Fix tests: Import SSLError from requests.exceptions

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

.github/security.md

@@ -1,19 +1,27 @@
-CrewAI takes the security of our software products and services seriously, which includes all source code repositories managed through our GitHub organization.
-If you believe you have found a security vulnerability in any CrewAI product or service, please report it to us as described below.
+## CrewAI Security Vulnerability Reporting Policy
 
- ## Reporting a Vulnerability
- Please do not report security vulnerabilities through public GitHub issues.
- To report a vulnerability, please email us at security@crewai.com.
- Please include the requested information listed below so that we can triage your report more quickly
+CrewAI prioritizes the security of our software products, services, and GitHub repositories. To promptly address vulnerabilities, follow these steps for reporting security issues:
 
- - Type of issue (e.g. SQL injection, cross-site scripting, etc.)
- - Full paths of source file(s) related to the manifestation of the issue
- - The location of the affected source code (tag/branch/commit or direct URL)
- - Any special configuration required to reproduce the issue
- - Step-by-step instructions to reproduce the issue (please include screenshots if needed)
- - Proof-of-concept or exploit code (if possible)
- - Impact of the issue, including how an attacker might exploit the issue
+### Reporting Process
+Do **not** report vulnerabilities via public GitHub issues.
 
- Once we have received your report, we will respond to you at the email address you provide. If the issue is confirmed, we will release a patch as soon as possible depending on the complexity of the issue.
+Email all vulnerability reports directly to:  
+**security@crewai.com**
 
- At this time, we are not offering a bug bounty program. Any rewards will be at our discretion.
+### Required Information
+To help us quickly validate and remediate the issue, your report must include:
+
+- **Vulnerability Type:** Clearly state the vulnerability type (e.g., SQL injection, XSS, privilege escalation).
+- **Affected Source Code:** Provide full file paths and direct URLs (branch, tag, or commit).
+- **Reproduction Steps:** Include detailed, step-by-step instructions. Screenshots are recommended.
+- **Special Configuration:** Document any special settings or configurations required to reproduce.
+- **Proof-of-Concept (PoC):** Provide exploit or PoC code (if available).
+- **Impact Assessment:** Clearly explain the severity and potential exploitation scenarios.
+
+### Our Response
+- We will acknowledge receipt of your report promptly via your provided email.
+- Confirmed vulnerabilities will receive priority remediation based on severity.
+- Patches will be released as swiftly as possible following verification.
+
+### Reward Notice
+Currently, we do not offer a bug bounty program. Rewards, if issued, are discretionary.

.github/workflows/linter.yml

@@ -5,12 +5,29 @@ on: [pull_request]
 jobs:
   lint:
     runs-on: ubuntu-latest
+    env:
+      TARGET_BRANCH: ${{ github.event.pull_request.base.ref }}
     steps:
       - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
 
-      - name: Install Requirements
+      - name: Fetch Target Branch
+        run: git fetch origin $TARGET_BRANCH --depth=1
+
+      - name: Install Ruff
+        run: pip install ruff
+
+      - name: Get Changed Python Files
+        id: changed-files
         run: |
-          pip install ruff
+          merge_base=$(git merge-base origin/"$TARGET_BRANCH" HEAD)
+          changed_files=$(git diff --name-only --diff-filter=ACMRTUB "$merge_base" | grep '\.py$' || true)
+          echo "files<<EOF" >> $GITHUB_OUTPUT
+          echo "$changed_files" >> $GITHUB_OUTPUT
+          echo "EOF" >> $GITHUB_OUTPUT
 
-      - name: Run Ruff Linter
-        run: ruff check
+      - name: Run Ruff on Changed Files
+        if: ${{ steps.changed-files.outputs.files != '' }}
+        run: |
+          echo "${{ steps.changed-files.outputs.files }}" | tr " " "\n" | xargs -I{} ruff check "{}"

.ruff.toml

@@ -2,8 +2,3 @@ exclude = [
     "templates",
     "__init__.py",
 ]
-
-[lint]
-select = [
-    "I", # isort rules
-]

docs/cli.md

@@ -0,0 +1,120 @@
+# CrewAI CLI Documentation
+
+The CrewAI Command Line Interface (CLI) provides tools for creating, managing, and running CrewAI projects.
+
+## Installation
+
+The CLI is automatically installed when you install the CrewAI package:
+
+```bash
+pip install crewai
+```
+
+## Available Commands
+
+### Create Command
+
+The `create` command allows you to create new crews or flows.
+
+```bash
+crewai create [TYPE] [NAME] [OPTIONS]
+```
+
+#### Arguments
+
+- `TYPE`: Type of project to create. Must be either `crew` or `flow`.
+- `NAME`: Name of the project to create.
+
+#### Options
+
+- `--provider`: The provider to use for the crew.
+- `--skip_provider`: Skip provider validation.
+- `--skip_ssl_verify`: Skip SSL certificate verification when fetching provider data (not secure).
+
+#### Examples
+
+Create a new crew:
+
+```bash
+crewai create crew my_crew
+```
+
+Create a new crew with a specific provider:
+
+```bash
+crewai create crew my_crew --provider openai
+```
+
+Create a new crew and skip SSL certificate verification (useful in environments with self-signed certificates):
+
+```bash
+crewai create crew my_crew --skip_ssl_verify
+```
+
+> **Warning**: Using the `--skip_ssl_verify` flag is not recommended in production environments as it bypasses SSL certificate verification, which can expose your system to security risks. Only use this flag in development environments or when you understand the security implications.
+
+Create a new flow:
+
+```bash
+crewai create flow my_flow
+```
+
+### Run Command
+
+The `run` command executes your crew.
+
+```bash
+crewai run
+```
+
+### Train Command
+
+The `train` command trains your crew.
+
+```bash
+crewai train [OPTIONS]
+```
+
+#### Options
+
+- `-n, --n_iterations`: Number of iterations to train the crew (default: 5).
+- `-f, --filename`: Path to a custom file for training (default: "trained_agents_data.pkl").
+
+### Reset Memories Command
+
+The `reset_memories` command resets the crew memories.
+
+```bash
+crewai reset_memories [OPTIONS]
+```
+
+#### Options
+
+- `-l, --long`: Reset LONG TERM memory.
+- `-s, --short`: Reset SHORT TERM memory.
+- `-e, --entities`: Reset ENTITIES memory.
+- `-kn, --knowledge`: Reset KNOWLEDGE storage.
+- `-k, --kickoff-outputs`: Reset LATEST KICKOFF TASK OUTPUTS.
+- `-a, --all`: Reset ALL memories.
+
+### Other Commands
+
+- `version`: Show the installed version of crewai.
+- `replay`: Replay the crew execution from a specific task.
+- `log_tasks_outputs`: Retrieve your latest crew.kickoff() task outputs.
+- `test`: Test the crew and evaluate the results.
+- `install`: Install the Crew.
+- `update`: Update the pyproject.toml of the Crew project to use uv.
+- `signup`: Sign Up/Login to CrewAI+.
+- `login`: Sign Up/Login to CrewAI+.
+- `chat`: Start a conversation with the Crew.
+
+## Security Considerations
+
+When using the CrewAI CLI, be aware of the following security considerations:
+
+1. **API Keys**: Store your API keys securely in environment variables or a `.env` file. Never hardcode them in your scripts.
+
+2. **SSL Verification**: The `--skip_ssl_verify` flag bypasses SSL certificate verification, which can expose your system to security risks. Only use this flag in development environments or when you understand the security implications.
+
+3. **Provider Data**: When fetching provider data, ensure that you're using a secure connection. The CLI will display a warning when SSL verification is disabled.

docs/concepts/knowledge.mdx

@@ -700,4 +700,11 @@ recent_news = SpaceNewsKnowledgeSource(
     - Configure appropriate embedding models
     - Consider using local embedding providers for faster processing
   </Accordion>
+
+  <Accordion title="One Time Knowledge">
+    - With the typical file structure provided by CrewAI, knowledge sources are embedded every time the kickoff is triggered.
+    - If the knowledge sources are large, this leads to inefficiency and increased latency, as the same data is embedded each time.
+    - To resolve this, directly initialize the knowledge parameter instead of the knowledge_sources parameter.
+    - Link to the issue to get complete idea [Github Issue](https://github.com/crewAIInc/crewAI/issues/2755)
+  </Accordion>  
 </AccordionGroup>

docs/concepts/llms.mdx

@@ -169,19 +169,55 @@ In this section, you'll find detailed examples that help you select, configure,
     ```
   </Accordion>
 
-  <Accordion title="Google">
-    Set the following environment variables in your `.env` file:
+  <Accordion title="Google (Gemini API)">
+    Set your API key in your `.env` file. If you need a key, or need to find an
+    existing key, check [AI Studio](https://aistudio.google.com/apikey).
 
-    ```toml Code
-    # Option 1: Gemini accessed with an API key.
+    ```toml .env
     # https://ai.google.dev/gemini-api/docs/api-key
     GEMINI_API_KEY=<your-api-key>
-
-    # Option 2: Vertex AI IAM credentials for Gemini, Anthropic, and Model Garden.
-    # https://cloud.google.com/vertex-ai/generative-ai/docs/overview
     ```
 
-    Get credentials from your Google Cloud Console and save it to a JSON file with the following code:
+    Example usage in your CrewAI project:
+    ```python Code
+    from crewai import LLM
+
+    llm = LLM(
+        model="gemini/gemini-2.0-flash",
+        temperature=0.7,
+    )
+    ```
+
+    ### Gemini models
+
+    Google offers a range of powerful models optimized for different use cases.
+
+    | Model                          | Context Window | Best For                                                          |
+    |--------------------------------|----------------|-------------------------------------------------------------------|
+    | gemini-2.5-flash-preview-04-17 | 1M tokens      | Adaptive thinking, cost efficiency                                |
+    | gemini-2.5-pro-preview-05-06   | 1M tokens      | Enhanced thinking and reasoning, multimodal understanding, advanced coding, and more |
+    | gemini-2.0-flash               | 1M tokens      | Next generation features, speed, thinking, and realtime streaming |
+    | gemini-2.0-flash-lite          | 1M tokens      | Cost efficiency and low latency                                   |
+    | gemini-1.5-flash               | 1M tokens      | Balanced multimodal model, good for most tasks                    |
+    | gemini-1.5-flash-8B            | 1M tokens      | Fastest, most cost-efficient, good for high-frequency tasks       |
+    | gemini-1.5-pro                 | 2M tokens      | Best performing, wide variety of reasoning tasks including logical reasoning, coding, and creative collaboration |
+
+    The full list of models is available in the [Gemini model docs](https://ai.google.dev/gemini-api/docs/models).
+
+    ### Gemma
+
+    The Gemini API also allows you to use your API key to access [Gemma models](https://ai.google.dev/gemma/docs) hosted on Google infrastructure.
+
+    | Model          | Context Window |
+    |----------------|----------------|
+    | gemma-3-1b-it  | 32k tokens     |
+    | gemma-3-4b-it  | 32k tokens     |
+    | gemma-3-12b-it | 32k tokens     |
+    | gemma-3-27b-it | 128k tokens    |
+
+  </Accordion>
+  <Accordion title="Google (Vertex AI)">
+    Get credentials from your Google Cloud Console and save it to a JSON file, then load it with the following code:
     ```python Code
     import json
 
@@ -205,14 +241,18 @@ In this section, you'll find detailed examples that help you select, configure,
         vertex_credentials=vertex_credentials_json
     )
     ```
+
     Google offers a range of powerful models optimized for different use cases:
 
-    | Model                  | Context Window | Best For                                                          |
-    |-----------------------|----------------|------------------------------------------------------------------|
-    | gemini-2.0-flash-exp  | 1M tokens      | Higher quality at faster speed, multimodal model, good for most tasks |
-    | gemini-1.5-flash      | 1M tokens      | Balanced multimodal model, good for most tasks                    |
-    | gemini-1.5-flash-8B   | 1M tokens      | Fastest, most cost-efficient, good for high-frequency tasks       |
-    | gemini-1.5-pro        | 2M tokens      | Best performing, wide variety of reasoning tasks including logical reasoning, coding, and creative collaboration |
+    | Model                          | Context Window | Best For                                                          |
+    |--------------------------------|----------------|-------------------------------------------------------------------|
+    | gemini-2.5-flash-preview-04-17 | 1M tokens      | Adaptive thinking, cost efficiency                                |
+    | gemini-2.5-pro-preview-05-06   | 1M tokens      | Enhanced thinking and reasoning, multimodal understanding, advanced coding, and more |
+    | gemini-2.0-flash               | 1M tokens      | Next generation features, speed, thinking, and realtime streaming |
+    | gemini-2.0-flash-lite          | 1M tokens      | Cost efficiency and low latency                                   |
+    | gemini-1.5-flash               | 1M tokens      | Balanced multimodal model, good for most tasks                    |
+    | gemini-1.5-flash-8B            | 1M tokens      | Fastest, most cost-efficient, good for high-frequency tasks       |
+    | gemini-1.5-pro                 | 2M tokens      | Best performing, wide variety of reasoning tasks including logical reasoning, coding, and creative collaboration |
   </Accordion>
 
   <Accordion title="Azure">

docs/how-to/arize-phoenix-observability.mdx

@@ -68,7 +68,13 @@ We'll create a CrewAI application where two agents collaborate to research and w
 ```python
 from crewai import Agent, Crew, Process, Task
 from crewai_tools import SerperDevTool
+from openinference.instrumentation.crewai import CrewAIInstrumentor
+from phoenix.otel import register
 
+# setup monitoring for your crew
+tracer_provider = register(
+    endpoint="http://localhost:6006/v1/traces")
+CrewAIInstrumentor().instrument(skip_dep_check=True, tracer_provider=tracer_provider)
 search_tool = SerperDevTool()
 
 # Define your agents with roles and goals

src/crewai/agent.py

@@ -25,6 +25,7 @@ from crewai.utilities.agent_utils import (
 )
 from crewai.utilities.constants import TRAINED_AGENTS_DATA_FILE, TRAINING_DATA_FILE
 from crewai.utilities.converter import generate_model_description
+from crewai.utilities.errors import AgentRepositoryError
 from crewai.utilities.events.agent_events import (
     AgentExecutionCompletedEvent,
     AgentExecutionErrorEvent,
@@ -134,6 +135,49 @@ class Agent(BaseAgent):
         default=None,
         description="Knowledge search query for the agent dynamically generated by the agent.",
     )
+    from_repository: Optional[str] = Field(
+        default=None,
+        description="The Agent's role to be used from your repository.",
+    )
+
+    @model_validator(mode="before")
+    def validate_from_repository(cls, v):
+        if v is not None and (from_repository := v.get("from_repository")):
+            return cls._load_agent_from_repository(from_repository) | v
+        return v
+
+    @classmethod
+    def _load_agent_from_repository(cls, from_repository: str) -> Dict[str, Any]:
+        attributes: Dict[str, Any] = {}
+        if from_repository:
+            import importlib
+
+            from crewai.cli.authentication.token import get_auth_token
+            from crewai.cli.plus_api import PlusAPI
+
+            client = PlusAPI(api_key=get_auth_token())
+            response = client.get_agent(from_repository)
+            if response.status_code != 200:
+                raise AgentRepositoryError(
+                    f"Agent {from_repository} could not be loaded: {response.text}"
+                )
+
+            agent = response.json()
+            for key, value in agent.items():
+                if key == "tools":
+                    attributes[key] = []
+                    for tool_name in value:
+                        try:
+                            module = importlib.import_module("crewai_tools")
+                            tool_class = getattr(module, tool_name)
+                            attributes[key].append(tool_class())
+                        except Exception as e:
+                            raise AgentRepositoryError(
+                                f"Tool {tool_name} could not be loaded: {e}"
+                            ) from e
+                else:
+                    attributes[key] = value
+        return attributes
 
     @model_validator(mode="after")
     def post_init_setup(self):

src/crewai/cli/authentication/token.py

@@ -5,5 +5,5 @@ def get_auth_token() -> str:
     """Get the authentication token."""
     access_token = TokenManager().get_token()
     if not access_token:
-        raise Exception()
+        raise Exception("No token found, make sure you are logged in")
     return access_token

src/crewai/cli/cli.py

@@ -1,6 +1,5 @@
-import os
 from importlib.metadata import version as get_version
-from typing import Optional, Tuple
+from typing import Optional
 
 import click
 
@@ -37,10 +36,11 @@ def crewai():
 @click.argument("name")
 @click.option("--provider", type=str, help="The provider to use for the crew")
 @click.option("--skip_provider", is_flag=True, help="Skip provider validation")
-def create(type, name, provider, skip_provider=False):
+@click.option("--skip_ssl_verify", is_flag=True, help="Skip SSL certificate verification (not secure)")
+def create(type, name, provider, skip_provider=False, skip_ssl_verify=False):
     """Create a new crew, or flow."""
     if type == "crew":
-        create_crew(name, provider, skip_provider)
+        create_crew(name, provider, skip_provider, skip_ssl_verify=skip_ssl_verify)
     elif type == "flow":
         create_flow(name)
     else:

src/crewai/cli/constants.py

@@ -13,7 +13,7 @@ ENV_VARS = {
     ],
     "gemini": [
         {
-            "prompt": "Enter your GEMINI API key (press Enter to skip)",
+            "prompt": "Enter your GEMINI API key from https://ai.dev/apikey (press Enter to skip)",
             "key_name": "GEMINI_API_KEY",
         }
     ],

src/crewai/cli/create_crew.py

@@ -89,12 +89,12 @@ def copy_template_files(folder_path, name, class_name, parent_folder):
             copy_template(src_file, dst_file, name, class_name, folder_path.name)
 
 
-def create_crew(name, provider=None, skip_provider=False, parent_folder=None):
+def create_crew(name, provider=None, skip_provider=False, parent_folder=None, skip_ssl_verify=False):
     folder_path, folder_name, class_name = create_folder_structure(name, parent_folder)
     env_vars = load_env_vars(folder_path)
     if not skip_provider:
         if not provider:
-            provider_models = get_provider_data()
+            provider_models = get_provider_data(skip_ssl_verify)
             if not provider_models:
                 return
 
@@ -114,7 +114,7 @@ def create_crew(name, provider=None, skip_provider=False, parent_folder=None):
                 click.secho("Keeping existing provider configuration.", fg="yellow")
                 return
 
-        provider_models = get_provider_data()
+        provider_models = get_provider_data(skip_ssl_verify)
         if not provider_models:
             return
 

src/crewai/cli/plus_api.py

@@ -14,6 +14,7 @@ class PlusAPI:
 
     TOOLS_RESOURCE = "/crewai_plus/api/v1/tools"
     CREWS_RESOURCE = "/crewai_plus/api/v1/crews"
+    AGENTS_RESOURCE = "/crewai_plus/api/v1/agents"
 
     def __init__(self, api_key: str) -> None:
         self.api_key = api_key
@@ -37,6 +38,9 @@ class PlusAPI:
     def get_tool(self, handle: str):
         return self._make_request("GET", f"{self.TOOLS_RESOURCE}/{handle}")
 
+    def get_agent(self, handle: str):
+        return self._make_request("GET", f"{self.AGENTS_RESOURCE}/{handle}")
+
     def publish_tool(
         self,
         handle: str,

src/crewai/cli/provider.py

@@ -106,13 +106,14 @@ def select_model(provider, provider_models):
     return selected_model
 
 
-def load_provider_data(cache_file, cache_expiry):
+def load_provider_data(cache_file, cache_expiry, skip_ssl_verify=False):
     """
     Loads provider data from a cache file if it exists and is not expired. If the cache is expired or corrupted, it fetches the data from the web.
 
     Args:
     - cache_file (Path): The path to the cache file.
     - cache_expiry (int): The cache expiry time in seconds.
+    - skip_ssl_verify (bool): Whether to skip SSL certificate verification.
 
     Returns:
     - dict or None: The loaded provider data or None if the operation fails.
@@ -133,7 +134,7 @@ def load_provider_data(cache_file, cache_expiry):
             "Cache expired or not found. Fetching provider data from the web...",
             fg="cyan",
         )
-    return fetch_provider_data(cache_file)
+    return fetch_provider_data(cache_file, skip_ssl_verify)
 
 
 def read_cache_file(cache_file):
@@ -147,34 +148,65 @@ def read_cache_file(cache_file):
     - dict or None: The JSON content of the cache file or None if the JSON is invalid.
     """
     try:
+        if not cache_file.exists():
+            return None
         with open(cache_file, "r") as f:
-            return json.load(f)
-    except json.JSONDecodeError:
+            data = json.load(f)
+            if not isinstance(data, dict):
+                click.secho("Invalid cache file format", fg="yellow")
+                return None
+            return data
+    except json.JSONDecodeError as e:
+        click.secho(f"Error parsing cache file: {str(e)}", fg="yellow")
+        return None
+    except OSError as e:
+        click.secho(f"Error reading cache file: {str(e)}", fg="yellow")
         return None
 
 
-def fetch_provider_data(cache_file):
+def fetch_provider_data(cache_file, skip_ssl_verify=False):
     """
     Fetches provider data from a specified URL and caches it to a file.
 
     Args:
     - cache_file (Path): The path to the cache file.
+    - skip_ssl_verify (bool): Whether to skip SSL certificate verification.
 
     Returns:
     - dict or None: The fetched provider data or None if the operation fails.
     """
     try:
-        response = requests.get(JSON_URL, stream=True, timeout=60)
+        if skip_ssl_verify:
+            click.secho(
+                "Warning: SSL certificate verification is disabled. This is not secure!",
+                fg="yellow",
+            )
+        response = requests.get(JSON_URL, stream=True, timeout=60, verify=not skip_ssl_verify)
         response.raise_for_status()
         data = download_data(response)
         with open(cache_file, "w") as f:
             json.dump(data, f)
         return data
+    except requests.Timeout:
+        click.secho("Timeout while fetching provider data", fg="red")
+        return None
+    except requests.SSLError as e:
+        click.secho(f"SSL verification failed: {str(e)}", fg="red")
+        if not skip_ssl_verify:
+            click.secho(
+                "You can bypass SSL verification with --skip_ssl_verify flag (not secure)",
+                fg="yellow",
+            )
+        return None
     except requests.RequestException as e:
-        click.secho(f"Error fetching provider data: {e}", fg="red")
+        click.secho(f"Error fetching provider data: {str(e)}", fg="red")
+        return None
     except json.JSONDecodeError:
         click.secho("Error parsing provider data. Invalid JSON format.", fg="red")
-    return None
+        return None
+    except OSError as e:
+        click.secho(f"Error writing to cache file: {str(e)}", fg="red")
+        return None
 
 
 def download_data(response):
@@ -201,10 +233,13 @@ def download_data(response):
     return json.loads(data_content.decode("utf-8"))
 
 
-def get_provider_data():
+def get_provider_data(skip_ssl_verify=False):
     """
     Retrieves provider data from a cache file, filters out models based on provider criteria, and returns a dictionary of providers mapped to their models.
 
+    Args:
+    - skip_ssl_verify (bool): Whether to skip SSL certificate verification.
+
     Returns:
     - dict or None: A dictionary of providers mapped to their models or None if the operation fails.
     """
@@ -213,7 +248,7 @@ def get_provider_data():
     cache_file = cache_dir / "provider_cache.json"
     cache_expiry = 24 * 3600
 
-    data = load_provider_data(cache_file, cache_expiry)
+    data = load_provider_data(cache_file, cache_expiry, skip_ssl_verify)
     if not data:
         return None
 

src/crewai/llm.py

@@ -5,8 +5,7 @@ import sys
 import threading
 import warnings
 from collections import defaultdict
-from contextlib import contextmanager
-from types import SimpleNamespace
+from contextlib import contextmanager, redirect_stderr, redirect_stdout
 from typing import (
     Any,
     DefaultDict,
@@ -31,7 +30,6 @@ from crewai.utilities.events.llm_events import (
     LLMCallType,
     LLMStreamChunkEvent,
 )
-from crewai.utilities.events.tool_usage_events import ToolExecutionErrorEvent
 
 with warnings.catch_warnings():
     warnings.simplefilter("ignore", UserWarning)
@@ -45,6 +43,9 @@ with warnings.catch_warnings():
     from litellm.utils import supports_response_schema
 
 
+import io
+from typing import TextIO
+
 from crewai.llms.base_llm import BaseLLM
 from crewai.utilities.events import crewai_event_bus
 from crewai.utilities.exceptions.context_window_exceeding_exception import (
@@ -54,12 +55,17 @@ from crewai.utilities.exceptions.context_window_exceeding_exception import (
 load_dotenv()
 
 
-class FilteredStream:
-    def __init__(self, original_stream):
+class FilteredStream(io.TextIOBase):
+    _lock = None
+
+    def __init__(self, original_stream: TextIO):
         self._original_stream = original_stream
         self._lock = threading.Lock()
 
-    def write(self, s) -> int:
+    def write(self, s: str) -> int:
+        if not self._lock:
+            self._lock = threading.Lock()
+
         with self._lock:
             # Filter out extraneous messages from LiteLLM
             if (
@@ -214,15 +220,11 @@ def suppress_warnings():
         )
 
         # Redirect stdout and stderr
-        old_stdout = sys.stdout
-        old_stderr = sys.stderr
-        sys.stdout = FilteredStream(old_stdout)
-        sys.stderr = FilteredStream(old_stderr)
-        try:
+        with (
+            redirect_stdout(FilteredStream(sys.stdout)),
+            redirect_stderr(FilteredStream(sys.stderr)),
+        ):
             yield
-        finally:
-            sys.stdout = old_stdout
-            sys.stderr = old_stderr
 
 
 class Delta(TypedDict):

src/crewai/utilities/errors.py

@@ -1,4 +1,5 @@
 """Error message definitions for CrewAI database operations."""
+
 from typing import Optional
 
 
@@ -37,3 +38,9 @@ class DatabaseError:
             The formatted error message
         """
         return template.format(str(error))
+
+
+class AgentRepositoryError(Exception):
+    """Exception raised when an agent repository is not found."""
+
+    ...

tests/agent_test.py

@@ -2,7 +2,7 @@
 
 import os
 from unittest import mock
-from unittest.mock import patch
+from unittest.mock import MagicMock, patch
 
 import pytest
 
@@ -18,6 +18,7 @@ from crewai.tools import tool
 from crewai.tools.tool_calling import InstructorToolCalling
 from crewai.tools.tool_usage import ToolUsage
 from crewai.utilities import RPMController
+from crewai.utilities.errors import AgentRepositoryError
 from crewai.utilities.events import crewai_event_bus
 from crewai.utilities.events.tool_usage_events import ToolUsageFinishedEvent
 
@@ -308,9 +309,7 @@ def test_cache_hitting():
     def handle_tool_end(source, event):
         received_events.append(event)
 
-    with (
-        patch.object(CacheHandler, "read") as read,
-    ):
+    with (patch.object(CacheHandler, "read") as read,):
         read.return_value = "0"
         task = Task(
             description="What is 2 times 6? Ignore correctness and just return the result of the multiplication tool, you must use the tool.",
@@ -1040,7 +1039,7 @@ def test_agent_human_input():
             CrewAgentExecutor,
             "_invoke_loop",
             return_value=AgentFinish(output="Hello", thought="", text=""),
-        ) as mock_invoke_loop,
+        ),
     ):
         # Execute the task
         output = agent.execute_task(task)
@@ -2025,3 +2024,86 @@ def test_get_knowledge_search_query():
                 },
             ]
         )
+
+
+@pytest.fixture
+def mock_get_auth_token():
+    with patch(
+        "crewai.cli.authentication.token.get_auth_token", return_value="test_token"
+    ):
+        yield
+
+
+@patch("crewai.cli.plus_api.PlusAPI.get_agent")
+def test_agent_from_repository(mock_get_agent, mock_get_auth_token):
+    from crewai_tools import SerperDevTool
+
+    mock_get_response = MagicMock()
+    mock_get_response.status_code = 200
+    mock_get_response.json.return_value = {
+        "role": "test role",
+        "goal": "test goal",
+        "backstory": "test backstory",
+        "tools": ["SerperDevTool"],
+    }
+    mock_get_agent.return_value = mock_get_response
+    agent = Agent(from_repository="test_agent")
+
+    assert agent.role == "test role"
+    assert agent.goal == "test goal"
+    assert agent.backstory == "test backstory"
+    assert len(agent.tools) == 1
+    assert isinstance(agent.tools[0], SerperDevTool)
+
+
+@patch("crewai.cli.plus_api.PlusAPI.get_agent")
+def test_agent_from_repository_override_attributes(mock_get_agent, mock_get_auth_token):
+    from crewai_tools import SerperDevTool
+
+    mock_get_response = MagicMock()
+    mock_get_response.status_code = 200
+    mock_get_response.json.return_value = {
+        "role": "test role",
+        "goal": "test goal",
+        "backstory": "test backstory",
+        "tools": ["SerperDevTool"],
+    }
+    mock_get_agent.return_value = mock_get_response
+    agent = Agent(from_repository="test_agent", role="Custom Role")
+
+    assert agent.role == "Custom Role"
+    assert agent.goal == "test goal"
+    assert agent.backstory == "test backstory"
+    assert len(agent.tools) == 1
+    assert isinstance(agent.tools[0], SerperDevTool)
+
+
+@patch("crewai.cli.plus_api.PlusAPI.get_agent")
+def test_agent_from_repository_with_invalid_tools(mock_get_agent, mock_get_auth_token):
+    mock_get_response = MagicMock()
+    mock_get_response.status_code = 200
+    mock_get_response.json.return_value = {
+        "role": "test role",
+        "goal": "test goal",
+        "backstory": "test backstory",
+        "tools": ["DoesNotExist"],
+    }
+    mock_get_agent.return_value = mock_get_response
+    with pytest.raises(
+        AgentRepositoryError,
+        match="Tool DoesNotExist could not be loaded: module 'crewai_tools' has no attribute 'DoesNotExist'",
+    ):
+        Agent(from_repository="test_agent")
+
+
+@patch("crewai.cli.plus_api.PlusAPI.get_agent")
+def test_agent_from_repository_agent_not_found(mock_get_agent, mock_get_auth_token):
+    mock_get_response = MagicMock()
+    mock_get_response.status_code = 404
+    mock_get_response.text = "Agent not found"
+    mock_get_agent.return_value = mock_get_response
+    with pytest.raises(
+        AgentRepositoryError,
+        match="Agent NOT_FOUND could not be loaded: Agent not found",
+    ):
+        Agent(from_repository="NOT_FOUND")

tests/cassettes/test_agent_human_input.yaml

@@ -0,0 +1,520 @@
+interactions:
+- request:
+    body: !!binary |
+      CqcXCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkS/hYKEgoQY3Jld2FpLnRl
+      bGVtZXRyeRJ5ChBuJJtOdNaB05mOW/p3915eEgj2tkAd3rZcASoQVG9vbCBVc2FnZSBFcnJvcjAB
+      OYa7/URvKBUYQUpcFEVvKBUYShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuODYuMEoPCgNsbG0SCAoG
+      Z3B0LTRvegIYAYUBAAEAABLJBwoQifhX01E5i+5laGdALAlZBBIIBuGM1aN+OPgqDENyZXcgQ3Jl
+      YXRlZDABORVGruBvKBUYQaipwOBvKBUYShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuODYuMEoaCg5w
+      eXRob25fdmVyc2lvbhIICgYzLjEyLjdKLgoIY3Jld19rZXkSIgogN2U2NjA4OTg5ODU5YTY3ZWVj
+      ODhlZWY3ZmNlODUyMjVKMQoHY3Jld19pZBImCiRiOThiNWEwMC01YTI1LTQxMDctYjQwNS1hYmYz
+      MjBhOGYzYThKHAoMY3Jld19wcm9jZXNzEgwKCnNlcXVlbnRpYWxKEQoLY3Jld19tZW1vcnkSAhAA
+      ShoKFGNyZXdfbnVtYmVyX29mX3Rhc2tzEgIYAUobChVjcmV3X251bWJlcl9vZl9hZ2VudHMSAhgB
+      SuQCCgtjcmV3X2FnZW50cxLUAgrRAlt7ImtleSI6ICIyMmFjZDYxMWU0NGVmNWZhYzA1YjUzM2Q3
+      NWU4ODkzYiIsICJpZCI6ICJkNWIyMzM1YS0yMmIyLTQyZWEtYmYwNS03OTc3NmU3MmYzOTIiLCAi
+      cm9sZSI6ICJEYXRhIFNjaWVudGlzdCIsICJ2ZXJib3NlPyI6IGZhbHNlLCAibWF4X2l0ZXIiOiAy
+      MCwgIm1heF9ycG0iOiBudWxsLCAiZnVuY3Rpb25fY2FsbGluZ19sbG0iOiAiIiwgImxsbSI6ICJn
+      cHQtNG8tbWluaSIsICJkZWxlZ2F0aW9uX2VuYWJsZWQ/IjogZmFsc2UsICJhbGxvd19jb2RlX2V4
+      ZWN1dGlvbj8iOiBmYWxzZSwgIm1heF9yZXRyeV9saW1pdCI6IDIsICJ0b29sc19uYW1lcyI6IFsi
+      Z2V0IGdyZWV0aW5ncyJdfV1KkgIKCmNyZXdfdGFza3MSgwIKgAJbeyJrZXkiOiAiYTI3N2IzNGIy
+      YzE0NmYwYzU2YzVlMTM1NmU4ZjhhNTciLCAiaWQiOiAiMjJiZWMyMzEtY2QyMS00YzU4LTgyN2Ut
+      MDU4MWE4ZjBjMTExIiwgImFzeW5jX2V4ZWN1dGlvbj8iOiBmYWxzZSwgImh1bWFuX2lucHV0PyI6
+      IGZhbHNlLCAiYWdlbnRfcm9sZSI6ICJEYXRhIFNjaWVudGlzdCIsICJhZ2VudF9rZXkiOiAiMjJh
+      Y2Q2MTFlNDRlZjVmYWMwNWI1MzNkNzVlODg5M2IiLCAidG9vbHNfbmFtZXMiOiBbImdldCBncmVl
+      dGluZ3MiXX1degIYAYUBAAEAABKOAgoQ5WYoxRtTyPjge4BduhL0rRIIv2U6rvWALfwqDFRhc2sg
+      Q3JlYXRlZDABOX068uBvKBUYQZkv8+BvKBUYSi4KCGNyZXdfa2V5EiIKIDdlNjYwODk4OTg1OWE2
+      N2VlYzg4ZWVmN2ZjZTg1MjI1SjEKB2NyZXdfaWQSJgokYjk4YjVhMDAtNWEyNS00MTA3LWI0MDUt
+      YWJmMzIwYThmM2E4Si4KCHRhc2tfa2V5EiIKIGEyNzdiMzRiMmMxNDZmMGM1NmM1ZTEzNTZlOGY4
+      YTU3SjEKB3Rhc2tfaWQSJgokMjJiZWMyMzEtY2QyMS00YzU4LTgyN2UtMDU4MWE4ZjBjMTExegIY
+      AYUBAAEAABKQAQoQXyeDtJDFnyp2Fjk9YEGTpxIIaNE7gbhPNYcqClRvb2wgVXNhZ2UwATkaXTvj
+      bygVGEGvx0rjbygVGEoaCg5jcmV3YWlfdmVyc2lvbhIICgYwLjg2LjBKHAoJdG9vbF9uYW1lEg8K
+      DUdldCBHcmVldGluZ3NKDgoIYXR0ZW1wdHMSAhgBegIYAYUBAAEAABLVBwoQMWfznt0qwauEzl7T
+      UOQxRBII9q+pUS5EdLAqDENyZXcgQ3JlYXRlZDABORONPORvKBUYQSAoS+RvKBUYShoKDmNyZXdh
+      aV92ZXJzaW9uEggKBjAuODYuMEoaCg5weXRob25fdmVyc2lvbhIICgYzLjEyLjdKLgoIY3Jld19r
+      ZXkSIgogYzMwNzYwMDkzMjY3NjE0NDRkNTdjNzFkMWRhM2YyN2NKMQoHY3Jld19pZBImCiQ3OTQw
+      MTkyNS1iOGU5LTQ3MDgtODUzMC00NDhhZmEzYmY4YjBKHAoMY3Jld19wcm9jZXNzEgwKCnNlcXVl
+      bnRpYWxKEQoLY3Jld19tZW1vcnkSAhAAShoKFGNyZXdfbnVtYmVyX29mX3Rhc2tzEgIYAUobChVj
+      cmV3X251bWJlcl9vZl9hZ2VudHMSAhgBSuoCCgtjcmV3X2FnZW50cxLaAgrXAlt7ImtleSI6ICI5
+      OGYzYjFkNDdjZTk2OWNmMDU3NzI3Yjc4NDE0MjVjZCIsICJpZCI6ICI5OTJkZjYyZi1kY2FiLTQy
+      OTUtOTIwNi05MDBkNDExNGIxZTkiLCAicm9sZSI6ICJGcmllbmRseSBOZWlnaGJvciIsICJ2ZXJi
+      b3NlPyI6IGZhbHNlLCAibWF4X2l0ZXIiOiAyMCwgIm1heF9ycG0iOiBudWxsLCAiZnVuY3Rpb25f
+      Y2FsbGluZ19sbG0iOiAiIiwgImxsbSI6ICJncHQtNG8tbWluaSIsICJkZWxlZ2F0aW9uX2VuYWJs
+      ZWQ/IjogZmFsc2UsICJhbGxvd19jb2RlX2V4ZWN1dGlvbj8iOiBmYWxzZSwgIm1heF9yZXRyeV9s
+      aW1pdCI6IDIsICJ0b29sc19uYW1lcyI6IFsiZGVjaWRlIGdyZWV0aW5ncyJdfV1KmAIKCmNyZXdf
+      dGFza3MSiQIKhgJbeyJrZXkiOiAiODBkN2JjZDQ5MDk5MjkwMDgzODMyZjBlOTgzMzgwZGYiLCAi
+      aWQiOiAiMmZmNjE5N2UtYmEyNy00YjczLWI0YTctNGZhMDQ4ZTYyYjQ3IiwgImFzeW5jX2V4ZWN1
+      dGlvbj8iOiBmYWxzZSwgImh1bWFuX2lucHV0PyI6IGZhbHNlLCAiYWdlbnRfcm9sZSI6ICJGcmll
+      bmRseSBOZWlnaGJvciIsICJhZ2VudF9rZXkiOiAiOThmM2IxZDQ3Y2U5NjljZjA1NzcyN2I3ODQx
+      NDI1Y2QiLCAidG9vbHNfbmFtZXMiOiBbImRlY2lkZSBncmVldGluZ3MiXX1degIYAYUBAAEAABKO
+      AgoQnjTp5boK7/+DQxztYIpqihIIgGnMUkBtzHEqDFRhc2sgQ3JlYXRlZDABOcpYcuRvKBUYQalE
+      c+RvKBUYSi4KCGNyZXdfa2V5EiIKIGMzMDc2MDA5MzI2NzYxNDQ0ZDU3YzcxZDFkYTNmMjdjSjEK
+      B2NyZXdfaWQSJgokNzk0MDE5MjUtYjhlOS00NzA4LTg1MzAtNDQ4YWZhM2JmOGIwSi4KCHRhc2tf
+      a2V5EiIKIDgwZDdiY2Q0OTA5OTI5MDA4MzgzMmYwZTk4MzM4MGRmSjEKB3Rhc2tfaWQSJgokMmZm
+      NjE5N2UtYmEyNy00YjczLWI0YTctNGZhMDQ4ZTYyYjQ3egIYAYUBAAEAABKTAQoQ26H9pLUgswDN
+      p9XhJwwL6BIIx3bw7mAvPYwqClRvb2wgVXNhZ2UwATmy7NPlbygVGEEvb+HlbygVGEoaCg5jcmV3
+      YWlfdmVyc2lvbhIICgYwLjg2LjBKHwoJdG9vbF9uYW1lEhIKEERlY2lkZSBHcmVldGluZ3NKDgoI
+      YXR0ZW1wdHMSAhgBegIYAYUBAAEAAA==
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '2986'
+      Content-Type:
+      - application/x-protobuf
+      User-Agent:
+      - OTel-OTLP-Exporter-Python/1.27.0
+    method: POST
+    uri: https://telemetry.crewai.com:4319/v1/traces
+  response:
+    body:
+      string: "\n\0"
+    headers:
+      Content-Length:
+      - '2'
+      Content-Type:
+      - application/x-protobuf
+      Date:
+      - Fri, 27 Dec 2024 22:14:53 GMT
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are test role. test backstory\nYour
+      personal goal is: test goal\nTo give my best complete final answer to the task
+      use the exact following format:\n\nThought: I now can give a great answer\nFinal
+      Answer: Your final answer must be the great and the most complete as possible,
+      it must be outcome described.\n\nI MUST use these formats, my job depends on
+      it!"}, {"role": "user", "content": "\nCurrent Task: Say the word: Hi\n\nThis
+      is the expect criteria for your final answer: The word: Hi\nyou MUST return
+      the actual complete content as the final answer, not a summary.\n\nBegin! This
+      is VERY important to you, use the tools available and give your best Final Answer,
+      your job depends on it!\n\nThought:"}], "model": "gpt-4o-mini", "stop": ["\nObservation:"],
+      "stream": false}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '824'
+      content-type:
+      - application/json
+      cookie:
+      - _cfuvid=ePJSDFdHag2D8lj21_ijAMWjoA6xfnPNxN4uekvC728-1727226247743-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.52.1
+      x-stainless-arch:
+      - x64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - Linux
+      x-stainless-package-version:
+      - 1.52.1
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-AjCtZLLrWi8ZASpP9bz6HaCV7xBIn\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1735337693,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"I now can give a great answer  \\nFinal
+      Answer: Hi\",\n        \"refusal\": null\n      },\n      \"logprobs\": null,\n
+      \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      158,\n    \"completion_tokens\": 12,\n    \"total_tokens\": 170,\n    \"prompt_tokens_details\":
+      {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+      {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"system_fingerprint\":
+      \"fp_0aa8d3e20b\"\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8f8caa83deca756b-SEA
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Fri, 27 Dec 2024 22:14:53 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=wJkq_yLkzE3OdxE0aMJz.G0kce969.9JxRmZ0ratl4c-1735337693-1.0.1.1-OKpUoRrSPFGvWv5Hp5ET1PNZ7iZNHPKEAuakpcQUxxPSeisUIIR3qIOZ31MGmYugqB5.wkvidgbxOAagqJvmnw;
+        path=/; expires=Fri, 27-Dec-24 22:44:53 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=A_ASCLNAVfQoyucWOAIhecWtEpNotYoZr0bAFihgNxs-1735337693273-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '404'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '30000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-requests:
+      - '29999'
+      x-ratelimit-remaining-tokens:
+      - '149999816'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_6ac84634bff9193743c4b0911c09b4a6
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "system", "content": "Determine if the following
+      feedback indicates that the user is satisfied or if further changes are needed.
+      Respond with ''True'' if further changes are needed, or ''False'' if the user
+      is satisfied. **Important** Do not include any additional commentary outside
+      of your ''True'' or ''False'' response.\n\nFeedback: \"Don''t say hi, say Hello
+      instead!\""}], "model": "gpt-4o-mini", "stop": ["\nObservation:"], "stream":
+      false}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '461'
+      content-type:
+      - application/json
+      cookie:
+      - _cfuvid=A_ASCLNAVfQoyucWOAIhecWtEpNotYoZr0bAFihgNxs-1735337693273-0.0.1.1-604800000;
+        __cf_bm=wJkq_yLkzE3OdxE0aMJz.G0kce969.9JxRmZ0ratl4c-1735337693-1.0.1.1-OKpUoRrSPFGvWv5Hp5ET1PNZ7iZNHPKEAuakpcQUxxPSeisUIIR3qIOZ31MGmYugqB5.wkvidgbxOAagqJvmnw
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.52.1
+      x-stainless-arch:
+      - x64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - Linux
+      x-stainless-package-version:
+      - 1.52.1
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-AjCtZNlWdrrPZhq0MJDqd16sMuQEJ\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1735337693,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"True\",\n        \"refusal\": null\n
+      \     },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n
+      \ ],\n  \"usage\": {\n    \"prompt_tokens\": 78,\n    \"completion_tokens\":
+      1,\n    \"total_tokens\": 79,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+      0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n
+      \     \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"system_fingerprint\":
+      \"fp_0aa8d3e20b\"\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8f8caa87094f756b-SEA
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Fri, 27 Dec 2024 22:14:53 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '156'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '30000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-requests:
+      - '29999'
+      x-ratelimit-remaining-tokens:
+      - '149999898'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_ec74bef2a9ef7b2144c03fd7f7bbeab0
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are test role. test backstory\nYour
+      personal goal is: test goal\nTo give my best complete final answer to the task
+      use the exact following format:\n\nThought: I now can give a great answer\nFinal
+      Answer: Your final answer must be the great and the most complete as possible,
+      it must be outcome described.\n\nI MUST use these formats, my job depends on
+      it!"}, {"role": "user", "content": "\nCurrent Task: Say the word: Hi\n\nThis
+      is the expect criteria for your final answer: The word: Hi\nyou MUST return
+      the actual complete content as the final answer, not a summary.\n\nBegin! This
+      is VERY important to you, use the tools available and give your best Final Answer,
+      your job depends on it!\n\nThought:"}, {"role": "assistant", "content": "I now
+      can give a great answer  \nFinal Answer: Hi"}, {"role": "user", "content": "Feedback:
+      Don''t say hi, say Hello instead!"}], "model": "gpt-4o-mini", "stop": ["\nObservation:"],
+      "stream": false}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '986'
+      content-type:
+      - application/json
+      cookie:
+      - _cfuvid=A_ASCLNAVfQoyucWOAIhecWtEpNotYoZr0bAFihgNxs-1735337693273-0.0.1.1-604800000;
+        __cf_bm=wJkq_yLkzE3OdxE0aMJz.G0kce969.9JxRmZ0ratl4c-1735337693-1.0.1.1-OKpUoRrSPFGvWv5Hp5ET1PNZ7iZNHPKEAuakpcQUxxPSeisUIIR3qIOZ31MGmYugqB5.wkvidgbxOAagqJvmnw
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.52.1
+      x-stainless-arch:
+      - x64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - Linux
+      x-stainless-package-version:
+      - 1.52.1
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-AjCtZGv4f3h7GDdhyOy9G0sB1lRgC\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1735337693,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Thought: I understand the feedback and
+      will adjust my response accordingly.  \\nFinal Answer: Hello\",\n        \"refusal\":
+      null\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n
+      \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 188,\n    \"completion_tokens\":
+      18,\n    \"total_tokens\": 206,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+      0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n
+      \     \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"system_fingerprint\":
+      \"fp_0aa8d3e20b\"\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8f8caa88cac4756b-SEA
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Fri, 27 Dec 2024 22:14:54 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '358'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '30000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-requests:
+      - '29999'
+      x-ratelimit-remaining-tokens:
+      - '149999793'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_ae1ab6b206d28ded6fee3c83ed0c2ab7
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "system", "content": "Determine if the following
+      feedback indicates that the user is satisfied or if further changes are needed.
+      Respond with ''True'' if further changes are needed, or ''False'' if the user
+      is satisfied. **Important** Do not include any additional commentary outside
+      of your ''True'' or ''False'' response.\n\nFeedback: \"looks good\""}], "model":
+      "gpt-4o-mini", "stop": ["\nObservation:"], "stream": false}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '439'
+      content-type:
+      - application/json
+      cookie:
+      - _cfuvid=A_ASCLNAVfQoyucWOAIhecWtEpNotYoZr0bAFihgNxs-1735337693273-0.0.1.1-604800000;
+        __cf_bm=wJkq_yLkzE3OdxE0aMJz.G0kce969.9JxRmZ0ratl4c-1735337693-1.0.1.1-OKpUoRrSPFGvWv5Hp5ET1PNZ7iZNHPKEAuakpcQUxxPSeisUIIR3qIOZ31MGmYugqB5.wkvidgbxOAagqJvmnw
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.52.1
+      x-stainless-arch:
+      - x64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - Linux
+      x-stainless-package-version:
+      - 1.52.1
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-AjCtaiHL4TY8Dssk0j2miqmjrzquy\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1735337694,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"False\",\n        \"refusal\": null\n
+      \     },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n
+      \ ],\n  \"usage\": {\n    \"prompt_tokens\": 73,\n    \"completion_tokens\":
+      1,\n    \"total_tokens\": 74,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+      0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n
+      \     \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"system_fingerprint\":
+      \"fp_0aa8d3e20b\"\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8f8caa8bdd26756b-SEA
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Fri, 27 Dec 2024 22:14:54 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '184'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '30000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-requests:
+      - '29999'
+      x-ratelimit-remaining-tokens:
+      - '149999902'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_652891f79c1104a7a8436275d78a69f1
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1

tests/cli/create_test.py

@@ -0,0 +1,40 @@
+from unittest import mock
+
+import pytest
+from click.testing import CliRunner
+
+from crewai.cli.cli import create
+
+
+@pytest.fixture
+def runner():
+    return CliRunner()
+
+
+class TestCreateCommand:
+    @mock.patch("crewai.cli.cli.create_crew")
+    def test_create_crew_with_ssl_verify_default(self, mock_create_crew, runner):
+        """Test that create crew command passes skip_ssl_verify=False by default."""
+        result = runner.invoke(create, ["crew", "test_crew"])
+
+        assert result.exit_code == 0
+        mock_create_crew.assert_called_once()
+        assert mock_create_crew.call_args[1]["skip_ssl_verify"] is False
+
+    @mock.patch("crewai.cli.cli.create_crew")
+    def test_create_crew_with_skip_ssl_verify(self, mock_create_crew, runner):
+        """Test that create crew command passes skip_ssl_verify=True when flag is used."""
+        result = runner.invoke(create, ["crew", "test_crew", "--skip_ssl_verify"])
+
+        assert result.exit_code == 0
+        mock_create_crew.assert_called_once()
+        assert mock_create_crew.call_args[1]["skip_ssl_verify"] is True
+
+    @mock.patch("crewai.cli.cli.create_flow")
+    def test_create_flow_ignores_skip_ssl_verify(self, mock_create_flow, runner):
+        """Test that create flow command ignores the skip_ssl_verify flag."""
+        result = runner.invoke(create, ["flow", "test_flow", "--skip_ssl_verify"])
+
+        assert result.exit_code == 0
+        mock_create_flow.assert_called_once()
+        assert mock_create_flow.call_args == mock.call("test_flow")

tests/cli/provider_test.py

@@ -0,0 +1,147 @@
+import tempfile
+from pathlib import Path
+from unittest import mock
+
+import pytest
+import requests
+from requests.exceptions import RequestException, SSLError, Timeout
+
+from crewai.cli.provider import (
+    fetch_provider_data,
+    get_provider_data,
+    load_provider_data,
+    read_cache_file,
+)
+
+
+@pytest.fixture
+def mock_response():
+    """Mock a successful response from requests.get."""
+    mock_resp = mock.Mock()
+    mock_resp.headers = {"content-length": "100"}
+    mock_resp.iter_content.return_value = [b'{"model1": {"litellm_provider": "openai"}}']
+    return mock_resp
+
+
+@pytest.fixture
+def mock_cache_file():
+    """Create a temporary file to use as a cache file."""
+    with tempfile.NamedTemporaryFile() as tmp:
+        yield Path(tmp.name)
+
+
+class TestProviderFunctions:
+    @mock.patch("crewai.cli.provider.requests.get")
+    def test_fetch_provider_data_with_ssl_verify(self, mock_get, mock_response, mock_cache_file):
+        """Test that fetch_provider_data calls requests.get with verify=True by default."""
+        mock_get.return_value = mock_response
+
+        fetch_provider_data(mock_cache_file)
+
+        mock_get.assert_called_once()
+        assert mock_get.call_args[1]["verify"] is True
+
+    @mock.patch("crewai.cli.provider.requests.get")
+    def test_fetch_provider_data_without_ssl_verify(self, mock_get, mock_response, mock_cache_file):
+        """Test that fetch_provider_data calls requests.get with verify=False when skip_ssl_verify=True."""
+        mock_get.return_value = mock_response
+
+        fetch_provider_data(mock_cache_file, skip_ssl_verify=True)
+
+        mock_get.assert_called_once()
+        assert mock_get.call_args[1]["verify"] is False
+
+    @mock.patch("crewai.cli.provider.requests.get")
+    def test_fetch_provider_data_handles_request_exception(self, mock_get, mock_cache_file):
+        """Test that fetch_provider_data handles RequestException properly."""
+        mock_get.side_effect = RequestException("Test error")
+
+        result = fetch_provider_data(mock_cache_file)
+
+        assert result is None
+        mock_get.assert_called_once()
+
+    @mock.patch("crewai.cli.provider.requests.get")
+    def test_fetch_provider_data_handles_timeout(self, mock_get, mock_cache_file):
+        """Test that fetch_provider_data handles Timeout exception properly."""
+        mock_get.side_effect = Timeout("Connection timed out")
+
+        result = fetch_provider_data(mock_cache_file)
+
+        assert result is None
+        mock_get.assert_called_once()
+
+    @mock.patch("crewai.cli.provider.requests.get")
+    def test_fetch_provider_data_handles_ssl_error(self, mock_get, mock_cache_file):
+        """Test that fetch_provider_data handles SSLError exception properly."""
+        mock_get.side_effect = SSLError("SSL Certificate verification failed")
+
+        result = fetch_provider_data(mock_cache_file)
+
+        assert result is None
+        mock_get.assert_called_once()
+
+    @mock.patch("crewai.cli.provider.requests.get")
+    def test_fetch_provider_data_handles_json_decode_error(
+        self, mock_get, mock_response, mock_cache_file
+    ):
+        """Test that fetch_provider_data handles JSONDecodeError properly."""
+        mock_get.return_value = mock_response
+        mock_response.iter_content.return_value = [b"invalid json"]
+
+        result = fetch_provider_data(mock_cache_file)
+
+        assert result is None
+        mock_get.assert_called_once()
+
+    @mock.patch("builtins.open", new_callable=mock.mock_open, read_data="invalid json")
+    def test_read_cache_file_handles_json_decode_error(self, mock_file, mock_cache_file):
+        """Test that read_cache_file handles JSONDecodeError properly."""
+        with mock.patch.object(Path, "exists", return_value=True):
+            result = read_cache_file(mock_cache_file)
+
+        assert result is None
+        mock_file.assert_called_once_with(mock_cache_file, "r")
+
+    @mock.patch("builtins.open")
+    def test_read_cache_file_handles_os_error(self, mock_file, mock_cache_file):
+        """Test that read_cache_file handles OSError properly."""
+        mock_file.side_effect = OSError("File I/O error")
+        with mock.patch.object(Path, "exists", return_value=True):
+            result = read_cache_file(mock_cache_file)
+
+        assert result is None
+        mock_file.assert_called_once_with(mock_cache_file, "r")
+
+    @mock.patch("builtins.open", new_callable=mock.mock_open, read_data='{"key": [1, 2, 3]}')
+    def test_read_cache_file_handles_invalid_format(self, mock_file, mock_cache_file):
+        """Test that read_cache_file handles invalid data format properly."""
+        with mock.patch.object(Path, "exists", return_value=True):
+            with mock.patch("json.load", return_value=["not", "a", "dict"]):
+                result = read_cache_file(mock_cache_file)
+
+        assert result is None
+        mock_file.assert_called_once_with(mock_cache_file, "r")
+
+    @mock.patch("crewai.cli.provider.fetch_provider_data")
+    @mock.patch("crewai.cli.provider.read_cache_file")
+    def test_load_provider_data_with_ssl_verify(
+        self, mock_read_cache, mock_fetch, mock_cache_file
+    ):
+        """Test that load_provider_data passes skip_ssl_verify to fetch_provider_data."""
+        mock_read_cache.return_value = None
+        mock_fetch.return_value = {"model1": {"litellm_provider": "openai"}}
+
+        load_provider_data(mock_cache_file, 3600, skip_ssl_verify=True)
+
+        mock_fetch.assert_called_once_with(mock_cache_file, True)
+
+    @mock.patch("crewai.cli.provider.load_provider_data")
+    def test_get_provider_data_with_ssl_verify(self, mock_load, tmp_path):
+        """Test that get_provider_data passes skip_ssl_verify to load_provider_data."""
+        mock_load.return_value = {"model1": {"litellm_provider": "openai"}}
+
+        get_provider_data(skip_ssl_verify=True)
+
+        mock_load.assert_called_once()
+        assert mock_load.call_args[0][2] is True  # skip_ssl_verify parameter