Reimplement skills loading using SkillsManager + skills/list op. (#7914)

refactor the way we load and manage skills:
1. Move skill discovery/caching into SkillsManager and reuse it across
sessions.
2. Add the skills/list API (Op::ListSkills/SkillsListResponse) to fetch
skills for one or more cwds. Also update app-server for VSCE/App;
3. Trigger skills/list during session startup so UIs preload skills and
handle errors immediately.

codex-rs/docs/protocol_v1.md

@@ -68,6 +68,7 @@ For complete documentation of the `Op` and `EventMsg` variants, refer to [protoc
   - `Op::UserInput` – Any input from the user to kick off a `Task`
   - `Op::Interrupt` – Interrupts a running task
   - `Op::ExecApproval` – Approve or deny code execution
+  - `Op::ListSkills` – Request skills for one or more cwd values
 - `EventMsg`
   - `EventMsg::AgentMessage` – Messages from the `Model`
   - `EventMsg::ExecApprovalRequest` – Request approval from user to execute a command
@@ -75,6 +76,7 @@ For complete documentation of the `Op` and `EventMsg` variants, refer to [protoc
   - `EventMsg::Error` – A task stopped with an error
   - `EventMsg::Warning` – A non-fatal warning that the client should surface to the user
   - `EventMsg::TurnComplete` – Contains a `response_id` bookmark for last `response_id` executed by the task. This can be used to continue the task at a later point in time, perhaps with additional user input.
+  - `EventMsg::ListSkillsResponse` – Response payload with per-cwd skill entries (`cwd`, `skills`, `errors`)
 
 The `response_id` returned from each task matches the OpenAI `response_id` stored in the API's `/responses` endpoint. It can be stored and used in future `Sessions` to resume threads of work.