feat(core): support custom model aliases in config.toml

This adds config.toml-defined model aliases that map to provider model slugs while applying alias-specific context settings for the active session.

- added custom_models config entries plus schema and docs coverage
- taught ModelsManager to resolve aliases to a provider-facing request_model while preserving the user-facing alias slug
- applied alias-specific context_window and model_auto_compact_token_limit overrides during model info resolution
- updated session/test plumbing and added regression coverage for alias resolution with local and remote model catalogs

Model selection and per-session context overrides already flow through ModelsManager and Config. Resolving aliases there keeps the provider slug separate from the user-facing alias while reusing the existing override plumbing.

- just write-config-schema
- just fmt
- cargo test -p codex-app-server -p codex-api -p codex-exec -p codex-mcp-server
- cargo test -p codex-tui
- cargo test -p codex-protocol -p codex-core (same two existing seatbelt failures remained in this environment: create_seatbelt_args_with_read_only_git_pointer_file and create_seatbelt_args_with_read_only_git_and_codex_subpaths)
- just fix -p codex-core -p codex-protocol -p codex-app-server -p codex-api -p codex-exec -p codex-mcp-server -p codex-tui

codex-rs/codex-api/tests/models_integration.rs

@@ -54,6 +54,7 @@ async fn models_client_hits_models_endpoint() {
     let response = ModelsResponse {
         models: vec![ModelInfo {
             slug: "gpt-test".to_string(),
+            request_model: None,
             display_name: "gpt-test".to_string(),
             description: Some("desc".to_string()),
             default_reasoning_level: Some(ReasoningEffort::Medium),