andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-01-08 15:48:29 +00:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity

support unsafe code execution. add in docker install and running checks. (#1496)

Browse Source 
* support unsafe code execution. add in docker install and running checks.

* Update return type
This commit is contained in:
Brandon Hancock (bhancock_ai)
2024-10-23 11:01:00 -04:00
committed by GitHub
parent 7d68e287cc
commit e1fd83e6a7
2 changed files with 37 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
docs/concepts/agents.mdx
View File

@@ -31,16 +31,17 @@ Think of an agent as a member of a team, with specific skills and a particular j
| **Max RPM** *(optional)* | `max_rpm` | Max RPM is the maximum number of requests per minute the agent can perform to avoid rate limits. It's optional and can be left unspecified, with a default value of `None`. |
| **Max Execution Time** *(optional)* | `max_execution_time` | Max Execution Time is the maximum execution time for an agent to execute a task. It's optional and can be left unspecified, with a default value of `None`, meaning no max execution time. |
| **Verbose** *(optional)* | `verbose` | Setting this to `True` configures the internal logger to provide detailed execution logs, aiding in debugging and monitoring. Default is `False`. |
| **Allow Delegation** *(optional)* | `allow_delegation` | Agents can delegate tasks or questions to one another, ensuring that each task is handled by the most suitable agent. Default is `False`.
| **Allow Delegation** *(optional)* | `allow_delegation` | Agents can delegate tasks or questions to one another, ensuring that each task is handled by the most suitable agent. Default is `False`. |
| **Step Callback** *(optional)* | `step_callback` | A function that is called after each step of the agent. This can be used to log the agent's actions or to perform other operations. It will overwrite the crew `step_callback`. |
| **Cache** *(optional)* | `cache` | Indicates if the agent should use a cache for tool usage. Default is `True`. |
| **System Template** *(optional)* | `system_template` | Specifies the system format for the agent. Default is `None`. |
| **Prompt Template** *(optional)* | `prompt_template` | Specifies the prompt format for the agent. Default is `None`. |
| **Response Template** *(optional)* | `response_template` | Specifies the response format for the agent. Default is `None`. |
| **Allow Code Execution** *(optional)* | `allow_code_execution` | Enable code execution for the agent. Default is `False`. |
| **Max Retry Limit** *(optional)* | `max_retry_limit` | Maximum number of retries for an agent to execute a task when an error occurs. Default is `2`.
| **Max Retry Limit** *(optional)* | `max_retry_limit` | Maximum number of retries for an agent to execute a task when an error occurs. Default is `2`. |
| **Use System Prompt** *(optional)* | `use_system_prompt` | Adds the ability to not use system prompt (to support o1 models). Default is `True`. |
| **Respect Context Window** *(optional)* | `respect_context_window` | Summary strategy to avoid overflowing the context window. Default is `True`. |
| **Code Execution Mode** *(optional)* | `code_execution_mode` | Determines the mode for code execution: 'safe' (using Docker) or 'unsafe' (direct execution on the host machine). Default is `safe`. |
## Creating an agent
@@ -83,6 +84,7 @@ agent = Agent(
max_retry_limit=2, # Optional
use_system_prompt=True, # Optional
respect_context_window=True, # Optional
code_execution_mode='safe', # Optional, defaults to 'safe'
)
```
@@ -156,4 +158,4 @@ crew = my_crew.kickoff(inputs={"input": "Mark Twain"})
## Conclusion
Agents are the building blocks of the CrewAI framework. By understanding how to define and interact with agents,
you can create sophisticated AI systems that leverage the power of collaborative intelligence.
you can create sophisticated AI systems that leverage the power of collaborative intelligence. The `code_execution_mode` attribute provides flexibility in how agents execute code, allowing for both secure and direct execution options.

34
src/crewai/agent.py
View File

@@ -1,6 +1,8 @@
import os
import shutil
import subprocess
from inspect import signature
from typing import Any, List, Optional, Union
from typing import Any, List, Literal, Optional, Union
from pydantic import Field, InstanceOf, PrivateAttr, model_validator
@@ -112,6 +114,10 @@ class Agent(BaseAgent):
default=2,
description="Maximum number of retries for an agent to execute a task when an error occurs.",
)
code_execution_mode: Literal["safe", "unsafe"] = Field(
default="safe",
description="Mode for code execution: 'safe' (using Docker) or 'unsafe' (direct execution).",
)
@model_validator(mode="after")
def post_init_setup(self):
@@ -173,6 +179,9 @@ class Agent(BaseAgent):
if not self.agent_executor:
self._setup_agent_executor()
if self.allow_code_execution:
self._validate_docker_installation()
return self
def _setup_agent_executor(self):
@@ -308,7 +317,9 @@ class Agent(BaseAgent):
try:
from crewai_tools import CodeInterpreterTool
return [CodeInterpreterTool()]
# Set the unsafe_mode based on the code_execution_mode attribute
unsafe_mode = self.code_execution_mode == "unsafe"
return [CodeInterpreterTool(unsafe_mode=unsafe_mode)]
except ModuleNotFoundError:
self._logger.log(
"info", "Coding tools not available. Install crewai_tools. "
@@ -408,6 +419,25 @@ class Agent(BaseAgent):
return "\n".join(tool_strings)
def _validate_docker_installation(self) -> None:
"""Check if Docker is installed and running."""
if not shutil.which("docker"):
raise RuntimeError(
f"Docker is not installed. Please install Docker to use code execution with agent: {self.role}"
)
try:
subprocess.run(
["docker", "info"],
check=True,
stdout=subprocess.PIPE,
stderr=subprocess.PIPE,
)
except subprocess.CalledProcessError:
raise RuntimeError(
f"Docker is not running. Please start Docker to use code execution with agent: {self.role}"
)
@staticmethod
def __tools_names(tools) -> str:
return ", ".join([t.name for t in tools])