Merge branch 'main' into custom-tags

docs/clients/client.mdx

@@ -91,7 +91,7 @@ For more control over connection details (like headers for SSE, environment vari
 
 ### Multi-Server Clients
 
-<VersionBadge version="2.3.6" />
+<VersionBadge version="2.4.0" />
 
 FastMCP supports creating clients that connect to multiple MCP servers through a single client interface using a standard MCP configuration format (`MCPConfig`). This configuration approach makes it easy to connect to multiple specialized servers or create composable systems with a simple, declarative syntax.
 

docs/clients/transports.mdx

@@ -323,7 +323,7 @@ Communication happens through efficient in-memory queues, making it very fast an
 
 ### MCPConfig Transport
 
-<VersionBadge version="2.3.6" />
+<VersionBadge version="2.4.0" />
 
 - **Class:** `fastmcp.client.transports.MCPConfigTransport`
 - **Inferred From:** An instance of `MCPConfig` or a dictionary matching the MCPConfig schema

docs/servers/composition.mdx

@@ -35,7 +35,7 @@ The choice of importing or mounting depends on your use case and requirements.
 
 FastMCP supports [MCP proxying](/patterns/proxy), which allows you to mirror a local or remote server in a local FastMCP instance. Proxies are fully compatible with both importing and mounting.
 
-<VersionBadge version="2.3.6" />
+<VersionBadge version="2.4.0" />
 
 You can also create proxies from configuration dictionaries that follow the MCPConfig schema, which is useful for quickly connecting to one or more remote servers. See the [Proxy Servers documentation](/servers/proxy#configuration-based-proxies) for details on configuration-based proxying. Note that MCPConfig follows an emerging standard and its format may evolve over time.
 

docs/servers/context.mdx

@@ -228,8 +228,8 @@ async def analyze_sentiment(text: str, ctx: Context) -> dict:
     # Create a sampling prompt asking for sentiment analysis
     prompt = f"Analyze the sentiment of the following text as positive, negative, or neutral. Just output a single word - 'positive', 'negative', or 'neutral'. Text to analyze: {text}"
     
-    # Send the sampling request to the client's LLM
-    response = await ctx.sample(prompt)
+    # Send the sampling request to the client's LLM (provide a hint for the model you want to use)
+    response = await ctx.sample(prompt, model_preferences="claude-3-sonnet")
     
     # Process the LLM's response
     sentiment = response.text.strip().lower()
@@ -247,11 +247,12 @@ async def analyze_sentiment(text: str, ctx: Context) -> dict:
 
 **Method signature:**
 
-- **`ctx.sample(messages: str | list[str | SamplingMessage], system_prompt: str | None = None, temperature: float | None = None, max_tokens: int | None = None) -> TextContent | ImageContent`**
+- **`ctx.sample(messages: str | list[str | SamplingMessage], system_prompt: str | None = None, temperature: float | None = None, max_tokens: int | None = None, model_preferences: ModelPreferences | str | list[str] | None = None) -> TextContent | ImageContent`**
   - `messages`: A string or list of strings/message objects to send to the LLM
   - `system_prompt`: Optional system prompt to guide the LLM's behavior
   - `temperature`: Optional sampling temperature (controls randomness)
   - `max_tokens`: Optional maximum number of tokens to generate (defaults to 512)
+  - `model_preferences`: Optional model selection preferences (e.g., a model hint string, list of hints, or a ModelPreferences object)
   - Returns the LLM's response as TextContent or ImageContent
 
 When providing a simple string, it's treated as a user message. For more complex scenarios, you can provide a list of messages with different roles.

docs/servers/proxy.mdx

@@ -106,7 +106,7 @@ proxy = FastMCP.as_proxy(
 
 ### Configuration-Based Proxies
 
-<VersionBadge version="2.3.6" />
+<VersionBadge version="2.4.0" />
 
 You can create a proxy directly from a configuration dictionary that follows the MCPConfig schema. This is useful for quickly setting up proxies to remote servers without manually configuring each connection detail.