Azure Container Apps dynamic sessions Code runtime Tool
Guide for using the Azure Container Apps dynamic sessions based code Interpreter tool with PraisonAI agents.
Overview
The Azure Container Apps dynamic sessions based code Interpreter tool is a tool that allows you to execute and run development environments using the AI Agents.
The user sends code to run; the agent executes it in an Azure dynamic session and returns the output.
pip install langchain-azure-dynamic-sessions langchain-openai langchainhub langchain langchain-communityfrom praisonaiagents import Agent, AgentTeam
import getpass
from langchain_azure_dynamic_sessions import SessionsPythonREPLTool
POOL_MANAGEMENT_ENDPOINT = getpass.getpass()
coder_agent = Agent(instructions="""word = "strawberry"
count = word.count("r")
print(f"There are {count}'R's in the word 'Strawberry'")""", tools=[SessionsPythonREPLTool])
agents = AgentTeam(agents=[coder_agent])
agents.start()Getting Started
- Simple Usage
- Install dependencies (see Overview above)
- Set required API keys in your environment
- Run the agent example in Overview
- With Configuration
Use the same tool with an agent — see the Overview example, or pass env vars from the sections above.
How It Works
Best Practices
Keep sessions short-lived
Azure Container Apps dynamic sessions are ephemeral — treat each run as stateless and pass all inputs explicitly.
Validate untrusted code
Only run code the agent generated from trusted instructions. Sandbox limits protect the host, not your data.
Handle timeouts
Long-running code can hit the session timeout. Wrap execution in error handling so the agent recovers gracefully.