Web Search
Where search results come from: Bing browser search by default, model-native search, and the search services bundled with each model subscription; page fetching reads the response body directly.
Settings → Web Search has two parts: where search results come from, and how web pages are fetched.
Search sources
One master switch plus an "active source" dropdown. The default is Bing, which searches through the background browser and needs no API key — but it does require the built-in Browser Control plugin to be enabled, because that plugin is what runs the search. Turn the master switch off and the search tool is not exposed at all; you can still fetch pages when you supply a URL directly, so disabling search is not the same as going offline.
Source options:
- Bing (default): searches Bing through the background browser, no key needed. On a connection failure or a verification page it reports the error explicitly instead of quietly switching providers — this is deliberate, because a silent fallback would leave you believing the results you got were all of them.
- Model-native: the provider searches on the server side. The model itself has to support it (the official Anthropic and OpenAI models do); third-party gateways and custom baseUrl values do not, and in that case it falls back to Bing browser search automatically. With this option selected, the client's search tool is hidden from the model so it sees only one search surface.
- Subscription search: Claude subscription, Codex, Cursor, Qoder, QwenWork, WorkBuddy, Antigravity, TRAE CN, Kiro, Kimi, Bailian Token Plan, MiniMax M Plan, and Zhipu Coding Plan can each answer searches with their own account's bundled search service, without using the current session's model and without requiring the session itself to use that source. These reuse the sign-in credentials under Settings → Model Sources; picking a source you have not connected prompts you to connect it first, and expired credentials produce an explicit error.
- Brave and custom endpoints are retired: neither has a settings entry any more. An existing configuration from an earlier version that is already active stays visible, but it cannot be selected again.
Two more knobs: blocked domains (comma-separated; results from these domains are excluded) and maximum searches (how many searches per turn are allowed, so it cannot keep searching forever). There is no UI for an allow-list of domains; to use one, edit the engine configuration.
Changing the source or entering a key takes effect for new sessions.
Fetching web pages
Page fetching does not follow the search source or the chat model, and it keeps working when search is off. It reads the response body and does not run JavaScript on the page, so it does not need a separate browser install. Open the in-app browser to view a page after its scripts run.
- Blocked domains: comma-separated; fetching these domains is forbidden. This is a security guardrail — list private domains you do not want fetched, for example, and a link cannot pull their content out.