Working!

frontend/src/Conversation.tsx

@@ -386,25 +386,11 @@ const Conversation = forwardRef<ConversationHandle, ConversationProps>(({
       const decoder = new TextDecoder();
       let buffer = '';
 
-      while (true) {
+      const process_line = async (line: string) => {
-        const { done, value } = await reader.read();
-        if (done) {
-          break;
-        }
-
-        const chunk = decoder.decode(value, { stream: true });
-
-        // Process each complete line immediately
-        buffer += chunk;
-        let lines = buffer.split('\n');
-        buffer = lines.pop() || ''; // Keep incomplete line in buffer
-        for (const line of lines) {
-          if (!line.trim()) continue;
-
-          try {
         const update = JSON.parse(line);
 
         switch (update.status) {
+          case 'searching':
           case 'processing':
           case 'thinking':
             // Force an immediate state update based on the message type
@@ -458,9 +444,26 @@ const Conversation = forwardRef<ConversationHandle, ConversationProps>(({
             await new Promise(resolve => setTimeout(resolve, 0));
             break;
         }
+      }
+
+      while (true) {
+        const { done, value } = await reader.read();
+        if (done) {
+          break;
+        }
+
+        const chunk = decoder.decode(value, { stream: true });
+
+        // Process each complete line immediately
+        buffer += chunk;
+        let lines = buffer.split('\n');
+        buffer = lines.pop() || ''; // Keep incomplete line in buffer
+        for (const line of lines) {
+          if (!line.trim()) continue;
+          try {
+            await process_line(line);
           } catch (e) {
             setSnack("Error processing query", "error")
-            console.error('Error parsing JSON:', e, line);
           }
         }
       }
@@ -468,47 +471,7 @@ const Conversation = forwardRef<ConversationHandle, ConversationProps>(({
       // Process any remaining buffer content
       if (buffer.trim()) {
         try {
-          const update = JSON.parse(buffer);
+          await process_line(buffer);
-
-          switch (update.status) {
-            case 'processing':
-            case 'thinking':
-              // Force an immediate state update based on the message type
-              // Update processing message with immediate re-render
-              setProcessingMessage({ role: 'status', content: update.response });
-              // Add a small delay to ensure React has time to update the UI
-              await new Promise(resolve => setTimeout(resolve, 0));
-              break;
-            case 'error':
-              // Show error
-              setProcessingMessage({ role: 'error', content: update.response });
-              setTimeout(() => {
-                setProcessingMessage(undefined);
-              }, 5000);
-              break;
-            case 'done':
-              console.log('Done processing:', update);
-              if (onResponse) {
-                update.message = onResponse(update);
-              }
-              setProcessingMessage(undefined);
-              const backstoryMessage: BackstoryMessage = update;
-              setConversation([
-                ...conversationRef.current, {
-                  //   role: 'user',
-                  //   content: backstoryMessage.prompt || "",
-                  // }, {
-                  role: 'assistant',
-                  origin: type,
-                  prompt: backstoryMessage.prompt || "",
-                  content: backstoryMessage.response || "",
-                  preamble: backstoryMessage.preamble || {},
-                  full_content: backstoryMessage.full_content || "",
-                  metadata: backstoryMessage.metadata,
-                  actions: backstoryMessage.actions,
-                }] as MessageList);            
-              break;
-          }
         } catch (e) {
           setSnack("Error processing query", "error")
         }

src/utils/agents/chat.py

@@ -92,18 +92,22 @@ class Chat(Agent, ABC):
       ]
     ]
   
-    for value in llm.chat(
+    message.status = "thinking"
+    for response in llm.chat(
       model=model, 
       messages=messages, 
       #tools=llm_tools(context.tools) if message.enable_tools else None, 
       options={ "num_ctx": message.metadata["ctx_size"] if message.metadata["ctx_size"] else defines.max_context },
       stream=True,
     ):
-      logging.info(f"LLM: {'done' if value.done else 'thinking'} - {value.message.content}")
+      logging.info(f"LLM: {'done' if response.done else 'thinking'} - {response.message.content}")
-      message.response += value.message.content
+      message.response += response.message.content
+      message.metadata["eval_count"] += response["eval_count"]
+      message.metadata["eval_duration"] += response["eval_duration"]
+      message.metadata["prompt_eval_count"] += response["prompt_eval_count"]
+      message.metadata["prompt_eval_duration"] += response["prompt_eval_duration"]      
       yield message
-      if value.done:
+      if response.done:
-        response = value
         message.status = "done"
 
     if not response:
@@ -113,10 +117,6 @@ class Chat(Agent, ABC):
       self.context.processing = False
       return
     
-    message.metadata["eval_count"] += response["eval_count"]
-    message.metadata["eval_duration"] += response["eval_duration"]
-    message.metadata["prompt_eval_count"] += response["prompt_eval_count"]
-    message.metadata["prompt_eval_duration"] += response["prompt_eval_duration"]
     self.context_tokens = response["prompt_eval_count"] + response["eval_count"]
 
     yield message
@@ -212,7 +212,7 @@ class Chat(Agent, ABC):
       message.metadata["ctx_size"] = self.context.get_optimal_ctx_size(self.context_tokens, messages=message.full_content)
       
       message.response = f"Processing {'RAG augmented ' if message.metadata['rag'] else ''}query..."
-      message.status = "thinking"    
+      message.status = "searching"    
       yield message
 
       async for message in self.generate_llm_response(llm, model, message):