What causes "Timed out waiting for ChatGPT response: + requestId" in musistudio/claude-code-router?

Retry the request — transient backend slowness is the most common cause

musistudio/claude-code-router · error · Error

Timed out waiting for ChatGPT response: + requestId

Error message

Timed out waiting for ChatGPT response:  + requestId

What it means

Polling helper that waits (100ms loop) for a response keyed by requestId to appear in a Map of resolved ChatGPT request replies; it throws when the deadline elapses. It means the upstream ChatGPT-backed request never produced (or never matched) a response within the timeout window.

Source

Thrown at packages/core/src/agents/codex/cli-middleware-runtime.ts:4908

  if (toolUseId) response.toolUseID = toolUseId;
  return { type: "control_response", response: { subtype: "success", request_id: requestId, response } };
}

function claudeControlElicitationResponse(requestId, value) {
  return { type: "control_response", response: { subtype: "success", request_id: requestId, response: value || {} } };
}

async function waitForAppResponse(map, requestId, timeoutMs) {
  const started = Date.now();
  while (Date.now() - started < timeoutMs) {
    if (map.has(requestId)) {
      const value = map.get(requestId);
      map.delete(requestId);
      return value;
    }
    await sleep(100);
  }
  throw new Error("Timed out waiting for ChatGPT response: " + requestId);
}

function permissionResponseAllows(value) {
  if (!value) return false;
  if (value.approved === true || value.allow === true || value.allowed === true || value.decision === "allow") return true;
  if (value.approved === false || value.allow === false || value.allowed === false || value.decision === "deny") return false;
  if (typeof value === "boolean") return value;
  return Boolean(value);
}

function writeResponse(id, result) {
  writeRaw({ id, result });
}

function writeError(id, code, message) {
  writeRaw({ id, error: { code, message } });
}

View on GitHub (pinned to 99f24806c6)

Solutions

Retry the request — transient backend slowness is the most common cause
Increase the response timeout constant if your workload routinely exceeds it
Verify network/proxy connectivity to the ChatGPT backend and that the session is still alive
Log the requestId alongside responses to detect correlation (key mismatch) bugs

Example fix

// before
const value = await waitForChatGptResponse(map, requestId); // throws on timeout

// after
const value = await waitForChatGptResponse(map, requestId)
  .catch(() => retryWithBackoff(() => issueChatGptRequest(params), 3));

Defensive patterns

Strategy: retry

Validate before calling

null

Type guard

null

Try / catch

try { return await waitForChatGptResponse(map, requestId); } catch (e) { if (/Timed out waiting for ChatGPT response/.test(String(e))) { return await withBackoff(() => issueChatGptRequest(params), 3); } throw e; }

Prevention

Retry once on timeout before surfacing the error to users
Raise the timeout for long-generation workloads
Log requestId on both request and response paths to catch correlation bugs

When it happens

Trigger: Awaiting a ChatGPT response whose reply never lands in the map: upstream network stall, requestId mismatch/correlation bug, response arrived after the timeout expired, or the backing session died before responding.

Common situations: Slow ChatGPT backend exceeding the fixed timeout; proxy/firewall dropping long-lived connections; requestId reused or malformed so the response is stored under a different key; Codex session disconnected mid-request.

Understand the failure class

Timeouts: ETIMEDOUT, deadlines, and hung requests — what actually expires when a request times out.

Related errors

AI-assisted analysis of musistudio/claude-code-router@99f24806c6 (2026-08-27). Data as JSON: /api/errors/81a50519ed6418f6. Report an issue: GitHub.