fix: reconcile live cacheStats to DB truth on turn-sealed

Addresses the live-accumulator overshoot a Gemini review surfaced: the
frontend adds every streamed usage event to cacheStats, but a rate-limited
fallback attempt's usage is discarded server-side (never persisted). Live
numbers overshot until a reload re-seeded from the DB aggregate.

Fix: turn-sealed (emitted AFTER the atomic usage-row write) now carries the
authoritative getUsageStatsForTab aggregate. The store REPLACES (not adds)
cacheStats with it every turn — landing the just-sealed turn's usage AND
self-healing any live drift, including the discarded-fallback overshoot. No
extra round-trip (piggybacks turn-sealed); idempotent in the happy path.

- core: add UsageStats type; getUsageStatsForTab returns it; turn-sealed gains
  optional usageStats field.
- api: agent-manager reads getUsageStatsForTab post-flush and attaches it to
  the turn-sealed emit (try/catch: omit on DB error).
- frontend: turn-sealed handler replaces cacheStats (undefined ⇒ untouched
  back-compat; null ⇒ clear).

Tests: frontend reconcile/self-heal/back-compat/null-clear; api turn-sealed
carries aggregate. 509 -> 514 passing; typecheck + biome green.

1 files changed, 14 insertions, 4 deletions

diff --git a/packages/frontend/src/lib/tabs.svelte.ts b/packages/frontend/src/lib/tabs.svelte.ts
index 54f17d9..65e35a8 100644
--- a/packages/frontend/src/lib/tabs.svelte.ts
+++ b/packages/frontend/src/lib/tabs.svelte.ts
@@ -756,10 +756,11 @@ export function createTabStore() {
 			modelId?: string | null;
 			parentTabId?: string | null;
 			// Backend usage aggregate (GET /tabs). Structurally identical to
-			// CacheStats, so it seeds `cacheStats` directly on reload. Seeding
-			// happens ONLY here (hydrate runs when tabs.length === 0, i.e. a true
-			// reload) — never on `statuses` reconnect or `turn-sealed` — so the
-			// persisted aggregate and in-session live `usage` events never overlap.
+			// CacheStats, so it seeds `cacheStats` directly on reload. This is the
+			// initial seed (hydrate runs only when tabs.length === 0, i.e. a true
+			// reload); thereafter `turn-sealed` REPLACES cacheStats with the same
+			// aggregate each turn, keeping the live accumulator reconciled to the DB
+			// truth. Neither path ADDS to live events, so there is no double-count.
 			usageStats?: CacheStats | null;
 		}> = [];
 		try {
@@ -934,6 +935,15 @@ export function createTabStore() {
 				// tail into the sealed chunk log (refetch real seqs), preserving any
 				// newer in-flight turn. Deferred while scrolled up.
 				reconcileSealedTurn(tabId, event.turnId);
+				// Reconcile cacheStats to the DB source-of-truth carried on the event.
+				// REPLACE (not add): the aggregate already includes every persisted
+				// usage row for this tab, so this both lands the just-sealed turn's
+				// usage AND self-heals any live overshoot (e.g. a rate-limited
+				// fallback attempt streamed usage live but was discarded server-side).
+				// `usageStats === undefined` (older backend) leaves cacheStats as-is.
+				if (event.usageStats !== undefined) {
+					updateTab(tabId, { cacheStats: event.usageStats ?? undefined });
+				}
 				break;
 			}
 			case "statuses": {