Add Luna Reserve usage fallback to the TUI (#42372)

## Why

When ordinary included usage is exhausted, eligible users need a way to keep working with the backend-provided Luna Reserve quota and return to their previous model once ordinary usage recovers.

## What changed

- Automatically switch eligible TUI tasks to Luna Reserve after an authoritative account usage read, preserving the prior model and reasoning effort per task.
- Restrict model selection while on Reserve to its supported reasoning levels, keep queued turns on the accepted model, and restore the saved model after a fresh read confirms recovery.
- Surface Reserve usage in the composer and `/status`, and expose `normalModelSlug` in app-server rate-limit snapshots so clients can use the associated model's display metadata without changing the request model.
- Poll account limits more frequently near exhaustion and retain compatibility with app servers that only accept the legacy null request parameters.

## Testing

- Added coverage for Reserve entry, queued-turn handling, task reconstruction, recovery authorization, account changes, model selection, usage rendering, and banner dismissal.

GitOrigin-RevId: 46a435e9531051f8cec3f6a46c4b9f7cfa479747
This commit is contained in:
dhruvgupta-oai authored and copyberry committed 2026-09-02 21:50:51 +00:00
1 parent 76f47103fe
commit 5037919777
76 files changed
+1907 -135

No files matched your search

@@ -26,6 +26,8 @@ impl ChatWidget {
.set_queue_submissions(/*queue_submissions*/ false);
if previous_thread_id != self.thread_id {
self.backend_banner_notice_model = None;
self.automatic_model_switch_state =
backend_banners::AutomaticModelSwitchState::default();
self.pending_automatic_thread_names.clear();
self.review.recent_auto_review_denials = RecentAutoReviewDenials::default();
self.clear_thread_usage_state();
@@ -114,6 +116,19 @@ impl ChatWidget {
.set_active_reasoning_effort_baseline(effort.as_ref());
self.refresh_model_display();
self.refresh_status_surfaces();
if previous_thread_id != self.thread_id
&& self.should_prefetch_rate_limits()
&& (self.current_model() == crate::model_catalog::LUNA_RESERVE_MODEL
|| self.backend_banner_fallback().is_some())
{
// Reconcile this task with retained account state before sending its initial/queued
// prompt. Do not wait for the next usage poll after /new, /resume or a thread switch.
self.hold_rate_limit_recovery();
self.app_event_tx
.send(AppEvent::ApplyBackendBannerFallback {
thread_id: session.thread_id,
});
}
self.sync_service_tier_commands();
self.sync_personality_command_enabled();
self.sync_plugins_command_enabled();