fix: Fix type-checker error in crew_agent_executor.py

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

docs/how-to/langfuse-observability.mdx

@@ -1,98 +0,0 @@
----
-title: Agent Monitoring with Langfuse
-description: Learn how to integrate Langfuse with CrewAI via OpenTelemetry using OpenLit
-icon: magnifying-glass-chart
----
-
-# Integrate Langfuse with CrewAI
-
-This notebook demonstrates how to integrate **Langfuse** with **CrewAI** using OpenTelemetry via the **OpenLit** SDK. By the end of this notebook, you will be able to trace your CrewAI applications with Langfuse for improved observability and debugging.
-
-> **What is Langfuse?** [Langfuse](https://langfuse.com) is an open-source LLM engineering platform. It provides tracing and monitoring capabilities for LLM applications, helping developers debug, analyze, and optimize their AI systems. Langfuse integrates with various tools and frameworks via native integrations, OpenTelemetry, and APIs/SDKs.
-
-## Get Started
-
-We'll walk through a simple example of using CrewAI and integrating it with Langfuse via OpenTelemetry using OpenLit.
-
-### Step 1: Install Dependencies
-
-
-```python
-%pip install langfuse openlit crewai crewai_tools
-```
-
-### Step 2: Set Up Environment Variables
-
-Set your Langfuse API keys and configure OpenTelemetry export settings to send traces to Langfuse. Please refer to the [Langfuse OpenTelemetry Docs](https://langfuse.com/docs/opentelemetry/get-started) for more information on the Langfuse OpenTelemetry endpoint `/api/public/otel` and authentication.
-
-
-```python
-import os
-import base64
-
-LANGFUSE_PUBLIC_KEY="pk-lf-..."
-LANGFUSE_SECRET_KEY="sk-lf-..."
-LANGFUSE_AUTH=base64.b64encode(f"{LANGFUSE_PUBLIC_KEY}:{LANGFUSE_SECRET_KEY}".encode()).decode()
-
-os.environ["OTEL_EXPORTER_OTLP_ENDPOINT"] = "https://cloud.langfuse.com/api/public/otel" # EU data region
-# os.environ["OTEL_EXPORTER_OTLP_ENDPOINT"] = "https://us.cloud.langfuse.com/api/public/otel" # US data region
-os.environ["OTEL_EXPORTER_OTLP_HEADERS"] = f"Authorization=Basic {LANGFUSE_AUTH}"
-
-# your openai key
-os.environ["OPENAI_API_KEY"] = "sk-..."
-```
-
-### Step 3: Initialize OpenLit
-
-Initialize the OpenLit OpenTelemetry instrumentation SDK to start capturing OpenTelemetry traces.
-
-
-```python
-import openlit
-
-openlit.init()
-```
-
-### Step 4: Create a Simple CrewAI Application
-
-We'll create a simple CrewAI application where multiple agents collaborate to answer a user's question.
-
-
-```python
-from crewai import Agent, Task, Crew
-
-from crewai_tools import (
-    WebsiteSearchTool
-)
-
-web_rag_tool = WebsiteSearchTool()
-
-writer = Agent(
-        role="Writer",
-        goal="You make math engaging and understandable for young children through poetry",
-        backstory="You're an expert in writing haikus but you know nothing of math.",
-        tools=[web_rag_tool],  
-    )
-
-task = Task(description=("What is {multiplication}?"),
-            expected_output=("Compose a haiku that includes the answer."),
-            agent=writer)
-
-crew = Crew(
-  agents=[writer],
-  tasks=[task],
-  share_crew=False
-)
-```
-
-### Step 5: See Traces in Langfuse
-
-After running the agent, you can view the traces generated by your CrewAI application in [Langfuse](https://cloud.langfuse.com). You should see detailed steps of the LLM interactions, which can help you debug and optimize your AI agent.
-
-![CrewAI example trace in Langfuse](https://langfuse.com/images/cookbook/integration_crewai/crewai-example-trace.png)
-
-_[Public example trace in Langfuse](https://cloud.langfuse.com/project/cloramnkj0002jz088vzn1ja4/traces/e2cf380ffc8d47d28da98f136140642b?timestamp=2025-02-05T15%3A12%3A02.717Z&observation=3b32338ee6a5d9af)_
-
-## References
-
-- [Langfuse OpenTelemetry Docs](https://langfuse.com/docs/opentelemetry/get-started)

docs/how-to/portkey-observability-and-guardrails.mdx

@@ -0,0 +1,211 @@
+# Portkey Integration with CrewAI
+<img src="https://raw.githubusercontent.com/siddharthsambharia-portkey/Portkey-Product-Images/main/Portkey-CrewAI.png" alt="Portkey CrewAI Header Image" width="70%" />
+
+
+[Portkey](https://portkey.ai/?utm_source=crewai&utm_medium=crewai&utm_campaign=crewai) is a 2-line upgrade to make your CrewAI agents reliable, cost-efficient, and fast.
+
+Portkey adds 4 core production capabilities to any CrewAI agent:
+1. Routing to **200+ LLMs**
+2. Making each LLM call more robust
+3. Full-stack tracing & cost, performance analytics
+4. Real-time guardrails to enforce behavior
+
+
+
+
+
+## Getting Started
+
+1. **Install Required Packages:**
+
+```bash
+pip install -qU crewai portkey-ai
+```
+
+2. **Configure the LLM Client:**
+
+To build CrewAI Agents with Portkey, you'll need two keys:
+- **Portkey API Key**: Sign up on the [Portkey app](https://app.portkey.ai/?utm_source=crewai&utm_medium=crewai&utm_campaign=crewai) and copy your API key
+- **Virtual Key**: Virtual Keys securely manage your LLM API keys in one place. Store your LLM provider API keys securely in Portkey's vault
+
+```python
+from crewai import LLM
+from portkey_ai import createHeaders, PORTKEY_GATEWAY_URL
+
+gpt_llm = LLM(
+    model="gpt-4",
+    base_url=PORTKEY_GATEWAY_URL,
+    api_key="dummy", # We are using Virtual key
+    extra_headers=createHeaders(
+        api_key="YOUR_PORTKEY_API_KEY",
+        virtual_key="YOUR_VIRTUAL_KEY", # Enter your Virtual key from Portkey
+    )
+)
+```
+
+3. **Create and Run Your First Agent:**
+
+```python
+from crewai import Agent, Task, Crew
+
+# Define your agents with roles and goals
+coder = Agent(
+    role='Software developer',
+    goal='Write clear, concise code on demand',
+    backstory='An expert coder with a keen eye for software trends.',
+    llm=gpt_llm
+)
+
+# Create tasks for your agents
+task1 = Task(
+    description="Define the HTML for making a simple website with heading- Hello World! Portkey is working!",
+    expected_output="A clear and concise HTML code",
+    agent=coder
+)
+
+# Instantiate your crew
+crew = Crew(
+    agents=[coder],
+    tasks=[task1],
+)
+
+result = crew.kickoff()
+print(result)
+```
+
+
+## Key Features
+
+| Feature | Description |
+|---------|-------------|
+| 🌐 Multi-LLM Support | Access OpenAI, Anthropic, Gemini, Azure, and 250+ providers through a unified interface |
+| 🛡️ Production Reliability | Implement retries, timeouts, load balancing, and fallbacks |
+| 📊 Advanced Observability | Track 40+ metrics including costs, tokens, latency, and custom metadata |
+| 🔍 Comprehensive Logging | Debug with detailed execution traces and function call logs |
+| 🚧 Security Controls | Set budget limits and implement role-based access control |
+| 🔄 Performance Analytics | Capture and analyze feedback for continuous improvement |
+| 💾 Intelligent Caching | Reduce costs and latency with semantic or simple caching |
+
+
+## Production Features with Portkey Configs
+
+All features mentioned below are through Portkey's Config system. Portkey's Config system allows you to define routing strategies using simple JSON objects in your LLM API calls. You can create and manage Configs directly in your code or through the Portkey Dashboard. Each Config has a unique ID for easy reference.
+
+<Frame>
+    <img src="https://raw.githubusercontent.com/Portkey-AI/docs-core/refs/heads/main/images/libraries/libraries-3.avif"/>
+</Frame>
+
+
+### 1. Use 250+ LLMs
+Access various LLMs like Anthropic, Gemini, Mistral, Azure OpenAI, and more with minimal code changes. Switch between providers or use them together seamlessly. [Learn more about Universal API](https://portkey.ai/docs/product/ai-gateway/universal-api)
+
+
+Easily switch between different LLM providers:
+
+```python
+# Anthropic Configuration
+anthropic_llm = LLM(
+    model="claude-3-5-sonnet-latest",
+    base_url=PORTKEY_GATEWAY_URL,
+    api_key="dummy",
+    extra_headers=createHeaders(
+        api_key="YOUR_PORTKEY_API_KEY",
+        virtual_key="YOUR_ANTHROPIC_VIRTUAL_KEY", #You don't need provider when using Virtual keys
+        trace_id="anthropic_agent"
+    )
+)
+
+# Azure OpenAI Configuration
+azure_llm = LLM(
+    model="gpt-4",
+    base_url=PORTKEY_GATEWAY_URL,
+    api_key="dummy",
+    extra_headers=createHeaders(
+        api_key="YOUR_PORTKEY_API_KEY",
+        virtual_key="YOUR_AZURE_VIRTUAL_KEY", #You don't need provider when using Virtual keys
+        trace_id="azure_agent"
+    )
+)
+```
+
+
+### 2. Caching
+Improve response times and reduce costs with two powerful caching modes:
+- **Simple Cache**: Perfect for exact matches
+- **Semantic Cache**: Matches responses for requests that are semantically similar
+[Learn more about Caching](https://portkey.ai/docs/product/ai-gateway/cache-simple-and-semantic)
+
+```py
+config = {
+    "cache": {
+        "mode": "semantic",  # or "simple" for exact matching
+    }
+}
+```
+
+### 3. Production Reliability
+Portkey provides comprehensive reliability features:
+- **Automatic Retries**: Handle temporary failures gracefully
+- **Request Timeouts**: Prevent hanging operations
+- **Conditional Routing**: Route requests based on specific conditions
+- **Fallbacks**: Set up automatic provider failovers
+- **Load Balancing**: Distribute requests efficiently
+
+[Learn more about Reliability Features](https://portkey.ai/docs/product/ai-gateway/)
+
+
+
+### 4. Metrics
+
+Agent runs are complex. Portkey automatically logs **40+ comprehensive metrics** for your AI agents, including cost, tokens used, latency, etc. Whether you need a broad overview or granular insights into your agent runs, Portkey's customizable filters provide the metrics you need.
+
+
+- Cost per agent interaction
+- Response times and latency
+- Token usage and efficiency
+- Success/failure rates
+- Cache hit rates
+
+<img src="https://github.com/siddharthsambharia-portkey/Portkey-Product-Images/blob/main/Portkey-Dashboard.png?raw=true" width="70%" alt="Portkey Dashboard" />
+
+### 5. Detailed Logging
+Logs are essential for understanding agent behavior, diagnosing issues, and improving performance. They provide a detailed record of agent activities and tool use, which is crucial for debugging and optimizing processes.
+
+
+Access a dedicated section to view records of agent executions, including parameters, outcomes, function calls, and errors. Filter logs based on multiple parameters such as trace ID, model, tokens used, and metadata.
+
+<details>
+  <summary><b>Traces</b></summary>
+  <img src="https://raw.githubusercontent.com/siddharthsambharia-portkey/Portkey-Product-Images/main/Portkey-Traces.png" alt="Portkey Traces" width="70%" />
+</details>
+
+<details>
+  <summary><b>Logs</b></summary>
+  <img src="https://raw.githubusercontent.com/siddharthsambharia-portkey/Portkey-Product-Images/main/Portkey-Logs.png" alt="Portkey Logs" width="70%" />
+</details>
+
+### 6. Enterprise Security Features
+- Set budget limit and rate limts per Virtual Key (disposable API keys)
+- Implement role-based access control
+- Track system changes with audit logs
+- Configure data retention policies
+
+
+
+For detailed information on creating and managing Configs, visit the [Portkey documentation](https://docs.portkey.ai/product/ai-gateway/configs).
+
+## Resources
+
+- [📘 Portkey Documentation](https://docs.portkey.ai)
+- [📊 Portkey Dashboard](https://app.portkey.ai/?utm_source=crewai&utm_medium=crewai&utm_campaign=crewai)
+- [🐦 Twitter](https://twitter.com/portkeyai)
+- [💬 Discord Community](https://discord.gg/DD7vgKK299)
+
+
+
+
+
+
+
+
+

docs/how-to/portkey-observability.mdx

@@ -1,5 +1,5 @@
 ---
-title: Agent Monitoring with Portkey
+title: Portkey Observability and Guardrails
 description: How to use Portkey with CrewAI
 icon: key
 ---

docs/mint.json

@@ -103,8 +103,7 @@
         "how-to/langtrace-observability",
         "how-to/mlflow-observability",
         "how-to/openlit-observability",
-        "how-to/portkey-observability",
-        "how-to/langfuse-observability"
+        "how-to/portkey-observability"
       ]
     },
     {

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "crewai"
-version = "0.102.0"
+version = "0.100.1"
 description = "Cutting-edge framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks."
 readme = "README.md"
 requires-python = ">=3.10,<3.13"
@@ -45,7 +45,7 @@ Documentation = "https://docs.crewai.com"
 Repository = "https://github.com/crewAIInc/crewAI"
 
 [project.optional-dependencies]
-tools = ["crewai-tools>=0.36.0"]
+tools = ["crewai-tools>=0.32.1"]
 embeddings = [
     "tiktoken~=0.7.0"
 ]

src/crewai/__init__.py

@@ -14,7 +14,7 @@ warnings.filterwarnings(
     category=UserWarning,
     module="pydantic.main",
 )
-__version__ = "0.102.0"
+__version__ = "0.100.1"
 __all__ = [
     "Agent",
     "Crew",

src/crewai/agents/crew_agent_executor.py

@@ -366,23 +366,41 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
             tool_result = tool_calling.message
             return ToolResult(result=tool_result, result_as_answer=False)
         else:
-            if tool_calling.tool_name.casefold().strip() in [
-                name.casefold().strip() for name in self.tool_name_to_tool_map
-            ] or tool_calling.tool_name.casefold().replace("_", " ") in [
-                name.casefold().strip() for name in self.tool_name_to_tool_map
-            ]:
+            valid_names = [name.casefold().strip() for name in self.tool_name_to_tool_map]
+            tool_name = tool_calling.tool_name.casefold().strip()
+            tool_name_alt = tool_calling.tool_name.casefold().replace("_", " ")
+            
+            if tool_name in valid_names or tool_name_alt in valid_names:
                 tool_result = tool_usage.use(tool_calling, agent_action.text)
+                tool_result = self._clean_tool_result(tool_result)
                 tool = self.tool_name_to_tool_map.get(tool_calling.tool_name)
-                if tool:
-                    return ToolResult(
-                        result=tool_result, result_as_answer=tool.result_as_answer
-                    )
-            else:
-                tool_result = self._i18n.errors("wrong_tool_name").format(
-                    tool=tool_calling.tool_name,
-                    tools=", ".join([tool.name.casefold() for tool in self.tools]),
+                return ToolResult(
+                    result=tool_result,
+                    result_as_answer=tool.result_as_answer if tool else False
                 )
-        return ToolResult(result=tool_result, result_as_answer=False)
+            
+            tool_result = self._i18n.errors("wrong_tool_name").format(
+                tool=tool_calling.tool_name,
+                tools=", ".join([tool.name.casefold() for tool in self.tools]),
+            )
+            return ToolResult(result=tool_result, result_as_answer=False)
+
+    def _clean_tool_result(self, tool_result: Any) -> Any:
+        """Clean tool result by removing trailing backticks.
+        
+        This is particularly important in hierarchical mode where tool outputs
+        might contain markdown formatting that needs to be cleaned up.
+        
+        Args:
+            tool_result: The result from a tool execution, can be any type
+            
+        Returns:
+            The cleaned result with any trailing backticks removed if it's a string,
+            otherwise returns the original result unchanged
+        """
+        if isinstance(tool_result, str):
+            return tool_result.rstrip('`').rstrip('```')
+        return tool_result
 
     def _summarize_messages(self) -> None:
         messages_groups = []

src/crewai/cli/templates/crew/pyproject.toml

@@ -5,7 +5,7 @@ description = "{{name}} using crewAI"
 authors = [{ name = "Your Name", email = "you@example.com" }]
 requires-python = ">=3.10,<3.13"
 dependencies = [
-    "crewai[tools]>=0.102.0,<1.0.0"
+    "crewai[tools]>=0.100.1,<1.0.0"
 ]
 
 [project.scripts]

src/crewai/cli/templates/flow/pyproject.toml

@@ -5,7 +5,7 @@ description = "{{name}} using crewAI"
 authors = [{ name = "Your Name", email = "you@example.com" }]
 requires-python = ">=3.10,<3.13"
 dependencies = [
-    "crewai[tools]>=0.102.0,<1.0.0",
+    "crewai[tools]>=0.100.1,<1.0.0",
 ]
 
 [project.scripts]

src/crewai/cli/templates/tool/pyproject.toml

@@ -5,7 +5,7 @@ description = "Power up your crews with {{folder_name}}"
 readme = "README.md"
 requires-python = ">=3.10,<3.13"
 dependencies = [
-    "crewai[tools]>=0.102.0"
+    "crewai[tools]>=0.100.1"
 ]
 
 [tool.crewai]

src/crewai/flow/flow.py

@@ -1,11 +1,6 @@
 import asyncio
-import dataclasses
-import functools
 import inspect
 import logging
-import threading
-import time
-from contextlib import contextmanager
 from typing import (
     Any,
     Callable,
@@ -19,22 +14,6 @@ from typing import (
     Union,
     cast,
 )
-
-from typing_extensions import Protocol
-
-logger = logging.getLogger(__name__)
-
-
-class SerializationError(Exception):
-    """Error during state serialization."""
-    pass
-
-
-class LockProtocol(Protocol):
-    """Protocol for thread-safe primitives."""
-    def acquire(self) -> bool: ...
-    def release(self) -> None: ...
-    def _is_owned(self) -> bool: ...
 from uuid import uuid4
 
 from blinker import Signal
@@ -415,6 +394,7 @@ class FlowMeta(type):
                 or hasattr(attr_value, "__trigger_methods__")
                 or hasattr(attr_value, "__is_router__")
             ):
+
                 # Register start methods
                 if hasattr(attr_value, "__is_start_method__"):
                     start_methods.append(attr_name)
@@ -457,23 +437,6 @@ class Flow(Generic[T], metaclass=FlowMeta):
     initial_state: Union[Type[T], T, None] = None
     event_emitter = Signal("event_emitter")
 
-    @contextmanager
-    def _performance_monitor(self, operation: str):
-        """Monitor performance of an operation.
-        
-        Args:
-            operation: Name of the operation being monitored
-            
-        Yields:
-            None
-        """
-        start = time.perf_counter()
-        try:
-            yield
-        finally:
-            duration = time.perf_counter() - start
-            logger.debug(f"{operation} took {duration:.4f} seconds")
-
     def __class_getitem__(cls: Type["Flow"], item: Type[T]) -> Type["Flow"]:
         class _FlowGeneric(cls):  # type: ignore
             _initial_state_T = item  # type: ignore
@@ -606,172 +569,6 @@ class Flow(Generic[T], metaclass=FlowMeta):
             f"Initial state must be dict or BaseModel, got {type(self.initial_state)}"
         )
 
-    # Cache thread-safe primitive types
-    THREAD_SAFE_TYPES = {
-        type(threading.RLock()): threading.RLock,
-        type(threading.Lock()): threading.Lock,
-        type(threading.Semaphore()): threading.Semaphore,
-        type(threading.Event()): threading.Event,
-        type(threading.Condition()): threading.Condition,
-        type(asyncio.Lock()): asyncio.Lock,
-        type(asyncio.Event()): asyncio.Event,
-        type(asyncio.Condition()): asyncio.Condition,
-        type(asyncio.Semaphore()): asyncio.Semaphore,
-    }
-
-    def _get_thread_safe_primitive_type(self, value: Any) -> Optional[Type[LockProtocol]]:
-        """Get the type of a thread-safe primitive for recreation.
-        
-        Args:
-            value: Any Python value to check
-            
-        Returns:
-            The type of the thread-safe primitive, or None if not a primitive
-        """
-        return (self.THREAD_SAFE_TYPES.get(type(value))
-                if hasattr(value, '_is_owned') and hasattr(value, 'acquire')
-                else None)
-
-    @functools.lru_cache(maxsize=128)
-    def _get_dataclass_fields(self, cls):
-        """Get cached dataclass fields.
-        
-        Args:
-            cls: Dataclass type
-            
-        Returns:
-            Dict mapping field names to Field objects
-        """
-        return {field.name: field for field in dataclasses.fields(cls)}
-
-    def _serialize_dataclass(self, value: Any) -> Union[Dict[str, Any], Any]:
-        """Serialize a dataclass instance.
-        
-        Args:
-            value: A dataclass instance
-            
-        Returns:
-            A new instance of the dataclass with thread-safe primitives recreated
-        """
-        try:
-            if not hasattr(value, '__class__'):
-                return value
-                
-            if hasattr(value, '__pydantic_validate__'):
-                return value.__pydantic_validate__()
-                
-            # Get field values, handling thread-safe primitives
-            field_values = {}
-            for field_name, field in self._get_dataclass_fields(value.__class__).items():
-                field_value = getattr(value, field_name)
-                primitive_type = self._get_thread_safe_primitive_type(field_value)
-                if primitive_type is not None:
-                    field_values[field_name] = primitive_type()
-                else:
-                    field_values[field_name] = self._serialize_value(field_value)
-                    
-            # Create new instance
-            return value.__class__(**field_values)
-        except Exception as e:
-            logger.error(f"Dataclass serialization error for {type(value)}: {str(e)}")
-            raise SerializationError(f"Failed to serialize dataclass {type(value)}") from e
-
-    def _serialize_value(self, value: Any) -> Any:
-        """Recursively serialize a value, handling thread locks.
-        
-        Args:
-            value: Any Python value to serialize
-            
-        Returns:
-            Serialized version of the value with thread-safe primitives handled
-            
-        Raises:
-            SerializationError: If serialization fails
-        """
-        with self._performance_monitor(f"serialize_{type(value).__name__}"):
-            try:
-                # Handle None
-                if value is None:
-                    return None
-                    
-                # Handle thread-safe primitives
-                primitive_type = self._get_thread_safe_primitive_type(value)
-                if primitive_type is not None:
-                    return primitive_type()
-                    
-                # Handle Pydantic models
-                if isinstance(value, BaseModel):
-                    model_class = type(value)
-                    model_data = value.model_dump(exclude_none=True)
-                    
-                    # Create new instance
-                    instance = model_class(**model_data)
-                    
-                    # Copy excluded fields that are thread-safe primitives
-                    for field_name, field in value.__class__.model_fields.items():
-                        if field.exclude:
-                            field_value = getattr(value, field_name, None)
-                            if field_value is not None:
-                                primitive_type = self._get_thread_safe_primitive_type(field_value)
-                                if primitive_type is not None:
-                                    setattr(instance, field_name, primitive_type())
-                    
-                    return instance
-                    
-                # Handle dataclasses
-                if dataclasses.is_dataclass(value):
-                    return self._serialize_dataclass(value)
-                    
-                # Handle dictionaries
-                if isinstance(value, dict):
-                    return {
-                        k: self._serialize_value(v)
-                        for k, v in value.items()
-                    }
-                    
-                # Handle lists, tuples, and sets
-                if isinstance(value, (list, tuple, set)):
-                    serialized = [self._serialize_value(item) for item in value]
-                    return (
-                        serialized if isinstance(value, list)
-                        else tuple(serialized) if isinstance(value, tuple)
-                        else set(serialized)
-                    )
-                    
-                # Handle other types
-                return value
-                
-            except Exception as e:
-                logger.error(f"Serialization error for {type(value)}: {str(e)}")
-                raise SerializationError(f"Failed to serialize {type(value)}") from e
-            
-        # Handle dataclasses
-        if dataclasses.is_dataclass(value):
-            return self._serialize_dataclass(value)
-            
-        # Handle dictionaries
-        if isinstance(value, dict):
-            return {
-                k: self._serialize_value(v)
-                for k, v in value.items()
-            }
-            
-        # Handle lists, tuples, and sets
-        if isinstance(value, (list, tuple, set)):
-            serialized = [self._serialize_value(item) for item in value]
-            return (
-                serialized if isinstance(value, list)
-                else tuple(serialized) if isinstance(value, tuple)
-                else set(serialized)
-            )
-            
-        # Handle other types
-        return value
-
-    def _copy_state(self) -> T:
-        """Create a deep copy of the current state."""
-        return self._serialize_value(self._state)
-
     @property
     def state(self) -> T:
         return self._state
@@ -943,7 +740,6 @@ class Flow(Generic[T], metaclass=FlowMeta):
             event=FlowStartedEvent(
                 type="flow_started",
                 flow_name=self.__class__.__name__,
-                inputs=inputs,
             ),
         )
         self._log_flow_event(
@@ -1007,18 +803,6 @@ class Flow(Generic[T], metaclass=FlowMeta):
     async def _execute_method(
         self, method_name: str, method: Callable, *args: Any, **kwargs: Any
     ) -> Any:
-        dumped_params = {f"_{i}": arg for i, arg in enumerate(args)} | (kwargs or {})
-        self.event_emitter.send(
-            self,
-            event=MethodExecutionStartedEvent(
-                type="method_execution_started",
-                method_name=method_name,
-                flow_name=self.__class__.__name__,
-                params=dumped_params,
-                state=self._copy_state(),
-            ),
-        )
-
         result = (
             await method(*args, **kwargs)
             if asyncio.iscoroutinefunction(method)
@@ -1028,18 +812,6 @@ class Flow(Generic[T], metaclass=FlowMeta):
         self._method_execution_counts[method_name] = (
             self._method_execution_counts.get(method_name, 0) + 1
         )
-
-        self.event_emitter.send(
-            self,
-            event=MethodExecutionFinishedEvent(
-                type="method_execution_finished",
-                method_name=method_name,
-                flow_name=self.__class__.__name__,
-                state=self._copy_state(),
-                result=result,
-            ),
-        )
-
         return result
 
     async def _execute_listeners(self, trigger_method: str, result: Any) -> None:
@@ -1178,6 +950,16 @@ class Flow(Generic[T], metaclass=FlowMeta):
         """
         try:
             method = self._methods[listener_name]
+
+            self.event_emitter.send(
+                self,
+                event=MethodExecutionStartedEvent(
+                    type="method_execution_started",
+                    method_name=listener_name,
+                    flow_name=self.__class__.__name__,
+                ),
+            )
+
             sig = inspect.signature(method)
             params = list(sig.parameters.values())
             method_params = [p for p in params if p.name != "self"]
@@ -1189,6 +971,15 @@ class Flow(Generic[T], metaclass=FlowMeta):
             else:
                 listener_result = await self._execute_method(listener_name, method)
 
+            self.event_emitter.send(
+                self,
+                event=MethodExecutionFinishedEvent(
+                    type="method_execution_finished",
+                    method_name=listener_name,
+                    flow_name=self.__class__.__name__,
+                ),
+            )
+
             # Execute listeners (and possibly routers) of this listener
             await self._execute_listeners(listener_name, listener_result)
 

src/crewai/flow/flow_events.py

@@ -1,8 +1,6 @@
 from dataclasses import dataclass, field
 from datetime import datetime
-from typing import Any, Dict, Optional, Union
-
-from pydantic import BaseModel
+from typing import Any, Optional
 
 
 @dataclass
@@ -17,21 +15,17 @@ class Event:
 
 @dataclass
 class FlowStartedEvent(Event):
-    inputs: Optional[Dict[str, Any]] = None
+    pass
 
 
 @dataclass
 class MethodExecutionStartedEvent(Event):
     method_name: str
-    state: Union[Dict[str, Any], BaseModel]
-    params: Optional[Dict[str, Any]] = None
 
 
 @dataclass
 class MethodExecutionFinishedEvent(Event):
     method_name: str
-    state: Union[Dict[str, Any], BaseModel]
-    result: Any = None
 
 
 @dataclass

tests/cassettes/test_hierarchical_tool_output_formatting[ - ].yaml

@@ -0,0 +1,111 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Crew Manager. You
+      are a seasoned manager with a knack for getting the best out of your team.\nYou
+      are also known for your ability to delegate work to the right people, and to
+      ask the right questions to get the best out of your team.\nEven though you don''t
+      perform tasks by yourself, you have a lot of experience in the field, which
+      allows you to properly evaluate the work of your team members.\nYour personal
+      goal is: Manage the team to complete the task in the best way possible.\nYou
+      ONLY have access to the following tools, and should NEVER make up tools that
+      are not listed here:\n\nTool Name: Delegate work to coworker\nTool Arguments:
+      {''task'': {''description'': ''The task to delegate'', ''type'': ''str''}, ''context'':
+      {''description'': ''The context for the task'', ''type'': ''str''}, ''coworker'':
+      {''description'': ''The role/name of the coworker to delegate to'', ''type'':
+      ''str''}}\nTool Description: Delegate a specific task to one of the following
+      coworkers: Researcher\nThe input to this tool should be the coworker, the task
+      you want them to do, and ALL necessary context to execute the task, they know
+      nothing about the task, so share absolute everything you know, don''t reference
+      things but instead explain them.\nTool Name: Ask question to coworker\nTool
+      Arguments: {''question'': {''description'': ''The question to ask'', ''type'':
+      ''str''}, ''context'': {''description'': ''The context for the question'', ''type'':
+      ''str''}, ''coworker'': {''description'': ''The role/name of the coworker to
+      ask'', ''type'': ''str''}}\nTool Description: Ask a specific question to one
+      of the following coworkers: Researcher\nThe input to this tool should be the
+      coworker, the question you have for them, and ALL necessary context to ask the
+      question properly, they know nothing about the question, so share absolute everything
+      you know, don''t reference things but instead explain them.\n\nIMPORTANT: Use
+      the following format in your response:\n\n```\nThought: you should always think
+      about what to do\nAction: the action to take, only one name of [Delegate work
+      to coworker, Ask question to coworker], just the name, exactly as it''s written.\nAction
+      Input: the input to the action, just a simple JSON object, enclosed in curly
+      braces, using \" to wrap keys and values.\nObservation: the result of the action\n```\n\nOnce
+      all necessary information is gathered, return the following format:\n\n```\nThought:
+      I now know the final answer\nFinal Answer: the final answer to the original
+      input question\n```"}, {"role": "user", "content": "\nCurrent Task: Test task
+      using test_tool\n\nThis is the expected criteria for your final answer: Test
+      output\nyou MUST return the actual complete content as the final answer, not
+      a summary.\n\nBegin! This is VERY important to you, use the tools available
+      and give your best Final Answer, your job depends on it!\n\nThought:"}], "model":
+      "gpt-4o", "stop": ["\nObservation:"]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '2915'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=0nI_3cs9LKHlz0_cVifl9lVXZWfNQrzhLRZzoaDCVJs-1739358791-1.0.1.1-GJZzVGs1fHQe9gucVHUCoDlI3mwg3JyXCBIIChx_OsB0jgqbzt1s2et96vUgpdjONt9C2tB8OQ6fk70k3vhh0w;
+        _cfuvid=TvEPcNq35qaIgBFFzOP7g7NQf632eeMrvRDJyr7UTro-1739358791985-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.61.0
+      x-stainless-arch:
+      - x64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - Linux
+      x-stainless-package-version:
+      - 1.61.0
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n    \"error\": {\n        \"message\": \"Incorrect API key provided:
+      sk-fake-**********2345. You can find your API key at https://platform.openai.com/account/api-keys.\",\n
+      \       \"type\": \"invalid_request_error\",\n        \"param\": null,\n        \"code\":
+      \"invalid_api_key\"\n    }\n}\n"
+    headers:
+      CF-RAY:
+      - 910c25fe3c8ca373-SEA
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '272'
+      Content-Type:
+      - application/json; charset=utf-8
+      Date:
+      - Wed, 12 Feb 2025 11:13:16 GMT
+      Server:
+      - cloudflare
+      X-Content-Type-Options:
+      - nosniff
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      vary:
+      - Origin
+      x-request-id:
+      - req_a5651cefb4c7ae9483499a8e538f579d
+    http_version: HTTP/1.1
+    status_code: 401
+version: 1

tests/cassettes/test_hierarchical_tool_output_formatting[None-None].yaml

@@ -0,0 +1,111 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Crew Manager. You
+      are a seasoned manager with a knack for getting the best out of your team.\nYou
+      are also known for your ability to delegate work to the right people, and to
+      ask the right questions to get the best out of your team.\nEven though you don''t
+      perform tasks by yourself, you have a lot of experience in the field, which
+      allows you to properly evaluate the work of your team members.\nYour personal
+      goal is: Manage the team to complete the task in the best way possible.\nYou
+      ONLY have access to the following tools, and should NEVER make up tools that
+      are not listed here:\n\nTool Name: Delegate work to coworker\nTool Arguments:
+      {''task'': {''description'': ''The task to delegate'', ''type'': ''str''}, ''context'':
+      {''description'': ''The context for the task'', ''type'': ''str''}, ''coworker'':
+      {''description'': ''The role/name of the coworker to delegate to'', ''type'':
+      ''str''}}\nTool Description: Delegate a specific task to one of the following
+      coworkers: Researcher\nThe input to this tool should be the coworker, the task
+      you want them to do, and ALL necessary context to execute the task, they know
+      nothing about the task, so share absolute everything you know, don''t reference
+      things but instead explain them.\nTool Name: Ask question to coworker\nTool
+      Arguments: {''question'': {''description'': ''The question to ask'', ''type'':
+      ''str''}, ''context'': {''description'': ''The context for the question'', ''type'':
+      ''str''}, ''coworker'': {''description'': ''The role/name of the coworker to
+      ask'', ''type'': ''str''}}\nTool Description: Ask a specific question to one
+      of the following coworkers: Researcher\nThe input to this tool should be the
+      coworker, the question you have for them, and ALL necessary context to ask the
+      question properly, they know nothing about the question, so share absolute everything
+      you know, don''t reference things but instead explain them.\n\nIMPORTANT: Use
+      the following format in your response:\n\n```\nThought: you should always think
+      about what to do\nAction: the action to take, only one name of [Delegate work
+      to coworker, Ask question to coworker], just the name, exactly as it''s written.\nAction
+      Input: the input to the action, just a simple JSON object, enclosed in curly
+      braces, using \" to wrap keys and values.\nObservation: the result of the action\n```\n\nOnce
+      all necessary information is gathered, return the following format:\n\n```\nThought:
+      I now know the final answer\nFinal Answer: the final answer to the original
+      input question\n```"}, {"role": "user", "content": "\nCurrent Task: Test task
+      using test_tool\n\nThis is the expected criteria for your final answer: Test
+      output\nyou MUST return the actual complete content as the final answer, not
+      a summary.\n\nBegin! This is VERY important to you, use the tools available
+      and give your best Final Answer, your job depends on it!\n\nThought:"}], "model":
+      "gpt-4o", "stop": ["\nObservation:"]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '2915'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=0nI_3cs9LKHlz0_cVifl9lVXZWfNQrzhLRZzoaDCVJs-1739358791-1.0.1.1-GJZzVGs1fHQe9gucVHUCoDlI3mwg3JyXCBIIChx_OsB0jgqbzt1s2et96vUgpdjONt9C2tB8OQ6fk70k3vhh0w;
+        _cfuvid=TvEPcNq35qaIgBFFzOP7g7NQf632eeMrvRDJyr7UTro-1739358791985-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.61.0
+      x-stainless-arch:
+      - x64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - Linux
+      x-stainless-package-version:
+      - 1.61.0
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n    \"error\": {\n        \"message\": \"Incorrect API key provided:
+      sk-fake-**********2345. You can find your API key at https://platform.openai.com/account/api-keys.\",\n
+      \       \"type\": \"invalid_request_error\",\n        \"param\": null,\n        \"code\":
+      \"invalid_api_key\"\n    }\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 910c25fa2a76a373-SEA
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '272'
+      Content-Type:
+      - application/json; charset=utf-8
+      Date:
+      - Wed, 12 Feb 2025 11:13:15 GMT
+      Server:
+      - cloudflare
+      X-Content-Type-Options:
+      - nosniff
+      alt-svc:
+      - h3=":443"; ma=86400
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      vary:
+      - Origin
+      x-request-id:
+      - req_3ad40f35d4ad6d42f9bbb7fd8ace9a68
+    http_version: HTTP/1.1
+    status_code: 401
+version: 1

tests/cassettes/test_hierarchical_tool_output_formatting[malformed`result```test-malformed`result```test].yaml

@@ -0,0 +1,111 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Crew Manager. You
+      are a seasoned manager with a knack for getting the best out of your team.\nYou
+      are also known for your ability to delegate work to the right people, and to
+      ask the right questions to get the best out of your team.\nEven though you don''t
+      perform tasks by yourself, you have a lot of experience in the field, which
+      allows you to properly evaluate the work of your team members.\nYour personal
+      goal is: Manage the team to complete the task in the best way possible.\nYou
+      ONLY have access to the following tools, and should NEVER make up tools that
+      are not listed here:\n\nTool Name: Delegate work to coworker\nTool Arguments:
+      {''task'': {''description'': ''The task to delegate'', ''type'': ''str''}, ''context'':
+      {''description'': ''The context for the task'', ''type'': ''str''}, ''coworker'':
+      {''description'': ''The role/name of the coworker to delegate to'', ''type'':
+      ''str''}}\nTool Description: Delegate a specific task to one of the following
+      coworkers: Researcher\nThe input to this tool should be the coworker, the task
+      you want them to do, and ALL necessary context to execute the task, they know
+      nothing about the task, so share absolute everything you know, don''t reference
+      things but instead explain them.\nTool Name: Ask question to coworker\nTool
+      Arguments: {''question'': {''description'': ''The question to ask'', ''type'':
+      ''str''}, ''context'': {''description'': ''The context for the question'', ''type'':
+      ''str''}, ''coworker'': {''description'': ''The role/name of the coworker to
+      ask'', ''type'': ''str''}}\nTool Description: Ask a specific question to one
+      of the following coworkers: Researcher\nThe input to this tool should be the
+      coworker, the question you have for them, and ALL necessary context to ask the
+      question properly, they know nothing about the question, so share absolute everything
+      you know, don''t reference things but instead explain them.\n\nIMPORTANT: Use
+      the following format in your response:\n\n```\nThought: you should always think
+      about what to do\nAction: the action to take, only one name of [Delegate work
+      to coworker, Ask question to coworker], just the name, exactly as it''s written.\nAction
+      Input: the input to the action, just a simple JSON object, enclosed in curly
+      braces, using \" to wrap keys and values.\nObservation: the result of the action\n```\n\nOnce
+      all necessary information is gathered, return the following format:\n\n```\nThought:
+      I now know the final answer\nFinal Answer: the final answer to the original
+      input question\n```"}, {"role": "user", "content": "\nCurrent Task: Test task
+      using test_tool\n\nThis is the expected criteria for your final answer: Test
+      output\nyou MUST return the actual complete content as the final answer, not
+      a summary.\n\nBegin! This is VERY important to you, use the tools available
+      and give your best Final Answer, your job depends on it!\n\nThought:"}], "model":
+      "gpt-4o", "stop": ["\nObservation:"]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '2915'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=0nI_3cs9LKHlz0_cVifl9lVXZWfNQrzhLRZzoaDCVJs-1739358791-1.0.1.1-GJZzVGs1fHQe9gucVHUCoDlI3mwg3JyXCBIIChx_OsB0jgqbzt1s2et96vUgpdjONt9C2tB8OQ6fk70k3vhh0w;
+        _cfuvid=TvEPcNq35qaIgBFFzOP7g7NQf632eeMrvRDJyr7UTro-1739358791985-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.61.0
+      x-stainless-arch:
+      - x64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - Linux
+      x-stainless-package-version:
+      - 1.61.0
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n    \"error\": {\n        \"message\": \"Incorrect API key provided:
+      sk-fake-**********2345. You can find your API key at https://platform.openai.com/account/api-keys.\",\n
+      \       \"type\": \"invalid_request_error\",\n        \"param\": null,\n        \"code\":
+      \"invalid_api_key\"\n    }\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 910c26028e7ba373-SEA
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '272'
+      Content-Type:
+      - application/json; charset=utf-8
+      Date:
+      - Wed, 12 Feb 2025 11:13:17 GMT
+      Server:
+      - cloudflare
+      X-Content-Type-Options:
+      - nosniff
+      alt-svc:
+      - h3=":443"; ma=86400
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      vary:
+      - Origin
+      x-request-id:
+      - req_6f0f7d9e36bbb3ffea4d672b30b700b9
+    http_version: HTTP/1.1
+    status_code: 401
+version: 1

tests/cassettes/test_hierarchical_tool_output_formatting[test ```result```-test ```result].yaml

@@ -0,0 +1,111 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Crew Manager. You
+      are a seasoned manager with a knack for getting the best out of your team.\nYou
+      are also known for your ability to delegate work to the right people, and to
+      ask the right questions to get the best out of your team.\nEven though you don''t
+      perform tasks by yourself, you have a lot of experience in the field, which
+      allows you to properly evaluate the work of your team members.\nYour personal
+      goal is: Manage the team to complete the task in the best way possible.\nYou
+      ONLY have access to the following tools, and should NEVER make up tools that
+      are not listed here:\n\nTool Name: Delegate work to coworker\nTool Arguments:
+      {''task'': {''description'': ''The task to delegate'', ''type'': ''str''}, ''context'':
+      {''description'': ''The context for the task'', ''type'': ''str''}, ''coworker'':
+      {''description'': ''The role/name of the coworker to delegate to'', ''type'':
+      ''str''}}\nTool Description: Delegate a specific task to one of the following
+      coworkers: Researcher\nThe input to this tool should be the coworker, the task
+      you want them to do, and ALL necessary context to execute the task, they know
+      nothing about the task, so share absolute everything you know, don''t reference
+      things but instead explain them.\nTool Name: Ask question to coworker\nTool
+      Arguments: {''question'': {''description'': ''The question to ask'', ''type'':
+      ''str''}, ''context'': {''description'': ''The context for the question'', ''type'':
+      ''str''}, ''coworker'': {''description'': ''The role/name of the coworker to
+      ask'', ''type'': ''str''}}\nTool Description: Ask a specific question to one
+      of the following coworkers: Researcher\nThe input to this tool should be the
+      coworker, the question you have for them, and ALL necessary context to ask the
+      question properly, they know nothing about the question, so share absolute everything
+      you know, don''t reference things but instead explain them.\n\nIMPORTANT: Use
+      the following format in your response:\n\n```\nThought: you should always think
+      about what to do\nAction: the action to take, only one name of [Delegate work
+      to coworker, Ask question to coworker], just the name, exactly as it''s written.\nAction
+      Input: the input to the action, just a simple JSON object, enclosed in curly
+      braces, using \" to wrap keys and values.\nObservation: the result of the action\n```\n\nOnce
+      all necessary information is gathered, return the following format:\n\n```\nThought:
+      I now know the final answer\nFinal Answer: the final answer to the original
+      input question\n```"}, {"role": "user", "content": "\nCurrent Task: Test task
+      using test_tool\n\nThis is the expected criteria for your final answer: Test
+      output\nyou MUST return the actual complete content as the final answer, not
+      a summary.\n\nBegin! This is VERY important to you, use the tools available
+      and give your best Final Answer, your job depends on it!\n\nThought:"}], "model":
+      "gpt-4o", "stop": ["\nObservation:"]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '2915'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=0nI_3cs9LKHlz0_cVifl9lVXZWfNQrzhLRZzoaDCVJs-1739358791-1.0.1.1-GJZzVGs1fHQe9gucVHUCoDlI3mwg3JyXCBIIChx_OsB0jgqbzt1s2et96vUgpdjONt9C2tB8OQ6fk70k3vhh0w;
+        _cfuvid=TvEPcNq35qaIgBFFzOP7g7NQf632eeMrvRDJyr7UTro-1739358791985-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.61.0
+      x-stainless-arch:
+      - x64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - Linux
+      x-stainless-package-version:
+      - 1.61.0
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n    \"error\": {\n        \"message\": \"Incorrect API key provided:
+      sk-fake-**********2345. You can find your API key at https://platform.openai.com/account/api-keys.\",\n
+      \       \"type\": \"invalid_request_error\",\n        \"param\": null,\n        \"code\":
+      \"invalid_api_key\"\n    }\n}\n"
+    headers:
+      CF-RAY:
+      - 910c25f5e85ba373-SEA
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '272'
+      Content-Type:
+      - application/json; charset=utf-8
+      Date:
+      - Wed, 12 Feb 2025 11:13:15 GMT
+      Server:
+      - cloudflare
+      X-Content-Type-Options:
+      - nosniff
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      vary:
+      - Origin
+      x-request-id:
+      - req_49a0c35d5999eb9f6d71fcea9fa3c68f
+    http_version: HTTP/1.1
+    status_code: 401
+version: 1

tests/cassettes/test_hierarchical_tool_output_formatting[test result-test result].yaml

@@ -0,0 +1,111 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Crew Manager. You
+      are a seasoned manager with a knack for getting the best out of your team.\nYou
+      are also known for your ability to delegate work to the right people, and to
+      ask the right questions to get the best out of your team.\nEven though you don''t
+      perform tasks by yourself, you have a lot of experience in the field, which
+      allows you to properly evaluate the work of your team members.\nYour personal
+      goal is: Manage the team to complete the task in the best way possible.\nYou
+      ONLY have access to the following tools, and should NEVER make up tools that
+      are not listed here:\n\nTool Name: Delegate work to coworker\nTool Arguments:
+      {''task'': {''description'': ''The task to delegate'', ''type'': ''str''}, ''context'':
+      {''description'': ''The context for the task'', ''type'': ''str''}, ''coworker'':
+      {''description'': ''The role/name of the coworker to delegate to'', ''type'':
+      ''str''}}\nTool Description: Delegate a specific task to one of the following
+      coworkers: Researcher\nThe input to this tool should be the coworker, the task
+      you want them to do, and ALL necessary context to execute the task, they know
+      nothing about the task, so share absolute everything you know, don''t reference
+      things but instead explain them.\nTool Name: Ask question to coworker\nTool
+      Arguments: {''question'': {''description'': ''The question to ask'', ''type'':
+      ''str''}, ''context'': {''description'': ''The context for the question'', ''type'':
+      ''str''}, ''coworker'': {''description'': ''The role/name of the coworker to
+      ask'', ''type'': ''str''}}\nTool Description: Ask a specific question to one
+      of the following coworkers: Researcher\nThe input to this tool should be the
+      coworker, the question you have for them, and ALL necessary context to ask the
+      question properly, they know nothing about the question, so share absolute everything
+      you know, don''t reference things but instead explain them.\n\nIMPORTANT: Use
+      the following format in your response:\n\n```\nThought: you should always think
+      about what to do\nAction: the action to take, only one name of [Delegate work
+      to coworker, Ask question to coworker], just the name, exactly as it''s written.\nAction
+      Input: the input to the action, just a simple JSON object, enclosed in curly
+      braces, using \" to wrap keys and values.\nObservation: the result of the action\n```\n\nOnce
+      all necessary information is gathered, return the following format:\n\n```\nThought:
+      I now know the final answer\nFinal Answer: the final answer to the original
+      input question\n```"}, {"role": "user", "content": "\nCurrent Task: Test task
+      using test_tool\n\nThis is the expected criteria for your final answer: Test
+      output\nyou MUST return the actual complete content as the final answer, not
+      a summary.\n\nBegin! This is VERY important to you, use the tools available
+      and give your best Final Answer, your job depends on it!\n\nThought:"}], "model":
+      "gpt-4o", "stop": ["\nObservation:"]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '2915'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=0nI_3cs9LKHlz0_cVifl9lVXZWfNQrzhLRZzoaDCVJs-1739358791-1.0.1.1-GJZzVGs1fHQe9gucVHUCoDlI3mwg3JyXCBIIChx_OsB0jgqbzt1s2et96vUgpdjONt9C2tB8OQ6fk70k3vhh0w;
+        _cfuvid=TvEPcNq35qaIgBFFzOP7g7NQf632eeMrvRDJyr7UTro-1739358791985-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.61.0
+      x-stainless-arch:
+      - x64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - Linux
+      x-stainless-package-version:
+      - 1.61.0
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n    \"error\": {\n        \"message\": \"Incorrect API key provided:
+      sk-fake-**********2345. You can find your API key at https://platform.openai.com/account/api-keys.\",\n
+      \       \"type\": \"invalid_request_error\",\n        \"param\": null,\n        \"code\":
+      \"invalid_api_key\"\n    }\n}\n"
+    headers:
+      CF-RAY:
+      - 910c25f1be28a373-SEA
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '272'
+      Content-Type:
+      - application/json; charset=utf-8
+      Date:
+      - Wed, 12 Feb 2025 11:13:14 GMT
+      Server:
+      - cloudflare
+      X-Content-Type-Options:
+      - nosniff
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      vary:
+      - Origin
+      x-request-id:
+      - req_573ccd417b499cf38012dec20261964d
+    http_version: HTTP/1.1
+    status_code: 401
+version: 1

tests/cassettes/test_hierarchical_tool_output_formatting[test result`-test result].yaml

@@ -0,0 +1,111 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Crew Manager. You
+      are a seasoned manager with a knack for getting the best out of your team.\nYou
+      are also known for your ability to delegate work to the right people, and to
+      ask the right questions to get the best out of your team.\nEven though you don''t
+      perform tasks by yourself, you have a lot of experience in the field, which
+      allows you to properly evaluate the work of your team members.\nYour personal
+      goal is: Manage the team to complete the task in the best way possible.\nYou
+      ONLY have access to the following tools, and should NEVER make up tools that
+      are not listed here:\n\nTool Name: Delegate work to coworker\nTool Arguments:
+      {''task'': {''description'': ''The task to delegate'', ''type'': ''str''}, ''context'':
+      {''description'': ''The context for the task'', ''type'': ''str''}, ''coworker'':
+      {''description'': ''The role/name of the coworker to delegate to'', ''type'':
+      ''str''}}\nTool Description: Delegate a specific task to one of the following
+      coworkers: Researcher\nThe input to this tool should be the coworker, the task
+      you want them to do, and ALL necessary context to execute the task, they know
+      nothing about the task, so share absolute everything you know, don''t reference
+      things but instead explain them.\nTool Name: Ask question to coworker\nTool
+      Arguments: {''question'': {''description'': ''The question to ask'', ''type'':
+      ''str''}, ''context'': {''description'': ''The context for the question'', ''type'':
+      ''str''}, ''coworker'': {''description'': ''The role/name of the coworker to
+      ask'', ''type'': ''str''}}\nTool Description: Ask a specific question to one
+      of the following coworkers: Researcher\nThe input to this tool should be the
+      coworker, the question you have for them, and ALL necessary context to ask the
+      question properly, they know nothing about the question, so share absolute everything
+      you know, don''t reference things but instead explain them.\n\nIMPORTANT: Use
+      the following format in your response:\n\n```\nThought: you should always think
+      about what to do\nAction: the action to take, only one name of [Delegate work
+      to coworker, Ask question to coworker], just the name, exactly as it''s written.\nAction
+      Input: the input to the action, just a simple JSON object, enclosed in curly
+      braces, using \" to wrap keys and values.\nObservation: the result of the action\n```\n\nOnce
+      all necessary information is gathered, return the following format:\n\n```\nThought:
+      I now know the final answer\nFinal Answer: the final answer to the original
+      input question\n```"}, {"role": "user", "content": "\nCurrent Task: Test task
+      using test_tool\n\nThis is the expected criteria for your final answer: Test
+      output\nyou MUST return the actual complete content as the final answer, not
+      a summary.\n\nBegin! This is VERY important to you, use the tools available
+      and give your best Final Answer, your job depends on it!\n\nThought:"}], "model":
+      "gpt-4o", "stop": ["\nObservation:"]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '2915'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=0nI_3cs9LKHlz0_cVifl9lVXZWfNQrzhLRZzoaDCVJs-1739358791-1.0.1.1-GJZzVGs1fHQe9gucVHUCoDlI3mwg3JyXCBIIChx_OsB0jgqbzt1s2et96vUgpdjONt9C2tB8OQ6fk70k3vhh0w;
+        _cfuvid=TvEPcNq35qaIgBFFzOP7g7NQf632eeMrvRDJyr7UTro-1739358791985-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.61.0
+      x-stainless-arch:
+      - x64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - Linux
+      x-stainless-package-version:
+      - 1.61.0
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n    \"error\": {\n        \"message\": \"Incorrect API key provided:
+      sk-fake-**********2345. You can find your API key at https://platform.openai.com/account/api-keys.\",\n
+      \       \"type\": \"invalid_request_error\",\n        \"param\": null,\n        \"code\":
+      \"invalid_api_key\"\n    }\n}\n"
+    headers:
+      CF-RAY:
+      - 910c25e84886a373-SEA
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '272'
+      Content-Type:
+      - application/json; charset=utf-8
+      Date:
+      - Wed, 12 Feb 2025 11:13:13 GMT
+      Server:
+      - cloudflare
+      X-Content-Type-Options:
+      - nosniff
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      vary:
+      - Origin
+      x-request-id:
+      - req_e48016407be31edd1f9ee2e1bb4d1b30
+    http_version: HTTP/1.1
+    status_code: 401
+version: 1

tests/cassettes/test_hierarchical_tool_output_formatting[test result```-test result].yaml

@@ -0,0 +1,114 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Crew Manager. You
+      are a seasoned manager with a knack for getting the best out of your team.\nYou
+      are also known for your ability to delegate work to the right people, and to
+      ask the right questions to get the best out of your team.\nEven though you don''t
+      perform tasks by yourself, you have a lot of experience in the field, which
+      allows you to properly evaluate the work of your team members.\nYour personal
+      goal is: Manage the team to complete the task in the best way possible.\nYou
+      ONLY have access to the following tools, and should NEVER make up tools that
+      are not listed here:\n\nTool Name: Delegate work to coworker\nTool Arguments:
+      {''task'': {''description'': ''The task to delegate'', ''type'': ''str''}, ''context'':
+      {''description'': ''The context for the task'', ''type'': ''str''}, ''coworker'':
+      {''description'': ''The role/name of the coworker to delegate to'', ''type'':
+      ''str''}}\nTool Description: Delegate a specific task to one of the following
+      coworkers: Researcher\nThe input to this tool should be the coworker, the task
+      you want them to do, and ALL necessary context to execute the task, they know
+      nothing about the task, so share absolute everything you know, don''t reference
+      things but instead explain them.\nTool Name: Ask question to coworker\nTool
+      Arguments: {''question'': {''description'': ''The question to ask'', ''type'':
+      ''str''}, ''context'': {''description'': ''The context for the question'', ''type'':
+      ''str''}, ''coworker'': {''description'': ''The role/name of the coworker to
+      ask'', ''type'': ''str''}}\nTool Description: Ask a specific question to one
+      of the following coworkers: Researcher\nThe input to this tool should be the
+      coworker, the question you have for them, and ALL necessary context to ask the
+      question properly, they know nothing about the question, so share absolute everything
+      you know, don''t reference things but instead explain them.\n\nIMPORTANT: Use
+      the following format in your response:\n\n```\nThought: you should always think
+      about what to do\nAction: the action to take, only one name of [Delegate work
+      to coworker, Ask question to coworker], just the name, exactly as it''s written.\nAction
+      Input: the input to the action, just a simple JSON object, enclosed in curly
+      braces, using \" to wrap keys and values.\nObservation: the result of the action\n```\n\nOnce
+      all necessary information is gathered, return the following format:\n\n```\nThought:
+      I now know the final answer\nFinal Answer: the final answer to the original
+      input question\n```"}, {"role": "user", "content": "\nCurrent Task: Test task
+      using test_tool\n\nThis is the expected criteria for your final answer: Test
+      output\nyou MUST return the actual complete content as the final answer, not
+      a summary.\n\nBegin! This is VERY important to you, use the tools available
+      and give your best Final Answer, your job depends on it!\n\nThought:"}], "model":
+      "gpt-4o", "stop": ["\nObservation:"]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '2915'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.61.0
+      x-stainless-arch:
+      - x64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - Linux
+      x-stainless-package-version:
+      - 1.61.0
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n    \"error\": {\n        \"message\": \"Incorrect API key provided:
+      sk-fake-**********2345. You can find your API key at https://platform.openai.com/account/api-keys.\",\n
+      \       \"type\": \"invalid_request_error\",\n        \"param\": null,\n        \"code\":
+      \"invalid_api_key\"\n    }\n}\n"
+    headers:
+      CF-RAY:
+      - 910c25e11d1da373-SEA
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '272'
+      Content-Type:
+      - application/json; charset=utf-8
+      Date:
+      - Wed, 12 Feb 2025 11:13:11 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=0nI_3cs9LKHlz0_cVifl9lVXZWfNQrzhLRZzoaDCVJs-1739358791-1.0.1.1-GJZzVGs1fHQe9gucVHUCoDlI3mwg3JyXCBIIChx_OsB0jgqbzt1s2et96vUgpdjONt9C2tB8OQ6fk70k3vhh0w;
+        path=/; expires=Wed, 12-Feb-25 11:43:11 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=TvEPcNq35qaIgBFFzOP7g7NQf632eeMrvRDJyr7UTro-1739358791985-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      X-Content-Type-Options:
+      - nosniff
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      vary:
+      - Origin
+      x-request-id:
+      - req_e07e0bddd718b7d5978b6bd9f138fa40
+    http_version: HTTP/1.1
+    status_code: 401
+version: 1

tests/cassettes/test_hierarchical_tool_output_formatting[test result``````-test result].yaml

@@ -0,0 +1,111 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Crew Manager. You
+      are a seasoned manager with a knack for getting the best out of your team.\nYou
+      are also known for your ability to delegate work to the right people, and to
+      ask the right questions to get the best out of your team.\nEven though you don''t
+      perform tasks by yourself, you have a lot of experience in the field, which
+      allows you to properly evaluate the work of your team members.\nYour personal
+      goal is: Manage the team to complete the task in the best way possible.\nYou
+      ONLY have access to the following tools, and should NEVER make up tools that
+      are not listed here:\n\nTool Name: Delegate work to coworker\nTool Arguments:
+      {''task'': {''description'': ''The task to delegate'', ''type'': ''str''}, ''context'':
+      {''description'': ''The context for the task'', ''type'': ''str''}, ''coworker'':
+      {''description'': ''The role/name of the coworker to delegate to'', ''type'':
+      ''str''}}\nTool Description: Delegate a specific task to one of the following
+      coworkers: Researcher\nThe input to this tool should be the coworker, the task
+      you want them to do, and ALL necessary context to execute the task, they know
+      nothing about the task, so share absolute everything you know, don''t reference
+      things but instead explain them.\nTool Name: Ask question to coworker\nTool
+      Arguments: {''question'': {''description'': ''The question to ask'', ''type'':
+      ''str''}, ''context'': {''description'': ''The context for the question'', ''type'':
+      ''str''}, ''coworker'': {''description'': ''The role/name of the coworker to
+      ask'', ''type'': ''str''}}\nTool Description: Ask a specific question to one
+      of the following coworkers: Researcher\nThe input to this tool should be the
+      coworker, the question you have for them, and ALL necessary context to ask the
+      question properly, they know nothing about the question, so share absolute everything
+      you know, don''t reference things but instead explain them.\n\nIMPORTANT: Use
+      the following format in your response:\n\n```\nThought: you should always think
+      about what to do\nAction: the action to take, only one name of [Delegate work
+      to coworker, Ask question to coworker], just the name, exactly as it''s written.\nAction
+      Input: the input to the action, just a simple JSON object, enclosed in curly
+      braces, using \" to wrap keys and values.\nObservation: the result of the action\n```\n\nOnce
+      all necessary information is gathered, return the following format:\n\n```\nThought:
+      I now know the final answer\nFinal Answer: the final answer to the original
+      input question\n```"}, {"role": "user", "content": "\nCurrent Task: Test task
+      using test_tool\n\nThis is the expected criteria for your final answer: Test
+      output\nyou MUST return the actual complete content as the final answer, not
+      a summary.\n\nBegin! This is VERY important to you, use the tools available
+      and give your best Final Answer, your job depends on it!\n\nThought:"}], "model":
+      "gpt-4o", "stop": ["\nObservation:"]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '2915'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=0nI_3cs9LKHlz0_cVifl9lVXZWfNQrzhLRZzoaDCVJs-1739358791-1.0.1.1-GJZzVGs1fHQe9gucVHUCoDlI3mwg3JyXCBIIChx_OsB0jgqbzt1s2et96vUgpdjONt9C2tB8OQ6fk70k3vhh0w;
+        _cfuvid=TvEPcNq35qaIgBFFzOP7g7NQf632eeMrvRDJyr7UTro-1739358791985-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.61.0
+      x-stainless-arch:
+      - x64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - Linux
+      x-stainless-package-version:
+      - 1.61.0
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n    \"error\": {\n        \"message\": \"Incorrect API key provided:
+      sk-fake-**********2345. You can find your API key at https://platform.openai.com/account/api-keys.\",\n
+      \       \"type\": \"invalid_request_error\",\n        \"param\": null,\n        \"code\":
+      \"invalid_api_key\"\n    }\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 910c25ec6a9fa373-SEA
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '272'
+      Content-Type:
+      - application/json; charset=utf-8
+      Date:
+      - Wed, 12 Feb 2025 11:13:13 GMT
+      Server:
+      - cloudflare
+      X-Content-Type-Options:
+      - nosniff
+      alt-svc:
+      - h3=":443"; ma=86400
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      vary:
+      - Origin
+      x-request-id:
+      - req_f9215c0efc514e3dfea73d6c5f49eb4e
+    http_version: HTTP/1.1
+    status_code: 401
+version: 1

tests/conftest.py

@@ -8,6 +8,11 @@ from dotenv import load_dotenv
 
 load_result = load_dotenv(override=True)
 
+@pytest.fixture(autouse=True)
+def mock_openai_key(monkeypatch):
+    """Mock OpenAI API key for VCR cassettes."""
+    monkeypatch.setenv("OPENAI_API_KEY", "sk-fake-test-key-12345")
+
 @pytest.fixture(autouse=True)
 def setup_test_environment():
     """Set up test environment with a temporary directory for SQLite storage."""

tests/crew_test.py

@@ -3,6 +3,7 @@
 import hashlib
 import json
 from concurrent.futures import Future
+from typing import Any
 from unittest import mock
 from unittest.mock import MagicMock, patch
 
@@ -14,7 +15,9 @@ from crewai.agent import Agent
 from crewai.agents.cache import CacheHandler
 from crewai.crew import Crew
 from crewai.crews.crew_output import CrewOutput
-from crewai.knowledge.source.string_knowledge_source import StringKnowledgeSource
+from crewai.knowledge.source.string_knowledge_source import (
+    StringKnowledgeSource,
+)
 from crewai.memory.contextual.contextual_memory import ContextualMemory
 from crewai.process import Process
 from crewai.project import crew
@@ -22,10 +25,13 @@ from crewai.task import Task
 from crewai.tasks.conditional_task import ConditionalTask
 from crewai.tasks.output_format import OutputFormat
 from crewai.tasks.task_output import TaskOutput
+from crewai.tools.base_tool import BaseTool
 from crewai.types.usage_metrics import UsageMetrics
 from crewai.utilities import Logger
 from crewai.utilities.rpm_controller import RPMController
-from crewai.utilities.task_output_storage_handler import TaskOutputStorageHandler
+from crewai.utilities.task_output_storage_handler import (
+    TaskOutputStorageHandler,
+)
 
 ceo = Agent(
     role="CEO",
@@ -315,6 +321,69 @@ def test_sync_task_execution():
         assert mock_execute_sync.call_count == len(tasks)
 
 
+@pytest.mark.vcr(
+    filter_headers=["authorization"],
+    record_mode="once",
+    decode_compressed_response=True,
+    ignore_localhost=True,
+    match_on=["method", "scheme", "host", "port", "path"]
+)
+@pytest.mark.parametrize(
+    "tool_output,expected",
+    [
+        ("test result```", "test result"),
+        ("test result`", "test result"),
+        ("test result``````", "test result"),
+        ("test result", "test result"),
+        ("test ```result```", "test ```result"),  # Only strip trailing backticks
+        (None, "None"),  # Test non-string input gets converted to string
+        (" ", " "),  # Test whitespace string
+        (
+            "malformed`result```test",
+            "malformed`result```test",
+        ),  # Test non-trailing backticks
+    ],
+)
+def test_hierarchical_tool_output_formatting(tool_output, expected):
+    """Test that tool outputs in hierarchical mode don't have extra backticks.
+
+    This test verifies that the tool output cleaning functionality correctly handles
+    various scenarios of backtick formatting, ensuring only trailing backticks are
+    removed while preserving any inline markdown formatting.
+    """
+
+    class TestTool(BaseTool):
+        name: str = "test_tool"
+        description: str = "A test tool"
+
+        def _run(self, *args: Any, **kwargs: Any) -> str:
+            return tool_output
+
+    task = Task(
+        description="Test task using test_tool",
+        expected_output="Test output",
+    )
+
+    crew = Crew(
+        agents=[researcher],
+        process=Process.hierarchical,
+        manager_llm="gpt-4o",
+        tasks=[task],
+        tools=[TestTool()],
+    )
+
+    with patch.object(
+        Task,
+        "execute_sync",
+        return_value=TaskOutput(
+            description="Test task", raw=expected, agent="researcher"
+        ),
+    ) as mock_execute_sync:
+        result = crew.kickoff()
+        assert mock_execute_sync.called
+        assert result.raw == expected
+
+
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_hierarchical_process():
     task = Task(
@@ -591,12 +660,12 @@ def test_crew_with_delegating_agents_should_not_override_task_tools():
         _, kwargs = mock_execute_sync.call_args
         tools = kwargs["tools"]
 
-        assert any(
-            isinstance(tool, TestTool) for tool in tools
-        ), "TestTool should be present"
-        assert any(
-            "delegate" in tool.name.lower() for tool in tools
-        ), "Delegation tool should be present"
+        assert any(isinstance(tool, TestTool) for tool in tools), (
+            "TestTool should be present"
+        )
+        assert any("delegate" in tool.name.lower() for tool in tools), (
+            "Delegation tool should be present"
+        )
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
@@ -655,12 +724,12 @@ def test_crew_with_delegating_agents_should_not_override_agent_tools():
         _, kwargs = mock_execute_sync.call_args
         tools = kwargs["tools"]
 
-        assert any(
-            isinstance(tool, TestTool) for tool in new_ceo.tools
-        ), "TestTool should be present"
-        assert any(
-            "delegate" in tool.name.lower() for tool in tools
-        ), "Delegation tool should be present"
+        assert any(isinstance(tool, TestTool) for tool in new_ceo.tools), (
+            "TestTool should be present"
+        )
+        assert any("delegate" in tool.name.lower() for tool in tools), (
+            "Delegation tool should be present"
+        )
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
@@ -784,17 +853,17 @@ def test_task_tools_override_agent_tools_with_allow_delegation():
         used_tools = kwargs["tools"]
 
         # Confirm AnotherTestTool is present but TestTool is not
-        assert any(
-            isinstance(tool, AnotherTestTool) for tool in used_tools
-        ), "AnotherTestTool should be present"
-        assert not any(
-            isinstance(tool, TestTool) for tool in used_tools
-        ), "TestTool should not be present among used tools"
+        assert any(isinstance(tool, AnotherTestTool) for tool in used_tools), (
+            "AnotherTestTool should be present"
+        )
+        assert not any(isinstance(tool, TestTool) for tool in used_tools), (
+            "TestTool should not be present among used tools"
+        )
 
         # Confirm delegation tool(s) are present
-        assert any(
-            "delegate" in tool.name.lower() for tool in used_tools
-        ), "Delegation tool should be present"
+        assert any("delegate" in tool.name.lower() for tool in used_tools), (
+            "Delegation tool should be present"
+        )
 
     # Finally, make sure the agent's original tools remain unchanged
     assert len(researcher_with_delegation.tools) == 1
@@ -1595,9 +1664,9 @@ def test_code_execution_flag_adds_code_tool_upon_kickoff():
 
         # Verify that exactly one tool was used and it was a CodeInterpreterTool
         assert len(used_tools) == 1, "Should have exactly one tool"
-        assert isinstance(
-            used_tools[0], CodeInterpreterTool
-        ), "Tool should be CodeInterpreterTool"
+        assert isinstance(used_tools[0], CodeInterpreterTool), (
+            "Tool should be CodeInterpreterTool"
+        )
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
@@ -3418,9 +3487,9 @@ def test_fetch_inputs():
     expected_placeholders = {"role_detail", "topic", "field"}
     actual_placeholders = crew.fetch_inputs()
 
-    assert (
-        actual_placeholders == expected_placeholders
-    ), f"Expected {expected_placeholders}, but got {actual_placeholders}"
+    assert actual_placeholders == expected_placeholders, (
+        f"Expected {expected_placeholders}, but got {actual_placeholders}"
+    )
 
 
 def test_task_tools_preserve_code_execution_tools():
@@ -3493,20 +3562,20 @@ def test_task_tools_preserve_code_execution_tools():
         used_tools = kwargs["tools"]
 
         # Verify all expected tools are present
-        assert any(
-            isinstance(tool, TestTool) for tool in used_tools
-        ), "Task's TestTool should be present"
-        assert any(
-            isinstance(tool, CodeInterpreterTool) for tool in used_tools
-        ), "CodeInterpreterTool should be present"
-        assert any(
-            "delegate" in tool.name.lower() for tool in used_tools
-        ), "Delegation tool should be present"
+        assert any(isinstance(tool, TestTool) for tool in used_tools), (
+            "Task's TestTool should be present"
+        )
+        assert any(isinstance(tool, CodeInterpreterTool) for tool in used_tools), (
+            "CodeInterpreterTool should be present"
+        )
+        assert any("delegate" in tool.name.lower() for tool in used_tools), (
+            "Delegation tool should be present"
+        )
 
         # Verify the total number of tools (TestTool + CodeInterpreter + 2 delegation tools)
-        assert (
-            len(used_tools) == 4
-        ), "Should have TestTool, CodeInterpreter, and 2 delegation tools"
+        assert len(used_tools) == 4, (
+            "Should have TestTool, CodeInterpreter, and 2 delegation tools"
+        )
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
@@ -3550,9 +3619,9 @@ def test_multimodal_flag_adds_multimodal_tools():
         used_tools = kwargs["tools"]
 
         # Check that the multimodal tool was added
-        assert any(
-            isinstance(tool, AddImageTool) for tool in used_tools
-        ), "AddImageTool should be present when agent is multimodal"
+        assert any(isinstance(tool, AddImageTool) for tool in used_tools), (
+            "AddImageTool should be present when agent is multimodal"
+        )
 
         # Verify we have exactly one tool (just the AddImageTool)
         assert len(used_tools) == 1, "Should only have the AddImageTool"
@@ -3778,9 +3847,9 @@ def test_crew_guardrail_feedback_in_context():
     assert len(execution_contexts) > 1, "Task should have been executed multiple times"
 
     # Verify that the second execution included the guardrail feedback
-    assert (
-        "Output must contain the keyword 'IMPORTANT'" in execution_contexts[1]
-    ), "Guardrail feedback should be included in retry context"
+    assert "Output must contain the keyword 'IMPORTANT'" in execution_contexts[1], (
+        "Guardrail feedback should be included in retry context"
+    )
 
     # Verify final output meets guardrail requirements
     assert "IMPORTANT" in result.raw, "Final output should contain required keyword"

tests/flow_test.py

@@ -1,18 +1,11 @@
 """Test Flow creation and execution basic functionality."""
 
 import asyncio
-from datetime import datetime
 
 import pytest
 from pydantic import BaseModel
 
 from crewai.flow.flow import Flow, and_, listen, or_, router, start
-from crewai.flow.flow_events import (
-    FlowFinishedEvent,
-    FlowStartedEvent,
-    MethodExecutionFinishedEvent,
-    MethodExecutionStartedEvent,
-)
 
 
 def test_simple_sequential_flow():
@@ -405,218 +398,3 @@ def test_router_with_multiple_conditions():
 
     # final_step should run after router_and
     assert execution_order.index("log_final_step") > execution_order.index("router_and")
-
-
-def test_unstructured_flow_event_emission():
-    """Test that the correct events are emitted during unstructured flow
-    execution with all fields validated."""
-
-    class PoemFlow(Flow):
-        @start()
-        def prepare_flower(self):
-            self.state["flower"] = "roses"
-            return "foo"
-
-        @start()
-        def prepare_color(self):
-            self.state["color"] = "red"
-            return "bar"
-
-        @listen(prepare_color)
-        def write_first_sentence(self):
-            return f"{self.state['flower']} are {self.state['color']}"
-
-        @listen(write_first_sentence)
-        def finish_poem(self, first_sentence):
-            separator = self.state.get("separator", "\n")
-            return separator.join([first_sentence, "violets are blue"])
-
-        @listen(finish_poem)
-        def save_poem_to_database(self):
-            # A method without args/kwargs to ensure events are sent correctly
-            pass
-
-    event_log = []
-
-    def handle_event(_, event):
-        event_log.append(event)
-
-    flow = PoemFlow()
-    flow.event_emitter.connect(handle_event)
-    flow.kickoff(inputs={"separator": ", "})
-
-    assert isinstance(event_log[0], FlowStartedEvent)
-    assert event_log[0].flow_name == "PoemFlow"
-    assert event_log[0].inputs == {"separator": ", "}
-    assert isinstance(event_log[0].timestamp, datetime)
-
-    # Asserting for concurrent start method executions in a for loop as you
-    # can't guarantee ordering in asynchronous executions
-    for i in range(1, 5):
-        event = event_log[i]
-        assert isinstance(event.state, dict)
-        assert isinstance(event.state["id"], str)
-
-        if event.method_name == "prepare_flower":
-            if isinstance(event, MethodExecutionStartedEvent):
-                assert event.params == {}
-                assert event.state["separator"] == ", "
-            elif isinstance(event, MethodExecutionFinishedEvent):
-                assert event.result == "foo"
-                assert event.state["flower"] == "roses"
-                assert event.state["separator"] == ", "
-            else:
-                assert False, "Unexpected event type for prepare_flower"
-        elif event.method_name == "prepare_color":
-            if isinstance(event, MethodExecutionStartedEvent):
-                assert event.params == {}
-                assert event.state["separator"] == ", "
-            elif isinstance(event, MethodExecutionFinishedEvent):
-                assert event.result == "bar"
-                assert event.state["color"] == "red"
-                assert event.state["separator"] == ", "
-            else:
-                assert False, "Unexpected event type for prepare_color"
-        else:
-            assert False, f"Unexpected method {event.method_name} in prepare events"
-
-    assert isinstance(event_log[5], MethodExecutionStartedEvent)
-    assert event_log[5].method_name == "write_first_sentence"
-    assert event_log[5].params == {}
-    assert isinstance(event_log[5].state, dict)
-    assert event_log[5].state["flower"] == "roses"
-    assert event_log[5].state["color"] == "red"
-    assert event_log[5].state["separator"] == ", "
-
-    assert isinstance(event_log[6], MethodExecutionFinishedEvent)
-    assert event_log[6].method_name == "write_first_sentence"
-    assert event_log[6].result == "roses are red"
-
-    assert isinstance(event_log[7], MethodExecutionStartedEvent)
-    assert event_log[7].method_name == "finish_poem"
-    assert event_log[7].params == {"_0": "roses are red"}
-    assert isinstance(event_log[7].state, dict)
-    assert event_log[7].state["flower"] == "roses"
-    assert event_log[7].state["color"] == "red"
-
-    assert isinstance(event_log[8], MethodExecutionFinishedEvent)
-    assert event_log[8].method_name == "finish_poem"
-    assert event_log[8].result == "roses are red, violets are blue"
-
-    assert isinstance(event_log[9], MethodExecutionStartedEvent)
-    assert event_log[9].method_name == "save_poem_to_database"
-    assert event_log[9].params == {}
-    assert isinstance(event_log[9].state, dict)
-    assert event_log[9].state["flower"] == "roses"
-    assert event_log[9].state["color"] == "red"
-
-    assert isinstance(event_log[10], MethodExecutionFinishedEvent)
-    assert event_log[10].method_name == "save_poem_to_database"
-    assert event_log[10].result is None
-
-    assert isinstance(event_log[11], FlowFinishedEvent)
-    assert event_log[11].flow_name == "PoemFlow"
-    assert event_log[11].result is None
-    assert isinstance(event_log[11].timestamp, datetime)
-
-
-def test_structured_flow_event_emission():
-    """Test that the correct events are emitted during structured flow
-    execution with all fields validated."""
-
-    class OnboardingState(BaseModel):
-        name: str = ""
-        sent: bool = False
-
-    class OnboardingFlow(Flow[OnboardingState]):
-        @start()
-        def user_signs_up(self):
-            self.state.sent = False
-
-        @listen(user_signs_up)
-        def send_welcome_message(self):
-            self.state.sent = True
-            return f"Welcome, {self.state.name}!"
-
-    event_log = []
-
-    def handle_event(_, event):
-        event_log.append(event)
-
-    flow = OnboardingFlow()
-    flow.event_emitter.connect(handle_event)
-    flow.kickoff(inputs={"name": "Anakin"})
-
-    assert isinstance(event_log[0], FlowStartedEvent)
-    assert event_log[0].flow_name == "OnboardingFlow"
-    assert event_log[0].inputs == {"name": "Anakin"}
-    assert isinstance(event_log[0].timestamp, datetime)
-
-    assert isinstance(event_log[1], MethodExecutionStartedEvent)
-    assert event_log[1].method_name == "user_signs_up"
-
-    assert isinstance(event_log[2], MethodExecutionFinishedEvent)
-    assert event_log[2].method_name == "user_signs_up"
-
-    assert isinstance(event_log[3], MethodExecutionStartedEvent)
-    assert event_log[3].method_name == "send_welcome_message"
-    assert event_log[3].params == {}
-    assert getattr(event_log[3].state, "sent") is False
-
-    assert isinstance(event_log[4], MethodExecutionFinishedEvent)
-    assert event_log[4].method_name == "send_welcome_message"
-    assert getattr(event_log[4].state, "sent") is True
-    assert event_log[4].result == "Welcome, Anakin!"
-
-    assert isinstance(event_log[5], FlowFinishedEvent)
-    assert event_log[5].flow_name == "OnboardingFlow"
-    assert event_log[5].result == "Welcome, Anakin!"
-    assert isinstance(event_log[5].timestamp, datetime)
-
-
-def test_stateless_flow_event_emission():
-    """Test that the correct events are emitted stateless during flow execution
-    with all fields validated."""
-
-    class StatelessFlow(Flow):
-        @start()
-        def init(self):
-            pass
-
-        @listen(init)
-        def process(self):
-            return "Deeds will not be less valiant because they are unpraised."
-
-    event_log = []
-
-    def handle_event(_, event):
-        event_log.append(event)
-
-    flow = StatelessFlow()
-    flow.event_emitter.connect(handle_event)
-    flow.kickoff()
-
-    assert isinstance(event_log[0], FlowStartedEvent)
-    assert event_log[0].flow_name == "StatelessFlow"
-    assert event_log[0].inputs is None
-    assert isinstance(event_log[0].timestamp, datetime)
-
-    assert isinstance(event_log[1], MethodExecutionStartedEvent)
-    assert event_log[1].method_name == "init"
-
-    assert isinstance(event_log[2], MethodExecutionFinishedEvent)
-    assert event_log[2].method_name == "init"
-
-    assert isinstance(event_log[3], MethodExecutionStartedEvent)
-    assert event_log[3].method_name == "process"
-
-    assert isinstance(event_log[4], MethodExecutionFinishedEvent)
-    assert event_log[4].method_name == "process"
-
-    assert isinstance(event_log[5], FlowFinishedEvent)
-    assert event_log[5].flow_name == "StatelessFlow"
-    assert (
-        event_log[5].result
-        == "Deeds will not be less valiant because they are unpraised."
-    )
-    assert isinstance(event_log[5].timestamp, datetime)

tests/test_flow_thread_locks.py

@@ -1,182 +0,0 @@
-"""Tests for Flow with thread locks."""
-import asyncio
-import threading
-from typing import Optional
-from uuid import uuid4
-
-import pytest
-from pydantic import BaseModel, Field, field_validator
-
-from crewai.flow.flow import Flow, listen, start
-
-
-class ThreadSafeState(BaseModel):
-    """Test state model with thread locks."""
-    model_config = {
-        "arbitrary_types_allowed": True,
-        "exclude": {"lock"}
-    }
-    
-    id: str = Field(default_factory=lambda: str(uuid4()))
-    lock: Optional[threading.RLock] = Field(default=None, exclude=True)
-    value: str = ""
-    
-    def __init__(self, **data):
-        super().__init__(**data)
-        if self.lock is None:
-            self.lock = threading.RLock()
-
-
-class LockFlow(Flow[ThreadSafeState]):
-    """Test flow with thread locks."""
-    initial_state = ThreadSafeState
-
-    @start()
-    async def step_1(self):
-        with self.state.lock:
-            self.state.value = "step 1"
-            return "step 1"
-
-    @listen(step_1)
-    async def step_2(self, result):
-        with self.state.lock:
-            self.state.value += " -> step 2"
-            return result + " -> step 2"
-
-
-def test_flow_with_thread_locks():
-    """Test Flow with thread locks in state."""
-    flow = LockFlow()
-    result = asyncio.run(flow.kickoff_async())
-    assert result == "step 1 -> step 2"
-    assert flow.state.value == "step 1 -> step 2"
-
-
-def test_kickoff_async_with_lock_inputs():
-    """Test kickoff_async with thread lock inputs."""
-    flow = LockFlow()
-    inputs = {
-        "lock": threading.RLock(),
-        "value": "test"
-    }
-    result = asyncio.run(flow.kickoff_async(inputs=inputs))
-    assert result == "step 1 -> step 2"
-    assert flow.state.value == "step 1 -> step 2"
-
-
-class ComplexState(BaseModel):
-    """Test state model with nested thread locks."""
-    model_config = {
-        "arbitrary_types_allowed": True,
-        "exclude": {"outer_lock"}
-    }
-    
-    id: str = Field(default_factory=lambda: str(uuid4()))
-    outer_lock: Optional[threading.RLock] = Field(default=None, exclude=True)
-    inner: Optional[ThreadSafeState] = Field(default_factory=ThreadSafeState)
-    value: str = ""
-    
-    def __init__(self, **data):
-        super().__init__(**data)
-        if self.outer_lock is None:
-            self.outer_lock = threading.RLock()
-
-
-class NestedLockFlow(Flow[ComplexState]):
-    """Test flow with nested thread locks."""
-    initial_state = ComplexState
-
-    @start()
-    async def step_1(self):
-        with self.state.outer_lock:
-            with self.state.inner.lock:
-                self.state.value = "outer"
-                self.state.inner.value = "inner"
-                return "step 1"
-
-    @listen(step_1)
-    async def step_2(self, result):
-        with self.state.outer_lock:
-            with self.state.inner.lock:
-                self.state.value += " -> outer 2"
-                self.state.inner.value += " -> inner 2"
-                return result + " -> step 2"
-
-
-def test_flow_with_nested_locks():
-    """Test Flow with nested thread locks in state."""
-    flow = NestedLockFlow()
-    result = asyncio.run(flow.kickoff_async())
-    assert result == "step 1 -> step 2"
-    assert flow.state.value == "outer -> outer 2"
-    assert flow.state.inner.value == "inner -> inner 2"
-
-
-class AsyncLockState(BaseModel):
-    """Test state model with async locks."""
-    model_config = {
-        "arbitrary_types_allowed": True,
-        "exclude": {"lock", "event"}
-    }
-    
-    id: str = Field(default_factory=lambda: str(uuid4()))
-    lock: Optional[asyncio.Lock] = Field(default=None, exclude=True)
-    event: Optional[asyncio.Event] = Field(default=None, exclude=True)
-    value: str = ""
-    
-    def __init__(self, **data):
-        super().__init__(**data)
-        if self.lock is None:
-            self.lock = asyncio.Lock()
-        if self.event is None:
-            self.event = asyncio.Event()
-
-
-class AsyncLockFlow(Flow[AsyncLockState]):
-    """Test flow with async locks."""
-    initial_state = AsyncLockState
-
-    @start()
-    async def step_1(self):
-        async with self.state.lock:
-            self.state.value = "step 1"
-            self.state.event.set()
-            return "step 1"
-
-    @listen(step_1)
-    async def step_2(self, result):
-        async with self.state.lock:
-            await self.state.event.wait()
-            self.state.value += " -> step 2"
-            return result + " -> step 2"
-
-
-def test_flow_with_async_locks():
-    """Test Flow with async locks in state."""
-    flow = AsyncLockFlow()
-    result = asyncio.run(flow.kickoff_async())
-    assert result == "step 1 -> step 2"
-    assert flow.state.value == "step 1 -> step 2"
-
-
-def test_flow_concurrent_access():
-    """Test Flow with concurrent access."""
-    flow = LockFlow()
-    results = []
-    errors = []
-    
-    async def run_flow():
-        try:
-            result = await flow.kickoff_async()
-            results.append(result)
-        except Exception as e:
-            errors.append(e)
-    
-    async def test():
-        tasks = [run_flow() for _ in range(10)]
-        await asyncio.gather(*tasks)
-    
-    asyncio.run(test())
-    assert len(results) == 10
-    assert not errors
-    assert all(result == "step 1 -> step 2" for result in results)

uv.lock

@@ -198,6 +198,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/39/e3/893e8757be2612e6c266d9bb58ad2e3651524b5b40cf56761e985a28b13e/asgiref-3.8.1-py3-none-any.whl", hash = "sha256:3e1e3ecc849832fe52ccf2cb6686b7a55f82bb1d6aee72a58826471390335e47", size = 23828 },
 ]
 
+[[package]]
+name = "asn1crypto"
+version = "1.5.1"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/de/cf/d547feed25b5244fcb9392e288ff9fdc3280b10260362fc45d37a798a6ee/asn1crypto-1.5.1.tar.gz", hash = "sha256:13ae38502be632115abf8a24cbe5f4da52e3b5231990aff31123c805306ccb9c", size = 121080 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/c9/7f/09065fd9e27da0eda08b4d6897f1c13535066174cc023af248fc2a8d5e5a/asn1crypto-1.5.1-py2.py3-none-any.whl", hash = "sha256:db4e40728b728508912cbb3d44f19ce188f218e9eba635821bb4b68564f8fd67", size = 105045 },
+]
+
 [[package]]
 name = "asttokens"
 version = "2.4.1"
@@ -219,6 +228,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/a7/fa/e01228c2938de91d47b307831c62ab9e4001e747789d0b05baf779a6488c/async_timeout-4.0.3-py3-none-any.whl", hash = "sha256:7405140ff1230c310e51dc27b3145b9092d659ce68ff733fb0cefe3ee42be028", size = 5721 },
 ]
 
+[[package]]
+name = "atpublic"
+version = "5.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/5d/18/b1d247792440378abeeb0853f9daa2a127284b68776af6815990be7fcdb0/atpublic-5.0.tar.gz", hash = "sha256:d5cb6cbabf00ec1d34e282e8ce7cbc9b74ba4cb732e766c24e2d78d1ad7f723f", size = 14646 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/6b/03/2cb0e5326e19b7d877bc9c3a7ef436a30a06835b638580d1f5e21a0409ed/atpublic-5.0-py3-none-any.whl", hash = "sha256:b651dcd886666b1042d1e38158a22a4f2c267748f4e97fde94bc492a4a28a3f3", size = 5207 },
+]
+
 [[package]]
 name = "attrs"
 version = "24.2.0"
@@ -244,6 +262,18 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/e4/0e/38cb7b781371e79e9c697fb78f3ccd18fda8bd547d0a2e76e616561a3792/auth0_python-4.7.2-py3-none-any.whl", hash = "sha256:df2224f9b1e170b3aa12d8bc7ff02eadb7cc229307a09ec6b8a55fd1e0e05dc8", size = 131834 },
 ]
 
+[[package]]
+name = "authlib"
+version = "1.3.1"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "cryptography" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/09/47/df70ecd34fbf86d69833fe4e25bb9ecbaab995c8e49df726dd416f6bb822/authlib-1.3.1.tar.gz", hash = "sha256:7ae843f03c06c5c0debd63c9db91f9fda64fa62a42a77419fa15fbb7e7a58917", size = 146074 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/87/1f/bc95e43ffb57c05b8efcc376dd55a0240bf58f47ddf5a0f92452b6457b75/Authlib-1.3.1-py2.py3-none-any.whl", hash = "sha256:d35800b973099bbadc49b42b256ecb80041ad56b7fe1216a362c7943c088f377", size = 223827 },
+]
+
 [[package]]
 name = "autoflake"
 version = "2.3.1"
@@ -565,14 +595,14 @@ wheels = [
 
 [[package]]
 name = "click"
-version = "8.1.8"
+version = "8.1.7"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "colorama", marker = "platform_system == 'Windows'" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/b9/2e/0090cbf739cee7d23781ad4b89a9894a41538e4fcf4c31dcdd705b78eb8b/click-8.1.8.tar.gz", hash = "sha256:ed53c9d8990d83c2a27deae68e4ee337473f6330c040a31d4225c9574d16096a", size = 226593 }
+sdist = { url = "https://files.pythonhosted.org/packages/96/d3/f04c7bfcf5c1862a2a5b845c6b2b360488cf47af55dfa79c98f6a6bf98b5/click-8.1.7.tar.gz", hash = "sha256:ca9853ad459e787e2192211578cc907e7594e294c7ccc834310722b41b9ca6de", size = 336121 }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/7e/d4/7ebdbd03970677812aac39c869717059dbb71a4cfc033ca6e5221787892c/click-8.1.8-py3-none-any.whl", hash = "sha256:63c132bbbed01578a06712a2d1f497bb62d9c1c0d329b7903a866228027263b2", size = 98188 },
+    { url = "https://files.pythonhosted.org/packages/00/2e/d53fa4befbf2cfa713304affc7ca780ce4fc1fd8710527771b58311a3229/click-8.1.7-py3-none-any.whl", hash = "sha256:ae74fb96c20a0277a1d615f1e4d73c8414f5a98db8b799a7931d1582f3390c28", size = 97941 },
 ]
 
 [[package]]
@@ -619,7 +649,7 @@ wheels = [
 
 [[package]]
 name = "crewai"
-version = "0.102.0"
+version = "0.100.1"
 source = { editable = "." }
 dependencies = [
     { name = "appdirs" },
@@ -703,7 +733,7 @@ requires-dist = [
     { name = "blinker", specifier = ">=1.9.0" },
     { name = "chromadb", specifier = ">=0.5.23" },
     { name = "click", specifier = ">=8.1.7" },
-    { name = "crewai-tools", marker = "extra == 'tools'", specifier = ">=0.36.0" },
+    { name = "crewai-tools", marker = "extra == 'tools'", specifier = ">=0.32.1" },
     { name = "docling", marker = "extra == 'docling'", specifier = ">=2.12.0" },
     { name = "fastembed", marker = "extra == 'fastembed'", specifier = ">=0.4.1" },
     { name = "instructor", specifier = ">=1.3.3" },
@@ -752,24 +782,33 @@ dev = [
 
 [[package]]
 name = "crewai-tools"
-version = "0.36.0"
+version = "0.32.1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
+    { name = "beautifulsoup4" },
     { name = "chromadb" },
-    { name = "click" },
     { name = "crewai" },
     { name = "docker" },
+    { name = "docx2txt" },
     { name = "embedchain" },
     { name = "lancedb" },
+    { name = "linkup-sdk" },
     { name = "openai" },
+    { name = "patronus" },
     { name = "pydantic" },
     { name = "pyright" },
     { name = "pytube" },
     { name = "requests" },
+    { name = "scrapegraph-py" },
+    { name = "selenium" },
+    { name = "serpapi" },
+    { name = "snowflake" },
+    { name = "spider-client" },
+    { name = "weaviate-client" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/4d/e1/d65778cf4aea106f3f60a4208521f04bc7f1d26be4e34eeb63cae6297d50/crewai_tools-0.36.0.tar.gz", hash = "sha256:761b396ee6a4019a988720dd6a14e1409f5de9d0cdc2a8662b487d87efb1a6bf", size = 900178 }
+sdist = { url = "https://files.pythonhosted.org/packages/e9/e7/fb07f0089028f7c9003770641d21f5844d4fa22bf5cc4c4b3676bfa0e1fe/crewai_tools-0.32.1.tar.gz", hash = "sha256:41acea9243b17a463f355d48dfe7d73bd59738c8862a8da780eae008e0136414", size = 887378 }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/bd/b6/533632a6c2a2e623fc4a1677458aff3539413a196fb220a7fece4ead3f71/crewai_tools-0.36.0-py3-none-any.whl", hash = "sha256:dbd0d95a080acfb281e105f4376e1e98576dae6d53d94f7b883c57af893668b3", size = 545937 },
+    { url = "https://files.pythonhosted.org/packages/36/f0/8f98f1a2b90b9b989bd01cf48b5e3bb2d842be2062bfd3177a77561e7b61/crewai_tools-0.32.1-py3-none-any.whl", hash = "sha256:6cb436dc66e19e35285a4fce501158a13bce99b244370574f568ec33c5513351", size = 537264 },
 ]
 
 [[package]]
@@ -1060,6 +1099,12 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/d5/7c/e9fcff7623954d86bdc17782036cbf715ecab1bec4847c008557affe1ca8/docstring_parser-0.16-py3-none-any.whl", hash = "sha256:bf0a1387354d3691d102edef7ec124f219ef639982d096e26e3b60aeffa90637", size = 36533 },
 ]
 
+[[package]]
+name = "docx2txt"
+version = "0.8"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/7d/7d/60ee3f2b16d9bfdfa72e8599470a2c1a5b759cb113c6fe1006be28359327/docx2txt-0.8.tar.gz", hash = "sha256:2c06d98d7cfe2d3947e5760a57d924e3ff07745b379c8737723922e7009236e5", size = 2814 }
+
 [[package]]
 name = "durationpy"
 version = "0.9"
@@ -1601,6 +1646,19 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/1d/1f/acf03ee901313446d52c3916d527d4981de9f6f3edc69267d05509dcfa7b/grpcio-1.67.0-cp312-cp312-win_amd64.whl", hash = "sha256:985b2686f786f3e20326c4367eebdaed3e7aa65848260ff0c6644f817042cb15", size = 4343545 },
 ]
 
+[[package]]
+name = "grpcio-health-checking"
+version = "1.62.3"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "grpcio" },
+    { name = "protobuf" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/eb/9f/09df9b02fc8eafa3031d878c8a4674a0311293c8c6f1c942cdaeec204126/grpcio-health-checking-1.62.3.tar.gz", hash = "sha256:5074ba0ce8f0dcfe328408ec5c7551b2a835720ffd9b69dade7fa3e0dc1c7a93", size = 15640 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/40/4c/ee3173906196b741ac6ba55a9788ba9ebf2cd05f91715a49b6c3bfbb9d73/grpcio_health_checking-1.62.3-py3-none-any.whl", hash = "sha256:f29da7dd144d73b4465fe48f011a91453e9ff6c8af0d449254cf80021cab3e0d", size = 18547 },
+]
+
 [[package]]
 name = "grpcio-status"
 version = "1.62.3"
@@ -1812,6 +1870,52 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/76/c6/c88e154df9c4e1a2a66ccf0005a88dfb2650c1dffb6f5ce603dfbd452ce3/idna-3.10-py3-none-any.whl", hash = "sha256:946d195a0d259cbba61165e88e65941f16e9b36ea6ddb97f00452bae8b1287d3", size = 70442 },
 ]
 
+[[package]]
+name = "ijson"
+version = "3.3.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/6c/83/28e9e93a3a61913e334e3a2e78ea9924bb9f9b1ac45898977f9d9dd6133f/ijson-3.3.0.tar.gz", hash = "sha256:7f172e6ba1bee0d4c8f8ebd639577bfe429dee0f3f96775a067b8bae4492d8a0", size = 60079 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/ad/89/96e3608499b4a500b9bc27aa8242704e675849dd65bdfa8682b00a92477e/ijson-3.3.0-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:7f7a5250599c366369fbf3bc4e176f5daa28eb6bc7d6130d02462ed335361675", size = 85009 },
+    { url = "https://files.pythonhosted.org/packages/e4/7e/1098503500f5316c5f7912a51c91aca5cbc609c09ce4ecd9c4809983c560/ijson-3.3.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:f87a7e52f79059f9c58f6886c262061065eb6f7554a587be7ed3aa63e6b71b34", size = 57796 },
+    { url = "https://files.pythonhosted.org/packages/78/f7/27b8c27a285628719ff55b68507581c86b551eb162ce810fe51e3e1a25f2/ijson-3.3.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:b73b493af9e947caed75d329676b1b801d673b17481962823a3e55fe529c8b8b", size = 57218 },
+    { url = "https://files.pythonhosted.org/packages/0c/c5/1698094cb6a336a223c30e1167cc1b15cdb4bfa75399c1a2eb82fa76cc3c/ijson-3.3.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d5576415f3d76290b160aa093ff968f8bf6de7d681e16e463a0134106b506f49", size = 117153 },
+    { url = "https://files.pythonhosted.org/packages/4b/21/c206dda0945bd832cc9b0894596b0efc2cb1819a0ac61d8be1429ac09494/ijson-3.3.0-cp310-cp310-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:4e9ffe358d5fdd6b878a8a364e96e15ca7ca57b92a48f588378cef315a8b019e", size = 110781 },
+    { url = "https://files.pythonhosted.org/packages/f4/f5/2d733e64577109a9b255d14d031e44a801fa20df9ccc58b54a31e8ecf9e6/ijson-3.3.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8643c255a25824ddd0895c59f2319c019e13e949dc37162f876c41a283361527", size = 114527 },
+    { url = "https://files.pythonhosted.org/packages/8d/a8/78bfee312aa23417b86189a65f30b0edbceaee96dc6a616cc15f611187d1/ijson-3.3.0-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:df3ab5e078cab19f7eaeef1d5f063103e1ebf8c26d059767b26a6a0ad8b250a3", size = 116824 },
+    { url = "https://files.pythonhosted.org/packages/5d/a4/aff410f7d6aa1a77ee2ab2d6a2d2758422726270cb149c908a9baf33cf58/ijson-3.3.0-cp310-cp310-musllinux_1_2_i686.whl", hash = "sha256:3dc1fb02c6ed0bae1b4bf96971258bf88aea72051b6e4cebae97cff7090c0607", size = 112647 },
+    { url = "https://files.pythonhosted.org/packages/77/ee/2b5122dc4713f5a954267147da36e7156240ca21b04ed5295bc0cabf0fbe/ijson-3.3.0-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:e9afd97339fc5a20f0542c971f90f3ca97e73d3050cdc488d540b63fae45329a", size = 114156 },
+    { url = "https://files.pythonhosted.org/packages/b3/d7/ad3b266490b60c6939e8a07fd8e4b7e2002aea08eaa9572a016c3e3a9129/ijson-3.3.0-cp310-cp310-win32.whl", hash = "sha256:844c0d1c04c40fd1b60f148dc829d3f69b2de789d0ba239c35136efe9a386529", size = 48931 },
+    { url = "https://files.pythonhosted.org/packages/0b/68/b9e1c743274c8a23dddb12d2ed13b5f021f6d21669d51ff7fa2e9e6c19df/ijson-3.3.0-cp310-cp310-win_amd64.whl", hash = "sha256:d654d045adafdcc6c100e8e911508a2eedbd2a1b5f93f930ba13ea67d7704ee9", size = 50965 },
+    { url = "https://files.pythonhosted.org/packages/fd/df/565ba72a6f4b2c833d051af8e2228cfa0b1fef17bb44995c00ad27470c52/ijson-3.3.0-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:501dce8eaa537e728aa35810656aa00460a2547dcb60937c8139f36ec344d7fc", size = 85041 },
+    { url = "https://files.pythonhosted.org/packages/f0/42/1361eaa57ece921d0239881bae6a5e102333be5b6e0102a05ec3caadbd5a/ijson-3.3.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:658ba9cad0374d37b38c9893f4864f284cdcc7d32041f9808fba8c7bcaadf134", size = 57829 },
+    { url = "https://files.pythonhosted.org/packages/f5/b0/143dbfe12e1d1303ea8d8cd6f40e95cea8f03bcad5b79708614a7856c22e/ijson-3.3.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:2636cb8c0f1023ef16173f4b9a233bcdb1df11c400c603d5f299fac143ca8d70", size = 57217 },
+    { url = "https://files.pythonhosted.org/packages/0d/80/b3b60c5e5be2839365b03b915718ca462c544fdc71e7a79b7262837995ef/ijson-3.3.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:cd174b90db68c3bcca273e9391934a25d76929d727dc75224bf244446b28b03b", size = 121878 },
+    { url = "https://files.pythonhosted.org/packages/8d/eb/7560fafa4d40412efddf690cb65a9bf2d3429d6035e544103acbf5561dc4/ijson-3.3.0-cp311-cp311-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:97a9aea46e2a8371c4cf5386d881de833ed782901ac9f67ebcb63bb3b7d115af", size = 115620 },
+    { url = "https://files.pythonhosted.org/packages/51/2b/5a34c7841388dce161966e5286931518de832067cd83e6f003d93271e324/ijson-3.3.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c594c0abe69d9d6099f4ece17763d53072f65ba60b372d8ba6de8695ce6ee39e", size = 119200 },
+    { url = "https://files.pythonhosted.org/packages/3e/b7/1d64fbec0d0a7b0c02e9ad988a89614532028ead8bb52a2456c92e6ee35a/ijson-3.3.0-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:8e0ff16c224d9bfe4e9e6bd0395826096cda4a3ef51e6c301e1b61007ee2bd24", size = 121107 },
+    { url = "https://files.pythonhosted.org/packages/d4/b9/01044f09850bc545ffc85b35aaec473d4f4ca2b6667299033d252c1b60dd/ijson-3.3.0-cp311-cp311-musllinux_1_2_i686.whl", hash = "sha256:0015354011303175eae7e2ef5136414e91de2298e5a2e9580ed100b728c07e51", size = 116658 },
+    { url = "https://files.pythonhosted.org/packages/fb/0d/53856b61f3d952d299d1695c487e8e28058d01fa2adfba3d6d4b4660c242/ijson-3.3.0-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:034642558afa57351a0ffe6de89e63907c4cf6849070cc10a3b2542dccda1afe", size = 118186 },
+    { url = "https://files.pythonhosted.org/packages/95/2d/5bd86e2307dd594840ee51c4e32de953fee837f028acf0f6afb08914cd06/ijson-3.3.0-cp311-cp311-win32.whl", hash = "sha256:192e4b65495978b0bce0c78e859d14772e841724d3269fc1667dc6d2f53cc0ea", size = 48938 },
+    { url = "https://files.pythonhosted.org/packages/55/e1/4ba2b65b87f67fb19d698984d92635e46d9ce9dd748ce7d009441a586710/ijson-3.3.0-cp311-cp311-win_amd64.whl", hash = "sha256:72e3488453754bdb45c878e31ce557ea87e1eb0f8b4fc610373da35e8074ce42", size = 50972 },
+    { url = "https://files.pythonhosted.org/packages/8a/4d/3992f7383e26a950e02dc704bc6c5786a080d5c25fe0fc5543ef477c1883/ijson-3.3.0-cp312-cp312-macosx_10_9_universal2.whl", hash = "sha256:988e959f2f3d59ebd9c2962ae71b97c0df58323910d0b368cc190ad07429d1bb", size = 84550 },
+    { url = "https://files.pythonhosted.org/packages/1b/cc/3d4372e0d0b02a821b982f1fdf10385512dae9b9443c1597719dd37769a9/ijson-3.3.0-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:b2f73f0d0fce5300f23a1383d19b44d103bb113b57a69c36fd95b7c03099b181", size = 57572 },
+    { url = "https://files.pythonhosted.org/packages/02/de/970d48b1ff9da5d9513c86fdd2acef5cb3415541c8069e0d92a151b84adb/ijson-3.3.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:0ee57a28c6bf523d7cb0513096e4eb4dac16cd935695049de7608ec110c2b751", size = 56902 },
+    { url = "https://files.pythonhosted.org/packages/5e/a0/4537722c8b3b05e82c23dfe09a3a64dd1e44a013a5ca58b1e77dfe48b2f1/ijson-3.3.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e0155a8f079c688c2ccaea05de1ad69877995c547ba3d3612c1c336edc12a3a5", size = 127400 },
+    { url = "https://files.pythonhosted.org/packages/b2/96/54956062a99cf49f7a7064b573dcd756da0563ce57910dc34e27a473d9b9/ijson-3.3.0-cp312-cp312-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:7ab00721304af1ae1afa4313ecfa1bf16b07f55ef91e4a5b93aeaa3e2bd7917c", size = 118786 },
+    { url = "https://files.pythonhosted.org/packages/07/74/795319531c5b5504508f595e631d592957f24bed7ff51a15bc4c61e7b24c/ijson-3.3.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:40ee3821ee90be0f0e95dcf9862d786a7439bd1113e370736bfdf197e9765bfb", size = 126288 },
+    { url = "https://files.pythonhosted.org/packages/69/6a/e0cec06fbd98851d5d233b59058c1dc2ea767c9bb6feca41aa9164fff769/ijson-3.3.0-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:da3b6987a0bc3e6d0f721b42c7a0198ef897ae50579547b0345f7f02486898f5", size = 129569 },
+    { url = "https://files.pythonhosted.org/packages/2a/4f/82c0d896d8dcb175f99ced7d87705057bcd13523998b48a629b90139a0dc/ijson-3.3.0-cp312-cp312-musllinux_1_2_i686.whl", hash = "sha256:63afea5f2d50d931feb20dcc50954e23cef4127606cc0ecf7a27128ed9f9a9e6", size = 121508 },
+    { url = "https://files.pythonhosted.org/packages/2b/b6/8973474eba4a917885e289d9e138267d3d1f052c2d93b8c968755661a42d/ijson-3.3.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:b5c3e285e0735fd8c5a26d177eca8b52512cdd8687ca86ec77a0c66e9c510182", size = 127896 },
+    { url = "https://files.pythonhosted.org/packages/94/25/00e66af887adbbe70002e0479c3c2340bdfa17a168e25d4ab5a27b53582d/ijson-3.3.0-cp312-cp312-win32.whl", hash = "sha256:907f3a8674e489abdcb0206723e5560a5cb1fa42470dcc637942d7b10f28b695", size = 49272 },
+    { url = "https://files.pythonhosted.org/packages/25/a2/e187beee237808b2c417109ae0f4f7ee7c81ecbe9706305d6ac2a509cc45/ijson-3.3.0-cp312-cp312-win_amd64.whl", hash = "sha256:8f890d04ad33262d0c77ead53c85f13abfb82f2c8f078dfbf24b78f59534dfdd", size = 51272 },
+    { url = "https://files.pythonhosted.org/packages/c3/28/2e1cf00abe5d97aef074e7835b86a94c9a06be4629a0e2c12600792b51ba/ijson-3.3.0-pp310-pypy310_pp73-macosx_10_9_x86_64.whl", hash = "sha256:2af323a8aec8a50fa9effa6d640691a30a9f8c4925bd5364a1ca97f1ac6b9b5c", size = 54308 },
+    { url = "https://files.pythonhosted.org/packages/04/d2/8c541c28da4f931bac8177e251efe2b6902f7c486d2d4bdd669eed4ff5c0/ijson-3.3.0-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f64f01795119880023ba3ce43072283a393f0b90f52b66cc0ea1a89aa64a9ccb", size = 66010 },
+    { url = "https://files.pythonhosted.org/packages/d0/02/8fec0b9037a368811dba7901035e8e0973ebda308f57f30c42101a16a5f7/ijson-3.3.0-pp310-pypy310_pp73-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:a716e05547a39b788deaf22725490855337fc36613288aa8ae1601dc8c525553", size = 66770 },
+    { url = "https://files.pythonhosted.org/packages/47/23/90c61f978c83647112460047ea0137bde9c7fe26600ce255bb3e17ea7a21/ijson-3.3.0-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:473f5d921fadc135d1ad698e2697025045cd8ed7e5e842258295012d8a3bc702", size = 64159 },
+    { url = "https://files.pythonhosted.org/packages/20/af/aab1a36072590af62d848f03981f1c587ca40a391fc61e418e388d8b0d46/ijson-3.3.0-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:dd26b396bc3a1e85f4acebeadbf627fa6117b97f4c10b177d5779577c6607744", size = 51095 },
+]
+
 [[package]]
 name = "imageio"
 version = "2.36.1"
@@ -2255,6 +2359,19 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/83/60/d497a310bde3f01cb805196ac61b7ad6dc5dcf8dce66634dc34364b20b4f/lazy_loader-0.4-py3-none-any.whl", hash = "sha256:342aa8e14d543a154047afb4ba8ef17f5563baad3fc610d7b15b213b0f119efc", size = 12097 },
 ]
 
+[[package]]
+name = "linkup-sdk"
+version = "0.2.1"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "httpx" },
+    { name = "pydantic" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/2e/ba/b06e8f2ca2f0ce255a40ee4505637536acfe83ec997cd8b61bd5cd031513/linkup_sdk-0.2.1.tar.gz", hash = "sha256:b00ba7cb0117358e975d50196501ac49b247509fd236121e40abe40e6a2a3e9a", size = 8918 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/4f/90/2903b9e2eba501ceb6c6b4fc57bbeddde7e8964921a05d424f5a6125cbd0/linkup_sdk-0.2.1-py3-none-any.whl", hash = "sha256:bf50c88e659c6d9291cbd5e3e99b6a20a14c9b1eb2dc7acca763a3ae6f84b26e", size = 7961 },
+]
+
 [[package]]
 name = "litellm"
 version = "1.60.2"
@@ -3307,6 +3424,18 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/9f/8a/ce7c28e4ea337f6d95261345d7c61322f8561c52f57b263a3ad7025984f4/orjson-3.10.10-cp312-none-win_amd64.whl", hash = "sha256:384cd13579a1b4cd689d218e329f459eb9ddc504fa48c5a83ef4889db7fd7a4f", size = 139389 },
 ]
 
+[[package]]
+name = "outcome"
+version = "1.3.0.post0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "attrs" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/98/df/77698abfac98571e65ffeb0c1fba8ffd692ab8458d617a0eed7d9a8d38f2/outcome-1.3.0.post0.tar.gz", hash = "sha256:9dcf02e65f2971b80047b377468e72a268e15c0af3cf1238e6ff14f7f91143b8", size = 21060 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/55/8b/5ab7257531a5d830fc8000c476e63c935488d74609b50f9384a643ec0a62/outcome-1.3.0.post0-py2.py3-none-any.whl", hash = "sha256:e771c5ce06d1415e356078d3bdd68523f284b4ce5419828922b6871e65eda82b", size = 10692 },
+]
+
 [[package]]
 name = "overrides"
 version = "7.7.0"
@@ -3396,6 +3525,24 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/cc/20/ff623b09d963f88bfde16306a54e12ee5ea43e9b597108672ff3a408aad6/pathspec-0.12.1-py3-none-any.whl", hash = "sha256:a0d503e138a4c123b27490a4f7beda6a01c6f288df0e4a8b79c7eb0dc7b4cc08", size = 31191 },
 ]
 
+[[package]]
+name = "patronus"
+version = "0.0.17"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "httpx" },
+    { name = "pandas" },
+    { name = "pydantic" },
+    { name = "pydantic-settings" },
+    { name = "pyyaml" },
+    { name = "tqdm" },
+    { name = "typing-extensions" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/c5/a0/d5218ff6f2eab18c5a90266d21cdac673c85070e82e3f8aba538b3200f54/patronus-0.0.17.tar.gz", hash = "sha256:7298f770d4f6774b955806fb319c2c872fda3551bd7fa63d975bbeedc14b28de", size = 27377 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/0e/9e/717c4508d675549ff081a7fecf25af7d70f9d7ad87ea0d4825e02de3b801/patronus-0.0.17-py3-none-any.whl", hash = "sha256:1f322eeee838974515fdb7cbf8530ad25c6c59686abbcb28c1fdbf23d34eb10d", size = 31516 },
+]
+
 [[package]]
 name = "pdfminer-six"
 version = "20231228"
@@ -3956,6 +4103,18 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/c2/35/c0edf199257ef0a7d407d29cd51c4e70d1dad4370a5f44deb65a7a5475e2/pymdown_extensions-10.11.2-py3-none-any.whl", hash = "sha256:41cdde0a77290e480cf53892f5c5e50921a7ee3e5cd60ba91bf19837b33badcf", size = 259044 },
 ]
 
+[[package]]
+name = "pyopenssl"
+version = "24.3.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "cryptography" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/c1/d4/1067b82c4fc674d6f6e9e8d26b3dff978da46d351ca3bac171544693e085/pyopenssl-24.3.0.tar.gz", hash = "sha256:49f7a019577d834746bc55c5fce6ecbcec0f2b4ec5ce1cf43a9a173b8138bb36", size = 178944 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/42/22/40f9162e943f86f0fc927ebc648078be87def360d9d8db346619fb97df2b/pyOpenSSL-24.3.0-py3-none-any.whl", hash = "sha256:e474f5a473cd7f92221cc04976e48f4d11502804657a08a989fb3be5514c904a", size = 56111 },
+]
+
 [[package]]
 name = "pypdf"
 version = "5.0.1"
@@ -4033,6 +4192,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/48/0a/c99fb7d7e176f8b176ef19704a32e6a9c6aafdf19ef75a187f701fc15801/pysbd-0.3.4-py3-none-any.whl", hash = "sha256:cd838939b7b0b185fcf86b0baf6636667dfb6e474743beeff878e9f42e022953", size = 71082 },
 ]
 
+[[package]]
+name = "pysocks"
+version = "1.7.1"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/bd/11/293dd436aea955d45fc4e8a35b6ae7270f5b8e00b53cf6c024c83b657a11/PySocks-1.7.1.tar.gz", hash = "sha256:3f8804571ebe159c380ac6de37643bb4685970655d3bba243530d6558b799aa0", size = 284429 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/8d/59/b4572118e098ac8e46e399a1dd0f2d85403ce8bbaad9ec79373ed6badaf9/PySocks-1.7.1-py3-none-any.whl", hash = "sha256:2725bd0a9925919b9b51739eea5f9e2bae91e83288108a9ad338b2e3a4435ee5", size = 16725 },
+]
+
 [[package]]
 name = "pytest"
 version = "8.3.3"
@@ -4692,6 +4860,39 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/aa/7d/43ab67228ef98c6b5dd42ab386eae2d7877036970a0d7e3dd3eb47a0d530/scipy-1.14.1-cp312-cp312-win_amd64.whl", hash = "sha256:2ff38e22128e6c03ff73b6bb0f85f897d2362f8c052e3b8ad00532198fbdae3f", size = 44521212 },
 ]
 
+[[package]]
+name = "scrapegraph-py"
+version = "1.8.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "aiohttp" },
+    { name = "beautifulsoup4" },
+    { name = "pydantic" },
+    { name = "python-dotenv" },
+    { name = "requests" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/33/90/2388754061394a6c95fd5ad48cf4550208ce081c99cbc883672d52ccc360/scrapegraph_py-1.8.0.tar.gz", hash = "sha256:e075f6e6012a14a038537d0664609229069d9d2c2956bcbf9362f0c5c48de786", size = 108112 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/f7/80/14aeb7ba092cfc6928844a6726855f0c33489107f344e71dd8071f6433ed/scrapegraph_py-1.8.0-py3-none-any.whl", hash = "sha256:279176c972a770bac37a284e0bc25e34793797f30ff24dfba8fbcbfda79c8c88", size = 14460 },
+]
+
+[[package]]
+name = "selenium"
+version = "4.25.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "certifi" },
+    { name = "trio" },
+    { name = "trio-websocket" },
+    { name = "typing-extensions" },
+    { name = "urllib3", extra = ["socks"] },
+    { name = "websocket-client" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/0e/5a/d3735b189b91715fd0f5a9b8d55e2605061309849470e96ab830f02cba40/selenium-4.25.0.tar.gz", hash = "sha256:95d08d3b82fb353f3c474895154516604c7f0e6a9a565ae6498ef36c9bac6921", size = 957765 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/aa/85/fa44f23dd5d5066a72f7c4304cce4b5ff9a6e7fd92431a48b2c63fbf63ec/selenium-4.25.0-py3-none-any.whl", hash = "sha256:3798d2d12b4a570bc5790163ba57fef10b2afee958bf1d80f2a3cf07c4141f33", size = 9693127 },
+]
+
 [[package]]
 name = "semchunk"
 version = "2.2.0"
@@ -4705,6 +4906,18 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/f8/85/3940bb4c586e10603d169d13ffccd59ed32fcb8d1b8104c3aef0e525b3b2/semchunk-2.2.0-py3-none-any.whl", hash = "sha256:7db19ca90ddb48f99265e789e07a7bb111ae25185f9cc3d44b94e1e61b9067fc", size = 10243 },
 ]
 
+[[package]]
+name = "serpapi"
+version = "0.1.5"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "requests" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/f0/fa/3fd8809287f3977a3e752bb88610e918d49cb1038b14f4bc51e13e594197/serpapi-0.1.5.tar.gz", hash = "sha256:b9707ed54750fdd2f62dc3a17c6a3fb7fa421dc37902fd65b2263c0ac765a1a5", size = 14191 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/df/6a/21deade04100d64844e494353a5d65e7971fbdfddf78eb1f248423593ad0/serpapi-0.1.5-py2.py3-none-any.whl", hash = "sha256:6467b6adec1231059f754ccaa952b229efeaa8b9cae6e71f879703ec9e5bb3d1", size = 10966 },
+]
+
 [[package]]
 name = "setuptools"
 version = "75.2.0"
@@ -4770,6 +4983,96 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/e9/44/75a9c9421471a6c4805dbf2356f7c181a29c1879239abab1ea2cc8f38b40/sniffio-1.3.1-py3-none-any.whl", hash = "sha256:2f6da418d1f1e0fddd844478f41680e794e6051915791a034ff65e5f100525a2", size = 10235 },
 ]
 
+[[package]]
+name = "snowflake"
+version = "1.0.2"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "snowflake-core" },
+    { name = "snowflake-legacy" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/80/d1/830929fb7b54586f4ee601f409e80343e16f32b9b579246cd6fa9984bcff/snowflake-1.0.2.tar.gz", hash = "sha256:4009e59af24e444de4a9e9d340fff0979cca8a02a4feee4665da97eb9c76d958", size = 6033 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/b6/25/4cbba4da3f9b333d132680a66221d1a101309cce330fa8be38b674ceafd0/snowflake-1.0.2-py3-none-any.whl", hash = "sha256:6bb0fc70aa10234769202861ccb4b091f5e9fb1bbc61a1e708db93baa3f221f4", size = 5623 },
+]
+
+[[package]]
+name = "snowflake-connector-python"
+version = "3.12.4"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "asn1crypto" },
+    { name = "certifi" },
+    { name = "cffi" },
+    { name = "charset-normalizer" },
+    { name = "cryptography" },
+    { name = "filelock" },
+    { name = "idna" },
+    { name = "packaging" },
+    { name = "platformdirs" },
+    { name = "pyjwt" },
+    { name = "pyopenssl" },
+    { name = "pytz" },
+    { name = "requests" },
+    { name = "sortedcontainers" },
+    { name = "tomlkit" },
+    { name = "typing-extensions" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/6b/de/f43d9c827ccc1974696ffd3c0495e2d4e98b0414b2353b7de932621f23dd/snowflake_connector_python-3.12.4.tar.gz", hash = "sha256:289e0691dfbf8ec8b7a8f58bcbb95a819890fe5e5b278fdbfc885059a63a946f", size = 743445 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/53/6c/edc8909e424654a7a3c18cbf804d8a35c17a65a2131f866a87ed8e762bd0/snowflake_connector_python-3.12.4-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:6f141c159e3244bd660279f87f32e39351b2845fcb75f8138f31d2219f983b05", size = 958038 },
+    { url = "https://files.pythonhosted.org/packages/93/a3/34c5082dfb9b555c914f4233224b8bc1f2c4d5668bc71bb587680b8dcd73/snowflake_connector_python-3.12.4-cp310-cp310-macosx_11_0_x86_64.whl", hash = "sha256:091458ba777c24adff659c5c28f0f5bb0bcca8a9b6ecc5641ae25b7c20a8f43d", size = 970665 },
+    { url = "https://files.pythonhosted.org/packages/f8/87/9eceaaba58b2ec4f9094fc3a04d953bbabbfdcc05a6b14ef12610c1039f9/snowflake_connector_python-3.12.4-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:23049d341da681ec7131cead71cdf7b1761ae5bcc08bcbdb931dcef6c25e8a5f", size = 2496731 },
+    { url = "https://files.pythonhosted.org/packages/66/0a/e35e9e0a142f3779007b0246166a245305858b198ed0dd3a41a3d2405512/snowflake_connector_python-3.12.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:cc88a09d77a8ce7e445094b2409b606ddb208b5fc9f7c7a379d0255a8d566e9d", size = 2520041 },
+    { url = "https://files.pythonhosted.org/packages/79/77/9a238c153600adff8fbd1136d9f4be1e42cb827cbe1865924bfe84653e85/snowflake_connector_python-3.12.4-cp310-cp310-win_amd64.whl", hash = "sha256:3c33fbba036805c1767ea48eb40ffc3fb79d61f2a4bb4e77b571ea6f6a998be8", size = 918272 },
+    { url = "https://files.pythonhosted.org/packages/0d/95/e8aac28d6913e4b59f96e6d361f31b9576b5f0abe4d2c4f7decf9f075932/snowflake_connector_python-3.12.4-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:2ec5cfaa1526084cf4d0e7849d5ace601245cb4ad9675ab3cd7d799b3abea481", size = 958125 },
+    { url = "https://files.pythonhosted.org/packages/67/b6/a847a94e03bdf39010048feacd57f250a91a655eed333d7d32b165f65201/snowflake_connector_python-3.12.4-cp311-cp311-macosx_11_0_x86_64.whl", hash = "sha256:ff225824b3a0fa5e822442de72172f97028f04ae183877f1305d538d8d6c5d11", size = 970770 },
+    { url = "https://files.pythonhosted.org/packages/0e/91/f97812ae9946944bcd9bfe1965af1cb9b1844919da879d90b90dfd3e5086/snowflake_connector_python-3.12.4-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a9beced2789dc75e8f1e749aa637e7ec9b03302b4ed4b793ae0f1ff32823370e", size = 2519875 },
+    { url = "https://files.pythonhosted.org/packages/37/52/500d72079bfb322ebdf3892180ecf3dc73c117b3a966ee8d4bb1378882b2/snowflake_connector_python-3.12.4-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5ea47450a04ff713f3adf28053e34103bd990291e62daee9721c76597af4b2b5", size = 2542320 },
+    { url = "https://files.pythonhosted.org/packages/59/92/74ead6bee8dd29fe372002ce59477221e04b9da96ad7aafe584afce02937/snowflake_connector_python-3.12.4-cp311-cp311-win_amd64.whl", hash = "sha256:748f9125854dca07ea471bb2bb3c5bb932a53f9b8a77ba348b50b738c77203ce", size = 918363 },
+    { url = "https://files.pythonhosted.org/packages/a5/a3/1cbe0b52b810f069bdc96c372b2d91ac51aeac32986c2832aa3fe0b0b0e5/snowflake_connector_python-3.12.4-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:4bcd0371b20d199f15e6a3c0b489bf18e27f2a88c84cf3194b2569ca039fa7d1", size = 957561 },
+    { url = "https://files.pythonhosted.org/packages/f4/05/8a5e16bd908a89f36d59686d356890c4bd6a976a487f86274181010f4b49/snowflake_connector_python-3.12.4-cp312-cp312-macosx_11_0_x86_64.whl", hash = "sha256:7900d82a450b206fa2ed6c42cd65d9b3b9fd4547eca1696937175fac2a03ba37", size = 969045 },
+    { url = "https://files.pythonhosted.org/packages/79/1b/8f5ab15d224d7bf76533c55cfd8ce73b185ce94d84241f0e900739ce3f37/snowflake_connector_python-3.12.4-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:300f0562aeea55e40ee03b45205dbef7b78f5ba2f1787a278c7b807e7d8db22c", size = 2533969 },
+    { url = "https://files.pythonhosted.org/packages/6e/d9/2e2fd72e0251691b5c54a219256c455141a2d3c104e411b82de598c62553/snowflake_connector_python-3.12.4-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a6762a00948f003be55d7dc5de9de690315d01951a94371ec3db069d9303daba", size = 2558052 },
+    { url = "https://files.pythonhosted.org/packages/e8/cb/e0ab230ad5adc9932e595bdbec693b2499d446666daf6cb9cae306a41dd2/snowflake_connector_python-3.12.4-cp312-cp312-win_amd64.whl", hash = "sha256:83ca896790a7463b6c8cd42e1a29b8ea197cc920839ae6ee96a467475eab4ec2", size = 916627 },
+]
+
+[[package]]
+name = "snowflake-core"
+version = "1.0.2"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "atpublic" },
+    { name = "pydantic" },
+    { name = "python-dateutil" },
+    { name = "pyyaml" },
+    { name = "requests" },
+    { name = "snowflake-connector-python" },
+    { name = "urllib3" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/1d/cf/6f91e5b2daaf3df9ae666a65f5ba3938f11a40784e4ada5218ecf154b29a/snowflake_core-1.0.2.tar.gz", hash = "sha256:8bf267ff1efcd17f157432c6e24f6d2eb6c2aeed66f43ab34b215aa76d8edf02", size = 1092618 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/75/3c/ec228b7325b32781081c72254dd0ef793943e853d82616e862e231909c6c/snowflake_core-1.0.2-py3-none-any.whl", hash = "sha256:55c37cf526a0d78dd3359ad96b9ecd7130bbbbc2f5a2fec77bb3da0dac2dc688", size = 1555690 },
+]
+
+[[package]]
+name = "snowflake-legacy"
+version = "1.0.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/94/41/a6211bd2109913eee1506d37865ab13cf9a8cc2faa41833da3d1ffec654b/snowflake_legacy-1.0.0.tar.gz", hash = "sha256:2044661c79ba01841ab279c5e74b994532244c9d103224eba16eb159c8ed6033", size = 4043 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/aa/8c/64f9b5ee0c3f376a733584c480b31addbf2baff7bb41f655e5e3f3719d3b/snowflake_legacy-1.0.0-py3-none-any.whl", hash = "sha256:25f9678f180d7d5f5b60d17f8112f0ee8a7a77b82c67fd599ed6e27bd502be5a", size = 3059 },
+]
+
+[[package]]
+name = "sortedcontainers"
+version = "2.4.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/e8/c4/ba2f8066cceb6f23394729afe52f3bf7adec04bf9ed2c820b39e19299111/sortedcontainers-2.4.0.tar.gz", hash = "sha256:25caa5a06cc30b6b83d11423433f65d1f9d76c4c6a0c90e3379eaa43b9bfdb88", size = 30594 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/32/46/9cb0e58b2deb7f82b84065f37f3bffeb12413f947f9388e4cac22c4621ce/sortedcontainers-2.4.0-py2.py3-none-any.whl", hash = "sha256:a163dcaede0f1c021485e957a39245190e74249897e2ae4b2aa38595db237ee0", size = 29575 },
+]
+
 [[package]]
 name = "soupsieve"
 version = "2.6"
@@ -4779,6 +5082,18 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/d1/c2/fe97d779f3ef3b15f05c94a2f1e3d21732574ed441687474db9d342a7315/soupsieve-2.6-py3-none-any.whl", hash = "sha256:e72c4ff06e4fb6e4b5a9f0f55fe6e81514581fca1515028625d0f299c602ccc9", size = 36186 },
 ]
 
+[[package]]
+name = "spider-client"
+version = "0.1.25"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "aiohttp" },
+    { name = "ijson" },
+    { name = "requests" },
+    { name = "tenacity" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/b8/f2/06d89322f0054ea72e8d5580199f580e29df23476cb3cfe83a70a2a58a1b/spider-client-0.1.25.tar.gz", hash = "sha256:92ca4ce1d9d715dd8db52684ea417653940d8f3bbc13383d78683bc4fbb899a2", size = 15412 }
+
 [[package]]
 name = "sqlalchemy"
 version = "2.0.36"
@@ -5010,6 +5325,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/c4/ac/ce90573ba446a9bbe65838ded066a805234d159b4446ae9f8ec5bbd36cbd/tomli_w-1.1.0-py3-none-any.whl", hash = "sha256:1403179c78193e3184bfaade390ddbd071cba48a32a2e62ba11aae47490c63f7", size = 6440 },
 ]
 
+[[package]]
+name = "tomlkit"
+version = "0.13.2"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/b1/09/a439bec5888f00a54b8b9f05fa94d7f901d6735ef4e55dcec9bc37b5d8fa/tomlkit-0.13.2.tar.gz", hash = "sha256:fff5fe59a87295b278abd31bec92c15d9bc4a06885ab12bcea52c71119392e79", size = 192885 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/f9/b6/a447b5e4ec71e13871be01ba81f5dfc9d0af7e473da256ff46bc0e24026f/tomlkit-0.13.2-py3-none-any.whl", hash = "sha256:7a974427f6e119197f670fbbbeae7bef749a6c14e793db934baefc1b5f03efde", size = 37955 },
+]
+
 [[package]]
 name = "torch"
 version = "2.4.1"
@@ -5115,6 +5439,38 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/51/51/b87caa939fedf307496e4dbf412f4b909af3d9ca8b189fc3b65c1faa456f/transformers-4.46.3-py3-none-any.whl", hash = "sha256:a12ef6f52841fd190a3e5602145b542d03507222f2c64ebb7ee92e8788093aef", size = 10034536 },
 ]
 
+[[package]]
+name = "trio"
+version = "0.27.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "attrs" },
+    { name = "cffi", marker = "implementation_name != 'pypy' and os_name == 'nt'" },
+    { name = "exceptiongroup", marker = "python_full_version < '3.11'" },
+    { name = "idna" },
+    { name = "outcome" },
+    { name = "sniffio" },
+    { name = "sortedcontainers" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/17/d1/a83dee5be404da7afe5a71783a33b8907bacb935a6dc8c69ab785e4a3eed/trio-0.27.0.tar.gz", hash = "sha256:1dcc95ab1726b2da054afea8fd761af74bad79bd52381b84eae408e983c76831", size = 568064 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/3c/83/ec3196c360afffbc5b342ead48d1eb7393dd74fa70bca75d33905a86f211/trio-0.27.0-py3-none-any.whl", hash = "sha256:68eabbcf8f457d925df62da780eff15ff5dc68fd6b367e2dde59f7aaf2a0b884", size = 481734 },
+]
+
+[[package]]
+name = "trio-websocket"
+version = "0.11.1"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "exceptiongroup", marker = "python_full_version < '3.11'" },
+    { name = "trio" },
+    { name = "wsproto" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/dd/36/abad2385853077424a11b818d9fd8350d249d9e31d583cb9c11cd4c85eda/trio-websocket-0.11.1.tar.gz", hash = "sha256:18c11793647703c158b1f6e62de638acada927344d534e3c7628eedcb746839f", size = 26511 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/48/be/a9ae5f50cad5b6f85bd2574c2c923730098530096e170c1ce7452394d7aa/trio_websocket-0.11.1-py3-none-any.whl", hash = "sha256:520d046b0d030cf970b8b2b2e00c4c2245b3807853ecd44214acd33d74581638", size = 17408 },
+]
+
 [[package]]
 name = "triton"
 version = "3.0.0"
@@ -5195,6 +5551,11 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/ce/d9/5f4c13cecde62396b0d3fe530a50ccea91e7dfc1ccf0e09c228841bb5ba8/urllib3-2.2.3-py3-none-any.whl", hash = "sha256:ca899ca043dcb1bafa3e262d73aa25c465bfb49e0bd9dd5d59f1d0acba2f8fac", size = 126338 },
 ]
 
+[package.optional-dependencies]
+socks = [
+    { name = "pysocks" },
+]
+
 [[package]]
 name = "uv"
 version = "0.4.26"
@@ -5271,6 +5632,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/8f/eb/f7032be105877bcf924709c97b1bf3b90255b4ec251f9340cef912559f28/uvloop-0.21.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:183aef7c8730e54c9a3ee3227464daed66e37ba13040bb3f350bc2ddc040f22f", size = 4659022 },
 ]
 
+[[package]]
+name = "validators"
+version = "0.34.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/64/07/91582d69320f6f6daaf2d8072608a4ad8884683d4840e7e4f3a9dbdcc639/validators-0.34.0.tar.gz", hash = "sha256:647fe407b45af9a74d245b943b18e6a816acf4926974278f6dd617778e1e781f", size = 70955 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/6e/78/36828a4d857b25896f9774c875714ba4e9b3bc8a92d2debe3f4df3a83d4f/validators-0.34.0-py3-none-any.whl", hash = "sha256:c804b476e3e6d3786fa07a30073a4ef694e617805eb1946ceee3fe5a9b8b1321", size = 43536 },
+]
+
 [[package]]
 name = "vcrpy"
 version = "5.1.0"
@@ -5390,6 +5760,25 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/fd/84/fd2ba7aafacbad3c4201d395674fc6348826569da3c0937e75505ead3528/wcwidth-0.2.13-py2.py3-none-any.whl", hash = "sha256:3da69048e4540d84af32131829ff948f1e022c1c6bdb8d6102117aac784f6859", size = 34166 },
 ]
 
+[[package]]
+name = "weaviate-client"
+version = "4.9.6"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "authlib" },
+    { name = "grpcio" },
+    { name = "grpcio-health-checking" },
+    { name = "grpcio-tools" },
+    { name = "httpx" },
+    { name = "pydantic" },
+    { name = "requests" },
+    { name = "validators" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/5d/7d/3894d12065d006743271b0b6bcc3bf911910473e91179d5966966816d694/weaviate_client-4.9.6.tar.gz", hash = "sha256:56d67c40fc94b0d53e81e0aa4477baaebbf3646fbec26551df66e396a72adcb6", size = 696813 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/2f/40/e3550e743b92ddd8dc69ebfd69cceb6de45b7d9a1cd439995454b499e9a3/weaviate_client-4.9.6-py3-none-any.whl", hash = "sha256:1d3b551939c0f7314f25e417cbcf4cf34e7adf942627993eef36ae6b4a044673", size = 386998 },
+]
+
 [[package]]
 name = "webencodings"
 version = "0.5.1"
@@ -5504,6 +5893,18 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/ff/21/abdedb4cdf6ff41ebf01a74087740a709e2edb146490e4d9beea054b0b7a/wrapt-1.16.0-py3-none-any.whl", hash = "sha256:6906c4100a8fcbf2fa735f6059214bb13b97f75b1a61777fcf6432121ef12ef1", size = 23362 },
 ]
 
+[[package]]
+name = "wsproto"
+version = "1.2.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "h11" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/c9/4a/44d3c295350d776427904d73c189e10aeae66d7f555bb2feee16d1e4ba5a/wsproto-1.2.0.tar.gz", hash = "sha256:ad565f26ecb92588a3e43bc3d96164de84cd9902482b130d0ddbaa9664a85065", size = 53425 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/78/58/e860788190eba3bcce367f74d29c4675466ce8dddfba85f7827588416f01/wsproto-1.2.0-py3-none-any.whl", hash = "sha256:b9acddd652b585d75b20477888c56642fdade28bdfd3579aa24a4d2c037dd736", size = 24226 },
+]
+
 [[package]]
 name = "xlsxwriter"
 version = "3.2.0"