2- Use string service tiers in session protocol (#20971)

## Summary
- break service tier session/op/app-server protocol fields from the
closed enum to string tier ids
- send the service tier string directly through model requests, prewarm,
compaction, memories, and TUI/app-server turn starts
- regenerate app-server protocol JSON/TypeScript schemas, removing the
standalone ServiceTier TS enum

## Verification
- just fmt
- cargo check -p codex-core -p codex-app-server -p codex-tui
- just write-app-server-schema

---------

Co-authored-by: Codex <noreply@openai.com>

codex-rs/core/src/codex_thread.rs

@@ -11,7 +11,6 @@ use codex_protocol::config_types::ApprovalsReviewer;
 use codex_protocol::config_types::CollaborationMode;
 use codex_protocol::config_types::Personality;
 use codex_protocol::config_types::ReasoningSummary;
-use codex_protocol::config_types::ServiceTier;
 use codex_protocol::config_types::WindowsSandboxLevel;
 use codex_protocol::error::CodexErr;
 use codex_protocol::error::Result as CodexResult;
@@ -53,7 +52,7 @@ use codex_rollout::state_db::StateDbHandle;
 pub struct ThreadConfigSnapshot {
     pub model: String,
     pub model_provider_id: String,
-    pub service_tier: Option<ServiceTier>,
+    pub service_tier: Option<String>,
     pub approval_policy: AskForApproval,
     pub approvals_reviewer: ApprovalsReviewer,
     pub permission_profile: PermissionProfile,
@@ -91,7 +90,7 @@ pub struct CodexThreadTurnContextOverrides {
     pub model: Option<String>,
     pub effort: Option<Option<ReasoningEffort>>,
     pub summary: Option<ReasoningSummary>,
-    pub service_tier: Option<Option<ServiceTier>>,
+    pub service_tier: Option<Option<String>>,
     pub collaboration_mode: Option<CollaborationMode>,
     pub personality: Option<Personality>,
 }