docs: fix remaining multi-step "Settings → Models" instructions

Addresses cubic P2s on #1330: two sections spelled the old path out as
separate steps ("Click Settings… Select Models tab"), plus a few
shorthand "in Settings" mentions that refer to the Models page.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_012heLWVTmopC5FkipUgnvsN

Author: lfnovo

docs/0-START-HERE/quick-start-cloud.md

@@ -103,9 +103,8 @@ Your provider's models are now available!
 
 ## Step 5: Configure Your Model (1 min)
 
-1. Go to **Settings** (gear icon)
-2. Navigate to **Models**
-3. Select your provider's model:
+1. In the sidebar, open **Manage** → **Models**
+2. Select your provider's model:
 
 | Provider | Recommended Model | Notes |
 |----------|-------------------|-------|

docs/1-INSTALLATION/index.md

@@ -124,7 +124,7 @@ Before installing, you'll need:
 
 Once you're up and running:
 
-1. **Configure Models** - Choose your AI provider in Settings
+1. **Configure Models** - Choose your AI provider in Manage → Models
 2. **Create First Notebook** - Start organizing research
 3. **Add Sources** - PDFs, web links, documents
 4. **Explore Features** - Chat, search, transformations

docs/1-INSTALLATION/windows-native.md

@@ -228,7 +228,7 @@ GOOGLE_API_KEY=your-key-here
 
 ## Available AI Models
 
-Once running, add models in Settings. Common model names:
+Once running, add models in Manage → Models. Common model names:
 
 | Provider  | Models                                                       |
 | --------- | ------------------------------------------------------------ |

docs/3-USER-GUIDE/api-configuration.md

@@ -70,8 +70,8 @@ API keys stored in the database are encrypted using Fernet (AES-128-CBC + HMAC-S
 
 ## Accessing Credential Configuration
 
-1. Click **Settings** in the navigation bar
-2. Select **Models** tab
+1. In the sidebar, find the **Manage** section
+2. Click **Models**
 3. You'll see existing credentials and an **Add Credential** button
 
 ```

docs/5-CONFIGURATION/ai-providers.md

@@ -61,7 +61,7 @@ Heavy use: $50-100+/month
 ```
 
 **Troubleshooting:**
-- "Invalid API key" → Check key starts with "sk-proj-" and test the connection in Settings
+- "Invalid API key" → Check key starts with "sk-proj-" and test the connection in Manage → Models
 - "Rate limit exceeded" → Wait or upgrade account
 - "Model not available" → Try gpt-4o-mini instead, or re-discover models
 
@@ -109,7 +109,7 @@ Opus: $10-50+/month
 - Fast processing
 
 **Troubleshooting:**
-- "Invalid API key" → Check it starts with "sk-ant-" and test in Settings
+- "Invalid API key" → Check it starts with "sk-ant-" and test in Manage → Models
 - "Overloaded" → Anthropic is busy, retry later
 - "Model unavailable" → Re-discover models from the credential
 

docs/5-CONFIGURATION/index.md

@@ -23,7 +23,7 @@ Three things:
 - **Google Gemini** (multi-modal, long context)
 - **Groq** (ultra-fast inference)
 
-Setup: Get API key → Add credential in Settings UI → Done
+Setup: Get API key → Add credential in Manage → Models → Done
 
 → Go to **[AI Providers Guide](ai-providers.md)**
 

docs/5-CONFIGURATION/openai-compatible.md

@@ -41,7 +41,7 @@ Open Notebook can connect to any server using this format.
 3. Download a model (e.g., Llama 3)
 4. Start the local server (default: port 1234)
 
-### Step 2: Configure in Settings UI (Recommended)
+### Step 2: Configure in Manage → Models (Recommended)
 
 1. Go to **Manage** → **Models**
 2. Click **Add Credential** → Select **OpenAI-Compatible**