fix(ai): trust requested Codex service tier (#3307)

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

@@ -499,6 +499,95 @@ describe("openai-codex streaming", () => {
 		await streamResult.result();
 	});
 
+	it.each([
+		["flex", 0.5],
+		["priority", 2],
+	] as const)("uses the client-sent %s service tier when Codex echoes default", async (serviceTier, multiplier) => {
+		const tempDir = mkdtempSync(join(tmpdir(), "pi-codex-stream-"));
+		process.env.PI_CODING_AGENT_DIR = tempDir;
+		const token = mockToken();
+		const sse = `${[
+			`data: ${JSON.stringify({
+				type: "response.output_item.added",
+				item: { type: "message", id: "msg_1", role: "assistant", status: "in_progress", content: [] },
+			})}`,
+			`data: ${JSON.stringify({ type: "response.content_part.added", part: { type: "output_text", text: "" } })}`,
+			`data: ${JSON.stringify({ type: "response.output_text.delta", delta: "Hello" })}`,
+			`data: ${JSON.stringify({
+				type: "response.output_item.done",
+				item: {
+					type: "message",
+					id: "msg_1",
+					role: "assistant",
+					status: "completed",
+					content: [{ type: "output_text", text: "Hello" }],
+				},
+			})}`,
+			`data: ${JSON.stringify({
+				type: "response.completed",
+				response: {
+					status: "completed",
+					service_tier: "default",
+					usage: {
+						input_tokens: 1000000,
+						output_tokens: 1000000,
+						total_tokens: 2000000,
+						input_tokens_details: { cached_tokens: 0 },
+					},
+				},
+			})}`,
+		].join("\n\n")}\n\n`;
+
+		const encoder = new TextEncoder();
+		const stream = new ReadableStream<Uint8Array>({
+			start(controller) {
+				controller.enqueue(encoder.encode(sse));
+				controller.close();
+			},
+		});
+
+		global.fetch = vi.fn(async (input: string | URL) => {
+			const url = typeof input === "string" ? input : input.toString();
+			if (url === "https://api.github.com/repos/openai/codex/releases/latest") {
+				return new Response(JSON.stringify({ tag_name: "rust-v0.0.0" }), { status: 200 });
+			}
+			if (url.startsWith("https://raw.githubusercontent.com/openai/codex/")) {
+				return new Response("PROMPT", { status: 200, headers: { etag: '"etag"' } });
+			}
+			if (url === "https://chatgpt.com/backend-api/codex/responses") {
+				return new Response(stream, {
+					status: 200,
+					headers: { "content-type": "text/event-stream" },
+				});
+			}
+			return new Response("not found", { status: 404 });
+		}) as typeof fetch;
+
+		const model: Model<"openai-codex-responses"> = {
+			id: "gpt-5.1-codex",
+			name: "GPT-5.1 Codex",
+			api: "openai-codex-responses",
+			provider: "openai-codex",
+			baseUrl: "https://chatgpt.com/backend-api",
+			reasoning: true,
+			input: ["text"],
+			cost: { input: 1, output: 2, cacheRead: 0, cacheWrite: 0 },
+			contextWindow: 400000,
+			maxTokens: 128000,
+		};
+
+		const context: Context = {
+			systemPrompt: "You are a helpful assistant.",
+			messages: [{ role: "user", content: "Say hello", timestamp: Date.now() }],
+		};
+
+		const result = await streamOpenAICodexResponses(model, context, { apiKey: token, serviceTier }).result();
+
+		expect(result.usage.cost.input).toBe(1 * multiplier);
+		expect(result.usage.cost.output).toBe(2 * multiplier);
+		expect(result.usage.cost.total).toBe(3 * multiplier);
+	});
+
 	it("does not set session_id/x-client-request-id headers when sessionId is not provided", async () => {
 		const tempDir = mkdtempSync(join(tmpdir(), "pi-codex-stream-"));
 		process.env.PI_CODING_AGENT_DIR = tempDir;