,79 @@ CrewAI는 여러분이 청취할 수 있는 다양한 이벤트를 제공합니
 - **MemorySaveFailedEvent**: 메모리 저장 작업에 실패할 때 발생합니다. 값, 메타데이터, agent 역할, 오류 메시지를 포함합니다.
 - **MemoryRetrievalStartedEvent**: 태스크 프롬프트를 위한 메모리 검색이 시작될 때 발생합니다. 선택적 태스크 ID를 포함합니다.
 - **MemoryRetrievalCompletedEvent**: 태스크 프롬프트를 위한 메모리 검색이 성공적으로 완료될 때 발생합니다. 태스크 ID, 메모리 내용, 검색 실행 시간을 포함합니다.
+- **MemoryRetrievalFailedEvent**: 태스크 프롬프트를 위한 메모리 검색이 실패할 때 발생합니다. 선택적 태스크 ID와 오류 메시지를 포함합니다.
+
+### 추론 이벤트
+
+- **AgentReasoningStartedEvent**: 에이전트가 태스크에 대한 추론을 시작할 때 발생합니다. 에이전트 역할, 태스크 ID, 시도 횟수를 포함합니다.
+- **AgentReasoningCompletedEvent**: 에이전트가 추론 과정을 마칠 때 발생합니다. 에이전트 역할, 태스크 ID, 생성된 계획, 에이전트가 진행할 준비가 되었는지 여부를 포함합니다.
+- **AgentReasoningFailedEvent**: 추론 과정이 실패할 때 발생합니다. 에이전트 역할, 태스크 ID, 오류 메시지를 포함합니다.
+
+### 관찰 이벤트
+
+- **StepObservationStartedEvent**: Planner가 단계 결과를 관찰하기 시작할 때 발생합니다. 매 단계 실행 후, 관찰 LLM 호출 전에 발생합니다. 에이전트 역할, 단계 번호, 단계 설명을 포함합니다.
+- **StepObservationCompletedEvent**: Planner가 단계 결과 관찰을 마칠 때 발생합니다. 단계 성공 여부, 학습된 핵심 정보, 남은 계획의 유효성, 전체 재계획 필요 여부, 제안된 개선 사항을 포함합니다.
+- **StepObservationFailedEvent**: 관찰 LLM 호출 자체가 실패할 때 발생합니다. 시스템은 기본적으로 계획을 계속 진행합니다. 오류 메시지를 포함합니다.
+- **PlanRefinementEvent**: Planner가 전체 재계획 없이 다음 단계 설명을 개선할 때 발생합니다. 개선된 단계 수와 적용된 개선 사항을 포함합니다.
+- **PlanReplanTriggeredEvent**: 남은 계획이 근본적으로 잘못된 것으로 판단되어 Planner가 전체 재계획을 트리거할 때 발생합니다. 재계획 이유, 재계획 횟수, 보존된 완료 단계 수를 포함합니다.
+- **GoalAchievedEarlyEvent**: Planner가 목표가 조기에 달성되었음을 감지하고 나머지 단계를 건너뛸 때 발생합니다. 남은 단계 수와 완료된 단계 수를 포함합니다.
+
+### A2A (Agent-to-Agent) 이벤트
+
+#### 위임 이벤트
+
+- **A2ADelegationStartedEvent**: A2A 위임이 시작될 때 발생합니다. 엔드포인트 URL, 태스크 설명, 에이전트 ID, 컨텍스트 ID, 멀티턴 여부, 턴 번호, agent card 메타데이터, 프로토콜 버전, 프로바이더 정보, 선택적 skill ID를 포함합니다.
+- **A2ADelegationCompletedEvent**: A2A 위임이 완료될 때 발생합니다. 완료 상태(`completed`, `input_required`, `failed` 등), 결과, 오류 메시지, 컨텍스트 ID, agent card 메타데이터를 포함합니다.
+- **A2AParallelDelegationStartedEvent**: 여러 A2A 에이전트로의 병렬 위임이 시작될 때 발생합니다. 엔드포인트 목록과 태스크 설명을 포함합니다.
+- **A2AParallelDelegationCompletedEvent**: 여러 A2A 에이전트로의 병렬 위임이 완료될 때 발생합니다. 엔드포인트 목록, 성공 수, 실패 수, 결과 요약을 포함합니다.
+
+#### 대화 이벤트
+
+- **A2AConversationStartedEvent**: 멀티턴 A2A 대화 시작 시 한 번 발생합니다. 첫 번째 메시지 교환 전에 발생합니다. 에이전트 ID, 엔드포인트, 컨텍스트 ID, agent card 메타데이터, 프로토콜 버전, 프로바이더 정보를 포함합니다.
+- **A2AMessageSentEvent**: A2A 에이전트에 메시지가 전송될 때 발생합니다. 메시지 내용, 턴 번호, 컨텍스트 ID, 메시지 ID, 멀티턴 여부를 포함합니다.
+- **A2AResponseReceivedEvent**: A2A 에이전트로부터 응답이 수신될 때 발생합니다. 응답 내용, 턴 번호, 컨텍스트 ID, 메시지 ID, 상태, 최종 응답 여부를 포함합니다.
+- **A2AConversationCompletedEvent**: 멀티턴 A2A 대화 종료 시 한 번 발생합니다. 최종 상태(`completed` 또는 `failed`), 최종 결과, 오류 메시지, 컨텍스트 ID, 총 턴 수를 포함합니다.
+
+#### 스트리밍 이벤트
+
+- **A2AStreamingStartedEvent**: A2A 위임을 위한 스트리밍 모드가 시작될 때 발생합니다. 태스크 ID, 컨텍스트 ID, 엔드포인트, 턴 번호, 멀티턴 여부를 포함합니다.
+- **A2AStreamingChunkEvent**: 스트리밍 청크가 수신될 때 발생합니다. 청크 텍스트, 청크 인덱스, 최종 청크 여부, 태스크 ID, 컨텍스트 ID, 턴 번호를 포함합니다.
+
+#### 폴링 및 푸시 알림 이벤트
+
+- **A2APollingStartedEvent**: A2A 위임을 위한 폴링 모드가 시작될 때 발생합니다. 태스크 ID, 컨텍스트 ID, 폴링 간격(초), 엔드포인트를 포함합니다.
+- **A2APollingStatusEvent**: 각 폴링 반복 시 발생합니다. 태스크 ID, 컨텍스트 ID, 현재 태스크 상태, 경과 시간, 폴링 횟수를 포함합니다.
+- **A2APushNotificationRegisteredEvent**: 푸시 알림 콜백이 등록될 때 발생합니다. 태스크 ID, 컨텍스트 ID, 콜백 URL, 엔드포인트를 포함합니다.
+- **A2APushNotificationReceivedEvent**: 원격 A2A 에이전트로부터 푸시 알림이 수신될 때 발생합니다. 태스크 ID, 컨텍스트 ID, 현재 상태를 포함합니다.
+- **A2APushNotificationSentEvent**: 콜백 URL로 푸시 알림이 전송될 때 발생합니다. 태스크 ID, 컨텍스트 ID, 콜백 URL, 상태, 전달 성공 여부, 선택적 오류 메시지를 포함합니다.
+- **A2APushNotificationTimeoutEvent**: 푸시 알림 대기가 시간 초과될 때 발생합니다. 태스크 ID, 컨텍스트 ID, 시간 초과 시간(초)을 포함합니다.
+
+#### 연결 및 인증 이벤트
+
+- **A2AAgentCardFetchedEvent**: agent card가 성공적으로 가져올 때 발생합니다. 엔드포인트, 에이전트 이름, agent card 메타데이터, 프로토콜 버전, 프로바이더 정보, 캐시 여부, 가져오기 시간(밀리초)을 포함합니다.
+- **A2AAuthenticationFailedEvent**: A2A 에이전트 인증이 실패할 때 발생합니다. 엔드포인트, 시도된 인증 유형(예: `bearer`, `oauth2`, `api_key`), 오류 메시지, HTTP 상태 코드를 포함합니다.
+- **A2AConnectionErrorEvent**: A2A 통신 중 연결 오류가 발생할 때 발생합니다. 엔드포인트, 오류 메시지, 오류 유형(예: `timeout`, `connection_refused`, `dns_error`), HTTP 상태 코드, 시도 중인 작업을 포함합니다.
+- **A2ATransportNegotiatedEvent**: A2A 에이전트와 전송 프로토콜이 협상될 때 발생합니다. 협상된 전송, 협상된 URL, 선택 소스(`client_preferred`, `server_preferred`, `fallback`), 클라이언트/서버 지원 전송을 포함합니다.
+- **A2AContentTypeNegotiatedEvent**: A2A 에이전트와 콘텐츠 유형이 협상될 때 발생합니다. 클라이언트/서버 입출력 모드, 협상된 입출력 모드, 협상 성공 여부를 포함합니다.
+
+#### 아티팩트 이벤트
+
+- **A2AArtifactReceivedEvent**: 원격 A2A 에이전트로부터 아티팩트가 수신될 때 발생합니다. 태스크 ID, 아티팩트 ID, 아티팩트 이름, 설명, MIME 유형, 크기(바이트), 콘텐츠 추가 여부를 포함합니다.
+
+#### 서버 태스크 이벤트
+
+- **A2AServerTaskStartedEvent**: A2A 서버 태스크 실행이 시작될 때 발생합니다. 태스크 ID와 컨텍스트 ID를 포함합니다.
+- **A2AServerTaskCompletedEvent**: A2A 서버 태스크 실행이 완료될 때 발생합니다. 태스크 ID, 컨텍스트 ID, 결과를 포함합니다.
+- **A2AServerTaskCanceledEvent**: A2A 서버 태스크 실행이 취소될 때 발생합니다. 태스크 ID와 컨텍스트 ID를 포함합니다.
+- **A2AServerTaskFailedEvent**: A2A 서버 태스크 실행이 실패할 때 발생합니다. 태스크 ID, 컨텍스트 ID, 오류 메시지를 포함합니다.
+
+#### 컨텍스트 수명 주기 이벤트
+
+- **A2AContextCreatedEvent**: A2A 컨텍스트가 생성될 때 발생합니다. 컨텍스트는 대화 또는 워크플로우에서 관련 태스크를 그룹화합니다. 컨텍스트 ID와 생성 타임스탬프를 포함합니다.
+- **A2AContextExpiredEvent**: TTL로 인해 A2A 컨텍스트가 만료될 때 발생합니다. 컨텍스트 ID, 생성 타임스탬프, 수명(초), 태스크 수를 포함합니다.
+- **A2AContextIdleEvent**: A2A 컨텍스트가 유휴 상태가 될 때(설정된 임계값 동안 활동 없음) 발생합니다. 컨텍스트 ID, 유휴 시간(초), 태스크 수를 포함합니다.
+- **A2AContextCompletedEvent**: A2A 컨텍스트의 모든 태스크가 완료될 때 발생합니다. 컨텍스트 ID, 총 태스크 수, 지속 시간(초)을 포함합니다.
+- **A2AContextPrunedEvent**: A2A 컨텍스트가 정리(삭제)될 때 발생합니다. 컨텍스트 ID, 태스크 수, 수명(초)을 포함합니다.
 
 ## 이벤트 핸들러 구조
 

docs/ko/guides/coding-tools/agents-md.mdx

@@ -0,0 +1,61 @@
+---
+title: 코딩 도구
+description: AGENTS.md를 사용하여 CrewAI 프로젝트 전반에서 코딩 에이전트와 IDE를 안내합니다.
+icon: terminal
+mode: "wide"
+---
+
+## AGENTS.md를 사용하는 이유
+
+`AGENTS.md`는 가벼운 저장소 로컬 지침 파일로, 코딩 에이전트에게 일관되고 프로젝트별 안내를 제공합니다. 프로젝트 루트에 배치하고 어시스턴트가 작업하는 방식(컨벤션, 명령어, 아키텍처 노트, 가드레일)에 대한 신뢰할 수 있는 소스로 활용하세요.
+
+## CLI로 프로젝트 생성
+
+CrewAI CLI를 사용하여 프로젝트를 스캐폴딩하면, `AGENTS.md`가 루트에 자동으로 추가됩니다.
+
+```bash
+# Crew
+crewai create crew my_crew
+
+# Flow
+crewai create flow my_flow
+
+# Tool repository
+crewai tool create my_tool
+```
+
+## 도구 설정: 어시스턴트에 AGENTS.md 연결
+
+### Codex
+
+Codex는 저장소에 배치된 `AGENTS.md` 파일로 안내할 수 있습니다. 컨벤션, 명령어, 워크플로우 기대치 등 지속적인 프로젝트 컨텍스트를 제공하는 데 사용하세요.
+
+### Claude Code
+
+Claude Code는 프로젝트 메모리를 `CLAUDE.md`에 저장합니다. `/init`으로 부트스트랩하고 `/memory`로 편집할 수 있습니다. Claude Code는 `CLAUDE.md` 내에서 임포트도 지원하므로, `@AGENTS.md`와 같은 한 줄을 추가하여 공유 지침을 중복 없이 가져올 수 있습니다.
+
+간단하게 다음과 같이 사용할 수 있습니다:
+
+```bash
+mv AGENTS.md CLAUDE.md
+```
+
+### Gemini CLI와 Google Antigravity
+
+Gemini CLI와 Antigravity는 저장소 루트 및 상위 디렉토리에서 프로젝트 컨텍스트 파일(기본값: `GEMINI.md`)을 로드합니다. Gemini CLI 설정에서 `context.fileName`을 설정하여 `AGENTS.md`를 대신(또는 추가로) 읽도록 구성할 수 있습니다. 예를 들어, `AGENTS.md`만 설정하거나 각 도구의 형식을 유지하고 싶다면 `AGENTS.md`와 `GEMINI.md`를 모두 포함할 수 있습니다.
+
+간단하게 다음과 같이 사용할 수 있습니다:
+
+```bash
+mv AGENTS.md GEMINI.md
+```
+
+### Cursor
+
+Cursor는 `AGENTS.md`를 프로젝트 지침 파일로 지원합니다. 프로젝트 루트에 배치하여 Cursor의 코딩 어시스턴트에 안내를 제공하세요.
+
+### Windsurf
+
+Claude Code는 Windsurf와의 공식 통합을 제공합니다. Windsurf 내에서 Claude Code를 사용하는 경우, 위의 Claude Code 안내를 따르고 `CLAUDE.md`에서 `AGENTS.md`를 임포트하세요.
+
+Windsurf의 네이티브 어시스턴트를 사용하는 경우, 프로젝트 규칙 또는 지침 기능(사용 가능한 경우)을 구성하여 `AGENTS.md`에서 읽거나 내용을 직접 붙여넣으세요.

docs/ko/guides/tools/publish-custom-tools.mdx

@@ -0,0 +1,244 @@
+---
+title: 커스텀 도구 배포하기
+description: PyPI에 게시할 수 있는 CrewAI 호환 도구를 빌드, 패키징, 배포하는 방법을 안내합니다.
+icon: box-open
+mode: "wide"
+---
+
+## 개요
+
+CrewAI의 도구 시스템은 확장 가능하도록 설계되었습니다. 다른 사용자에게도 유용한 도구를 만들었다면, 독립적인 Python 라이브러리로 패키징하여 PyPI에 게시하고 모든 CrewAI 사용자가 사용할 수 있도록 할 수 있습니다. CrewAI 저장소에 PR을 보낼 필요가 없습니다.
+
+이 가이드에서는 도구 계약 구현, 패키지 구조화, PyPI 게시까지의 전체 과정을 안내합니다.
+
+<Note type="info" title="배포할 계획이 없으신가요?">
+프로젝트 내에서만 사용할 커스텀 도구가 필요하다면 [커스텀 도구 생성](/ko/learn/create-custom-tools) 가이드를 참고하세요.
+</Note>
+
+## 도구 계약
+
+모든 CrewAI 도구는 다음 두 가지 인터페이스 중 하나를 충족해야 합니다:
+
+### 옵션 1: `BaseTool` 서브클래싱
+
+`crewai.tools.BaseTool`을 서브클래싱하고 `_run` 메서드를 구현합니다. `name`, `description`, 그리고 선택적으로 입력 검증을 위한 `args_schema`를 정의합니다.
+
+```python
+from crewai.tools import BaseTool
+from pydantic import BaseModel, Field
+
+
+class GeolocateInput(BaseModel):
+    """GeolocateTool의 입력 스키마."""
+    address: str = Field(..., description="지오코딩할 도로명 주소.")
+
+
+class GeolocateTool(BaseTool):
+    name: str = "Geolocate"
+    description: str = "도로명 주소를 위도/경도 좌표로 변환합니다."
+    args_schema: type[BaseModel] = GeolocateInput
+
+    def _run(self, address: str) -> str:
+        # 구현 로직
+        return f"40.7128, -74.0060"
+```
+
+### 옵션 2: `@tool` 데코레이터 사용
+
+간단한 도구의 경우, `@tool` 데코레이터로 함수를 CrewAI 도구로 변환할 수 있습니다. 함수에는 반드시 독스트링(도구 설명으로 사용됨)과 타입 어노테이션이 있어야 합니다.
+
+```python
+from crewai.tools import tool
+
+
+@tool("Geolocate")
+def geolocate(address: str) -> str:
+    """도로명 주소를 위도/경도 좌표로 변환합니다."""
+    return "40.7128, -74.0060"
+```
+
+### 핵심 요구사항
+
+어떤 방식을 사용하든, 도구는 다음을 충족해야 합니다:
+
+- **`name`** — 짧고 설명적인 식별자.
+- **`description`** — 에이전트에게 도구를 언제, 어떻게 사용할지 알려줍니다. 에이전트가 도구를 얼마나 잘 활용하는지에 직접적으로 영향을 미치므로 명확하고 구체적으로 작성하세요.
+- **`_run`** (BaseTool) 또는 **함수 본문** (@tool) 구현 — 동기 실행 로직.
+- 모든 매개변수와 반환 값에 **타입 어노테이션** 사용.
+- **문자열** 결과를 반환 (또는 의미 있게 문자열로 변환 가능한 값).
+
+### 선택사항: 비동기 지원
+
+I/O 바운드 작업을 수행하는 도구의 경우 비동기 실행을 위해 `_arun`을 구현합니다:
+
+```python
+class GeolocateTool(BaseTool):
+    name: str = "Geolocate"
+    description: str = "도로명 주소를 위도/경도 좌표로 변환합니다."
+
+    def _run(self, address: str) -> str:
+        # 동기 구현
+        ...
+
+    async def _arun(self, address: str) -> str:
+        # 비동기 구현
+        ...
+```
+
+### 선택사항: `args_schema`를 통한 입력 검증
+
+Pydantic 모델을 `args_schema`로 정의하면 자동 입력 검증과 명확한 에러 메시지를 받을 수 있습니다. 제공하지 않으면 CrewAI가 `_run` 메서드의 시그니처에서 추론합니다.
+
+```python
+from pydantic import BaseModel, Field
+
+
+class TranslateInput(BaseModel):
+    """TranslateTool의 입력 스키마."""
+    text: str = Field(..., description="번역할 텍스트.")
+    target_language: str = Field(
+        default="en",
+        description="대상 언어의 ISO 639-1 언어 코드.",
+    )
+```
+
+배포용 도구에는 명시적 스키마를 권장합니다 — 에이전트 동작이 개선되고 사용자에게 더 명확한 문서를 제공합니다.
+
+### 선택사항: 환경 변수
+
+도구에 API 키나 기타 설정이 필요한 경우, `env_vars`로 선언하여 사용자가 무엇을 설정해야 하는지 알 수 있도록 합니다:
+
+```python
+from crewai.tools import BaseTool, EnvVar
+
+
+class GeolocateTool(BaseTool):
+    name: str = "Geolocate"
+    description: str = "도로명 주소를 위도/경도 좌표로 변환합니다."
+    env_vars: list[EnvVar] = [
+        EnvVar(
+            name="GEOCODING_API_KEY",
+            description="지오코딩 서비스 API 키.",
+            required=True,
+        ),
+    ]
+
+    def _run(self, address: str) -> str:
+        ...
+```
+
+## 패키지 구조
+
+프로젝트를 표준 Python 패키지로 구성합니다. 권장 레이아웃:
+
+```
+crewai-geolocate/
+├── pyproject.toml
+├── LICENSE
+├── README.md
+└── src/
+    └── crewai_geolocate/
+        ├── __init__.py
+        └── tools.py
+```
+
+### `pyproject.toml`
+
+```toml
+[project]
+name = "crewai-geolocate"
+version = "0.1.0"
+description = "도로명 주소를 지오코딩하는 CrewAI 도구."
+requires-python = ">=3.10"
+dependencies = [
+    "crewai",
+]
+
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+```
+
+사용자가 자동으로 호환 버전을 받을 수 있도록 `crewai`를 의존성으로 선언합니다.
+
+### `__init__.py`
+
+사용자가 직접 import할 수 있도록 도구 클래스를 re-export합니다:
+
+```python
+from crewai_geolocate.tools import GeolocateTool
+
+__all__ = ["GeolocateTool"]
+```
+
+### 명명 규칙
+
+- **패키지 이름**: `crewai-` 접두사를 사용합니다 (예: `crewai-geolocate`). PyPI에서 검색할 때 도구를 쉽게 찾을 수 있습니다.
+- **모듈 이름**: 밑줄을 사용합니다 (예: `crewai_geolocate`).
+- **도구 클래스 이름**: `Tool`로 끝나는 PascalCase를 사용합니다 (예: `GeolocateTool`).
+
+## 도구 테스트
+
+게시 전에 도구가 크루 내에서 작동하는지 확인합니다:
+
+```python
+from crewai import Agent, Crew, Task
+from crewai_geolocate import GeolocateTool
+
+agent = Agent(
+    role="Location Analyst",
+    goal="주어진 주소의 좌표를 찾습니다.",
+    backstory="지리공간 데이터 전문가.",
+    tools=[GeolocateTool()],
+)
+
+task = Task(
+    description="1600 Pennsylvania Avenue, Washington, DC의 좌표를 찾으세요.",
+    expected_output="해당 주소의 위도와 경도.",
+    agent=agent,
+)
+
+crew = Crew(agents=[agent], tasks=[task])
+result = crew.kickoff()
+print(result)
+```
+
+## PyPI에 게시하기
+
+도구 테스트를 완료하고 준비가 되면:
+
+```bash
+# 패키지 빌드
+uv build
+
+# PyPI에 게시
+uv publish
+```
+
+처음 게시하는 경우 [PyPI 계정](https://pypi.org/account/register/)과 [API 토큰](https://pypi.org/help/#apitoken)이 필요합니다.
+
+### 게시 후
+
+사용자는 다음과 같이 도구를 설치할 수 있습니다:
+
+```bash
+pip install crewai-geolocate
+```
+
+또는 uv를 사용하여:
+
+```bash
+uv add crewai-geolocate
+```
+
+그런 다음 크루에서 사용합니다:
+
+```python
+from crewai_geolocate import GeolocateTool
+
+agent = Agent(
+    role="Location Analyst",
+    tools=[GeolocateTool()],
+    # ...
+)
+```

docs/ko/learn/create-custom-tools.mdx

@@ -9,6 +9,10 @@ mode: "wide"
 
 이 가이드는 CrewAI 프레임워크를 위한 커스텀 툴을 생성하는 방법과 최신 기능(툴 위임, 오류 처리, 동적 툴 호출 등)을 통합하여 이러한 툴을 효율적으로 관리하고 활용하는 방법에 대해 자세히 안내합니다. 또한 협업 툴의 중요성을 강조하며, 에이전트가 다양한 작업을 수행할 수 있도록 지원합니다.
 
+<Tip>
+  **커뮤니티에 도구를 배포하고 싶으신가요?** 다른 사용자에게도 유용한 도구를 만들고 있다면, [커스텀 도구 배포하기](/ko/guides/tools/publish-custom-tools) 가이드에서 도구를 패키징하고 PyPI에 배포하는 방법을 알아보세요.
+</Tip>
+
 ### `BaseTool` 서브클래싱
 
 개인화된 툴을 생성하려면 `BaseTool`을 상속받고, 입력 검증을 위한 `args_schema`와 `_run` 메서드를 포함한 필요한 속성들을 정의해야 합니다.

docs/pt-BR/concepts/event-listener.mdx

@@ -196,12 +196,19 @@ O CrewAI fornece uma ampla variedade de eventos para escuta:
 - **CrewTrainStartedEvent**: Emitido ao iniciar o treinamento de um Crew
 - **CrewTrainCompletedEvent**: Emitido ao concluir o treinamento de um Crew
 - **CrewTrainFailedEvent**: Emitido ao falhar no treinamento de um Crew
+- **CrewTestResultEvent**: Emitido quando um resultado de teste de Crew está disponível. Contém a pontuação de qualidade, duração da execução e modelo utilizado.
 
 ### Eventos de Agent
 
 - **AgentExecutionStartedEvent**: Emitido quando um Agent inicia a execução de uma tarefa
 - **AgentExecutionCompletedEvent**: Emitido quando um Agent conclui a execução de uma tarefa
 - **AgentExecutionErrorEvent**: Emitido quando um Agent encontra um erro durante a execução
+- **LiteAgentExecutionStartedEvent**: Emitido quando um LiteAgent inicia a execução. Contém as informações do agente, ferramentas e mensagens.
+- **LiteAgentExecutionCompletedEvent**: Emitido quando um LiteAgent conclui a execução. Contém as informações do agente e a saída.
+- **LiteAgentExecutionErrorEvent**: Emitido quando um LiteAgent encontra um erro durante a execução. Contém as informações do agente e a mensagem de erro.
+- **AgentEvaluationStartedEvent**: Emitido quando uma avaliação de agente é iniciada. Contém o ID do agente, papel do agente, ID da tarefa opcional e número da iteração.
+- **AgentEvaluationCompletedEvent**: Emitido quando uma avaliação de agente é concluída. Contém o ID do agente, papel do agente, ID da tarefa opcional, número da iteração, categoria da métrica e pontuação.
+- **AgentEvaluationFailedEvent**: Emitido quando uma avaliação de agente falha. Contém o ID do agente, papel do agente, ID da tarefa opcional, número da iteração e mensagem de erro.
 
 ### Eventos de Task
 
@@ -219,6 +226,16 @@ O CrewAI fornece uma ampla variedade de eventos para escuta:
 - **ToolExecutionErrorEvent**: Emitido quando ocorre erro na execução de uma ferramenta
 - **ToolSelectionErrorEvent**: Emitido ao ocorrer erro na seleção de uma ferramenta
 
+### Eventos de MCP
+
+- **MCPConnectionStartedEvent**: Emitido ao iniciar a conexão com um servidor MCP. Contém o nome do servidor, URL, tipo de transporte, timeout de conexão e se é uma tentativa de reconexão.
+- **MCPConnectionCompletedEvent**: Emitido ao conectar com sucesso a um servidor MCP. Contém o nome do servidor, duração da conexão em milissegundos e se foi uma reconexão.
+- **MCPConnectionFailedEvent**: Emitido quando a conexão com um servidor MCP falha. Contém o nome do servidor, mensagem de erro e tipo de erro (`timeout`, `authentication`, `network`, etc.).
+- **MCPToolExecutionStartedEvent**: Emitido ao iniciar a execução de uma ferramenta MCP. Contém o nome do servidor, nome da ferramenta e argumentos da ferramenta.
+- **MCPToolExecutionCompletedEvent**: Emitido quando a execução de uma ferramenta MCP é concluída com sucesso. Contém o nome do servidor, nome da ferramenta, resultado e duração da execução em milissegundos.
+- **MCPToolExecutionFailedEvent**: Emitido quando a execução de uma ferramenta MCP falha. Contém o nome do servidor, nome da ferramenta, mensagem de erro e tipo de erro (`timeout`, `validation`, `server_error`, etc.).
+- **MCPConfigFetchFailedEvent**: Emitido quando a obtenção da configuração de um servidor MCP falha (ex.: o MCP não está conectado na sua conta, erro de API ou falha de conexão após a configuração ser obtida). Contém o slug, mensagem de erro e tipo de erro (`not_connected`, `api_error`, `connection_failed`).
+
 ### Eventos de Knowledge
 
 - **KnowledgeRetrievalStartedEvent**: Emitido ao iniciar recuperação de conhecimento
@@ -232,16 +249,26 @@ O CrewAI fornece uma ampla variedade de eventos para escuta:
 
 - **LLMGuardrailStartedEvent**: Emitido ao iniciar validação dos guardrails. Contém detalhes do guardrail aplicado e tentativas.
 - **LLMGuardrailCompletedEvent**: Emitido ao concluir validação dos guardrails. Contém detalhes sobre sucesso/falha na validação, resultados e mensagens de erro, se houver.
+- **LLMGuardrailFailedEvent**: Emitido quando a validação do guardrail falha. Contém a mensagem de erro e o número de tentativas.
 
 ### Eventos de Flow
 
 - **FlowCreatedEvent**: Emitido ao criar um Flow
 - **FlowStartedEvent**: Emitido ao iniciar a execução de um Flow
 - **FlowFinishedEvent**: Emitido ao concluir a execução de um Flow
+- **FlowPausedEvent**: Emitido quando um Flow é pausado aguardando feedback humano. Contém o nome do flow, ID do flow, nome do método, estado atual, mensagem exibida ao solicitar feedback e lista opcional de resultados possíveis para roteamento.
 - **FlowPlotEvent**: Emitido ao plotar um Flow
 - **MethodExecutionStartedEvent**: Emitido ao iniciar a execução de um método do Flow
 - **MethodExecutionFinishedEvent**: Emitido ao concluir a execução de um método do Flow
 - **MethodExecutionFailedEvent**: Emitido ao falhar na execução de um método do Flow
+- **MethodExecutionPausedEvent**: Emitido quando um método do Flow é pausado aguardando feedback humano. Contém o nome do flow, nome do método, estado atual, ID do flow, mensagem exibida ao solicitar feedback e lista opcional de resultados possíveis para roteamento.
+
+### Eventos de Human In The Loop
+
+- **FlowInputRequestedEvent**: Emitido quando um Flow solicita entrada do usuário via `Flow.ask()`. Contém o nome do flow, nome do método, a pergunta ou prompt exibido ao usuário e metadados opcionais (ex.: ID do usuário, canal, contexto da sessão).
+- **FlowInputReceivedEvent**: Emitido quando a entrada do usuário é recebida após `Flow.ask()`. Contém o nome do flow, nome do método, a pergunta original, a resposta do usuário (ou `None` se expirou), metadados opcionais da solicitação e metadados opcionais da resposta do provedor (ex.: quem respondeu, ID do thread, timestamps).
+- **HumanFeedbackRequestedEvent**: Emitido quando um método decorado com `@human_feedback` requer entrada de um revisor humano. Contém o nome do flow, nome do método, a saída do método exibida ao humano para revisão, a mensagem exibida ao solicitar feedback e lista opcional de resultados possíveis para roteamento.
+- **HumanFeedbackReceivedEvent**: Emitido quando um humano fornece feedback em resposta a um método decorado com `@human_feedback`. Contém o nome do flow, nome do método, o texto bruto do feedback fornecido pelo humano e a string de resultado consolidada (se emit foi especificado).
 
 ### Eventos de LLM
 
@@ -249,6 +276,91 @@ O CrewAI fornece uma ampla variedade de eventos para escuta:
 - **LLMCallCompletedEvent**: Emitido ao concluir uma chamada LLM
 - **LLMCallFailedEvent**: Emitido ao falhar uma chamada LLM
 - **LLMStreamChunkEvent**: Emitido para cada chunk recebido durante respostas em streaming do LLM
+- **LLMThinkingChunkEvent**: Emitido quando um chunk de pensamento/raciocínio é recebido de um modelo de pensamento. Contém o texto do chunk e ID de resposta opcional.
+
+### Eventos de Memória
+
+- **MemoryQueryStartedEvent**: Emitido quando uma consulta de memória é iniciada. Contém a consulta, limite e threshold de pontuação opcional.
+- **MemoryQueryCompletedEvent**: Emitido quando uma consulta de memória é concluída com sucesso. Contém a consulta, resultados, limite, threshold de pontuação e tempo de execução da consulta.
+- **MemoryQueryFailedEvent**: Emitido quando uma consulta de memória falha. Contém a consulta, limite, threshold de pontuação e mensagem de erro.
+- **MemorySaveStartedEvent**: Emitido quando uma operação de salvamento de memória é iniciada. Contém o valor a ser salvo, metadados e papel do agente opcional.
+- **MemorySaveCompletedEvent**: Emitido quando uma operação de salvamento de memória é concluída com sucesso. Contém o valor salvo, metadados, papel do agente e tempo de salvamento.
+- **MemorySaveFailedEvent**: Emitido quando uma operação de salvamento de memória falha. Contém o valor, metadados, papel do agente e mensagem de erro.
+- **MemoryRetrievalStartedEvent**: Emitido quando a recuperação de memória para um prompt de tarefa é iniciada. Contém o ID da tarefa opcional.
+- **MemoryRetrievalCompletedEvent**: Emitido quando a recuperação de memória para um prompt de tarefa é concluída com sucesso. Contém o ID da tarefa, conteúdo da memória e tempo de execução da recuperação.
+- **MemoryRetrievalFailedEvent**: Emitido quando a recuperação de memória para um prompt de tarefa falha. Contém o ID da tarefa opcional e mensagem de erro.
+
+### Eventos de Raciocínio
+
+- **AgentReasoningStartedEvent**: Emitido quando um agente começa a raciocinar sobre uma tarefa. Contém o papel do agente, ID da tarefa e número da tentativa.
+- **AgentReasoningCompletedEvent**: Emitido quando um agente finaliza seu processo de raciocínio. Contém o papel do agente, ID da tarefa, o plano produzido e se o agente está pronto para prosseguir.
+- **AgentReasoningFailedEvent**: Emitido quando o processo de raciocínio falha. Contém o papel do agente, ID da tarefa e mensagem de erro.
+
+### Eventos de Observação
+
+- **StepObservationStartedEvent**: Emitido quando o Planner começa a observar o resultado de um passo. Disparado após cada execução de passo, antes da chamada LLM de observação. Contém o papel do agente, número do passo e descrição do passo.
+- **StepObservationCompletedEvent**: Emitido quando o Planner finaliza a observação do resultado de um passo. Contém se o passo foi concluído com sucesso, informações-chave aprendidas, se o plano restante ainda é válido, se é necessário um replanejamento completo e refinamentos sugeridos.
+- **StepObservationFailedEvent**: Emitido quando a chamada LLM de observação falha. O sistema continua o plano por padrão. Contém a mensagem de erro.
+- **PlanRefinementEvent**: Emitido quando o Planner refina descrições de passos futuros sem replanejamento completo. Contém o número de passos refinados e os refinamentos aplicados.
+- **PlanReplanTriggeredEvent**: Emitido quando o Planner dispara um replanejamento completo porque o plano restante foi considerado fundamentalmente incorreto. Contém o motivo do replanejamento, contagem de replanejamentos e número de passos concluídos preservados.
+- **GoalAchievedEarlyEvent**: Emitido quando o Planner detecta que o objetivo foi alcançado antecipadamente e os passos restantes serão ignorados. Contém o número de passos restantes e passos concluídos.
+
+### Eventos A2A (Agent-to-Agent)
+
+#### Eventos de Delegação
+
+- **A2ADelegationStartedEvent**: Emitido quando a delegação A2A é iniciada. Contém a URL do endpoint, descrição da tarefa, ID do agente, ID do contexto, se é multiturn, número do turno, metadados do agent card, versão do protocolo, informações do provedor e ID da skill opcional.
+- **A2ADelegationCompletedEvent**: Emitido quando a delegação A2A é concluída. Contém o status de conclusão (`completed`, `input_required`, `failed`, etc.), resultado, mensagem de erro, ID do contexto e metadados do agent card.
+- **A2AParallelDelegationStartedEvent**: Emitido quando a delegação paralela para múltiplos agentes A2A é iniciada. Contém a lista de endpoints e a descrição da tarefa.
+- **A2AParallelDelegationCompletedEvent**: Emitido quando a delegação paralela para múltiplos agentes A2A é concluída. Contém a lista de endpoints, contagem de sucessos, contagem de falhas e resumo dos resultados.
+
+#### Eventos de Conversação
+
+- **A2AConversationStartedEvent**: Emitido uma vez no início de uma conversação multiturn A2A, antes da primeira troca de mensagens. Contém o ID do agente, endpoint, ID do contexto, metadados do agent card, versão do protocolo e informações do provedor.
+- **A2AMessageSentEvent**: Emitido quando uma mensagem é enviada ao agente A2A. Contém o conteúdo da mensagem, número do turno, ID do contexto, ID da mensagem e se é multiturn.
+- **A2AResponseReceivedEvent**: Emitido quando uma resposta é recebida do agente A2A. Contém o conteúdo da resposta, número do turno, ID do contexto, ID da mensagem, status e se é a resposta final.
+- **A2AConversationCompletedEvent**: Emitido uma vez ao final de uma conversação multiturn A2A. Contém o status final (`completed` ou `failed`), resultado final, mensagem de erro, ID do contexto e número total de turnos.
+
+#### Eventos de Streaming
+
+- **A2AStreamingStartedEvent**: Emitido quando o modo streaming é iniciado para delegação A2A. Contém o ID da tarefa, ID do contexto, endpoint, número do turno e se é multiturn.
+- **A2AStreamingChunkEvent**: Emitido quando um chunk de streaming é recebido. Contém o texto do chunk, índice do chunk, se é o chunk final, ID da tarefa, ID do contexto e número do turno.
+
+#### Eventos de Polling e Push Notification
+
+- **A2APollingStartedEvent**: Emitido quando o modo polling é iniciado para delegação A2A. Contém o ID da tarefa, ID do contexto, intervalo de polling em segundos e endpoint.
+- **A2APollingStatusEvent**: Emitido em cada iteração de polling. Contém o ID da tarefa, ID do contexto, estado atual da tarefa, segundos decorridos e contagem de polls.
+- **A2APushNotificationRegisteredEvent**: Emitido quando um callback de push notification é registrado. Contém o ID da tarefa, ID do contexto, URL do callback e endpoint.
+- **A2APushNotificationReceivedEvent**: Emitido quando uma push notification é recebida do agente A2A remoto. Contém o ID da tarefa, ID do contexto e estado atual.
+- **A2APushNotificationSentEvent**: Emitido quando uma push notification é enviada para uma URL de callback. Contém o ID da tarefa, ID do contexto, URL do callback, estado, se a entrega foi bem-sucedida e mensagem de erro opcional.
+- **A2APushNotificationTimeoutEvent**: Emitido quando a espera por push notification expira. Contém o ID da tarefa, ID do contexto e duração do timeout em segundos.
+
+#### Eventos de Conexão e Autenticação
+
+- **A2AAgentCardFetchedEvent**: Emitido quando um agent card é obtido com sucesso. Contém o endpoint, nome do agente, metadados do agent card, versão do protocolo, informações do provedor, se foi do cache e tempo de busca em milissegundos.
+- **A2AAuthenticationFailedEvent**: Emitido quando a autenticação com um agente A2A falha. Contém o endpoint, tipo de autenticação tentada (ex.: `bearer`, `oauth2`, `api_key`), mensagem de erro e código de status HTTP.
+- **A2AConnectionErrorEvent**: Emitido quando ocorre um erro de conexão durante a comunicação A2A. Contém o endpoint, mensagem de erro, tipo de erro (ex.: `timeout`, `connection_refused`, `dns_error`), código de status HTTP e a operação sendo tentada.
+- **A2ATransportNegotiatedEvent**: Emitido quando o protocolo de transporte é negociado com um agente A2A. Contém o transporte negociado, URL negociada, fonte de seleção (`client_preferred`, `server_preferred`, `fallback`) e transportes suportados pelo cliente/servidor.
+- **A2AContentTypeNegotiatedEvent**: Emitido quando os tipos de conteúdo são negociados com um agente A2A. Contém os modos de entrada/saída do cliente/servidor, modos de entrada/saída negociados e se a negociação foi bem-sucedida.
+
+#### Eventos de Artefatos
+
+- **A2AArtifactReceivedEvent**: Emitido quando um artefato é recebido de um agente A2A remoto. Contém o ID da tarefa, ID do artefato, nome do artefato, descrição, tipo MIME, tamanho em bytes e se o conteúdo deve ser concatenado.
+
+#### Eventos de Tarefa do Servidor
+
+- **A2AServerTaskStartedEvent**: Emitido quando a execução de uma tarefa do servidor A2A é iniciada. Contém o ID da tarefa e ID do contexto.
+- **A2AServerTaskCompletedEvent**: Emitido quando a execução de uma tarefa do servidor A2A é concluída. Contém o ID da tarefa, ID do contexto e resultado.
+- **A2AServerTaskCanceledEvent**: Emitido quando a execução de uma tarefa do servidor A2A é cancelada. Contém o ID da tarefa e ID do contexto.
+- **A2AServerTaskFailedEvent**: Emitido quando a execução de uma tarefa do servidor A2A falha. Contém o ID da tarefa, ID do contexto e mensagem de erro.
+
+#### Eventos de Ciclo de Vida do Contexto
+
+- **A2AContextCreatedEvent**: Emitido quando um contexto A2A é criado. Contextos agrupam tarefas relacionadas em uma conversação ou workflow. Contém o ID do contexto e timestamp de criação.
+- **A2AContextExpiredEvent**: Emitido quando um contexto A2A expira devido ao TTL. Contém o ID do contexto, timestamp de criação, idade em segundos e contagem de tarefas.
+- **A2AContextIdleEvent**: Emitido quando um contexto A2A fica inativo (sem atividade pelo threshold configurado). Contém o ID do contexto, tempo de inatividade em segundos e contagem de tarefas.
+- **A2AContextCompletedEvent**: Emitido quando todas as tarefas em um contexto A2A são concluídas. Contém o ID do contexto, total de tarefas e duração em segundos.
+- **A2AContextPrunedEvent**: Emitido quando um contexto A2A é podado (deletado). Contém o ID do contexto, contagem de tarefas e idade em segundos.
 
 ## Estrutura dos Handlers de Evento
 

docs/pt-BR/guides/coding-tools/agents-md.mdx

@@ -0,0 +1,61 @@
+---
+title: Ferramentas de Codificação
+description: Use o AGENTS.md para guiar agentes de codificação e IDEs em seus projetos CrewAI.
+icon: terminal
+mode: "wide"
+---
+
+## Por que AGENTS.md
+
+`AGENTS.md` é um arquivo de instruções leve e local do repositório que fornece aos agentes de codificação orientações consistentes e específicas do projeto. Mantenha-o na raiz do projeto e trate-o como a fonte da verdade para como você deseja que os assistentes trabalhem: convenções, comandos, notas de arquitetura e proteções.
+
+## Criar um Projeto com o CLI
+
+Use o CLI do CrewAI para criar a estrutura de um projeto, e o `AGENTS.md` será automaticamente adicionado na raiz.
+
+```bash
+# Crew
+crewai create crew my_crew
+
+# Flow
+crewai create flow my_flow
+
+# Tool repository
+crewai tool create my_tool
+```
+
+## Configuração de Ferramentas: Direcione Assistentes para o AGENTS.md
+
+### Codex
+
+O Codex pode ser guiado por arquivos `AGENTS.md` colocados no seu repositório. Use-os para fornecer contexto persistente do projeto, como convenções, comandos e expectativas de fluxo de trabalho.
+
+### Claude Code
+
+O Claude Code armazena a memória do projeto em `CLAUDE.md`. Você pode inicializá-lo com `/init` e editá-lo usando `/memory`. O Claude Code também suporta importações dentro do `CLAUDE.md`, então você pode adicionar uma única linha como `@AGENTS.md` para incluir as instruções compartilhadas sem duplicá-las.
+
+Você pode simplesmente usar:
+
+```bash
+mv AGENTS.md CLAUDE.md
+```
+
+### Gemini CLI e Google Antigravity
+
+O Gemini CLI e o Antigravity carregam um arquivo de contexto do projeto (padrão: `GEMINI.md`) da raiz do repositório e diretórios pais. Você pode configurá-lo para ler o `AGENTS.md` em vez disso (ou além) definindo `context.fileName` nas configurações do Gemini CLI. Por exemplo, defina apenas para `AGENTS.md`, ou inclua tanto `AGENTS.md` quanto `GEMINI.md` se quiser manter o formato de cada ferramenta.
+
+Você pode simplesmente usar:
+
+```bash
+mv AGENTS.md GEMINI.md
+```
+
+### Cursor
+
+O Cursor suporta `AGENTS.md` como arquivo de instruções do projeto. Coloque-o na raiz do projeto para fornecer orientação ao assistente de codificação do Cursor.
+
+### Windsurf
+
+O Claude Code fornece uma integração oficial com o Windsurf. Se você usa o Claude Code dentro do Windsurf, siga a orientação do Claude Code acima e importe o `AGENTS.md` a partir do `CLAUDE.md`.
+
+Se você está usando o assistente nativo do Windsurf, configure o recurso de regras ou instruções do projeto (se disponível) para ler o `AGENTS.md` ou cole o conteúdo diretamente.

docs/pt-BR/guides/tools/publish-custom-tools.mdx

@@ -0,0 +1,244 @@
+---
+title: Publicar Ferramentas Personalizadas
+description: Como construir, empacotar e publicar suas próprias ferramentas compatíveis com CrewAI no PyPI para que qualquer usuário do CrewAI possa instalá-las e usá-las.
+icon: box-open
+mode: "wide"
+---
+
+## Visão Geral
+
+O sistema de ferramentas do CrewAI foi projetado para ser extensível. Se você construiu uma ferramenta que pode beneficiar outros, pode empacotá-la como uma biblioteca Python independente, publicá-la no PyPI e disponibilizá-la para qualquer usuário do CrewAI — sem necessidade de PR para o repositório do CrewAI.
+
+Este guia percorre todo o processo: implementação do contrato de ferramentas, estruturação do pacote e publicação no PyPI.
+
+<Note type="info" title="Não pretende publicar?">
+Se você precisa apenas de uma ferramenta personalizada para seu próprio projeto, consulte o guia [Criar Ferramentas Personalizadas](/pt-BR/learn/create-custom-tools).
+</Note>
+
+## O Contrato de Ferramentas
+
+Toda ferramenta CrewAI deve satisfazer uma das duas interfaces:
+
+### Opção 1: Subclassificar `BaseTool`
+
+Subclassifique `crewai.tools.BaseTool` e implemente o método `_run`. Defina `name`, `description` e, opcionalmente, um `args_schema` para validação de entrada.
+
+```python
+from crewai.tools import BaseTool
+from pydantic import BaseModel, Field
+
+
+class GeolocateInput(BaseModel):
+    """Esquema de entrada para GeolocateTool."""
+    address: str = Field(..., description="O endereço para geolocalizar.")
+
+
+class GeolocateTool(BaseTool):
+    name: str = "Geolocate"
+    description: str = "Converte um endereço em coordenadas de latitude/longitude."
+    args_schema: type[BaseModel] = GeolocateInput
+
+    def _run(self, address: str) -> str:
+        # Sua implementação aqui
+        return f"40.7128, -74.0060"
+```
+
+### Opção 2: Usar o Decorador `@tool`
+
+Para ferramentas mais simples, o decorador `@tool` transforma uma função em uma ferramenta CrewAI. A função **deve** ter uma docstring (usada como descrição da ferramenta) e anotações de tipo.
+
+```python
+from crewai.tools import tool
+
+
+@tool("Geolocate")
+def geolocate(address: str) -> str:
+    """Converte um endereço em coordenadas de latitude/longitude."""
+    return "40.7128, -74.0060"
+```
+
+### Requisitos Essenciais
+
+Independentemente da abordagem escolhida, sua ferramenta deve:
+
+- Ter um **`name`** — um identificador curto e descritivo.
+- Ter uma **`description`** — informa ao agente quando e como usar a ferramenta. Isso afeta diretamente a qualidade do uso da ferramenta pelo agente, então seja claro e específico.
+- Implementar **`_run`** (BaseTool) ou fornecer um **corpo de função** (@tool) — a lógica de execução síncrona.
+- Usar **anotações de tipo** em todos os parâmetros e valores de retorno.
+- Retornar um resultado em **string** (ou algo que possa ser convertido de forma significativa).
+
+### Opcional: Suporte Assíncrono
+
+Se sua ferramenta realiza operações de I/O, implemente `_arun` para execução assíncrona:
+
+```python
+class GeolocateTool(BaseTool):
+    name: str = "Geolocate"
+    description: str = "Converte um endereço em coordenadas de latitude/longitude."
+
+    def _run(self, address: str) -> str:
+        # Implementação síncrona
+        ...
+
+    async def _arun(self, address: str) -> str:
+        # Implementação assíncrona
+        ...
+```
+
+### Opcional: Validação de Entrada com `args_schema`
+
+Defina um modelo Pydantic como seu `args_schema` para obter validação automática de entrada e mensagens de erro claras. Se não fornecer um, o CrewAI irá inferi-lo da assinatura do seu método `_run`.
+
+```python
+from pydantic import BaseModel, Field
+
+
+class TranslateInput(BaseModel):
+    """Esquema de entrada para TranslateTool."""
+    text: str = Field(..., description="O texto a ser traduzido.")
+    target_language: str = Field(
+        default="en",
+        description="Código de idioma ISO 639-1 para o idioma de destino.",
+    )
+```
+
+Esquemas explícitos são recomendados para ferramentas publicadas — produzem melhor comportamento do agente e documentação mais clara para seus usuários.
+
+### Opcional: Variáveis de Ambiente
+
+Se sua ferramenta requer chaves de API ou outra configuração, declare-as com `env_vars` para que os usuários saibam o que configurar:
+
+```python
+from crewai.tools import BaseTool, EnvVar
+
+
+class GeolocateTool(BaseTool):
+    name: str = "Geolocate"
+    description: str = "Converte um endereço em coordenadas de latitude/longitude."
+    env_vars: list[EnvVar] = [
+        EnvVar(
+            name="GEOCODING_API_KEY",
+            description="Chave de API para o serviço de geocodificação.",
+            required=True,
+        ),
+    ]
+
+    def _run(self, address: str) -> str:
+        ...
+```
+
+## Estrutura do Pacote
+
+Estruture seu projeto como um pacote Python padrão. Layout recomendado:
+
+```
+crewai-geolocate/
+├── pyproject.toml
+├── LICENSE
+├── README.md
+└── src/
+    └── crewai_geolocate/
+        ├── __init__.py
+        └── tools.py
+```
+
+### `pyproject.toml`
+
+```toml
+[project]
+name = "crewai-geolocate"
+version = "0.1.0"
+description = "Uma ferramenta CrewAI para geolocalizar endereços."
+requires-python = ">=3.10"
+dependencies = [
+    "crewai",
+]
+
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+```
+
+Declare `crewai` como dependência para que os usuários obtenham automaticamente uma versão compatível.
+
+### `__init__.py`
+
+Re-exporte suas classes de ferramenta para que os usuários possam importá-las diretamente:
+
+```python
+from crewai_geolocate.tools import GeolocateTool
+
+__all__ = ["GeolocateTool"]
+```
+
+### Convenções de Nomenclatura
+
+- **Nome do pacote**: Use o prefixo `crewai-` (ex.: `crewai-geolocate`). Isso torna sua ferramenta fácil de encontrar no PyPI.
+- **Nome do módulo**: Use underscores (ex.: `crewai_geolocate`).
+- **Nome da classe da ferramenta**: Use PascalCase terminando em `Tool` (ex.: `GeolocateTool`).
+
+## Testando sua Ferramenta
+
+Antes de publicar, verifique se sua ferramenta funciona dentro de uma crew:
+
+```python
+from crewai import Agent, Crew, Task
+from crewai_geolocate import GeolocateTool
+
+agent = Agent(
+    role="Analista de Localização",
+    goal="Encontrar coordenadas para os endereços fornecidos.",
+    backstory="Um especialista em dados geoespaciais.",
+    tools=[GeolocateTool()],
+)
+
+task = Task(
+    description="Encontre as coordenadas de 1600 Pennsylvania Avenue, Washington, DC.",
+    expected_output="A latitude e longitude do endereço.",
+    agent=agent,
+)
+
+crew = Crew(agents=[agent], tasks=[task])
+result = crew.kickoff()
+print(result)
+```
+
+## Publicando no PyPI
+
+Quando sua ferramenta estiver testada e pronta:
+
+```bash
+# Construir o pacote
+uv build
+
+# Publicar no PyPI
+uv publish
+```
+
+Se é sua primeira vez publicando, você precisará de uma [conta no PyPI](https://pypi.org/account/register/) e um [token de API](https://pypi.org/help/#apitoken).
+
+### Após a Publicação
+
+Os usuários podem instalar sua ferramenta com:
+
+```bash
+pip install crewai-geolocate
+```
+
+Ou com uv:
+
+```bash
+uv add crewai-geolocate
+```
+
+E então usá-la em suas crews:
+
+```python
+from crewai_geolocate import GeolocateTool
+
+agent = Agent(
+    role="Analista de Localização",
+    tools=[GeolocateTool()],
+    # ...
+)
+```

docs/pt-BR/learn/create-custom-tools.mdx

@@ -11,6 +11,10 @@ Este guia traz instruções detalhadas sobre como criar ferramentas personalizad
 incorporando funcionalidades recentes, como delegação de ferramentas, tratamento de erros e chamada dinâmica de ferramentas. Destaca também a importância de ferramentas de colaboração,
 permitindo que agentes executem uma ampla gama de ações.
 
+<Tip>
+  **Quer publicar sua ferramenta para a comunidade?** Se você está construindo uma ferramenta que pode beneficiar outros, confira o guia [Publicar Ferramentas Personalizadas](/pt-BR/guides/tools/publish-custom-tools) para aprender como empacotar e distribuir sua ferramenta no PyPI.
+</Tip>
+
 ### Subclassificando `BaseTool`
 
 Para criar uma ferramenta personalizada, herde de `BaseTool` e defina os atributos necessários, incluindo o `args_schema` para validação de entrada e o método `_run`.

lib/crewai-tools/src/crewai_tools/tools/file_writer_tool/file_writer_tool.py

@@ -1,4 +1,5 @@
 import os
+from pathlib import Path
 from typing import Any
 
 from crewai.tools import BaseTool
@@ -30,27 +31,39 @@ class FileWriterTool(BaseTool):
 
     def _run(self, **kwargs: Any) -> str:
         try:
+            directory = kwargs.get("directory") or "./"
+            filename = kwargs["filename"]
+
+            filepath = os.path.join(directory, filename)
+
+            # Prevent path traversal: the resolved path must be strictly inside
+            # the resolved directory. This blocks ../sequences, absolute paths in
+            # filename, and symlink escapes regardless of how directory is set.
+            # is_relative_to() does a proper path-component comparison that is
+            # safe on case-insensitive filesystems and avoids the "// " edge case
+            # that plagues startswith(real_directory + os.sep).
+            # We also reject the case where filepath resolves to the directory
+            # itself, since that is not a valid file target.
+            real_directory = Path(directory).resolve()
+            real_filepath = Path(filepath).resolve()
+            if not real_filepath.is_relative_to(real_directory) or real_filepath == real_directory:
+                return "Error: Invalid file path — the filename must not escape the target directory."
+
             if kwargs.get("directory"):
-                os.makedirs(kwargs["directory"], exist_ok=True)
+                os.makedirs(real_directory, exist_ok=True)
 
-            # Construct the full path
-            filepath = os.path.join(kwargs.get("directory") or "", kwargs["filename"])
-
-            # Convert overwrite to boolean
             kwargs["overwrite"] = strtobool(kwargs["overwrite"])
 
-            # Check if file exists and overwrite is not allowed
-            if os.path.exists(filepath) and not kwargs["overwrite"]:
-                return f"File {filepath} already exists and overwrite option was not passed."
+            if os.path.exists(real_filepath) and not kwargs["overwrite"]:
+                return f"File {real_filepath} already exists and overwrite option was not passed."
 
-            # Write content to the file
             mode = "w" if kwargs["overwrite"] else "x"
-            with open(filepath, mode) as file:
+            with open(real_filepath, mode) as file:
                 file.write(kwargs["content"])
-            return f"Content successfully written to {filepath}"
+            return f"Content successfully written to {real_filepath}"
         except FileExistsError:
             return (
-                f"File {filepath} already exists and overwrite option was not passed."
+                f"File {real_filepath} already exists and overwrite option was not passed."
             )
         except KeyError as e:
             return f"An error occurred while accessing key: {e!s}"

lib/crewai-tools/tests/tools/test_file_writer_tool.py

@@ -135,3 +135,59 @@ def test_file_exists_error_handling(tool, temp_env, overwrite):
 
     assert "already exists and overwrite option was not passed" in result
     assert read_file(path) == "Pre-existing content"
+
+
+# --- Path traversal prevention ---
+
+def test_blocks_traversal_in_filename(tool, temp_env):
+    # Create a sibling "outside" directory so we can assert nothing was written there.
+    outside_dir = tempfile.mkdtemp()
+    outside_file = os.path.join(outside_dir, "outside.txt")
+    try:
+        result = tool._run(
+            filename=f"../{os.path.basename(outside_dir)}/outside.txt",
+            directory=temp_env["temp_dir"],
+            content="should not be written",
+            overwrite=True,
+        )
+        assert "Error" in result
+        assert not os.path.exists(outside_file)
+    finally:
+        shutil.rmtree(outside_dir, ignore_errors=True)
+
+
+def test_blocks_absolute_path_in_filename(tool, temp_env):
+    # Use a temp file outside temp_dir as the absolute target so we don't
+    # depend on /etc/passwd existing or being writable on the host.
+    outside_dir = tempfile.mkdtemp()
+    outside_file = os.path.join(outside_dir, "target.txt")
+    try:
+        result = tool._run(
+            filename=outside_file,
+            directory=temp_env["temp_dir"],
+            content="should not be written",
+            overwrite=True,
+        )
+        assert "Error" in result
+        assert not os.path.exists(outside_file)
+    finally:
+        shutil.rmtree(outside_dir, ignore_errors=True)
+
+
+def test_blocks_symlink_escape(tool, temp_env):
+    # Symlink inside temp_dir pointing to a separate temp "outside" directory.
+    outside_dir = tempfile.mkdtemp()
+    outside_file = os.path.join(outside_dir, "target.txt")
+    link = os.path.join(temp_env["temp_dir"], "escape")
+    os.symlink(outside_dir, link)
+    try:
+        result = tool._run(
+            filename="escape/target.txt",
+            directory=temp_env["temp_dir"],
+            content="should not be written",
+            overwrite=True,
+        )
+        assert "Error" in result
+        assert not os.path.exists(outside_file)
+    finally:
+        shutil.rmtree(outside_dir, ignore_errors=True)

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

@@ -66,6 +66,7 @@ from crewai.mcp.tool_resolver import MCPToolResolver
 from crewai.rag.embeddings.types import EmbedderConfig
 from crewai.security.fingerprint import Fingerprint
 from crewai.tools.agent_tools.agent_tools import AgentTools
+from crewai.types.callback import SerializableCallable
 from crewai.utilities.agent_utils import (
     get_tool_names,
     is_inside_event_loop,
@@ -75,6 +76,7 @@ from crewai.utilities.agent_utils import (
 )
 from crewai.utilities.constants import TRAINED_AGENTS_DATA_FILE, TRAINING_DATA_FILE
 from crewai.utilities.converter import Converter, ConverterError
+from crewai.utilities.env import get_env_context
 from crewai.utilities.guardrail import process_guardrail
 from crewai.utilities.guardrail_types import GuardrailType
 from crewai.utilities.llm_utils import create_llm
@@ -142,7 +144,7 @@ class Agent(BaseAgent):
         default=None,
         description="Maximum execution time for an agent to execute a task",
     )
-    step_callback: Any | None = Field(
+    step_callback: SerializableCallable | None = Field(
         default=None,
         description="Callback to be executed after each step of the agent execution.",
     )
@@ -150,10 +152,10 @@ class Agent(BaseAgent):
         default=True,
         description="Use system prompt for the agent.",
     )
-    llm: str | InstanceOf[BaseLLM] | Any = Field(
+    llm: str | InstanceOf[BaseLLM] | None = Field(
         description="Language model that will run the agent.", default=None
     )
-    function_calling_llm: str | InstanceOf[BaseLLM] | Any | None = Field(
+    function_calling_llm: str | InstanceOf[BaseLLM] | None = Field(
         description="Language model that will run the agent.", default=None
     )
     system_template: str | None = Field(
@@ -339,7 +341,7 @@ class Agent(BaseAgent):
         return (
             hasattr(self.llm, "supports_function_calling")
             and callable(getattr(self.llm, "supports_function_calling", None))
-            and self.llm.supports_function_calling()
+            and self.llm.supports_function_calling()  # type: ignore[union-attr]
             and len(tools) > 0
         )
 
@@ -364,6 +366,7 @@ class Agent(BaseAgent):
             ValueError: If the max execution time is not a positive integer.
             RuntimeError: If the agent execution fails for other reasons.
         """
+        get_env_context()
         # Only call handle_reasoning for legacy CrewAgentExecutor
         # For AgentExecutor, planning is handled in AgentExecutor.generate_plan()
         if self.executor_class is not AgentExecutor:

lib/crewai/src/crewai/agents/agent_builder/base_agent.py

@@ -1,7 +1,6 @@
 from __future__ import annotations
 
 from abc import ABC, abstractmethod
-from collections.abc import Callable
 from copy import copy as shallow_copy
 from hashlib import md5
 import re
@@ -12,6 +11,7 @@ from pydantic import (
     UUID4,
     BaseModel,
     Field,
+    InstanceOf,
     PrivateAttr,
     field_validator,
     model_validator,
@@ -26,10 +26,14 @@ from crewai.agents.tools_handler import ToolsHandler
 from crewai.knowledge.knowledge import Knowledge
 from crewai.knowledge.knowledge_config import KnowledgeConfig
 from crewai.knowledge.source.base_knowledge_source import BaseKnowledgeSource
+from crewai.knowledge.storage.base_knowledge_storage import BaseKnowledgeStorage
 from crewai.mcp.config import MCPServerConfig
+from crewai.memory.memory_scope import MemoryScope, MemorySlice
+from crewai.memory.unified_memory import Memory
 from crewai.rag.embeddings.types import EmbedderConfig
 from crewai.security.security_config import SecurityConfig
 from crewai.tools.base_tool import BaseTool, Tool
+from crewai.types.callback import SerializableCallable
 from crewai.utilities.config import process_config
 from crewai.utilities.i18n import I18N, get_i18n
 from crewai.utilities.logger import Logger
@@ -179,7 +183,7 @@ class BaseAgent(BaseModel, ABC, metaclass=AgentMeta):
         default=None,
         description="Knowledge sources for the agent.",
     )
-    knowledge_storage: Any | None = Field(
+    knowledge_storage: InstanceOf[BaseKnowledgeStorage] | None = Field(
         default=None,
         description="Custom knowledge storage for the agent.",
     )
@@ -187,7 +191,7 @@ class BaseAgent(BaseModel, ABC, metaclass=AgentMeta):
         default_factory=SecurityConfig,
         description="Security configuration for the agent, including fingerprinting.",
     )
-    callbacks: list[Callable[[Any], Any]] = Field(
+    callbacks: list[SerializableCallable] = Field(
         default_factory=list, description="Callbacks to be used for the agent"
     )
     adapted_agent: bool = Field(
@@ -205,7 +209,7 @@ class BaseAgent(BaseModel, ABC, metaclass=AgentMeta):
         default=None,
         description="List of MCP server references. Supports 'https://server.com/path' for external servers and bare slugs like 'notion' for connected MCP integrations. Use '#tool_name' suffix for specific tools.",
     )
-    memory: Any = Field(
+    memory: bool | Memory | MemoryScope | MemorySlice | None = Field(
         default=None,
         description=(
             "Enable agent memory. Pass True for default Memory(), "

lib/crewai/src/crewai/crew.py

@@ -35,6 +35,7 @@ from typing_extensions import Self
 
 if TYPE_CHECKING:
     from crewai_files import FileInput
+    from opentelemetry.trace import Span
 
 try:
     from crewai_files import get_supported_content_types
@@ -83,6 +84,8 @@ from crewai.knowledge.knowledge import Knowledge
 from crewai.knowledge.source.base_knowledge_source import BaseKnowledgeSource
 from crewai.llm import LLM
 from crewai.llms.base_llm import BaseLLM
+from crewai.memory.memory_scope import MemoryScope, MemorySlice
+from crewai.memory.unified_memory import Memory
 from crewai.process import Process
 from crewai.rag.embeddings.types import EmbedderConfig
 from crewai.rag.types import SearchResult
@@ -94,10 +97,12 @@ from crewai.tasks.task_output import TaskOutput
 from crewai.tools.agent_tools.agent_tools import AgentTools
 from crewai.tools.agent_tools.read_file_tool import ReadFileTool
 from crewai.tools.base_tool import BaseTool
+from crewai.types.callback import SerializableCallable
 from crewai.types.streaming import CrewStreamingOutput
 from crewai.types.usage_metrics import UsageMetrics
 from crewai.utilities.constants import NOT_SPECIFIED, TRAINING_DATA_FILE
 from crewai.utilities.crew.models import CrewContext
+from crewai.utilities.env import get_env_context
 from crewai.utilities.evaluators.crew_evaluator_handler import CrewEvaluator
 from crewai.utilities.evaluators.task_evaluator import TaskEvaluator
 from crewai.utilities.file_handler import FileHandler
@@ -165,12 +170,12 @@ class Crew(FlowTrackable, BaseModel):
     """
 
     __hash__ = object.__hash__
-    _execution_span: Any = PrivateAttr()
+    _execution_span: Span | None = PrivateAttr()
     _rpm_controller: RPMController = PrivateAttr()
     _logger: Logger = PrivateAttr()
     _file_handler: FileHandler = PrivateAttr()
     _cache_handler: InstanceOf[CacheHandler] = PrivateAttr(default_factory=CacheHandler)
-    _memory: Any = PrivateAttr(default=None)  # Unified Memory | MemoryScope
+    _memory: Memory | MemoryScope | MemorySlice | None = PrivateAttr(default=None)
     _train: bool | None = PrivateAttr(default=False)
     _train_iteration: int | None = PrivateAttr()
     _inputs: dict[str, Any] | None = PrivateAttr(default=None)
@@ -188,7 +193,7 @@ class Crew(FlowTrackable, BaseModel):
     agents: list[BaseAgent] = Field(default_factory=list)
     process: Process = Field(default=Process.sequential)
     verbose: bool = Field(default=False)
-    memory: bool | Any = Field(
+    memory: bool | Memory | MemoryScope | MemorySlice | None = Field(
         default=False,
         description=(
             "Enable crew memory. Pass True for default Memory(), "
@@ -203,36 +208,34 @@ class Crew(FlowTrackable, BaseModel):
         default=None,
         description="Metrics for the LLM usage during all tasks execution.",
     )
-    manager_llm: str | InstanceOf[BaseLLM] | Any | None = Field(
+    manager_llm: str | InstanceOf[BaseLLM] | None = Field(
         description="Language model that will run the agent.", default=None
     )
     manager_agent: BaseAgent | None = Field(
         description="Custom agent that will be used as manager.", default=None
     )
-    function_calling_llm: str | InstanceOf[LLM] | Any | None = Field(
+    function_calling_llm: str | InstanceOf[LLM] | None = Field(
         description="Language model that will run the agent.", default=None
     )
     config: Json[dict[str, Any]] | dict[str, Any] | None = Field(default=None)
     id: UUID4 = Field(default_factory=uuid.uuid4, frozen=True)
     share_crew: bool | None = Field(default=False)
-    step_callback: Any | None = Field(
+    step_callback: SerializableCallable | None = Field(
         default=None,
         description="Callback to be executed after each step for all agents execution.",
     )
-    task_callback: Any | None = Field(
+    task_callback: SerializableCallable | None = Field(
         default=None,
         description="Callback to be executed after each task for all agents execution.",
     )
-    before_kickoff_callbacks: list[
-        Callable[[dict[str, Any] | None], dict[str, Any] | None]
-    ] = Field(
+    before_kickoff_callbacks: list[SerializableCallable] = Field(
         default_factory=list,
         description=(
             "List of callbacks to be executed before crew kickoff. "
             "It may be used to adjust inputs before the crew is executed."
         ),
     )
-    after_kickoff_callbacks: list[Callable[[CrewOutput], CrewOutput]] = Field(
+    after_kickoff_callbacks: list[SerializableCallable] = Field(
         default_factory=list,
         description=(
             "List of callbacks to be executed after crew kickoff. "
@@ -348,7 +351,7 @@ class Crew(FlowTrackable, BaseModel):
             self._file_handler = FileHandler(self.output_log_file)
         self._rpm_controller = RPMController(max_rpm=self.max_rpm, logger=self._logger)
         if self.function_calling_llm and not isinstance(self.function_calling_llm, LLM):
-            self.function_calling_llm = create_llm(self.function_calling_llm)
+            self.function_calling_llm = create_llm(self.function_calling_llm)  # type: ignore[assignment]
 
         return self
 
@@ -362,7 +365,7 @@ class Crew(FlowTrackable, BaseModel):
             if self.embedder is not None:
                 from crewai.rag.embeddings.factory import build_embedder
 
-                embedder = build_embedder(self.embedder)
+                embedder = build_embedder(self.embedder)  # type: ignore[arg-type]
             self._memory = Memory(embedder=embedder)
         elif self.memory:
             # User passed a Memory / MemoryScope / MemorySlice instance
@@ -679,6 +682,7 @@ class Crew(FlowTrackable, BaseModel):
         Returns:
             CrewOutput or CrewStreamingOutput if streaming is enabled.
         """
+        get_env_context()
         if self.stream:
             enable_agent_streaming(self.agents)
             ctx = StreamingContext()

lib/crewai/src/crewai/events/event_listener.py

@@ -34,6 +34,12 @@ from crewai.events.types.crew_events import (
     CrewTrainFailedEvent,
     CrewTrainStartedEvent,
 )
+from crewai.events.types.env_events import (
+    CCEnvEvent,
+    CodexEnvEvent,
+    CursorEnvEvent,
+    DefaultEnvEvent,
+)
 from crewai.events.types.flow_events import (
     FlowCreatedEvent,
     FlowFinishedEvent,
@@ -143,6 +149,23 @@ class EventListener(BaseEventListener):
     # ----------- CREW EVENTS -----------
 
     def setup_listeners(self, crewai_event_bus: CrewAIEventsBus) -> None:
+
+        @crewai_event_bus.on(CCEnvEvent)
+        def on_cc_env(_: Any, event: CCEnvEvent) -> None:
+            self._telemetry.env_context_span(event.type)
+
+        @crewai_event_bus.on(CodexEnvEvent)
+        def on_codex_env(_: Any, event: CodexEnvEvent) -> None:
+            self._telemetry.env_context_span(event.type)
+
+        @crewai_event_bus.on(CursorEnvEvent)
+        def on_cursor_env(_: Any, event: CursorEnvEvent) -> None:
+            self._telemetry.env_context_span(event.type)
+
+        @crewai_event_bus.on(DefaultEnvEvent)
+        def on_default_env(_: Any, event: DefaultEnvEvent) -> None:
+            self._telemetry.env_context_span(event.type)
+
         @crewai_event_bus.on(CrewKickoffStartedEvent)
         def on_crew_started(source: Any, event: CrewKickoffStartedEvent) -> None:
             self.formatter.handle_crew_started(event.crew_name or "Crew", source.id)

lib/crewai/src/crewai/events/listeners/tracing/trace_listener.py

@@ -58,6 +58,12 @@ from crewai.events.types.crew_events import (
     CrewKickoffFailedEvent,
     CrewKickoffStartedEvent,
 )
+from crewai.events.types.env_events import (
+    CCEnvEvent,
+    CodexEnvEvent,
+    CursorEnvEvent,
+    DefaultEnvEvent,
+)
 from crewai.events.types.flow_events import (
     FlowCreatedEvent,
     FlowFinishedEvent,
@@ -192,6 +198,7 @@ class TraceCollectionListener(BaseEventListener):
         if self._listeners_setup:
             return
 
+        self._register_env_event_handlers(crewai_event_bus)
         self._register_flow_event_handlers(crewai_event_bus)
         self._register_context_event_handlers(crewai_event_bus)
         self._register_action_event_handlers(crewai_event_bus)
@@ -200,6 +207,25 @@ class TraceCollectionListener(BaseEventListener):
 
         self._listeners_setup = True
 
+    def _register_env_event_handlers(self, event_bus: CrewAIEventsBus) -> None:
+        """Register handlers for environment context events."""
+
+        @event_bus.on(CCEnvEvent)
+        def on_cc_env(source: Any, event: CCEnvEvent) -> None:
+            self._handle_action_event("cc_env", source, event)
+
+        @event_bus.on(CodexEnvEvent)
+        def on_codex_env(source: Any, event: CodexEnvEvent) -> None:
+            self._handle_action_event("codex_env", source, event)
+
+        @event_bus.on(CursorEnvEvent)
+        def on_cursor_env(source: Any, event: CursorEnvEvent) -> None:
+            self._handle_action_event("cursor_env", source, event)
+
+        @event_bus.on(DefaultEnvEvent)
+        def on_default_env(source: Any, event: DefaultEnvEvent) -> None:
+            self._handle_action_event("default_env", source, event)
+
     def _register_flow_event_handlers(self, event_bus: CrewAIEventsBus) -> None:
         """Register handlers for flow events."""
 

lib/crewai/src/crewai/events/types/env_events.py

@@ -0,0 +1,36 @@
+from typing import Annotated, Literal
+
+from pydantic import Field, TypeAdapter
+
+from crewai.events.base_events import BaseEvent
+
+
+class CCEnvEvent(BaseEvent):
+    type: Literal["cc_env"] = "cc_env"
+
+
+class CodexEnvEvent(BaseEvent):
+    type: Literal["codex_env"] = "codex_env"
+
+
+class CursorEnvEvent(BaseEvent):
+    type: Literal["cursor_env"] = "cursor_env"
+
+
+class DefaultEnvEvent(BaseEvent):
+    type: Literal["default_env"] = "default_env"
+
+
+EnvContextEvent = Annotated[
+    CCEnvEvent | CodexEnvEvent | CursorEnvEvent | DefaultEnvEvent,
+    Field(discriminator="type"),
+]
+
+env_context_event_adapter: TypeAdapter[EnvContextEvent] = TypeAdapter(EnvContextEvent)
+
+ENV_CONTEXT_EVENT_TYPES: tuple[type[BaseEvent], ...] = (
+    CCEnvEvent,
+    CodexEnvEvent,
+    CursorEnvEvent,
+    DefaultEnvEvent,
+)

lib/crewai/src/crewai/flow/flow.py

@@ -81,6 +81,7 @@ from crewai.flow.flow_wrappers import (
     SimpleFlowCondition,
     StartMethod,
 )
+from crewai.flow.input_provider import InputProvider
 from crewai.flow.persistence.base import FlowPersistence
 from crewai.flow.types import (
     FlowExecutionData,
@@ -99,6 +100,8 @@ from crewai.flow.utils import (
     is_flow_method_name,
     is_simple_flow_condition,
 )
+from crewai.memory.memory_scope import MemoryScope, MemorySlice
+from crewai.memory.unified_memory import Memory
 
 
 if TYPE_CHECKING:
@@ -110,6 +113,7 @@ if TYPE_CHECKING:
 
 from crewai.flow.visualization import build_flow_structure, render_interactive
 from crewai.types.streaming import CrewStreamingOutput, FlowStreamingOutput
+from crewai.utilities.env import get_env_context
 from crewai.utilities.streaming import (
     TaskInfo,
     create_async_chunk_generator,
@@ -500,7 +504,7 @@ class LockedListProxy(list, Generic[T]):  # type: ignore[type-arg]
 
     def index(
         self, value: T, start: SupportsIndex = 0, stop: SupportsIndex | None = None
-    ) -> int:  # type: ignore[override]
+    ) -> int:
         if stop is None:
             return self._list.index(value, start)
         return self._list.index(value, start, stop)
@@ -519,13 +523,13 @@ class LockedListProxy(list, Generic[T]):  # type: ignore[type-arg]
     def copy(self) -> list[T]:
         return self._list.copy()
 
-    def __add__(self, other: list[T]) -> list[T]:
+    def __add__(self, other: list[T]) -> list[T]:  # type: ignore[override]
         return self._list + other
 
     def __radd__(self, other: list[T]) -> list[T]:
         return other + self._list
 
-    def __iadd__(self, other: Iterable[T]) -> LockedListProxy[T]:
+    def __iadd__(self, other: Iterable[T]) -> LockedListProxy[T]:  # type: ignore[override]
         with self._lock:
             self._list += list(other)
         return self
@@ -629,13 +633,13 @@ class LockedDictProxy(dict, Generic[T]):  # type: ignore[type-arg]
     def copy(self) -> dict[str, T]:
         return self._dict.copy()
 
-    def __or__(self, other: dict[str, T]) -> dict[str, T]:
+    def __or__(self, other: dict[str, T]) -> dict[str, T]:  # type: ignore[override]
         return self._dict | other
 
-    def __ror__(self, other: dict[str, T]) -> dict[str, T]:
+    def __ror__(self, other: dict[str, T]) -> dict[str, T]:  # type: ignore[override]
         return other | self._dict
 
-    def __ior__(self, other: dict[str, T]) -> LockedDictProxy[T]:
+    def __ior__(self, other: dict[str, T]) -> LockedDictProxy[T]:  # type: ignore[override]
         with self._lock:
             self._dict |= other
         return self
@@ -821,10 +825,8 @@ class Flow(Generic[T], metaclass=FlowMeta):
     name: str | None = None
     tracing: bool | None = None
     stream: bool = False
-    memory: Any = (
-        None  # Memory | MemoryScope | MemorySlice | None; auto-created if not set
-    )
-    input_provider: Any = None  # InputProvider | None; per-flow override for self.ask()
+    memory: Memory | MemoryScope | MemorySlice | None = None
+    input_provider: InputProvider | None = None
 
     def __class_getitem__(cls: type[Flow[T]], item: type[T]) -> type[Flow[T]]:
         class _FlowGeneric(cls):  # type: ignore
@@ -903,8 +905,6 @@ class Flow(Generic[T], metaclass=FlowMeta):
         # Internal flows (RecallFlow, EncodingFlow) set _skip_auto_memory
         # to avoid creating a wasteful standalone Memory instance.
         if self.memory is None and not getattr(self, "_skip_auto_memory", False):
-            from crewai.memory.unified_memory import Memory
-
             self.memory = Memory()
 
         # Register all flow-related methods
@@ -950,10 +950,16 @@ class Flow(Generic[T], metaclass=FlowMeta):
 
         Raises:
             ValueError: If no memory is configured for this flow.
+            TypeError: If batch remember is attempted on a MemoryScope or MemorySlice.
         """
         if self.memory is None:
             raise ValueError("No memory configured for this flow")
         if isinstance(content, list):
+            if not isinstance(self.memory, Memory):
+                raise TypeError(
+                    "Batch remember requires a Memory instance, "
+                    f"got {type(self.memory).__name__}"
+                )
             return self.memory.remember_many(content, **kwargs)
         return self.memory.remember(content, **kwargs)
 
@@ -1309,7 +1315,25 @@ class Flow(Generic[T], metaclass=FlowMeta):
         context = self._pending_feedback_context
         emit = context.emit
         default_outcome = context.default_outcome
-        llm = context.llm
+
+        # Try to get the live LLM from the re-imported decorator instead of the
+        # serialized string. When a flow pauses for HITL and resumes (possibly in
+        # a different process), context.llm only contains a model string like
+        # 'gemini/gemini-3-flash-preview'. This loses credentials, project,
+        # location, safety_settings, and client_params. By looking up the method
+        # on the re-imported flow class, we can retrieve the fully-configured LLM
+        # that was passed to the @human_feedback decorator.
+        llm = context.llm  # fallback to serialized string
+        method = self._methods.get(FlowMethodName(context.method_name))
+        if method is not None:
+            live_llm = getattr(method, "_hf_llm", None)
+            if live_llm is not None:
+                from crewai.llms.base_llm import BaseLLM as BaseLLMClass
+
+                # Only use live LLM if it's a BaseLLM instance (not a string)
+                # String values offer no benefit over the serialized context.llm
+                if isinstance(live_llm, BaseLLMClass):
+                    llm = live_llm
 
         # Determine outcome
         collapsed_outcome: str | None = None
@@ -1770,6 +1794,7 @@ class Flow(Generic[T], metaclass=FlowMeta):
         Returns:
             The final output from the flow or FlowStreamingOutput if streaming.
         """
+        get_env_context()
         if self.stream:
             result_holder: list[Any] = []
             current_task_info: TaskInfo = {
@@ -2723,7 +2748,7 @@ class Flow(Generic[T], metaclass=FlowMeta):
 
     # ── User Input (self.ask) ────────────────────────────────────────
 
-    def _resolve_input_provider(self) -> Any:
+    def _resolve_input_provider(self) -> InputProvider:
         """Resolve the input provider using the priority chain.
 
         Resolution order:

lib/crewai/src/crewai/flow/flow_config.py

@@ -6,7 +6,7 @@ customize Flow behavior at runtime.
 
 from __future__ import annotations
 
-from typing import TYPE_CHECKING, Any
+from typing import TYPE_CHECKING
 
 
 if TYPE_CHECKING:
@@ -32,17 +32,17 @@ class FlowConfig:
         self._input_provider: InputProvider | None = None
 
     @property
-    def hitl_provider(self) -> Any:
+    def hitl_provider(self) -> HumanFeedbackProvider | None:
         """Get the configured HITL provider."""
         return self._hitl_provider
 
     @hitl_provider.setter
-    def hitl_provider(self, provider: Any) -> None:
+    def hitl_provider(self, provider: HumanFeedbackProvider | None) -> None:
         """Set the HITL provider."""
         self._hitl_provider = provider
 
     @property
-    def input_provider(self) -> Any:
+    def input_provider(self) -> InputProvider | None:
         """Get the configured input provider for ``Flow.ask()``.
 
         Returns:
@@ -52,7 +52,7 @@ class FlowConfig:
         return self._input_provider
 
     @input_provider.setter
-    def input_provider(self, provider: Any) -> None:
+    def input_provider(self, provider: InputProvider | None) -> None:
         """Set the input provider for ``Flow.ask()``.
 
         Args:

lib/crewai/src/crewai/flow/flow_wrappers.py

@@ -75,6 +75,7 @@ class FlowMethod(Generic[P, R]):
             "__is_router__",
             "__router_paths__",
             "__human_feedback_config__",
+            "_hf_llm",  # Live LLM object for HITL resume
         ]:
             if hasattr(meth, attr):
                 setattr(self, attr, getattr(meth, attr))

lib/crewai/src/crewai/flow/human_feedback.py

@@ -572,6 +572,14 @@ def human_feedback(
             wrapper.__is_router__ = True
             wrapper.__router_paths__ = list(emit)
 
+        # Stash the live LLM object for HITL resume to retrieve.
+        # When a flow pauses for human feedback and later resumes (possibly in a
+        # different process), the serialized context only contains a model string.
+        # By storing the original LLM on the wrapper, resume_async can retrieve
+        # the fully-configured LLM (with credentials, project, safety_settings, etc.)
+        # instead of creating a bare LLM from just the model string.
+        wrapper._hf_llm = llm
+
         return wrapper  # type: ignore[no-any-return]
 
     return decorator

lib/crewai/src/crewai/memory/unified_memory.py

@@ -22,7 +22,6 @@ from crewai.events.types.memory_events import (
 )
 from crewai.llms.base_llm import BaseLLM
 from crewai.memory.analyze import extract_memories_from_content
-from crewai.memory.recall_flow import RecallFlow
 from crewai.memory.storage.backend import StorageBackend
 from crewai.memory.types import (
     MemoryConfig,
@@ -620,6 +619,8 @@ class Memory(BaseModel):
                         )
                     results.sort(key=lambda m: m.score, reverse=True)
             else:
+                from crewai.memory.recall_flow import RecallFlow
+
                 flow = RecallFlow(
                     storage=self._storage,
                     llm=self._llm,

lib/crewai/src/crewai/task.py

@@ -67,6 +67,7 @@ except ImportError:
         return []
 
 
+from crewai.types.callback import SerializableCallable
 from crewai.utilities.guardrail import (
     process_guardrail,
 )
@@ -124,7 +125,7 @@ class Task(BaseModel):
         description="Configuration for the agent",
         default=None,
     )
-    callback: Any | None = Field(
+    callback: SerializableCallable | None = Field(
         description="Callback to be executed after the task is completed.", default=None
     )
     agent: BaseAgent | None = Field(

lib/crewai/src/crewai/telemetry/telemetry.py

@@ -986,6 +986,22 @@ class Telemetry:
 
         self._safe_telemetry_operation(_operation)
 
+    def env_context_span(self, tool: str) -> None:
+        """Records the coding tool environment context."""
+
+        def _operation() -> None:
+            tracer = trace.get_tracer("crewai.telemetry")
+            span = tracer.start_span("Environment Context")
+            self._add_attribute(
+                span,
+                "crewai_version",
+                version("crewai"),
+            )
+            self._add_attribute(span, "tool", tool)
+            close_span(span)
+
+        self._safe_telemetry_operation(_operation)
+
     def human_feedback_span(
         self,
         event_type: str,

lib/crewai/src/crewai/tools/base_tool.py

@@ -281,6 +281,7 @@ class BaseTool(BaseModel, ABC):
             result_as_answer=self.result_as_answer,
             max_usage_count=self.max_usage_count,
             current_usage_count=self.current_usage_count,
+            cache_function=self.cache_function,
         )
         structured_tool._original_tool = self
         return structured_tool

lib/crewai/src/crewai/tools/structured_tool.py

@@ -58,6 +58,7 @@ class CrewStructuredTool:
         result_as_answer: bool = False,
         max_usage_count: int | None = None,
         current_usage_count: int = 0,
+        cache_function: Callable[..., bool] | None = None,
     ) -> None:
         """Initialize the structured tool.
 
@@ -69,6 +70,7 @@ class CrewStructuredTool:
             result_as_answer: Whether to return the output directly
             max_usage_count: Maximum number of times this tool can be used. None means unlimited usage.
             current_usage_count: Current number of times this tool has been used.
+            cache_function: Function to determine if the tool result should be cached.
         """
         self.name = name
         self.description = description
@@ -78,6 +80,7 @@ class CrewStructuredTool:
         self.result_as_answer = result_as_answer
         self.max_usage_count = max_usage_count
         self.current_usage_count = current_usage_count
+        self.cache_function = cache_function
         self._original_tool: BaseTool | None = None
 
         # Validate the function signature matches the schema
@@ -86,7 +89,7 @@ class CrewStructuredTool:
     @classmethod
     def from_function(
         cls,
-        func: Callable,
+        func: Callable[..., Any],
         name: str | None = None,
         description: str | None = None,
         return_direct: bool = False,
@@ -147,7 +150,7 @@ class CrewStructuredTool:
     @staticmethod
     def _create_schema_from_function(
         name: str,
-        func: Callable,
+        func: Callable[..., Any],
     ) -> type[BaseModel]:
         """Create a Pydantic schema from a function's signature.
 
@@ -182,7 +185,7 @@ class CrewStructuredTool:
 
         # Create model
         schema_name = f"{name.title()}Schema"
-        return create_model(schema_name, **fields)  # type: ignore[call-overload]
+        return create_model(schema_name, **fields)  # type: ignore[call-overload, no-any-return]
 
     def _validate_function_signature(self) -> None:
         """Validate that the function signature matches the args schema."""
@@ -210,7 +213,7 @@ class CrewStructuredTool:
                         f"not found in args_schema"
                     )
 
-    def _parse_args(self, raw_args: str | dict) -> dict:
+    def _parse_args(self, raw_args: str | dict[str, Any]) -> dict[str, Any]:
         """Parse and validate the input arguments against the schema.
 
         Args:
@@ -234,8 +237,8 @@ class CrewStructuredTool:
 
     async def ainvoke(
         self,
-        input: str | dict,
-        config: dict | None = None,
+        input: str | dict[str, Any],
+        config: dict[str, Any] | None = None,
         **kwargs: Any,
     ) -> Any:
         """Asynchronously invoke the tool.
@@ -269,7 +272,7 @@ class CrewStructuredTool:
         except Exception:
             raise
 
-    def _run(self, *args, **kwargs) -> Any:
+    def _run(self, *args: Any, **kwargs: Any) -> Any:
         """Legacy method for compatibility."""
         # Convert args/kwargs to our expected format
         input_dict = dict(zip(self.args_schema.model_fields.keys(), args, strict=False))
@@ -277,7 +280,10 @@ class CrewStructuredTool:
         return self.invoke(input_dict)
 
     def invoke(
-        self, input: str | dict, config: dict | None = None, **kwargs: Any
+        self,
+        input: str | dict[str, Any],
+        config: dict[str, Any] | None = None,
+        **kwargs: Any,
     ) -> Any:
         """Main method for tool execution."""
         parsed_args = self._parse_args(input)
@@ -313,9 +319,10 @@ class CrewStructuredTool:
             self._original_tool.current_usage_count = self.current_usage_count
 
     @property
-    def args(self) -> dict:
+    def args(self) -> dict[str, Any]:
         """Get the tool's input arguments schema."""
-        return self.args_schema.model_json_schema()["properties"]
+        schema: dict[str, Any] = self.args_schema.model_json_schema()["properties"]
+        return schema
 
     def __repr__(self) -> str:
         return f"CrewStructuredTool(name='{sanitize_tool_name(self.name)}', description='{self.description}')"

lib/crewai/src/crewai/types/callback.py

@@ -0,0 +1,152 @@
+"""Serializable callback type for Pydantic models.
+
+Provides a ``SerializableCallable`` type alias that enables full JSON
+round-tripping of callback fields, e.g. ``"builtins.print"`` ↔ ``print``.
+Lambdas and closures serialize to a dotted path but cannot be deserialized
+back — use module-level named functions for checkpointable callbacks.
+"""
+
+from __future__ import annotations
+
+from collections.abc import Callable
+import importlib
+import inspect
+import os
+from typing import Annotated, Any
+import warnings
+
+from pydantic import BeforeValidator, WithJsonSchema
+from pydantic.functional_serializers import PlainSerializer
+
+
+def _is_non_roundtrippable(fn: object) -> bool:
+    """Return ``True`` if *fn* cannot survive a serialize/deserialize round-trip.
+
+    Built-in functions, plain module-level functions, and classes produce
+    dotted paths that :func:`_resolve_dotted_path` can reliably resolve.
+    Bound methods, ``functools.partial`` objects, callable class instances,
+    lambdas, and closures all fail or silently change semantics during
+    round-tripping.
+
+    Args:
+        fn: The object to check.
+
+    Returns:
+        ``True`` if *fn* would not round-trip through JSON serialization.
+    """
+    if inspect.isbuiltin(fn) or inspect.isclass(fn):
+        return False
+    if inspect.isfunction(fn):
+        qualname = getattr(fn, "__qualname__", "")
+        return qualname.endswith("<lambda>") or "<locals>" in qualname
+    return True
+
+
+def string_to_callable(value: Any) -> Callable[..., Any]:
+    """Convert a dotted path string to the callable it references.
+
+    If *value* is already callable it is returned as-is, with a warning if
+    it cannot survive JSON round-tripping.  Otherwise, it is treated as
+    ``"module.qualname"`` and resolved via :func:`_resolve_dotted_path`.
+
+    Args:
+        value: A callable or a dotted-path string e.g. ``"builtins.print"``.
+
+    Returns:
+        The resolved callable.
+
+    Raises:
+        ValueError: If *value* is not callable or a resolvable dotted-path string.
+    """
+    if callable(value):
+        if _is_non_roundtrippable(value):
+            warnings.warn(
+                f"{type(value).__name__} callbacks cannot be serialized "
+                "and will prevent checkpointing. "
+                "Use a module-level named function instead.",
+                UserWarning,
+                stacklevel=2,
+            )
+        return value  # type: ignore[no-any-return]
+    if not isinstance(value, str):
+        raise ValueError(
+            f"Expected a callable or dotted-path string, got {type(value).__name__}"
+        )
+    if "." not in value:
+        raise ValueError(
+            f"Invalid callback path {value!r}: expected 'module.name' format"
+        )
+    if not os.environ.get("CREWAI_DESERIALIZE_CALLBACKS"):
+        raise ValueError(
+            f"Refusing to resolve callback path {value!r}: "
+            "set CREWAI_DESERIALIZE_CALLBACKS=1 to allow. "
+            "Only enable this for trusted checkpoint data."
+        )
+    return _resolve_dotted_path(value)
+
+
+def _resolve_dotted_path(path: str) -> Callable[..., Any]:
+    """Import a module and walk attribute lookups to resolve a dotted path.
+
+    Handles multi-level qualified names like ``"module.ClassName.method"``
+    by trying progressively shorter module paths and resolving the remainder
+    as chained attribute lookups.
+
+    Args:
+        path: A dotted string e.g. ``"builtins.print"`` or
+              ``"mymodule.MyClass.my_method"``.
+
+    Returns:
+        The resolved callable.
+
+    Raises:
+        ValueError: If no valid module can be imported from the path.
+    """
+    parts = path.split(".")
+    # Try importing progressively shorter prefixes as the module.
+    for i in range(len(parts), 0, -1):
+        module_path = ".".join(parts[:i])
+        try:
+            obj: Any = importlib.import_module(module_path)
+        except (ImportError, TypeError, ValueError):
+            continue
+        # Walk the remaining attribute chain.
+        try:
+            for attr in parts[i:]:
+                obj = getattr(obj, attr)
+        except AttributeError:
+            continue
+        if callable(obj):
+            return obj  # type: ignore[no-any-return]
+    raise ValueError(f"Cannot resolve callback {path!r}")
+
+
+def callable_to_string(fn: Callable[..., Any]) -> str:
+    """Serialize a callable to its dotted-path string representation.
+
+    Uses ``fn.__module__`` and ``fn.__qualname__`` to produce a string such
+    as ``"builtins.print"``.  Lambdas and closures produce paths that contain
+    ``<locals>`` and cannot be round-tripped via :func:`string_to_callable`.
+
+    Args:
+        fn: The callable to serialize.
+
+    Returns:
+        A dotted string of the form ``"module.qualname"``.
+    """
+    module = getattr(fn, "__module__", None)
+    qualname = getattr(fn, "__qualname__", None)
+    if module is None or qualname is None:
+        raise ValueError(
+            f"Cannot serialize {fn!r}: missing __module__ or __qualname__. "
+            "Use a module-level named function for checkpointable callbacks."
+        )
+    return f"{module}.{qualname}"
+
+
+SerializableCallable = Annotated[
+    Callable[..., Any],
+    BeforeValidator(string_to_callable),
+    PlainSerializer(callable_to_string, return_type=str, when_used="json"),
+    WithJsonSchema({"type": "string"}),
+]

lib/crewai/src/crewai/utilities/constants.py

@@ -8,6 +8,21 @@ TRAINED_AGENTS_DATA_FILE: Final[str] = "trained_agents_data.pkl"
 KNOWLEDGE_DIRECTORY: Final[str] = "knowledge"
 MAX_FILE_NAME_LENGTH: Final[int] = 255
 EMITTER_COLOR: Final[PrinterColor] = "bold_blue"
+CC_ENV_VAR: Final[str] = "CLAUDECODE"
+CODEX_ENV_VARS: Final[tuple[str, ...]] = (
+    "CODEX_CI",
+    "CODEX_MANAGED_BY_NPM",
+    "CODEX_SANDBOX",
+    "CODEX_SANDBOX_NETWORK_DISABLED",
+    "CODEX_THREAD_ID",
+)
+CURSOR_ENV_VARS: Final[tuple[str, ...]] = (
+    "CURSOR_AGENT",
+    "CURSOR_EXTENSION_HOST_ROLE",
+    "CURSOR_SANDBOX",
+    "CURSOR_TRACE_ID",
+    "CURSOR_WORKSPACE_LABEL",
+)
 
 
 class _NotSpecified:

lib/crewai/src/crewai/utilities/env.py

@@ -0,0 +1,39 @@
+import contextvars
+import os
+
+from crewai.events.event_bus import crewai_event_bus
+from crewai.events.types.env_events import (
+    CCEnvEvent,
+    CodexEnvEvent,
+    CursorEnvEvent,
+    DefaultEnvEvent,
+)
+from crewai.utilities.constants import CC_ENV_VAR, CODEX_ENV_VARS, CURSOR_ENV_VARS
+
+
+_env_context_emitted: contextvars.ContextVar[bool] = contextvars.ContextVar(
+    "_env_context_emitted", default=False
+)
+
+
+def _is_codex_env() -> bool:
+    return any(os.environ.get(var) for var in CODEX_ENV_VARS)
+
+
+def _is_cursor_env() -> bool:
+    return any(os.environ.get(var) for var in CURSOR_ENV_VARS)
+
+
+def get_env_context() -> None:
+    if _env_context_emitted.get():
+        return
+    _env_context_emitted.set(True)
+
+    if os.environ.get(CC_ENV_VAR):
+        crewai_event_bus.emit(None, CCEnvEvent())
+    elif _is_codex_env():
+        crewai_event_bus.emit(None, CodexEnvEvent())
+    elif _is_cursor_env():
+        crewai_event_bus.emit(None, CursorEnvEvent())
+    else:
+        crewai_event_bus.emit(None, DefaultEnvEvent())

lib/crewai/src/crewai/utilities/lock_store.py

@@ -1,7 +1,7 @@
 """Centralised lock factory.
 
-If ``REDIS_URL`` is set, locks are distributed via ``portalocker.RedisLock``. Otherwise, falls
-back to the standard ``portalocker.Lock``.
+If ``REDIS_URL`` is set and the ``redis`` package is installed, locks are distributed via
+``portalocker.RedisLock``. Otherwise, falls back to the standard ``portalocker.Lock``.
 """
 
 from __future__ import annotations
@@ -30,6 +30,18 @@ _REDIS_URL: str | None = os.environ.get("REDIS_URL")
 _DEFAULT_TIMEOUT: Final[int] = 120
 
 
+def _redis_available() -> bool:
+    """Return True if redis is installed and REDIS_URL is set."""
+    if not _REDIS_URL:
+        return False
+    try:
+        import redis  # noqa: F401
+
+        return True
+    except ImportError:
+        return False
+
+
 @lru_cache(maxsize=1)
 def _redis_connection() -> redis.Redis:
     """Return a cached Redis connection, creating one on first call."""
@@ -51,7 +63,7 @@ def lock(name: str, *, timeout: float = _DEFAULT_TIMEOUT) -> Iterator[None]:
     """
     channel = f"crewai:{md5(name.encode(), usedforsecurity=False).hexdigest()}"
 
-    if _REDIS_URL:
+    if _redis_available():
         with portalocker.RedisLock(
             channel=channel,
             connection=_redis_connection(),

lib/crewai/tests/agents/test_agent.py

@@ -1690,7 +1690,10 @@ def test_agent_with_knowledge_sources_works_with_copy():
         with patch(
             "crewai.knowledge.storage.knowledge_storage.KnowledgeStorage"
         ) as mock_knowledge_storage:
+            from crewai.knowledge.storage.base_knowledge_storage import BaseKnowledgeStorage
+
             mock_knowledge_storage_instance = mock_knowledge_storage.return_value
+            mock_knowledge_storage_instance.__class__ = BaseKnowledgeStorage
             agent.knowledge_storage = mock_knowledge_storage_instance
 
             agent_copy = agent.copy()

lib/crewai/tests/test_async_human_feedback.py

@@ -1216,3 +1216,275 @@ class TestAsyncHumanFeedbackEdgeCases:
 
             assert flow.last_human_feedback.outcome == "approved"
             assert flow.last_human_feedback.feedback == ""
+
+
+# =============================================================================
+# Tests for _hf_llm attribute and live LLM resolution on resume
+# =============================================================================
+
+
+class TestLiveLLMPreservationOnResume:
+    """Tests for preserving the full LLM config across HITL resume."""
+
+    def test_hf_llm_attribute_set_on_wrapper_with_basellm(self) -> None:
+        """Test that _hf_llm is set on the wrapper when llm is a BaseLLM instance."""
+        from crewai.llms.base_llm import BaseLLM
+
+        # Create a mock BaseLLM object
+        mock_llm = MagicMock(spec=BaseLLM)
+        mock_llm.model = "gemini/gemini-3-flash"
+
+        class TestFlow(Flow):
+            @start()
+            @human_feedback(
+                message="Review:",
+                emit=["approved", "rejected"],
+                llm=mock_llm,
+            )
+            def review(self):
+                return "content"
+
+        flow = TestFlow()
+        method = flow._methods.get("review")
+        assert method is not None
+        assert hasattr(method, "_hf_llm")
+        assert method._hf_llm is mock_llm
+
+    def test_hf_llm_attribute_set_on_wrapper_with_string(self) -> None:
+        """Test that _hf_llm is set on the wrapper even when llm is a string."""
+
+        class TestFlow(Flow):
+            @start()
+            @human_feedback(
+                message="Review:",
+                emit=["approved", "rejected"],
+                llm="gpt-4o-mini",
+            )
+            def review(self):
+                return "content"
+
+        flow = TestFlow()
+        method = flow._methods.get("review")
+        assert method is not None
+        assert hasattr(method, "_hf_llm")
+        assert method._hf_llm == "gpt-4o-mini"
+
+    @patch("crewai.flow.flow.crewai_event_bus.emit")
+    def test_resume_async_uses_live_basellm_over_serialized_string(
+        self, mock_emit: MagicMock
+    ) -> None:
+        """Test that resume_async uses the live BaseLLM from decorator instead of serialized string.
+
+        This is the main bug fix: when a flow resumes, it should use the fully-configured
+        LLM from the re-imported decorator (with credentials, project, etc.) instead of
+        creating a new LLM from just the model string.
+        """
+        with tempfile.TemporaryDirectory() as tmpdir:
+            db_path = os.path.join(tmpdir, "test_flows.db")
+            persistence = SQLiteFlowPersistence(db_path)
+
+            from crewai.llms.base_llm import BaseLLM
+
+            # Create a mock BaseLLM with full config (simulating Gemini with service account)
+            live_llm = MagicMock(spec=BaseLLM)
+            live_llm.model = "gemini/gemini-3-flash"
+
+            class TestFlow(Flow):
+                result_path: str = ""
+
+                @start()
+                @human_feedback(
+                    message="Approve?",
+                    emit=["approved", "rejected"],
+                    llm=live_llm,  # Full LLM object with credentials
+                )
+                def review(self):
+                    return "content"
+
+                @listen("approved")
+                def handle_approved(self):
+                    self.result_path = "approved"
+                    return "Approved!"
+
+            # Save pending feedback with just a model STRING (simulating serialization)
+            context = PendingFeedbackContext(
+                flow_id="live-llm-test",
+                flow_class="TestFlow",
+                method_name="review",
+                method_output="content",
+                message="Approve?",
+                emit=["approved", "rejected"],
+                llm="gemini/gemini-3-flash",  # Serialized string, NOT the live object
+            )
+            persistence.save_pending_feedback(
+                flow_uuid="live-llm-test",
+                context=context,
+                state_data={"id": "live-llm-test"},
+            )
+
+            # Restore flow - this re-imports the class with the live LLM
+            flow = TestFlow.from_pending("live-llm-test", persistence)
+
+            # Mock _collapse_to_outcome to capture what LLM it receives
+            captured_llm = []
+
+            def capture_llm(feedback, outcomes, llm):
+                captured_llm.append(llm)
+                return "approved"
+
+            with patch.object(flow, "_collapse_to_outcome", side_effect=capture_llm):
+                flow.resume("looks good!")
+
+            # The key assertion: _collapse_to_outcome received the LIVE BaseLLM object,
+            # NOT the serialized string. The live_llm was captured at class definition
+            # time and stored on the method wrapper as _hf_llm.
+            assert len(captured_llm) == 1
+            # Verify it's the same object that was passed to the decorator
+            # (which is stored on the method's _hf_llm attribute)
+            method = flow._methods.get("review")
+            assert method is not None
+            assert captured_llm[0] is method._hf_llm
+            # And verify it's a BaseLLM instance, not a string
+            assert isinstance(captured_llm[0], BaseLLM)
+
+    @patch("crewai.flow.flow.crewai_event_bus.emit")
+    def test_resume_async_falls_back_to_serialized_string_when_no_hf_llm(
+        self, mock_emit: MagicMock
+    ) -> None:
+        """Test that resume_async falls back to context.llm when _hf_llm is not available.
+
+        This ensures backward compatibility with flows that were paused before this fix.
+        """
+        with tempfile.TemporaryDirectory() as tmpdir:
+            db_path = os.path.join(tmpdir, "test_flows.db")
+            persistence = SQLiteFlowPersistence(db_path)
+
+            class TestFlow(Flow):
+                @start()
+                @human_feedback(
+                    message="Approve?",
+                    emit=["approved", "rejected"],
+                    llm="gpt-4o-mini",
+                )
+                def review(self):
+                    return "content"
+
+            # Save pending feedback
+            context = PendingFeedbackContext(
+                flow_id="fallback-test",
+                flow_class="TestFlow",
+                method_name="review",
+                method_output="content",
+                message="Approve?",
+                emit=["approved", "rejected"],
+                llm="gpt-4o-mini",
+            )
+            persistence.save_pending_feedback(
+                flow_uuid="fallback-test",
+                context=context,
+                state_data={"id": "fallback-test"},
+            )
+
+            flow = TestFlow.from_pending("fallback-test", persistence)
+
+            # Remove _hf_llm to simulate old decorator without this attribute
+            method = flow._methods.get("review")
+            if hasattr(method, "_hf_llm"):
+                delattr(method, "_hf_llm")
+
+            # Mock _collapse_to_outcome to capture what LLM it receives
+            captured_llm = []
+
+            def capture_llm(feedback, outcomes, llm):
+                captured_llm.append(llm)
+                return "approved"
+
+            with patch.object(flow, "_collapse_to_outcome", side_effect=capture_llm):
+                flow.resume("looks good!")
+
+            # Should fall back to the serialized string
+            assert len(captured_llm) == 1
+            assert captured_llm[0] == "gpt-4o-mini"
+
+    @patch("crewai.flow.flow.crewai_event_bus.emit")
+    def test_resume_async_uses_string_from_context_when_hf_llm_is_string(
+        self, mock_emit: MagicMock
+    ) -> None:
+        """Test that when _hf_llm is a string (not BaseLLM), we still use context.llm.
+
+        String LLM values offer no benefit over the serialized context.llm,
+        so we don't prefer them.
+        """
+        with tempfile.TemporaryDirectory() as tmpdir:
+            db_path = os.path.join(tmpdir, "test_flows.db")
+            persistence = SQLiteFlowPersistence(db_path)
+
+            class TestFlow(Flow):
+                @start()
+                @human_feedback(
+                    message="Approve?",
+                    emit=["approved", "rejected"],
+                    llm="gpt-4o-mini",  # String LLM
+                )
+                def review(self):
+                    return "content"
+
+            # Save pending feedback
+            context = PendingFeedbackContext(
+                flow_id="string-llm-test",
+                flow_class="TestFlow",
+                method_name="review",
+                method_output="content",
+                message="Approve?",
+                emit=["approved", "rejected"],
+                llm="gpt-4o-mini",
+            )
+            persistence.save_pending_feedback(
+                flow_uuid="string-llm-test",
+                context=context,
+                state_data={"id": "string-llm-test"},
+            )
+
+            flow = TestFlow.from_pending("string-llm-test", persistence)
+
+            # Verify _hf_llm is a string
+            method = flow._methods.get("review")
+            assert method._hf_llm == "gpt-4o-mini"
+
+            # Mock _collapse_to_outcome to capture what LLM it receives
+            captured_llm = []
+
+            def capture_llm(feedback, outcomes, llm):
+                captured_llm.append(llm)
+                return "approved"
+
+            with patch.object(flow, "_collapse_to_outcome", side_effect=capture_llm):
+                flow.resume("looks good!")
+
+            # Should use context.llm since _hf_llm is a string (not BaseLLM)
+            assert len(captured_llm) == 1
+            assert captured_llm[0] == "gpt-4o-mini"
+
+    def test_hf_llm_set_for_async_wrapper(self) -> None:
+        """Test that _hf_llm is set on async wrapper functions."""
+        import asyncio
+        from crewai.llms.base_llm import BaseLLM
+
+        mock_llm = MagicMock(spec=BaseLLM)
+        mock_llm.model = "gemini/gemini-3-flash"
+
+        class TestFlow(Flow):
+            @start()
+            @human_feedback(
+                message="Review:",
+                emit=["approved", "rejected"],
+                llm=mock_llm,
+            )
+            async def async_review(self):
+                return "content"
+
+        flow = TestFlow()
+        method = flow._methods.get("async_review")
+        assert method is not None
+        assert hasattr(method, "_hf_llm")
+        assert method._hf_llm is mock_llm

lib/crewai/tests/test_callback.py

@@ -0,0 +1,237 @@
+"""Tests for crewai.types.callback — SerializableCallable round-tripping."""
+
+from __future__ import annotations
+
+import functools
+import os
+from typing import Any
+import pytest
+from pydantic import BaseModel, ValidationError
+
+from crewai.types.callback import (
+    SerializableCallable,
+    _is_non_roundtrippable,
+    _resolve_dotted_path,
+    callable_to_string,
+    string_to_callable,
+)
+
+
+# ── Helpers ──────────────────────────────────────────────────────────
+
+
+def module_level_function() -> str:
+    """Plain module-level function that should round-trip."""
+    return "hello"
+
+
+class _CallableInstance:
+    """Callable class instance — non-roundtrippable."""
+
+    def __call__(self) -> str:
+        return "instance"
+
+
+class _HasMethod:
+    def method(self) -> str:
+        return "method"
+
+
+class _Model(BaseModel):
+    cb: SerializableCallable | None = None
+
+
+# ── _is_non_roundtrippable ───────────────────────────────────────────
+
+
+class TestIsNonRoundtrippable:
+    def test_builtin_is_roundtrippable(self) -> None:
+        assert _is_non_roundtrippable(print) is False
+        assert _is_non_roundtrippable(len) is False
+
+    def test_class_is_roundtrippable(self) -> None:
+        assert _is_non_roundtrippable(dict) is False
+        assert _is_non_roundtrippable(_CallableInstance) is False
+
+    def test_module_level_function_is_roundtrippable(self) -> None:
+        assert _is_non_roundtrippable(module_level_function) is False
+
+    def test_lambda_is_non_roundtrippable(self) -> None:
+        assert _is_non_roundtrippable(lambda: None) is True
+
+    def test_closure_is_non_roundtrippable(self) -> None:
+        x = 1
+
+        def closure() -> int:
+            return x
+
+        assert _is_non_roundtrippable(closure) is True
+
+    def test_bound_method_is_non_roundtrippable(self) -> None:
+        assert _is_non_roundtrippable(_HasMethod().method) is True
+
+    def test_partial_is_non_roundtrippable(self) -> None:
+        assert _is_non_roundtrippable(functools.partial(print, "hi")) is True
+
+    def test_callable_instance_is_non_roundtrippable(self) -> None:
+        assert _is_non_roundtrippable(_CallableInstance()) is True
+
+
+# ── callable_to_string ───────────────────────────────────────────────
+
+
+class TestCallableToString:
+    def test_module_level_function(self) -> None:
+        result = callable_to_string(module_level_function)
+        assert result == f"{__name__}.module_level_function"
+
+    def test_class(self) -> None:
+        result = callable_to_string(dict)
+        assert result == "builtins.dict"
+
+    def test_builtin(self) -> None:
+        result = callable_to_string(print)
+        assert result == "builtins.print"
+
+    def test_lambda_produces_locals_path(self) -> None:
+        fn = lambda: None  # noqa: E731
+        result = callable_to_string(fn)
+        assert "<lambda>" in result
+
+    def test_missing_qualname_raises(self) -> None:
+        obj = type("NoQual", (), {"__module__": "test"})()
+        obj.__qualname__ = None  # type: ignore[assignment]
+        with pytest.raises(ValueError, match="missing __module__ or __qualname__"):
+            callable_to_string(obj)
+
+    def test_missing_module_raises(self) -> None:
+        # Create an object where getattr(obj, "__module__", None) returns None
+        ns: dict[str, Any] = {"__qualname__": "x", "__module__": None}
+        obj = type("NoMod", (), ns)()
+        with pytest.raises(ValueError, match="missing __module__"):
+            callable_to_string(obj)
+
+
+# ── string_to_callable ───────────────────────────────────────────────
+
+
+class TestStringToCallable:
+    def test_callable_passthrough(self) -> None:
+        assert string_to_callable(print) is print
+
+    def test_roundtrippable_callable_no_warning(self, recwarn: pytest.WarningsChecker) -> None:
+        string_to_callable(module_level_function)
+        our_warnings = [
+            w for w in recwarn if "cannot be serialized" in str(w.message)
+        ]
+        assert our_warnings == []
+
+    def test_non_roundtrippable_warns(self) -> None:
+        with pytest.warns(UserWarning, match="cannot be serialized"):
+            string_to_callable(functools.partial(print))
+
+    def test_non_callable_non_string_raises(self) -> None:
+        with pytest.raises(ValueError, match="Expected a callable"):
+            string_to_callable(42)
+
+    def test_string_without_dot_raises(self) -> None:
+        with pytest.raises(ValueError, match="expected 'module.name' format"):
+            string_to_callable("nodots")
+
+    def test_string_refused_without_env_var(self, monkeypatch: pytest.MonkeyPatch) -> None:
+        monkeypatch.delenv("CREWAI_DESERIALIZE_CALLBACKS", raising=False)
+        with pytest.raises(ValueError, match="Refusing to resolve"):
+            string_to_callable("builtins.print")
+
+    def test_string_resolves_with_env_var(self, monkeypatch: pytest.MonkeyPatch) -> None:
+        monkeypatch.setenv("CREWAI_DESERIALIZE_CALLBACKS", "1")
+        result = string_to_callable("builtins.print")
+        assert result is print
+
+    def test_string_resolves_multi_level_path(self, monkeypatch: pytest.MonkeyPatch) -> None:
+        monkeypatch.setenv("CREWAI_DESERIALIZE_CALLBACKS", "1")
+        result = string_to_callable("os.path.join")
+        assert result is os.path.join
+
+    def test_unresolvable_path_raises(self, monkeypatch: pytest.MonkeyPatch) -> None:
+        monkeypatch.setenv("CREWAI_DESERIALIZE_CALLBACKS", "1")
+        with pytest.raises(ValueError, match="Cannot resolve"):
+            string_to_callable("nonexistent.module.func")
+
+
+# ── _resolve_dotted_path ─────────────────────────────────────────────
+
+
+class TestResolveDottedPath:
+    def test_builtin(self) -> None:
+        assert _resolve_dotted_path("builtins.print") is print
+
+    def test_nested_module_attribute(self) -> None:
+        assert _resolve_dotted_path("os.path.join") is os.path.join
+
+    def test_class_on_module(self) -> None:
+        from collections import OrderedDict
+
+        assert _resolve_dotted_path("collections.OrderedDict") is OrderedDict
+
+    def test_nonexistent_raises(self) -> None:
+        with pytest.raises(ValueError, match="Cannot resolve"):
+            _resolve_dotted_path("no.such.module.func")
+
+    def test_non_callable_attribute_skipped(self) -> None:
+        # os.sep is a string, not callable — should not resolve
+        with pytest.raises(ValueError, match="Cannot resolve"):
+            _resolve_dotted_path("os.sep")
+
+
+# ── Pydantic integration round-trip ──────────────────────────────────
+
+
+class TestSerializableCallableRoundTrip:
+    def test_json_serialize_module_function(self) -> None:
+        m = _Model(cb=module_level_function)
+        data = m.model_dump(mode="json")
+        assert data["cb"] == f"{__name__}.module_level_function"
+
+    def test_json_round_trip(self, monkeypatch: pytest.MonkeyPatch) -> None:
+        monkeypatch.setenv("CREWAI_DESERIALIZE_CALLBACKS", "1")
+        m = _Model(cb=print)
+        json_str = m.model_dump_json()
+        restored = _Model.model_validate_json(json_str)
+        assert restored.cb is print
+
+    def test_json_round_trip_class(self, monkeypatch: pytest.MonkeyPatch) -> None:
+        monkeypatch.setenv("CREWAI_DESERIALIZE_CALLBACKS", "1")
+        m = _Model(cb=dict)
+        json_str = m.model_dump_json()
+        restored = _Model.model_validate_json(json_str)
+        assert restored.cb is dict
+
+    def test_python_mode_preserves_callable(self) -> None:
+        m = _Model(cb=module_level_function)
+        data = m.model_dump(mode="python")
+        assert data["cb"] is module_level_function
+
+    def test_none_field(self) -> None:
+        m = _Model(cb=None)
+        assert m.cb is None
+        data = m.model_dump(mode="json")
+        assert data["cb"] is None
+
+    def test_validation_error_for_int(self) -> None:
+        with pytest.raises(ValidationError):
+            _Model(cb=42)  # type: ignore[arg-type]
+
+    def test_deserialization_refused_without_env(
+        self, monkeypatch: pytest.MonkeyPatch
+    ) -> None:
+        monkeypatch.delenv("CREWAI_DESERIALIZE_CALLBACKS", raising=False)
+        with pytest.raises(ValidationError, match="Refusing to resolve"):
+            _Model.model_validate({"cb": "builtins.print"})
+
+    def test_json_schema_is_string(self) -> None:
+        schema = _Model.model_json_schema()
+        cb_schema = schema["properties"]["cb"]
+        # anyOf for Optional: one string, one null
+        types = {item.get("type") for item in cb_schema.get("anyOf", [cb_schema])}
+        assert "string" in types

lib/crewai/tests/test_project.py

@@ -6,6 +6,7 @@ from crewai.agent import Agent
 from crewai.agents.agent_builder.base_agent import BaseAgent
 from crewai.crew import Crew
 from crewai.llm import LLM
+from crewai.llms.base_llm import BaseLLM
 from crewai.project import (
     CrewBase,
     after_kickoff,
@@ -371,9 +372,12 @@ def test_internal_crew_with_mcp():
     mock_adapter = Mock()
     mock_adapter.tools = ToolCollection([simple_tool, another_simple_tool])
 
+    mock_llm = Mock()
+    mock_llm.__class__ = BaseLLM
+
     with (
         patch("crewai_tools.MCPServerAdapter", return_value=mock_adapter) as adapter_mock,
-        patch("crewai.llm.LLM.__new__", return_value=Mock()),
+        patch("crewai.llm.LLM.__new__", return_value=mock_llm),
     ):
         crew = InternalCrewWithMCP()
         assert crew.reporting_analyst().tools == [simple_tool, another_simple_tool]

lib/crewai/tests/tools/test_structured_tool.py

@@ -38,6 +38,44 @@ def test_initialization(basic_function, schema_class):
     assert tool.args_schema == schema_class
 
 
+def test_cache_function_passed_through(basic_function, schema_class):
+    """Test that cache_function is stored on CrewStructuredTool."""
+
+    def no_cache(_args: dict, _result: str) -> bool:
+        return False
+
+    tool = CrewStructuredTool(
+        name="test_tool",
+        description="Test tool description",
+        func=basic_function,
+        args_schema=schema_class,
+        cache_function=no_cache,
+    )
+
+    assert tool.cache_function is no_cache
+
+
+def test_base_tool_passes_cache_function_to_structured_tool():
+    """Test that BaseTool.to_structured_tool propagates cache_function."""
+    from crewai.tools import BaseTool
+
+    def no_cache(_args: dict, _result: str) -> bool:
+        return False
+
+    class MyCacheTool(BaseTool):
+        name: str = "cache_test"
+        description: str = "tool for testing cache passthrough"
+
+        def _run(self, query: str = "") -> str:
+            return "result"
+
+    my_tool = MyCacheTool()
+    my_tool.cache_function = no_cache  # type: ignore[assignment]
+    structured = my_tool.to_structured_tool()
+
+    assert structured.cache_function is no_cache
+
+
 def test_from_function(basic_function):
     """Test creating tool from function"""
     tool = CrewStructuredTool.from_function(

lib/crewai/tests/utilities/test_lock_store.py

@@ -0,0 +1,70 @@
+"""Tests for lock_store.
+
+We verify our own logic: the _redis_available guard and which portalocker
+backend is selected. We trust portalocker to handle actual locking mechanics.
+"""
+
+from __future__ import annotations
+
+import sys
+from unittest import mock
+
+import pytest
+
+import crewai.utilities.lock_store as lock_store
+from crewai.utilities.lock_store import lock
+
+
+@pytest.fixture(autouse=True)
+def no_redis_url(monkeypatch):
+    monkeypatch.setattr(lock_store, "_REDIS_URL", None)
+
+
+# ---------------------------------------------------------------------------
+# _redis_available
+# ---------------------------------------------------------------------------
+
+
+def test_redis_not_available_without_url():
+    assert lock_store._redis_available() is False
+
+
+def test_redis_not_available_when_package_missing(monkeypatch):
+    monkeypatch.setattr(lock_store, "_REDIS_URL", "redis://localhost:6379")
+    monkeypatch.setitem(sys.modules, "redis", None)  # None → ImportError on import
+    assert lock_store._redis_available() is False
+
+
+def test_redis_available_with_url_and_package(monkeypatch):
+    monkeypatch.setattr(lock_store, "_REDIS_URL", "redis://localhost:6379")
+    monkeypatch.setitem(sys.modules, "redis", mock.MagicMock())
+    assert lock_store._redis_available() is True
+
+
+# ---------------------------------------------------------------------------
+# lock strategy selection
+# ---------------------------------------------------------------------------
+
+
+def test_uses_file_lock_when_redis_unavailable():
+    with mock.patch("portalocker.Lock") as mock_lock:
+        with lock("file_test"):
+            pass
+
+    mock_lock.assert_called_once()
+    assert "crewai:" in mock_lock.call_args.args[0]
+
+
+def test_uses_redis_lock_when_redis_available(monkeypatch):
+    fake_conn = mock.MagicMock()
+    monkeypatch.setattr(lock_store, "_redis_available", mock.Mock(return_value=True))
+    monkeypatch.setattr(lock_store, "_redis_connection", mock.Mock(return_value=fake_conn))
+
+    with mock.patch("portalocker.RedisLock") as mock_redis_lock:
+        with lock("redis_test"):
+            pass
+
+    mock_redis_lock.assert_called_once()
+    kwargs = mock_redis_lock.call_args.kwargs
+    assert kwargs["channel"].startswith("crewai:")
+    assert kwargs["connection"] is fake_conn

lib/devtools/src/crewai_devtools/cli.py

@@ -5,6 +5,7 @@ from pathlib import Path
 import subprocess
 import sys
 import time
+from typing import Final, Literal
 
 import click
 from dotenv import load_dotenv
@@ -250,7 +251,9 @@ def add_docs_version(docs_json_path: Path, version: str) -> bool:
     return True
 
 
-_PT_BR_MONTHS = {
+ChangelogLang = Literal["en", "pt-BR", "ko"]
+
+_PT_BR_MONTHS: Final[dict[int, str]] = {
     1: "jan",
     2: "fev",
     3: "mar",
@@ -265,7 +268,9 @@ _PT_BR_MONTHS = {
     12: "dez",
 }
 
-_CHANGELOG_LOCALES: dict[str, dict[str, str]] = {
+_CHANGELOG_LOCALES: Final[
+    dict[ChangelogLang, dict[Literal["link_text", "language_name"], str]]
+] = {
     "en": {
         "link_text": "View release on GitHub",
         "language_name": "English",
@@ -283,7 +288,7 @@ _CHANGELOG_LOCALES: dict[str, dict[str, str]] = {
 
 def translate_release_notes(
     release_notes: str,
-    lang: str,
+    lang: ChangelogLang,
     client: OpenAI,
 ) -> str:
     """Translate release notes into the target language using OpenAI.
@@ -326,7 +331,7 @@ def translate_release_notes(
         return release_notes
 
 
-def _format_changelog_date(lang: str) -> str:
+def _format_changelog_date(lang: ChangelogLang) -> str:
     """Format today's date for a changelog entry in the given language."""
     from datetime import datetime
 
@@ -342,7 +347,7 @@ def update_changelog(
     changelog_path: Path,
     version: str,
     release_notes: str,
-    lang: str = "en",
+    lang: ChangelogLang = "en",
 ) -> bool:
     """Prepend a new release entry to a docs changelog file.
 
@@ -475,6 +480,23 @@ def get_packages(lib_dir: Path) -> list[Path]:
     return packages
 
 
+PrereleaseIndicator = Literal["a", "b", "rc", "alpha", "beta", "dev"]
+_PRERELEASE_INDICATORS: Final[tuple[PrereleaseIndicator, ...]] = (
+    "a",
+    "b",
+    "rc",
+    "alpha",
+    "beta",
+    "dev",
+)
+
+
+def _is_prerelease(version: str) -> bool:
+    """Check if a version string represents a pre-release."""
+    v = version.lower().lstrip("v")
+    return any(indicator in v for indicator in _PRERELEASE_INDICATORS)
+
+
 def get_commits_from_last_tag(tag_name: str, version: str) -> tuple[str, str]:
     """Get commits from the last tag, excluding current version.
 
@@ -489,6 +511,9 @@ def get_commits_from_last_tag(tag_name: str, version: str) -> tuple[str, str]:
         all_tags = run_command(["git", "tag", "--sort=-version:refname"]).split("\n")
         prev_tags = [t for t in all_tags if t and t != tag_name and t != f"v{version}"]
 
+        if not _is_prerelease(version):
+            prev_tags = [t for t in prev_tags if not _is_prerelease(t)]
+
         if prev_tags:
             last_tag = prev_tags[0]
             commit_range = f"{last_tag}..HEAD"
@@ -678,20 +703,28 @@ def _generate_release_notes(
 
     with console.status("[cyan]Generating release notes..."):
         try:
-            prev_bump_commit = run_command(
+            prev_bump_output = run_command(
                 [
                     "git",
                     "log",
                     "--grep=^feat: bump versions to",
-                    "--format=%H",
-                    "-n",
-                    "2",
+                    "--format=%H %s",
                 ]
             )
-            commits_list = prev_bump_commit.strip().split("\n")
+            bump_entries = [
+                line for line in prev_bump_output.strip().split("\n") if line.strip()
+            ]
 
-            if len(commits_list) > 1:
-                prev_commit = commits_list[1]
+            is_stable = not _is_prerelease(version)
+            prev_commit = None
+            for entry in bump_entries[1:]:
+                bump_ver = entry.split("feat: bump versions to", 1)[-1].strip()
+                if is_stable and _is_prerelease(bump_ver):
+                    continue
+                prev_commit = entry.split()[0]
+                break
+
+            if prev_commit:
                 commit_range = f"{prev_commit}..HEAD"
                 commits = run_command(
                     ["git", "log", commit_range, "--pretty=format:%s"]
@@ -777,10 +810,7 @@ def _generate_release_notes(
             "\n[green]✓[/green] Using generated release notes without editing"
         )
 
-    is_prerelease = any(
-        indicator in version.lower()
-        for indicator in ["a", "b", "rc", "alpha", "beta", "dev"]
-    )
+    is_prerelease = _is_prerelease(version)
 
     return release_notes, openai_client, is_prerelease
 
@@ -799,7 +829,7 @@ def _update_docs_and_create_pr(
         The docs branch name if a PR was created, None otherwise.
     """
     docs_json_path = cwd / "docs" / "docs.json"
-    changelog_langs = ["en", "pt-BR", "ko"]
+    changelog_langs: list[ChangelogLang] = ["en", "pt-BR", "ko"]
 
     if not dry_run:
         docs_files_staged: list[str] = []

uv.lock

@@ -5556,11 +5556,11 @@ wheels = [
 
 [[package]]
 name = "pyasn1"
-version = "0.6.2"
+version = "0.6.3"
 source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/fe/b6/6e630dff89739fcd427e3f72b3d905ce0acb85a45d4ec3e2678718a3487f/pyasn1-0.6.2.tar.gz", hash = "sha256:9b59a2b25ba7e4f8197db7686c09fb33e658b98339fadb826e9512629017833b", size = 146586, upload-time = "2026-01-16T18:04:18.534Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/5c/5f/6583902b6f79b399c9c40674ac384fd9cd77805f9e6205075f828ef11fb2/pyasn1-0.6.3.tar.gz", hash = "sha256:697a8ecd6d98891189184ca1fa05d1bb00e2f84b5977c481452050549c8a72cf", size = 148685, upload-time = "2026-03-17T01:06:53.382Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/44/b5/a96872e5184f354da9c84ae119971a0a4c221fe9b27a4d94bd43f2596727/pyasn1-0.6.2-py3-none-any.whl", hash = "sha256:1eb26d860996a18e9b6ed05e7aae0e9fc21619fcee6af91cca9bad4fbea224bf", size = 83371, upload-time = "2026-01-16T18:04:17.174Z" },
+    { url = "https://files.pythonhosted.org/packages/5d/a0/7d793dce3fa811fe047d6ae2431c672364b462850c6235ae306c0efd025f/pyasn1-0.6.3-py3-none-any.whl", hash = "sha256:a80184d120f0864a52a073acc6fc642847d0be408e7c7252f31390c0f4eadcde", size = 83997, upload-time = "2026-03-17T01:06:52.036Z" },
 ]
 
 [[package]]