github/copilot-sdk · error · RuntimeError

Copilot request was cancelled by the runtime.

Error message

Copilot request was cancelled by the runtime.

What it means

write_response() refuses to write body data once the runtime has cancelled the Copilot request (the `cancelled` flag was set via the cancellation path). Continuing to write would stream bytes to a request_id the client/runtime has abandoned. The library raises immediately so the handler can stop producing output.

Solutions

1. Check `response.cancelled` before each write (or wrap writes in try/except RuntimeError and break the stream loop).
2. Stop generation as soon as cancellation is observed; do not attempt further writes or end_response().
3. Register a cancellation callback that terminates the upstream model stream so writes never happen post-cancel.

Example fix

// before
for chunk in model_stream:
    await response.write_response(chunk)

// after
for chunk in model_stream:
    if response.cancelled:
        break
    try:
        await response.write_response(chunk)
    except RuntimeError:
        break

if response.cancelled:
    stop_generation()
    return

def is_writable(response) -> bool:
    return not response.cancelled and response.started and not response.finished

try:
    await response.write_response(chunk)
except RuntimeError as e:
    if "cancelled by the runtime" in str(e):
        break  # client/runtime gone; stop streaming
    raise

When it happens

Trigger: The runtime cancelled the request (client disconnect, timeout, explicit cancel) and the handler subsequently calls write_response(); long-running generation continues streaming after a cancel notification arrives.

Common situations: User closes the connection or hits stop mid-generation while a model callback keeps streaming; timeouts in the runtime cancelling the exchange while the handler loop is mid-chunk.

Related errors

• Request cancelled by runtime
• Request cancelled by runtime
• Copilot request was cancelled by the runtime.
• Request cancelled by runtime
• LLM inference request was cancelled by the runtime

AI-assisted analysis of github/copilot-sdk@cd8cf15dc3 (2026-09-09). Data as JSON: /api/errors/323698eeae6d59bb. Report an issue: GitHub.

Appendix: source

Thrown at python/copilot/copilot_request_handler.py:456

        headers: LlmInferenceHeaders | None = None,
    ) -> None:
        if self.started:
            raise RuntimeError("Copilot request response start() called twice.")
        if self.finished:
            raise RuntimeError("Copilot request response already finished.")
        self.started = True
        await self._require_rpc().http_response_start(
            LlmInferenceHTTPResponseStartRequest(
                headers=headers or {},
                request_id=self.request_id,
                status=status,
                status_text=status_text,
            )
        )

    async def write_response(self, data: str | bytes) -> None:
        if self.cancelled:
            raise RuntimeError("Copilot request was cancelled by the runtime.")
        if not self.started:
            raise RuntimeError("Copilot request response write() called before start().")
        if self.finished:
            raise RuntimeError("Copilot request response write() called after end()/error().")
        if isinstance(data, bytes):
            payload = base64.b64encode(data).decode("ascii")
            is_binary = True
        else:
            payload = data
            is_binary = False
        await self._require_rpc().http_response_chunk(
            LlmInferenceHTTPResponseChunkRequest(
                data=payload,
                request_id=self.request_id,
                binary=is_binary or None,
                end=False,
            )
        )

View on GitHub (pinned to cd8cf15dc3)