Show estimated thread usage in /status (#38281)

## What changed

- Extend `account/usage/read` with an optional `threadId` request and a
  backward-compatible `threadUsage` response containing estimated credits,
  optional USD cost, and model, reasoning, speed, and token breakdowns.
- Fetch thread usage for eligible Business and Enterprise plans when `/status`
  is opened, then update the rendered status card asynchronously.
- Preserve terminal scrollback when replacing a visible status-card tail, and
  append a refreshed card when the original tail can no longer be updated.

## Testing

- Add app-server coverage for authentication, canonical thread IDs,
  unavailable billing routes, and malformed IDs.
- Add TUI coverage for usage formatting, stale responses, retries, history
  updates, terminal reflow, and scrollback preservation.

GitOrigin-RevId: 49300914b3fba917c0f08e8595363e04e5ba6d37

codex-rs/app-server-protocol/src/protocol/v2/account.rs

@@ -1,3 +1,4 @@
+use super::ThreadUsage;
 use crate::JsonSchema;
 use crate::TS;
 use crate::protocol::common::AuthMode;
@@ -383,12 +384,27 @@ pub enum ConsumeAccountRateLimitResetCreditOutcome {
     AlreadyRedeemed,
 }
 
+#[derive(Serialize, Deserialize, Debug, Clone, Default, PartialEq, Eq, JsonSchema, TS)]
+#[serde(rename_all = "camelCase")]
+#[ts(export_to = "v2/")]
+pub struct GetAccountTokenUsageParams {
+    /// When present, read estimated usage for this thread instead of account-wide token activity.
+    #[ts(optional = nullable)]
+    pub thread_id: Option<String>,
+}
+
+pub type NullableGetAccountTokenUsageParams = Option<GetAccountTokenUsageParams>;
+
 #[derive(Serialize, Deserialize, Debug, Clone, PartialEq, Eq, JsonSchema, TS)]
 #[serde(rename_all = "camelCase")]
 #[ts(export_to = "v2/")]
 pub struct GetAccountTokenUsageResponse {
     pub summary: AccountTokenUsageSummary,
     pub daily_usage_buckets: Option<Vec<AccountTokenUsageDailyBucket>>,
+    /// Estimated usage when a thread was requested and its billing route is available.
+    #[serde(default)]
+    #[ts(optional, as = "Option<Option<ThreadUsage>>")]
+    pub thread_usage: Option<ThreadUsage>,
 }
 
 #[derive(Serialize, Deserialize, Debug, Clone, PartialEq, Eq, JsonSchema, TS)]

codex-rs/app-server-protocol/src/protocol/v2/mod.rs

@@ -26,6 +26,7 @@ mod remote_control;
 mod review;
 mod thread;
 mod thread_data;
+mod thread_usage;
 mod turn;
 mod windows_sandbox;
 
@@ -56,6 +57,7 @@ pub use review::*;
 pub use shared::*;
 pub use thread::*;
 pub use thread_data::*;
+pub use thread_usage::*;
 pub use turn::*;
 pub use windows_sandbox::*;
 

codex-rs/app-server-protocol/src/protocol/v2/thread_usage.rs

@@ -0,0 +1,29 @@
+use crate::JsonSchema;
+use crate::TS;
+use serde::Deserialize;
+use serde::Serialize;
+
+#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, Eq, JsonSchema, TS)]
+#[serde(rename_all = "camelCase")]
+#[ts(export_to = "v2/")]
+pub struct ThreadUsage {
+    pub thread_id: String,
+    pub estimated_usage_credits_micros: i64,
+    pub estimated_usage_usd_micros: Option<i64>,
+    pub groups: Vec<ThreadUsageBreakdownGroup>,
+}
+
+#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, Eq, JsonSchema, TS)]
+#[serde(rename_all = "camelCase")]
+#[ts(export_to = "v2/")]
+pub struct ThreadUsageBreakdownGroup {
+    pub model: Option<String>,
+    pub reasoning_effort: Option<String>,
+    pub speed: Option<String>,
+    pub estimated_usage_credits_micros: i64,
+    pub net_new_input_tokens: Option<i64>,
+    pub cached_input_tokens: Option<i64>,
+    pub input_tokens: Option<i64>,
+    pub output_tokens: Option<i64>,
+    pub total_tokens: Option<i64>,
+}