Centralize thread MCP state in McpRuntime (#34930)

## What changed

- Make `McpRuntime` own the published MCP configuration, connections, elicitation routing, and selected capability roots for a thread.
- Capture immutable MCP bindings for model steps and tool calls so in-flight work keeps a consistent connection set and approval authority while refreshed state is published atomically.
- Mark MCP state dirty when relevant configuration, plugins, environments, authentication, or elicitation capabilities change, then rebuild it before the next sampling request or out-of-band MCP operation.
- Separate config reloads from server invalidation: `ReloadMcpConfig` applies resolved MCP inputs, while `RefreshMcpServers` requests reinitialization from the thread's latest state.

## Testing

- Cover refreshed state visibility for existing turns, stable step bindings, current approval authority, cancelled refresh retries, resource-client reconciliation, and Apps recovery between sampling requests.

GitOrigin-RevId: 59eabb1aa8dc083426bd18ef4d3630508f376401

codex-rs/app-server/src/effective_plugin_change.rs

@@ -32,16 +32,11 @@ pub(crate) fn effective_plugins_changed_callback(
         thread_manager.skills_service().clear_cache();
 
         let refresh_thread_manager = Arc::clone(&thread_manager);
-        let refresh_config_manager = config_manager.clone();
         tokio::spawn(async move {
             if refresh_thread_manager.list_thread_ids().await.is_empty() {
                 return;
             }
-            crate::mcp_refresh::queue_best_effort_refresh(
-                &refresh_thread_manager,
-                &refresh_config_manager,
-            )
-            .await;
+            crate::mcp_refresh::invalidate_loaded_threads(&refresh_thread_manager).await;
         });
 
         if change.materialized_remote_plugins.is_empty() {