Merge 19ff2be8f2 into 995bef73de

add: model gpt-5

Dockerfile

@@ -1,57 +1,79 @@
 FROM node:18-alpine AS base
 
+# Install dependencies only when needed
 FROM base AS deps
-
 RUN apk add --no-cache libc6-compat
-
 WORKDIR /app
 
-COPY package.json yarn.lock ./
+# Copy package files
+COPY package.json yarn.lock* ./
 
-RUN yarn config set registry 'https://registry.npmmirror.com/'
-RUN yarn install
+# Configure yarn and install dependencies
+RUN yarn config set registry 'https://registry.npmmirror.com/' && \
+    yarn install --frozen-lockfile
 
+# Rebuild the source code only when needed
 FROM base AS builder
-
 RUN apk update && apk add --no-cache git
-
-ENV OPENAI_API_KEY=""
-ENV GOOGLE_API_KEY=""
-ENV CODE=""
-
 WORKDIR /app
+
+# Copy node_modules from deps stage
 COPY --from=deps /app/node_modules ./node_modules
 COPY . .
 
+# Set build-time environment variables
+ENV NEXT_TELEMETRY_DISABLED 1
+ENV NODE_ENV production
+
+# Build the application
 RUN yarn build
 
+# Production image, copy all the files and run next
 FROM base AS runner
 WORKDIR /app
 
-RUN apk add proxychains-ng
+# Install proxychains for proxy support
+RUN apk add --no-cache proxychains-ng
 
+# Set runtime environment
+ENV NODE_ENV production
+ENV NEXT_TELEMETRY_DISABLED 1
+
+# Environment variables (will be overridden at runtime)
 ENV PROXY_URL=""
 ENV OPENAI_API_KEY=""
 ENV GOOGLE_API_KEY=""
 ENV CODE=""
 ENV ENABLE_MCP=""
 
-COPY --from=builder /app/public ./public
-COPY --from=builder /app/.next/standalone ./
-COPY --from=builder /app/.next/static ./.next/static
-COPY --from=builder /app/.next/server ./.next/server
+# Create a non-root user
+RUN addgroup --system --gid 1001 nodejs && \
+    adduser --system --uid 1001 nextjs
 
-RUN mkdir -p /app/app/mcp && chmod 777 /app/app/mcp
+# Copy built application
+COPY --from=builder /app/public ./public
+COPY --from=builder --chown=nextjs:nodejs /app/.next/standalone ./
+COPY --from=builder --chown=nextjs:nodejs /app/.next/static ./.next/static
+
+# Create and set up MCP directory
+RUN mkdir -p /app/app/mcp && \
+    chmod 777 /app/app/mcp
 COPY --from=builder /app/app/mcp/mcp_config.default.json /app/app/mcp/mcp_config.json
 
+# Switch to non-root user
+USER nextjs
+
 EXPOSE 3000
 
+ENV PORT 3000
+ENV HOSTNAME "0.0.0.0"
+
+# Start the application
 CMD if [ -n "$PROXY_URL" ]; then \
-    export HOSTNAME="0.0.0.0"; \
     protocol=$(echo $PROXY_URL | cut -d: -f1); \
     host=$(echo $PROXY_URL | cut -d/ -f3 | cut -d: -f1); \
     port=$(echo $PROXY_URL | cut -d: -f3); \
-    conf=/etc/proxychains.conf; \
+    conf=/tmp/proxychains.conf; \
     echo "strict_chain" > $conf; \
     echo "proxy_dns" >> $conf; \
     echo "remote_dns_subnet 224" >> $conf; \
@@ -61,7 +83,6 @@ CMD if [ -n "$PROXY_URL" ]; then \
     echo "localnet ::1/128" >> $conf; \
     echo "[ProxyList]" >> $conf; \
     echo "$protocol $host $port" >> $conf; \
-    cat /etc/proxychains.conf; \
     proxychains -f $conf node server.js; \
     else \
     node server.js; \

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",