fix(ai): disable hidden provider 429 retries (#4991)

packages/ai/test/openai-codex-stream.test.ts

@@ -1131,7 +1131,11 @@ describe("openai-codex streaming", () => {
 			messages: [{ role: "user", content: "Say hello", timestamp: Date.now() }],
 		};
 
-		const resultPromise = streamOpenAICodexResponses(model, context, { apiKey: token, transport: "sse" }).result();
+		const resultPromise = streamOpenAICodexResponses(model, context, {
+			apiKey: token,
+			transport: "sse",
+			maxRetries: 1,
+		}).result();
 		await vi.advanceTimersByTimeAsync(0);
 		expect(setTimeoutSpy).toHaveBeenCalledWith(expect.any(Function), expectedDelay);
 
@@ -1193,7 +1197,11 @@ describe("openai-codex streaming", () => {
 			messages: [{ role: "user", content: "Say hello", timestamp: Date.now() }],
 		};
 
-		const resultPromise = streamOpenAICodexResponses(model, context, { apiKey: token, transport: "sse" }).result();
+		const resultPromise = streamOpenAICodexResponses(model, context, {
+			apiKey: token,
+			transport: "sse",
+			maxRetries: 3,
+		}).result();
 		await vi.advanceTimersByTimeAsync(0);
 		expect(setTimeoutSpy).toHaveBeenNthCalledWith(1, expect.any(Function), 1000);
 

packages/ai/test/openai-completions-retry.test.ts

@@ -0,0 +1,86 @@
+import { beforeEach, describe, expect, it, vi } from "vitest";
+import { streamOpenAICompletions } from "../src/providers/openai-completions.ts";
+import type { Context, Model } from "../src/types.ts";
+
+const mockState = vi.hoisted(() => ({
+	requestOptions: [] as unknown[],
+}));
+
+vi.mock("openai", () => {
+	class FakeOpenAI {
+		chat = {
+			completions: {
+				create: (_params: unknown, options: unknown) => {
+					mockState.requestOptions.push(options);
+					const stream = {
+						async *[Symbol.asyncIterator]() {
+							yield {
+								id: "chatcmpl-test",
+								choices: [{ index: 0, delta: { content: "ok" } }],
+							};
+							yield {
+								id: "chatcmpl-test",
+								choices: [{ index: 0, delta: {}, finish_reason: "stop" }],
+							};
+						},
+					};
+					const promise = Promise.resolve(stream) as Promise<typeof stream> & {
+						withResponse: () => Promise<{
+							data: typeof stream;
+							response: { status: number; headers: Headers };
+						}>;
+					};
+					promise.withResponse = async () => ({
+						data: stream,
+						response: { status: 200, headers: new Headers() },
+					});
+					return promise;
+				},
+			},
+		};
+	}
+	return { default: FakeOpenAI };
+});
+
+const model: Model<"openai-completions"> = {
+	id: "test-model",
+	name: "Test Model",
+	api: "openai-completions",
+	provider: "opencode-go",
+	baseUrl: "https://opencode.ai/zen/go/v1",
+	reasoning: false,
+	input: ["text"],
+	cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
+	contextWindow: 1000,
+	maxTokens: 100,
+};
+
+const context: Context = {
+	systemPrompt: "",
+	messages: [{ role: "user", content: [{ type: "text", text: "hi" }], timestamp: 0 }],
+	tools: [],
+};
+
+async function consume(options?: { maxRetries?: number }) {
+	const stream = streamOpenAICompletions(model, context, { apiKey: "test", ...options });
+	for await (const _event of stream) {
+		void _event;
+	}
+	return stream.result();
+}
+
+describe("openai-completions provider retries", () => {
+	beforeEach(() => {
+		mockState.requestOptions = [];
+	});
+
+	it("disables SDK retries by default", async () => {
+		await consume();
+		expect(mockState.requestOptions).toEqual([expect.objectContaining({ maxRetries: 0 })]);
+	});
+
+	it("honors explicit provider retry settings", async () => {
+		await consume({ maxRetries: 2 });
+		expect(mockState.requestOptions).toEqual([expect.objectContaining({ maxRetries: 2 })]);
+	});
+});