feat: embed AI travel chat in collection recommendations

docs/docs/guides/travel_agent.md

@@ -2,6 +2,8 @@
 
 Voyage includes a **Travel Agent** interface exposed through an **MCP-compatible HTTP endpoint**. This lets external MCP clients read and manage trip itineraries programmatically for authenticated users.
 
+> **Note**: This is the *external* programmatic interface. For the *in-app* AI chat assistant (conversational trip planning), see the AI Travel Chat section in [How to use Voyage](../usage/usage.md#ai-travel-chat).
+
 ## Endpoint
 
 - Default path: `api/mcp`

docs/docs/intro/voyage_overview.md

@@ -23,7 +23,8 @@ Voyage is a full-fledged travel companion. With Voyage, you can log your adventu
   - Locations and itineraries can be shared via a public link or directly with other Voyage users.
   - Collaborators can view and edit shared itineraries (collections), making planning a breeze.
 - **Customizable Themes** 🎨: Choose from 10 built-in themes including Light, Dark, Dim, Night, Forest, Aqua, Catppuccin Mocha, Aesthetic Light, Aesthetic Dark, and Northern Lights. Theme selection persists across sessions.
-- **Travel Agent (MCP) access** 🤖: Voyage exposes an authenticated MCP endpoint so external clients can list collections, inspect itineraries, create itinerary items, and reorder trip timelines. See the [Travel Agent (MCP) guide](../guides/travel_agent.md).
+- **AI Travel Chat** 🤖: An AI-powered chat assistant lives inside Collections → Recommendations, letting you brainstorm destinations and plan trips conversationally. The provider list is dynamic — backed by LiteLLM's full provider catalog — and includes OpenAI, Anthropic, Gemini, Ollama, Groq, Mistral, GitHub Models, OpenRouter, and OpenCode Zen. Configure your preferred provider's API key in Settings.
+- **Travel Agent (MCP) access** 🔧: Voyage exposes an authenticated MCP endpoint so external clients can list collections, inspect itineraries, create itinerary items, and reorder trip timelines. See the [Travel Agent (MCP) guide](../guides/travel_agent.md).
 
 ## Why Voyage?
 

docs/docs/usage/usage.md

@@ -22,6 +22,10 @@ The term "Location" is now used instead of "Adventure" - the usage remains the s
 - **Trail**: a trail is a path or route that is associated with a location. Trails can be used to document hiking paths, biking routes, or any other type of journey that has a specific path. Trails are linked to locations either by link to an external service (e.g., AllTrails) or from the [Wanderer](/docs/configuration/wanderer_integration) integration. When linked via the Wanderer integration, trails can provide additional context and information about the journey such as distance and elevation gain.
 - **Activity**: an activity is what you actually do at a location. This can include things like hiking, biking, skiing, kayaking, or any other outdoor activity. Activities are associated with a visit and include fields such as the type of activity, time, distance, and trail taken. They can be manually entered or imported from the [Strava](/docs/configuration/strava_integration) integration. Once an activity is added, it will appear on the location map based on the data from the GPX file.
 
+#### AI Travel Chat
+
+The AI travel chat is embedded in the **Collections → Recommendations** view. Select a collection, switch to the Recommendations tab, and use the chat to brainstorm destinations, ask for travel advice, or get location suggestions. The chat supports multiple LLM providers — configure your API key in **Settings → API Keys** and pick a provider from the dropdown in the chat interface. The provider list is loaded dynamically from the backend, so any provider supported by LiteLLM (plus OpenCode Zen) is available.
+
 #### Collections
 
 - **Collection**: a collection is a way to group locations together. Collections are flexible and can be used in many ways. When no start or end date is added to a collection, it acts like a folder to group locations together. When a start and end date is added to a collection, it acts like a trip to group locations together that were visited during that time period. With start and end dates, the collection is transformed into a full itinerary with a timeline-style day view — each day displays numbered stops as compact cards (without image banners), connector rows between consecutive locations showing distance and travel time via OSRM routing (walking if ≤ 20 min, driving otherwise) with automatic haversine fallback when OSRM is unavailable, and a single `+ Add` control for inserting new places. Lodging placement follows directional rules: on check-in day it appears after the last stop, on check-out day it appears before the first stop, and on days with no locations a single lodging card is shown (or two cards when a checkout and checkin are different lodgings). Connector rows link lodging to adjacent locations. Day-level quick actions include Auto-fill (populates an empty itinerary from dated records) and Optimize (nearest-neighbor route ordering for coordinate-backed stops). The day date pill displays a weather temperature summary when available, with graceful fallback if weather data is unavailable. The itinerary also includes a map showing the route taken between locations. Your most recently updated collections also appear on the dashboard. For example, you could have a collection for a trip to Europe with dates so you can plan where you want to visit, a collection of local hiking trails, or a collection for a list of restaurants you want to try.