Skip to content

Open-source AI browser agent for Chrome and Firefox (monorepo) 🧠

Preserve Compass exception in decision model Auto default across documentation

Emre Sokulluc2978aa99889
diff --git a/web/docs/providers/index.html b/web/docs/providers/index.html
index 77e7ac8de..0f4e3d7da 100644
--- a/web/docs/providers/index.html
+++ b/web/docs/providers/index.html
@@ -35,7 +35,7 @@
<section class="doc-section" id="troubleshoot"><h2>When Test Connection fails</h2><ol><li><strong>Connection refused:</strong> start the local server and confirm the port.</li><li><strong>CORS or origin error:</strong> allow the WebBrain extension origin in the local server.</li><li><strong>Unauthorized:</strong> paste a current key for the same provider as the base URL.</li><li><strong>Model not found:</strong> copy the exact model ID from the provider or use Load models.</li><li><strong>Requests time out:</strong> increase the General request timeout for large local models on CPU.</li><li><strong>Runs fail after a few turns:</strong> confirm the real context window; lower the prompt tier or load the model with a larger context.</li></ol><div class="callout tip"><strong class="callout-title">Test before you switch</strong><p>Keep the working provider active while you configure a new one. Save and test the new card first; only then click Set Active.</p></div></section>
- <section class="doc-section" id="assistive-models"><h2>Optional assistive models</h2><p>The active provider handles the main conversation, planning and final replies. Use <strong>Settings → Assistive Models</strong> for a separate <strong>Vision</strong> model, <strong>Speech to text</strong> endpoint or <strong>Decision models</strong>. These settings are independent of provider filtering and selection.</p><p>Vision and Decision models default to <strong>Auto</strong>: in Chrome they use Ternary Bonsai 2 2B Vision once it is downloaded and nothing before that. A decision model only answers yes-or-no and multiple-choice questions such as “Is this task finished?”; turn it <strong>On</strong> to use OpenRouter, TypeSafe, a local server, D1 or the in-browser model for every decision, or <strong>Off</strong> to never use one. Existing permissions and completion checks still apply. See <a href="/docs/settings/#multimodal">Assistive Models settings</a> for setup and data-sharing details.</p></section>
+ <section class="doc-section" id="assistive-models"><h2>Optional assistive models</h2><p>The active provider handles the main conversation, planning and final replies. Use <strong>Settings → Assistive Models</strong> for a separate <strong>Vision</strong> model, <strong>Speech to text</strong> endpoint or <strong>Decision models</strong>. These settings are independent of provider filtering and selection.</p><p>Vision and Decision models default to <strong>Auto</strong>: in Chrome they use Ternary Bonsai 2 2B Vision once it is downloaded (or Compass’s managed decision model for decisions while WebBrain Cloud is active), and nothing before that. A decision model only answers yes-or-no and multiple-choice questions such as “Is this task finished?”; turn it <strong>On</strong> to use OpenRouter, TypeSafe, a local server, D1 or the in-browser model for every decision, or <strong>Off</strong> to never use one. Existing permissions and completion checks still apply. See <a href="/docs/settings/#multimodal">Assistive Models settings</a> for setup and data-sharing details.</p></section>
<nav class="next-links" aria-label="Next guides"><a href="/docs/settings/"><span>Back</span>← Settings, explained</a><a href="/docs/safety/"><span>Next</span>Modes, safety & privacy →</a></nav>
</main>
<aside class="on-this-page" aria-label="On this page"><h2>On this page</h2><a href="#quick-choice">Quick choice</a><a href="#catalog">Provider catalog</a><a href="#setup">Configure</a><a href="#fields">Fields</a><a href="#local">Local models</a><a href="#tiers">Prompt tiers</a><a href="#troubleshoot">Troubleshoot</a></aside>
diff --git a/web/docs/settings/index.html b/web/docs/settings/index.html
index 293e8416c..60274dcd9 100644
--- a/web/docs/settings/index.html
+++ b/web/docs/settings/index.html
@@ -24,7 +24,7 @@
<div class="breadcrumb"><a href="/docs/">Docs</a> / Settings</div>
<section class="doc-hero"><div class="eyebrow">Settings, without guesswork</div><h1>Know what to change—and what to leave alone.</h1><p class="lede">Open Settings from the gear in the side panel or from your browser’s extension options. Most people only need General, Providers, and Permissions; the other tabs solve specific problems.</p><div class="meta">Screenshots from the Assistive Models update · synthetic configuration, no real credentials</div></section>
- <section class="doc-section" id="defaults"><h2>A good default setup</h2><div class="table-wrap"><table><thead><tr><th>Control</th><th>Recommended</th><th>Why</th></tr></thead><tbody><tr><td>Plan before Act</td><td>Try planning</td><td>Uses a plan when available and safely falls back to a read-only turn if planner formatting fails.</td></tr><tr><td>Plan review stops</td><td>Below confidence threshold</td><td>Low-confidence plans pause; confident plans can continue.</td></tr><tr><td>Review below confidence</td><td>90%</td><td>A conservative balance between supervision and flow.</td></tr><tr><td>Max Agent Steps</td><td>130</td><td>Enough room for multi-step work. Stop the run yourself if behavior looks repetitive.</td></tr><tr><td>LLM request timeout</td><td>120 seconds</td><td>Cloud models usually answer sooner; large local models may need the extra startup time.</td></tr><tr><td>Scheduled action confirmation</td><td>On</td><td>Unattended work still pauses before consequential actions.</td></tr><tr><td>Permission gate</td><td>On</td><td>WebBrain asks before it first acts on a site and remembers your explicit choice. The ⚠ button in the side panel header switches it too.</td></tr><tr><td>Decision models</td><td>Auto</td><td>Nothing to set up. Uses Ternary Bonsai 2 2B Vision for completion checks once it is downloaded, and no decision model before that.</td></tr><tr><td>In-browser vision model</td><td>Auto</td><td>Reads screenshots with Ternary Bonsai 2 2B Vision once it is downloaded, only when your chat model cannot see images.</td></tr></tbody></table></div></section>
+ <section class="doc-section" id="defaults"><h2>A good default setup</h2><div class="table-wrap"><table><thead><tr><th>Control</th><th>Recommended</th><th>Why</th></tr></thead><tbody><tr><td>Plan before Act</td><td>Try planning</td><td>Uses a plan when available and safely falls back to a read-only turn if planner formatting fails.</td></tr><tr><td>Plan review stops</td><td>Below confidence threshold</td><td>Low-confidence plans pause; confident plans can continue.</td></tr><tr><td>Review below confidence</td><td>90%</td><td>A conservative balance between supervision and flow.</td></tr><tr><td>Max Agent Steps</td><td>130</td><td>Enough room for multi-step work. Stop the run yourself if behavior looks repetitive.</td></tr><tr><td>LLM request timeout</td><td>120 seconds</td><td>Cloud models usually answer sooner; large local models may need the extra startup time.</td></tr><tr><td>Scheduled action confirmation</td><td>On</td><td>Unattended work still pauses before consequential actions.</td></tr><tr><td>Permission gate</td><td>On</td><td>WebBrain asks before it first acts on a site and remembers your explicit choice. The ⚠ button in the side panel header switches it too.</td></tr><tr><td>Decision models</td><td>Auto</td><td>Nothing to set up. Uses Ternary Bonsai 2 2B Vision for completion checks once it is downloaded (or Compass’s managed decision model while WebBrain Cloud is active), and no decision model otherwise.</td></tr><tr><td>In-browser vision model</td><td>Auto</td><td>Reads screenshots with Ternary Bonsai 2 2B Vision once it is downloaded, only when your chat model cannot see images.</td></tr></tbody></table></div></section>
<section class="doc-section" id="general"><div class="eyebrow">Everyday</div><h2>General: how the agent behaves</h2><p>Language and appearance are cosmetic. The controls below them change the agent loop: how it plans, when you review, how long it can work, and whether scheduled jobs can run.</p><figure class="shot"><a href="/docs/assets/screenshots/settings-general.jpg"><img src="/docs/assets/screenshots/settings-general.jpg" alt="WebBrain General settings showing language, appearance, planning, plan review and confidence controls"></a><figcaption>General starts with the controls you are most likely to use. Click the image to view it at full size.</figcaption></figure>
<h3>Planning controls</h3><ul><li><strong>Try planning</strong> is the best general choice. WebBrain attempts a structured plan before Act or Dev tools run; if planner formatting still fails after repair, that turn continues with the Ask prompt and read-only tools.</li><li><strong>Strict planning</strong> cancels the run when a valid plan cannot be produced. Use it where “no plan, no action” matters more than convenience.</li><li><strong>Off</strong> removes the extra full-plan call, while retaining the compact intent check and its safe read-only fallback. It can be faster and cheaper, but you lose the plan review checkpoint.</li></ul>
@@ -39,10 +39,10 @@
<section class="doc-section" id="captcha"><h2>CAPTCHA solvers</h2><p>General → Advanced has a dedicated block for CapSolver, 2Captcha, CapMonster Cloud, SolveCaptcha, Anti-Captcha, NopeCHA and NoneCap. Entering a key checks its enabled box; you can turn it off while keeping the key. Save persists that choice. Testing a balance does not enable solving.</p><p>Expand a provider’s Advanced section to adjust its weight. Defaults are 100 through 94 in the order above. Enable any number; compatible providers run from highest weight to lowest. Errors and timeouts can cause more than one service to charge.</p><p>hCaptcha uses NopeCHA or NoneCap. Other families have provider-specific coverage and input requirements. See the <a href="/docs/captcha/">CAPTCHA guide</a> for the full coverage table, fallback behavior, privacy and page-application limits.</p></section>
<section class="doc-section" id="providers"><div class="eyebrow">Everyday</div><h2>Providers: choose the brain</h2><p>Only one provider is active at a time. Filter the list by Local, Cloud, or Router; search by provider, model, or field; then open a card to edit it. The safe sequence is <strong>Save → Test Connection → Set Active</strong>.</p><figure class="shot"><a href="/docs/assets/screenshots/settings-providers.jpg"><img src="/docs/assets/screenshots/settings-providers.jpg" alt="WebBrain Providers settings with category filters, search and the active provider card"></a><figcaption>The active provider remains visible even when category filters are applied. Example model names are illustrative.</figcaption></figure><p>See <a href="/docs/providers/">Providers & models</a> for local server URLs, context windows, prompt tiers, and troubleshooting.</p></section>
- <section class="doc-section" id="multimodal"><div class="eyebrow">When needed</div><h2>Assistive Models: support the main agent</h2><p>Choose the main conversation model in <strong>Providers</strong>. Open <strong>Settings → Assistive Models</strong> for the optional models below; configuring one does not change your active provider.</p><p>Vision and Decision models both default to <strong>Auto</strong>. In Chrome with hardware WebGPU, Auto uses <strong>Ternary Bonsai 2 2B Vision</strong> (about 1.45 GB, runs on your device) once it is downloaded, and nothing before that. The <strong>Download a local model</strong> button on the install page, <strong>Providers → WebGPU</strong>, the Vision card and Apocalypse Mode all download that same model, so one download covers chat, screenshots and decisions.</p>
+ <section class="doc-section" id="multimodal"><div class="eyebrow">When needed</div><h2>Assistive Models: support the main agent</h2><p>Choose the main conversation model in <strong>Providers</strong>. Open <strong>Settings → Assistive Models</strong> for the optional models below; configuring one does not change your active provider.</p><p>Vision and Decision models both default to <strong>Auto</strong>. In Chrome with hardware WebGPU, Auto uses <strong>Ternary Bonsai 2 2B Vision</strong> (about 1.45 GB, runs on your device) once it is downloaded (while WebBrain Cloud is active, Compass’s managed decision model answers decisions instead), and nothing before that. The <strong>Download a local model</strong> button on the install page, <strong>Providers → WebGPU</strong>, the Vision card and Apocalypse Mode all download that same model, so one download covers chat, screenshots and decisions.</p>
<h3>Vision</h3><p>Pick what reads screenshots. An OpenAI-compatible endpoint, if you save one, reads every screenshot while the active provider keeps planning and tool calls. Without one, the active model reads screenshots itself if it can see images; if it cannot, the in-browser vision model does (Chrome only). Leave everything at its default to let the active provider handle vision. Screenshot limits and redaction are grouped here too.</p><p>The in-browser vision model has four settings:</p><ul><li><strong>Auto</strong> (default): uses Ternary Bonsai 2 2B Vision once it is downloaded and stays off until then.</li><li><strong>Ternary Bonsai 2 2B Vision</strong>: about 1.45 GB. The same model also chats and answers decisions.</li><li><strong>WebBrain VL 2 450M</strong>: about 810 MB, vision only. Its first download asks for your consent and checks WebGPU.</li><li><strong>Off</strong>: no in-browser vision model.</li></ul><p>Changing the setting never downloads anything; use the card’s <strong>Download</strong> button. Tasks never wait for a download, and screenshots read in the browser stay on your device. Firefox has no in-browser vision model.</p><figure class="shot"><a href="/docs/assets/screenshots/settings-assistive-models.jpg"><img src="/docs/assets/screenshots/settings-assistive-models.jpg" alt="Assistive Models settings: the Vision card with the in-browser vision model set to Auto and the optional OpenAI-compatible endpoint"></a><figcaption>A fresh install: the in-browser vision model is on Auto and stays off until Ternary Bonsai 2 2B Vision is downloaded.</figcaption></figure>
<h3>Speech to text</h3><p>Configure a Whisper-compatible endpoint for recordings. Leave it blank and WebBrain tries configured providers in this order: OpenAI, Groq, LM Studio, then llama.cpp.</p>
- <h3>Decision models</h3><p>A decision model is a small, fast model that answers the agent’s yes-or-no and multiple-choice questions, such as “Is this task finished?”, so your chat model doesn’t have to. It never plans, clicks or types. Choose one mode:</p><ul><li><strong>Auto</strong> (default): nothing to set up. In Chrome it uses Ternary Bonsai 2 2B Vision once it is downloaded, to check whether side panel tasks and scheduled watches and tasks really finished. While WebBrain Cloud (Compass) is your chat provider, Compass’s decision model answers instead. Otherwise no decision model is used. The card shows which one is in use.</li><li><strong>On</strong>: uses the provider you set up for every decision: OpenRouter, TypeSafe, a local System One server, D1, or the in-browser chat model in Chrome. All decisions are on by default. Open <strong>Choose which decisions use it</strong> to turn off individual ones (Verify completion, Verify scheduled watches, Verify scheduled task completion, Fast classifications, Fast browser actions — Experimental) and to set thresholds.</li><li><strong>Off</strong>: never uses a decision model, Compass’s included. Your chat model still checks whether tasks are finished.</li></ul><p>A mode change applies at once; On’s provider fields use <strong>Save</strong>. <strong>Test Connection</strong> sends one request with fixed example data. <strong>Reset</strong> returns to Auto and deletes saved decision keys. Cloud decision providers receive limited task and page data and may cost money; Strict Secret Mode disables decision models. Profiles that had decision outsourcing turned on before these modes keep working as On with their previous switches.</p><figure class="shot"><a href="/docs/assets/screenshots/settings-decision-models.jpg"><img src="/docs/assets/screenshots/settings-decision-models.jpg" alt="Decision models settings with Auto selected and the status line showing that no decision model is in use yet"></a><figcaption>Auto on a fresh install: nothing is downloaded yet, so no decision model is in use. Provider fields appear only with On.</figcaption></figure>
+ <h3>Decision models</h3><p>A decision model is a small, fast model that answers the agent’s yes-or-no and multiple-choice questions, such as “Is this task finished?”, so your chat model doesn’t have to. It never plans, clicks or types. Choose one mode:</p><ul><li><strong>Auto</strong> (default): nothing to set up. In Chrome it uses Ternary Bonsai 2 2B Vision once it is downloaded, to check whether side panel tasks and scheduled watches and tasks really finished. While WebBrain Cloud (Compass) is your chat provider, Compass’s decision model answers instead. Otherwise no decision model is used. The card shows which one is in use.</li><li><strong>On</strong>: uses the provider you set up for every decision: OpenRouter, TypeSafe, a local System One server, D1, or the in-browser chat model in Chrome. All decisions are on by default. Open <strong>Choose which decisions use it</strong> to turn off individual ones (Verify completion, Verify scheduled watches, Verify scheduled task completion, Fast classifications, Fast browser actions — Experimental) and to set thresholds.</li><li><strong>Off</strong>: never uses a decision model, Compass’s included. Your chat model still checks whether tasks are finished.</li></ul><p>A mode change applies at once; On’s provider fields use <strong>Save</strong>. <strong>Test Connection</strong> sends one request with fixed example data. <strong>Reset</strong> returns to Auto and deletes saved decision keys. Cloud decision providers receive limited task and page data and may cost money; Strict Secret Mode disables decision models. Profiles that had decision outsourcing turned on before these modes keep working as On with their previous switches.</p><figure class="shot"><a href="/docs/assets/screenshots/settings-decision-models.jpg"><img src="/docs/assets/screenshots/settings-decision-models.jpg" alt="Decision models settings with Auto selected and the status line showing that no decision model is in use yet"></a><figcaption>Auto on a fresh install: nothing is downloaded yet, so no decision model is in use (unless WebBrain Cloud is your active provider, which uses Compass’s decision model). Provider fields appear only with On.</figcaption></figure>
</section>
<section class="doc-section" id="memory"><div class="eyebrow">When needed</div><h2>Memory: decide what persists</h2><figure class="shot"><a href="/docs/assets/screenshots/settings-memory.jpg"><img src="/docs/assets/screenshots/settings-memory.jpg" alt="WebBrain Memory settings showing encrypted cloud sync and profile auto-fill"></a><figcaption>Memory groups three different features: encrypted sync, profile auto-fill, and user memory.</figcaption></figure><ul><li><strong>Encrypted Cloud Sync</strong> is for WebBrain Compass members. Supported provider keys, profile text, and memories are encrypted with your sync password before upload. WebBrain cannot recover that password. Chat history and OAuth sign-ins are not synced.</li><li><strong>Profile auto-fill</strong> is a reusable block of personal details. It is stored in plaintext in this browser profile and sent to the active provider when enabled.</li><li><strong>User memory</strong> stores durable preferences. Explicit <code>/memory --add</code> saves immediately. Auto-learn and learning from completed forms are optional.</li></ul><div class="callout danger"><strong class="callout-title">Do not turn memory into a password manager</strong><p>Do not store passwords, API keys, tokens, recovery codes, or other secrets in profile text or user memory.</p></div></section>
diff --git a/web/docs/zh/providers/index.html b/web/docs/zh/providers/index.html
index df5073993..ff0cfd269 100644
--- a/web/docs/zh/providers/index.html
+++ b/web/docs/zh/providers/index.html
@@ -20,7 +20,7 @@
<section class="doc-section" id="local"><h2>本地模型的额外环节</h2><div class="table-wrap"><table><thead><tr><th>服务器</th><th>常见 Base URL</th><th>API 密钥</th></tr></thead><tbody><tr><td>llama.cpp</td><td><code>http://localhost:8080</code></td><td>通常不需要</td></tr><tr><td>Ollama</td><td><code>http://localhost:11434/v1</code></td><td>不需要</td></tr><tr><td>ODS</td><td><code>http://localhost:11434/v1</code></td><td>可选;使用 ODS .env 中的端口</td></tr><tr><td>LM Studio</td><td><code>http://localhost:1234/v1</code></td><td>不需要</td></tr><tr><td>Jan</td><td><code>http://localhost:1337/v1</code></td><td>可选</td></tr><tr><td>vLLM</td><td><code>http://localhost:8000/v1</code></td><td>可选</td></tr><tr><td>SGLang</td><td><code>http://localhost:30000/v1</code></td><td>可选</td></tr></tbody></table></div><div class="callout warning"><strong class="callout-title">终端可用,不代表扩展一定可访问</strong><p>连接被拒绝通常是服务器未启动或端口错误;CORS/Origin 错误需要允许浏览器扩展来源。Ollama 常用:<code>OLLAMA_ORIGINS="chrome-extension://*,moz-extension://*" ollama serve</code>。</p></div></section>
<section class="doc-section" id="tiers"><h2>提示层级</h2><div class="mode-strip"><div class="mode ask"><strong>Compact</strong><span>最短提示与最小工具面,适合约 8k 上下文的小型本地模型。</span></div><div class="mode act"><strong>Mid</strong><span>包含常见浏览器任务、iframe、下载、计划任务和表单验证。推荐的本地起点。</span></div><div class="mode dev"><strong>Full</strong><span>增加 hover、拖放、框架与 Shadow DOM 等高级回退工具。</span></div></div><p>云提供商固定使用 Full;本地提供商默认 Mid;Compact 提供商不能使用 Dev 模式。</p></section>
<section class="doc-section" id="troubleshoot"><h2>测试连接失败时</h2><ol><li><strong>Connection refused:</strong>启动本地服务器并确认端口。</li><li><strong>CORS/Origin:</strong>在服务器中允许 WebBrain 扩展来源。</li><li><strong>Unauthorized:</strong>确认密钥与 Base URL 属于同一提供商。</li><li><strong>Model not found:</strong>复制精确模型 ID,或使用 Load models。</li><li><strong>超时:</strong>为大型 CPU 本地模型提高常规请求超时。</li><li><strong>几轮后失败:</strong>确认真实上下文窗口,降低提示层级或扩大模型上下文。</li></ol></section>
- <section class="doc-section" id="assistive-models"><h2>可选的辅助模型</h2><p>当前提供商负责主要对话、规划和最终回复。在<strong>设置 → 辅助模型</strong>中,可独立配置<strong>视觉</strong>模型、<strong>语音转文字</strong>端点或<strong>决策模型</strong>。这些设置不受提供商筛选或切换影响。</p><p>视觉和决策模型默认都是<strong>自动</strong>:在 Chrome 中,Ternary Bonsai 2 2B Vision 下载完成后使用它,下载前不使用。决策模型只回答“这个任务完成了吗?”这类是非题和选择题;选择<strong>开启</strong>可让 OpenRouter、TypeSafe、本地服务器、D1 或浏览器内模型回答所有决策,选择<strong>关闭</strong>则从不使用。现有权限与完成检查仍然适用。配置方法和数据共享说明见<a href="/docs/zh/settings/#multimodal">辅助模型设置</a>。</p></section>
+ <section class="doc-section" id="assistive-models"><h2>可选的辅助模型</h2><p>当前提供商负责主要对话、规划和最终回复。在<strong>设置 → 辅助模型</strong>中,可独立配置<strong>视觉</strong>模型、<strong>语音转文字</strong>端点或<strong>决策模型</strong>。这些设置不受提供商筛选或切换影响。</p><p>视觉和决策模型默认都是<strong>自动</strong>:在 Chrome 中,Ternary Bonsai 2 2B Vision 下载完成后使用它(WebBrain Cloud 激活时决策由 Compass 的托管决策模型处理),其他情况下下载前不使用。决策模型只回答“这个任务完成了吗?”这类是非题和选择题;选择<strong>开启</strong>可让 OpenRouter、TypeSafe、本地服务器、D1 或浏览器内模型回答所有决策,选择<strong>关闭</strong>则从不使用。现有权限与完成检查仍然适用。配置方法和数据共享说明见<a href="/docs/zh/settings/#multimodal">辅助模型设置</a>。</p></section>
<nav class="next-links" aria-label="后续指南"><a href="/docs/zh/settings/"><span>上一篇</span>← 设置说明</a><a href="/docs/zh/safety/"><span>下一篇</span>模式、安全与隐私 →</a></nav>
</main><aside class="on-this-page" aria-label="本页内容"><h2>本页内容</h2><a href="#choice">快速选择</a><a href="#catalog">提供商目录</a><a href="#setup">配置步骤</a><a href="#fields">字段</a><a href="#local">本地模型</a><a href="#tiers">提示层级</a><a href="#troubleshoot">排错</a></aside>
</div><footer class="site-footer"><div class="footer-inner"><span>WebBrain 用户指南</span><div class="footer-links"><a href="/privacy">隐私</a><a href="https://github.com/webbrain-one/webbrain/issues">报告问题</a></div></div></footer><script src="/docs/assets/docs.js?v=20260809"></script>
diff --git a/web/docs/zh/settings/index.html b/web/docs/zh/settings/index.html
index 9ef0265ad..f475e64bb 100644
--- a/web/docs/zh/settings/index.html
+++ b/web/docs/zh/settings/index.html
@@ -13,14 +13,14 @@
<a class="skip-link" href="#main">跳到正文</a><header class="site-header"><div class="header-inner"><a class="brand" href="/"><img src="/logo-github.png" alt=""><span>WebBrain</span><span class="brand-docs">用户指南</span></a><nav class="top-nav" aria-label="主导航"><a href="/">首页</a><a href="/docs/zh/" aria-current="page">文档</a><a href="/blog/">博客</a><a href="https://github.com/webbrain-one/webbrain">GitHub</a></nav><div class="header-tools"><a class="lang-switch" href="/docs/settings/" aria-label="Read in English"><span>EN</span><span class="active">中文</span></a><button class="icon-button" type="button" data-theme-toggle aria-label="切换主题">☀</button><button class="sidebar-toggle" type="button" data-sidebar-toggle aria-expanded="false" aria-label="打开文档菜单">☰</button></div></div></header>
<div class="docs-shell"><aside class="docs-sidebar" aria-label="文档目录"><div class="sidebar-group"><div class="sidebar-label">从这里开始</div><nav><a href="/docs/zh/">概览</a><a href="/docs/zh/faq/">常见问题</a></nav></div><div class="sidebar-group"><div class="sidebar-label">使用 WebBrain</div><nav><a href="/docs/zh/settings/" aria-current="page">设置说明</a><a href="/docs/zh/providers/">提供商与模型</a><a href="/docs/zh/easy-cli-proxy/">订阅代理</a><a href="/docs/zh/safety/">模式、安全与隐私</a><a href="/docs/zh/apocalypse-mode/">末日模式</a><a href="/docs/zh/formats/">导出与工作流</a><a href="/docs/zh/mcp/">MCP 服务器</a><a href="/docs/zh/lm-studio/">LM Studio 插件</a><a href="/docs/zh/ollama/">Ollama</a></nav></div><div class="sidebar-group"><div class="sidebar-label">社区</div><nav><a href="https://discord.gg/cgC325ssfw">Discord 支持</a></nav></div></aside>
<main class="doc-main" id="main"><div class="breadcrumb"><a href="/docs/zh/">文档</a> / 设置</div><section class="doc-hero"><div class="eyebrow">不再猜测设置含义</div><h1>知道该改什么,也知道什么可以不动。</h1><p class="lede">从侧边栏齿轮或浏览器扩展选项打开设置。大多数人主要使用“常规”“提供商”和“权限”;其他标签页用于解决特定问题。</p><div class="meta">截图来自辅助模型设置更新后的英文界面 · 中文界面的控件位置相同 · 合成示例不含真实凭据</div></section>
- <section class="doc-section" id="defaults"><h2>适合大多数人的默认值</h2><div class="table-wrap"><table><thead><tr><th>控制项</th><th>推荐值</th><th>原因</th></tr></thead><tbody><tr><td>执行前计划</td><td>尝试计划</td><td>有计划时使用;如果规划器格式化失败,安全回退到只读轮次。</td></tr><tr><td>计划审查</td><td>低于置信度阈值时停止</td><td>不确定的计划暂停,可靠计划可继续。</td></tr><tr><td>审查阈值</td><td>90%</td><td>在监督与流畅度之间较保守的平衡。</td></tr><tr><td>最大代理步骤</td><td>130</td><td>足够处理多步骤工作;出现重复时仍应手动停止。</td></tr><tr><td>LLM 请求超时</td><td>120 秒</td><td>云模型通常更快,大型本地模型启动可能更慢。</td></tr><tr><td>计划任务关键操作确认</td><td>开启</td><td>无人值守任务仍会在关键操作前暂停。</td></tr><tr><td>权限闸门</td><td>开启</td><td>首次在网站执行特定操作前询问,并记住你的明确选择。侧边栏标题栏的 ⚠ 按钮也可以切换它。</td></tr><tr><td>决策模型</td><td>自动</td><td>无需设置。Ternary Bonsai 2 2B Vision 下载完成后用它做完成检查,下载前不使用决策模型。</td></tr><tr><td>浏览器内视觉模型</td><td>自动</td><td>Ternary Bonsai 2 2B Vision 下载完成后用它读取截图,且仅在聊天模型无法看图时使用。</td></tr></tbody></table></div></section>
+ <section class="doc-section" id="defaults"><h2>适合大多数人的默认值</h2><div class="table-wrap"><table><thead><tr><th>控制项</th><th>推荐值</th><th>原因</th></tr></thead><tbody><tr><td>执行前计划</td><td>尝试计划</td><td>有计划时使用;如果规划器格式化失败,安全回退到只读轮次。</td></tr><tr><td>计划审查</td><td>低于置信度阈值时停止</td><td>不确定的计划暂停,可靠计划可继续。</td></tr><tr><td>审查阈值</td><td>90%</td><td>在监督与流畅度之间较保守的平衡。</td></tr><tr><td>最大代理步骤</td><td>130</td><td>足够处理多步骤工作;出现重复时仍应手动停止。</td></tr><tr><td>LLM 请求超时</td><td>120 秒</td><td>云模型通常更快,大型本地模型启动可能更慢。</td></tr><tr><td>计划任务关键操作确认</td><td>开启</td><td>无人值守任务仍会在关键操作前暂停。</td></tr><tr><td>权限闸门</td><td>开启</td><td>首次在网站执行特定操作前询问,并记住你的明确选择。侧边栏标题栏的 ⚠ 按钮也可以切换它。</td></tr><tr><td>决策模型</td><td>自动</td><td>无需设置。Ternary Bonsai 2 2B Vision 下载完成后用它做完成检查(WebBrain Cloud 激活时使用 Compass 的托管决策模型),其他情况下不使用决策模型。</td></tr><tr><td>浏览器内视觉模型</td><td>自动</td><td>Ternary Bonsai 2 2B Vision 下载完成后用它读取截图,且仅在聊天模型无法看图时使用。</td></tr></tbody></table></div></section>
<section class="doc-section" id="general"><div class="eyebrow">日常使用</div><h2>常规:代理如何行动</h2><figure class="shot"><a href="/docs/assets/screenshots/settings-general.jpg"><img src="/docs/assets/screenshots/settings-general.jpg" alt="WebBrain 常规设置英文界面,包含语言、外观、计划、计划审查和置信度"></a><figcaption>常规标签页顶部是最常用的控制项。点击可查看原图。</figcaption></figure><p><strong>尝试计划</strong>适合日常使用;<strong>严格计划</strong>会在无法生成有效计划时取消任务;<strong>关闭</strong>会省去一次规划调用,但也失去计划审查节点。</p><p>步骤上限统计一条消息中的工具调用步骤,不是聊天消息数。请求超时只限制模型开始响应前的等待时间,不会中断已经开始流式输出的响应。</p><div class="callout warning"><strong class="callout-title">无限步骤不等于更可靠</strong><p>∞ 只会移除机械停止点,不会让模型更不容易循环。除非你正在全程监督长任务,否则保留有限上限。</p></div></section>
<section class="doc-section" id="advanced"><div class="eyebrow">高级抽屉</div><h2>高级:带着明确目的再打开</h2><figure class="shot"><a href="/docs/assets/screenshots/settings-advanced.jpg"><img src="/docs/assets/screenshots/settings-advanced.jpg" alt="通过搜索定位到严格秘密处理高级设置"></a><figcaption>搜索框会自动展开匹配的高级设置,让选项与完整说明一起显示。</figcaption></figure><div class="table-wrap"><table><thead><tr><th>设置</th><th>通常保持</th><th>何时修改</th></tr></thead><tbody><tr><td>截图回退</td><td>视觉模型可用时开启</td><td>DOM 读取遗漏图表、画布或视觉内容。</td></tr><tr><td>网站适配器</td><td>开启</td><td>调试令牌使用或禁用站点专用提示。</td></tr><tr><td>API 变更观察器</td><td>关闭</td><td>研究重复 UI 操作与 API 快捷建议。</td></tr><tr><td>自动截图</td><td>状态变化时</td><td>需要更低图像成本,或每一步都要截图。</td></tr><tr><td>记录追踪</td><td>关闭</td><td>比较模型或诊断运行,并接受本地存储。</td></tr><tr><td>严格秘密处理</td><td>个人日常使用时关闭</td><td>屏幕共享或导出追踪,不希望凭据被引用。</td></tr><tr><td>允许访问本地网络</td><td>关闭</td><td>必须访问 localhost、内网或私有地址。</td></tr><tr><td>CAPTCHA 求解</td><td>关闭</td><td>你配置并充值一个或多个 CAPTCHA 服务。<a href="/docs/captcha/">提供商与使用指南(英文)</a>。</td></tr></tbody></table></div></section>
<section class="doc-section" id="captcha"><h2>CAPTCHA 求解服务</h2><p>常规 → 高级中的独立设置区支持 CapSolver、2Captcha、CapMonster Cloud、SolveCaptcha、Anti-Captcha、NopeCHA 和 NoneCap。输入密钥会勾选启用;你也可以取消勾选并保留密钥。保存后生效,测试余额不会自动启用服务。</p><p>展开每个服务的高级设置可修改权重,默认依次为 100 至 94。可同时启用多个服务,兼容的服务按权重从高到低尝试。错误或超时后的回退可能产生多次费用。hCaptcha 使用 NopeCHA 或 NoneCap;其他类型需要相应服务支持和页面参数。请阅读<a href="/docs/captcha/">完整 CAPTCHA 指南(英文)</a>。</p></section><section class="doc-section" id="providers"><div class="eyebrow">日常使用</div><h2>提供商:选择当前模型</h2><p>一次只有一个提供商处于活动状态。正确顺序是 <strong>保存 → 测试连接 → 设为活动</strong>。</p><figure class="shot"><a href="/docs/assets/screenshots/settings-providers.jpg"><img src="/docs/assets/screenshots/settings-providers.jpg" alt="WebBrain 提供商列表英文界面,包含分类筛选、搜索和当前活动提供商"></a><figcaption>即使使用分类筛选,当前活动提供商也会保留在列表中。</figcaption></figure><p>本地服务器地址、上下文窗口和提示层级见<a href="/docs/zh/providers/">提供商与模型</a>。</p></section>
- <section class="doc-section" id="multimodal"><div class="eyebrow">按需使用</div><h2>辅助模型:支持主要代理</h2><p>在<strong>提供商</strong>中选择主要对话模型;在<strong>设置 → 辅助模型</strong>中配置以下可选功能。配置辅助模型不会改变当前提供商。</p><p>视觉和决策模型默认都是<strong>自动</strong>。在支持硬件 WebGPU 的 Chrome 中,自动模式会在 <strong>Ternary Bonsai 2 2B Vision</strong>(约 1.45 GB,在本机运行)下载完成后使用它,下载前什么都不用。安装页上的<strong>下载本地模型</strong>按钮、<strong>提供商 → WebGPU</strong>、视觉卡片和末日模式下载的都是同一个模型,一次下载即可同时用于聊天、截图和决策。</p>
+ <section class="doc-section" id="multimodal"><div class="eyebrow">按需使用</div><h2>辅助模型:支持主要代理</h2><p>在<strong>提供商</strong>中选择主要对话模型;在<strong>设置 → 辅助模型</strong>中配置以下可选功能。配置辅助模型不会改变当前提供商。</p><p>视觉和决策模型默认都是<strong>自动</strong>。在支持硬件 WebGPU 的 Chrome 中,自动模式会在 <strong>Ternary Bonsai 2 2B Vision</strong>(约 1.45 GB,在本机运行)下载完成后使用它(WebBrain Cloud 激活时改由 Compass 的托管决策模型回答),其他情况下下载前不使用。安装页上的<strong>下载本地模型</strong>按钮、<strong>提供商 → WebGPU</strong>、视觉卡片和末日模式下载的都是同一个模型,一次下载即可同时用于聊天、截图和决策。</p>
<h3>视觉</h3><p>选择由谁读取截图。保存了 OpenAI 兼容端点时,所有截图都交给它,当前提供商继续负责规划和工具调用。没有端点时,当前模型若能看图就自己读取截图;不能看图时,由浏览器内视觉模型读取(仅 Chrome)。全部保持默认即可让当前提供商处理视觉。截图限制与截图打码也归在视觉部分。</p><p>浏览器内视觉模型有四个选项:</p><ul><li><strong>自动</strong>(默认):Ternary Bonsai 2 2B Vision 下载完成后使用它,下载前保持关闭。</li><li><strong>Ternary Bonsai 2 2B Vision</strong>:约 1.45 GB,同一个模型也能聊天和回答决策问题。</li><li><strong>WebBrain VL 2 450M</strong>:约 810 MB,只用于视觉。首次下载会征求你的同意并检查 WebGPU。</li><li><strong>关闭</strong>:不使用浏览器内视觉模型。</li></ul><p>更改选项不会自动下载任何内容,请使用卡片上的<strong>下载</strong>按钮。任务从不等待下载完成;在浏览器内读取的截图不会离开你的设备。Firefox 没有浏览器内视觉模型。</p><figure class="shot"><a href="/docs/assets/screenshots/settings-assistive-models.jpg"><img src="/docs/assets/screenshots/settings-assistive-models.jpg" alt="辅助模型英文界面:视觉卡片中浏览器内视觉模型设为自动,下方是可选的 OpenAI 兼容端点"></a><figcaption>全新安装:浏览器内视觉模型为自动,在 Ternary Bonsai 2 2B Vision 下载完成前保持关闭。</figcaption></figure>
<h3>语音转文字</h3><p>为录音配置 Whisper 兼容端点。留空时依次尝试已配置的 OpenAI、Groq、LM Studio、llama.cpp。</p>
- <h3>决策模型</h3><p>决策模型是一个小而快的模型,负责回答智能体的是非题和选择题,例如“这个任务完成了吗?”,这样聊天模型就不必处理这些问题。它从不规划、点击或输入。可选三种模式:</p><ul><li><strong>自动</strong>(默认):无需设置。在 Chrome 中,Ternary Bonsai 2 2B Vision 下载完成后,用它检查侧边栏任务以及计划监控和计划任务是否真正完成。当 WebBrain Cloud(Compass)是你的聊天提供商时,改由 Compass 的决策模型回答。其他情况下不使用决策模型。卡片会显示当前使用的是哪个。</li><li><strong>开启</strong>:所有决策都使用你配置的提供商:OpenRouter、TypeSafe、本地 System One 服务器、D1,或 Chrome 中的浏览器内聊天模型。所有决策默认开启。展开<strong>选择哪些决策使用它</strong>可以单独关闭某些决策(验证完成、验证计划监控、验证计划任务完成、快速分类、快速浏览器操作(实验性))并设置阈值。</li><li><strong>关闭</strong>:从不使用决策模型,包括 Compass 的决策模型。聊天模型仍会检查任务是否完成。</li></ul><p>切换模式立即生效;“开启”模式下的提供商字段需要点击<strong>保存</strong>。<strong>测试连接</strong>只用固定示例数据发送一次请求。<strong>重置</strong>会回到自动模式并删除已保存的决策密钥。云端决策提供商会收到有限的任务与页面数据,可能产生费用;严格秘密模式会禁用决策模型。在这些模式推出前已开启决策外包的配置会按“开启”继续工作,并保留原有开关。</p><figure class="shot"><a href="/docs/assets/screenshots/settings-decision-models.jpg"><img src="/docs/assets/screenshots/settings-decision-models.jpg" alt="决策模型英文设置界面,选中自动,状态行显示尚未使用决策模型"></a><figcaption>全新安装时的自动模式:尚未下载任何模型,因此没有使用决策模型。只有选择“开启”时才会显示提供商字段。</figcaption></figure>
+ <h3>决策模型</h3><p>决策模型是一个小而快的模型,负责回答智能体的是非题和选择题,例如“这个任务完成了吗?”,这样聊天模型就不必处理这些问题。它从不规划、点击或输入。可选三种模式:</p><ul><li><strong>自动</strong>(默认):无需设置。在 Chrome 中,Ternary Bonsai 2 2B Vision 下载完成后,用它检查侧边栏任务以及计划监控和计划任务是否真正完成。当 WebBrain Cloud(Compass)是你的聊天提供商时,改由 Compass 的决策模型回答。其他情况下不使用决策模型。卡片会显示当前使用的是哪个。</li><li><strong>开启</strong>:所有决策都使用你配置的提供商:OpenRouter、TypeSafe、本地 System One 服务器、D1,或 Chrome 中的浏览器内聊天模型。所有决策默认开启。展开<strong>选择哪些决策使用它</strong>可以单独关闭某些决策(验证完成、验证计划监控、验证计划任务完成、快速分类、快速浏览器操作(实验性))并设置阈值。</li><li><strong>关闭</strong>:从不使用决策模型,包括 Compass 的决策模型。聊天模型仍会检查任务是否完成。</li></ul><p>切换模式立即生效;“开启”模式下的提供商字段需要点击<strong>保存</strong>。<strong>测试连接</strong>只用固定示例数据发送一次请求。<strong>重置</strong>会回到自动模式并删除已保存的决策密钥。云端决策提供商会收到有限的任务与页面数据,可能产生费用;严格秘密模式会禁用决策模型。在这些模式推出前已开启决策外包的配置会按“开启”继续工作,并保留原有开关。</p><figure class="shot"><a href="/docs/assets/screenshots/settings-decision-models.jpg"><img src="/docs/assets/screenshots/settings-decision-models.jpg" alt="决策模型英文设置界面,选中自动,状态行显示尚未使用决策模型"></a><figcaption>全新安装时的自动模式:尚未下载任何模型,因此没有使用决策模型(除非当前提供商是 WebBrain Cloud,此时由 Compass 的决策模型回答)。只有选择“开启”时才会显示提供商字段。</figcaption></figure>
</section>
<section class="doc-section" id="memory"><div class="eyebrow">按需使用</div><h2>记忆:决定哪些信息长期保留</h2><figure class="shot"><a href="/docs/assets/screenshots/settings-memory.jpg"><img src="/docs/assets/screenshots/settings-memory.jpg" alt="WebBrain 记忆设置英文界面,显示加密云同步与个人资料自动填充"></a><figcaption>记忆标签页包含加密同步、个人资料自动填充和用户记忆三种不同功能。</figcaption></figure><ul><li><strong>加密云同步</strong>面向 WebBrain Compass 会员;支持的提供商密钥、个人资料和记忆会在上传前用同步密码加密。聊天历史与 OAuth 登录不会同步。</li><li><strong>个人资料自动填充</strong>以明文保存在当前浏览器配置中,启用后会发送给当前模型提供商。</li><li><strong>用户记忆</strong>保存稳定偏好;<code>/memory --add</code> 会立即保存,自动学习是可选项。</li></ul><div class="callout danger"><strong class="callout-title">不要把记忆当作密码管理器</strong><p>不要在个人资料或用户记忆中存放密码、API 密钥、令牌、恢复码等秘密。</p></div></section>
<section class="doc-section" id="skills"><div class="eyebrow">信任决定</div><h2>技能:附加指令与工具</h2><p>技能可以把指令加入系统提示;含 <code>webbrain-tools</code> 清单的技能还可暴露 HTTP 或下载任务工具。导入本身就是信任决定,只导入你信任的来源。</p></section>