microsoft/autogen · error · ValueError

Deployment name not initialized

Error message

Deployment name not initialized

What it means

AzureAIAgent.deployment_name raises ValueError when _deployment_name is falsy — the model deployment name was not provided at construction (or is empty), so there is nothing to report.

Source

Thrown at python/packages/autogen-ext/src/autogen_ext/agents/azure/_azure_ai_agent.py:389

            raise ValueError("Agent not initialized")
        return self._agent.id

    @property
    def description(self) -> str:
        if not self._description:
            raise ValueError("Description not initialized")
        return self._description

    @property
    def agent_id(self) -> str:
        if not self._agent_id:
            raise ValueError("Agent not initialized")
        return self._agent_id

    @property
    def deployment_name(self) -> str:
        if not self._deployment_name:
            raise ValueError("Deployment name not initialized")
        return self._deployment_name

    @property
    def instructions(self) -> str:
        if not self._instructions:
            raise ValueError("Instructions not initialized")
        return self._instructions

    @property
    def tools(self) -> List[ToolDefinition]:
        """
        Get the list of tools available to the agent.

        Returns:
            List[ToolDefinition]: The list of tool definitions.
        """
        return self._api_tools

View on GitHub (pinned to 027ecf0a37)

Solutions

1. Provide the deployment name at construction (e.g. via the constructor's deployment/model parameter).
2. Validate config before building the agent: fail fast if the deployment setting is missing.
3. Guard the property read with try/except or check the underlying config value instead.

Example fix

# before
agent = AzureAIAgent(client, name="a")
print(agent.deployment_name)  # ValueError
# after
agent = AzureAIAgent(client, name="a", deployment_name="gpt-4o-deploy")
print(agent.deployment_name)

deployment = os.getenv("AZURE_DEPLOYMENT")
if not deployment:
    raise SystemExit("AZURE_DEPLOYMENT is required")
agent = AzureAIAgent(client, name="a", deployment_name=deployment)

try:
    dn = agent.deployment_name
except ValueError:
    dn = os.environ["AZURE_DEPLOYMENT"]

When it happens

Trigger: Constructing AzureAIAgent without a deployment_name / model deployment argument and then reading agent.deployment_name.

Common situations: Configuration built from env vars or config files where the deployment key is missing or misspelled; empty-string defaults from os.getenv("DEPLOYMENT", "").

Related errors

• Description not initialized
• Instructions not initialized
• Unsupported tool string: {tool}
• BING_API_KEY environment variable is not set
• Please set AZURE_OPENAI_API_KEY environment variable.

AI-assisted analysis of microsoft/autogen@027ecf0a37 (2026-08-15). Data as JSON: /api/errors/865e86faede72280. Report an issue: GitHub.