fix(router-provider): fetch model metadata before context management decisions

Router providers (zoo-gateway, kimi-code) that are auth-scoped skip the
model cache entirely. On a fresh handler instance getModel() falls back
to hardcoded defaults (e.g. 200k context window) because the real model
list has not been fetched yet. Context management runs before
createMessage() which is where fetchModel() normally happens, so
condensing/truncation decisions use the wrong context window.

Add ensureModelFetched() to RouterProvider that fetches once when the
instance model map is empty. Call it in Task before context management
so getModel() returns accurate metadata from the API.

Co-authored-by: Cursor <cursoragent@cursor.com>

Author: JamesRobert20

src/api/index.ts

@@ -125,6 +125,13 @@ export interface ApiHandler {
 
 	getModel(): { id: string; info: ModelInfo }
 
+	/**
+	 * Ensures model metadata has been fetched from the remote API so that getModel()
+	 * returns accurate info (context window, pricing, etc.) instead of hardcoded defaults.
+	 * Only router providers that discover models over the network implement this.
+	 */
+	ensureModelFetched?(): Promise<void>
+
 	/**
 	 * Optional context window for context-management / auto-condense when it must differ from
 	 * getModel().info.contextWindow. Only VS Code LM overrides it (static `maxInputTokens` vs its

src/api/providers/__tests__/zoo-gateway.spec.ts

@@ -635,4 +635,51 @@ describe("ZooGatewayHandler", () => {
 			)
 		})
 	})
+
+	describe("ensureModelFetched", () => {
+		it("fetches models when instance models are empty", async () => {
+			const handler = new ZooGatewayHandler(mockOptions)
+			const { getModels } = await import("../fetchers/modelCache")
+
+			expect(handler.getModel().info.contextWindow).toBe(200000)
+
+			await handler.ensureModelFetched()
+
+			expect(getModels).toHaveBeenCalled()
+		})
+
+		it("skips the fetch when models are already populated", async () => {
+			const handler = new ZooGatewayHandler(mockOptions)
+			const { getModels } = await import("../fetchers/modelCache")
+
+			await handler.ensureModelFetched()
+			vitest.mocked(getModels).mockClear()
+
+			await handler.ensureModelFetched()
+			expect(getModels).not.toHaveBeenCalled()
+		})
+
+		it("makes getModel return the fetched context window instead of the default", async () => {
+			const { getModels } = await import("../fetchers/modelCache")
+			vitest.mocked(getModels).mockResolvedValueOnce({
+				"google/gemini-2.5-pro": {
+					maxTokens: 65536,
+					contextWindow: 1048576,
+					supportsImages: true,
+					supportsPromptCache: false,
+				},
+			})
+
+			const handler = new ZooGatewayHandler({
+				...mockOptions,
+				zooGatewayModelId: "google/gemini-2.5-pro",
+			})
+
+			expect(handler.getModel().info.contextWindow).toBe(200000)
+
+			await handler.ensureModelFetched()
+
+			expect(handler.getModel().info.contextWindow).toBe(1048576)
+		})
+	})
 })

src/api/providers/router-provider.ts

@@ -61,6 +61,12 @@ export abstract class RouterProvider extends BaseProvider {
 		return this.getModel()
 	}
 
+	async ensureModelFetched(): Promise<void> {
+		if (Object.keys(this.models).length === 0) {
+			await this.fetchModel()
+		}
+	}
+
 	override getModel(): { id: string; info: ModelInfo } {
 		// Use `||` (not `??`) so an empty-string modelId also falls back to the default,
 		// guaranteeing a non-empty id rather than forwarding "" to the API as an invalid

src/core/task/Task.ts

@@ -3842,6 +3842,7 @@ export class Task extends EventEmitter<TaskEvents> implements TaskLike {
 		const { profileThresholds = {}, mode, apiConfiguration } = state ?? {}
 
 		const { contextTokens } = this.getTokenUsage()
+		await this.api.ensureModelFetched?.()
 		const modelInfo = this.api.getModel().info
 
 		const maxTokens = getModelMaxOutputTokens({
@@ -4042,6 +4043,7 @@ export class Task extends EventEmitter<TaskEvents> implements TaskLike {
 		const { contextTokens } = this.getTokenUsage()
 
 		if (contextTokens) {
+			await this.api.ensureModelFetched?.()
 			const modelInfo = this.api.getModel().info
 
 			const maxTokens = getModelMaxOutputTokens({