fix(good-fences): give the model room to answer

gpt-oss-120b reasons before it answers, and Workers AI's default
max_tokens (256) ran out mid-thought: finish_reason "length", content
null. Ask for 4096, and when there's no reply text, say which choice
and message keys came back instead.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>

good-fences/src/model.ts

@@ -3,14 +3,24 @@
 /** a Workers AI text-generation model with no paid-plan requirement */
 export const MODEL = "@cf/openai/gpt-oss-120b";
 
+/** room for a reasoning model to think and then answer; the default, 256,
+ * runs out mid-thought (`finish_reason: length`) */
+const MAX_TOKENS = 4096;
+
 export type Message = Readonly<{ role: "system" | "user" | "assistant"; content: string }>;
 
 /** the reply text from an OpenAI-style chat completion */
 const replyText = (output: unknown): string => {
-	const { choices } = (output ?? {}) as { choices?: { message?: { content?: unknown } }[] };
-	const text = choices?.[0]?.message?.content;
+	const { choices } = (output ?? {}) as {
+		choices?: { message?: { content?: unknown }; finish_reason?: unknown }[];
+	};
+	const [choice] = choices ?? [];
+	const text = choice?.message?.content;
 	if (typeof text !== "string") {
-		throw Error(`no reply text in model output with keys: ${Object.keys(output ?? {}).join(", ")}`);
+		const where = choice
+			? `choice with finish_reason ${String(choice.finish_reason)} and message keys: ${Object.keys(choice.message ?? {}).join(", ")}`
+			: `model output with keys: ${Object.keys(output ?? {}).join(", ")}`;
+		throw Error(`no reply text in ${where}`);
 	}
 	return text;
 };
@@ -18,7 +28,7 @@ const replyText = (output: unknown): string => {
 /** `complete(messages)` on a Workers AI model; `ai` is the AI binding */
 export const makeWorkersAiModel = (ai: Ai, model: string) => ({
 	async complete(messages: readonly Message[]): Promise<string> {
-		const output = await ai.run(model as Parameters<Ai["run"]>[0], { messages: [...messages] });
+		const output = await ai.run(model as Parameters<Ai["run"]>[0], { messages: [...messages], max_tokens: MAX_TOKENS });
 		return replyText(output);
 	},
 });