# Web SDK configuration > Every config option of the Runbear Web SDK — suggestions, thinking, tool progress, user context, the input placeholder, assistant identity, the welcome message and component labels. Source: https://docs.runbear.io/api/web-sdk/configuration Last updated: 2026-09-30 Everything that shapes what the widget shows goes in `config`, passed to the `Runbear` constructor next to `assistantId` and `auth`. Every option is optional; leave `config` out and the widget uses the defaults below. ```ts const client = new Runbear({ assistantId: "…", auth: { mode: "session", fetchSessionToken }, config: { chatInput: { placeholder: "Ask about your order…" }, assistant: { name: "Acme Support", avatarUrl: "https://example.com/bot.png", showName: true }, welcomeMessage: "Hi! How can I help you today?", userContext: { plan: "pro", locale: "en-US" }, }, }) ``` ## Options | Option | Type | Default | Since | In session mode | | ----------------------- | ------------------------------------------ | ----------------------------------------- | ------------ | ----------------------------- | | `suggestions.enabled` | boolean | Off | All versions | No effect; the SDK warns once | | `thinking.enabled` | boolean | On | 0.1.1 | Same | | `toolProgress.enabled` | boolean | On | 0.1.2 | Same | | `userContext` | object of string, number or boolean values | None | All versions | Same | | `chatInput.placeholder` | string | `"Enter your message..."` | 0.1.6 | Same | | `assistant.name` | string | None | 0.1.9 | Same | | `assistant.avatarUrl` | string | Default avatar icon | 0.1.9 | Same | | `assistant.showName` | boolean | `false` | 0.1.9 | Same | | `welcomeMessage` | string | None | 0.1.9 | Same | | `components.labels` | object of strings | See [Component labels](#component-labels) | 0.3.0 | Same | ### suggestions `suggestions: { enabled: true }` asks the agent for follow-up questions after each reply and shows them under a "Suggested Questions" heading. Clicking one sends it as the visitor's message. The widget skips suggestions after a reply that rendered a [response component](/api/web-sdk/response-components.md), because they would repeat the component's own options. Suggestions use `POST /v1/chat/suggestions`, which a session pass can't call, so the option has no effect in session mode. ### thinking `thinking: { enabled: false }` hides the agent's thinking while a reply streams. Thinking only appears for agents whose model streams it, which are Anthropic and Claude Agent SDK agents; for other agents the option changes nothing. ### toolProgress `toolProgress: { enabled: false }` hides the inline progress lines the widget shows while the agent calls a tool. ### userContext `userContext` is sent with every message as `config.userContext`, so the agent can take it into account: a plan, a locale, an account id. See [Chat](/api/chat.md) for how the API passes it on. > **Warning** > > The browser sets `userContext`, so a visitor can change it. Never use it to decide what a visitor > is allowed to see or do. Enforce access in the tools and systems the agent calls, based on identity > your server has verified. ### chatInput.placeholder The text shown in the empty message box. ### assistant Identity shown on the agent's messages: - `name`: shown above each agent message when `showName` is `true`, and used for the avatar's initials. - `avatarUrl`: an image you host. It must be an `https:` URL; any other URL, or an image that fails to load, falls back to the initials from `name`, or to the default avatar icon. - `showName`: `false` by default, so the name isn't shown unless you opt in. The avatar shows whenever `avatarUrl` is valid. The widget doesn't read the agent's name or avatar from Runbear; these options are the only source. ### welcomeMessage A greeting shown as the first agent message before the visitor types. It is rendered in the browser only: no thread is created for it, the agent isn't called, and it costs no credits. It shows on a new conversation, including after `reset()`, and never on a conversation reopened with `startWithThread()` or `createChat(threadId)`, whose saved transcript is shown as it is. ### Component labels `components.labels` replaces the strings the `confirm` and `select` components show. Each label is optional, and a partial override replaces only what it names: | Label | Default | | --------------- | ------------------------------ | | `untitledGroup` | `"Choose an option"` | | `optionCount` | `"{count} options available"` | | `answered` | `"Answered."` | | `chosen` | `"You chose: {label}"` | | `streaming` | `"Waiting for the assistant…"` | [Customizing the rendered strings](/api/web-sdk/response-components.md#customizing-the-rendered-strings) says when each one shows. ## Attachments The widget has an attachment button, and visitors can also paste files into the message box. Each file can be up to 50 MB and must be one of the [supported file types](/api/files.md#supported-file-types). Empty files are ignored, and a file already attached isn't added twice. Attachments are available in proxy and direct mode. In session mode the attachment button is hidden, because a session pass can't upload files. ## Which strings you can change Only the input placeholder and the component labels are configurable. Other widget strings are fixed in this release, including the "Suggested Questions" heading and the "An unknown error occurred" message shown when a reply fails. ## Related - [Authentication](/api/web-sdk/authentication.md): the `auth` option - [Theming](/api/web-sdk/theming.md): colors, dark mode and CSS hooks - [Chat API](/api/web-sdk/chat-api.md): methods and events