crewAIInc/crewAI · error · RuntimeError

Brave Search API request timed out after {self._timeout}s: {

Error message

Brave Search API request timed out after {self._timeout}s: {exc}

What it means

Raised when requests.get() to Brave's endpoint raises requests.Timeout: the server did not respond within the tool's configured timeout (constructor arg, default 30s, stored as self._timeout). The wrapper includes both the configured seconds and the underlying exception. Like connection errors, timeouts are not retried internally.

Source

Thrown at lib/crewai-tools/src/crewai_tools/tools/brave_search_tool/base.py:201

        last_resp: requests.Response | None = None

        # Retry the request up to _max_retries times
        for attempt in range(_max_retries):
            self._rate_limit()

            try:
                resp = requests.get(
                    self.search_url,
                    headers=self._headers,
                    params=params,
                    timeout=self._timeout,
                )
            except requests.ConnectionError as exc:
                raise RuntimeError(
                    f"Brave Search API connection failed: {exc}"
                ) from exc
            except requests.Timeout as exc:
                raise RuntimeError(
                    f"Brave Search API request timed out after {self._timeout}s: {exc}"
                ) from exc

            logger.debug(
                "Brave Search API request: %s %s -> %d",
                "GET",
                resp.url,
                resp.status_code,
            )

            # Response was OK, return the JSON body
            if resp.ok:
                try:
                    result: dict[str, Any] = resp.json()
                    return result
                except ValueError as exc:
                    raise RuntimeError(
                        f"Brave Search API returned invalid JSON (HTTP {resp.status_code}): {exc}"

View on GitHub (pinned to 754d7323be)

Solutions

Increase the timeout at construction: BraveSearchTool(api_key=..., timeout=60).
Reduce response size (fewer results per query) to cut server time.
Wrap calls in your own retry with backoff — the tool does not retry timeouts.
If timeouts are sudden and global, check the Brave API status page.

Example fix

# before
tool = BraveSearchTool(api_key=key, timeout=5)

# after
tool = BraveSearchTool(api_key=key, timeout=60)

Defensive patterns

Strategy: retry

Try / catch

except RuntimeError as e:
    if "timed out" in str(e):
        result = tool._run(query)  # one retry; then raise so caller can back off or degrade
    else:
        raise

Prevention

Set timeout proportional to expected latency and result size (default 30s is fine for most; raise on slow links).
Request fewer results per query to keep server-side latency low.
Distinguish this from connection errors — a timeout means the host was reached but was slow.

When it happens

Trigger: Brave API slow under load; a low timeout constructor value (e.g. timeout=5) on high-latency links; oversized result sets (large count parameter) taking longer than the cap; network congestion.

Common situations: Mobile/high-latency networks; aggressive timeouts copied from fast internal services; requesting many results per query; Brave-side latency spikes.

Understand the failure class

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

Related errors

AI-assisted analysis of crewAIInc/crewAI@754d7323be (2026-08-15). Data as JSON: /api/errors/a3c230e11ef375bd. Report an issue: GitHub.