Merge d5c86ce9ab into c3b8c1587c

feat: new models for xAI (#6559)

app/client/platforms/openai.ts

@@ -200,6 +200,7 @@ export class ChatGPTApi implements LLMApi {
       options.config.model.startsWith("o1") ||
       options.config.model.startsWith("o3") ||
       options.config.model.startsWith("o4-mini");
+    const isGpt5 =  options.config.model.startsWith("gpt-5");
     if (isDalle3) {
       const prompt = getMessageTextContent(
         options.messages.slice(-1)?.pop() as any,
@@ -230,7 +231,7 @@ export class ChatGPTApi implements LLMApi {
         messages,
         stream: options.config.stream,
         model: modelConfig.model,
-        temperature: !isO1OrO3 ? modelConfig.temperature : 1,
+        temperature: (!isO1OrO3 && !isGpt5) ? modelConfig.temperature : 1,
         presence_penalty: !isO1OrO3 ? modelConfig.presence_penalty : 0,
         frequency_penalty: !isO1OrO3 ? modelConfig.frequency_penalty : 0,
         top_p: !isO1OrO3 ? modelConfig.top_p : 1,
@@ -238,7 +239,13 @@ export class ChatGPTApi implements LLMApi {
         // Please do not ask me why not send max_tokens, no reason, this param is just shit, I dont want to explain anymore.
       };
 
-      if (isO1OrO3) {
+      if (isGpt5) {
+  	// Remove max_tokens if present
+  	delete requestPayload.max_tokens;
+  	// Add max_completion_tokens (or max_completion_tokens if that's what you meant)
+  	requestPayload["max_completion_tokens"] = modelConfig.max_tokens;
+
+      } else if (isO1OrO3) {
         // by default the o1/o3 models will not attempt to produce output that includes markdown formatting
         // manually add "Formatting re-enabled" developer message to encourage markdown inclusion in model responses
         // (https://learn.microsoft.com/en-us/azure/ai-services/openai/how-to/reasoning?tabs=python-secure#markdown-output)
@@ -251,8 +258,9 @@ export class ChatGPTApi implements LLMApi {
         requestPayload["max_completion_tokens"] = modelConfig.max_tokens;
       }
 
+
       // add max_tokens to vision model
-      if (visionModel && !isO1OrO3) {
+      if (visionModel && !isO1OrO3 && ! isGpt5) {
         requestPayload["max_tokens"] = Math.max(modelConfig.max_tokens, 4000);
       }
     }

app/constant.ts

@@ -493,6 +493,7 @@ export const VISION_MODEL_REGEXES = [
   /o3/,
   /o4-mini/,
   /grok-4/i,
+  /gpt-5/
 ];
 
 export const EXCLUDE_VISION_MODEL_REGEXES = [/claude-3-5-haiku-20241022/];
@@ -517,6 +518,11 @@ const openaiModels = [
   "gpt-4.1-nano-2025-04-14",
   "gpt-4.5-preview",
   "gpt-4.5-preview-2025-02-27",
+  "gpt-5-chat",
+  "gpt-5-mini",
+  "gpt-5-nano",
+  "gpt-5",
+  "gpt-5-chat-2025-01-01-preview",
   "gpt-4o",
   "gpt-4o-2024-05-13",
   "gpt-4o-2024-08-06",
@@ -667,6 +673,11 @@ const xAIModes = [
   "grok-3-beta",
   "grok-3",
   "grok-3-latest",
+  "grok-4",
+  "grok-4-0709",
+  "grok-4-fast-non-reasoning",
+  "grok-4-fast-reasoning",
+  "grok-code-fast-1",
 ];
 
 const chatglmModels = [

next.config.mjs

@@ -21,9 +21,25 @@ const nextConfig = {
     }
 
     config.resolve.fallback = {
+      ...config.resolve.fallback,
       child_process: false,
+      process: false,
+      path: false,
+      fs: false,
+      os: false,
+      util: false,
+      stream: false,
+      buffer: require.resolve('buffer/'),
+      events: require.resolve('events/'),
     };
 
+    config.plugins.push(
+      new webpack.ProvidePlugin({
+        Buffer: ['buffer', 'Buffer'],
+        process: 'process/browser',
+      }),
+    );
+
     return config;
   },
   output: mode,