feat: Make MAX_TOKENS and MAX_RESPONSE_SEGMENTS configurable

Added MAX_TOKENS and MAX_RESPONSE_SEGMENTS to .env.example and documentation. Updated constants to read from environment variables, allowing configuration of token and response segment limits.

app/lib/.server/llm/constants.ts

@@ -1,5 +1,7 @@
 // see https://docs.anthropic.com/en/docs/about-claude/models
-export const MAX_TOKENS = 8000;
+export const MAX_TOKENS = process.env.MAX_TOKENS ? parseInt(process.env.MAX_TOKENS) : 8000;
 
 // limits the number of model responses that can be returned in a single request
-export const MAX_RESPONSE_SEGMENTS = 3;
+export const MAX_RESPONSE_SEGMENTS = process.env.MAX_RESPONSE_SEGMENTS
+  ? parseInt(process.env.MAX_RESPONSE_SEGMENTS)
+  : 5;

app/routes/api.chat/chat.server.ts

@@ -331,7 +331,7 @@ export async function chatAction({ request, userId }: ChatActionArgs) {
 
       const continueMessage = async (text: string) => {
         logger.info(
-          `达到最大 token 限制 (${MAX_TOKENS}): 继续消息, 还可以响应 (${MAX_RESPONSE_SEGMENTS - streamSwitches} 个分段)`,
+          `达到最大 token 限制 (${DEFAULT_MODEL_DETAILS?.maxTokenAllowed || MAX_TOKENS}): 继续消息, 还可以响应 (${MAX_RESPONSE_SEGMENTS - streamSwitches} 个分段)`,
         );
         messages.push({
           id: generateId(),