app-server-protocol: remove PermissionProfile from API (#22924)

## Why

The app server API should expose permission profile identity, not the
lower-level runtime permission model. `PermissionProfile` is the
compiled sandbox/network representation that the server uses internally;
exposing it through app-server-protocol forces clients to understand
details that should remain implementation-level.

The API boundary should prefer `ActivePermissionProfile`: a stable
profile id, plus future parent-profile metadata, that clients can pass
back when they want to select the same active permissions. This also
avoids schema generation collisions between the app-server v2 API type
space and the core protocol model.

Incidentally, while PR makes a number of changes to `command/exec`, note
that we are hoping to deprecate this API in favor of `process/spawn`, so
we don't need to be too finicky about these changes.

## What Changed

- Removed `PermissionProfile` from the app-server-protocol API surface,
including generated schema and TypeScript exports.
- Changed `CommandExecParams.permissionProfile` to
`ActivePermissionProfile`.
- Resolve command exec profile ids through `ConfigManager` for the
command cwd, matching turn override selection semantics.
- Updated downstream TUI tests/helpers to use core permission types
directly instead of app-server-protocol `PermissionProfile` shims.

codex-rs/protocol/src/models.rs

@@ -353,6 +353,10 @@ impl ActivePermissionProfile {
             extends: None,
         }
     }
+
+    pub fn read_only() -> Self {
+        Self::new(BUILT_IN_PERMISSION_PROFILE_READ_ONLY)
+    }
 }
 
 impl Default for PermissionProfile {