3 files changed, 28 insertions, 3 deletions
diff --git a/packages/frontend/src/lib/cache-warming.svelte.ts b/packages/frontend/src/lib/cache-warming.svelte.ts
index cda3fd1..0253c08 100644
--- a/packages/frontend/src/lib/cache-warming.svelte.ts
+++ b/packages/frontend/src/lib/cache-warming.svelte.ts
@@ -41,6 +41,12 @@ export interface WarmRequestParams {
 	keyId: string | null;
 	modelId: string | null;
 	agentModels: AgentModelEntry[] | null;
+	/**
+	 * The SAME reasoning effort the next real turn would use. It drives the
+	 * Anthropic thinking providerOptions, which is a message-cache key — warming
+	 * must match it so it refreshes the bucket the real message reads.
+	 */
+	reasoningEffort: string | null;
 }
 
 /** Reactive, per-tab warming UI state (read by the Chat Settings debug strip). */
@@ -177,6 +183,7 @@ export function createCacheWarmingStore() {
 					...(params?.keyId ? { keyId: params.keyId } : {}),
 					...(params?.modelId ? { modelId: params.modelId } : {}),
 					...(params?.agentModels ? { agentModels: params.agentModels } : {}),
+					...(params?.reasoningEffort ? { reasoningEffort: params.reasoningEffort } : {}),
 				}),
 			});
 			// A newer cancel/fire superseded this request — drop its result so it
diff --git a/packages/frontend/src/lib/tabs.svelte.ts b/packages/frontend/src/lib/tabs.svelte.ts
index a0125ef..ca04e62 100644
--- a/packages/frontend/src/lib/tabs.svelte.ts
+++ b/packages/frontend/src/lib/tabs.svelte.ts
@@ -251,7 +251,12 @@ export function createTabStore() {
 	cacheWarming.setRequestResolver((tabId) => {
 		const t = getTabById(tabId);
 		if (!t) return null;
-		return { keyId: t.keyId, modelId: t.modelId, agentModels: t.agentModels };
+		return {
+			keyId: t.keyId,
+			modelId: t.modelId,
+			agentModels: t.agentModels,
+			reasoningEffort: t.reasoningEffort,
+		};
 	});
 
 	$effect.root(() => {
diff --git a/packages/frontend/tests/cache-warming.test.ts b/packages/frontend/tests/cache-warming.test.ts
index 012efb1..583d563 100644
--- a/packages/frontend/tests/cache-warming.test.ts
+++ b/packages/frontend/tests/cache-warming.test.ts
@@ -98,7 +98,12 @@ describe("firing cadence", () => {
 		const fetchMock = makeFetchOk({ inputTokens: 1000, cacheReadTokens: 900 });
 		vi.stubGlobal("fetch", fetchMock);
 
-		store.setRequestResolver(() => ({ keyId: "k", modelId: "m", agentModels: null }));
+		store.setRequestResolver(() => ({
+			keyId: "k",
+			modelId: "m",
+			agentModels: null,
+			reasoningEffort: "high",
+		}));
 		store.setEnabled("tab-1", true);
 
 		await vi.advanceTimersByTimeAsync(WARM_INTERVAL_MS);
@@ -108,7 +113,15 @@ describe("firing cadence", () => {
 		const [url, opts] = (fetchMock as unknown as { mock: { calls: unknown[][] } }).mock
 			.calls[0] as [string, { body: string }];
 		expect(url).toContain("/chat/warm");
-		expect(JSON.parse(opts.body)).toMatchObject({ tabId: "tab-1", keyId: "k", modelId: "m" });
+		// The request forwards the SAME effort the real turn uses — it's an
+		// Anthropic message-cache key, so warming must match it to refresh the
+		// bucket the next real message reads.
+		expect(JSON.parse(opts.body)).toMatchObject({
+			tabId: "tab-1",
+			keyId: "k",
+			modelId: "m",
+			reasoningEffort: "high",
+		});
 
 		const s = store.stateFor("tab-1");
 		expect(s.lastPct).toBe(90); // 900 / 1000