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/core/src/compact_tests.rs

@@ -20,11 +20,7 @@ async fn process_compacted_history_with_test_session(
         crate::session::step_context::StepContext::for_test(Arc::clone(&turn_context));
     let world_state = Arc::new(session.build_world_state_for_step(&step_context).await);
     let initial_context = session
-        .build_initial_context_with_world_state_and_mcp(
-            &turn_context,
-            world_state.as_ref(),
-            step_context.mcp.as_ref(),
-        )
+        .build_initial_context_with_world_state(&turn_context, world_state.as_ref())
         .await;
     let initial_context_injection = InitialContextInjection::BeforeLastUserMessage {
         world_state,