Merge branch 'main' into feat-emit-stream-tool

- updated import path to crewai-tools
- removed old comment

.github/workflows/notify-downstream.yml

@@ -0,0 +1,33 @@
+name: Notify Downstream
+
+on:
+  push:
+    branches:
+      - main
+
+permissions:
+  contents: read
+
+jobs:
+  notify-downstream:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Generate GitHub App token
+        id: app-token
+        uses: tibdex/github-app-token@v2
+        with:
+          app_id: ${{ secrets.OSS_SYNC_APP_ID }}
+          private_key: ${{ secrets.OSS_SYNC_APP_PRIVATE_KEY }}
+
+      - name: Notify Repo B
+        uses: peter-evans/repository-dispatch@v3
+        with:
+          token: ${{ steps.app-token.outputs.token }}
+          repository: ${{ secrets.OSS_SYNC_DOWNSTREAM_REPO }}
+          event-type: upstream-commit
+          client-payload: |
+            {
+              "commit_sha": "${{ github.sha }}"
+            }
+

README.md

@@ -257,10 +257,14 @@ reporting_task:
 from crewai import Agent, Crew, Process, Task
 from crewai.project import CrewBase, agent, crew, task
 from crewai_tools import SerperDevTool
+from crewai.agents.agent_builder.base_agent import BaseAgent
+from typing import List
 
 @CrewBase
 class LatestAiDevelopmentCrew():
 	"""LatestAiDevelopment crew"""
+	agents: List[BaseAgent]
+	tasks: List[Task]
 
 	@agent
 	def researcher(self) -> Agent:

docs/concepts/agents.mdx

@@ -118,7 +118,7 @@ class LatestAiDevelopmentCrew():
   @agent
   def researcher(self) -> Agent:
     return Agent(
-      config=self.agents_config['researcher'],
+      config=self.agents_config['researcher'], # type: ignore[index]
       verbose=True,
       tools=[SerperDevTool()]
     )
@@ -126,7 +126,7 @@ class LatestAiDevelopmentCrew():
   @agent
   def reporting_analyst(self) -> Agent:
     return Agent(
-      config=self.agents_config['reporting_analyst'],
+      config=self.agents_config['reporting_analyst'], # type: ignore[index]
       verbose=True
     )
 ```

docs/concepts/crews.mdx

@@ -52,12 +52,16 @@ After creating your CrewAI project as outlined in the [Installation](/installati
 ```python code
 from crewai import Agent, Crew, Task, Process
 from crewai.project import CrewBase, agent, task, crew, before_kickoff, after_kickoff
-
+from crewai.agents.agent_builder.base_agent import BaseAgent
+from typing import List
 
 @CrewBase
 class YourCrewName:
     """Description of your crew"""
 
+    agents: List[BaseAgent]
+    tasks: List[Task]
+
     # Paths to your YAML configuration files
     # To see an example agent and task defined in YAML, checkout the following:
     # - Task: https://docs.crewai.com/concepts/tasks#yaml-configuration-recommended
@@ -80,27 +84,27 @@ class YourCrewName:
     @agent
     def agent_one(self) -> Agent:
         return Agent(
-            config=self.agents_config['agent_one'],
+            config=self.agents_config['agent_one'], # type: ignore[index]
             verbose=True
         )
 
     @agent
     def agent_two(self) -> Agent:
         return Agent(
-            config=self.agents_config['agent_two'],
+            config=self.agents_config['agent_two'], # type: ignore[index]
             verbose=True
         )
 
     @task
     def task_one(self) -> Task:
         return Task(
-            config=self.tasks_config['task_one']
+            config=self.tasks_config['task_one'] # type: ignore[index]
         )
 
     @task
     def task_two(self) -> Task:
         return Task(
-            config=self.tasks_config['task_two']
+            config=self.tasks_config['task_two'] # type: ignore[index]
         )
 
     @crew

docs/concepts/llms.mdx

@@ -438,7 +438,7 @@ In this section, you'll find detailed examples that help you select, configure,
         @agent
         def researcher(self) -> Agent:
             return Agent(
-                config=self.agents_config['researcher'],
+                config=self.agents_config['researcher'], # type: ignore[index]
                 llm=local_nvidia_nim_llm
             )
         
@@ -535,14 +535,13 @@ In this section, you'll find detailed examples that help you select, configure,
   <Accordion title="Hugging Face">
     Set the following environment variables in your `.env` file:
     ```toml Code
-    HUGGINGFACE_API_KEY=<your-api-key>
+    HF_TOKEN=<your-api-key>
     ```
 
     Example usage in your CrewAI project:
     ```python Code
     llm = LLM(
-        model="huggingface/meta-llama/Meta-Llama-3.1-8B-Instruct",
-        base_url="your_api_endpoint"
+        model="huggingface/meta-llama/Meta-Llama-3.1-8B-Instruct"
     )
     ```
   </Accordion>

docs/concepts/tasks.mdx

@@ -113,7 +113,7 @@ class LatestAiDevelopmentCrew():
   @agent
   def researcher(self) -> Agent:
     return Agent(
-      config=self.agents_config['researcher'],
+      config=self.agents_config['researcher'], # type: ignore[index]
       verbose=True,
       tools=[SerperDevTool()]
     )
@@ -121,20 +121,20 @@ class LatestAiDevelopmentCrew():
   @agent
   def reporting_analyst(self) -> Agent:
     return Agent(
-      config=self.agents_config['reporting_analyst'],
+      config=self.agents_config['reporting_analyst'], # type: ignore[index]
       verbose=True
     )
 
   @task
   def research_task(self) -> Task:
     return Task(
-      config=self.tasks_config['research_task']
+      config=self.tasks_config['research_task'] # type: ignore[index]
     )
 
   @task
   def reporting_task(self) -> Task:
     return Task(
-      config=self.tasks_config['reporting_task']
+      config=self.tasks_config['reporting_task'] # type: ignore[index]
     )
 
   @crew
@@ -288,26 +288,20 @@ To add a guardrail to a task, provide a validation function through the `guardra
 
 ```python Code
 from typing import Tuple, Union, Dict, Any
+from crewai import TaskOutput
 
-def validate_blog_content(result: str) -> Tuple[bool, Union[Dict[str, Any], str]]:
+def validate_blog_content(result: TaskOutput) -> Tuple[bool, Any]:
     """Validate blog content meets requirements."""
     try:
         # Check word count
         word_count = len(result.split())
         if word_count > 200:
-            return (False, {
-                "error": "Blog content exceeds 200 words",
-                "code": "WORD_COUNT_ERROR",
-                "context": {"word_count": word_count}
-            })
+            return (False, "Blog content exceeds 200 words")
 
         # Additional validation logic here
         return (True, result.strip())
     except Exception as e:
-        return (False, {
-            "error": "Unexpected error during validation",
-            "code": "SYSTEM_ERROR"
-        })
+        return (False, "Unexpected error during validation")
 
 blog_task = Task(
     description="Write a blog post about AI",
@@ -325,29 +319,24 @@ blog_task = Task(
    - Type hints are recommended but optional
 
 2. **Return Values**:
-   - Success: Return `(True, validated_result)`
-   - Failure: Return `(False, error_details)`
+   - On success: it returns a tuple of `(bool, Any)`. For example: `(True, validated_result)` 
+   - On Failure: it returns a tuple of `(bool, str)`. For example: `(False, "Error message explain the failure")`
 
 ### Error Handling Best Practices
 
 1. **Structured Error Responses**:
 ```python Code
-def validate_with_context(result: str) -> Tuple[bool, Union[Dict[str, Any], str]]:
+from crewai import TaskOutput
+
+def validate_with_context(result: TaskOutput) -> Tuple[bool, Any]:
     try:
         # Main validation logic
         validated_data = perform_validation(result)
         return (True, validated_data)
     except ValidationError as e:
-        return (False, {
-            "error": str(e),
-            "code": "VALIDATION_ERROR",
-            "context": {"input": result}
-        })
+        return (False, f"VALIDATION_ERROR: {str(e)}")
     except Exception as e:
-        return (False, {
-            "error": "Unexpected error",
-            "code": "SYSTEM_ERROR"
-        })
+        return (False, str(e))
 ```
 
 2. **Error Categories**:
@@ -358,28 +347,25 @@ def validate_with_context(result: str) -> Tuple[bool, Union[Dict[str, Any], str]
 3. **Validation Chain**:
 ```python Code
 from typing import Any, Dict, List, Tuple, Union
+from crewai import TaskOutput
 
-def complex_validation(result: str) -> Tuple[bool, Union[str, Dict[str, Any]]]:
+def complex_validation(result: TaskOutput) -> Tuple[bool, Any]:
     """Chain multiple validation steps."""
     # Step 1: Basic validation
     if not result:
-        return (False, {"error": "Empty result", "code": "EMPTY_INPUT"})
+        return (False, "Empty result")
 
     # Step 2: Content validation
     try:
         validated = validate_content(result)
         if not validated:
-            return (False, {"error": "Invalid content", "code": "CONTENT_ERROR"})
+            return (False, "Invalid content")
 
         # Step 3: Format validation
         formatted = format_output(validated)
         return (True, formatted)
     except Exception as e:
-        return (False, {
-            "error": str(e),
-            "code": "VALIDATION_ERROR",
-            "context": {"step": "content_validation"}
-        })
+        return (False, str(e))
 ```
 
 ### Handling Guardrail Results
@@ -394,19 +380,16 @@ When a guardrail returns `(False, error)`:
 Example with retry handling:
 ```python Code
 from typing import Optional, Tuple, Union
+from crewai import TaskOutput, Task
 
-def validate_json_output(result: str) -> Tuple[bool, Union[Dict[str, Any], str]]:
+def validate_json_output(result: TaskOutput) -> Tuple[bool, Any]:
     """Validate and parse JSON output."""
     try:
         # Try to parse as JSON
         data = json.loads(result)
         return (True, data)
     except json.JSONDecodeError as e:
-        return (False, {
-            "error": "Invalid JSON format",
-            "code": "JSON_ERROR",
-            "context": {"line": e.lineno, "column": e.colno}
-        })
+        return (False, "Invalid JSON format")
 
 task = Task(
     description="Generate a JSON report",

docs/guides/crews/first-crew.mdx

@@ -185,15 +185,20 @@ Let's modify the `crew.py` file:
 from crewai import Agent, Crew, Process, Task
 from crewai.project import CrewBase, agent, crew, task
 from crewai_tools import SerperDevTool
+from crewai.agents.agent_builder.base_agent import BaseAgent
+from typing import List
 
 @CrewBase
 class ResearchCrew():
     """Research crew for comprehensive topic analysis and reporting"""
 
+    agents: List[BaseAgent]
+    tasks: List[Task]
+
     @agent
     def researcher(self) -> Agent:
         return Agent(
-            config=self.agents_config['researcher'],
+            config=self.agents_config['researcher'], # type: ignore[index]
             verbose=True,
             tools=[SerperDevTool()]
         )
@@ -201,20 +206,20 @@ class ResearchCrew():
     @agent
     def analyst(self) -> Agent:
         return Agent(
-            config=self.agents_config['analyst'],
+            config=self.agents_config['analyst'], # type: ignore[index]
             verbose=True
         )
 
     @task
     def research_task(self) -> Task:
         return Task(
-            config=self.tasks_config['research_task']
+            config=self.tasks_config['research_task'] # type: ignore[index]
         )
 
     @task
     def analysis_task(self) -> Task:
         return Task(
-            config=self.tasks_config['analysis_task'],
+            config=self.tasks_config['analysis_task'], # type: ignore[index]
             output_file='output/report.md'
         )
 
@@ -387,4 +392,4 @@ Now that you've built your first crew, you can:
 
 <Check>
 Congratulations! You've successfully built your first CrewAI crew that can research and analyze any topic you provide. This foundational experience has equipped you with the skills to create increasingly sophisticated AI systems that can tackle complex, multi-stage problems through collaborative intelligence.
-</Check>
+</Check>

docs/guides/flows/first-flow.mdx

@@ -203,35 +203,40 @@ These task definitions provide detailed instructions to our agents, ensuring the
 # src/guide_creator_flow/crews/content_crew/content_crew.py
 from crewai import Agent, Crew, Process, Task
 from crewai.project import CrewBase, agent, crew, task
+from crewai.agents.agent_builder.base_agent import BaseAgent
+from typing import List
 
 @CrewBase
 class ContentCrew():
     """Content writing crew"""
 
+    agents: List[BaseAgent]
+    tasks: List[Task]
+
     @agent
     def content_writer(self) -> Agent:
         return Agent(
-            config=self.agents_config['content_writer'],
+            config=self.agents_config['content_writer'], # type: ignore[index]
             verbose=True
         )
 
     @agent
     def content_reviewer(self) -> Agent:
         return Agent(
-            config=self.agents_config['content_reviewer'],
+            config=self.agents_config['content_reviewer'], # type: ignore[index]
             verbose=True
         )
 
     @task
     def write_section_task(self) -> Task:
         return Task(
-            config=self.tasks_config['write_section_task']
+            config=self.tasks_config['write_section_task'] # type: ignore[index]
         )
 
     @task
     def review_section_task(self) -> Task:
         return Task(
-            config=self.tasks_config['review_section_task'],
+            config=self.tasks_config['review_section_task'], # type: ignore[index]
             context=[self.write_section_task()]
         )
 

docs/quickstart.mdx

@@ -87,15 +87,20 @@ Follow the steps below to get Crewing! 🚣‍♂️
     from crewai import Agent, Crew, Process, Task
     from crewai.project import CrewBase, agent, crew, task
     from crewai_tools import SerperDevTool
+    from crewai.agents.agent_builder.base_agent import BaseAgent
+    from typing import List
 
     @CrewBase
     class LatestAiDevelopmentCrew():
       """LatestAiDevelopment crew"""
 
+      agents: List[BaseAgent]
+      tasks: List[Task]
+
       @agent
       def researcher(self) -> Agent:
         return Agent(
-          config=self.agents_config['researcher'],
+          config=self.agents_config['researcher'], # type: ignore[index]
           verbose=True,
           tools=[SerperDevTool()]
         )
@@ -103,20 +108,20 @@ Follow the steps below to get Crewing! 🚣‍♂️
       @agent
       def reporting_analyst(self) -> Agent:
         return Agent(
-          config=self.agents_config['reporting_analyst'],
+          config=self.agents_config['reporting_analyst'], # type: ignore[index]
           verbose=True
         )
 
       @task
       def research_task(self) -> Task:
         return Task(
-          config=self.tasks_config['research_task'],
+          config=self.tasks_config['research_task'], # type: ignore[index]
         )
 
       @task
       def reporting_task(self) -> Task:
         return Task(
-          config=self.tasks_config['reporting_task'],
+          config=self.tasks_config['reporting_task'], # type: ignore[index]
           output_file='output/report.md' # This is the file that will be contain the final report.
         )
 

docs/tools/jsonsearchtool.mdx

@@ -30,7 +30,7 @@ pip install 'crewai[tools]'
 Here are updated examples on how to utilize the JSONSearchTool effectively for searching within JSON files. These examples take into account the current implementation and usage patterns identified in the codebase.
 
 ```python Code
-from crewai.json_tools import JSONSearchTool  # Updated import path
+from crewai_tools import JSONSearchTool
 
 # General JSON content search
 # This approach is suitable when the JSON path is either known beforehand or can be dynamically identified.

pyproject.toml

@@ -81,10 +81,10 @@ dev-dependencies = [
     "pillow>=10.2.0",
     "cairosvg>=2.7.1",
     "pytest>=8.0.0",
-    "pytest-vcr>=1.0.2",
     "python-dotenv>=1.0.0",
     "pytest-asyncio>=0.23.7",
     "pytest-subprocess>=1.5.2",
+    "pytest-recording>=0.13.2",
 ]
 
 [project.scripts]

src/crewai/agent.py

@@ -535,6 +535,7 @@ class Agent(BaseAgent):
             verbose=self.verbose,
             response_format=response_format,
             i18n=self.i18n,
+            original_agent=self,
         )
 
         return await lite_agent.kickoff_async(messages)

src/crewai/cli/constants.py

@@ -91,6 +91,12 @@ ENV_VARS = {
             "key_name": "CEREBRAS_API_KEY",
         },
     ],
+    "huggingface": [
+        {
+            "prompt": "Enter your Huggingface API key (HF_TOKEN) (press Enter to skip)",
+            "key_name": "HF_TOKEN",
+        },
+    ],
     "sambanova": [
         {
             "prompt": "Enter your SambaNovaCloud API key (press Enter to skip)",
@@ -106,6 +112,7 @@ PROVIDERS = [
     "gemini",
     "nvidia_nim",
     "groq",
+    "huggingface",
     "ollama",
     "watson",
     "bedrock",
@@ -270,6 +277,12 @@ MODELS = {
         "bedrock/mistral.mistral-7b-instruct-v0:2",
         "bedrock/mistral.mixtral-8x7b-instruct-v0:1",
     ],
+    "huggingface": [
+        "huggingface/meta-llama/Meta-Llama-3.1-8B-Instruct",
+        "huggingface/mistralai/Mixtral-8x7B-Instruct-v0.1",
+        "huggingface/tiiuae/falcon-180B-chat",
+        "huggingface/google/gemma-7b-it",
+    ],
     "sambanova": [
         "sambanova/Meta-Llama-3.3-70B-Instruct",
         "sambanova/QwQ-32B-Preview",

src/crewai/cli/templates/crew/crew.py

@@ -1,6 +1,7 @@
 from crewai import Agent, Crew, Process, Task
 from crewai.project import CrewBase, agent, crew, task
-
+from crewai.agents.agent_builder.base_agent import BaseAgent
+from typing import List
 # If you want to run a snippet of code before or after the crew starts,
 # you can use the @before_kickoff and @after_kickoff decorators
 # https://docs.crewai.com/concepts/crews#example-crew-class-with-decorators
@@ -9,25 +10,26 @@ from crewai.project import CrewBase, agent, crew, task
 class {{crew_name}}():
     """{{crew_name}} crew"""
 
+    agents: List[BaseAgent]
+    tasks: List[Task]
+
     # Learn more about YAML configuration files here:
     # Agents: https://docs.crewai.com/concepts/agents#yaml-configuration-recommended
     # Tasks: https://docs.crewai.com/concepts/tasks#yaml-configuration-recommended
-    agents_config = 'config/agents.yaml'
-    tasks_config = 'config/tasks.yaml'
-
+    
     # If you would like to add tools to your agents, you can learn more about it here:
     # https://docs.crewai.com/concepts/agents#agent-tools
     @agent
     def researcher(self) -> Agent:
         return Agent(
-            config=self.agents_config['researcher'],
+            config=self.agents_config['researcher'], # type: ignore[index]
             verbose=True
         )
 
     @agent
     def reporting_analyst(self) -> Agent:
         return Agent(
-            config=self.agents_config['reporting_analyst'],
+            config=self.agents_config['reporting_analyst'], # type: ignore[index]
             verbose=True
         )
 
@@ -37,13 +39,13 @@ class {{crew_name}}():
     @task
     def research_task(self) -> Task:
         return Task(
-            config=self.tasks_config['research_task'],
+            config=self.tasks_config['research_task'], # type: ignore[index]
         )
 
     @task
     def reporting_task(self) -> Task:
         return Task(
-            config=self.tasks_config['reporting_task'],
+            config=self.tasks_config['reporting_task'], # type: ignore[index]
             output_file='report.md'
         )
 

src/crewai/cli/templates/flow/crews/poem_crew/poem_crew.py

@@ -1,5 +1,7 @@
 from crewai import Agent, Crew, Process, Task
 from crewai.project import CrewBase, agent, crew, task
+from crewai.agents.agent_builder.base_agent import BaseAgent
+from typing import List
 
 # If you want to run a snippet of code before or after the crew starts,
 # you can use the @before_kickoff and @after_kickoff decorators
@@ -10,6 +12,9 @@ from crewai.project import CrewBase, agent, crew, task
 class PoemCrew:
     """Poem Crew"""
 
+    agents: List[BaseAgent]
+    tasks: List[Task]
+
     # Learn more about YAML configuration files here:
     # Agents: https://docs.crewai.com/concepts/agents#yaml-configuration-recommended
     # Tasks: https://docs.crewai.com/concepts/tasks#yaml-configuration-recommended
@@ -21,7 +26,7 @@ class PoemCrew:
     @agent
     def poem_writer(self) -> Agent:
         return Agent(
-            config=self.agents_config["poem_writer"],
+            config=self.agents_config["poem_writer"],  # type: ignore[index]
         )
 
     # To learn more about structured task outputs,
@@ -30,7 +35,7 @@ class PoemCrew:
     @task
     def write_poem(self) -> Task:
         return Task(
-            config=self.tasks_config["write_poem"],
+            config=self.tasks_config["write_poem"],  # type: ignore[index]
         )
 
     @crew

src/crewai/cli/utils.py

@@ -273,11 +273,9 @@ def get_crew(crew_path: str = "crew.py", require: bool = False) -> Crew | None:
                         for attr_name in dir(module):
                             attr = getattr(module, attr_name)
                             try:
-                                if isinstance(attr, Crew) and hasattr(attr, "kickoff"):
-                                    print(
-                                        f"Found valid crew object in attribute '{attr_name}' at {crew_os_path}."
-                                    )
-                                    return attr
+                                if callable(attr) and hasattr(attr, "crew"):
+                                    crew_instance = attr().crew()
+                                    return crew_instance
 
                             except Exception as e:
                                 print(f"Error processing attribute {attr_name}: {e}")

src/crewai/crew.py

@@ -1399,12 +1399,12 @@ class Crew(BaseModel):
             RuntimeError: If the specified memory system fails to reset
         """
         reset_functions = {
-            "long": (self._long_term_memory, "long term"),
-            "short": (self._short_term_memory, "short term"),
-            "entity": (self._entity_memory, "entity"),
-            "knowledge": (self.knowledge, "knowledge"),
-            "kickoff_outputs": (self._task_output_handler, "task output"),
-            "external": (self._external_memory, "external"),
+            "long": (getattr(self, "_long_term_memory", None), "long term"),
+            "short": (getattr(self, "_short_term_memory", None), "short term"),
+            "entity": (getattr(self, "_entity_memory", None), "entity"),
+            "knowledge": (getattr(self, "knowledge", None), "knowledge"),
+            "kickoff_outputs": (getattr(self, "_task_output_handler", None), "task output"),
+            "external": (getattr(self, "_external_memory", None), "external"),
         }
 
         memory_system, name = reset_functions[memory_type]

src/crewai/flow/persistence/sqlite.py

@@ -21,7 +21,7 @@ class SQLiteFlowPersistence(FlowPersistence):
     moderate performance requirements.
     """
 
-    db_path: str  # Type annotation for instance variable
+    db_path: str
 
     def __init__(self, db_path: Optional[str] = None):
         """Initialize SQLite persistence.

src/crewai/llm.py

@@ -4,9 +4,12 @@ import os
 import sys
 import threading
 import warnings
+from collections import defaultdict
 from contextlib import contextmanager
+from types import SimpleNamespace
 from typing import (
     Any,
+    DefaultDict,
     Dict,
     List,
     Literal,
@@ -18,7 +21,8 @@ from typing import (
 )
 
 from dotenv import load_dotenv
-from pydantic import BaseModel
+from litellm.types.utils import ChatCompletionDeltaToolCall
+from pydantic import BaseModel, Field
 
 from crewai.utilities.events.llm_events import (
     LLMCallCompletedEvent,
@@ -219,6 +223,15 @@ class StreamingChoices(TypedDict):
     finish_reason: Optional[str]
 
 
+class FunctionArgs(BaseModel):
+    name: str = ""
+    arguments: str = ""
+
+
+class AccumulatedToolArgs(BaseModel):
+    function: FunctionArgs = Field(default_factory=FunctionArgs)
+
+
 class LLM(BaseLLM):
     def __init__(
         self,
@@ -371,6 +384,11 @@ class LLM(BaseLLM):
         last_chunk = None
         chunk_count = 0
         usage_info = None
+        tool_calls = None
+
+        accumulated_tool_args: DefaultDict[int, AccumulatedToolArgs] = defaultdict(
+            AccumulatedToolArgs
+        )
 
         # --- 2) Make sure stream is set to True and include usage metrics
         params["stream"] = True
@@ -428,6 +446,20 @@ class LLM(BaseLLM):
                             if chunk_content is None and isinstance(delta, dict):
                                 # Some models might send empty content chunks
                                 chunk_content = ""
+
+                            # Enable tool calls using streaming
+                            if "tool_calls" in delta:
+                                tool_calls = delta["tool_calls"]
+
+                                if tool_calls:
+                                    result = self._handle_streaming_tool_calls(
+                                        tool_calls=tool_calls,
+                                        accumulated_tool_args=accumulated_tool_args,
+                                        available_functions=available_functions,
+                                    )
+                                    if result is not None:
+                                        chunk_content = result
+
                 except Exception as e:
                     logging.debug(f"Error extracting content from chunk: {e}")
                     logging.debug(f"Chunk format: {type(chunk)}, content: {chunk}")
@@ -442,7 +474,6 @@ class LLM(BaseLLM):
                         self,
                         event=LLMStreamChunkEvent(chunk=chunk_content),
                     )
-
             # --- 4) Fallback to non-streaming if no content received
             if not full_response.strip() and chunk_count == 0:
                 logging.warning(
@@ -501,7 +532,7 @@ class LLM(BaseLLM):
                         )
 
             # --- 6) If still empty, raise an error instead of using a default response
-            if not full_response.strip():
+            if not full_response.strip() and len(accumulated_tool_args) == 0:
                 raise Exception(
                     "No content received from streaming response. Received empty chunks or failed to extract content."
                 )
@@ -533,8 +564,8 @@ class LLM(BaseLLM):
                                 tool_calls = getattr(message, "tool_calls")
             except Exception as e:
                 logging.debug(f"Error checking for tool calls: {e}")
-
             # --- 8) If no tool calls or no available functions, return the text response directly
+
             if not tool_calls or not available_functions:
                 # Log token usage if available in streaming mode
                 self._handle_streaming_callbacks(callbacks, usage_info, last_chunk)
@@ -568,6 +599,47 @@ class LLM(BaseLLM):
             )
             raise Exception(f"Failed to get streaming response: {str(e)}")
 
+    def _handle_streaming_tool_calls(
+        self,
+        tool_calls: List[ChatCompletionDeltaToolCall],
+        accumulated_tool_args: DefaultDict[int, AccumulatedToolArgs],
+        available_functions: Optional[Dict[str, Any]] = None,
+    ) -> None | str:
+        for tool_call in tool_calls:
+            current_tool_accumulator = accumulated_tool_args[tool_call.index]
+
+            if tool_call.function.name:
+                current_tool_accumulator.function.name = tool_call.function.name
+
+            if tool_call.function.arguments:
+                current_tool_accumulator.function.arguments += (
+                    tool_call.function.arguments
+                )
+
+            crewai_event_bus.emit(
+                self,
+                event=LLMStreamChunkEvent(
+                    tool_call=tool_call.to_dict(),
+                    chunk=tool_call.function.arguments,
+                ),
+            )
+
+            if (
+                current_tool_accumulator.function.name
+                and current_tool_accumulator.function.arguments
+                and available_functions
+            ):
+                try:
+                    json.loads(current_tool_accumulator.function.arguments)
+
+                    return self._handle_tool_call(
+                        [current_tool_accumulator],
+                        available_functions,
+                    )
+                except json.JSONDecodeError:
+                    continue
+        return None
+
     def _handle_streaming_callbacks(
         self,
         callbacks: Optional[List[Any]],

src/crewai/telemetry/constants.py

@@ -0,0 +1,2 @@
+CREWAI_TELEMETRY_BASE_URL: str = "https://telemetry.crewai.com:4319"
+CREWAI_TELEMETRY_SERVICE_NAME: str = "crewAI-telemetry"

src/crewai/telemetry/telemetry.py

@@ -9,6 +9,11 @@ from contextlib import contextmanager
 from importlib.metadata import version
 from typing import TYPE_CHECKING, Any, Optional
 
+from crewai.telemetry.constants import (
+    CREWAI_TELEMETRY_BASE_URL,
+    CREWAI_TELEMETRY_SERVICE_NAME,
+)
+
 
 @contextmanager
 def suppress_warnings():
@@ -52,16 +57,15 @@ class Telemetry:
             return
 
         try:
-            telemetry_endpoint = "https://telemetry.crewai.com:4319"
             self.resource = Resource(
-                attributes={SERVICE_NAME: "crewAI-telemetry"},
+                attributes={SERVICE_NAME: CREWAI_TELEMETRY_SERVICE_NAME},
             )
             with suppress_warnings():
                 self.provider = TracerProvider(resource=self.resource)
 
             processor = BatchSpanProcessor(
                 OTLPSpanExporter(
-                    endpoint=f"{telemetry_endpoint}/v1/traces",
+                    endpoint=f"{CREWAI_TELEMETRY_BASE_URL}/v1/traces",
                     timeout=30,
                 )
             )
@@ -75,12 +79,12 @@ class Telemetry:
             ):
                 raise  # Re-raise the exception to not interfere with system signals
             self.ready = False
-            
+
     def _is_telemetry_disabled(self) -> bool:
         """Check if telemetry should be disabled based on environment variables."""
         return (
-            os.getenv("OTEL_SDK_DISABLED", "false").lower() == "true" or
-            os.getenv("CREWAI_DISABLE_TELEMETRY", "false").lower() == "true"
+            os.getenv("OTEL_SDK_DISABLED", "false").lower() == "true"
+            or os.getenv("CREWAI_DISABLE_TELEMETRY", "false").lower() == "true"
         )
 
     def set_tracer(self):

src/crewai/utilities/events/llm_events.py

@@ -1,6 +1,8 @@
 from enum import Enum
 from typing import Any, Dict, List, Optional, Union
 
+from pydantic import BaseModel
+
 from crewai.utilities.events.base_events import BaseEvent
 
 
@@ -41,8 +43,21 @@ class LLMCallFailedEvent(BaseEvent):
     type: str = "llm_call_failed"
 
 
+class FunctionCall(BaseModel):
+    arguments: str
+    name: Optional[str] = None
+
+
+class ToolCall(BaseModel):
+    id: Optional[str] = None
+    function: FunctionCall
+    type: Optional[str] = None
+    index: int
+
+
 class LLMStreamChunkEvent(BaseEvent):
     """Event emitted when a streaming chunk is received"""
 
     type: str = "llm_stream_chunk"
     chunk: str
+    tool_call: Optional[ToolCall] = None

tests/cassettes/test_handle_streaming_tool_calls.yaml

@@ -0,0 +1,133 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "user", "content": "What is the weather in New York?"}],
+      "model": "gpt-4o", "stop": [], "stream": true, "stream_options": {"include_usage":
+      true}, "tools": [{"type": "function", "function": {"name": "get_weather", "description":
+      "Get the current weather in a given location", "parameters": {"type": "object",
+      "properties": {"location": {"type": "string", "description": "The city and state,
+      e.g. San Francisco, CA"}}, "required": ["location"]}}}]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '470'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.74.0
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.74.0
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-read-timeout:
+      - '600.0'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.12
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: 'data: {"id":"chatcmpl-BMyImYKF6jsJsQzWvhNfNb4gAIRVc","object":"chat.completion.chunk","created":1744814716,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_bCEixqN8Y40SUyius8ZfVErH","type":"function","function":{"name":"get_weather","arguments":""}}],"refusal":null},"logprobs":null,"finish_reason":null}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BMyImYKF6jsJsQzWvhNfNb4gAIRVc","object":"chat.completion.chunk","created":1744814716,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"logprobs":null,"finish_reason":null}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BMyImYKF6jsJsQzWvhNfNb4gAIRVc","object":"chat.completion.chunk","created":1744814716,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"location"}}]},"logprobs":null,"finish_reason":null}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BMyImYKF6jsJsQzWvhNfNb4gAIRVc","object":"chat.completion.chunk","created":1744814716,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"logprobs":null,"finish_reason":null}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BMyImYKF6jsJsQzWvhNfNb4gAIRVc","object":"chat.completion.chunk","created":1744814716,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"New"}}]},"logprobs":null,"finish_reason":null}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BMyImYKF6jsJsQzWvhNfNb4gAIRVc","object":"chat.completion.chunk","created":1744814716,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"
+        York"}}]},"logprobs":null,"finish_reason":null}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BMyImYKF6jsJsQzWvhNfNb4gAIRVc","object":"chat.completion.chunk","created":1744814716,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":","}}]},"logprobs":null,"finish_reason":null}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BMyImYKF6jsJsQzWvhNfNb4gAIRVc","object":"chat.completion.chunk","created":1744814716,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"
+        NY"}}]},"logprobs":null,"finish_reason":null}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BMyImYKF6jsJsQzWvhNfNb4gAIRVc","object":"chat.completion.chunk","created":1744814716,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"}"}}]},"logprobs":null,"finish_reason":null}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BMyImYKF6jsJsQzWvhNfNb4gAIRVc","object":"chat.completion.chunk","created":1744814716,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"tool_calls"}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BMyImYKF6jsJsQzWvhNfNb4gAIRVc","object":"chat.completion.chunk","created":1744814716,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[],"usage":{"prompt_tokens":68,"completion_tokens":18,"total_tokens":86,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}}}
+
+
+        data: [DONE]
+
+
+        '
+    headers:
+      CF-RAY:
+      - 93147723ecc1f237-GRU
+      Connection:
+      - keep-alive
+      Content-Type:
+      - text/event-stream; charset=utf-8
+      Date:
+      - Wed, 16 Apr 2025 14:45:16 GMT
+      Server:
+      - cloudflare
+      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:
+      - '620'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '30000000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '29999989'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_0a08d5f042ef769aeb2c941e398f65f4
+    status:
+      code: 200
+      message: OK
+version: 1

tests/cassettes/test_handle_streaming_tool_calls_no_available_functions.yaml

@@ -0,0 +1,133 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "user", "content": "What is the weather in New York?"}],
+      "model": "gpt-4o", "stop": [], "stream": true, "stream_options": {"include_usage":
+      true}, "tools": [{"type": "function", "function": {"name": "get_weather", "description":
+      "Get the current weather in a given location", "parameters": {"type": "object",
+      "properties": {"location": {"type": "string", "description": "The city and state,
+      e.g. San Francisco, CA"}}, "required": ["location"]}}}]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '470'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.74.0
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.74.0
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-read-timeout:
+      - '600.0'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.12
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: 'data: {"id":"chatcmpl-BMy4cOLWqB5n5X1Zog3uV9Y7Lrkwp","object":"chat.completion.chunk","created":1744813838,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_ccog5nyDCLYpoWzksuCkGEqY","type":"function","function":{"name":"get_weather","arguments":""}}],"refusal":null},"logprobs":null,"finish_reason":null}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BMy4cOLWqB5n5X1Zog3uV9Y7Lrkwp","object":"chat.completion.chunk","created":1744813838,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"logprobs":null,"finish_reason":null}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BMy4cOLWqB5n5X1Zog3uV9Y7Lrkwp","object":"chat.completion.chunk","created":1744813838,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"location"}}]},"logprobs":null,"finish_reason":null}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BMy4cOLWqB5n5X1Zog3uV9Y7Lrkwp","object":"chat.completion.chunk","created":1744813838,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"logprobs":null,"finish_reason":null}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BMy4cOLWqB5n5X1Zog3uV9Y7Lrkwp","object":"chat.completion.chunk","created":1744813838,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"New"}}]},"logprobs":null,"finish_reason":null}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BMy4cOLWqB5n5X1Zog3uV9Y7Lrkwp","object":"chat.completion.chunk","created":1744813838,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"
+        York"}}]},"logprobs":null,"finish_reason":null}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BMy4cOLWqB5n5X1Zog3uV9Y7Lrkwp","object":"chat.completion.chunk","created":1744813838,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":","}}]},"logprobs":null,"finish_reason":null}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BMy4cOLWqB5n5X1Zog3uV9Y7Lrkwp","object":"chat.completion.chunk","created":1744813838,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"
+        NY"}}]},"logprobs":null,"finish_reason":null}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BMy4cOLWqB5n5X1Zog3uV9Y7Lrkwp","object":"chat.completion.chunk","created":1744813838,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"}"}}]},"logprobs":null,"finish_reason":null}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BMy4cOLWqB5n5X1Zog3uV9Y7Lrkwp","object":"chat.completion.chunk","created":1744813838,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"tool_calls"}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BMy4cOLWqB5n5X1Zog3uV9Y7Lrkwp","object":"chat.completion.chunk","created":1744813838,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[],"usage":{"prompt_tokens":68,"completion_tokens":18,"total_tokens":86,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}}}
+
+
+        data: [DONE]
+
+
+        '
+    headers:
+      CF-RAY:
+      - 931461bbddc27df9-GRU
+      Connection:
+      - keep-alive
+      Content-Type:
+      - text/event-stream; charset=utf-8
+      Date:
+      - Wed, 16 Apr 2025 14:30:39 GMT
+      Server:
+      - cloudflare
+      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:
+      - '445'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '30000000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '29999989'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_1bb5862de2891623d44c012aba597c5e
+    status:
+      code: 200
+      message: OK
+version: 1

tests/cassettes/test_handle_streaming_tool_calls_no_tools.yaml

@@ -0,0 +1,279 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "user", "content": "What is the weather in New York?"}],
+      "model": "gpt-4o", "stop": [], "stream": true, "stream_options": {"include_usage":
+      true}}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '169'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.74.0
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.74.0
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-read-timeout:
+      - '600.0'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.12
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: 'data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"logprobs":null,"finish_reason":null}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"I''m"},"logprobs":null,"finish_reason":null}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"
+        unable"},"logprobs":null,"finish_reason":null}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"
+        to"},"logprobs":null,"finish_reason":null}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"
+        provide"},"logprobs":null,"finish_reason":null}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"
+        real"},"logprobs":null,"finish_reason":null}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"-time"},"logprobs":null,"finish_reason":null}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"
+        information"},"logprobs":null,"finish_reason":null}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"
+        or"},"logprobs":null,"finish_reason":null}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"
+        current"},"logprobs":null,"finish_reason":null}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"
+        weather"},"logprobs":null,"finish_reason":null}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"
+        updates"},"logprobs":null,"finish_reason":null}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"."},"logprobs":null,"finish_reason":null}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"
+        For"},"logprobs":null,"finish_reason":null}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"
+        the"},"logprobs":null,"finish_reason":null}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"
+        latest"},"logprobs":null,"finish_reason":null}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"
+        weather"},"logprobs":null,"finish_reason":null}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"
+        information"},"logprobs":null,"finish_reason":null}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"
+        in"},"logprobs":null,"finish_reason":null}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"
+        New"},"logprobs":null,"finish_reason":null}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"
+        York"},"logprobs":null,"finish_reason":null}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":","},"logprobs":null,"finish_reason":null}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"
+        I"},"logprobs":null,"finish_reason":null}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"
+        recommend"},"logprobs":null,"finish_reason":null}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"
+        checking"},"logprobs":null,"finish_reason":null}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"
+        a"},"logprobs":null,"finish_reason":null}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"
+        reliable"},"logprobs":null,"finish_reason":null}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"
+        weather"},"logprobs":null,"finish_reason":null}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"
+        website"},"logprobs":null,"finish_reason":null}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"
+        or"},"logprobs":null,"finish_reason":null}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"
+        app"},"logprobs":null,"finish_reason":null}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":","},"logprobs":null,"finish_reason":null}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"
+        such"},"logprobs":null,"finish_reason":null}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"
+        as"},"logprobs":null,"finish_reason":null}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"
+        the"},"logprobs":null,"finish_reason":null}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"
+        National"},"logprobs":null,"finish_reason":null}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"
+        Weather"},"logprobs":null,"finish_reason":null}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"
+        Service"},"logprobs":null,"finish_reason":null}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":","},"logprobs":null,"finish_reason":null}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"
+        Weather"},"logprobs":null,"finish_reason":null}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":".com"},"logprobs":null,"finish_reason":null}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":","},"logprobs":null,"finish_reason":null}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"
+        or"},"logprobs":null,"finish_reason":null}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"
+        a"},"logprobs":null,"finish_reason":null}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"
+        similar"},"logprobs":null,"finish_reason":null}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"
+        service"},"logprobs":null,"finish_reason":null}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{"content":"."},"logprobs":null,"finish_reason":null}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}],"usage":null}
+
+
+        data: {"id":"chatcmpl-BMy4dVQFM7KUrmflCVk4i454PXCga","object":"chat.completion.chunk","created":1744813839,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_22890b9c0a","choices":[],"usage":{"prompt_tokens":15,"completion_tokens":47,"total_tokens":62,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}}}
+
+
+        data: [DONE]
+
+
+        '
+    headers:
+      CF-RAY:
+      - 931461c25bb47df9-GRU
+      Connection:
+      - keep-alive
+      Content-Type:
+      - text/event-stream; charset=utf-8
+      Date:
+      - Wed, 16 Apr 2025 14:30:40 GMT
+      Server:
+      - cloudflare
+      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:
+      - '298'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '30000000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '29999989'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_89971fd68e5a59c9fa50e04106228b0a
+    status:
+      code: 200
+      message: OK
+version: 1

tests/cli/test_constants.py

@@ -0,0 +1,23 @@
+import pytest
+
+from crewai.cli.constants import ENV_VARS, MODELS, PROVIDERS
+
+
+def test_huggingface_in_providers():
+    """Test that Huggingface is in the PROVIDERS list."""
+    assert "huggingface" in PROVIDERS
+
+
+def test_huggingface_env_vars():
+    """Test that Huggingface environment variables are properly configured."""
+    assert "huggingface" in ENV_VARS
+    assert any(
+        detail.get("key_name") == "HF_TOKEN"
+        for detail in ENV_VARS["huggingface"]
+    )
+
+
+def test_huggingface_models():
+    """Test that Huggingface models are properly configured."""
+    assert "huggingface" in MODELS
+    assert len(MODELS["huggingface"]) > 0

tests/conftest.py

@@ -8,6 +8,7 @@ from dotenv import load_dotenv
 
 load_result = load_dotenv(override=True)
 
+
 @pytest.fixture(autouse=True)
 def setup_test_environment():
     """Set up test environment with a temporary directory for SQLite storage."""
@@ -15,11 +16,13 @@ def setup_test_environment():
         # Create the directory with proper permissions
         storage_dir = Path(temp_dir) / "crewai_test_storage"
         storage_dir.mkdir(parents=True, exist_ok=True)
-        
+
         # Validate that the directory was created successfully
         if not storage_dir.exists() or not storage_dir.is_dir():
-            raise RuntimeError(f"Failed to create test storage directory: {storage_dir}")
-        
+            raise RuntimeError(
+                f"Failed to create test storage directory: {storage_dir}"
+            )
+
         # Verify directory permissions
         try:
             # Try to create a test file to verify write permissions
@@ -27,11 +30,20 @@ def setup_test_environment():
             test_file.touch()
             test_file.unlink()
         except (OSError, IOError) as e:
-            raise RuntimeError(f"Test storage directory {storage_dir} is not writable: {e}")
-        
+            raise RuntimeError(
+                f"Test storage directory {storage_dir} is not writable: {e}"
+            )
+
         # Set environment variable to point to the test storage directory
         os.environ["CREWAI_STORAGE_DIR"] = str(storage_dir)
-        
+
         yield
-        
+
         # Cleanup is handled automatically when tempfile context exits
+
+
+@pytest.fixture(scope="module")
+def vcr_config(request) -> dict:
+    return {
+        "cassette_library_dir": "tests/cassettes",
+    }

tests/crew_test.py

@@ -42,11 +42,6 @@ from crewai.utilities.events.event_listener import EventListener
 from crewai.utilities.rpm_controller import RPMController
 from crewai.utilities.task_output_storage_handler import TaskOutputStorageHandler
 
-# Skip streaming tests when running in CI/CD environments
-skip_streaming_in_ci = pytest.mark.skipif(
-    os.getenv("CI") is not None, reason="Skipping streaming tests in CI/CD environments"
-)
-
 ceo = Agent(
     role="CEO",
     goal="Make sure the writers in your company produce amazing content.",
@@ -963,7 +958,6 @@ def test_api_calls_throttling(capsys):
         moveon.assert_called()
 
 
-@skip_streaming_in_ci
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_crew_kickoff_usage_metrics():
     inputs = [
@@ -999,7 +993,6 @@ def test_crew_kickoff_usage_metrics():
         assert result.token_usage.cached_prompt_tokens == 0
 
 
-@skip_streaming_in_ci
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_crew_kickoff_streaming_usage_metrics():
     inputs = [
@@ -4069,11 +4062,17 @@ def test_crew_guardrail_feedback_in_context():
 
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_before_kickoff_callback():
-    from crewai.project import CrewBase, agent, before_kickoff, task
+    from crewai.project import CrewBase
 
     @CrewBase
     class TestCrewClass:
-        from crewai.project import crew
+        from typing import List
+
+        from crewai.agents.agent_builder.base_agent import BaseAgent
+        from crewai.project import CrewBase, agent, before_kickoff, crew, task
+
+        agents: List[BaseAgent]
+        tasks: List[Task]
 
         agents_config = None
         tasks_config = None
@@ -4250,53 +4249,93 @@ def test_crew_kickoff_for_each_works_with_manager_agent_copy():
     assert crew_copy.manager_agent.role == crew.manager_agent.role
     assert crew_copy.manager_agent.goal == crew.manager_agent.goal
 
+
 def test_crew_copy_with_memory():
     """Test that copying a crew with memory enabled does not raise validation errors and copies memory correctly."""
     agent = Agent(role="Test Agent", goal="Test Goal", backstory="Test Backstory")
     task = Task(description="Test Task", expected_output="Test Output", agent=agent)
     crew = Crew(agents=[agent], tasks=[task], memory=True)
 
-    original_short_term_id = id(crew._short_term_memory) if crew._short_term_memory else None
-    original_long_term_id = id(crew._long_term_memory) if crew._long_term_memory else None
+    original_short_term_id = (
+        id(crew._short_term_memory) if crew._short_term_memory else None
+    )
+    original_long_term_id = (
+        id(crew._long_term_memory) if crew._long_term_memory else None
+    )
     original_entity_id = id(crew._entity_memory) if crew._entity_memory else None
     original_external_id = id(crew._external_memory) if crew._external_memory else None
     original_user_id = id(crew._user_memory) if crew._user_memory else None
 
-
     try:
         crew_copy = crew.copy()
 
-        assert hasattr(crew_copy, "_short_term_memory"), "Copied crew should have _short_term_memory"
-        assert crew_copy._short_term_memory is not None, "Copied _short_term_memory should not be None"
-        assert id(crew_copy._short_term_memory) != original_short_term_id, "Copied _short_term_memory should be a new object"
+        assert hasattr(
+            crew_copy, "_short_term_memory"
+        ), "Copied crew should have _short_term_memory"
+        assert (
+            crew_copy._short_term_memory is not None
+        ), "Copied _short_term_memory should not be None"
+        assert (
+            id(crew_copy._short_term_memory) != original_short_term_id
+        ), "Copied _short_term_memory should be a new object"
 
-        assert hasattr(crew_copy, "_long_term_memory"), "Copied crew should have _long_term_memory"
-        assert crew_copy._long_term_memory is not None, "Copied _long_term_memory should not be None"
-        assert id(crew_copy._long_term_memory) != original_long_term_id, "Copied _long_term_memory should be a new object"
+        assert hasattr(
+            crew_copy, "_long_term_memory"
+        ), "Copied crew should have _long_term_memory"
+        assert (
+            crew_copy._long_term_memory is not None
+        ), "Copied _long_term_memory should not be None"
+        assert (
+            id(crew_copy._long_term_memory) != original_long_term_id
+        ), "Copied _long_term_memory should be a new object"
 
-        assert hasattr(crew_copy, "_entity_memory"), "Copied crew should have _entity_memory"
-        assert crew_copy._entity_memory is not None, "Copied _entity_memory should not be None"
-        assert id(crew_copy._entity_memory) != original_entity_id, "Copied _entity_memory should be a new object"
+        assert hasattr(
+            crew_copy, "_entity_memory"
+        ), "Copied crew should have _entity_memory"
+        assert (
+            crew_copy._entity_memory is not None
+        ), "Copied _entity_memory should not be None"
+        assert (
+            id(crew_copy._entity_memory) != original_entity_id
+        ), "Copied _entity_memory should be a new object"
 
         if original_external_id:
-             assert hasattr(crew_copy, "_external_memory"), "Copied crew should have _external_memory"
-             assert crew_copy._external_memory is not None, "Copied _external_memory should not be None"
-             assert id(crew_copy._external_memory) != original_external_id, "Copied _external_memory should be a new object"
+            assert hasattr(
+                crew_copy, "_external_memory"
+            ), "Copied crew should have _external_memory"
+            assert (
+                crew_copy._external_memory is not None
+            ), "Copied _external_memory should not be None"
+            assert (
+                id(crew_copy._external_memory) != original_external_id
+            ), "Copied _external_memory should be a new object"
         else:
-             assert not hasattr(crew_copy, "_external_memory") or crew_copy._external_memory is None, "Copied _external_memory should be None if not originally present"
+            assert (
+                not hasattr(crew_copy, "_external_memory")
+                or crew_copy._external_memory is None
+            ), "Copied _external_memory should be None if not originally present"
 
         if original_user_id:
-             assert hasattr(crew_copy, "_user_memory"), "Copied crew should have _user_memory"
-             assert crew_copy._user_memory is not None, "Copied _user_memory should not be None"
-             assert id(crew_copy._user_memory) != original_user_id, "Copied _user_memory should be a new object"
+            assert hasattr(
+                crew_copy, "_user_memory"
+            ), "Copied crew should have _user_memory"
+            assert (
+                crew_copy._user_memory is not None
+            ), "Copied _user_memory should not be None"
+            assert (
+                id(crew_copy._user_memory) != original_user_id
+            ), "Copied _user_memory should be a new object"
         else:
-             assert not hasattr(crew_copy, "_user_memory") or crew_copy._user_memory is None, "Copied _user_memory should be None if not originally present"
-
+            assert (
+                not hasattr(crew_copy, "_user_memory") or crew_copy._user_memory is None
+            ), "Copied _user_memory should be None if not originally present"
 
     except pydantic_core.ValidationError as e:
-         if "Input should be an instance of" in str(e) and ("Memory" in str(e)):
-              pytest.fail(f"Copying with memory raised Pydantic ValidationError, likely due to incorrect memory copy: {e}")
-         else:
-              raise e # Re-raise other validation errors
+        if "Input should be an instance of" in str(e) and ("Memory" in str(e)):
+            pytest.fail(
+                f"Copying with memory raised Pydantic ValidationError, likely due to incorrect memory copy: {e}"
+            )
+        else:
+            raise e  # Re-raise other validation errors
     except Exception as e:
         pytest.fail(f"Copying crew raised an unexpected exception: {e}")

tests/llm_test.py

@@ -2,13 +2,16 @@ import os
 from time import sleep
 from unittest.mock import MagicMock, patch
 
+import litellm
 import pytest
 from pydantic import BaseModel
 
 from crewai.agents.agent_builder.utilities.base_token_process import TokenProcess
 from crewai.llm import CONTEXT_WINDOW_USAGE_RATIO, LLM
-from crewai.utilities.events import crewai_event_bus
-from crewai.utilities.events.tool_usage_events import ToolExecutionErrorEvent
+from crewai.utilities.events import (
+    LLMCallCompletedEvent,
+    LLMStreamChunkEvent,
+)
 from crewai.utilities.token_counter_callback import TokenCalcHandler
 
 
@@ -304,6 +307,27 @@ def test_context_window_validation():
     assert "must be between 1024 and 2097152" in str(excinfo.value)
 
 
+@pytest.fixture
+def get_weather_tool_schema():
+    return {
+        "type": "function",
+        "function": {
+            "name": "get_weather",
+            "description": "Get the current weather in a given location",
+            "parameters": {
+                "type": "object",
+                "properties": {
+                    "location": {
+                        "type": "string",
+                        "description": "The city and state, e.g. San Francisco, CA",
+                    }
+                },
+                "required": ["location"],
+            },
+        },
+    }
+
+
 @pytest.mark.vcr(filter_headers=["authorization"])
 @pytest.fixture
 def anthropic_llm():
@@ -395,3 +419,117 @@ def test_deepseek_r1_with_open_router():
     result = llm.call("What is the capital of France?")
     assert isinstance(result, str)
     assert "Paris" in result
+
+
+def assert_event_count(
+    mock_emit,
+    expected_completed_tool_call: int = 0,
+    expected_stream_chunk: int = 0,
+    expected_completed_llm_call: int = 0,
+    expected_final_chunk_result: str = "",
+):
+    event_count = {
+        "completed_tool_call": 0,
+        "stream_chunk": 0,
+        "completed_llm_call": 0,
+    }
+    final_chunk_result = ""
+    for _call in mock_emit.call_args_list:
+        event = _call[1]["event"]
+
+        if (
+            isinstance(event, LLMCallCompletedEvent)
+            and event.call_type.value == "tool_call"
+        ):
+            event_count["completed_tool_call"] += 1
+        elif isinstance(event, LLMStreamChunkEvent):
+            event_count["stream_chunk"] += 1
+            final_chunk_result += event.chunk
+        elif (
+            isinstance(event, LLMCallCompletedEvent)
+            and event.call_type.value == "llm_call"
+        ):
+            event_count["completed_llm_call"] += 1
+        else:
+            continue
+
+    assert event_count["completed_tool_call"] == expected_completed_tool_call
+    assert event_count["stream_chunk"] == expected_stream_chunk
+    assert event_count["completed_llm_call"] == expected_completed_llm_call
+    assert final_chunk_result == expected_final_chunk_result
+
+
+@pytest.fixture
+def mock_emit() -> MagicMock:
+    from crewai.utilities.events.crewai_event_bus import CrewAIEventsBus
+
+    with patch.object(CrewAIEventsBus, "emit") as mock_emit:
+        yield mock_emit
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_handle_streaming_tool_calls(get_weather_tool_schema, mock_emit):
+    llm = LLM(model="openai/gpt-4o", stream=True)
+    response = llm.call(
+        messages=[
+            {"role": "user", "content": "What is the weather in New York?"},
+        ],
+        tools=[get_weather_tool_schema],
+        available_functions={
+            "get_weather": lambda location: f"The weather in {location} is sunny"
+        },
+    )
+    assert response == "The weather in New York, NY is sunny"
+
+    expected_final_chunk_result = (
+        '{"location":"New York, NY"}The weather in New York, NY is sunny'
+    )
+    assert_event_count(
+        mock_emit=mock_emit,
+        expected_completed_tool_call=1,
+        expected_stream_chunk=10,
+        expected_completed_llm_call=1,
+        expected_final_chunk_result=expected_final_chunk_result,
+    )
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_handle_streaming_tool_calls_no_available_functions(
+    get_weather_tool_schema, mock_emit
+):
+    llm = LLM(model="openai/gpt-4o", stream=True)
+    response = llm.call(
+        messages=[
+            {"role": "user", "content": "What is the weather in New York?"},
+        ],
+        tools=[get_weather_tool_schema],
+    )
+    assert response == ""
+
+    assert_event_count(
+        mock_emit=mock_emit,
+        expected_stream_chunk=9,
+        expected_completed_llm_call=1,
+        expected_final_chunk_result='{"location":"New York, NY"}',
+    )
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_handle_streaming_tool_calls_no_tools(mock_emit):
+    llm = LLM(model="openai/gpt-4o", stream=True)
+    response = llm.call(
+        messages=[
+            {"role": "user", "content": "What is the weather in New York?"},
+        ],
+    )
+    assert (
+        response
+        == "I'm unable to provide real-time information or current weather updates. For the latest weather information in New York, I recommend checking a reliable weather website or app, such as the National Weather Service, Weather.com, or a similar service."
+    )
+
+    assert_event_count(
+        mock_emit=mock_emit,
+        expected_stream_chunk=46,
+        expected_completed_llm_call=1,
+        expected_final_chunk_result=response,
+    )

tests/memory/cassettes/test_save_and_search_with_provider.yaml

@@ -1,270 +0,0 @@
-interactions:
-- request:
-    body: ''
-    headers:
-      accept:
-      - '*/*'
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      host:
-      - api.mem0.ai
-      user-agent:
-      - python-httpx/0.27.0
-    method: GET
-    uri: https://api.mem0.ai/v1/memories/?user_id=test
-  response:
-    body:
-      string: '[]'
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 8b477138bad847b9-BOM
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '2'
-      Content-Type:
-      - application/json
-      Date:
-      - Sat, 17 Aug 2024 06:00:11 GMT
-      NEL:
-      - '{"success_fraction":0,"report_to":"cf-nel","max_age":604800}'
-      Report-To:
-      - '{"endpoints":[{"url":"https:\/\/a.nel.cloudflare.com\/report\/v4?s=uuyH2foMJVDpV%2FH52g1q%2FnvXKe3dBKVzvsK0mqmSNezkiszNR9OgrEJfVqmkX%2FlPFRP2sH4zrOuzGo6k%2FjzsjYJczqSWJUZHN2pPujiwnr1E9W%2BdLGKmG6%2FqPrGYAy2SBRWkkJVWsTO3OQ%3D%3D"}],"group":"cf-nel","max_age":604800}'
-      Server:
-      - cloudflare
-      allow:
-      - GET, POST, DELETE, OPTIONS
-      alt-svc:
-      - h3=":443"; ma=86400
-      cross-origin-opener-policy:
-      - same-origin
-      referrer-policy:
-      - same-origin
-      vary:
-      - Accept, origin, Cookie
-      x-content-type-options:
-      - nosniff
-      x-frame-options:
-      - DENY
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"batch": [{"properties": {"python_version": "3.12.4 (v3.12.4:8e8a4baf65,
-      Jun  6 2024, 17:33:18) [Clang 13.0.0 (clang-1300.0.29.30)]", "os": "darwin",
-      "os_version": "Darwin Kernel Version 23.4.0: Wed Feb 21 21:44:54 PST 2024; root:xnu-10063.101.15~2/RELEASE_ARM64_T6030",
-      "os_release": "23.4.0", "processor": "arm", "machine": "arm64", "function":
-      "mem0.client.main.MemoryClient", "$lib": "posthog-python", "$lib_version": "3.5.0",
-      "$geoip_disable": true}, "timestamp": "2024-08-17T06:00:11.526640+00:00", "context":
-      {}, "distinct_id": "fd411bd3-99a2-42d6-acd7-9fca8ad09580", "event": "client.init"}],
-      "historical_migration": false, "sentAt": "2024-08-17T06:00:11.701621+00:00",
-      "api_key": "phc_hgJkUVJFYtmaJqrvf6CYN67TIQ8yhXAkWzUn9AMU4yX"}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '740'
-      Content-Type:
-      - application/json
-      User-Agent:
-      - posthog-python/3.5.0
-    method: POST
-    uri: https://us.i.posthog.com/batch/
-  response:
-    body:
-      string: '{"status":"Ok"}'
-    headers:
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '15'
-      Content-Type:
-      - application/json
-      Date:
-      - Sat, 17 Aug 2024 06:00:12 GMT
-      access-control-allow-credentials:
-      - 'true'
-      server:
-      - envoy
-      vary:
-      - origin, access-control-request-method, access-control-request-headers
-      x-envoy-upstream-service-time:
-      - '69'
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"messages": [{"role": "user", "content": "Remember the following insights
-      from Agent run: test value with provider"}], "metadata": {"task": "test_task_provider",
-      "agent": "test_agent_provider"}, "app_id": "Researcher"}'
-    headers:
-      accept:
-      - '*/*'
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '219'
-      content-type:
-      - application/json
-      host:
-      - api.mem0.ai
-      user-agent:
-      - python-httpx/0.27.0
-    method: POST
-    uri: https://api.mem0.ai/v1/memories/
-  response:
-    body:
-      string: '{"message":"ok"}'
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 8b477140282547b9-BOM
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '16'
-      Content-Type:
-      - application/json
-      Date:
-      - Sat, 17 Aug 2024 06:00:13 GMT
-      NEL:
-      - '{"success_fraction":0,"report_to":"cf-nel","max_age":604800}'
-      Report-To:
-      - '{"endpoints":[{"url":"https:\/\/a.nel.cloudflare.com\/report\/v4?s=FRjJKSk3YxVj03wA7S05H8ts35KnWfqS3wb6Rfy4kVZ4BgXfw7nJbm92wI6vEv5fWcAcHVnOlkJDggs11B01BMuB2k3a9RqlBi0dJNiMuk%2Bgm5xE%2BODMPWJctYNRwQMjNVbteUpS%2Fad8YA%3D%3D"}],"group":"cf-nel","max_age":604800}'
-      Server:
-      - cloudflare
-      allow:
-      - GET, POST, DELETE, OPTIONS
-      alt-svc:
-      - h3=":443"; ma=86400
-      cross-origin-opener-policy:
-      - same-origin
-      referrer-policy:
-      - same-origin
-      vary:
-      - Accept, origin, Cookie
-      x-content-type-options:
-      - nosniff
-      x-frame-options:
-      - DENY
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"query": "test value with provider", "limit": 3, "app_id": "Researcher"}'
-    headers:
-      accept:
-      - '*/*'
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '73'
-      content-type:
-      - application/json
-      host:
-      - api.mem0.ai
-      user-agent:
-      - python-httpx/0.27.0
-    method: POST
-    uri: https://api.mem0.ai/v1/memories/search/
-  response:
-    body:
-      string: '[]'
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 8b47714d083b47b9-BOM
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '2'
-      Content-Type:
-      - application/json
-      Date:
-      - Sat, 17 Aug 2024 06:00:14 GMT
-      NEL:
-      - '{"success_fraction":0,"report_to":"cf-nel","max_age":604800}'
-      Report-To:
-      - '{"endpoints":[{"url":"https:\/\/a.nel.cloudflare.com\/report\/v4?s=2DRWL1cdKdMvnE8vx1fPUGeTITOgSGl3N5g84PS6w30GRqpfz79BtSx6REhpnOiFV8kM6KGqln0iCZ5yoHc2jBVVJXhPJhQ5t0uerD9JFnkphjISrJOU1MJjZWneT9PlNABddxvVNCmluA%3D%3D"}],"group":"cf-nel","max_age":604800}'
-      Server:
-      - cloudflare
-      allow:
-      - POST, OPTIONS
-      alt-svc:
-      - h3=":443"; ma=86400
-      cross-origin-opener-policy:
-      - same-origin
-      referrer-policy:
-      - same-origin
-      vary:
-      - Accept, origin, Cookie
-      x-content-type-options:
-      - nosniff
-      x-frame-options:
-      - DENY
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"batch": [{"properties": {"python_version": "3.12.4 (v3.12.4:8e8a4baf65,
-      Jun  6 2024, 17:33:18) [Clang 13.0.0 (clang-1300.0.29.30)]", "os": "darwin",
-      "os_version": "Darwin Kernel Version 23.4.0: Wed Feb 21 21:44:54 PST 2024; root:xnu-10063.101.15~2/RELEASE_ARM64_T6030",
-      "os_release": "23.4.0", "processor": "arm", "machine": "arm64", "function":
-      "mem0.client.main.MemoryClient", "$lib": "posthog-python", "$lib_version": "3.5.0",
-      "$geoip_disable": true}, "timestamp": "2024-08-17T06:00:13.593952+00:00", "context":
-      {}, "distinct_id": "fd411bd3-99a2-42d6-acd7-9fca8ad09580", "event": "client.add"}],
-      "historical_migration": false, "sentAt": "2024-08-17T06:00:13.858277+00:00",
-      "api_key": "phc_hgJkUVJFYtmaJqrvf6CYN67TIQ8yhXAkWzUn9AMU4yX"}'
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '739'
-      Content-Type:
-      - application/json
-      User-Agent:
-      - posthog-python/3.5.0
-    method: POST
-    uri: https://us.i.posthog.com/batch/
-  response:
-    body:
-      string: '{"status":"Ok"}'
-    headers:
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '15'
-      Content-Type:
-      - application/json
-      Date:
-      - Sat, 17 Aug 2024 06:00:13 GMT
-      access-control-allow-credentials:
-      - 'true'
-      server:
-      - envoy
-      vary:
-      - origin, access-control-request-method, access-control-request-headers
-      x-envoy-upstream-service-time:
-      - '33'
-    status:
-      code: 200
-      message: OK
-version: 1

tests/project_test.py

@@ -1,6 +1,9 @@
+from typing import List
+
 import pytest
 
 from crewai.agent import Agent
+from crewai.agents.agent_builder.base_agent import BaseAgent
 from crewai.crew import Crew
 from crewai.llm import LLM
 from crewai.project import (
@@ -40,28 +43,32 @@ class InternalCrew:
     agents_config = "config/agents.yaml"
     tasks_config = "config/tasks.yaml"
 
+    agents: List[BaseAgent]
+    tasks: List[Task]
+
     @llm
     def local_llm(self):
         return LLM(
-            model='openai/model_name',
+            model="openai/model_name",
             api_key="None",
-            base_url="http://xxx.xxx.xxx.xxx:8000/v1")
+            base_url="http://xxx.xxx.xxx.xxx:8000/v1",
+        )
 
     @agent
     def researcher(self):
-        return Agent(config=self.agents_config["researcher"])
+        return Agent(config=self.agents_config["researcher"])  # type: ignore[index]
 
     @agent
     def reporting_analyst(self):
-        return Agent(config=self.agents_config["reporting_analyst"])
+        return Agent(config=self.agents_config["reporting_analyst"])  # type: ignore[index]
 
     @task
     def research_task(self):
-        return Task(config=self.tasks_config["research_task"])
+        return Task(config=self.tasks_config["research_task"])  # type: ignore[index]
 
     @task
     def reporting_task(self):
-        return Task(config=self.tasks_config["reporting_task"])
+        return Task(config=self.tasks_config["reporting_task"])  # type: ignore[index]
 
     @before_kickoff
     def modify_inputs(self, inputs):
@@ -165,24 +172,27 @@ def test_before_kickoff_with_none_input():
 def test_multiple_before_after_kickoff():
     @CrewBase
     class MultipleHooksCrew:
+        agents: List[BaseAgent]
+        tasks: List[Task]
+
         agents_config = "config/agents.yaml"
         tasks_config = "config/tasks.yaml"
 
         @agent
         def researcher(self):
-            return Agent(config=self.agents_config["researcher"])
+            return Agent(config=self.agents_config["researcher"])  # type: ignore[index]
 
         @agent
         def reporting_analyst(self):
-            return Agent(config=self.agents_config["reporting_analyst"])
+            return Agent(config=self.agents_config["reporting_analyst"])  # type: ignore[index]
 
         @task
         def research_task(self):
-            return Task(config=self.tasks_config["research_task"])
+            return Task(config=self.tasks_config["research_task"])  # type: ignore[index]
 
         @task
         def reporting_task(self):
-            return Task(config=self.tasks_config["reporting_task"])
+            return Task(config=self.tasks_config["reporting_task"])  # type: ignore[index]
 
         @before_kickoff
         def first_before(self, inputs):

tests/tools/agent_tools/agent_tools_test.py

@@ -16,6 +16,13 @@ delegate_tool = tools[0]
 ask_tool = tools[1]
 
 
+@pytest.fixture(scope="module")
+def vcr_config(request) -> dict:
+    return {
+        "cassette_library_dir": "tests/tools/agent_tools/cassettes",
+    }
+
+
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_delegate_work():
     result = delegate_tool.run(

tests/utilities/test_converter.py

@@ -21,6 +21,13 @@ from crewai.utilities.converter import (
 from crewai.utilities.pydantic_schema_parser import PydanticSchemaParser
 
 
+@pytest.fixture(scope="module")
+def vcr_config(request) -> dict:
+    return {
+        "cassette_library_dir": "tests/utilities/cassettes",
+    }
+
+
 # Sample Pydantic models for testing
 class EmailResponse(BaseModel):
     previous_message_content: str

tests/utilities/test_events.py

@@ -50,10 +50,13 @@ from crewai.utilities.events.tool_usage_events import (
     ToolUsageErrorEvent,
 )
 
-# Skip streaming tests when running in CI/CD environments
-skip_streaming_in_ci = pytest.mark.skipif(
-    os.getenv("CI") is not None, reason="Skipping streaming tests in CI/CD environments"
-)
+
+@pytest.fixture(scope="module")
+def vcr_config(request) -> dict:
+    return {
+        "cassette_library_dir": "tests/utilities/cassettes",
+    }
+
 
 base_agent = Agent(
     role="base_agent",
@@ -625,7 +628,6 @@ def test_llm_emits_call_failed_event():
         assert received_events[0].error == error_message
 
 
-@skip_streaming_in_ci
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_llm_emits_stream_chunk_events():
     """Test that LLM emits stream chunk events when streaming is enabled."""
@@ -650,7 +652,6 @@ def test_llm_emits_stream_chunk_events():
         assert "".join(received_chunks) == response
 
 
-@skip_streaming_in_ci
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_llm_no_stream_chunks_when_streaming_disabled():
     """Test that LLM doesn't emit stream chunk events when streaming is disabled."""

uv.lock

@@ -1,42 +1,32 @@
 version = 1
+revision = 1
 requires-python = ">=3.10, <3.13"
 resolution-markers = [
-    "python_full_version < '3.11' and platform_system == 'Darwin' and sys_platform == 'darwin'",
-    "python_full_version < '3.11' and platform_machine == 'aarch64' and platform_system == 'Linux' and sys_platform == 'darwin'",
-    "(python_full_version < '3.11' and platform_machine != 'aarch64' and platform_system != 'Darwin' and sys_platform == 'darwin') or (python_full_version < '3.11' and platform_system != 'Darwin' and platform_system != 'Linux' and sys_platform == 'darwin')",
-    "python_full_version < '3.11' and platform_machine == 'aarch64' and platform_system == 'Darwin' and sys_platform == 'linux'",
-    "python_full_version < '3.11' and platform_machine == 'aarch64' and platform_system == 'Linux' and sys_platform == 'linux'",
-    "python_full_version < '3.11' and platform_machine == 'aarch64' and platform_system != 'Darwin' and platform_system != 'Linux' and sys_platform == 'linux'",
-    "(python_full_version < '3.11' and platform_machine != 'aarch64' and platform_system == 'Darwin' and sys_platform != 'darwin') or (python_full_version < '3.11' and platform_system == 'Darwin' and sys_platform != 'darwin' and sys_platform != 'linux')",
-    "python_full_version < '3.11' and platform_machine == 'aarch64' and platform_system == 'Linux' and sys_platform != 'darwin' and sys_platform != 'linux'",
-    "(python_full_version < '3.11' and platform_machine != 'aarch64' and platform_system != 'Darwin' and sys_platform != 'darwin') or (python_full_version < '3.11' and platform_system != 'Darwin' and platform_system != 'Linux' and sys_platform != 'darwin' and sys_platform != 'linux')",
-    "python_full_version == '3.11.*' and platform_system == 'Darwin' and sys_platform == 'darwin'",
-    "python_full_version == '3.11.*' and platform_machine == 'aarch64' and platform_system == 'Linux' and sys_platform == 'darwin'",
-    "(python_full_version == '3.11.*' and platform_machine != 'aarch64' and platform_system != 'Darwin' and sys_platform == 'darwin') or (python_full_version == '3.11.*' and platform_system != 'Darwin' and platform_system != 'Linux' and sys_platform == 'darwin')",
-    "python_full_version == '3.11.*' and platform_machine == 'aarch64' and platform_system == 'Darwin' and sys_platform == 'linux'",
-    "python_full_version == '3.11.*' and platform_machine == 'aarch64' and platform_system == 'Linux' and sys_platform == 'linux'",
-    "python_full_version == '3.11.*' and platform_machine == 'aarch64' and platform_system != 'Darwin' and platform_system != 'Linux' and sys_platform == 'linux'",
-    "(python_full_version == '3.11.*' and platform_machine != 'aarch64' and platform_system == 'Darwin' and sys_platform != 'darwin') or (python_full_version == '3.11.*' and platform_system == 'Darwin' and sys_platform != 'darwin' and sys_platform != 'linux')",
-    "python_full_version == '3.11.*' and platform_machine == 'aarch64' and platform_system == 'Linux' and sys_platform != 'darwin' and sys_platform != 'linux'",
-    "(python_full_version == '3.11.*' and platform_machine != 'aarch64' and platform_system != 'Darwin' and sys_platform != 'darwin') or (python_full_version == '3.11.*' and platform_system != 'Darwin' and platform_system != 'Linux' and sys_platform != 'darwin' and sys_platform != 'linux')",
-    "python_full_version >= '3.12' and python_full_version < '3.12.4' and platform_system == 'Darwin' and sys_platform == 'darwin'",
-    "python_full_version >= '3.12' and python_full_version < '3.12.4' and platform_machine == 'aarch64' and platform_system == 'Linux' and sys_platform == 'darwin'",
-    "(python_full_version >= '3.12' and python_full_version < '3.12.4' and platform_machine != 'aarch64' and platform_system != 'Darwin' and sys_platform == 'darwin') or (python_full_version >= '3.12' and python_full_version < '3.12.4' and platform_system != 'Darwin' and platform_system != 'Linux' and sys_platform == 'darwin')",
-    "python_full_version >= '3.12' and python_full_version < '3.12.4' and platform_machine == 'aarch64' and platform_system == 'Darwin' and sys_platform == 'linux'",
-    "python_full_version >= '3.12' and python_full_version < '3.12.4' and platform_machine == 'aarch64' and platform_system == 'Linux' and sys_platform == 'linux'",
-    "python_full_version >= '3.12' and python_full_version < '3.12.4' and platform_machine == 'aarch64' and platform_system != 'Darwin' and platform_system != 'Linux' and sys_platform == 'linux'",
-    "(python_full_version >= '3.12' and python_full_version < '3.12.4' and platform_machine != 'aarch64' and platform_system == 'Darwin' and sys_platform != 'darwin') or (python_full_version >= '3.12' and python_full_version < '3.12.4' and platform_system == 'Darwin' and sys_platform != 'darwin' and sys_platform != 'linux')",
-    "python_full_version >= '3.12' and python_full_version < '3.12.4' and platform_machine == 'aarch64' and platform_system == 'Linux' and sys_platform != 'darwin' and sys_platform != 'linux'",
-    "(python_full_version >= '3.12' and python_full_version < '3.12.4' and platform_machine != 'aarch64' and platform_system != 'Darwin' and sys_platform != 'darwin') or (python_full_version >= '3.12' and python_full_version < '3.12.4' and platform_system != 'Darwin' and platform_system != 'Linux' and sys_platform != 'darwin' and sys_platform != 'linux')",
-    "python_full_version >= '3.12.4' and platform_system == 'Darwin' and sys_platform == 'darwin'",
-    "python_full_version >= '3.12.4' and platform_machine == 'aarch64' and platform_system == 'Linux' and sys_platform == 'darwin'",
-    "(python_full_version >= '3.12.4' and platform_machine != 'aarch64' and platform_system != 'Darwin' and sys_platform == 'darwin') or (python_full_version >= '3.12.4' and platform_system != 'Darwin' and platform_system != 'Linux' and sys_platform == 'darwin')",
-    "python_full_version >= '3.12.4' and platform_machine == 'aarch64' and platform_system == 'Darwin' and sys_platform == 'linux'",
-    "python_full_version >= '3.12.4' and platform_machine == 'aarch64' and platform_system == 'Linux' and sys_platform == 'linux'",
-    "python_full_version >= '3.12.4' and platform_machine == 'aarch64' and platform_system != 'Darwin' and platform_system != 'Linux' and sys_platform == 'linux'",
-    "(python_full_version >= '3.12.4' and platform_machine != 'aarch64' and platform_system == 'Darwin' and sys_platform != 'darwin') or (python_full_version >= '3.12.4' and platform_system == 'Darwin' and sys_platform != 'darwin' and sys_platform != 'linux')",
-    "python_full_version >= '3.12.4' and platform_machine == 'aarch64' and platform_system == 'Linux' and sys_platform != 'darwin' and sys_platform != 'linux'",
-    "(python_full_version >= '3.12.4' and platform_machine != 'aarch64' and platform_system != 'Darwin' and sys_platform != 'darwin') or (python_full_version >= '3.12.4' and platform_system != 'Darwin' and platform_system != 'Linux' and sys_platform != 'darwin' and sys_platform != 'linux')",
+    "python_full_version < '3.11' and platform_python_implementation == 'PyPy' and sys_platform == 'darwin'",
+    "python_full_version < '3.11' and platform_python_implementation != 'PyPy' and sys_platform == 'darwin'",
+    "python_version < '0'",
+    "python_full_version < '3.11' and platform_machine == 'aarch64' and platform_python_implementation == 'PyPy' and sys_platform == 'linux'",
+    "python_full_version < '3.11' and platform_machine == 'aarch64' and platform_python_implementation != 'PyPy' and sys_platform == 'linux'",
+    "(python_full_version < '3.11' and platform_machine != 'aarch64' and platform_python_implementation == 'PyPy' and sys_platform == 'linux') or (python_full_version < '3.11' and platform_python_implementation == 'PyPy' and sys_platform != 'darwin' and sys_platform != 'linux')",
+    "(python_full_version < '3.11' and platform_machine != 'aarch64' and platform_python_implementation != 'PyPy' and sys_platform == 'linux') or (python_full_version < '3.11' and platform_python_implementation != 'PyPy' and sys_platform != 'darwin' and sys_platform != 'linux')",
+    "python_full_version == '3.11.*' and platform_python_implementation == 'PyPy' and sys_platform == 'darwin'",
+    "python_full_version == '3.11.*' and platform_python_implementation != 'PyPy' and sys_platform == 'darwin'",
+    "python_full_version == '3.11.*' and platform_machine == 'aarch64' and platform_python_implementation == 'PyPy' and sys_platform == 'linux'",
+    "python_full_version == '3.11.*' and platform_machine == 'aarch64' and platform_python_implementation != 'PyPy' and sys_platform == 'linux'",
+    "(python_full_version == '3.11.*' and platform_machine != 'aarch64' and platform_python_implementation == 'PyPy' and sys_platform == 'linux') or (python_full_version == '3.11.*' and platform_python_implementation == 'PyPy' and sys_platform != 'darwin' and sys_platform != 'linux')",
+    "(python_full_version == '3.11.*' and platform_machine != 'aarch64' and platform_python_implementation != 'PyPy' and sys_platform == 'linux') or (python_full_version == '3.11.*' and platform_python_implementation != 'PyPy' and sys_platform != 'darwin' and sys_platform != 'linux')",
+    "python_full_version >= '3.12' and python_full_version < '3.12.4' and platform_python_implementation == 'PyPy' and sys_platform == 'darwin'",
+    "python_full_version >= '3.12' and python_full_version < '3.12.4' and platform_python_implementation != 'PyPy' and sys_platform == 'darwin'",
+    "python_full_version >= '3.12' and python_full_version < '3.12.4' and platform_machine == 'aarch64' and platform_python_implementation == 'PyPy' and sys_platform == 'linux'",
+    "python_full_version >= '3.12' and python_full_version < '3.12.4' and platform_machine == 'aarch64' and platform_python_implementation != 'PyPy' and sys_platform == 'linux'",
+    "(python_full_version >= '3.12' and python_full_version < '3.12.4' and platform_machine != 'aarch64' and platform_python_implementation == 'PyPy' and sys_platform == 'linux') or (python_full_version >= '3.12' and python_full_version < '3.12.4' and platform_python_implementation == 'PyPy' and sys_platform != 'darwin' and sys_platform != 'linux')",
+    "(python_full_version >= '3.12' and python_full_version < '3.12.4' and platform_machine != 'aarch64' and platform_python_implementation != 'PyPy' and sys_platform == 'linux') or (python_full_version >= '3.12' and python_full_version < '3.12.4' and platform_python_implementation != 'PyPy' and sys_platform != 'darwin' and sys_platform != 'linux')",
+    "python_full_version >= '3.12.4' and platform_python_implementation == 'PyPy' and sys_platform == 'darwin'",
+    "python_full_version >= '3.12.4' and platform_python_implementation != 'PyPy' and sys_platform == 'darwin'",
+    "python_full_version >= '3.12.4' and platform_machine == 'aarch64' and platform_python_implementation == 'PyPy' and sys_platform == 'linux'",
+    "python_full_version >= '3.12.4' and platform_machine == 'aarch64' and platform_python_implementation != 'PyPy' and sys_platform == 'linux'",
+    "(python_full_version >= '3.12.4' and platform_machine != 'aarch64' and platform_python_implementation == 'PyPy' and sys_platform == 'linux') or (python_full_version >= '3.12.4' and platform_python_implementation == 'PyPy' and sys_platform != 'darwin' and sys_platform != 'linux')",
+    "(python_full_version >= '3.12.4' and platform_machine != 'aarch64' and platform_python_implementation != 'PyPy' and sys_platform == 'linux') or (python_full_version >= '3.12.4' and platform_python_implementation != 'PyPy' and sys_platform != 'darwin' and sys_platform != 'linux')",
 ]
 
 [[package]]
@@ -344,7 +334,7 @@ name = "build"
 version = "1.2.2.post1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "colorama", marker = "os_name == 'nt'" },
+    { name = "colorama", marker = "(os_name == 'nt' and platform_machine != 'aarch64' and sys_platform == 'linux') or (os_name == 'nt' and sys_platform != 'darwin' and sys_platform != 'linux')" },
     { name = "importlib-metadata", marker = "python_full_version < '3.10.2'" },
     { name = "packaging" },
     { name = "pyproject-hooks" },
@@ -579,7 +569,7 @@ name = "click"
 version = "8.1.8"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "colorama", marker = "platform_system == 'Windows'" },
+    { name = "colorama", marker = "sys_platform == 'win32'" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/b9/2e/0090cbf739cee7d23781ad4b89a9894a41538e4fcf4c31dcdd705b78eb8b/click-8.1.8.tar.gz", hash = "sha256:ed53c9d8990d83c2a27deae68e4ee337473f6330c040a31d4225c9574d16096a", size = 226593 }
 wheels = [
@@ -703,8 +693,8 @@ dev = [
     { name = "pre-commit" },
     { name = "pytest" },
     { name = "pytest-asyncio" },
+    { name = "pytest-recording" },
     { name = "pytest-subprocess" },
-    { name = "pytest-vcr" },
     { name = "python-dotenv" },
     { name = "ruff" },
 ]
@@ -745,6 +735,7 @@ requires-dist = [
     { name = "tomli-w", specifier = ">=1.1.0" },
     { name = "uv", specifier = ">=0.4.25" },
 ]
+provides-extras = ["tools", "embeddings", "agentops", "fastembed", "pdfplumber", "pandas", "openpyxl", "mem0", "docling", "aisuite"]
 
 [package.metadata.requires-dev]
 dev = [
@@ -759,8 +750,8 @@ dev = [
     { name = "pre-commit", specifier = ">=3.6.0" },
     { name = "pytest", specifier = ">=8.0.0" },
     { name = "pytest-asyncio", specifier = ">=0.23.7" },
+    { name = "pytest-recording", specifier = ">=0.13.2" },
     { name = "pytest-subprocess", specifier = ">=1.5.2" },
-    { name = "pytest-vcr", specifier = ">=1.0.2" },
     { name = "python-dotenv", specifier = ">=1.0.0" },
     { name = "ruff", specifier = ">=0.8.2" },
 ]
@@ -2518,7 +2509,7 @@ version = "1.6.1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "click" },
-    { name = "colorama", marker = "platform_system == 'Windows'" },
+    { name = "colorama", marker = "sys_platform == 'win32'" },
     { name = "ghp-import" },
     { name = "jinja2" },
     { name = "markdown" },
@@ -2699,7 +2690,7 @@ version = "2.10.2"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "pygments" },
-    { name = "pywin32", marker = "platform_system == 'Windows'" },
+    { name = "pywin32", marker = "sys_platform == 'win32'" },
     { name = "tqdm" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/3a/93/80ac75c20ce54c785648b4ed363c88f148bf22637e10c9863db4fbe73e74/mpire-2.10.2.tar.gz", hash = "sha256:f66a321e93fadff34585a4bfa05e95bd946cf714b442f51c529038eb45773d97", size = 271270 }
@@ -2946,7 +2937,7 @@ name = "nvidia-cudnn-cu12"
 version = "9.1.0.70"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "nvidia-cublas-cu12", marker = "(platform_machine != 'aarch64' and platform_system != 'Darwin') or (platform_system != 'Darwin' and platform_system != 'Linux' and sys_platform != 'linux')" },
+    { name = "nvidia-cublas-cu12", marker = "(platform_machine != 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux')" },
 ]
 wheels = [
     { url = "https://files.pythonhosted.org/packages/9f/fd/713452cd72343f682b1c7b9321e23829f00b842ceaedcda96e742ea0b0b3/nvidia_cudnn_cu12-9.1.0.70-py3-none-manylinux2014_x86_64.whl", hash = "sha256:165764f44ef8c61fcdfdfdbe769d687e06374059fbb388b6c89ecb0e28793a6f", size = 664752741 },
@@ -2973,9 +2964,9 @@ name = "nvidia-cusolver-cu12"
 version = "11.4.5.107"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "nvidia-cublas-cu12", marker = "(platform_machine != 'aarch64' and platform_system != 'Darwin') or (platform_system != 'Darwin' and platform_system != 'Linux' and sys_platform != 'linux')" },
-    { name = "nvidia-cusparse-cu12", marker = "(platform_machine != 'aarch64' and platform_system != 'Darwin') or (platform_system != 'Darwin' and platform_system != 'Linux' and sys_platform != 'linux')" },
-    { name = "nvidia-nvjitlink-cu12", marker = "(platform_machine != 'aarch64' and platform_system != 'Darwin') or (platform_system != 'Darwin' and platform_system != 'Linux' and sys_platform != 'linux')" },
+    { name = "nvidia-cublas-cu12", marker = "(platform_machine != 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux')" },
+    { name = "nvidia-cusparse-cu12", marker = "(platform_machine != 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux')" },
+    { name = "nvidia-nvjitlink-cu12", marker = "(platform_machine != 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux')" },
 ]
 wheels = [
     { url = "https://files.pythonhosted.org/packages/bc/1d/8de1e5c67099015c834315e333911273a8c6aaba78923dd1d1e25fc5f217/nvidia_cusolver_cu12-11.4.5.107-py3-none-manylinux1_x86_64.whl", hash = "sha256:8a7ec542f0412294b15072fa7dab71d31334014a69f953004ea7a118206fe0dd", size = 124161928 },
@@ -2986,7 +2977,7 @@ name = "nvidia-cusparse-cu12"
 version = "12.1.0.106"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "nvidia-nvjitlink-cu12", marker = "(platform_machine != 'aarch64' and platform_system != 'Darwin') or (platform_system != 'Darwin' and platform_system != 'Linux' and sys_platform != 'linux')" },
+    { name = "nvidia-nvjitlink-cu12", marker = "(platform_machine != 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux')" },
 ]
 wheels = [
     { url = "https://files.pythonhosted.org/packages/65/5b/cfaeebf25cd9fdec14338ccb16f6b2c4c7fa9163aefcf057d86b9cc248bb/nvidia_cusparse_cu12-12.1.0.106-py3-none-manylinux1_x86_64.whl", hash = "sha256:f3b50f42cf363f86ab21f720998517a659a48131e8d538dc02f8768237bd884c", size = 195958278 },
@@ -2997,7 +2988,6 @@ name = "nvidia-nccl-cu12"
 version = "2.20.5"
 source = { registry = "https://pypi.org/simple" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/c1/bb/d09dda47c881f9ff504afd6f9ca4f502ded6d8fc2f572cacc5e39da91c28/nvidia_nccl_cu12-2.20.5-py3-none-manylinux2014_aarch64.whl", hash = "sha256:1fc150d5c3250b170b29410ba682384b14581db722b2531b0d8d33c595f33d01", size = 176238458 },
     { url = "https://files.pythonhosted.org/packages/4b/2a/0a131f572aa09f741c30ccd45a8e56316e8be8dfc7bc19bf0ab7cfef7b19/nvidia_nccl_cu12-2.20.5-py3-none-manylinux2014_x86_64.whl", hash = "sha256:057f6bf9685f75215d0c53bf3ac4a10b3e6578351de307abad9e18a99182af56", size = 176249402 },
 ]
 
@@ -3007,7 +2997,6 @@ version = "12.6.85"
 source = { registry = "https://pypi.org/simple" }
 wheels = [
     { url = "https://files.pythonhosted.org/packages/9d/d7/c5383e47c7e9bf1c99d5bd2a8c935af2b6d705ad831a7ec5c97db4d82f4f/nvidia_nvjitlink_cu12-12.6.85-py3-none-manylinux2010_x86_64.manylinux_2_12_x86_64.whl", hash = "sha256:eedc36df9e88b682efe4309aa16b5b4e78c2407eac59e8c10a6a47535164369a", size = 19744971 },
-    { url = "https://files.pythonhosted.org/packages/31/db/dc71113d441f208cdfe7ae10d4983884e13f464a6252450693365e166dcf/nvidia_nvjitlink_cu12-12.6.85-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:cf4eaa7d4b6b543ffd69d6abfb11efdeb2db48270d94dfd3a452c24150829e41", size = 19270338 },
 ]
 
 [[package]]
@@ -3525,7 +3514,7 @@ name = "portalocker"
 version = "2.10.1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "pywin32", marker = "platform_system == 'Windows'" },
+    { name = "pywin32", marker = "sys_platform == 'win32'" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/ed/d3/c6c64067759e87af98cc668c1cc75171347d0f1577fab7ca3749134e3cd4/portalocker-2.10.1.tar.gz", hash = "sha256:ef1bf844e878ab08aee7e40184156e1151f228f103aa5c6bd0724cc330960f8f", size = 40891 }
 wheels = [
@@ -4075,6 +4064,20 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/96/31/6607dab48616902f76885dfcf62c08d929796fc3b2d2318faf9fd54dbed9/pytest_asyncio-0.24.0-py3-none-any.whl", hash = "sha256:a811296ed596b69bf0b6f3dc40f83bcaf341b155a269052d82efa2b25ac7037b", size = 18024 },
 ]
 
+[[package]]
+name = "pytest-recording"
+version = "0.13.2"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "pytest" },
+    { name = "vcrpy", version = "5.1.0", source = { registry = "https://pypi.org/simple" }, marker = "platform_python_implementation == 'PyPy'" },
+    { name = "vcrpy", version = "7.0.0", source = { registry = "https://pypi.org/simple" }, marker = "platform_python_implementation != 'PyPy'" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/fe/2a/ea6b8036ae01979eae02d8ad5a7da14dec90d9176b613e49fb8d134c78fc/pytest_recording-0.13.2.tar.gz", hash = "sha256:000c3babbb466681457fd65b723427c1779a0c6c17d9e381c3142a701e124877", size = 25270 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/72/52/8e67a969e9fad3fa5ec4eab9f2a7348ff04692065c7deda21d76e9112703/pytest_recording-0.13.2-py3-none-any.whl", hash = "sha256:3820fe5743d1ac46e807989e11d073cb776a60bdc544cf43ebca454051b22d13", size = 12783 },
+]
+
 [[package]]
 name = "pytest-subprocess"
 version = "1.5.2"
@@ -4087,19 +4090,6 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/10/77/a80e8f9126b95ffd5ad4d04bd14005c68dcbf0d88f53b2b14893f6cc7232/pytest_subprocess-1.5.2-py3-none-any.whl", hash = "sha256:23ac7732aa8bd45f1757265b1316eb72a7f55b41fb21e2ca22e149ba3629fa46", size = 20886 },
 ]
 
-[[package]]
-name = "pytest-vcr"
-version = "1.0.2"
-source = { registry = "https://pypi.org/simple" }
-dependencies = [
-    { name = "pytest" },
-    { name = "vcrpy" },
-]
-sdist = { url = "https://files.pythonhosted.org/packages/1a/60/104c619483c1a42775d3f8b27293f1ecfc0728014874d065e68cb9702d49/pytest-vcr-1.0.2.tar.gz", hash = "sha256:23ee51b75abbcc43d926272773aae4f39f93aceb75ed56852d0bf618f92e1896", size = 3810 }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/9d/d3/ff520d11e6ee400602711d1ece8168dcfc5b6d8146fb7db4244a6ad6a9c3/pytest_vcr-1.0.2-py2.py3-none-any.whl", hash = "sha256:2f316e0539399bea0296e8b8401145c62b6f85e9066af7e57b6151481b0d6d9c", size = 4137 },
-]
-
 [[package]]
 name = "python-bidi"
 version = "0.6.3"
@@ -5032,19 +5022,19 @@ dependencies = [
     { name = "fsspec" },
     { name = "jinja2" },
     { name = "networkx" },
-    { name = "nvidia-cublas-cu12", marker = "platform_machine == 'x86_64' and platform_system == 'Linux'" },
-    { name = "nvidia-cuda-cupti-cu12", marker = "platform_machine == 'x86_64' and platform_system == 'Linux'" },
-    { name = "nvidia-cuda-nvrtc-cu12", marker = "platform_machine == 'x86_64' and platform_system == 'Linux'" },
-    { name = "nvidia-cuda-runtime-cu12", marker = "platform_machine == 'x86_64' and platform_system == 'Linux'" },
-    { name = "nvidia-cudnn-cu12", marker = "platform_machine == 'x86_64' and platform_system == 'Linux'" },
-    { name = "nvidia-cufft-cu12", marker = "platform_machine == 'x86_64' and platform_system == 'Linux'" },
-    { name = "nvidia-curand-cu12", marker = "platform_machine == 'x86_64' and platform_system == 'Linux'" },
-    { name = "nvidia-cusolver-cu12", marker = "platform_machine == 'x86_64' and platform_system == 'Linux'" },
-    { name = "nvidia-cusparse-cu12", marker = "platform_machine == 'x86_64' and platform_system == 'Linux'" },
-    { name = "nvidia-nccl-cu12", marker = "platform_machine == 'x86_64' and platform_system == 'Linux'" },
-    { name = "nvidia-nvtx-cu12", marker = "platform_machine == 'x86_64' and platform_system == 'Linux'" },
+    { name = "nvidia-cublas-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-cuda-cupti-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-cuda-nvrtc-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-cuda-runtime-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-cudnn-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-cufft-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-curand-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-cusolver-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-cusparse-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-nccl-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
+    { name = "nvidia-nvtx-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
     { name = "sympy" },
-    { name = "triton", marker = "platform_machine == 'x86_64' and platform_system == 'Linux'" },
+    { name = "triton", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
     { name = "typing-extensions" },
 ]
 wheels = [
@@ -5091,7 +5081,7 @@ name = "tqdm"
 version = "4.66.5"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "colorama", marker = "platform_system == 'Windows'" },
+    { name = "colorama", marker = "sys_platform == 'win32'" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/58/83/6ba9844a41128c62e810fddddd72473201f3eacde02046066142a2d96cc5/tqdm-4.66.5.tar.gz", hash = "sha256:e1020aef2e5096702d8a025ac7d16b1577279c9d63f8375b63083e9a5f0fcbad", size = 169504 }
 wheels = [
@@ -5133,7 +5123,7 @@ name = "triton"
 version = "3.0.0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "filelock", marker = "(platform_machine != 'aarch64' and platform_system != 'Darwin') or (platform_system != 'Darwin' and platform_system != 'Linux' and sys_platform != 'linux')" },
+    { name = "filelock", marker = "(platform_machine != 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux')" },
 ]
 wheels = [
     { url = "https://files.pythonhosted.org/packages/45/27/14cc3101409b9b4b9241d2ba7deaa93535a217a211c86c4cc7151fb12181/triton-3.0.0-1-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:e1efef76935b2febc365bfadf74bcb65a6f959a9872e5bddf44cc9e0adce1e1a", size = 209376304 },
@@ -5288,16 +5278,59 @@ wheels = [
 name = "vcrpy"
 version = "5.1.0"
 source = { registry = "https://pypi.org/simple" }
+resolution-markers = [
+    "python_full_version < '3.11' and platform_python_implementation == 'PyPy' and sys_platform == 'darwin'",
+    "python_full_version < '3.11' and platform_machine == 'aarch64' and platform_python_implementation == 'PyPy' and sys_platform == 'linux'",
+    "(python_full_version < '3.11' and platform_machine != 'aarch64' and platform_python_implementation == 'PyPy' and sys_platform == 'linux') or (python_full_version < '3.11' and platform_python_implementation == 'PyPy' and sys_platform != 'darwin' and sys_platform != 'linux')",
+    "python_full_version == '3.11.*' and platform_python_implementation == 'PyPy' and sys_platform == 'darwin'",
+    "python_full_version == '3.11.*' and platform_machine == 'aarch64' and platform_python_implementation == 'PyPy' and sys_platform == 'linux'",
+    "(python_full_version == '3.11.*' and platform_machine != 'aarch64' and platform_python_implementation == 'PyPy' and sys_platform == 'linux') or (python_full_version == '3.11.*' and platform_python_implementation == 'PyPy' and sys_platform != 'darwin' and sys_platform != 'linux')",
+    "python_full_version >= '3.12' and python_full_version < '3.12.4' and platform_python_implementation == 'PyPy' and sys_platform == 'darwin'",
+    "python_full_version >= '3.12' and python_full_version < '3.12.4' and platform_machine == 'aarch64' and platform_python_implementation == 'PyPy' and sys_platform == 'linux'",
+    "(python_full_version >= '3.12' and python_full_version < '3.12.4' and platform_machine != 'aarch64' and platform_python_implementation == 'PyPy' and sys_platform == 'linux') or (python_full_version >= '3.12' and python_full_version < '3.12.4' and platform_python_implementation == 'PyPy' and sys_platform != 'darwin' and sys_platform != 'linux')",
+    "python_full_version >= '3.12.4' and platform_python_implementation == 'PyPy' and sys_platform == 'darwin'",
+    "python_full_version >= '3.12.4' and platform_machine == 'aarch64' and platform_python_implementation == 'PyPy' and sys_platform == 'linux'",
+    "(python_full_version >= '3.12.4' and platform_machine != 'aarch64' and platform_python_implementation == 'PyPy' and sys_platform == 'linux') or (python_full_version >= '3.12.4' and platform_python_implementation == 'PyPy' and sys_platform != 'darwin' and sys_platform != 'linux')",
+]
 dependencies = [
-    { name = "pyyaml" },
-    { name = "wrapt" },
-    { name = "yarl" },
+    { name = "pyyaml", marker = "platform_python_implementation == 'PyPy'" },
+    { name = "wrapt", marker = "platform_python_implementation == 'PyPy'" },
+    { name = "yarl", marker = "platform_python_implementation == 'PyPy'" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/a5/ea/a166a3cce4ac5958ba9bbd9768acdb1ba38ae17ff7986da09fa5b9dbc633/vcrpy-5.1.0.tar.gz", hash = "sha256:bbf1532f2618a04f11bce2a99af3a9647a32c880957293ff91e0a5f187b6b3d2", size = 84576 }
 wheels = [
     { url = "https://files.pythonhosted.org/packages/2a/5b/3f70bcb279ad30026cc4f1df0a0491a0205a24dddd88301f396c485de9e7/vcrpy-5.1.0-py2.py3-none-any.whl", hash = "sha256:605e7b7a63dcd940db1df3ab2697ca7faf0e835c0852882142bafb19649d599e", size = 41969 },
 ]
 
+[[package]]
+name = "vcrpy"
+version = "7.0.0"
+source = { registry = "https://pypi.org/simple" }
+resolution-markers = [
+    "python_full_version < '3.11' and platform_python_implementation != 'PyPy' and sys_platform == 'darwin'",
+    "python_full_version < '3.11' and platform_machine == 'aarch64' and platform_python_implementation != 'PyPy' and sys_platform == 'linux'",
+    "(python_full_version < '3.11' and platform_machine != 'aarch64' and platform_python_implementation != 'PyPy' and sys_platform == 'linux') or (python_full_version < '3.11' and platform_python_implementation != 'PyPy' and sys_platform != 'darwin' and sys_platform != 'linux')",
+    "python_full_version == '3.11.*' and platform_python_implementation != 'PyPy' and sys_platform == 'darwin'",
+    "python_full_version == '3.11.*' and platform_machine == 'aarch64' and platform_python_implementation != 'PyPy' and sys_platform == 'linux'",
+    "(python_full_version == '3.11.*' and platform_machine != 'aarch64' and platform_python_implementation != 'PyPy' and sys_platform == 'linux') or (python_full_version == '3.11.*' and platform_python_implementation != 'PyPy' and sys_platform != 'darwin' and sys_platform != 'linux')",
+    "python_full_version >= '3.12' and python_full_version < '3.12.4' and platform_python_implementation != 'PyPy' and sys_platform == 'darwin'",
+    "python_full_version >= '3.12' and python_full_version < '3.12.4' and platform_machine == 'aarch64' and platform_python_implementation != 'PyPy' and sys_platform == 'linux'",
+    "(python_full_version >= '3.12' and python_full_version < '3.12.4' and platform_machine != 'aarch64' and platform_python_implementation != 'PyPy' and sys_platform == 'linux') or (python_full_version >= '3.12' and python_full_version < '3.12.4' and platform_python_implementation != 'PyPy' and sys_platform != 'darwin' and sys_platform != 'linux')",
+    "python_full_version >= '3.12.4' and platform_python_implementation != 'PyPy' and sys_platform == 'darwin'",
+    "python_full_version >= '3.12.4' and platform_machine == 'aarch64' and platform_python_implementation != 'PyPy' and sys_platform == 'linux'",
+    "(python_full_version >= '3.12.4' and platform_machine != 'aarch64' and platform_python_implementation != 'PyPy' and sys_platform == 'linux') or (python_full_version >= '3.12.4' and platform_python_implementation != 'PyPy' and sys_platform != 'darwin' and sys_platform != 'linux')",
+]
+dependencies = [
+    { name = "pyyaml", marker = "platform_python_implementation != 'PyPy'" },
+    { name = "urllib3", marker = "platform_python_implementation != 'PyPy'" },
+    { name = "wrapt", marker = "platform_python_implementation != 'PyPy'" },
+    { name = "yarl", marker = "platform_python_implementation != 'PyPy'" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/25/d3/856e06184d4572aada1dd559ddec3bedc46df1f2edc5ab2c91121a2cccdb/vcrpy-7.0.0.tar.gz", hash = "sha256:176391ad0425edde1680c5b20738ea3dc7fb942520a48d2993448050986b3a50", size = 85502 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/13/5d/1f15b252890c968d42b348d1e9b0aa12d5bf3e776704178ec37cceccdb63/vcrpy-7.0.0-py2.py3-none-any.whl", hash = "sha256:55791e26c18daa363435054d8b35bd41a4ac441b6676167635d1b37a71dbe124", size = 42321 },
+]
+
 [[package]]
 name = "virtualenv"
 version = "20.27.0"