Enforce Agent Plugin runtime boundaries (#37027)

## What changed

- Track Agent Plugin manifests through plugin, skill, and MCP loading so their capabilities use format-specific behavior without changing legacy plugins.
- Discover only direct-child skills, exclude app and hook capabilities, isolate MCP data, and reject MCP configuration files that are non-regular or resolve outside the plugin root.
- Bound model-visible skill instructions, plugin instructions, MCP descriptions, schemas, individual tools, and the aggregate Agent Plugin MCP tool set.
- Stop MCP and OAuth redirects when Agent Plugins send configured or authorization headers, while retaining existing redirect behavior for legacy MCP servers.

## Testing

- Add coverage for capability filtering, skill discovery, isolated MCP data and reserved-path expansion, unsafe MCP configuration files, context limits, and redirect handling.

GitOrigin-RevId: c9af66b051269f3226628ca280a58d32c808c38f

codex-rs/tui/src/chatwidget/tests/plan_mode.rs

@@ -1310,6 +1310,7 @@ async fn submit_user_message_emits_structured_plugin_mentions_from_bindings() {
         .set_plugin_mentions(Some(vec![codex_plugin::PluginCapabilitySummary {
             config_name: "sample@test".to_string(),
             display_name: "Sample Plugin".to_string(),
+            plugin_namespace: None,
             description: None,
             has_skills: true,
             mcp_server_names: Vec::new(),