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/config/mod.rs

@@ -1632,6 +1632,10 @@ impl Config {
                 .features
                 .enabled(Feature::SkillMcpDependencyInstall),
             approval_policy: self.permissions.approval_policy.clone(),
+            permission_profile: self.permissions.permission_profile().clone(),
+            config_layer_stack: self.config_layer_stack.clone(),
+            approvals_reviewer: self.approvals_reviewer,
+            environment_cwds: HashMap::new(),
             codex_linux_sandbox_exe: self.codex_linux_sandbox_exe.clone(),
             use_legacy_landlock: self.features.use_legacy_landlock(),
             apps_enabled: self.features.enabled(Feature::Apps),