Expose exact per-response usage in raw app-server events (#32985)

## Why

Clients that account for individual upstream Responses API calls need the exact
usage for each completion rather than accumulated or estimated thread usage.

## What changed

- Add the opt-in `rawResponse/completed` app-server notification with the
  `threadId`, `turnId`, `responseId`, and upstream `usage` payload.
- Emit the transient event for normal turns and compaction requests when
  `experimentalRawEvents` is enabled. The event is not persisted or replayed,
  and `usage` is `null` when the upstream response omits it.
- Export the notification in the app-server schemas and document its behavior.

## Testing

- Cover exact token breakdowns for turn and compaction completions.

GitOrigin-RevId: 49040a060bf1784c1ff1dd62112efb4a778428c4

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

@@ -1375,6 +1375,18 @@ pub struct ThreadTokenUsageUpdatedNotification {
     pub token_usage: ThreadTokenUsage,
 }
 
+/// Internal-only notification containing the exact usage from one upstream
+/// Responses API completion.
+#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
+#[serde(rename_all = "camelCase")]
+#[ts(export_to = "v2/")]
+pub struct RawResponseCompletedNotification {
+    pub thread_id: String,
+    pub turn_id: String,
+    pub response_id: String,
+    pub usage: Option<TokenUsageBreakdown>,
+}
+
 #[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
 #[serde(rename_all = "camelCase")]
 #[ts(export_to = "v2/")]