feat(context-window): show current/max context usage per tab/model

Add a 'Context Window' sidebar view showing the live context occupancy
(latest request's input+output) against the model's maximum context
window, resolved dynamically from the models.dev catalog.

- core: models.dev catalog module (resolveContextLimit) with disk cache,
  TTL, stale-fallback + offline penalty memo; null for unknown models.
- api: GET /models/context-limit?provider=&modelId=.
- frontend: ContextWindowPanel + computeContextUsage helper; App resolves
  + caches the active model's max (anthropic/opencode-anthropic only);
  percent shown to 2 decimals; degrades to bare token count when max
  unknown.
- tests: core catalog (13), api route (3), frontend helper (6).

2 files changed, 48 insertions, 0 deletions

diff --git a/packages/api/src/routes/models.ts b/packages/api/src/routes/models.ts
index 03c079a..6a0f5dc 100644
--- a/packages/api/src/routes/models.ts
+++ b/packages/api/src/routes/models.ts
@@ -17,6 +17,7 @@ import {
 	listStoredCredentials,
 	refreshAccountCredentialsAsync,
 	resolveApiKey,
+	resolveContextLimit,
 	setApiKey,
 	validateAccountCredentials,
 } from "@dispatch/core";
@@ -161,6 +162,21 @@ modelsRoutes.get("/available", async (c) => {
 	return c.json({ models });
 });
 
+// Resolve a model's MAXIMUM context window (in tokens) from the models.dev
+// catalog. Returns `{ contextLimit: number | null }`; `null` means the model's
+// limit is unknown (unsupported provider, unknown model, or catalog offline),
+// which the frontend renders without a denominator/percentage.
+modelsRoutes.get("/context-limit", async (c) => {
+	const provider = c.req.query("provider");
+	const modelId = c.req.query("modelId");
+	if (!provider || !modelId) {
+		return c.json({ error: "provider and modelId query parameters are required" }, 400);
+	}
+
+	const contextLimit = await resolveContextLimit(provider, modelId);
+	return c.json({ contextLimit });
+});
+
 // List available Claude accounts with validated credentials
 modelsRoutes.get("/claude-accounts", async (c) => {
 	const candidates = resolveClaudeAccounts();
diff --git a/packages/api/tests/routes.test.ts b/packages/api/tests/routes.test.ts
index c768cee..e4b8f0f 100644
--- a/packages/api/tests/routes.test.ts
+++ b/packages/api/tests/routes.test.ts
@@ -268,6 +268,13 @@ vi.mock("@dispatch/core", () => ({
 			execute: async () => "mock",
 		};
 	},
+	// ── models.dev context-limit stub ─────────────────────────────
+	resolveContextLimit(provider: string, modelId: string) {
+		if (provider === "anthropic" && modelId === "claude-sonnet-4-5") {
+			return Promise.resolve(200000);
+		}
+		return Promise.resolve(null);
+	},
 	// ── ntfy notifications stubs ──────────────────────────────────
 	NotificationDispatcher: class MockNotificationDispatcher {
 		attachToAgentManager() {
@@ -751,3 +758,28 @@ describe("Wake schedule routes", () => {
 		expect(body.schedule["13"]).toBeUndefined();
 	});
 });
+
+describe("GET /models/context-limit", () => {
+	it("returns the resolved context limit for a known model", async () => {
+		const res = await app.request(
+			"/models/context-limit?provider=anthropic&modelId=claude-sonnet-4-5",
+		);
+		expect(res.status).toBe(200);
+		const body = (await res.json()) as { contextLimit: number | null };
+		expect(body.contextLimit).toBe(200000);
+	});
+
+	it("returns null contextLimit for an unknown model", async () => {
+		const res = await app.request("/models/context-limit?provider=anthropic&modelId=mystery");
+		expect(res.status).toBe(200);
+		const body = (await res.json()) as { contextLimit: number | null };
+		expect(body.contextLimit).toBeNull();
+	});
+
+	it("400s when provider or modelId is missing", async () => {
+		const res1 = await app.request("/models/context-limit?provider=anthropic");
+		expect(res1.status).toBe(400);
+		const res2 = await app.request("/models/context-limit?modelId=claude-sonnet-4-5");
+		expect(res2.status).toBe(400);
+	});
+});