microsoft/semantic-kernel · error · AgentInvokeException

Exception occurred while fetching token.

Error message

Exception occurred while fetching token.

What it means

A catch-all AgentInvokeException wrapping any unexpected Exception during the token-fetch flow (both branches). It logs the original via logger.exception and re-raises with 'from ex' to preserve the chain. This handles non-HTTP failures like connection errors, timeouts, JSON decode errors, or DNS failures that escape the status checks.

Source

Thrown at python/samples/demos/copilot_studio_agent/src/direct_line_agent.py:81

                            logger.error("Token generation response missing token: %s", data)
                            raise AgentInvokeException("No token received from token generation.")
                    else:
                        logger.error("Token generation endpoint error status: %s", resp.status)
                        raise AgentInvokeException("Failed to generate token using bot_secret.")
            else:
                async with self.session.get(self.token_endpoint) as resp:
                    if resp.status == 200:
                        data = await resp.json()
                        self.directline_token = data.get("token")
                        if not self.directline_token:
                            logger.error("Token endpoint returned no token: %s", data)
                            raise AgentInvokeException("No token received.")
                    else:
                        logger.error("Token endpoint error status: %s", resp.status)
                        raise AgentInvokeException("Failed to fetch token from token endpoint.")
        except Exception as ex:
            logger.exception("Exception fetching token: %s", ex)
            raise AgentInvokeException("Exception occurred while fetching token.") from ex

    @trace_agent_get_response
    @override
    async def get_response(
        self,
        history: ChatHistory,
        arguments: dict[str, Any] | None = None,
        **kwargs: Any,
    ) -> ChatMessageContent:
        """
        Get a response from the DirectLine Bot.
        """
        responses = []
        async for response in self.invoke(history, arguments, **kwargs):
            responses.append(response)

        if not responses:
            raise AgentInvokeException("No response from DirectLine Bot.")

View on GitHub (pinned to c028a0c7dc)

Solutions

1. Read the chained exception (the `from ex` original) — it carries the real cause (timeout, connection reset, etc.).
2. Fix the underlying network/connectivity issue; verify DNS and TLS to the endpoint.
3. Add a timeout to the session/requests to fail fast and distinguish timeouts from other errors.

Example fix

// before
except Exception as ex:
    logger.exception("Exception fetching token: %s", ex)
    raise AgentInvokeException("Exception occurred while fetching token.") from ex

// after  # surface the specific cause for diagnosis
except (aiohttp.ClientError, asyncio.TimeoutError) as ex:
    logger.exception("Network error fetching token: %s", ex)
    raise AgentInvokeException(f"Network error fetching token: {ex}") from ex

try:
    await fetch_token()
except AgentInvokeException as e:
    logger.exception("Token fetch failed: %s", e.__cause__)
    raise

When it happens

Trigger: Any exception other than the handled status/missing-token cases: aiohttp ClientError, asyncio.TimeoutError, JSONDecodeError on a non-JSON 200 body, DNS resolution failure, etc.

Common situations: Network unreachable; proxy/firewall blocking the endpoint; response wasn't valid JSON; SSL certificate problem; the aiohttp session was closed.

Related errors

• No token received from token generation.
• Failed to generate token using bot_secret.
• No token received.
• Failed to fetch token from token endpoint.
• Failed to start conversation.

AI-assisted analysis of microsoft/semantic-kernel@c028a0c7dc (2026-08-13). Data as JSON: /api/errors/69c9c9fd5cf3c796. Report an issue: GitHub.