feat(app-server): add next prompt suggestion RPC [2 of 3]

[fcoury-oai]

Why

Clients need an explicit v2 API for requesting a next-prompt suggestion from an existing thread. This layer exposes that API on top of the core engine without adding the TUI presentation behavior.

What changed

• Add thread/suggestNextPrompt v2 request/response types and generated JSON/TypeScript schema fixtures.
• Route the new request through the app-server message processor and turn processor.
• Sample suggestions from loaded thread history with cancellation support and no tool exposure.
• Add focused app-server coverage for loaded-history sampling and in-flight cancellation.
• Document the new method in the app-server README.

Testing

• cargo test -p codex-app-server-protocol
• cargo test -p codex-app-server thread_suggest_next_prompt
• CARGO_TARGET_DIR=/private/tmp/codex-next-suggestion-stack-target ./tools/argument-comment-lint/run.py -p codex-core -p codex-app-server-protocol -p codex-app-server -p codex-tui

Generated/schema churn: yes, app-server v2 JSON and TypeScript schema fixtures are updated in this PR.

Stack

1. #24126 next-prompt suggestion engine
2. feat(app-server): add next prompt suggestion RPC [2 of 3] #24127 next-prompt app-server RPC (this PR)
3. #23976 next-prompt TUI

[chatgpt-codex-connector]

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: ebf3205853

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".