fix: properly clone ConditionalTask instances

Previously copying a Task always returned an instance of Task even when we are cloning a subclass, such ConditionalTask.
This commit ensures that the clone preserve the original class type

docs/changelog.mdx

@@ -4,7 +4,7 @@ description: View the latest updates and changes to CrewAI
 icon: timeline
 ---
 
-<Update label="2024-03-17" description="v0.108.0">
+<Update label="2025-03-17" description="v0.108.0">
   **Features**
   - Converted tabs to spaces in `crew.py` template
   - Enhanced LLM Streaming Response Handling and Event System
@@ -24,7 +24,7 @@ icon: timeline
   - Added documentation for `ApifyActorsTool`
 </Update>
 
-<Update label="2024-03-10" description="v0.105.0">
+<Update label="2025-03-10" description="v0.105.0">
   **Core Improvements & Fixes**
   - Fixed issues with missing template variables and user memory configuration
   - Improved async flow support and addressed agent response formatting
@@ -45,7 +45,7 @@ icon: timeline
   - Fixed typos in prompts and updated Amazon Bedrock model listings
 </Update>
 
-<Update label="2024-02-12" description="v0.102.0">
+<Update label="2025-02-12" description="v0.102.0">
   **Core Improvements & Fixes**
   - Enhanced LLM Support: Improved structured LLM output, parameter handling, and formatting for Anthropic models
   - Crew & Agent Stability: Fixed issues with cloning agents/crews using knowledge sources, multiple task outputs in conditional tasks, and ignored Crew task callbacks
@@ -65,7 +65,7 @@ icon: timeline
   - Fixed Various Typos & Formatting Issues
 </Update>
 
-<Update label="2024-01-28" description="v0.100.0">
+<Update label="2025-01-28" description="v0.100.0">
   **Features**
   - Add Composio docs
   - Add SageMaker as a LLM provider
@@ -80,7 +80,7 @@ icon: timeline
   - Improve formatting and clarity in CLI and Composio Tool docs
 </Update>
 
-<Update label="2024-01-20" description="v0.98.0">
+<Update label="2025-01-20" description="v0.98.0">
   **Features**
   - Conversation crew v1
   - Add unique ID to flow states
@@ -101,7 +101,7 @@ icon: timeline
   - Fixed typos, nested pydantic model issue, and docling issues
 </Update>
 
-<Update label="2024-01-04" description="v0.95.0">
+<Update label="2025-01-04" description="v0.95.0">
   **New Features**
   - Adding Multimodal Abilities to Crew
   - Programatic Guardrails
@@ -131,7 +131,7 @@ icon: timeline
   - Suppressed userWarnings from litellm pydantic issues
 </Update>
 
-<Update label="2023-12-05" description="v0.86.0">
+<Update label="2024-12-05" description="v0.86.0">
   **Changes**
   - Remove all references to pipeline and pipeline router
   - Add Nvidia NIM as provider in Custom LLM
@@ -141,7 +141,7 @@ icon: timeline
   - Simplify template crew
 </Update>
 
-<Update label="2023-12-04" description="v0.85.0">
+<Update label="2024-12-04" description="v0.85.0">
   **Features**
   - Added knowledge to agent level
   - Feat/remove langchain
@@ -161,7 +161,7 @@ icon: timeline
   - Improvements to LLM Configuration and Usage
 </Update>
 
-<Update label="2023-11-25" description="v0.83.0">
+<Update label="2024-11-25" description="v0.83.0">
   **New Features**
   - New before_kickoff and after_kickoff crew callbacks
   - Support to pre-seed agents with Knowledge
@@ -178,7 +178,7 @@ icon: timeline
   - Update Docs
 </Update>
 
-<Update label="2023-11-13" description="v0.80.0">
+<Update label="2024-11-13" description="v0.80.0">
   **Fixes**
   - Fixing Tokens callback replacement bug
   - Fixing Step callback issue

docs/concepts/event-listener.mdx

@@ -1,6 +1,7 @@
 ---
 title: 'Event Listeners'
 description: 'Tap into CrewAI events to build custom integrations and monitoring'
+icon: spinner
 ---
 
 # Event Listeners

docs/concepts/llms.mdx

@@ -59,7 +59,7 @@ There are three ways to configure LLMs in CrewAI. Choose the method that best fi
         goal: Conduct comprehensive research and analysis
         backstory: A dedicated research professional with years of experience
         verbose: true
-        llm: openai/gpt-4o-mini # your model here 
+        llm: openai/gpt-4o-mini # your model here
         # (see provider configuration examples below for more)
     ```
 
@@ -111,7 +111,7 @@ There are three ways to configure LLMs in CrewAI. Choose the method that best fi
 ## Provider Configuration Examples
 
 
-CrewAI supports a multitude of LLM providers, each offering unique features, authentication methods, and model capabilities. 
+CrewAI supports a multitude of LLM providers, each offering unique features, authentication methods, and model capabilities.
 In this section, you'll find detailed examples that help you select, configure, and optimize the LLM that best fits your project's needs.
 
 <AccordionGroup>
@@ -121,7 +121,7 @@ In this section, you'll find detailed examples that help you select, configure,
     ```toml Code
     # Required
     OPENAI_API_KEY=sk-...
-    
+
     # Optional
     OPENAI_API_BASE=<custom-base-url>
     OPENAI_ORGANIZATION=<your-org-id>
@@ -226,7 +226,7 @@ In this section, you'll find detailed examples that help you select, configure,
     AZURE_API_KEY=<your-api-key>
     AZURE_API_BASE=<your-resource-url>
     AZURE_API_VERSION=<api-version>
-    
+
     # Optional
     AZURE_AD_TOKEN=<your-azure-ad-token>
     AZURE_API_TYPE=<your-azure-api-type>
@@ -289,7 +289,7 @@ In this section, you'll find detailed examples that help you select, configure,
     | Mistral 8x7B Instruct   | Up to 32k tokens     | An MOE LLM that follows instructions, completes requests, and generates creative text. |
 
   </Accordion>
-  
+
   <Accordion title="Amazon SageMaker">
     ```toml Code
     AWS_ACCESS_KEY_ID=<your-access-key>
@@ -474,7 +474,7 @@ In this section, you'll find detailed examples that help you select, configure,
     WATSONX_URL=<your-url>
     WATSONX_APIKEY=<your-apikey>
     WATSONX_PROJECT_ID=<your-project-id>
-    
+
     # Optional
     WATSONX_TOKEN=<your-token>
     WATSONX_DEPLOYMENT_SPACE_ID=<your-space-id>
@@ -491,7 +491,7 @@ In this section, you'll find detailed examples that help you select, configure,
 
   <Accordion title="Ollama (Local LLMs)">
     1. Install Ollama: [ollama.ai](https://ollama.ai/)
-    2. Run a model: `ollama run llama2`
+    2. Run a model: `ollama run llama3`
     3. Configure:
 
     ```python Code
@@ -600,7 +600,7 @@ In this section, you'll find detailed examples that help you select, configure,
     ```toml Code
     OPENROUTER_API_KEY=<your-api-key>
     ```
-    
+
     Example usage in your CrewAI project:
     ```python Code
     llm = LLM(
@@ -723,7 +723,7 @@ Learn how to get the most out of your LLM configuration:
         - Small tasks (up to 4K tokens): Standard models
         - Medium tasks (between 4K-32K): Enhanced models
         - Large tasks (over 32K): Large context models
-        
+
         ```python
         # Configure model with appropriate settings
         llm = LLM(
@@ -760,11 +760,11 @@ Learn how to get the most out of your LLM configuration:
     <Warning>
       Most authentication issues can be resolved by checking API key format and environment variable names.
     </Warning>
-    
+
     ```bash
     # OpenAI
     OPENAI_API_KEY=sk-...
-    
+
     # Anthropic
     ANTHROPIC_API_KEY=sk-ant-...
     ```
@@ -773,11 +773,11 @@ Learn how to get the most out of your LLM configuration:
     <Check>
       Always include the provider prefix in model names
     </Check>
-    
+
     ```python
     # Correct
     llm = LLM(model="openai/gpt-4")
-    
+
     # Incorrect
     llm = LLM(model="gpt-4")
     ```
@@ -786,5 +786,10 @@ Learn how to get the most out of your LLM configuration:
     <Tip>
       Use larger context models for extensive tasks
     </Tip>
+    
+    ```python
+    # Large context model
+    llm = LLM(model="openai/gpt-4o")  # 128K tokens
+    ```
   </Tab>
 </Tabs>

docs/custom_llm.md

@@ -0,0 +1,642 @@
+# Custom LLM Implementations
+
+CrewAI now supports custom LLM implementations through the `BaseLLM` abstract base class. This allows you to create your own LLM implementations that don't rely on litellm's authentication mechanism.
+
+## Using Custom LLM Implementations
+
+To create a custom LLM implementation, you need to:
+
+1. Inherit from the `BaseLLM` abstract base class
+2. Implement the required methods:
+   - `call()`: The main method to call the LLM with messages
+   - `supports_function_calling()`: Whether the LLM supports function calling
+   - `supports_stop_words()`: Whether the LLM supports stop words
+   - `get_context_window_size()`: The context window size of the LLM
+
+## Example: Basic Custom LLM
+
+```python
+from crewai import BaseLLM
+from typing import Any, Dict, List, Optional, Union
+
+class CustomLLM(BaseLLM):
+    def __init__(self, api_key: str, endpoint: str):
+        super().__init__()  # Initialize the base class to set default attributes
+        if not api_key or not isinstance(api_key, str):
+            raise ValueError("Invalid API key: must be a non-empty string")
+        if not endpoint or not isinstance(endpoint, str):
+            raise ValueError("Invalid endpoint URL: must be a non-empty string")
+        self.api_key = api_key
+        self.endpoint = endpoint
+        self.stop = []  # You can customize stop words if needed
+        
+    def call(
+        self,
+        messages: Union[str, List[Dict[str, str]]],
+        tools: Optional[List[dict]] = None,
+        callbacks: Optional[List[Any]] = None,
+        available_functions: Optional[Dict[str, Any]] = None,
+    ) -> Union[str, Any]:
+        """Call the LLM with the given messages.
+        
+        Args:
+            messages: Input messages for the LLM.
+            tools: Optional list of tool schemas for function calling.
+            callbacks: Optional list of callback functions.
+            available_functions: Optional dict mapping function names to callables.
+            
+        Returns:
+            Either a text response from the LLM or the result of a tool function call.
+            
+        Raises:
+            TimeoutError: If the LLM request times out.
+            RuntimeError: If the LLM request fails for other reasons.
+            ValueError: If the response format is invalid.
+        """
+        # Implement your own logic to call the LLM
+        # For example, using requests:
+        import requests
+        
+        try:
+            headers = {
+                "Authorization": f"Bearer {self.api_key}",
+                "Content-Type": "application/json"
+            }
+            
+            # Convert string message to proper format if needed
+            if isinstance(messages, str):
+                messages = [{"role": "user", "content": messages}]
+            
+            data = {
+                "messages": messages,
+                "tools": tools
+            }
+            
+            response = requests.post(
+                self.endpoint, 
+                headers=headers, 
+                json=data,
+                timeout=30  # Set a reasonable timeout
+            )
+            response.raise_for_status()  # Raise an exception for HTTP errors
+            return response.json()["choices"][0]["message"]["content"]
+        except requests.Timeout:
+            raise TimeoutError("LLM request timed out")
+        except requests.RequestException as e:
+            raise RuntimeError(f"LLM request failed: {str(e)}")
+        except (KeyError, IndexError, ValueError) as e:
+            raise ValueError(f"Invalid response format: {str(e)}")
+        
+    def supports_function_calling(self) -> bool:
+        """Check if the LLM supports function calling.
+        
+        Returns:
+            True if the LLM supports function calling, False otherwise.
+        """
+        # Return True if your LLM supports function calling
+        return True
+        
+    def supports_stop_words(self) -> bool:
+        """Check if the LLM supports stop words.
+        
+        Returns:
+            True if the LLM supports stop words, False otherwise.
+        """
+        # Return True if your LLM supports stop words
+        return True
+        
+    def get_context_window_size(self) -> int:
+        """Get the context window size of the LLM.
+        
+        Returns:
+            The context window size as an integer.
+        """
+        # Return the context window size of your LLM
+        return 8192
+```
+
+## Error Handling Best Practices
+
+When implementing custom LLMs, it's important to handle errors properly to ensure robustness and reliability. Here are some best practices:
+
+### 1. Implement Try-Except Blocks for API Calls
+
+Always wrap API calls in try-except blocks to handle different types of errors:
+
+```python
+def call(
+    self,
+    messages: Union[str, List[Dict[str, str]]],
+    tools: Optional[List[dict]] = None,
+    callbacks: Optional[List[Any]] = None,
+    available_functions: Optional[Dict[str, Any]] = None,
+) -> Union[str, Any]:
+    try:
+        # API call implementation
+        response = requests.post(
+            self.endpoint,
+            headers=self.headers,
+            json=self.prepare_payload(messages),
+            timeout=30  # Set a reasonable timeout
+        )
+        response.raise_for_status()  # Raise an exception for HTTP errors
+        return response.json()["choices"][0]["message"]["content"]
+    except requests.Timeout:
+        raise TimeoutError("LLM request timed out")
+    except requests.RequestException as e:
+        raise RuntimeError(f"LLM request failed: {str(e)}")
+    except (KeyError, IndexError, ValueError) as e:
+        raise ValueError(f"Invalid response format: {str(e)}")
+```
+
+### 2. Implement Retry Logic for Transient Failures
+
+For transient failures like network issues or rate limiting, implement retry logic with exponential backoff:
+
+```python
+def call(
+    self,
+    messages: Union[str, List[Dict[str, str]]],
+    tools: Optional[List[dict]] = None,
+    callbacks: Optional[List[Any]] = None,
+    available_functions: Optional[Dict[str, Any]] = None,
+) -> Union[str, Any]:
+    import time
+    
+    max_retries = 3
+    retry_delay = 1  # seconds
+    
+    for attempt in range(max_retries):
+        try:
+            response = requests.post(
+                self.endpoint,
+                headers=self.headers,
+                json=self.prepare_payload(messages),
+                timeout=30
+            )
+            response.raise_for_status()
+            return response.json()["choices"][0]["message"]["content"]
+        except (requests.Timeout, requests.ConnectionError) as e:
+            if attempt < max_retries - 1:
+                time.sleep(retry_delay * (2 ** attempt))  # Exponential backoff
+                continue
+            raise TimeoutError(f"LLM request failed after {max_retries} attempts: {str(e)}")
+        except requests.RequestException as e:
+            raise RuntimeError(f"LLM request failed: {str(e)}")
+```
+
+### 3. Validate Input Parameters
+
+Always validate input parameters to prevent runtime errors:
+
+```python
+def __init__(self, api_key: str, endpoint: str):
+    super().__init__()
+    if not api_key or not isinstance(api_key, str):
+        raise ValueError("Invalid API key: must be a non-empty string")
+    if not endpoint or not isinstance(endpoint, str):
+        raise ValueError("Invalid endpoint URL: must be a non-empty string")
+    self.api_key = api_key
+    self.endpoint = endpoint
+```
+
+### 4. Handle Authentication Errors Gracefully
+
+Provide clear error messages for authentication failures:
+
+```python
+def call(
+    self,
+    messages: Union[str, List[Dict[str, str]]],
+    tools: Optional[List[dict]] = None,
+    callbacks: Optional[List[Any]] = None,
+    available_functions: Optional[Dict[str, Any]] = None,
+) -> Union[str, Any]:
+    try:
+        response = requests.post(self.endpoint, headers=self.headers, json=data)
+        if response.status_code == 401:
+            raise ValueError("Authentication failed: Invalid API key or token")
+        elif response.status_code == 403:
+            raise ValueError("Authorization failed: Insufficient permissions")
+        response.raise_for_status()
+        # Process response
+    except Exception as e:
+        # Handle error
+        raise
+```
+
+## Example: JWT-based Authentication
+
+For services that use JWT-based authentication instead of API keys, you can implement a custom LLM like this:
+
+```python
+from crewai import BaseLLM, Agent, Task
+from typing import Any, Dict, List, Optional, Union
+
+class JWTAuthLLM(BaseLLM):
+    def __init__(self, jwt_token: str, endpoint: str):
+        super().__init__()  # Initialize the base class to set default attributes
+        if not jwt_token or not isinstance(jwt_token, str):
+            raise ValueError("Invalid JWT token: must be a non-empty string")
+        if not endpoint or not isinstance(endpoint, str):
+            raise ValueError("Invalid endpoint URL: must be a non-empty string")
+        self.jwt_token = jwt_token
+        self.endpoint = endpoint
+        self.stop = []  # You can customize stop words if needed
+        
+    def call(
+        self,
+        messages: Union[str, List[Dict[str, str]]],
+        tools: Optional[List[dict]] = None,
+        callbacks: Optional[List[Any]] = None,
+        available_functions: Optional[Dict[str, Any]] = None,
+    ) -> Union[str, Any]:
+        """Call the LLM with JWT authentication.
+        
+        Args:
+            messages: Input messages for the LLM.
+            tools: Optional list of tool schemas for function calling.
+            callbacks: Optional list of callback functions.
+            available_functions: Optional dict mapping function names to callables.
+            
+        Returns:
+            Either a text response from the LLM or the result of a tool function call.
+            
+        Raises:
+            TimeoutError: If the LLM request times out.
+            RuntimeError: If the LLM request fails for other reasons.
+            ValueError: If the response format is invalid.
+        """
+        # Implement your own logic to call the LLM with JWT authentication
+        import requests
+        
+        try:
+            headers = {
+                "Authorization": f"Bearer {self.jwt_token}",
+                "Content-Type": "application/json"
+            }
+            
+            # Convert string message to proper format if needed
+            if isinstance(messages, str):
+                messages = [{"role": "user", "content": messages}]
+            
+            data = {
+                "messages": messages,
+                "tools": tools
+            }
+            
+            response = requests.post(
+                self.endpoint,
+                headers=headers,
+                json=data,
+                timeout=30  # Set a reasonable timeout
+            )
+            
+            if response.status_code == 401:
+                raise ValueError("Authentication failed: Invalid JWT token")
+            elif response.status_code == 403:
+                raise ValueError("Authorization failed: Insufficient permissions")
+                
+            response.raise_for_status()  # Raise an exception for HTTP errors
+            return response.json()["choices"][0]["message"]["content"]
+        except requests.Timeout:
+            raise TimeoutError("LLM request timed out")
+        except requests.RequestException as e:
+            raise RuntimeError(f"LLM request failed: {str(e)}")
+        except (KeyError, IndexError, ValueError) as e:
+            raise ValueError(f"Invalid response format: {str(e)}")
+        
+    def supports_function_calling(self) -> bool:
+        """Check if the LLM supports function calling.
+        
+        Returns:
+            True if the LLM supports function calling, False otherwise.
+        """
+        return True
+        
+    def supports_stop_words(self) -> bool:
+        """Check if the LLM supports stop words.
+        
+        Returns:
+            True if the LLM supports stop words, False otherwise.
+        """
+        return True
+        
+    def get_context_window_size(self) -> int:
+        """Get the context window size of the LLM.
+        
+        Returns:
+            The context window size as an integer.
+        """
+        return 8192
+```
+
+## Troubleshooting
+
+Here are some common issues you might encounter when implementing custom LLMs and how to resolve them:
+
+### 1. Authentication Failures
+
+**Symptoms**: 401 Unauthorized or 403 Forbidden errors
+
+**Solutions**:
+- Verify that your API key or JWT token is valid and not expired
+- Check that you're using the correct authentication header format
+- Ensure that your token has the necessary permissions
+
+### 2. Timeout Issues
+
+**Symptoms**: Requests taking too long or timing out
+
+**Solutions**:
+- Implement timeout handling as shown in the examples
+- Use retry logic with exponential backoff
+- Consider using a more reliable network connection
+
+### 3. Response Parsing Errors
+
+**Symptoms**: KeyError, IndexError, or ValueError when processing responses
+
+**Solutions**:
+- Validate the response format before accessing nested fields
+- Implement proper error handling for malformed responses
+- Check the API documentation for the expected response format
+
+### 4. Rate Limiting
+
+**Symptoms**: 429 Too Many Requests errors
+
+**Solutions**:
+- Implement rate limiting in your custom LLM
+- Add exponential backoff for retries
+- Consider using a token bucket algorithm for more precise rate control
+
+## Advanced Features
+
+### Logging
+
+Adding logging to your custom LLM can help with debugging and monitoring:
+
+```python
+import logging
+from typing import Any, Dict, List, Optional, Union
+
+class LoggingLLM(BaseLLM):
+    def __init__(self, api_key: str, endpoint: str):
+        super().__init__()
+        self.api_key = api_key
+        self.endpoint = endpoint
+        self.logger = logging.getLogger("crewai.llm.custom")
+        
+    def call(
+        self,
+        messages: Union[str, List[Dict[str, str]]],
+        tools: Optional[List[dict]] = None,
+        callbacks: Optional[List[Any]] = None,
+        available_functions: Optional[Dict[str, Any]] = None,
+    ) -> Union[str, Any]:
+        self.logger.info(f"Calling LLM with {len(messages) if isinstance(messages, list) else 1} messages")
+        try:
+            # API call implementation
+            response = self._make_api_call(messages, tools)
+            self.logger.debug(f"LLM response received: {response[:100]}...")
+            return response
+        except Exception as e:
+            self.logger.error(f"LLM call failed: {str(e)}")
+            raise
+```
+
+### Rate Limiting
+
+Implementing rate limiting can help avoid overwhelming the LLM API:
+
+```python
+import time
+from typing import Any, Dict, List, Optional, Union
+
+class RateLimitedLLM(BaseLLM):
+    def __init__(
+        self, 
+        api_key: str, 
+        endpoint: str, 
+        requests_per_minute: int = 60
+    ):
+        super().__init__()
+        self.api_key = api_key
+        self.endpoint = endpoint
+        self.requests_per_minute = requests_per_minute
+        self.request_times: List[float] = []
+        
+    def call(
+        self,
+        messages: Union[str, List[Dict[str, str]]],
+        tools: Optional[List[dict]] = None,
+        callbacks: Optional[List[Any]] = None,
+        available_functions: Optional[Dict[str, Any]] = None,
+    ) -> Union[str, Any]:
+        self._enforce_rate_limit()
+        # Record this request time
+        self.request_times.append(time.time())
+        # Make the actual API call
+        return self._make_api_call(messages, tools)
+        
+    def _enforce_rate_limit(self) -> None:
+        """Enforce the rate limit by waiting if necessary."""
+        now = time.time()
+        # Remove request times older than 1 minute
+        self.request_times = [t for t in self.request_times if now - t < 60]
+        
+        if len(self.request_times) >= self.requests_per_minute:
+            # Calculate how long to wait
+            oldest_request = min(self.request_times)
+            wait_time = 60 - (now - oldest_request)
+            if wait_time > 0:
+                time.sleep(wait_time)
+```
+
+### Metrics Collection
+
+Collecting metrics can help you monitor your LLM usage:
+
+```python
+import time
+from typing import Any, Dict, List, Optional, Union
+
+class MetricsCollectingLLM(BaseLLM):
+    def __init__(self, api_key: str, endpoint: str):
+        super().__init__()
+        self.api_key = api_key
+        self.endpoint = endpoint
+        self.metrics: Dict[str, Any] = {
+            "total_calls": 0,
+            "total_tokens": 0,
+            "errors": 0,
+            "latency": []
+        }
+        
+    def call(
+        self,
+        messages: Union[str, List[Dict[str, str]]],
+        tools: Optional[List[dict]] = None,
+        callbacks: Optional[List[Any]] = None,
+        available_functions: Optional[Dict[str, Any]] = None,
+    ) -> Union[str, Any]:
+        start_time = time.time()
+        self.metrics["total_calls"] += 1
+        
+        try:
+            response = self._make_api_call(messages, tools)
+            # Estimate tokens (simplified)
+            if isinstance(messages, str):
+                token_estimate = len(messages) // 4
+            else:
+                token_estimate = sum(len(m.get("content", "")) // 4 for m in messages)
+            self.metrics["total_tokens"] += token_estimate
+            return response
+        except Exception as e:
+            self.metrics["errors"] += 1
+            raise
+        finally:
+            latency = time.time() - start_time
+            self.metrics["latency"].append(latency)
+            
+    def get_metrics(self) -> Dict[str, Any]:
+        """Return the collected metrics."""
+        avg_latency = sum(self.metrics["latency"]) / len(self.metrics["latency"]) if self.metrics["latency"] else 0
+        return {
+            **self.metrics,
+            "avg_latency": avg_latency
+        }
+```
+
+## Advanced Usage: Function Calling
+
+If your LLM supports function calling, you can implement the function calling logic in your custom LLM:
+
+```python
+import json
+from typing import Any, Dict, List, Optional, Union
+
+def call(
+    self,
+    messages: Union[str, List[Dict[str, str]]],
+    tools: Optional[List[dict]] = None,
+    callbacks: Optional[List[Any]] = None,
+    available_functions: Optional[Dict[str, Any]] = None,
+) -> Union[str, Any]:
+    import requests
+    
+    try:
+        headers = {
+            "Authorization": f"Bearer {self.jwt_token}",
+            "Content-Type": "application/json"
+        }
+        
+        # Convert string message to proper format if needed
+        if isinstance(messages, str):
+            messages = [{"role": "user", "content": messages}]
+        
+        data = {
+            "messages": messages,
+            "tools": tools
+        }
+        
+        response = requests.post(
+            self.endpoint,
+            headers=headers,
+            json=data,
+            timeout=30
+        )
+        response.raise_for_status()
+        response_data = response.json()
+        
+        # Check if the LLM wants to call a function
+        if response_data["choices"][0]["message"].get("tool_calls"):
+            tool_calls = response_data["choices"][0]["message"]["tool_calls"]
+            
+            # Process each tool call
+            for tool_call in tool_calls:
+                function_name = tool_call["function"]["name"]
+                function_args = json.loads(tool_call["function"]["arguments"])
+                
+                if available_functions and function_name in available_functions:
+                    function_to_call = available_functions[function_name]
+                    function_response = function_to_call(**function_args)
+                    
+                    # Add the function response to the messages
+                    messages.append({
+                        "role": "tool",
+                        "tool_call_id": tool_call["id"],
+                        "name": function_name,
+                        "content": str(function_response)
+                    })
+            
+            # Call the LLM again with the updated messages
+            return self.call(messages, tools, callbacks, available_functions)
+        
+        # Return the text response if no function call
+        return response_data["choices"][0]["message"]["content"]
+    except requests.Timeout:
+        raise TimeoutError("LLM request timed out")
+    except requests.RequestException as e:
+        raise RuntimeError(f"LLM request failed: {str(e)}")
+    except (KeyError, IndexError, ValueError) as e:
+        raise ValueError(f"Invalid response format: {str(e)}")
+```
+
+## Using Your Custom LLM with CrewAI
+
+Once you've implemented your custom LLM, you can use it with CrewAI agents and crews:
+
+```python
+from crewai import Agent, Task, Crew
+from typing import Dict, Any
+
+# Create your custom LLM instance
+jwt_llm = JWTAuthLLM(
+    jwt_token="your.jwt.token", 
+    endpoint="https://your-llm-endpoint.com/v1/chat/completions"
+)
+
+# Use it with an agent
+agent = Agent(
+    role="Research Assistant",
+    goal="Find information on a topic",
+    backstory="You are a research assistant tasked with finding information.",
+    llm=jwt_llm,
+)
+
+# Create a task for the agent
+task = Task(
+    description="Research the benefits of exercise",
+    agent=agent,
+    expected_output="A summary of the benefits of exercise",
+)
+
+# Execute the task
+result = agent.execute_task(task)
+print(result)
+
+# Or use it with a crew
+crew = Crew(
+    agents=[agent],
+    tasks=[task],
+    manager_llm=jwt_llm,  # Use your custom LLM for the manager
+)
+
+# Run the crew
+result = crew.kickoff()
+print(result)
+```
+
+## Implementing Your Own Authentication Mechanism
+
+The `BaseLLM` class allows you to implement any authentication mechanism you need, not just JWT or API keys. You can use:
+
+- OAuth tokens
+- Client certificates
+- Custom headers
+- Session-based authentication
+- Any other authentication method required by your LLM provider
+
+Simply implement the appropriate authentication logic in your custom LLM class.

docs/docs.json

@@ -97,13 +97,19 @@
               "how-to/kickoff-async",
               "how-to/kickoff-for-each",
               "how-to/replay-tasks-from-latest-crew-kickoff",
-              "how-to/conditional-tasks",
+              "how-to/conditional-tasks"
+            ]
+          },
+          {
+            "group": "Agent Monitoring & Observability",
+            "pages": [
+              "how-to/weave-integration",
               "how-to/agentops-observability",
+              "how-to/langfuse-observability",
               "how-to/langtrace-observability",
               "how-to/mlflow-observability",
               "how-to/openlit-observability",
-              "how-to/portkey-observability",
-              "how-to/langfuse-observability"
+              "how-to/portkey-observability"
             ]
           },
           {
@@ -111,6 +117,8 @@
             "pages": [
               "tools/aimindtool",
               "tools/apifyactorstool",
+              "tools/bedrockinvokeagenttool",
+              "tools/bedrockkbretriever",
               "tools/bravesearchtool",
               "tools/browserbaseloadtool",
               "tools/codedocssearchtool",

docs/how-to/agentops-observability.mdx

@@ -1,5 +1,5 @@
 ---
-title: Agent Monitoring with AgentOps
+title: AgentOps Integration
 description: Understanding and logging your agent performance with AgentOps.
 icon: paperclip
 ---

docs/how-to/kickoff-for-each.mdx

@@ -39,8 +39,7 @@ analysis_crew = Crew(
     agents=[coding_agent],
     tasks=[data_analysis_task],
     verbose=True,
-    memory=False,
-    respect_context_window=True  # enable by default
+    memory=False
 )
 
 datasets = [

docs/how-to/langfuse-observability.mdx

@@ -1,7 +1,7 @@
 ---
-title: Agent Monitoring with Langfuse
+title: Langfuse Integration
 description: Learn how to integrate Langfuse with CrewAI via OpenTelemetry using OpenLit
-icon: magnifying-glass-chart
+icon: vials
 ---
 
 # Integrate Langfuse with CrewAI

docs/how-to/langtrace-observability.mdx

@@ -1,5 +1,5 @@
 ---
-title: Agent Monitoring with Langtrace
+title: Langtrace Integration
 description: How to monitor cost, latency, and performance of CrewAI Agents using Langtrace, an external observability tool.
 icon: chart-line
 ---

docs/how-to/mlflow-observability.mdx

@@ -1,5 +1,5 @@
 ---
-title: Agent Monitoring with MLflow
+title: MLflow Integration
 description: Quickly start monitoring your Agents with MLflow.
 icon: bars-staggered
 ---

docs/how-to/openlit-observability.mdx

@@ -1,5 +1,5 @@
 ---
-title: Agent Monitoring with OpenLIT
+title: OpenLIT Integration
 description: Quickly start monitoring your Agents in just a single line of code with OpenTelemetry.
 icon: magnifying-glass-chart
 ---

docs/how-to/portkey-observability.mdx

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

docs/how-to/weave-integration.mdx

@@ -0,0 +1,124 @@
+---
+title: Weave Integration
+description: Learn how to use Weights & Biases (W&B) Weave to track, experiment with, evaluate, and improve your CrewAI applications.
+icon: radar
+---
+
+# Weave Overview
+
+[Weights & Biases (W&B) Weave](https://weave-docs.wandb.ai/) is a framework for tracking, experimenting with, evaluating, deploying, and improving LLM-based applications. 
+
+![Overview of W&B Weave CrewAI tracing usage](/images/weave-tracing.gif)
+
+Weave provides comprehensive support for every stage of your CrewAI application development:
+
+- **Tracing & Monitoring**: Automatically track LLM calls and application logic to debug and analyze production systems
+- **Systematic Iteration**: Refine and iterate on prompts, datasets, and models
+- **Evaluation**: Use custom or pre-built scorers to systematically assess and enhance agent performance
+- **Guardrails**: Protect your agents with pre- and post-safeguards for content moderation and prompt safety
+
+Weave automatically captures traces for your CrewAI applications, enabling you to monitor and analyze your agents' performance, interactions, and execution flow. This helps you build better evaluation datasets and optimize your agent workflows.
+
+## Setup Instructions
+
+<Steps>
+    <Step title="Install required packages">
+      ```shell
+      pip install crewai weave
+      ```
+    </Step>
+    <Step title="Set up W&B Account">
+      Sign up for a [Weights & Biases account](https://wandb.ai) if you haven't already. You'll need this to view your traces and metrics.
+    </Step>
+    <Step title="Initialize Weave in Your Application">
+      Add the following code to your application:
+
+      ```python
+      import weave
+
+      # Initialize Weave with your project name
+      weave.init(project_name="crewai_demo")
+      ```
+      
+      After initialization, Weave will provide a URL where you can view your traces and metrics.
+    </Step>
+    <Step title="Create your Crews/Flows">
+      ```python
+      from crewai import Agent, Task, Crew, LLM, Process
+
+      # Create an LLM with a temperature of 0 to ensure deterministic outputs
+      llm = LLM(model="gpt-4o", temperature=0)
+
+      # Create agents
+      researcher = Agent(
+          role='Research Analyst',
+          goal='Find and analyze the best investment opportunities',
+          backstory='Expert in financial analysis and market research',
+          llm=llm,
+          verbose=True,
+          allow_delegation=False,
+      )
+
+      writer = Agent(
+          role='Report Writer',
+          goal='Write clear and concise investment reports',
+          backstory='Experienced in creating detailed financial reports',
+          llm=llm,
+          verbose=True,
+          allow_delegation=False,
+      )
+
+      # Create tasks
+      research_task = Task(
+          description='Deep research on the {topic}',
+          expected_output='Comprehensive market data including key players, market size, and growth trends.',
+          agent=researcher
+      )
+
+      writing_task = Task(
+          description='Write a detailed report based on the research',
+          expected_output='The report should be easy to read and understand. Use bullet points where applicable.',
+          agent=writer
+      )
+
+      # Create a crew
+      crew = Crew(
+          agents=[researcher, writer],
+          tasks=[research_task, writing_task],
+          verbose=True,
+          process=Process.sequential,
+      )
+
+      # Run the crew
+      result = crew.kickoff(inputs={"topic": "AI in material science"})
+      print(result)
+      ```
+    </Step>
+    <Step title="View Traces in Weave">
+      After running your CrewAI application, visit the Weave URL provided during initialization to view:
+      - LLM calls and their metadata
+      - Agent interactions and task execution flow
+      - Performance metrics like latency and token usage
+      - Any errors or issues that occurred during execution
+
+      <Frame caption="Weave Tracing Dashboard">
+        <img src="/images/weave-tracing.png" alt="Weave tracing example with CrewAI" />
+      </Frame>
+    </Step>
+</Steps>
+
+## Features
+
+- Weave automatically captures all CrewAI operations: agent interactions and task executions; LLM calls with metadata and token usage; tool usage and results.
+- The integration supports all CrewAI execution methods: `kickoff()`, `kickoff_for_each()`, `kickoff_async()`, and `kickoff_for_each_async()`.
+- Automatic tracing of all [crewAI-tools](https://github.com/crewAIInc/crewAI-tools).
+- Flow feature support with decorator patching (`@start`, `@listen`, `@router`, `@or_`, `@and_`).
+- Track custom guardrails passed to CrewAI `Task` with `@weave.op()`.
+
+For detailed information on what's supported, visit the [Weave CrewAI documentation](https://weave-docs.wandb.ai/guides/integrations/crewai/#getting-started-with-flow).
+
+## Resources
+
+- [📘 Weave Documentation](https://weave-docs.wandb.ai)
+- [📊 Example Weave x CrewAI dashboard](https://wandb.ai/ayut/crewai_demo/weave/traces?cols=%7B%22wb_run_id%22%3Afalse%2C%22attributes.weave.client_version%22%3Afalse%2C%22attributes.weave.os_name%22%3Afalse%2C%22attributes.weave.os_release%22%3Afalse%2C%22attributes.weave.os_version%22%3Afalse%2C%22attributes.weave.source%22%3Afalse%2C%22attributes.weave.sys_version%22%3Afalse%7D&peekPath=%2Fayut%2Fcrewai_demo%2Fcalls%2F0195c838-38cb-71a2-8a15-651ecddf9d89)
+- [🐦 X](https://x.com/weave_wb)

docs/quickstart.mdx

@@ -300,7 +300,7 @@ email_summarizer:
 ```
 
 <Tip>
-  Note how we use the same name for the agent in the `tasks.yaml` (`email_summarizer_task`) file as the method name in the `crew.py` (`email_summarizer_task`) file.
+  Note how we use the same name for the task in the `tasks.yaml` (`email_summarizer_task`) file as the method name in the `crew.py` (`email_summarizer_task`) file.
 </Tip>
 
 ```yaml tasks.yaml

docs/tools/bedrockinvokeagenttool.mdx

@@ -0,0 +1,187 @@
+---
+title: Bedrock Invoke Agent Tool
+description: Enables CrewAI agents to invoke Amazon Bedrock Agents and leverage their capabilities within your workflows
+icon: aws
+---
+
+# `BedrockInvokeAgentTool`
+
+The `BedrockInvokeAgentTool` enables CrewAI agents to invoke Amazon Bedrock Agents and leverage their capabilities within your workflows.
+
+## Installation
+
+```bash
+uv pip install 'crewai[tools]'
+```
+
+## Requirements
+
+- AWS credentials configured (either through environment variables or AWS CLI)
+- `boto3` and `python-dotenv` packages
+- Access to Amazon Bedrock Agents
+
+## Usage
+
+Here's how to use the tool with a CrewAI agent:
+
+```python {2, 4-8}
+from crewai import Agent, Task, Crew
+from crewai_tools.aws.bedrock.agents.invoke_agent_tool import BedrockInvokeAgentTool
+
+# Initialize the tool
+agent_tool = BedrockInvokeAgentTool(
+    agent_id="your-agent-id",
+    agent_alias_id="your-agent-alias-id"
+)
+
+# Create a CrewAI agent that uses the tool
+aws_expert = Agent(
+    role='AWS Service Expert',
+    goal='Help users understand AWS services and quotas',
+    backstory='I am an expert in AWS services and can provide detailed information about them.',
+    tools=[agent_tool],
+    verbose=True
+)
+
+# Create a task for the agent
+quota_task = Task(
+    description="Find out the current service quotas for EC2 in us-west-2 and explain any recent changes.",
+    agent=aws_expert
+)
+
+# Create a crew with the agent
+crew = Crew(
+    agents=[aws_expert],
+    tasks=[quota_task],
+    verbose=2
+)
+
+# Run the crew
+result = crew.kickoff()
+print(result)
+```
+
+## Tool Arguments
+
+| Argument | Type | Required | Default | Description |
+|:---------|:-----|:---------|:--------|:------------|
+| **agent_id** | `str` | Yes | None | The unique identifier of the Bedrock agent |
+| **agent_alias_id** | `str` | Yes | None | The unique identifier of the agent alias |
+| **session_id** | `str` | No | timestamp | The unique identifier of the session |
+| **enable_trace** | `bool` | No | False | Whether to enable trace for debugging |
+| **end_session** | `bool` | No | False | Whether to end the session after invocation |
+| **description** | `str` | No | None | Custom description for the tool |
+
+## Environment Variables
+
+```bash
+BEDROCK_AGENT_ID=your-agent-id           # Alternative to passing agent_id
+BEDROCK_AGENT_ALIAS_ID=your-agent-alias-id # Alternative to passing agent_alias_id
+AWS_REGION=your-aws-region               # Defaults to us-west-2
+AWS_ACCESS_KEY_ID=your-access-key        # Required for AWS authentication
+AWS_SECRET_ACCESS_KEY=your-secret-key    # Required for AWS authentication
+```
+
+## Advanced Usage
+
+### Multi-Agent Workflow with Session Management
+
+```python {2, 4-22}
+from crewai import Agent, Task, Crew, Process
+from crewai_tools.aws.bedrock.agents.invoke_agent_tool import BedrockInvokeAgentTool
+
+# Initialize tools with session management
+initial_tool = BedrockInvokeAgentTool(
+    agent_id="your-agent-id",
+    agent_alias_id="your-agent-alias-id",
+    session_id="custom-session-id"
+)
+
+followup_tool = BedrockInvokeAgentTool(
+    agent_id="your-agent-id",
+    agent_alias_id="your-agent-alias-id",
+    session_id="custom-session-id"
+)
+
+final_tool = BedrockInvokeAgentTool(
+    agent_id="your-agent-id",
+    agent_alias_id="your-agent-alias-id",
+    session_id="custom-session-id",
+    end_session=True
+)
+
+# Create agents for different stages
+researcher = Agent(
+    role='AWS Service Researcher',
+    goal='Gather information about AWS services',
+    backstory='I am specialized in finding detailed AWS service information.',
+    tools=[initial_tool]
+)
+
+analyst = Agent(
+    role='Service Compatibility Analyst',
+    goal='Analyze service compatibility and requirements',
+    backstory='I analyze AWS services for compatibility and integration possibilities.',
+    tools=[followup_tool]
+)
+
+summarizer = Agent(
+    role='Technical Documentation Writer',
+    goal='Create clear technical summaries',
+    backstory='I specialize in creating clear, concise technical documentation.',
+    tools=[final_tool]
+)
+
+# Create tasks
+research_task = Task(
+    description="Find all available AWS services in us-west-2 region.",
+    agent=researcher
+)
+
+analysis_task = Task(
+    description="Analyze which services support IPv6 and their implementation requirements.",
+    agent=analyst
+)
+
+summary_task = Task(
+    description="Create a summary of IPv6-compatible services and their key features.",
+    agent=summarizer
+)
+
+# Create a crew with the agents and tasks
+crew = Crew(
+    agents=[researcher, analyst, summarizer],
+    tasks=[research_task, analysis_task, summary_task],
+    process=Process.sequential,
+    verbose=2
+)
+
+# Run the crew
+result = crew.kickoff()
+```
+
+## Use Cases
+
+### Hybrid Multi-Agent Collaborations
+- Create workflows where CrewAI agents collaborate with managed Bedrock agents running as services in AWS
+- Enable scenarios where sensitive data processing happens within your AWS environment while other agents operate externally
+- Bridge on-premises CrewAI agents with cloud-based Bedrock agents for distributed intelligence workflows
+
+### Data Sovereignty and Compliance
+- Keep data-sensitive agentic workflows within your AWS environment while allowing external CrewAI agents to orchestrate tasks
+- Maintain compliance with data residency requirements by processing sensitive information only within your AWS account
+- Enable secure multi-agent collaborations where some agents cannot access your organization's private data
+
+### Seamless AWS Service Integration
+- Access any AWS service through Amazon Bedrock Actions without writing complex integration code
+- Enable CrewAI agents to interact with AWS services through natural language requests
+- Leverage pre-built Bedrock agent capabilities to interact with AWS services like Bedrock Knowledge Bases, Lambda, and more
+
+### Scalable Hybrid Agent Architectures
+- Offload computationally intensive tasks to managed Bedrock agents while lightweight tasks run in CrewAI
+- Scale agent processing by distributing workloads between local CrewAI agents and cloud-based Bedrock agents
+
+### Cross-Organizational Agent Collaboration
+- Enable secure collaboration between your organization's CrewAI agents and partner organizations' Bedrock agents
+- Create workflows where external expertise from Bedrock agents can be incorporated without exposing sensitive data
+- Build agent ecosystems that span organizational boundaries while maintaining security and data control

docs/tools/bedrockkbretriever.mdx

@@ -0,0 +1,165 @@
+---
+title: 'Bedrock Knowledge Base Retriever'
+description: 'Retrieve information from Amazon Bedrock Knowledge Bases using natural language queries'
+icon: aws
+---
+
+# `BedrockKBRetrieverTool`
+
+The `BedrockKBRetrieverTool` enables CrewAI agents to retrieve information from Amazon Bedrock Knowledge Bases using natural language queries.
+
+## Installation
+
+```bash
+uv pip install 'crewai[tools]'
+```
+
+## Requirements
+
+- AWS credentials configured (either through environment variables or AWS CLI)
+- `boto3` and `python-dotenv` packages
+- Access to Amazon Bedrock Knowledge Base
+
+## Usage
+
+Here's how to use the tool with a CrewAI agent:
+
+```python {2, 4-17}
+from crewai import Agent, Task, Crew
+from crewai_tools.aws.bedrock.knowledge_base.retriever_tool import BedrockKBRetrieverTool
+
+# Initialize the tool
+kb_tool = BedrockKBRetrieverTool(
+    knowledge_base_id="your-kb-id",
+    number_of_results=5
+)
+
+# Create a CrewAI agent that uses the tool
+researcher = Agent(
+    role='Knowledge Base Researcher',
+    goal='Find information about company policies',
+    backstory='I am a researcher specialized in retrieving and analyzing company documentation.',
+    tools=[kb_tool],
+    verbose=True
+)
+
+# Create a task for the agent
+research_task = Task(
+    description="Find our company's remote work policy and summarize the key points.",
+    agent=researcher
+)
+
+# Create a crew with the agent
+crew = Crew(
+    agents=[researcher],
+    tasks=[research_task],
+    verbose=2
+)
+
+# Run the crew
+result = crew.kickoff()
+print(result)   
+```
+
+## Tool Arguments
+
+| Argument | Type | Required | Default | Description |
+|:---------|:-----|:---------|:---------|:-------------|
+| **knowledge_base_id** | `str` | Yes | None | The unique identifier of the knowledge base (0-10 alphanumeric characters) |
+| **number_of_results** | `int` | No | 5 | Maximum number of results to return |
+| **retrieval_configuration** | `dict` | No | None | Custom configurations for the knowledge base query |
+| **guardrail_configuration** | `dict` | No | None | Content filtering settings |
+| **next_token** | `str` | No | None | Token for pagination |
+
+## Environment Variables
+
+```bash
+BEDROCK_KB_ID=your-knowledge-base-id  # Alternative to passing knowledge_base_id
+AWS_REGION=your-aws-region            # Defaults to us-east-1
+AWS_ACCESS_KEY_ID=your-access-key     # Required for AWS authentication
+AWS_SECRET_ACCESS_KEY=your-secret-key # Required for AWS authentication
+```
+
+## Response Format
+
+The tool returns results in JSON format:
+
+```json
+{
+  "results": [
+    {
+      "content": "Retrieved text content",
+      "content_type": "text",
+      "source_type": "S3",
+      "source_uri": "s3://bucket/document.pdf",
+      "score": 0.95,
+      "metadata": {
+        "additional": "metadata"
+      }
+    }
+  ],
+  "nextToken": "pagination-token",
+  "guardrailAction": "NONE"
+}
+```
+
+## Advanced Usage
+
+### Custom Retrieval Configuration
+
+```python
+kb_tool = BedrockKBRetrieverTool(
+    knowledge_base_id="your-kb-id",
+    retrieval_configuration={
+        "vectorSearchConfiguration": {
+            "numberOfResults": 10,
+            "overrideSearchType": "HYBRID"
+        }
+    }
+)
+
+policy_expert = Agent(
+    role='Policy Expert',
+    goal='Analyze company policies in detail',
+    backstory='I am an expert in corporate policy analysis with deep knowledge of regulatory requirements.',
+    tools=[kb_tool]
+)
+```
+
+## Supported Data Sources
+
+- Amazon S3
+- Confluence
+- Salesforce
+- SharePoint
+- Web pages
+- Custom document locations
+- Amazon Kendra
+- SQL databases    
+
+## Use Cases
+
+### Enterprise Knowledge Integration
+- Enable CrewAI agents to access your organization's proprietary knowledge without exposing sensitive data
+- Allow agents to make decisions based on your company's specific policies, procedures, and documentation
+- Create agents that can answer questions based on your internal documentation while maintaining data security
+
+### Specialized Domain Knowledge
+- Connect CrewAI agents to domain-specific knowledge bases (legal, medical, technical) without retraining models
+- Leverage existing knowledge repositories that are already maintained in your AWS environment
+- Combine CrewAI's reasoning with domain-specific information from your knowledge bases
+
+### Data-Driven Decision Making
+- Ground CrewAI agent responses in your actual company data rather than general knowledge
+- Ensure agents provide recommendations based on your specific business context and documentation
+- Reduce hallucinations by retrieving factual information from your knowledge bases
+
+### Scalable Information Access
+- Access terabytes of organizational knowledge without embedding it all into your models
+- Dynamically query only the relevant information needed for specific tasks
+- Leverage AWS's scalable infrastructure to handle large knowledge bases efficiently
+
+### Compliance and Governance
+- Ensure CrewAI agents provide responses that align with your company's approved documentation
+- Create auditable trails of information sources used by your agents
+- Maintain control over what information sources your agents can access

pyproject.toml

@@ -17,9 +17,9 @@ dependencies = [
     "pdfplumber>=0.11.4",
     "regex>=2024.9.11",
     # Telemetry and Monitoring
-    "opentelemetry-api>=1.22.0",
-    "opentelemetry-sdk>=1.22.0",
-    "opentelemetry-exporter-otlp-proto-http>=1.22.0",
+    "opentelemetry-api>=1.30.0",
+    "opentelemetry-sdk>=1.30.0",
+    "opentelemetry-exporter-otlp-proto-http>=1.30.0",
     # Data Handling
     "chromadb>=0.5.23",
     "openpyxl>=3.1.5",
@@ -64,6 +64,9 @@ mem0 = ["mem0ai>=0.1.29"]
 docling = [
     "docling>=2.12.0",
 ]
+aisuite = [
+    "aisuite>=0.1.10",
+]
 
 [tool.uv]
 dev-dependencies = [

src/crewai/__init__.py

@@ -5,6 +5,7 @@ from crewai.crew import Crew
 from crewai.flow.flow import Flow
 from crewai.knowledge.knowledge import Knowledge
 from crewai.llm import LLM
+from crewai.llms.base_llm import BaseLLM
 from crewai.process import Process
 from crewai.task import Task
 
@@ -21,6 +22,7 @@ __all__ = [
     "Process",
     "Task",
     "LLM",
+    "BaseLLM",
     "Flow",
     "Knowledge",
 ]

src/crewai/agent.py

@@ -11,7 +11,7 @@ from crewai.agents.crew_agent_executor import CrewAgentExecutor
 from crewai.knowledge.knowledge import Knowledge
 from crewai.knowledge.source.base_knowledge_source import BaseKnowledgeSource
 from crewai.knowledge.utils.knowledge_utils import extract_knowledge_context
-from crewai.llm import LLM
+from crewai.llm import BaseLLM
 from crewai.memory.contextual.contextual_memory import ContextualMemory
 from crewai.security import Fingerprint
 from crewai.task import Task
@@ -71,10 +71,10 @@ class Agent(BaseAgent):
         default=True,
         description="Use system prompt for the agent.",
     )
-    llm: Union[str, InstanceOf[LLM], Any] = Field(
+    llm: Union[str, InstanceOf[BaseLLM], Any] = Field(
         description="Language model that will run the agent.", default=None
     )
-    function_calling_llm: Optional[Union[str, InstanceOf[LLM], Any]] = Field(
+    function_calling_llm: Optional[Union[str, InstanceOf[BaseLLM], Any]] = Field(
         description="Language model that will run the agent.", default=None
     )
     system_template: Optional[str] = Field(
@@ -118,7 +118,9 @@ class Agent(BaseAgent):
         self.agent_ops_agent_name = self.role
 
         self.llm = create_llm(self.llm)
-        if self.function_calling_llm and not isinstance(self.function_calling_llm, LLM):
+        if self.function_calling_llm and not isinstance(
+            self.function_calling_llm, BaseLLM
+        ):
             self.function_calling_llm = create_llm(self.function_calling_llm)
 
         if not self.agent_executor:

src/crewai/agents/agent_builder/base_agent.py

@@ -25,6 +25,7 @@ from crewai.tools.base_tool import BaseTool, Tool
 from crewai.utilities import I18N, Logger, RPMController
 from crewai.utilities.config import process_config
 from crewai.utilities.converter import Converter
+from crewai.utilities.string_utils import interpolate_only
 
 T = TypeVar("T", bound="BaseAgent")
 
@@ -333,9 +334,15 @@ class BaseAgent(ABC, BaseModel):
             self._original_backstory = self.backstory
 
         if inputs:
-            self.role = self._original_role.format(**inputs)
-            self.goal = self._original_goal.format(**inputs)
-            self.backstory = self._original_backstory.format(**inputs)
+            self.role = interpolate_only(
+                input_string=self._original_role, inputs=inputs
+            )
+            self.goal = interpolate_only(
+                input_string=self._original_goal, inputs=inputs
+            )
+            self.backstory = interpolate_only(
+                input_string=self._original_backstory, inputs=inputs
+            )
 
     def set_cache_handler(self, cache_handler: CacheHandler) -> None:
         """Set the cache handler for the agent.

src/crewai/agents/crew_agent_executor.py

@@ -13,7 +13,7 @@ from crewai.agents.parser import (
     OutputParserException,
 )
 from crewai.agents.tools_handler import ToolsHandler
-from crewai.llm import LLM
+from crewai.llm import BaseLLM
 from crewai.tools.base_tool import BaseTool
 from crewai.tools.tool_usage import ToolUsage, ToolUsageErrorException
 from crewai.utilities import I18N, Printer
@@ -61,7 +61,7 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
         callbacks: List[Any] = [],
     ):
         self._i18n: I18N = I18N()
-        self.llm: LLM = llm
+        self.llm: BaseLLM = llm
         self.task = task
         self.agent = agent
         self.crew = crew
@@ -87,8 +87,14 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
         self.tool_name_to_tool_map: Dict[str, BaseTool] = {
             tool.name: tool for tool in self.tools
         }
-        self.stop = stop_words
-        self.llm.stop = list(set(self.llm.stop + self.stop))
+        existing_stop = self.llm.stop or []
+        self.llm.stop = list(
+            set(
+                existing_stop + self.stop
+                if isinstance(existing_stop, list)
+                else self.stop
+            )
+        )
 
     def invoke(self, inputs: Dict[str, str]) -> Dict[str, Any]:
         if "system" in self.prompt:

src/crewai/agents/parser.py

@@ -136,7 +136,7 @@ class CrewAgentParser:
 
     def _clean_action(self, text: str) -> str:
         """Clean action string by removing non-essential formatting characters."""
-        return re.sub(r"^\s*\*+\s*|\s*\*+\s*$", "", text).strip()
+        return text.strip().strip("*").strip()
 
     def _safe_repair_json(self, tool_input: str) -> str:
         UNABLE_TO_REPAIR_JSON_RESULTS = ['""', "{}"]

src/crewai/cli/crew_chat.py

@@ -14,7 +14,7 @@ from packaging import version
 from crewai.cli.utils import read_toml
 from crewai.cli.version import get_crewai_version
 from crewai.crew import Crew
-from crewai.llm import LLM
+from crewai.llm import LLM, BaseLLM
 from crewai.types.crew_chat import ChatInputField, ChatInputs
 from crewai.utilities.llm_utils import create_llm
 
@@ -116,7 +116,7 @@ def show_loading(event: threading.Event):
     print()
 
 
-def initialize_chat_llm(crew: Crew) -> Optional[LLM]:
+def initialize_chat_llm(crew: Crew) -> Optional[LLM | BaseLLM]:
     """Initializes the chat LLM and handles exceptions."""
     try:
         return create_llm(crew.chat_llm)

src/crewai/cli/git.py

@@ -1,4 +1,5 @@
 import subprocess
+from functools import lru_cache
 
 
 class Repository:
@@ -35,6 +36,7 @@ class Repository:
             encoding="utf-8",
         ).strip()
 
+    @lru_cache(maxsize=None)
     def is_git_repo(self) -> bool:
         """Check if the current directory is a git repository."""
         try:

src/crewai/crew.py

@@ -6,8 +6,9 @@ import warnings
 from concurrent.futures import Future
 from copy import copy as shallow_copy
 from hashlib import md5
-from typing import Any, Callable, Dict, List, Optional, Set, Tuple, Union
+from typing import Any, Callable, Dict, List, Optional, Set, Tuple, TypeVar, Union, cast
 
+from langchain_core.tools import BaseTool as LangchainBaseTool
 from pydantic import (
     UUID4,
     BaseModel,
@@ -26,7 +27,7 @@ from crewai.agents.cache import CacheHandler
 from crewai.crews.crew_output import CrewOutput
 from crewai.knowledge.knowledge import Knowledge
 from crewai.knowledge.source.base_knowledge_source import BaseKnowledgeSource
-from crewai.llm import LLM
+from crewai.llm import LLM, BaseLLM
 from crewai.memory.entity.entity_memory import EntityMemory
 from crewai.memory.long_term.long_term_memory import LongTermMemory
 from crewai.memory.short_term.short_term_memory import ShortTermMemory
@@ -37,7 +38,7 @@ from crewai.task import Task
 from crewai.tasks.conditional_task import ConditionalTask
 from crewai.tasks.task_output import TaskOutput
 from crewai.tools.agent_tools.agent_tools import AgentTools
-from crewai.tools.base_tool import Tool
+from crewai.tools.base_tool import BaseTool, Tool
 from crewai.types.usage_metrics import UsageMetrics
 from crewai.utilities import I18N, FileHandler, Logger, RPMController
 from crewai.utilities.constants import TRAINING_DATA_FILE
@@ -153,7 +154,7 @@ class Crew(BaseModel):
         default=None,
         description="Metrics for the LLM usage during all tasks execution.",
     )
-    manager_llm: Optional[Any] = Field(
+    manager_llm: Optional[Union[str, InstanceOf[BaseLLM], Any]] = Field(
         description="Language model that will run the agent.", default=None
     )
     manager_agent: Optional[BaseAgent] = Field(
@@ -187,7 +188,7 @@ class Crew(BaseModel):
         default=None,
         description="Maximum number of requests per minute for the crew execution to be respected.",
     )
-    prompt_file: str = Field(
+    prompt_file: Optional[str] = Field(
         default=None,
         description="Path to the prompt json file to be used for the crew.",
     )
@@ -199,7 +200,7 @@ class Crew(BaseModel):
         default=False,
         description="Plan the crew execution and add the plan to the crew.",
     )
-    planning_llm: Optional[Any] = Field(
+    planning_llm: Optional[Union[str, InstanceOf[BaseLLM], Any]] = Field(
         default=None,
         description="Language model that will run the AgentPlanner if planning is True.",
     )
@@ -215,7 +216,7 @@ class Crew(BaseModel):
         default=None,
         description="Knowledge sources for the crew. Add knowledge sources to the knowledge object.",
     )
-    chat_llm: Optional[Any] = Field(
+    chat_llm: Optional[Union[str, InstanceOf[BaseLLM], Any]] = Field(
         default=None,
         description="LLM used to handle chatting with the crew.",
     )
@@ -819,7 +820,12 @@ class Crew(BaseModel):
 
             # Determine which tools to use - task tools take precedence over agent tools
             tools_for_task = task.tools or agent_to_use.tools or []
-            tools_for_task = self._prepare_tools(agent_to_use, task, tools_for_task)
+            # Prepare tools and ensure they're compatible with task execution
+            tools_for_task = self._prepare_tools(
+                agent_to_use,
+                task,
+                cast(Union[List[Tool], List[BaseTool]], tools_for_task),
+            )
 
             self._log_task_start(task, agent_to_use.role)
 
@@ -838,7 +844,7 @@ class Crew(BaseModel):
                 future = task.execute_async(
                     agent=agent_to_use,
                     context=context,
-                    tools=tools_for_task,
+                    tools=cast(List[BaseTool], tools_for_task),
                 )
                 futures.append((task, future, task_index))
             else:
@@ -850,7 +856,7 @@ class Crew(BaseModel):
                 task_output = task.execute_sync(
                     agent=agent_to_use,
                     context=context,
-                    tools=tools_for_task,
+                    tools=cast(List[BaseTool], tools_for_task),
                 )
                 task_outputs.append(task_output)
                 self._process_task_result(task, task_output)
@@ -888,10 +894,12 @@ class Crew(BaseModel):
         return None
 
     def _prepare_tools(
-        self, agent: BaseAgent, task: Task, tools: List[Tool]
-    ) -> List[Tool]:
+        self, agent: BaseAgent, task: Task, tools: Union[List[Tool], List[BaseTool]]
+    ) -> List[BaseTool]:
         # Add delegation tools if agent allows delegation
-        if agent.allow_delegation:
+        if hasattr(agent, "allow_delegation") and getattr(
+            agent, "allow_delegation", False
+        ):
             if self.process == Process.hierarchical:
                 if self.manager_agent:
                     tools = self._update_manager_tools(task, tools)
@@ -900,17 +908,24 @@ class Crew(BaseModel):
                         "Manager agent is required for hierarchical process."
                     )
 
-            elif agent and agent.allow_delegation:
+            elif agent:
                 tools = self._add_delegation_tools(task, tools)
 
         # Add code execution tools if agent allows code execution
-        if agent.allow_code_execution:
+        if hasattr(agent, "allow_code_execution") and getattr(
+            agent, "allow_code_execution", False
+        ):
             tools = self._add_code_execution_tools(agent, tools)
 
-        if agent and agent.multimodal:
+        if (
+            agent
+            and hasattr(agent, "multimodal")
+            and getattr(agent, "multimodal", False)
+        ):
             tools = self._add_multimodal_tools(agent, tools)
 
-        return tools
+        # Return a List[BaseTool] which is compatible with both Task.execute_sync and Task.execute_async
+        return cast(List[BaseTool], tools)
 
     def _get_agent_to_use(self, task: Task) -> Optional[BaseAgent]:
         if self.process == Process.hierarchical:
@@ -918,11 +933,13 @@ class Crew(BaseModel):
         return task.agent
 
     def _merge_tools(
-        self, existing_tools: List[Tool], new_tools: List[Tool]
-    ) -> List[Tool]:
+        self,
+        existing_tools: Union[List[Tool], List[BaseTool]],
+        new_tools: Union[List[Tool], List[BaseTool]],
+    ) -> List[BaseTool]:
         """Merge new tools into existing tools list, avoiding duplicates by tool name."""
         if not new_tools:
-            return existing_tools
+            return cast(List[BaseTool], existing_tools)
 
         # Create mapping of tool names to new tools
         new_tool_map = {tool.name: tool for tool in new_tools}
@@ -933,23 +950,41 @@ class Crew(BaseModel):
         # Add all new tools
         tools.extend(new_tools)
 
-        return tools
+        return cast(List[BaseTool], tools)
 
     def _inject_delegation_tools(
-        self, tools: List[Tool], task_agent: BaseAgent, agents: List[BaseAgent]
-    ):
-        delegation_tools = task_agent.get_delegation_tools(agents)
-        return self._merge_tools(tools, delegation_tools)
+        self,
+        tools: Union[List[Tool], List[BaseTool]],
+        task_agent: BaseAgent,
+        agents: List[BaseAgent],
+    ) -> List[BaseTool]:
+        if hasattr(task_agent, "get_delegation_tools"):
+            delegation_tools = task_agent.get_delegation_tools(agents)
+            # Cast delegation_tools to the expected type for _merge_tools
+            return self._merge_tools(tools, cast(List[BaseTool], delegation_tools))
+        return cast(List[BaseTool], tools)
 
-    def _add_multimodal_tools(self, agent: BaseAgent, tools: List[Tool]):
-        multimodal_tools = agent.get_multimodal_tools()
-        return self._merge_tools(tools, multimodal_tools)
+    def _add_multimodal_tools(
+        self, agent: BaseAgent, tools: Union[List[Tool], List[BaseTool]]
+    ) -> List[BaseTool]:
+        if hasattr(agent, "get_multimodal_tools"):
+            multimodal_tools = agent.get_multimodal_tools()
+            # Cast multimodal_tools to the expected type for _merge_tools
+            return self._merge_tools(tools, cast(List[BaseTool], multimodal_tools))
+        return cast(List[BaseTool], tools)
 
-    def _add_code_execution_tools(self, agent: BaseAgent, tools: List[Tool]):
-        code_tools = agent.get_code_execution_tools()
-        return self._merge_tools(tools, code_tools)
+    def _add_code_execution_tools(
+        self, agent: BaseAgent, tools: Union[List[Tool], List[BaseTool]]
+    ) -> List[BaseTool]:
+        if hasattr(agent, "get_code_execution_tools"):
+            code_tools = agent.get_code_execution_tools()
+            # Cast code_tools to the expected type for _merge_tools
+            return self._merge_tools(tools, cast(List[BaseTool], code_tools))
+        return cast(List[BaseTool], tools)
 
-    def _add_delegation_tools(self, task: Task, tools: List[Tool]):
+    def _add_delegation_tools(
+        self, task: Task, tools: Union[List[Tool], List[BaseTool]]
+    ) -> List[BaseTool]:
         agents_for_delegation = [agent for agent in self.agents if agent != task.agent]
         if len(self.agents) > 1 and len(agents_for_delegation) > 0 and task.agent:
             if not tools:
@@ -957,7 +992,7 @@ class Crew(BaseModel):
             tools = self._inject_delegation_tools(
                 tools, task.agent, agents_for_delegation
             )
-        return tools
+        return cast(List[BaseTool], tools)
 
     def _log_task_start(self, task: Task, role: str = "None"):
         if self.output_log_file:
@@ -965,7 +1000,9 @@ class Crew(BaseModel):
                 task_name=task.name, task=task.description, agent=role, status="started"
             )
 
-    def _update_manager_tools(self, task: Task, tools: List[Tool]):
+    def _update_manager_tools(
+        self, task: Task, tools: Union[List[Tool], List[BaseTool]]
+    ) -> List[BaseTool]:
         if self.manager_agent:
             if task.agent:
                 tools = self._inject_delegation_tools(tools, task.agent, [task.agent])
@@ -973,7 +1010,7 @@ class Crew(BaseModel):
                 tools = self._inject_delegation_tools(
                     tools, self.manager_agent, self.agents
                 )
-        return tools
+        return cast(List[BaseTool], tools)
 
     def _get_context(self, task: Task, task_outputs: List[TaskOutput]):
         context = (
@@ -1214,13 +1251,14 @@ class Crew(BaseModel):
     def test(
         self,
         n_iterations: int,
-        eval_llm: Union[str, InstanceOf[LLM]],
+        eval_llm: Union[str, InstanceOf[BaseLLM]],
         inputs: Optional[Dict[str, Any]] = None,
     ) -> None:
         """Test and evaluate the Crew with the given inputs for n iterations concurrently using concurrent.futures."""
         try:
-            eval_llm = create_llm(eval_llm)
-            if not eval_llm:
+            # Create LLM instance and ensure it's of type LLM for CrewEvaluator
+            llm_instance = create_llm(eval_llm)
+            if not llm_instance:
                 raise ValueError("Failed to create LLM instance.")
 
             crewai_event_bus.emit(
@@ -1228,12 +1266,12 @@ class Crew(BaseModel):
                 CrewTestStartedEvent(
                     crew_name=self.name or "crew",
                     n_iterations=n_iterations,
-                    eval_llm=eval_llm,
+                    eval_llm=llm_instance,
                     inputs=inputs,
                 ),
             )
             test_crew = self.copy()
-            evaluator = CrewEvaluator(test_crew, eval_llm)  # type: ignore[arg-type]
+            evaluator = CrewEvaluator(test_crew, llm_instance)
 
             for i in range(1, n_iterations + 1):
                 evaluator.set_iteration(i)

src/crewai/llm.py

@@ -40,6 +40,7 @@ with warnings.catch_warnings():
     from litellm.utils import supports_response_schema
 
 
+from crewai.llms.base_llm import BaseLLM
 from crewai.utilities.events import crewai_event_bus
 from crewai.utilities.exceptions.context_window_exceeding_exception import (
     LLMContextLengthExceededException,
@@ -114,6 +115,60 @@ LLM_CONTEXT_WINDOW_SIZES = {
     "Llama-3.2-11B-Vision-Instruct": 16384,
     "Meta-Llama-3.2-3B-Instruct": 4096,
     "Meta-Llama-3.2-1B-Instruct": 16384,
+    # bedrock
+    "us.amazon.nova-pro-v1:0": 300000,
+    "us.amazon.nova-micro-v1:0": 128000,
+    "us.amazon.nova-lite-v1:0": 300000,
+    "us.anthropic.claude-3-5-sonnet-20240620-v1:0": 200000,
+    "us.anthropic.claude-3-5-haiku-20241022-v1:0": 200000,
+    "us.anthropic.claude-3-5-sonnet-20241022-v2:0": 200000,
+    "us.anthropic.claude-3-7-sonnet-20250219-v1:0": 200000,
+    "us.anthropic.claude-3-sonnet-20240229-v1:0": 200000,
+    "us.anthropic.claude-3-opus-20240229-v1:0": 200000,
+    "us.anthropic.claude-3-haiku-20240307-v1:0": 200000,
+    "us.meta.llama3-2-11b-instruct-v1:0": 128000,
+    "us.meta.llama3-2-3b-instruct-v1:0": 131000,
+    "us.meta.llama3-2-90b-instruct-v1:0": 128000,
+    "us.meta.llama3-2-1b-instruct-v1:0": 131000,
+    "us.meta.llama3-1-8b-instruct-v1:0": 128000,
+    "us.meta.llama3-1-70b-instruct-v1:0": 128000,
+    "us.meta.llama3-3-70b-instruct-v1:0": 128000,
+    "us.meta.llama3-1-405b-instruct-v1:0": 128000,
+    "eu.anthropic.claude-3-5-sonnet-20240620-v1:0": 200000,
+    "eu.anthropic.claude-3-sonnet-20240229-v1:0": 200000,
+    "eu.anthropic.claude-3-haiku-20240307-v1:0": 200000,
+    "eu.meta.llama3-2-3b-instruct-v1:0": 131000,
+    "eu.meta.llama3-2-1b-instruct-v1:0": 131000,
+    "apac.anthropic.claude-3-5-sonnet-20240620-v1:0": 200000,
+    "apac.anthropic.claude-3-5-sonnet-20241022-v2:0": 200000,
+    "apac.anthropic.claude-3-sonnet-20240229-v1:0": 200000,
+    "apac.anthropic.claude-3-haiku-20240307-v1:0": 200000,
+    "amazon.nova-pro-v1:0": 300000,
+    "amazon.nova-micro-v1:0": 128000,
+    "amazon.nova-lite-v1:0": 300000,
+    "anthropic.claude-3-5-sonnet-20240620-v1:0": 200000,
+    "anthropic.claude-3-5-haiku-20241022-v1:0": 200000,
+    "anthropic.claude-3-5-sonnet-20241022-v2:0": 200000,
+    "anthropic.claude-3-7-sonnet-20250219-v1:0": 200000,
+    "anthropic.claude-3-sonnet-20240229-v1:0": 200000,
+    "anthropic.claude-3-opus-20240229-v1:0": 200000,
+    "anthropic.claude-3-haiku-20240307-v1:0": 200000,
+    "anthropic.claude-v2:1": 200000,
+    "anthropic.claude-v2": 100000,
+    "anthropic.claude-instant-v1": 100000,
+    "meta.llama3-1-405b-instruct-v1:0": 128000,
+    "meta.llama3-1-70b-instruct-v1:0": 128000,
+    "meta.llama3-1-8b-instruct-v1:0": 128000,
+    "meta.llama3-70b-instruct-v1:0": 8000,
+    "meta.llama3-8b-instruct-v1:0": 8000,
+    "amazon.titan-text-lite-v1": 4000,
+    "amazon.titan-text-express-v1": 8000,
+    "cohere.command-text-v14": 4000,
+    "ai21.j2-mid-v1": 8191,
+    "ai21.j2-ultra-v1": 8191,
+    "ai21.jamba-instruct-v1:0": 256000,
+    "mistral.mistral-7b-instruct-v0:2": 32000,
+    "mistral.mixtral-8x7b-instruct-v0:1": 32000,
     # mistral
     "mistral-tiny": 32768,
     "mistral-small-latest": 32768,
@@ -164,7 +219,7 @@ class StreamingChoices(TypedDict):
     finish_reason: Optional[str]
 
 
-class LLM:
+class LLM(BaseLLM):
     def __init__(
         self,
         model: str,

src/crewai/llms/base_llm.py

@@ -0,0 +1,91 @@
+from abc import ABC, abstractmethod
+from typing import Any, Callable, Dict, List, Optional, Union
+
+
+class BaseLLM(ABC):
+    """Abstract base class for LLM implementations.
+
+    This class defines the interface that all LLM implementations must follow.
+    Users can extend this class to create custom LLM implementations that don't
+    rely on litellm's authentication mechanism.
+
+    Custom LLM implementations should handle error cases gracefully, including
+    timeouts, authentication failures, and malformed responses. They should also
+    implement proper validation for input parameters and provide clear error
+    messages when things go wrong.
+
+    Attributes:
+        stop (list): A list of stop sequences that the LLM should use to stop generation.
+            This is used by the CrewAgentExecutor and other components.
+    """
+
+    model: str
+    temperature: Optional[float] = None
+    stop: Optional[List[str]] = None
+
+    def __init__(
+        self,
+        model: str,
+        temperature: Optional[float] = None,
+    ):
+        """Initialize the BaseLLM with default attributes.
+
+        This constructor sets default values for attributes that are expected
+        by the CrewAgentExecutor and other components.
+
+        All custom LLM implementations should call super().__init__() to ensure
+        that these default attributes are properly initialized.
+        """
+        self.model = model
+        self.temperature = temperature
+        self.stop = []
+
+    @abstractmethod
+    def call(
+        self,
+        messages: Union[str, List[Dict[str, str]]],
+        tools: Optional[List[dict]] = None,
+        callbacks: Optional[List[Any]] = None,
+        available_functions: Optional[Dict[str, Any]] = None,
+    ) -> Union[str, Any]:
+        """Call the LLM with the given messages.
+
+        Args:
+            messages: Input messages for the LLM.
+                     Can be a string or list of message dictionaries.
+                     If string, it will be converted to a single user message.
+                     If list, each dict must have 'role' and 'content' keys.
+            tools: Optional list of tool schemas for function calling.
+                  Each tool should define its name, description, and parameters.
+            callbacks: Optional list of callback functions to be executed
+                      during and after the LLM call.
+            available_functions: Optional dict mapping function names to callables
+                               that can be invoked by the LLM.
+
+        Returns:
+            Either a text response from the LLM (str) or
+            the result of a tool function call (Any).
+
+        Raises:
+            ValueError: If the messages format is invalid.
+            TimeoutError: If the LLM request times out.
+            RuntimeError: If the LLM request fails for other reasons.
+        """
+        pass
+
+    def supports_stop_words(self) -> bool:
+        """Check if the LLM supports stop words.
+
+        Returns:
+            bool: True if the LLM supports stop words, False otherwise.
+        """
+        return True  # Default implementation assumes support for stop words
+
+    def get_context_window_size(self) -> int:
+        """Get the context window size for the LLM.
+
+        Returns:
+            int: The number of tokens/characters the model can handle.
+        """
+        # Default implementation - subclasses should override with model-specific values
+        return 4096

src/crewai/llms/third_party/ai_suite.py

@@ -0,0 +1,38 @@
+from typing import Any, Dict, List, Optional, Union
+
+import aisuite as ai
+
+from crewai.llms.base_llm import BaseLLM
+
+
+class AISuiteLLM(BaseLLM):
+    def __init__(self, model: str, temperature: Optional[float] = None, **kwargs):
+        super().__init__(model, temperature, **kwargs)
+        self.client = ai.Client()
+
+    def call(
+        self,
+        messages: Union[str, List[Dict[str, str]]],
+        tools: Optional[List[dict]] = None,
+        callbacks: Optional[List[Any]] = None,
+        available_functions: Optional[Dict[str, Any]] = None,
+    ) -> Union[str, Any]:
+        completion_params = self._prepare_completion_params(messages, tools)
+        response = self.client.chat.completions.create(**completion_params)
+
+        return response.choices[0].message.content
+
+    def _prepare_completion_params(
+        self,
+        messages: Union[str, List[Dict[str, str]]],
+        tools: Optional[List[dict]] = None,
+    ) -> Dict[str, Any]:
+        return {
+            "model": self.model,
+            "messages": messages,
+            "temperature": self.temperature,
+            "tools": tools,
+        }
+
+    def supports_function_calling(self) -> bool:
+        return False

src/crewai/memory/storage/mem0_storage.py

@@ -1,7 +1,7 @@
 import os
 from typing import Any, Dict, List
 
-from mem0 import MemoryClient
+from mem0 import Memory, MemoryClient
 
 from crewai.memory.storage.interface import Storage
 
@@ -32,13 +32,16 @@ class Mem0Storage(Storage):
         mem0_org_id = config.get("org_id")
         mem0_project_id = config.get("project_id")
 
-        # Initialize MemoryClient with available parameters
-        if mem0_org_id and mem0_project_id:
-            self.memory = MemoryClient(
-                api_key=mem0_api_key, org_id=mem0_org_id, project_id=mem0_project_id
-            )
+        # Initialize MemoryClient or Memory based on the presence of the mem0_api_key
+        if mem0_api_key:
+            if mem0_org_id and mem0_project_id:
+                self.memory = MemoryClient(
+                    api_key=mem0_api_key, org_id=mem0_org_id, project_id=mem0_project_id
+                )
+            else:
+                self.memory = MemoryClient(api_key=mem0_api_key)
         else:
-            self.memory = MemoryClient(api_key=mem0_api_key)
+            self.memory = Memory()  # Fallback to Memory if no Mem0 API key is provided
 
     def _sanitize_role(self, role: str) -> str:
         """

src/crewai/task.py

@@ -2,6 +2,7 @@ import datetime
 import inspect
 import json
 import logging
+import re
 import threading
 import uuid
 from concurrent.futures import Future
@@ -49,6 +50,7 @@ from crewai.utilities.events import (
 from crewai.utilities.events.crewai_event_bus import crewai_event_bus
 from crewai.utilities.i18n import I18N
 from crewai.utilities.printer import Printer
+from crewai.utilities.string_utils import interpolate_only
 
 
 class Task(BaseModel):
@@ -507,7 +509,9 @@ class Task(BaseModel):
             return
 
         try:
-            self.description = self._original_description.format(**inputs)
+            self.description = interpolate_only(
+                input_string=self._original_description, inputs=inputs
+            )
         except KeyError as e:
             raise ValueError(
                 f"Missing required template variable '{e.args[0]}' in description"
@@ -516,7 +520,7 @@ class Task(BaseModel):
             raise ValueError(f"Error interpolating description: {str(e)}") from e
 
         try:
-            self.expected_output = self.interpolate_only(
+            self.expected_output = interpolate_only(
                 input_string=self._original_expected_output, inputs=inputs
             )
         except (KeyError, ValueError) as e:
@@ -524,7 +528,7 @@ class Task(BaseModel):
 
         if self.output_file is not None:
             try:
-                self.output_file = self.interpolate_only(
+                self.output_file = interpolate_only(
                     input_string=self._original_output_file, inputs=inputs
                 )
             except (KeyError, ValueError) as e:
@@ -555,72 +559,6 @@ class Task(BaseModel):
                 f"\n\n{conversation_instruction}\n\n{conversation_history}"
             )
 
-    def interpolate_only(
-        self,
-        input_string: Optional[str],
-        inputs: Dict[str, Union[str, int, float, Dict[str, Any], List[Any]]],
-    ) -> str:
-        """Interpolate placeholders (e.g., {key}) in a string while leaving JSON untouched.
-
-        Args:
-            input_string: The string containing template variables to interpolate.
-                         Can be None or empty, in which case an empty string is returned.
-            inputs: Dictionary mapping template variables to their values.
-                   Supported value types are strings, integers, floats, and dicts/lists
-                   containing only these types and other nested dicts/lists.
-
-        Returns:
-            The interpolated string with all template variables replaced with their values.
-            Empty string if input_string is None or empty.
-
-        Raises:
-            ValueError: If a value contains unsupported types
-        """
-
-        # Validation function for recursive type checking
-        def validate_type(value: Any) -> None:
-            if value is None:
-                return
-            if isinstance(value, (str, int, float, bool)):
-                return
-            if isinstance(value, (dict, list)):
-                for item in value.values() if isinstance(value, dict) else value:
-                    validate_type(item)
-                return
-            raise ValueError(
-                f"Unsupported type {type(value).__name__} in inputs. "
-                "Only str, int, float, bool, dict, and list are allowed."
-            )
-
-        # Validate all input values
-        for key, value in inputs.items():
-            try:
-                validate_type(value)
-            except ValueError as e:
-                raise ValueError(f"Invalid value for key '{key}': {str(e)}") from e
-
-        if input_string is None or not input_string:
-            return ""
-        if "{" not in input_string and "}" not in input_string:
-            return input_string
-        if not inputs:
-            raise ValueError(
-                "Inputs dictionary cannot be empty when interpolating variables"
-            )
-        try:
-            escaped_string = input_string.replace("{", "{{").replace("}", "}}")
-
-            for key in inputs.keys():
-                escaped_string = escaped_string.replace(f"{{{{{key}}}}}", f"{{{key}}}")
-
-            return escaped_string.format(**inputs)
-        except KeyError as e:
-            raise KeyError(
-                f"Template variable '{e.args[0]}' not found in inputs dictionary"
-            ) from e
-        except ValueError as e:
-            raise ValueError(f"Error during string interpolation: {str(e)}") from e
-
     def increment_tools_errors(self) -> None:
         """Increment the tools errors counter."""
         self.tools_errors += 1
@@ -634,7 +572,15 @@ class Task(BaseModel):
     def copy(
         self, agents: List["BaseAgent"], task_mapping: Dict[str, "Task"]
     ) -> "Task":
-        """Create a deep copy of the Task."""
+        """Creates a deep copy of the Task while preserving its original class type.
+
+        Args:
+            agents: List of agents available for the task.
+            task_mapping: Dictionary mapping task IDs to Task instances.
+
+        Returns:
+            A copy of the task with the same class type as the original.
+        """
         exclude = {
             "id",
             "agent",
@@ -657,7 +603,7 @@ class Task(BaseModel):
         cloned_agent = get_agent_by_role(self.agent.role) if self.agent else None
         cloned_tools = copy(self.tools) if self.tools else []
 
-        copied_task = Task(
+        copied_task = self.__class__(
             **copied_data,
             context=cloned_context,
             agent=cloned_agent,

src/crewai/telemetry/telemetry.py

@@ -281,8 +281,16 @@ class Telemetry:
         return self._safe_telemetry_operation(operation)
 
     def task_ended(self, span: Span, task: Task, crew: Crew):
-        """Records task execution in a crew."""
+        """Records the completion of a task execution in a crew.
 
+        Args:
+            span (Span): The OpenTelemetry span tracking the task execution
+            task (Task): The task that was completed
+            crew (Crew): The crew context in which the task was executed
+
+        Note:
+            If share_crew is enabled, this will also record the task output
+        """
         def operation():
             if crew.share_crew:
                 self._add_attribute(
@@ -297,8 +305,13 @@ class Telemetry:
         self._safe_telemetry_operation(operation)
 
     def tool_repeated_usage(self, llm: Any, tool_name: str, attempts: int):
-        """Records the repeated usage 'error' of a tool by an agent."""
+        """Records when a tool is used repeatedly, which might indicate an issue.
 
+        Args:
+            llm (Any): The language model being used
+            tool_name (str): Name of the tool being repeatedly used
+            attempts (int): Number of attempts made with this tool
+        """
         def operation():
             tracer = trace.get_tracer("crewai.telemetry")
             span = tracer.start_span("Tool Repeated Usage")
@@ -317,8 +330,13 @@ class Telemetry:
         self._safe_telemetry_operation(operation)
 
     def tool_usage(self, llm: Any, tool_name: str, attempts: int):
-        """Records the usage of a tool by an agent."""
+        """Records the usage of a tool by an agent.
 
+        Args:
+            llm (Any): The language model being used
+            tool_name (str): Name of the tool being used
+            attempts (int): Number of attempts made with this tool
+        """
         def operation():
             tracer = trace.get_tracer("crewai.telemetry")
             span = tracer.start_span("Tool Usage")
@@ -337,8 +355,11 @@ class Telemetry:
         self._safe_telemetry_operation(operation)
 
     def tool_usage_error(self, llm: Any):
-        """Records the usage of a tool by an agent."""
+        """Records when a tool usage results in an error.
 
+        Args:
+            llm (Any): The language model being used when the error occurred
+        """
         def operation():
             tracer = trace.get_tracer("crewai.telemetry")
             span = tracer.start_span("Tool Usage Error")
@@ -357,6 +378,14 @@ class Telemetry:
     def individual_test_result_span(
         self, crew: Crew, quality: float, exec_time: int, model_name: str
     ):
+        """Records individual test results for a crew execution.
+
+        Args:
+            crew (Crew): The crew being tested
+            quality (float): Quality score of the execution
+            exec_time (int): Execution time in seconds
+            model_name (str): Name of the model used
+        """
         def operation():
             tracer = trace.get_tracer("crewai.telemetry")
             span = tracer.start_span("Crew Individual Test Result")
@@ -383,6 +412,14 @@ class Telemetry:
         inputs: dict[str, Any] | None,
         model_name: str,
     ):
+        """Records the execution of a test suite for a crew.
+
+        Args:
+            crew (Crew): The crew being tested
+            iterations (int): Number of test iterations
+            inputs (dict[str, Any] | None): Input parameters for the test
+            model_name (str): Name of the model used in testing
+        """
         def operation():
             tracer = trace.get_tracer("crewai.telemetry")
             span = tracer.start_span("Crew Test Execution")
@@ -408,6 +445,7 @@ class Telemetry:
         self._safe_telemetry_operation(operation)
 
     def deploy_signup_error_span(self):
+        """Records when an error occurs during the deployment signup process."""
         def operation():
             tracer = trace.get_tracer("crewai.telemetry")
             span = tracer.start_span("Deploy Signup Error")
@@ -417,6 +455,11 @@ class Telemetry:
         self._safe_telemetry_operation(operation)
 
     def start_deployment_span(self, uuid: Optional[str] = None):
+        """Records the start of a deployment process.
+
+        Args:
+            uuid (Optional[str]): Unique identifier for the deployment
+        """
         def operation():
             tracer = trace.get_tracer("crewai.telemetry")
             span = tracer.start_span("Start Deployment")
@@ -428,6 +471,7 @@ class Telemetry:
         self._safe_telemetry_operation(operation)
 
     def create_crew_deployment_span(self):
+        """Records the creation of a new crew deployment."""
         def operation():
             tracer = trace.get_tracer("crewai.telemetry")
             span = tracer.start_span("Create Crew Deployment")
@@ -437,6 +481,12 @@ class Telemetry:
         self._safe_telemetry_operation(operation)
 
     def get_crew_logs_span(self, uuid: Optional[str], log_type: str = "deployment"):
+        """Records the retrieval of crew logs.
+
+        Args:
+            uuid (Optional[str]): Unique identifier for the crew
+            log_type (str, optional): Type of logs being retrieved. Defaults to "deployment".
+        """
         def operation():
             tracer = trace.get_tracer("crewai.telemetry")
             span = tracer.start_span("Get Crew Logs")
@@ -449,6 +499,11 @@ class Telemetry:
         self._safe_telemetry_operation(operation)
 
     def remove_crew_span(self, uuid: Optional[str] = None):
+        """Records the removal of a crew.
+
+        Args:
+            uuid (Optional[str]): Unique identifier for the crew being removed
+        """
         def operation():
             tracer = trace.get_tracer("crewai.telemetry")
             span = tracer.start_span("Remove Crew")
@@ -574,6 +629,11 @@ class Telemetry:
         self._safe_telemetry_operation(operation)
 
     def flow_creation_span(self, flow_name: str):
+        """Records the creation of a new flow.
+
+        Args:
+            flow_name (str): Name of the flow being created
+        """
         def operation():
             tracer = trace.get_tracer("crewai.telemetry")
             span = tracer.start_span("Flow Creation")
@@ -584,6 +644,12 @@ class Telemetry:
         self._safe_telemetry_operation(operation)
 
     def flow_plotting_span(self, flow_name: str, node_names: list[str]):
+        """Records flow visualization/plotting activity.
+
+        Args:
+            flow_name (str): Name of the flow being plotted
+            node_names (list[str]): List of node names in the flow
+        """
         def operation():
             tracer = trace.get_tracer("crewai.telemetry")
             span = tracer.start_span("Flow Plotting")
@@ -595,6 +661,12 @@ class Telemetry:
         self._safe_telemetry_operation(operation)
 
     def flow_execution_span(self, flow_name: str, node_names: list[str]):
+        """Records the execution of a flow.
+
+        Args:
+            flow_name (str): Name of the flow being executed
+            node_names (list[str]): List of nodes being executed in the flow
+        """
         def operation():
             tracer = trace.get_tracer("crewai.telemetry")
             span = tracer.start_span("Flow Execution")

src/crewai/tools/tool_usage.py

@@ -455,7 +455,7 @@ class ToolUsage:
 
         # Attempt 4: Repair JSON
         try:
-            repaired_input = repair_json(tool_input)
+            repaired_input = repair_json(tool_input, skip_json_loads=True)
             self._printer.print(
                 content=f"Repaired JSON: {repaired_input}", color="blue"
             )

src/crewai/utilities/evaluators/crew_evaluator_handler.py

@@ -6,7 +6,7 @@ from rich.console import Console
 from rich.table import Table
 
 from crewai.agent import Agent
-from crewai.llm import LLM
+from crewai.llm import BaseLLM
 from crewai.task import Task
 from crewai.tasks.task_output import TaskOutput
 from crewai.telemetry import Telemetry
@@ -24,7 +24,7 @@ class CrewEvaluator:
 
     Attributes:
         crew (Crew): The crew of agents to evaluate.
-        eval_llm (LLM): Language model instance to use for evaluations
+        eval_llm (BaseLLM): Language model instance to use for evaluations
         tasks_scores (defaultdict): A dictionary to store the scores of the agents for each task.
         iteration (int): The current iteration of the evaluation.
     """
@@ -33,7 +33,7 @@ class CrewEvaluator:
     run_execution_times: defaultdict = defaultdict(list)
     iteration: int = 0
 
-    def __init__(self, crew, eval_llm: InstanceOf[LLM]):
+    def __init__(self, crew, eval_llm: InstanceOf[BaseLLM]):
         self.crew = crew
         self.llm = eval_llm
         self._telemetry = Telemetry()

src/crewai/utilities/formatter.py

@@ -1,10 +1,12 @@
-from typing import List
+import re
+from typing import TYPE_CHECKING, List
 
-from crewai.task import Task
-from crewai.tasks.task_output import TaskOutput
+if TYPE_CHECKING:
+    from crewai.task import Task
+    from crewai.tasks.task_output import TaskOutput
 
 
-def aggregate_raw_outputs_from_task_outputs(task_outputs: List[TaskOutput]) -> str:
+def aggregate_raw_outputs_from_task_outputs(task_outputs: List["TaskOutput"]) -> str:
     """Generate string context from the task outputs."""
     dividers = "\n\n----------\n\n"
 
@@ -13,7 +15,7 @@ def aggregate_raw_outputs_from_task_outputs(task_outputs: List[TaskOutput]) -> s
     return context
 
 
-def aggregate_raw_outputs_from_tasks(tasks: List[Task]) -> str:
+def aggregate_raw_outputs_from_tasks(tasks: List["Task"]) -> str:
     """Generate string context from the tasks."""
     task_outputs = [task.output for task in tasks if task.output is not None]
 

src/crewai/utilities/llm_utils.py

@@ -2,28 +2,28 @@ import os
 from typing import Any, Dict, List, Optional, Union
 
 from crewai.cli.constants import DEFAULT_LLM_MODEL, ENV_VARS, LITELLM_PARAMS
-from crewai.llm import LLM
+from crewai.llm import LLM, BaseLLM
 
 
 def create_llm(
     llm_value: Union[str, LLM, Any, None] = None,
-) -> Optional[LLM]:
+) -> Optional[LLM | BaseLLM]:
     """
     Creates or returns an LLM instance based on the given llm_value.
 
     Args:
-        llm_value (str | LLM | Any | None):
+        llm_value (str | BaseLLM | Any | None):
             - str: The model name (e.g., "gpt-4").
-            - LLM: Already instantiated LLM, returned as-is.
+            - BaseLLM: Already instantiated BaseLLM (including LLM), returned as-is.
             - Any: Attempt to extract known attributes like model_name, temperature, etc.
             - None: Use environment-based or fallback default model.
 
     Returns:
-        An LLM instance if successful, or None if something fails.
+        A BaseLLM instance if successful, or None if something fails.
     """
 
-    # 1) If llm_value is already an LLM object, return it directly
-    if isinstance(llm_value, LLM):
+    # 1) If llm_value is already a BaseLLM or LLM object, return it directly
+    if isinstance(llm_value, LLM) or isinstance(llm_value, BaseLLM):
         return llm_value
 
     # 2) If llm_value is a string (model name)

src/crewai/utilities/planning_handler.py

@@ -96,6 +96,10 @@ class CrewPlanner:
         tasks_summary = []
         for idx, task in enumerate(self.tasks):
             knowledge_list = self._get_agent_knowledge(task)
+            agent_tools = (
+                f"[{', '.join(str(tool) for tool in task.agent.tools)}]" if task.agent and task.agent.tools else '"agent has no tools"',
+                f',\n                "agent_knowledge": "[\\"{knowledge_list[0]}\\"]"' if knowledge_list and str(knowledge_list) != "None" else ""
+            )
             task_summary = f"""
                 Task Number {idx + 1} - {task.description}
                 "task_description": {task.description}
@@ -103,10 +107,7 @@ class CrewPlanner:
                 "agent": {task.agent.role if task.agent else "None"}
                 "agent_goal": {task.agent.goal if task.agent else "None"}
                 "task_tools": {task.tools}
-                "agent_tools": %s%s""" % (
-                    f"[{', '.join(str(tool) for tool in task.agent.tools)}]" if task.agent and task.agent.tools else '"agent has no tools"',
-                    f',\n                "agent_knowledge": "[\\"{knowledge_list[0]}\\"]"' if knowledge_list and str(knowledge_list) != "None" else ""
-                )
+                "agent_tools": {"".join(agent_tools)}"""
 
             tasks_summary.append(task_summary)
         return " ".join(tasks_summary)

src/crewai/utilities/string_utils.py

@@ -0,0 +1,82 @@
+import re
+from typing import Any, Dict, List, Optional, Union
+
+
+def interpolate_only(
+    input_string: Optional[str],
+    inputs: Dict[str, Union[str, int, float, Dict[str, Any], List[Any]]],
+) -> str:
+    """Interpolate placeholders (e.g., {key}) in a string while leaving JSON untouched.
+    Only interpolates placeholders that follow the pattern {variable_name} where
+    variable_name starts with a letter/underscore and contains only letters, numbers, and underscores.
+
+    Args:
+        input_string: The string containing template variables to interpolate.
+                     Can be None or empty, in which case an empty string is returned.
+        inputs: Dictionary mapping template variables to their values.
+               Supported value types are strings, integers, floats, and dicts/lists
+               containing only these types and other nested dicts/lists.
+
+    Returns:
+        The interpolated string with all template variables replaced with their values.
+        Empty string if input_string is None or empty.
+
+    Raises:
+        ValueError: If a value contains unsupported types or a template variable is missing
+    """
+
+    # Validation function for recursive type checking
+    def validate_type(value: Any) -> None:
+        if value is None:
+            return
+        if isinstance(value, (str, int, float, bool)):
+            return
+        if isinstance(value, (dict, list)):
+            for item in value.values() if isinstance(value, dict) else value:
+                validate_type(item)
+            return
+        raise ValueError(
+            f"Unsupported type {type(value).__name__} in inputs. "
+            "Only str, int, float, bool, dict, and list are allowed."
+        )
+
+    # Validate all input values
+    for key, value in inputs.items():
+        try:
+            validate_type(value)
+        except ValueError as e:
+            raise ValueError(f"Invalid value for key '{key}': {str(e)}") from e
+
+    if input_string is None or not input_string:
+        return ""
+    if "{" not in input_string and "}" not in input_string:
+        return input_string
+    if not inputs:
+        raise ValueError(
+            "Inputs dictionary cannot be empty when interpolating variables"
+        )
+
+    # The regex pattern to find valid variable placeholders
+    # Matches {variable_name} where variable_name starts with a letter/underscore
+    # and contains only letters, numbers, and underscores
+    pattern = r"\{([A-Za-z_][A-Za-z0-9_]*)\}"
+
+    # Find all matching variables in the input string
+    variables = re.findall(pattern, input_string)
+    result = input_string
+
+    # Check if all variables exist in inputs
+    missing_vars = [var for var in variables if var not in inputs]
+    if missing_vars:
+        raise KeyError(
+            f"Template variable '{missing_vars[0]}' not found in inputs dictionary"
+        )
+
+    # Replace each variable with its value
+    for var in variables:
+        if var in inputs:
+            placeholder = "{" + var + "}"
+            value = str(inputs[var])
+            result = result.replace(placeholder, value)
+
+    return result

tests/cassettes/test_before_kickoff_callback.yaml

@@ -710,4 +710,117 @@ interactions:
       - req_4ceac9bc8ae57f631959b91d2ab63c4d
     http_version: HTTP/1.1
     status_code: 200
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Test Agent. Test agent
+      backstory\nYour personal goal is: Test agent goal\nTo give my best complete
+      final answer to the task respond using the exact following format:\n\nThought:
+      I now can give a great answer\nFinal Answer: Your final answer must be the great
+      and the most complete as possible, it must be outcome described.\n\nI MUST use
+      these formats, my job depends on it!"}, {"role": "user", "content": "\nCurrent
+      Task: Test task description\n\nThis is the expected criteria for your final
+      answer: Test expected 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:
+      - '840'
+      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:
+      - MacOS
+      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:
+      - 3.12.9
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-BExKOliqPgvHyozZaBu5oN50CHtsa\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1742904348,\n  \"model\": \"gpt-4o-2024-08-06\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"I now can give a great answer  \\nFinal
+      Answer: Test expected output\",\n        \"refusal\": null,\n        \"annotations\":
+      []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n
+      \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 158,\n    \"completion_tokens\":
+      15,\n    \"total_tokens\": 173,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+      0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n
+      \     \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+      \"default\",\n  \"system_fingerprint\": \"fp_90d33c15d4\"\n}\n"
+    headers:
+      CF-RAY:
+      - 925e4749af02f227-GRU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 25 Mar 2025 12:05:48 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=VHa7Z7dJYptxXpaMxgldvK6HqIM.m74xpi.80N_EBDc-1742904348-1.0.1.1-VthD2riCSnAprFYhOZxfIrTjT33tybJHpHWB25Q_Hx4vuACCyF00tix6e6eorDReGcW3jb5cUzbGqYi47TrMsS4LYjxBv5eCo7cU9OuFajs;
+        path=/; expires=Tue, 25-Mar-25 12:35:48 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=Is8fSaH3lU8yHyT3fI7cRZiDqIYSI6sPpzfzvEV8HMc-1742904348760-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '377'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '50000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-requests:
+      - '49999'
+      x-ratelimit-remaining-tokens:
+      - '149999822'
+      x-ratelimit-reset-requests:
+      - 1ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_fd6b93e3b1a30868482c72306e7f63c2
+    http_version: HTTP/1.1
+    status_code: 200
 version: 1

tests/cassettes/test_custom_llm_implementation.yaml

@@ -0,0 +1,107 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are a helpful assistant."},
+      {"role": "user", "content": "What is the answer to life, the universe, and everything?"}],
+      "model": "gpt-4o-mini", "tools": null}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '206'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.61.0
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.61.0
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.8
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-B7W6FS0wpfndLdg12G3H6ZAXcYhJi\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1741131387,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"The answer to life, the universe, and
+      everything, famously found in Douglas Adams' \\\"The Hitchhiker's Guide to the
+      Galaxy,\\\" is the number 42. However, the question itself is left ambiguous,
+      leading to much speculation and humor in the story.\",\n        \"refusal\":
+      null\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n
+      \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 30,\n    \"completion_tokens\":
+      54,\n    \"total_tokens\": 84,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+      0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n
+      \     \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+      \"default\",\n  \"system_fingerprint\": \"fp_06737a9306\"\n}\n"
+    headers:
+      CF-RAY:
+      - 91b532234c18cf1f-SJC
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 04 Mar 2025 23:36:28 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=DgLb6UAE6W4Oeto1Bi2RiKXQVV5TTzkXdXWFdmAEwQQ-1741131388-1.0.1.1-jWQtsT95wOeQbmIxAK7cv8gJWxYi1tQ.IupuJzBDnZr7iEChwVUQBRfnYUBJPDsNly3bakCDArjD_S.FLKwH6xUfvlxgfd4YSBhBPy7bcgw;
+        path=/; expires=Wed, 05-Mar-25 00:06:28 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=Oa59XCmqjKLKwU34la1hkTunN57JW20E.ZHojvRBfow-1741131388236-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '776'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '30000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-requests:
+      - '29999'
+      x-ratelimit-remaining-tokens:
+      - '149999960'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_97824e8fe7c1aca3fbcba7c925388b39
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1

tests/cassettes/test_custom_llm_within_crew.yaml

@@ -0,0 +1,305 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are a helpful assistant."},
+      {"role": "user", "content": [{"role": "system", "content": "You are Say Hi.
+      You just say hi to the user\nYour personal goal is: Say hi to the user\nTo give
+      my best complete final answer to the task respond using the exact following
+      format:\n\nThought: I now can give a great answer\nFinal Answer: Your final
+      answer must be the great and the most complete as possible, it must be outcome
+      described.\n\nI MUST use these formats, my job depends on it!"}, {"role": "user",
+      "content": "\nCurrent Task: Say hi to the user\n\nThis is the expected criteria
+      for your final answer: A greeting to the user\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-mini", "tools": null}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '931'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.61.0
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.61.0
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.8
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"error\": {\n    \"message\": \"Missing required parameter: 'messages[1].content[0].type'.\",\n
+      \   \"type\": \"invalid_request_error\",\n    \"param\": \"messages[1].content[0].type\",\n
+      \   \"code\": \"missing_required_parameter\"\n  }\n}"
+    headers:
+      CF-RAY:
+      - 91b54660799a15b4-SJC
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '219'
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 04 Mar 2025 23:50:16 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=OwS.6cyfDpbxxx8vPp4THv5eNoDMQK0qSVN.wSUyOYk-1741132216-1.0.1.1-QBVd08CjfmDBpNnYQM5ILGbTUWKh6SDM9E4ARG4SV2Z9Q4ltFSFLXoo38OGJApUNZmzn4PtRsyAPsHt_dsrHPF6MD17FPcGtrnAHqCjJrfU;
+        path=/; expires=Wed, 05-Mar-25 00:20:16 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=n_ebDsAOhJm5Mc7OMx8JDiOaZq5qzHCnVxyS3KN0BwA-1741132216951-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '19'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '30000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-requests:
+      - '29999'
+      x-ratelimit-remaining-tokens:
+      - '149999974'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_042a4e8f9432f6fde7a02037bb6caafa
+    http_version: HTTP/1.1
+    status_code: 400
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are a helpful assistant."},
+      {"role": "user", "content": [{"role": "system", "content": "You are Say Hi.
+      You just say hi to the user\nYour personal goal is: Say hi to the user\nTo give
+      my best complete final answer to the task respond using the exact following
+      format:\n\nThought: I now can give a great answer\nFinal Answer: Your final
+      answer must be the great and the most complete as possible, it must be outcome
+      described.\n\nI MUST use these formats, my job depends on it!"}, {"role": "user",
+      "content": "\nCurrent Task: Say hi to the user\n\nThis is the expected criteria
+      for your final answer: A greeting to the user\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-mini", "tools": null}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '931'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.61.0
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.61.0
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.8
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"error\": {\n    \"message\": \"Missing required parameter: 'messages[1].content[0].type'.\",\n
+      \   \"type\": \"invalid_request_error\",\n    \"param\": \"messages[1].content[0].type\",\n
+      \   \"code\": \"missing_required_parameter\"\n  }\n}"
+    headers:
+      CF-RAY:
+      - 91b54664bb1acef1-SJC
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '219'
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 04 Mar 2025 23:50:17 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=.wGU4pJEajaSzFWjp05TBQwWbCNA2CgpYNu7UYOzbbM-1741132217-1.0.1.1-NoLiAx4qkplllldYYxZCOSQGsX6hsPUJIEyqmt84B3g7hjW1s7.jk9C9PYzXagHWjT0sQ9Ny4LZBA94lDJTfDBZpty8NJQha7ZKW0P_msH8;
+        path=/; expires=Wed, 05-Mar-25 00:20:17 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=GAjgJjVLtN49bMeWdWZDYLLkEkK51z5kxK4nKqhAzxY-1741132217161-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '25'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '30000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-requests:
+      - '29999'
+      x-ratelimit-remaining-tokens:
+      - '149999974'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_7a1d027da1ef4468e861e570c72e98fb
+    http_version: HTTP/1.1
+    status_code: 400
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are a helpful assistant."},
+      {"role": "user", "content": [{"role": "system", "content": "You are Say Hi.
+      You just say hi to the user\nYour personal goal is: Say hi to the user\nTo give
+      my best complete final answer to the task respond using the exact following
+      format:\n\nThought: I now can give a great answer\nFinal Answer: Your final
+      answer must be the great and the most complete as possible, it must be outcome
+      described.\n\nI MUST use these formats, my job depends on it!"}, {"role": "user",
+      "content": "\nCurrent Task: Say hi to the user\n\nThis is the expected criteria
+      for your final answer: A greeting to the user\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-mini", "tools": null}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '931'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.61.0
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.61.0
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.8
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"error\": {\n    \"message\": \"Missing required parameter: 'messages[1].content[0].type'.\",\n
+      \   \"type\": \"invalid_request_error\",\n    \"param\": \"messages[1].content[0].type\",\n
+      \   \"code\": \"missing_required_parameter\"\n  }\n}"
+    headers:
+      CF-RAY:
+      - 91b54666183beb22-SJC
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '219'
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 04 Mar 2025 23:50:17 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=VwjWHHpkZMJlosI9RbMqxYDBS1t0JK4tWpAy4lST2QM-1741132217-1.0.1.1-u7PU.ZvVBTXNB5R8vaYfWdPXAjWZ3ZcTAy656VaGDZmKIckk5od._eQdn0W0EGVtEMm3TuF60z4GZAPDwMYvb3_3cw1RuEMmQbp4IIrl7VY;
+        path=/; expires=Wed, 05-Mar-25 00:20:17 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=NglAAsQBoiabMuuHFgilRjflSPFqS38VGKnGyweuCuw-1741132217438-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '56'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '30000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-requests:
+      - '29999'
+      x-ratelimit-remaining-tokens:
+      - '149999974'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_3c335b308b82cc2214783a4bf2fc0fd4
+    http_version: HTTP/1.1
+    status_code: 400
+version: 1

tests/custom_llm_test.py

@@ -0,0 +1,359 @@
+from typing import Any, Dict, List, Optional, Union
+from unittest.mock import Mock
+
+import pytest
+
+from crewai import Agent, Crew, Process, Task
+from crewai.llms.base_llm import BaseLLM
+from crewai.utilities.llm_utils import create_llm
+
+
+class CustomLLM(BaseLLM):
+    """Custom LLM implementation for testing.
+
+    This is a simple implementation of the BaseLLM abstract base class
+    that returns a predefined response for testing purposes.
+    """
+
+    def __init__(self, response="Default response", model="test-model"):
+        """Initialize the CustomLLM with a predefined response.
+
+        Args:
+            response: The predefined response to return from call().
+        """
+        super().__init__(model=model)
+        self.response = response
+        self.call_count = 0
+
+    def call(
+        self,
+        messages,
+        tools=None,
+        callbacks=None,
+        available_functions=None,
+    ):
+        """
+        Mock LLM call that returns a predefined response.
+        Properly formats messages to match OpenAI's expected structure.
+        """
+        self.call_count += 1
+
+        # If input is a string, convert to proper message format
+        if isinstance(messages, str):
+            messages = [{"role": "user", "content": messages}]
+
+        # Ensure each message has properly formatted content
+        for message in messages:
+            if isinstance(message["content"], str):
+                message["content"] = [{"type": "text", "text": message["content"]}]
+
+        # Return predefined response in expected format
+        if "Thought:" in str(messages):
+            return f"Thought: I will say hi\nFinal Answer: {self.response}"
+        return self.response
+
+    def supports_function_calling(self) -> bool:
+        """Return False to indicate that function calling is not supported.
+
+        Returns:
+            False, indicating that this LLM does not support function calling.
+        """
+        return False
+
+    def supports_stop_words(self) -> bool:
+        """Return False to indicate that stop words are not supported.
+
+        Returns:
+            False, indicating that this LLM does not support stop words.
+        """
+        return False
+
+    def get_context_window_size(self) -> int:
+        """Return a default context window size.
+
+        Returns:
+            4096, a typical context window size for modern LLMs.
+        """
+        return 4096
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_custom_llm_implementation():
+    """Test that a custom LLM implementation works with create_llm."""
+    custom_llm = CustomLLM(response="The answer is 42")
+
+    # Test that create_llm returns the custom LLM instance directly
+    result_llm = create_llm(custom_llm)
+
+    assert result_llm is custom_llm
+
+    # Test calling the custom LLM
+    response = result_llm.call(
+        "What is the answer to life, the universe, and everything?"
+    )
+
+    # Verify that the response from the custom LLM was used
+    assert "42" in response
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_custom_llm_within_crew():
+    """Test that a custom LLM implementation works with create_llm."""
+    custom_llm = CustomLLM(response="Hello! Nice to meet you!", model="test-model")
+
+    agent = Agent(
+        role="Say Hi",
+        goal="Say hi to the user",
+        backstory="""You just say hi to the user""",
+        llm=custom_llm,
+    )
+
+    task = Task(
+        description="Say hi to the user",
+        expected_output="A greeting to the user",
+        agent=agent,
+    )
+
+    crew = Crew(
+        agents=[agent],
+        tasks=[task],
+        process=Process.sequential,
+    )
+
+    result = crew.kickoff()
+
+    # Assert the LLM was called
+    assert custom_llm.call_count > 0
+    # Assert we got a response
+    assert "Hello!" in result.raw
+
+
+def test_custom_llm_message_formatting():
+    """Test that the custom LLM properly formats messages"""
+    custom_llm = CustomLLM(response="Test response", model="test-model")
+
+    # Test with string input
+    result = custom_llm.call("Test message")
+    assert result == "Test response"
+
+    # Test with message list
+    messages = [
+        {"role": "system", "content": "System message"},
+        {"role": "user", "content": "User message"},
+    ]
+    result = custom_llm.call(messages)
+    assert result == "Test response"
+
+
+class JWTAuthLLM(BaseLLM):
+    """Custom LLM implementation with JWT authentication."""
+
+    def __init__(self, jwt_token: str):
+        super().__init__(model="test-model")
+        if not jwt_token or not isinstance(jwt_token, str):
+            raise ValueError("Invalid JWT token")
+        self.jwt_token = jwt_token
+        self.calls = []
+        self.stop = []
+
+    def call(
+        self,
+        messages: Union[str, List[Dict[str, str]]],
+        tools: Optional[List[dict]] = None,
+        callbacks: Optional[List[Any]] = None,
+        available_functions: Optional[Dict[str, Any]] = None,
+    ) -> Union[str, Any]:
+        """Record the call and return a predefined response."""
+        self.calls.append(
+            {
+                "messages": messages,
+                "tools": tools,
+                "callbacks": callbacks,
+                "available_functions": available_functions,
+            }
+        )
+        # In a real implementation, this would use the JWT token to authenticate
+        # with an external service
+        return "Response from JWT-authenticated LLM"
+
+    def supports_function_calling(self) -> bool:
+        """Return True to indicate that function calling is supported."""
+        return True
+
+    def supports_stop_words(self) -> bool:
+        """Return True to indicate that stop words are supported."""
+        return True
+
+    def get_context_window_size(self) -> int:
+        """Return a default context window size."""
+        return 8192
+
+
+def test_custom_llm_with_jwt_auth():
+    """Test a custom LLM implementation with JWT authentication."""
+    jwt_llm = JWTAuthLLM(jwt_token="example.jwt.token")
+
+    # Test that create_llm returns the JWT-authenticated LLM instance directly
+    result_llm = create_llm(jwt_llm)
+
+    assert result_llm is jwt_llm
+
+    # Test calling the JWT-authenticated LLM
+    response = result_llm.call("Test message")
+
+    # Verify that the JWT-authenticated LLM was called
+    assert len(jwt_llm.calls) > 0
+    # Verify that the response from the JWT-authenticated LLM was used
+    assert response == "Response from JWT-authenticated LLM"
+
+
+def test_jwt_auth_llm_validation():
+    """Test that JWT token validation works correctly."""
+    # Test with invalid JWT token (empty string)
+    with pytest.raises(ValueError, match="Invalid JWT token"):
+        JWTAuthLLM(jwt_token="")
+
+    # Test with invalid JWT token (non-string)
+    with pytest.raises(ValueError, match="Invalid JWT token"):
+        JWTAuthLLM(jwt_token=None)
+
+
+class TimeoutHandlingLLM(BaseLLM):
+    """Custom LLM implementation with timeout handling and retry logic."""
+
+    def __init__(self, max_retries: int = 3, timeout: int = 30):
+        """Initialize the TimeoutHandlingLLM with retry and timeout settings.
+
+        Args:
+            max_retries: Maximum number of retry attempts.
+            timeout: Timeout in seconds for each API call.
+        """
+        super().__init__(model="test-model")
+        self.max_retries = max_retries
+        self.timeout = timeout
+        self.calls = []
+        self.stop = []
+        self.fail_count = 0  # Number of times to simulate failure
+
+    def call(
+        self,
+        messages: Union[str, List[Dict[str, str]]],
+        tools: Optional[List[dict]] = None,
+        callbacks: Optional[List[Any]] = None,
+        available_functions: Optional[Dict[str, Any]] = None,
+    ) -> Union[str, Any]:
+        """Simulate API calls with timeout handling and retry logic.
+
+        Args:
+            messages: Input messages for the LLM.
+            tools: Optional list of tool schemas for function calling.
+            callbacks: Optional list of callback functions.
+            available_functions: Optional dict mapping function names to callables.
+
+        Returns:
+            A response string based on whether this is the first attempt or a retry.
+
+        Raises:
+            TimeoutError: If all retry attempts fail.
+        """
+        # Record the initial call
+        self.calls.append(
+            {
+                "messages": messages,
+                "tools": tools,
+                "callbacks": callbacks,
+                "available_functions": available_functions,
+                "attempt": 0,
+            }
+        )
+
+        # Simulate retry logic
+        for attempt in range(self.max_retries):
+            # Skip the first attempt recording since we already did that above
+            if attempt == 0:
+                # Simulate a failure if fail_count > 0
+                if self.fail_count > 0:
+                    self.fail_count -= 1
+                    # If we've used all retries, raise an error
+                    if attempt == self.max_retries - 1:
+                        raise TimeoutError(
+                            f"LLM request failed after {self.max_retries} attempts"
+                        )
+                    # Otherwise, continue to the next attempt (simulating backoff)
+                    continue
+                else:
+                    # Success on first attempt
+                    return "First attempt response"
+            else:
+                # This is a retry attempt (attempt > 0)
+                # Always record retry attempts
+                self.calls.append(
+                    {
+                        "retry_attempt": attempt,
+                        "messages": messages,
+                        "tools": tools,
+                        "callbacks": callbacks,
+                        "available_functions": available_functions,
+                    }
+                )
+
+                # Simulate a failure if fail_count > 0
+                if self.fail_count > 0:
+                    self.fail_count -= 1
+                    # If we've used all retries, raise an error
+                    if attempt == self.max_retries - 1:
+                        raise TimeoutError(
+                            f"LLM request failed after {self.max_retries} attempts"
+                        )
+                    # Otherwise, continue to the next attempt (simulating backoff)
+                    continue
+                else:
+                    # Success on retry
+                    return "Response after retry"
+
+    def supports_function_calling(self) -> bool:
+        """Return True to indicate that function calling is supported.
+
+        Returns:
+            True, indicating that this LLM supports function calling.
+        """
+        return True
+
+    def supports_stop_words(self) -> bool:
+        """Return True to indicate that stop words are supported.
+
+        Returns:
+            True, indicating that this LLM supports stop words.
+        """
+        return True
+
+    def get_context_window_size(self) -> int:
+        """Return a default context window size.
+
+        Returns:
+            8192, a typical context window size for modern LLMs.
+        """
+        return 8192
+
+
+def test_timeout_handling_llm():
+    """Test a custom LLM implementation with timeout handling and retry logic."""
+    # Test successful first attempt
+    llm = TimeoutHandlingLLM()
+    response = llm.call("Test message")
+    assert response == "First attempt response"
+    assert len(llm.calls) == 1
+
+    # Test successful retry
+    llm = TimeoutHandlingLLM()
+    llm.fail_count = 1  # Fail once, then succeed
+    response = llm.call("Test message")
+    assert response == "Response after retry"
+    assert len(llm.calls) == 2  # Initial call + successful retry call
+
+    # Test failure after all retries
+    llm = TimeoutHandlingLLM(max_retries=2)
+    llm.fail_count = 2  # Fail twice, which is all retries
+    with pytest.raises(TimeoutError, match="LLM request failed after 2 attempts"):
+        llm.call("Test message")
+    assert len(llm.calls) == 2  # Initial call + failed retry attempt

tests/task_test.py

@@ -15,6 +15,7 @@ from crewai import Agent, Crew, Process, Task
 from crewai.tasks.conditional_task import ConditionalTask
 from crewai.tasks.task_output import TaskOutput
 from crewai.utilities.converter import Converter
+from crewai.utilities.string_utils import interpolate_only
 
 
 def test_task_tool_reflect_agent_tools():
@@ -786,6 +787,25 @@ def test_conditional_task_definition_based_on_dict():
     assert task.agent is None
 
 
+def test_conditional_task_copy_preserves_type():
+    task_config = {
+        "description": "Give me an integer score between 1-5 for the following title: 'The impact of AI in the future of work', check examples to based your evaluation.",
+        "expected_output": "The score of the title.",
+    }
+    original_task = Task(**task_config)
+    copied_task = original_task.copy(agents=[], task_mapping={})
+    assert isinstance(copied_task, Task)
+
+    original_conditional_config = {
+        "description": "Give me an integer score between 1-5 for the following title: 'The impact of AI in the future of work'. Check examples to base your evaluation on.",
+        "expected_output": "The score of the title.",
+        "condition": lambda x: True,
+    }
+    original_conditional_task = ConditionalTask(**original_conditional_config)
+    copied_conditional_task = original_conditional_task.copy(agents=[], task_mapping={})
+    assert isinstance(copied_conditional_task, ConditionalTask)
+
+
 def test_interpolate_inputs():
     task = Task(
         description="Give me a list of 5 interesting ideas about {topic} to explore for an article, what makes them unique and interesting.",
@@ -822,7 +842,7 @@ def test_interpolate_only():
 
     # Test JSON structure preservation
     json_string = '{"info": "Look at {placeholder}", "nested": {"val": "{nestedVal}"}}'
-    result = task.interpolate_only(
+    result = interpolate_only(
         input_string=json_string,
         inputs={"placeholder": "the data", "nestedVal": "something else"},
     )
@@ -833,20 +853,18 @@ def test_interpolate_only():
 
     # Test normal string interpolation
     normal_string = "Hello {name}, welcome to {place}!"
-    result = task.interpolate_only(
+    result = interpolate_only(
         input_string=normal_string, inputs={"name": "John", "place": "CrewAI"}
     )
     assert result == "Hello John, welcome to CrewAI!"
 
     # Test empty string
-    result = task.interpolate_only(input_string="", inputs={"unused": "value"})
+    result = interpolate_only(input_string="", inputs={"unused": "value"})
     assert result == ""
 
     # Test string with no placeholders
     no_placeholders = "Hello, this is a test"
-    result = task.interpolate_only(
-        input_string=no_placeholders, inputs={"unused": "value"}
-    )
+    result = interpolate_only(input_string=no_placeholders, inputs={"unused": "value"})
     assert result == no_placeholders
 
 
@@ -858,7 +876,7 @@ def test_interpolate_only_with_dict_inside_expected_output():
     )
 
     json_string = '{"questions": {"main_question": "What is the user\'s name?", "secondary_question": "What is the user\'s age?"}}'
-    result = task.interpolate_only(
+    result = interpolate_only(
         input_string=json_string,
         inputs={
             "questions": {
@@ -872,18 +890,16 @@ def test_interpolate_only_with_dict_inside_expected_output():
     assert result == json_string
 
     normal_string = "Hello {name}, welcome to {place}!"
-    result = task.interpolate_only(
+    result = interpolate_only(
         input_string=normal_string, inputs={"name": "John", "place": "CrewAI"}
     )
     assert result == "Hello John, welcome to CrewAI!"
 
-    result = task.interpolate_only(input_string="", inputs={"unused": "value"})
+    result = interpolate_only(input_string="", inputs={"unused": "value"})
     assert result == ""
 
     no_placeholders = "Hello, this is a test"
-    result = task.interpolate_only(
-        input_string=no_placeholders, inputs={"unused": "value"}
-    )
+    result = interpolate_only(input_string=no_placeholders, inputs={"unused": "value"})
     assert result == no_placeholders
 
 
@@ -1085,12 +1101,12 @@ def test_interpolate_with_list_of_strings():
     # Test simple list of strings
     input_str = "Available items: {items}"
     inputs = {"items": ["apple", "banana", "cherry"]}
-    result = task.interpolate_only(input_str, inputs)
+    result = interpolate_only(input_str, inputs)
     assert result == f"Available items: {inputs['items']}"
 
     # Test empty list
     empty_list_input = {"items": []}
-    result = task.interpolate_only(input_str, empty_list_input)
+    result = interpolate_only(input_str, empty_list_input)
     assert result == "Available items: []"
 
 
@@ -1106,7 +1122,7 @@ def test_interpolate_with_list_of_dicts():
             {"name": "Bob", "age": 25, "skills": ["Java", "Cloud"]},
         ]
     }
-    result = task.interpolate_only("{people}", input_data)
+    result = interpolate_only("{people}", input_data)
 
     parsed_result = eval(result)
     assert isinstance(parsed_result, list)
@@ -1138,7 +1154,7 @@ def test_interpolate_with_nested_structures():
             ],
         }
     }
-    result = task.interpolate_only("{company}", input_data)
+    result = interpolate_only("{company}", input_data)
     parsed = eval(result)
 
     assert parsed["name"] == "TechCorp"
@@ -1161,7 +1177,7 @@ def test_interpolate_with_special_characters():
             "empty": "",
         }
     }
-    result = task.interpolate_only("{special_data}", input_data)
+    result = interpolate_only("{special_data}", input_data)
     parsed = eval(result)
 
     assert parsed["quotes"] == """This has "double" and 'single' quotes"""
@@ -1188,7 +1204,7 @@ def test_interpolate_mixed_types():
             },
         }
     }
-    result = task.interpolate_only("{data}", input_data)
+    result = interpolate_only("{data}", input_data)
     parsed = eval(result)
 
     assert parsed["name"] == "Test Dataset"
@@ -1216,7 +1232,7 @@ def test_interpolate_complex_combination():
             },
         ]
     }
-    result = task.interpolate_only("{report}", input_data)
+    result = interpolate_only("{report}", input_data)
     parsed = eval(result)
 
     assert len(parsed) == 2
@@ -1233,7 +1249,7 @@ def test_interpolate_invalid_type_validation():
 
     # Test with invalid top-level type
     with pytest.raises(ValueError) as excinfo:
-        task.interpolate_only("{data}", {"data": set()})  # type: ignore we are purposely testing this failure
+        interpolate_only("{data}", {"data": set()})  # type: ignore we are purposely testing this failure
 
     assert "Unsupported type set" in str(excinfo.value)
 
@@ -1246,7 +1262,7 @@ def test_interpolate_invalid_type_validation():
         }
     }
     with pytest.raises(ValueError) as excinfo:
-        task.interpolate_only("{data}", {"data": invalid_nested})
+        interpolate_only("{data}", {"data": invalid_nested})
     assert "Unsupported type set" in str(excinfo.value)
 
 
@@ -1265,24 +1281,22 @@ def test_interpolate_custom_object_validation():
 
     # Test with custom object at top level
     with pytest.raises(ValueError) as excinfo:
-        task.interpolate_only("{obj}", {"obj": CustomObject(5)})  # type: ignore we are purposely testing this failure
+        interpolate_only("{obj}", {"obj": CustomObject(5)})  # type: ignore we are purposely testing this failure
     assert "Unsupported type CustomObject" in str(excinfo.value)
 
     # Test with nested custom object in dictionary
     with pytest.raises(ValueError) as excinfo:
-        task.interpolate_only(
-            "{data}", {"data": {"valid": 1, "invalid": CustomObject(5)}}
-        )
+        interpolate_only("{data}", {"data": {"valid": 1, "invalid": CustomObject(5)}})
     assert "Unsupported type CustomObject" in str(excinfo.value)
 
     # Test with nested custom object in list
     with pytest.raises(ValueError) as excinfo:
-        task.interpolate_only("{data}", {"data": [1, "valid", CustomObject(5)]})
+        interpolate_only("{data}", {"data": [1, "valid", CustomObject(5)]})
     assert "Unsupported type CustomObject" in str(excinfo.value)
 
     # Test with deeply nested custom object
     with pytest.raises(ValueError) as excinfo:
-        task.interpolate_only(
+        interpolate_only(
             "{data}", {"data": {"level1": {"level2": [{"level3": CustomObject(5)}]}}}
         )
     assert "Unsupported type CustomObject" in str(excinfo.value)
@@ -1306,7 +1320,7 @@ def test_interpolate_valid_complex_types():
     }
 
     # Should not raise any errors
-    result = task.interpolate_only("{data}", {"data": valid_data})
+    result = interpolate_only("{data}", {"data": valid_data})
     parsed = eval(result)
     assert parsed["name"] == "Valid Dataset"
     assert parsed["stats"]["nested"]["deeper"]["b"] == 2.5
@@ -1319,16 +1333,16 @@ def test_interpolate_edge_cases():
     )
 
     # Test empty dict and list
-    assert task.interpolate_only("{}", {"data": {}}) == "{}"
-    assert task.interpolate_only("[]", {"data": []}) == "[]"
+    assert interpolate_only("{}", {"data": {}}) == "{}"
+    assert interpolate_only("[]", {"data": []}) == "[]"
 
     # Test numeric types
-    assert task.interpolate_only("{num}", {"num": 42}) == "42"
-    assert task.interpolate_only("{num}", {"num": 3.14}) == "3.14"
+    assert interpolate_only("{num}", {"num": 42}) == "42"
+    assert interpolate_only("{num}", {"num": 3.14}) == "3.14"
 
     # Test boolean values (valid JSON types)
-    assert task.interpolate_only("{flag}", {"flag": True}) == "True"
-    assert task.interpolate_only("{flag}", {"flag": False}) == "False"
+    assert interpolate_only("{flag}", {"flag": True}) == "True"
+    assert interpolate_only("{flag}", {"flag": False}) == "False"
 
 
 def test_interpolate_valid_types():
@@ -1346,7 +1360,7 @@ def test_interpolate_valid_types():
         "nested": {"flag": True, "empty": None},
     }
 
-    result = task.interpolate_only("{data}", {"data": valid_data})
+    result = interpolate_only("{data}", {"data": valid_data})
     parsed = eval(result)
 
     assert parsed["active"] is True

tests/utilities/test_string_utils.py

@@ -0,0 +1,187 @@
+from typing import Any, Dict, List, Union
+
+import pytest
+
+from crewai.utilities.string_utils import interpolate_only
+
+
+class TestInterpolateOnly:
+    """Tests for the interpolate_only function in string_utils.py."""
+
+    def test_basic_variable_interpolation(self):
+        """Test basic variable interpolation works correctly."""
+        template = "Hello, {name}! Welcome to {company}."
+        inputs: Dict[str, Union[str, int, float, Dict[str, Any], List[Any]]] = {
+            "name": "Alice",
+            "company": "CrewAI",
+        }
+
+        result = interpolate_only(template, inputs)
+
+        assert result == "Hello, Alice! Welcome to CrewAI."
+
+    def test_multiple_occurrences_of_same_variable(self):
+        """Test that multiple occurrences of the same variable are replaced."""
+        template = "{name} is using {name}'s account."
+        inputs: Dict[str, Union[str, int, float, Dict[str, Any], List[Any]]] = {
+            "name": "Bob"
+        }
+
+        result = interpolate_only(template, inputs)
+
+        assert result == "Bob is using Bob's account."
+
+    def test_json_structure_preservation(self):
+        """Test that JSON structures are preserved and not interpolated incorrectly."""
+        template = """
+        Instructions for {agent}:
+
+        Please return the following object:
+
+        {"name": "person's name", "age": 25, "skills": ["coding", "testing"]}
+        """
+        inputs: Dict[str, Union[str, int, float, Dict[str, Any], List[Any]]] = {
+            "agent": "DevAgent"
+        }
+
+        result = interpolate_only(template, inputs)
+
+        assert "Instructions for DevAgent:" in result
+        assert (
+            '{"name": "person\'s name", "age": 25, "skills": ["coding", "testing"]}'
+            in result
+        )
+
+    def test_complex_nested_json(self):
+        """Test with complex JSON structures containing curly braces."""
+        template = """
+        {agent} needs to process:
+        {
+          "config": {
+            "nested": {
+              "value": 42
+            },
+            "arrays": [1, 2, {"inner": "value"}]
+          }
+        }
+        """
+        inputs: Dict[str, Union[str, int, float, Dict[str, Any], List[Any]]] = {
+            "agent": "DataProcessor"
+        }
+
+        result = interpolate_only(template, inputs)
+
+        assert "DataProcessor needs to process:" in result
+        assert '"nested": {' in result
+        assert '"value": 42' in result
+        assert '[1, 2, {"inner": "value"}]' in result
+
+    def test_missing_variable(self):
+        """Test that an error is raised when a required variable is missing."""
+        template = "Hello, {name}!"
+        inputs: Dict[str, Union[str, int, float, Dict[str, Any], List[Any]]] = {
+            "not_name": "Alice"
+        }
+
+        with pytest.raises(KeyError) as excinfo:
+            interpolate_only(template, inputs)
+
+        assert "template variable" in str(excinfo.value).lower()
+        assert "name" in str(excinfo.value)
+
+    def test_invalid_input_types(self):
+        """Test that an error is raised with invalid input types."""
+        template = "Hello, {name}!"
+        # Using Any for this test since we're intentionally testing an invalid type
+        inputs: Dict[str, Any] = {"name": object()}  # Object is not a valid input type
+
+        with pytest.raises(ValueError) as excinfo:
+            interpolate_only(template, inputs)
+
+        assert "unsupported type" in str(excinfo.value).lower()
+
+    def test_empty_input_string(self):
+        """Test handling of empty or None input string."""
+        inputs: Dict[str, Union[str, int, float, Dict[str, Any], List[Any]]] = {
+            "name": "Alice"
+        }
+
+        assert interpolate_only("", inputs) == ""
+        assert interpolate_only(None, inputs) == ""
+
+    def test_no_variables_in_template(self):
+        """Test a template with no variables to replace."""
+        template = "This is a static string with no variables."
+        inputs: Dict[str, Union[str, int, float, Dict[str, Any], List[Any]]] = {
+            "name": "Alice"
+        }
+
+        result = interpolate_only(template, inputs)
+
+        assert result == template
+
+    def test_variable_name_starting_with_underscore(self):
+        """Test variables starting with underscore are replaced correctly."""
+        template = "Variable: {_special_var}"
+        inputs: Dict[str, Union[str, int, float, Dict[str, Any], List[Any]]] = {
+            "_special_var": "Special Value"
+        }
+
+        result = interpolate_only(template, inputs)
+
+        assert result == "Variable: Special Value"
+
+    def test_preserves_non_matching_braces(self):
+        """Test that non-matching braces patterns are preserved."""
+        template = (
+            "This {123} and {!var} should not be replaced but {valid_var} should."
+        )
+        inputs: Dict[str, Union[str, int, float, Dict[str, Any], List[Any]]] = {
+            "valid_var": "works"
+        }
+
+        result = interpolate_only(template, inputs)
+
+        assert (
+            result == "This {123} and {!var} should not be replaced but works should."
+        )
+
+    def test_complex_mixed_scenario(self):
+        """Test a complex scenario with both valid variables and JSON structures."""
+        template = """
+        {agent_name} is working on task {task_id}.
+        
+        Instructions:
+        1. Process the data
+        2. Return results as:
+        
+        {
+          "taskId": "{task_id}",
+          "results": {
+            "processed_by": "agent_name",
+            "status": "complete",
+            "values": [1, 2, 3]
+          }
+        }
+        """
+        inputs: Dict[str, Union[str, int, float, Dict[str, Any], List[Any]]] = {
+            "agent_name": "AnalyticsAgent",
+            "task_id": "T-12345",
+        }
+
+        result = interpolate_only(template, inputs)
+
+        assert "AnalyticsAgent is working on task T-12345" in result
+        assert '"taskId": "T-12345"' in result
+        assert '"processed_by": "agent_name"' in result  # This shouldn't be replaced
+        assert '"values": [1, 2, 3]' in result
+
+    def test_empty_inputs_dictionary(self):
+        """Test that an error is raised with empty inputs dictionary."""
+        template = "Hello, {name}!"
+        inputs: Dict[str, Any] = {}
+
+        with pytest.raises(ValueError) as excinfo:
+            interpolate_only(template, inputs)
+
+        assert "inputs dictionary cannot be empty" in str(excinfo.value).lower()

uv.lock

@@ -139,6 +139,18 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/76/ac/a7305707cb852b7e16ff80eaf5692309bde30e2b1100a1fcacdc8f731d97/aiosignal-1.3.1-py3-none-any.whl", hash = "sha256:f8376fb07dd1e86a584e4fcdec80b36b7f81aac666ebc724e2c090300dd83b17", size = 7617 },
 ]
 
+[[package]]
+name = "aisuite"
+version = "0.1.10"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "httpx" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/6a/9d/c7a8a76abb9011dd2bc9a5cb8ffa8231640e20bbdae177ce9ab6cb67c66c/aisuite-0.1.10.tar.gz", hash = "sha256:170e62d4c91fecb22e82a04e058154a111cef473681171e5df7346272e77f414", size = 29052 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/58/c2/9a34a01516de107e5f9406dbfd319b6004340708101d67fa107373da4058/aisuite-0.1.10-py3-none-any.whl", hash = "sha256:c8510ebe38d6546b6a06819171e201fcaf0bf9ae020ffcfe19b6bd90430781ad", size = 43984 },
+]
+
 [[package]]
 name = "alembic"
 version = "1.13.3"
@@ -651,6 +663,9 @@ dependencies = [
 agentops = [
     { name = "agentops" },
 ]
+aisuite = [
+    { name = "aisuite" },
+]
 docling = [
     { name = "docling" },
 ]
@@ -698,6 +713,7 @@ dev = [
 [package.metadata]
 requires-dist = [
     { name = "agentops", marker = "extra == 'agentops'", specifier = ">=0.3.0" },
+    { name = "aisuite", marker = "extra == 'aisuite'", specifier = ">=0.1.10" },
     { name = "appdirs", specifier = ">=1.4.4" },
     { name = "auth0-python", specifier = ">=4.7.1" },
     { name = "blinker", specifier = ">=1.9.0" },
@@ -715,9 +731,9 @@ requires-dist = [
     { name = "openai", specifier = ">=1.13.3" },
     { name = "openpyxl", specifier = ">=3.1.5" },
     { name = "openpyxl", marker = "extra == 'openpyxl'", specifier = ">=3.1.5" },
-    { name = "opentelemetry-api", specifier = ">=1.22.0" },
-    { name = "opentelemetry-exporter-otlp-proto-http", specifier = ">=1.22.0" },
-    { name = "opentelemetry-sdk", specifier = ">=1.22.0" },
+    { name = "opentelemetry-api", specifier = ">=1.30.0" },
+    { name = "opentelemetry-exporter-otlp-proto-http", specifier = ">=1.30.0" },
+    { name = "opentelemetry-sdk", specifier = ">=1.30.0" },
     { name = "pandas", marker = "extra == 'pandas'", specifier = ">=2.2.3" },
     { name = "pdfplumber", specifier = ">=0.11.4" },
     { name = "pdfplumber", marker = "extra == 'pdfplumber'", specifier = ">=0.11.4" },
@@ -1617,39 +1633,42 @@ wheels = [
 
 [[package]]
 name = "grpcio-tools"
-version = "1.62.3"
+version = "1.67.0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "grpcio" },
     { name = "protobuf" },
     { name = "setuptools" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/54/fa/b69bd8040eafc09b88bb0ec0fea59e8aacd1a801e688af087cead213b0d0/grpcio-tools-1.62.3.tar.gz", hash = "sha256:7c7136015c3d62c3eef493efabaf9e3380e3e66d24ee8e94c01cb71377f57833", size = 4538520 }
+sdist = { url = "https://files.pythonhosted.org/packages/e7/f8/62e15867651b72f6f95313e21d81f5f1c210b69a4cc664aecf52ec4c8a53/grpcio_tools-1.67.0.tar.gz", hash = "sha256:181b3d4e61b83142c182ec366f3079b0023509743986e54c9465ca38cac255f8", size = 5159163 }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/ff/eb/eb0a3aa9480c3689d31fd2ad536df6a828e97a60f667c8a93d05bdf07150/grpcio_tools-1.62.3-cp310-cp310-macosx_12_0_universal2.whl", hash = "sha256:2f968b049c2849540751ec2100ab05e8086c24bead769ca734fdab58698408c1", size = 5117556 },
-    { url = "https://files.pythonhosted.org/packages/f3/fb/8be3dda485f7fab906bfa02db321c3ecef953a87cdb5f6572ca08b187bcb/grpcio_tools-1.62.3-cp310-cp310-manylinux_2_17_aarch64.whl", hash = "sha256:0a8c0c4724ae9c2181b7dbc9b186df46e4f62cb18dc184e46d06c0ebeccf569e", size = 2719330 },
-    { url = "https://files.pythonhosted.org/packages/63/de/6978f8d10066e240141cd63d1fbfc92818d96bb53427074f47a8eda921e1/grpcio_tools-1.62.3-cp310-cp310-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:5782883a27d3fae8c425b29a9d3dcf5f47d992848a1b76970da3b5a28d424b26", size = 3070818 },
-    { url = "https://files.pythonhosted.org/packages/74/34/bb8f816893fc73fd6d830e895e8638d65d13642bb7a434f9175c5ca7da11/grpcio_tools-1.62.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f3d812daffd0c2d2794756bd45a353f89e55dc8f91eb2fc840c51b9f6be62667", size = 2804993 },
-    { url = "https://files.pythonhosted.org/packages/78/60/b2198d7db83293cdb9760fc083f077c73e4c182da06433b3b157a1567d06/grpcio_tools-1.62.3-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:b47d0dda1bdb0a0ba7a9a6de88e5a1ed61f07fad613964879954961e36d49193", size = 3684915 },
-    { url = "https://files.pythonhosted.org/packages/61/20/56dbdc4ecb14d42a03cd164ff45e6e84572bbe61ee59c50c39f4d556a8d5/grpcio_tools-1.62.3-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:ca246dffeca0498be9b4e1ee169b62e64694b0f92e6d0be2573e65522f39eea9", size = 3297482 },
-    { url = "https://files.pythonhosted.org/packages/4a/dc/e417a313c905744ce8cedf1e1edd81c41dc45ff400ae1c45080e18f26712/grpcio_tools-1.62.3-cp310-cp310-win32.whl", hash = "sha256:6a56d344b0bab30bf342a67e33d386b0b3c4e65868ffe93c341c51e1a8853ca5", size = 909793 },
-    { url = "https://files.pythonhosted.org/packages/d9/69/75e7ebfd8d755d3e7be5c6d1aa6d13220f5bba3a98965e4b50c329046777/grpcio_tools-1.62.3-cp310-cp310-win_amd64.whl", hash = "sha256:710fecf6a171dcbfa263a0a3e7070e0df65ba73158d4c539cec50978f11dad5d", size = 1052459 },
-    { url = "https://files.pythonhosted.org/packages/23/52/2dfe0a46b63f5ebcd976570aa5fc62f793d5a8b169e211c6a5aede72b7ae/grpcio_tools-1.62.3-cp311-cp311-macosx_10_10_universal2.whl", hash = "sha256:703f46e0012af83a36082b5f30341113474ed0d91e36640da713355cd0ea5d23", size = 5147623 },
-    { url = "https://files.pythonhosted.org/packages/f0/2e/29fdc6c034e058482e054b4a3c2432f84ff2e2765c1342d4f0aa8a5c5b9a/grpcio_tools-1.62.3-cp311-cp311-manylinux_2_17_aarch64.whl", hash = "sha256:7cc83023acd8bc72cf74c2edbe85b52098501d5b74d8377bfa06f3e929803492", size = 2719538 },
-    { url = "https://files.pythonhosted.org/packages/f9/60/abe5deba32d9ec2c76cdf1a2f34e404c50787074a2fee6169568986273f1/grpcio_tools-1.62.3-cp311-cp311-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:7ff7d58a45b75df67d25f8f144936a3e44aabd91afec833ee06826bd02b7fbe7", size = 3070964 },
-    { url = "https://files.pythonhosted.org/packages/bc/ad/e2b066684c75f8d9a48508cde080a3a36618064b9cadac16d019ca511444/grpcio_tools-1.62.3-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7f2483ea232bd72d98a6dc6d7aefd97e5bc80b15cd909b9e356d6f3e326b6e43", size = 2805003 },
-    { url = "https://files.pythonhosted.org/packages/9c/3f/59bf7af786eae3f9d24ee05ce75318b87f541d0950190ecb5ffb776a1a58/grpcio_tools-1.62.3-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:962c84b4da0f3b14b3cdb10bc3837ebc5f136b67d919aea8d7bb3fd3df39528a", size = 3685154 },
-    { url = "https://files.pythonhosted.org/packages/f1/79/4dd62478b91e27084c67b35a2316ce8a967bd8b6cb8d6ed6c86c3a0df7cb/grpcio_tools-1.62.3-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:8ad0473af5544f89fc5a1ece8676dd03bdf160fb3230f967e05d0f4bf89620e3", size = 3297942 },
-    { url = "https://files.pythonhosted.org/packages/b8/cb/86449ecc58bea056b52c0b891f26977afc8c4464d88c738f9648da941a75/grpcio_tools-1.62.3-cp311-cp311-win32.whl", hash = "sha256:db3bc9fa39afc5e4e2767da4459df82b095ef0cab2f257707be06c44a1c2c3e5", size = 910231 },
-    { url = "https://files.pythonhosted.org/packages/45/a4/9736215e3945c30ab6843280b0c6e1bff502910156ea2414cd77fbf1738c/grpcio_tools-1.62.3-cp311-cp311-win_amd64.whl", hash = "sha256:e0898d412a434e768a0c7e365acabe13ff1558b767e400936e26b5b6ed1ee51f", size = 1052496 },
-    { url = "https://files.pythonhosted.org/packages/2a/a5/d6887eba415ce318ae5005e8dfac3fa74892400b54b6d37b79e8b4f14f5e/grpcio_tools-1.62.3-cp312-cp312-macosx_10_10_universal2.whl", hash = "sha256:d102b9b21c4e1e40af9a2ab3c6d41afba6bd29c0aa50ca013bf85c99cdc44ac5", size = 5147690 },
-    { url = "https://files.pythonhosted.org/packages/8a/7c/3cde447a045e83ceb4b570af8afe67ffc86896a2fe7f59594dc8e5d0a645/grpcio_tools-1.62.3-cp312-cp312-manylinux_2_17_aarch64.whl", hash = "sha256:0a52cc9444df978438b8d2332c0ca99000521895229934a59f94f37ed896b133", size = 2720538 },
-    { url = "https://files.pythonhosted.org/packages/88/07/f83f2750d44ac4f06c07c37395b9c1383ef5c994745f73c6bfaf767f0944/grpcio_tools-1.62.3-cp312-cp312-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:141d028bf5762d4a97f981c501da873589df3f7e02f4c1260e1921e565b376fa", size = 3071571 },
-    { url = "https://files.pythonhosted.org/packages/37/74/40175897deb61e54aca716bc2e8919155b48f33aafec8043dda9592d8768/grpcio_tools-1.62.3-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:47a5c093ab256dec5714a7a345f8cc89315cb57c298b276fa244f37a0ba507f0", size = 2806207 },
-    { url = "https://files.pythonhosted.org/packages/ec/ee/d8de915105a217cbcb9084d684abdc032030dcd887277f2ef167372287fe/grpcio_tools-1.62.3-cp312-cp312-musllinux_1_1_i686.whl", hash = "sha256:f6831fdec2b853c9daa3358535c55eed3694325889aa714070528cf8f92d7d6d", size = 3685815 },
-    { url = "https://files.pythonhosted.org/packages/fd/d9/4360a6c12be3d7521b0b8c39e5d3801d622fbb81cc2721dbd3eee31e28c8/grpcio_tools-1.62.3-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:e02d7c1a02e3814c94ba0cfe43d93e872c758bd8fd5c2797f894d0c49b4a1dfc", size = 3298378 },
-    { url = "https://files.pythonhosted.org/packages/29/3b/7cdf4a9e5a3e0a35a528b48b111355cd14da601413a4f887aa99b6da468f/grpcio_tools-1.62.3-cp312-cp312-win32.whl", hash = "sha256:b881fd9505a84457e9f7e99362eeedd86497b659030cf57c6f0070df6d9c2b9b", size = 910416 },
-    { url = "https://files.pythonhosted.org/packages/6c/66/dd3ec249e44c1cc15e902e783747819ed41ead1336fcba72bf841f72c6e9/grpcio_tools-1.62.3-cp312-cp312-win_amd64.whl", hash = "sha256:11c625eebefd1fd40a228fc8bae385e448c7e32a6ae134e43cf13bbc23f902b7", size = 1052856 },
+    { url = "https://files.pythonhosted.org/packages/91/9d/7608eb89b41433a49dbf96f56d9c05b3a5ba08951702d54c368d370ab6aa/grpcio_tools-1.67.0-cp310-cp310-linux_armv7l.whl", hash = "sha256:12aa38af76b5ef00a55808c7c374ed18d5dc7cc8081b717e56da3c50df1776e2", size = 2308120 },
+    { url = "https://files.pythonhosted.org/packages/93/f2/d8cbc35e63bba98e4352427d01c64801fef9e9d9cd7fc5eea0538128e0e6/grpcio_tools-1.67.0-cp310-cp310-macosx_12_0_universal2.whl", hash = "sha256:b0b03d055127bbc7c629454804b53b5cad2cedfcf904576d159a8a04c22b8e66", size = 5500124 },
+    { url = "https://files.pythonhosted.org/packages/eb/b5/131d0eac92205d0ae3d3f7eecf655884ef7746aecac5a93520fb83d907d0/grpcio_tools-1.67.0-cp310-cp310-manylinux_2_17_aarch64.whl", hash = "sha256:02b0b50c59a8f7428326197027a2f586d216c46138c547f861533c46bff78bfe", size = 2282058 },
+    { url = "https://files.pythonhosted.org/packages/3f/3f/5e4de8d7fe38e8e42567a49a39f77d67e2905b00c69165e2e88f9d3005ac/grpcio_tools-1.67.0-cp310-cp310-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:b2afdfe151ed9edbd4a3fd646716f83b58010769c57f9c0aa1cf4c3bfb1240a8", size = 2617363 },
+    { url = "https://files.pythonhosted.org/packages/eb/53/3eb4eb7c178a229676d1ff0bcda640ebc0a104d12cdbd884f6796d118c56/grpcio_tools-1.67.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:fc3eeb87575b2b360c5ef5aef22eb76cfdd6a255d2f628a48ab0e5a61a0039fb", size = 2416026 },
+    { url = "https://files.pythonhosted.org/packages/a6/9a/9c584d21ed1fb8f7adac6135a569c9b3b1378b6b467fba8d94d14de70606/grpcio_tools-1.67.0-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:ead78089c4771605a1ff8894e47f2267440693f1beeee06fd5a788aede83370f", size = 3224904 },
+    { url = "https://files.pythonhosted.org/packages/93/6a/dab92a7aa1bae0d2e0735462fbde778011916e5124d7ee9b52d214f42552/grpcio_tools-1.67.0-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:0671dcdccef09ca4eb415c1d6f470a857c6486733c146676f6810a3ade1d42cb", size = 2870381 },
+    { url = "https://files.pythonhosted.org/packages/49/be/3f2c958ef65161f3eeae5a1013358ca3c2eab25174ec4fc8d46b6d6146c8/grpcio_tools-1.67.0-cp310-cp310-win32.whl", hash = "sha256:a7398d90b8c7da479aec8f853d3664d5a93c209f8ac3bd41cb7ae4e8677a45c6", size = 941140 },
+    { url = "https://files.pythonhosted.org/packages/17/e9/461db9af08badc647659fa4a382ab546981ebccb413fc625e4b7c0413305/grpcio_tools-1.67.0-cp310-cp310-win_amd64.whl", hash = "sha256:f7e7d70a74df7e07be7cceaa694b7e8e5f3bef8e0299906f60885ecf7a40adb4", size = 1091151 },
+    { url = "https://files.pythonhosted.org/packages/cd/0d/88f181eecef84c9c8c009fa4d49ce812a5717539b75aacea4a7be8b9587c/grpcio_tools-1.67.0-cp311-cp311-linux_armv7l.whl", hash = "sha256:655716bf931a22a090134d87953710033640996d31e36f5f9b0106ff5f552d8e", size = 2307990 },
+    { url = "https://files.pythonhosted.org/packages/de/22/94855e18588800c96eca95af3be918249f635e4635e3e46895949b0ca27e/grpcio_tools-1.67.0-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:484ae782f9d3ff58e0bbb2f4cad14d5f5d9132fc701835b1dffd2c2a06f73ba6", size = 5526488 },
+    { url = "https://files.pythonhosted.org/packages/c3/c7/086f6c287fed85c2a5e19cb457a42a0eae2df9534666ed252947170daf8e/grpcio_tools-1.67.0-cp311-cp311-manylinux_2_17_aarch64.whl", hash = "sha256:f3e34de876efe1273f91e25ef241e449ed7f9411472dd9ff56d2039618017c30", size = 2282139 },
+    { url = "https://files.pythonhosted.org/packages/40/1a/d8e2171ef7b5b1fda54fa2dc82807725c9e31dd6b4878e9d68ab8f3c48b7/grpcio_tools-1.67.0-cp311-cp311-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:d8301719edde2c3d388995703cdd962f558b76e9750405f772dce61402e4c3d0", size = 2617333 },
+    { url = "https://files.pythonhosted.org/packages/08/e8/e2b0a3e5890ad650d0cc9d92227f87a407784a9fc110438b85d01cf1ec71/grpcio_tools-1.67.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1629ea246044ccd473d9ac4c9f137a440d830b5e08d35225e1b354dbbb15b75d", size = 2415805 },
+    { url = "https://files.pythonhosted.org/packages/6a/43/a1731299e1662c24d89795a8ae4bb725f4a8a0c8e2dc6e12d3276eb96e14/grpcio_tools-1.67.0-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:d77a3c5cec0065267ca1a0b2589ececd1277ce25aa67f13ec50c816ee6f26f7f", size = 3224764 },
+    { url = "https://files.pythonhosted.org/packages/5d/03/968dd4b8de9ec4c6d287a8ba8b844f515a2cfcb350acefdb1fcb6f2945d9/grpcio_tools-1.67.0-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:c9bf992bcc7d9e6eaa20705056e1b955593092a38cec1746fef389d873ab2056", size = 2870440 },
+    { url = "https://files.pythonhosted.org/packages/9f/ea/e6bb028fec6f37aace620bd0a68e7c369bc975ece940dd3de08a2ef66edc/grpcio_tools-1.67.0-cp311-cp311-win32.whl", hash = "sha256:7e6e3db119c38629e0767cdb2ee18726ecc87e2249117d4c9e7ce06ea8c894ea", size = 940888 },
+    { url = "https://files.pythonhosted.org/packages/e5/26/b6f98fc9c1e6b8fa5b676bbb07e2bc70f388d4c513140fa38ffa9a15b934/grpcio_tools-1.67.0-cp311-cp311-win_amd64.whl", hash = "sha256:c6c27aec301a0e6cf231f9ee1c467c64002af51170fa7c0f3bb10bbfcd03fee7", size = 1091094 },
+    { url = "https://files.pythonhosted.org/packages/d6/b6/57e67c0244db8d7c0c312041293b806bfb1c9d66c26159e6faf39cc10356/grpcio_tools-1.67.0-cp312-cp312-linux_armv7l.whl", hash = "sha256:dca7f053cbdb26a587d4410ddb893877c585fb60a31f22fdd128e4f7c4dab27c", size = 2307646 },
+    { url = "https://files.pythonhosted.org/packages/52/43/837f08b85b04ac225aebe1d7da1a7a79fc313f231306c865b5112cef7dc4/grpcio_tools-1.67.0-cp312-cp312-macosx_10_9_universal2.whl", hash = "sha256:de8c4f68ffa690769d84329c17c7fdd5fbe4c61b8f8a0de03f1ad8ef8bb06963", size = 5525447 },
+    { url = "https://files.pythonhosted.org/packages/3e/5f/adb8b87f5c403ba53529b6645184beddfa63abf2c524a6dabaa430e6bab3/grpcio_tools-1.67.0-cp312-cp312-manylinux_2_17_aarch64.whl", hash = "sha256:6e4ecb24c27a78f09fead45d4ed873805d6026124ccb6793b6fb93a490b78ddf", size = 2281767 },
+    { url = "https://files.pythonhosted.org/packages/6e/cd/3d6a7971e28b96cb618abb281325517443744ecfe48aa03f27a17cd5d4e1/grpcio_tools-1.67.0-cp312-cp312-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:004d6ef1b5f724480f05c0bdc904bf8c78c43d633c537d99abe51b52ce0cadeb", size = 2617363 },
+    { url = "https://files.pythonhosted.org/packages/2d/a9/b8f1eae3db0f1b6f9548bd2032f48cb6f1ec9bc6781436d52dff4b352fab/grpcio_tools-1.67.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9dd257072c86eb9b36791b3674a513a215ba76bbdd38fc228f0e8c6dc5ce3524", size = 2415322 },
+    { url = "https://files.pythonhosted.org/packages/9b/fc/0045bf2e5c97a5ffe0ff2c9a4e4a62894402e8d7094162c2084a809c9d1c/grpcio_tools-1.67.0-cp312-cp312-musllinux_1_1_i686.whl", hash = "sha256:a8cca551317ed26e17d13b6ee27b2bd62f5fe9b3842b4e88389deb984f995848", size = 3225044 },
+    { url = "https://files.pythonhosted.org/packages/dc/73/eaf40958dd648dd98a0fbd30df2b51c5beb7ee24127c1f0bb99ea44fd435/grpcio_tools-1.67.0-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:a7ac3b4f837c693142f6688b629d1f6408f6ab250d927159b572555f5339fe25", size = 2870418 },
+    { url = "https://files.pythonhosted.org/packages/b4/77/e307e91816123444ff657bbae2269cb912f31a9390118ed371bde9d0c1f3/grpcio_tools-1.67.0-cp312-cp312-win32.whl", hash = "sha256:95feec33388e2a8f72c360a68efe6f0bfed9c771e94d21b7f2359d0010f60219", size = 940540 },
+    { url = "https://files.pythonhosted.org/packages/be/2a/0c1a64e88fbc17235b68d3178be6cf4a69aea5bd1deed683c0bbd2f5e9f9/grpcio_tools-1.67.0-cp312-cp312-win_amd64.whl", hash = "sha256:50a31d035193ebe7154181eac84734e25bdcdb36adba849d3b2adf1c3b0c382b", size = 1090427 },
 ]
 
 [[package]]
@@ -3116,32 +3135,32 @@ wheels = [
 
 [[package]]
 name = "opentelemetry-api"
-version = "1.27.0"
+version = "1.31.1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "deprecated" },
     { name = "importlib-metadata" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/c9/83/93114b6de85a98963aec218a51509a52ed3f8de918fe91eb0f7299805c3f/opentelemetry_api-1.27.0.tar.gz", hash = "sha256:ed673583eaa5f81b5ce5e86ef7cdaf622f88ef65f0b9aab40b843dcae5bef342", size = 62693 }
+sdist = { url = "https://files.pythonhosted.org/packages/8a/cf/db26ab9d748bf50d6edf524fb863aa4da616ba1ce46c57a7dff1112b73fb/opentelemetry_api-1.31.1.tar.gz", hash = "sha256:137ad4b64215f02b3000a0292e077641c8611aab636414632a9b9068593b7e91", size = 64059 }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/fb/1f/737dcdbc9fea2fa96c1b392ae47275165a7c641663fbb08a8d252968eed2/opentelemetry_api-1.27.0-py3-none-any.whl", hash = "sha256:953d5871815e7c30c81b56d910c707588000fff7a3ca1c73e6531911d53065e7", size = 63970 },
+    { url = "https://files.pythonhosted.org/packages/6c/c8/86557ff0da32f3817bc4face57ea35cfdc2f9d3bcefd42311ef860dcefb7/opentelemetry_api-1.31.1-py3-none-any.whl", hash = "sha256:1511a3f470c9c8a32eeea68d4ea37835880c0eed09dd1a0187acc8b1301da0a1", size = 65197 },
 ]
 
 [[package]]
 name = "opentelemetry-exporter-otlp-proto-common"
-version = "1.27.0"
+version = "1.31.1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "opentelemetry-proto" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/cd/2e/7eaf4ba595fb5213cf639c9158dfb64aacb2e4c7d74bfa664af89fa111f4/opentelemetry_exporter_otlp_proto_common-1.27.0.tar.gz", hash = "sha256:159d27cf49f359e3798c4c3eb8da6ef4020e292571bd8c5604a2a573231dd5c8", size = 17860 }
+sdist = { url = "https://files.pythonhosted.org/packages/53/e5/48662d9821d28f05ab8350a9a986ab99d9c0e8b23f8ff391c8df82742a9c/opentelemetry_exporter_otlp_proto_common-1.31.1.tar.gz", hash = "sha256:c748e224c01f13073a2205397ba0e415dcd3be9a0f95101ba4aace5fc730e0da", size = 20627 }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/41/27/4610ab3d9bb3cde4309b6505f98b3aabca04a26aa480aa18cede23149837/opentelemetry_exporter_otlp_proto_common-1.27.0-py3-none-any.whl", hash = "sha256:675db7fffcb60946f3a5c43e17d1168a3307a94a930ecf8d2ea1f286f3d4f79a", size = 17848 },
+    { url = "https://files.pythonhosted.org/packages/82/70/134282413000a3fc02e6b4e301b8c5d7127c43b50bd23cddbaf406ab33ff/opentelemetry_exporter_otlp_proto_common-1.31.1-py3-none-any.whl", hash = "sha256:7cadf89dbab12e217a33c5d757e67c76dd20ce173f8203e7370c4996f2e9efd8", size = 18823 },
 ]
 
 [[package]]
 name = "opentelemetry-exporter-otlp-proto-grpc"
-version = "1.27.0"
+version = "1.31.1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "deprecated" },
@@ -3152,14 +3171,14 @@ dependencies = [
     { name = "opentelemetry-proto" },
     { name = "opentelemetry-sdk" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/a1/d0/c1e375b292df26e0ffebf194e82cd197e4c26cc298582bda626ce3ce74c5/opentelemetry_exporter_otlp_proto_grpc-1.27.0.tar.gz", hash = "sha256:af6f72f76bcf425dfb5ad11c1a6d6eca2863b91e63575f89bb7b4b55099d968f", size = 26244 }
+sdist = { url = "https://files.pythonhosted.org/packages/0f/37/6ce465827ac69c52543afb5534146ccc40f54283a3a8a71ef87c91eb8933/opentelemetry_exporter_otlp_proto_grpc-1.31.1.tar.gz", hash = "sha256:c7f66b4b333c52248dc89a6583506222c896c74824d5d2060b818ae55510939a", size = 26620 }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/8d/80/32217460c2c64c0568cea38410124ff680a9b65f6732867bbf857c4d8626/opentelemetry_exporter_otlp_proto_grpc-1.27.0-py3-none-any.whl", hash = "sha256:56b5bbd5d61aab05e300d9d62a6b3c134827bbd28d0b12f2649c2da368006c9e", size = 18541 },
+    { url = "https://files.pythonhosted.org/packages/ee/25/9974fa3a431d7499bd9d179fb9bd7daaa3ad9eba3313f72da5226b6d02df/opentelemetry_exporter_otlp_proto_grpc-1.31.1-py3-none-any.whl", hash = "sha256:f4055ad2c9a2ea3ae00cbb927d6253233478b3b87888e197d34d095a62305fae", size = 18588 },
 ]
 
 [[package]]
 name = "opentelemetry-exporter-otlp-proto-http"
-version = "1.27.0"
+version = "1.31.1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "deprecated" },
@@ -3170,28 +3189,29 @@ dependencies = [
     { name = "opentelemetry-sdk" },
     { name = "requests" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/31/0a/f05c55e8913bf58a033583f2580a0ec31a5f4cf2beacc9e286dcb74d6979/opentelemetry_exporter_otlp_proto_http-1.27.0.tar.gz", hash = "sha256:2103479092d8eb18f61f3fbff084f67cc7f2d4a7d37e75304b8b56c1d09ebef5", size = 15059 }
+sdist = { url = "https://files.pythonhosted.org/packages/6d/9c/d8718fce3d14042beab5a41c8e17be1864c48d2067be3a99a5652d2414a3/opentelemetry_exporter_otlp_proto_http-1.31.1.tar.gz", hash = "sha256:723bd90eb12cfb9ae24598641cb0c92ca5ba9f1762103902f6ffee3341ba048e", size = 15140 }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/2d/8d/4755884afc0b1db6000527cac0ca17273063b6142c773ce4ecd307a82e72/opentelemetry_exporter_otlp_proto_http-1.27.0-py3-none-any.whl", hash = "sha256:688027575c9da42e179a69fe17e2d1eba9b14d81de8d13553a21d3114f3b4d75", size = 17203 },
+    { url = "https://files.pythonhosted.org/packages/f2/19/5041dbfdd0b2a6ab340596693759bfa7dcfa8f30b9fa7112bb7117358571/opentelemetry_exporter_otlp_proto_http-1.31.1-py3-none-any.whl", hash = "sha256:5dee1f051f096b13d99706a050c39b08e3f395905f29088bfe59e54218bd1cf4", size = 17257 },
 ]
 
 [[package]]
 name = "opentelemetry-instrumentation"
-version = "0.48b0"
+version = "0.52b1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "opentelemetry-api" },
-    { name = "setuptools" },
+    { name = "opentelemetry-semantic-conventions" },
+    { name = "packaging" },
     { name = "wrapt" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/04/0e/d9394839af5d55c8feb3b22cd11138b953b49739b20678ca96289e30f904/opentelemetry_instrumentation-0.48b0.tar.gz", hash = "sha256:94929685d906380743a71c3970f76b5f07476eea1834abd5dd9d17abfe23cc35", size = 24724 }
+sdist = { url = "https://files.pythonhosted.org/packages/49/c9/c52d444576b0776dbee71d2a4485be276cf46bec0123a5ba2f43f0cf7cde/opentelemetry_instrumentation-0.52b1.tar.gz", hash = "sha256:739f3bfadbbeec04dd59297479e15660a53df93c131d907bb61052e3d3c1406f", size = 28406 }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/0a/7f/405c41d4f359121376c9d5117dcf68149b8122d3f6c718996d037bd4d800/opentelemetry_instrumentation-0.48b0-py3-none-any.whl", hash = "sha256:a69750dc4ba6a5c3eb67986a337185a25b739966d80479befe37b546fc870b44", size = 29449 },
+    { url = "https://files.pythonhosted.org/packages/61/dd/a2b35078170941990e7a5194b9600fa75868958a9a2196a752da0e7b97a0/opentelemetry_instrumentation-0.52b1-py3-none-any.whl", hash = "sha256:8c0059c4379d77bbd8015c8d8476020efe873c123047ec069bb335e4b8717477", size = 31036 },
 ]
 
 [[package]]
 name = "opentelemetry-instrumentation-asgi"
-version = "0.48b0"
+version = "0.52b1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "asgiref" },
@@ -3200,14 +3220,14 @@ dependencies = [
     { name = "opentelemetry-semantic-conventions" },
     { name = "opentelemetry-util-http" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/44/ac/fd3d40bab3234ec3f5c052a815100676baaae1832fa1067935f11e5c59c6/opentelemetry_instrumentation_asgi-0.48b0.tar.gz", hash = "sha256:04c32174b23c7fa72ddfe192dad874954968a6a924608079af9952964ecdf785", size = 23435 }
+sdist = { url = "https://files.pythonhosted.org/packages/bc/db/79bdc2344b38e60fecc7e99159a3f5b4c0e1acec8de305fba0a713cc3692/opentelemetry_instrumentation_asgi-0.52b1.tar.gz", hash = "sha256:a6dbce9cb5b2c2f45ce4817ad21f44c67fd328358ad3ab911eb46f0be67f82ec", size = 24203 }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/db/74/a0e0d38622856597dd8e630f2bd793760485eb165708e11b8be1696bbb5a/opentelemetry_instrumentation_asgi-0.48b0-py3-none-any.whl", hash = "sha256:ddb1b5fc800ae66e85a4e2eca4d9ecd66367a8c7b556169d9e7b57e10676e44d", size = 15958 },
+    { url = "https://files.pythonhosted.org/packages/19/de/39ec078ae94a365d2f434b7e25886c267864aca5695b48fa5b60f80fbfb3/opentelemetry_instrumentation_asgi-0.52b1-py3-none-any.whl", hash = "sha256:f7179f477ed665ba21871972f979f21e8534edb971232e11920c8a22f4759236", size = 16338 },
 ]
 
 [[package]]
 name = "opentelemetry-instrumentation-fastapi"
-version = "0.48b0"
+version = "0.52b1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "opentelemetry-api" },
@@ -3216,57 +3236,57 @@ dependencies = [
     { name = "opentelemetry-semantic-conventions" },
     { name = "opentelemetry-util-http" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/58/20/43477da5850ef2cd3792715d442aecd051e885e0603b6ee5783b2104ba8f/opentelemetry_instrumentation_fastapi-0.48b0.tar.gz", hash = "sha256:21a72563ea412c0b535815aeed75fc580240f1f02ebc72381cfab672648637a2", size = 18497 }
+sdist = { url = "https://files.pythonhosted.org/packages/30/01/d159829077f2795c716445df6f8edfdd33391e82d712ba4613fb62b99dc5/opentelemetry_instrumentation_fastapi-0.52b1.tar.gz", hash = "sha256:d26ab15dc49e041301d5c2571605b8f5c3a6ee4a85b60940338f56c120221e98", size = 19247 }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/ee/50/745ab075a3041b7a5f29a579d2c28eaad54f64b4589d8f9fd364c62cf0f3/opentelemetry_instrumentation_fastapi-0.48b0-py3-none-any.whl", hash = "sha256:afeb820a59e139d3e5d96619600f11ce0187658b8ae9e3480857dd790bc024f2", size = 11777 },
+    { url = "https://files.pythonhosted.org/packages/23/89/acef7f625b218523873e32584dc5243d95ffa4facba737fd8b854c049c58/opentelemetry_instrumentation_fastapi-0.52b1-py3-none-any.whl", hash = "sha256:73c8804f053c5eb2fd2c948218bff9561f1ef65e89db326a6ab0b5bf829969f4", size = 12114 },
 ]
 
 [[package]]
 name = "opentelemetry-proto"
-version = "1.27.0"
+version = "1.31.1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "protobuf" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/9a/59/959f0beea798ae0ee9c979b90f220736fbec924eedbefc60ca581232e659/opentelemetry_proto-1.27.0.tar.gz", hash = "sha256:33c9345d91dafd8a74fc3d7576c5a38f18b7fdf8d02983ac67485386132aedd6", size = 34749 }
+sdist = { url = "https://files.pythonhosted.org/packages/5b/b0/e763f335b9b63482f1f31f46f9299c4d8388e91fc12737aa14fdb5d124ac/opentelemetry_proto-1.31.1.tar.gz", hash = "sha256:d93e9c2b444e63d1064fb50ae035bcb09e5822274f1683886970d2734208e790", size = 34363 }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/94/56/3d2d826834209b19a5141eed717f7922150224d1a982385d19a9444cbf8d/opentelemetry_proto-1.27.0-py3-none-any.whl", hash = "sha256:b133873de5581a50063e1e4b29cdcf0c5e253a8c2d8dc1229add20a4c3830ace", size = 52464 },
+    { url = "https://files.pythonhosted.org/packages/b6/f1/3baee86eab4f1b59b755f3c61a9b5028f380c88250bb9b7f89340502dbba/opentelemetry_proto-1.31.1-py3-none-any.whl", hash = "sha256:1398ffc6d850c2f1549ce355744e574c8cd7c1dba3eea900d630d52c41d07178", size = 55854 },
 ]
 
 [[package]]
 name = "opentelemetry-sdk"
-version = "1.27.0"
+version = "1.31.1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "opentelemetry-api" },
     { name = "opentelemetry-semantic-conventions" },
     { name = "typing-extensions" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/0d/9a/82a6ac0f06590f3d72241a587cb8b0b751bd98728e896cc4cbd4847248e6/opentelemetry_sdk-1.27.0.tar.gz", hash = "sha256:d525017dea0ccce9ba4e0245100ec46ecdc043f2d7b8315d56b19aff0904fa6f", size = 145019 }
+sdist = { url = "https://files.pythonhosted.org/packages/63/d9/4fe159908a63661e9e635e66edc0d0d816ed20cebcce886132b19ae87761/opentelemetry_sdk-1.31.1.tar.gz", hash = "sha256:c95f61e74b60769f8ff01ec6ffd3d29684743404603df34b20aa16a49dc8d903", size = 159523 }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/c1/bd/a6602e71e315055d63b2ff07172bd2d012b4cba2d4e00735d74ba42fc4d6/opentelemetry_sdk-1.27.0-py3-none-any.whl", hash = "sha256:365f5e32f920faf0fd9e14fdfd92c086e317eaa5f860edba9cdc17a380d9197d", size = 110505 },
+    { url = "https://files.pythonhosted.org/packages/bc/36/758e5d3746bc86a2af20aa5e2236a7c5aa4264b501dc0e9f40efd9078ef0/opentelemetry_sdk-1.31.1-py3-none-any.whl", hash = "sha256:882d021321f223e37afaca7b4e06c1d8bbc013f9e17ff48a7aa017460a8e7dae", size = 118866 },
 ]
 
 [[package]]
 name = "opentelemetry-semantic-conventions"
-version = "0.48b0"
+version = "0.52b1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "deprecated" },
     { name = "opentelemetry-api" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/0a/89/1724ad69f7411772446067cdfa73b598694c8c91f7f8c922e344d96d81f9/opentelemetry_semantic_conventions-0.48b0.tar.gz", hash = "sha256:12d74983783b6878162208be57c9effcb89dc88691c64992d70bb89dc00daa1a", size = 89445 }
+sdist = { url = "https://files.pythonhosted.org/packages/06/8c/599f9f27cff097ec4d76fbe9fe6d1a74577ceec52efe1a999511e3c42ef5/opentelemetry_semantic_conventions-0.52b1.tar.gz", hash = "sha256:7b3d226ecf7523c27499758a58b542b48a0ac8d12be03c0488ff8ec60c5bae5d", size = 111275 }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/b7/7a/4f0063dbb0b6c971568291a8bc19a4ca70d3c185db2d956230dd67429dfc/opentelemetry_semantic_conventions-0.48b0-py3-none-any.whl", hash = "sha256:a0de9f45c413a8669788a38569c7e0a11ce6ce97861a628cca785deecdc32a1f", size = 149685 },
+    { url = "https://files.pythonhosted.org/packages/98/be/d4ba300cfc1d4980886efbc9b48ee75242b9fcf940d9c4ccdc9ef413a7cf/opentelemetry_semantic_conventions-0.52b1-py3-none-any.whl", hash = "sha256:72b42db327e29ca8bb1b91e8082514ddf3bbf33f32ec088feb09526ade4bc77e", size = 183409 },
 ]
 
 [[package]]
 name = "opentelemetry-util-http"
-version = "0.48b0"
+version = "0.52b1"
 source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/d6/d7/185c494754340e0a3928fd39fde2616ee78f2c9d66253affaad62d5b7935/opentelemetry_util_http-0.48b0.tar.gz", hash = "sha256:60312015153580cc20f322e5cdc3d3ecad80a71743235bdb77716e742814623c", size = 7863 }
+sdist = { url = "https://files.pythonhosted.org/packages/23/3f/16a4225a953bbaae7d800140ed99813f092ea3071ba7780683299a87049b/opentelemetry_util_http-0.52b1.tar.gz", hash = "sha256:c03c8c23f1b75fadf548faece7ead3aecd50761c5593a2b2831b48730eee5b31", size = 8044 }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/ad/2e/36097c0a4d0115b8c7e377c90bab7783ac183bc5cb4071308f8959454311/opentelemetry_util_http-0.48b0-py3-none-any.whl", hash = "sha256:76f598af93aab50328d2a69c786beaedc8b6a7770f7a818cc307eb353debfffb", size = 6946 },
+    { url = "https://files.pythonhosted.org/packages/2c/00/1591b397c9efc0e4215d223553a1cb9090c8499888a4447f842443077d31/opentelemetry_util_http-0.52b1-py3-none-any.whl", hash = "sha256:6a6ab6bfa23fef96f4995233e874f67602adf9d224895981b4ab9d4dde23de78", size = 7305 },
 ]
 
 [[package]]
@@ -3628,16 +3648,16 @@ wheels = [
 
 [[package]]
 name = "protobuf"
-version = "4.25.5"
+version = "5.29.4"
 source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/67/dd/48d5fdb68ec74d70fabcc252e434492e56f70944d9f17b6a15e3746d2295/protobuf-4.25.5.tar.gz", hash = "sha256:7f8249476b4a9473645db7f8ab42b02fe1488cbe5fb72fddd445e0665afd8584", size = 380315 }
+sdist = { url = "https://files.pythonhosted.org/packages/17/7d/b9dca7365f0e2c4fa7c193ff795427cfa6290147e5185ab11ece280a18e7/protobuf-5.29.4.tar.gz", hash = "sha256:4f1dfcd7997b31ef8f53ec82781ff434a28bf71d9102ddde14d076adcfc78c99", size = 424902 }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/00/35/1b3c5a5e6107859c4ca902f4fbb762e48599b78129a05d20684fef4a4d04/protobuf-4.25.5-cp310-abi3-win32.whl", hash = "sha256:5e61fd921603f58d2f5acb2806a929b4675f8874ff5f330b7d6f7e2e784bbcd8", size = 392457 },
-    { url = "https://files.pythonhosted.org/packages/a7/ad/bf3f358e90b7e70bf7fb520702cb15307ef268262292d3bdb16ad8ebc815/protobuf-4.25.5-cp310-abi3-win_amd64.whl", hash = "sha256:4be0571adcbe712b282a330c6e89eae24281344429ae95c6d85e79e84780f5ea", size = 413449 },
-    { url = "https://files.pythonhosted.org/packages/51/49/d110f0a43beb365758a252203c43eaaad169fe7749da918869a8c991f726/protobuf-4.25.5-cp37-abi3-macosx_10_9_universal2.whl", hash = "sha256:b2fde3d805354df675ea4c7c6338c1aecd254dfc9925e88c6d31a2bcb97eb173", size = 394248 },
-    { url = "https://files.pythonhosted.org/packages/c6/ab/0f384ca0bc6054b1a7b6009000ab75d28a5506e4459378b81280ae7fd358/protobuf-4.25.5-cp37-abi3-manylinux2014_aarch64.whl", hash = "sha256:919ad92d9b0310070f8356c24b855c98df2b8bd207ebc1c0c6fcc9ab1e007f3d", size = 293717 },
-    { url = "https://files.pythonhosted.org/packages/05/a6/094a2640be576d760baa34c902dcb8199d89bce9ed7dd7a6af74dcbbd62d/protobuf-4.25.5-cp37-abi3-manylinux2014_x86_64.whl", hash = "sha256:fe14e16c22be926d3abfcb500e60cab068baf10b542b8c858fa27e098123e331", size = 294635 },
-    { url = "https://files.pythonhosted.org/packages/33/90/f198a61df8381fb43ae0fe81b3d2718e8dcc51ae8502c7657ab9381fbc4f/protobuf-4.25.5-py3-none-any.whl", hash = "sha256:0aebecb809cae990f8129ada5ca273d9d670b76d9bfc9b1809f0a9c02b7dbf41", size = 156467 },
+    { url = "https://files.pythonhosted.org/packages/9a/b2/043a1a1a20edd134563699b0e91862726a0dc9146c090743b6c44d798e75/protobuf-5.29.4-cp310-abi3-win32.whl", hash = "sha256:13eb236f8eb9ec34e63fc8b1d6efd2777d062fa6aaa68268fb67cf77f6839ad7", size = 422709 },
+    { url = "https://files.pythonhosted.org/packages/79/fc/2474b59570daa818de6124c0a15741ee3e5d6302e9d6ce0bdfd12e98119f/protobuf-5.29.4-cp310-abi3-win_amd64.whl", hash = "sha256:bcefcdf3976233f8a502d265eb65ea740c989bacc6c30a58290ed0e519eb4b8d", size = 434506 },
+    { url = "https://files.pythonhosted.org/packages/46/de/7c126bbb06aa0f8a7b38aaf8bd746c514d70e6a2a3f6dd460b3b7aad7aae/protobuf-5.29.4-cp38-abi3-macosx_10_9_universal2.whl", hash = "sha256:307ecba1d852ec237e9ba668e087326a67564ef83e45a0189a772ede9e854dd0", size = 417826 },
+    { url = "https://files.pythonhosted.org/packages/a2/b5/bade14ae31ba871a139aa45e7a8183d869efe87c34a4850c87b936963261/protobuf-5.29.4-cp38-abi3-manylinux2014_aarch64.whl", hash = "sha256:aec4962f9ea93c431d5714ed1be1c93f13e1a8618e70035ba2b0564d9e633f2e", size = 319574 },
+    { url = "https://files.pythonhosted.org/packages/46/88/b01ed2291aae68b708f7d334288ad5fb3e7aa769a9c309c91a0d55cb91b0/protobuf-5.29.4-cp38-abi3-manylinux2014_x86_64.whl", hash = "sha256:d7d3f7d1d5a66ed4942d4fefb12ac4b14a29028b209d4bfb25c68ae172059922", size = 319672 },
+    { url = "https://files.pythonhosted.org/packages/12/fb/a586e0c973c95502e054ac5f81f88394f24ccc7982dac19c515acd9e2c93/protobuf-5.29.4-py3-none-any.whl", hash = "sha256:3fde11b505e1597f71b875ef2fc52062b6a9740e5f7c8997ce878b6009145862", size = 172551 },
 ]
 
 [[package]]