@xuda.io/ai_module 1.1.5255 → 1.1.5257

package/index.mjs

@@ -4891,6 +4891,7 @@ const ai_chat_conversation = async function (req, job_id, headers) {
         let out_conversation_item_doc = await db_module.get_app_couch_doc_native(account_profile_info.app_id, out_conversation_item_obj._id);
         // out_conversation_item_doc.stat = 3;
         out_conversation_item_doc.conversation_item_reference_id = conversation_items?.data?.[0]?.id;
+        out_conversation_item_doc.prompt_suggestions = prompt_suggestions;
         await db_module.save_app_couch_doc_native(account_profile_info.app_id, out_conversation_item_doc);
 
         account_msa.record_ai_usage(uid, inputTokens, outputTokens, 'conversation chat', prompt, model, { conversation_id, ai_agent_id: in_conversation_item_obj.ai_agent_id, item_id: in_conversation_item_obj._id }, account_profile_info);
@@ -11032,7 +11033,8 @@ export const open_ai_alive_check = async function () {};
 // };
 
 export const get_chat_suggestions = async function (req) {
-  const { type = 'chat prompt', uid, conversation_item_id, no_of_suggestions = 3, ai_model = _conf.default_ai_model, context, exclude_agents = [] } = req;
+  //type = 'chat prompt'
+  const { type = 'chat response', uid, conversation_item_id, no_of_suggestions = 3, ai_model = _conf.default_ai_model, context, exclude_agents = [] } = req;
   let { ai_agents = [] } = req;
 
   try {
@@ -11120,41 +11122,33 @@ export const get_chat_suggestions = async function (req) {
       //${conversation_item_doc.text}
       //   Prompt Category: ${conversation_doc?.category_info?.category}
       //  Input: ${conversation_item_doc.prompt || conversation_doc.prompt}
+      // Format Compatibility: Analyze the ## Prompt Response. If it contains code, data structures, or specific document types (like HTML), prioritize agents whose agent_instructions or agent_name or agent instructions involve processing, transforming, or styling that specific format.
+
+      // Workflow Continuity: Choose agents that represent a logical "next step" in a development or content creation pipeline (e.g., if code was generated, suggest an agent that deploys, converts, or styles it).
+
+      // Contextual Relevance: Balance the selection with the ## User Info and ## Prompt Category to ensure the agents match the user's industry and intent.
 
       const prompt = `
      
         Role: You are an expert Routing Assistant specialized in connecting users with the most relevant specialized AI agents.
-
         Task: Select maximum ${no_of_suggestions} agents from the ## Agent List that are best suited to act upon or refine the current conversation state.
 
-         
         Selection Strategy:
-        1. Format Compatibility: Analyze the ## Output to Process. If it contains structured JSON, component definitions, or raw HTML, prioritize agents capable of transforming these formats (e.g., converting HTML/JSON to functional apps).
+        1. Format Compatibility: Analyze the ## ${type} to Process. If it contains structured JSON, component definitions, or raw HTML, prioritize agents capable of transforming these formats (e.g., converting HTML/JSON to functional apps).
         2. Workflow Continuity: Focus on the "Lifecycle" of the project. If a UI or content has been drafted, the logical next step is conversion to a production-ready format, styling, or deployment. 
         3. Explicit Intent: If the user’s original input was "make me a website" and the current state is a document definition, prioritize the agent that performs the final "Conversion" or "Building" step.
         4. Contextual Relevance: Match the user's business profile (Digital Marketing & Web Development) with technical agents that automate development tasks.
 
 
-
-
-        Format Compatibility: Analyze the ## Prompt Response. If it contains code, data structures, or specific document types (like HTML), prioritize agents whose agent_instructions or agent_name or agent instructions involve processing, transforming, or styling that specific format.
-
-        Workflow Continuity: Choose agents that represent a logical "next step" in a development or content creation pipeline (e.g., if code was generated, suggest an agent that deploys, converts, or styles it).
-
-        Contextual Relevance: Balance the selection with the ## User Info and ## Prompt Category to ensure the agents match the user's industry and intent.
-
+        ## ${type}: ${context ? context : 'Use the previous response output as the content to analyze for next agents.'}
+ 
         Input Context:
 
         User Profile: ${JSON.stringify(account_doc.account_info)}
         Prompt Category: ${conversation_doc?.category_info?.category}
         Input: ${conversation_item_doc.prompt || conversation_doc.prompt}
 
-        Current State:
-
-       
-
-        Output to Process: ${context ? context : 'Use the previous response output as the content to analyze for next agents.'}
-
+        
         Agent Source: ${JSON.stringify(agents_docs)}
 
         Output: > Return a JSON array of maximum ${no_of_suggestions} objects following this schema:

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@xuda.io/ai_module",
-  "version": "1.1.5255",
+  "version": "1.1.5257",
   "description": "Xuda AI Module",
   "main": "index.mjs",
   "type": "module",