Expose MCP provenance to tool lifecycle extensions (#40976)

## What changed

- Add optional `McpToolContext` metadata to `ToolStartInput`, exposing the
  model-visible MCP tool details and its source classification without exposing
  the executable client.
- Classify MCP calls as connectors, configured servers, plugin servers,
  executor-selected plugins, or other registrations based on the prepared call.
- Prepare each MCP call before notifying tool lifecycle contributors and reuse
  that same call for execution so the callback describes the call that runs.

## Testing

- Cover host-owned connector calls and extension-owned Apps server calls,
  including their distinct provenance and executed tool names.

GitOrigin-RevId: efd23f511b1045ffdd96349d621ad62365569b2b

codex-rs/codex-mcp/src/binding.rs

@@ -236,6 +236,18 @@ impl PreparedMcpCall {
         &self.server_name
     }
 
+    /// Returns whether this call is bound to the host-owned Codex Apps server.
+    pub fn is_host_owned_apps(&self) -> bool {
+        self.config
+            .mcp_server_catalog
+            .server(&self.server_name)
+            .is_some_and(|registration| {
+                registration
+                    .source()
+                    .is_host_owned_apps(&self.server_name, registration.config())
+            })
+    }
+
     pub fn server_origin(&self) -> Option<&str> {
         self.server_metadata
             .origin