feat(events): a better prompt with good integration with location agent

backend/agents/event_agent.go

@@ -13,47 +13,44 @@ import (
 )
 
 const eventPrompt = `
-**Role:** You are an Event Processing AI Assistant specialized in extracting event information from images, managing event data using provided tools, and ensuring accuracy and avoiding duplicates.
+**You are an AI processing events from images using internal thought.**
 
-**Primary Goal:** To analyze images, identify potential events (like meetings, appointments, conferences, invitations), extract key details (name, date/time, location description), check against existing events, retrieve location identifiers if applicable, create new event entries when necessary, and signal completion using the 'finish' tool.
+**Task:** Extract event details (Name, Date/Time, Location). Use think before deciding actions. Check duplicates with listEvents. Handle new events via getEventLocationId (if location exists) and createEvent. Use finish if no event or duplicate found.
+1.  **Analyze Image & Think:** Extract details. Use think to confirm if a valid event exists. If not -> stopAgent.
+2.  **Event Confirmed?** -> *Must* call listEvents, to check for existing events and prevent duplicates.
+3.  **Detect Duplicates** -> If the input contains an event that already exists from listEvents, then you should call stopAgent.
+4.  **New Events**
+		* If you think the input contains a location, then you can use getEventLocationId to retrieve the ID of the location. Only use this IF the input contains a location.
+    	* Call createEvent.
+5.  **Multiple Events:** Process sequentially using this logic.
 
-**Core Workflow:**
-
-**Duplicate Check (Mandatory if Event Found):**
-	* If potential event details were found, you **must** call the listEvents tool first to check for duplicates. **Generate only the listEvents tool call structure.**
-    * Once you receive the list, compare the extracted event details (Name, Start Date/Time primarily) against the existing events.
-    * **If a matching event already exists, proceed directly to Step 6 (call finish).**
-
-**Location ID Retrieval (Conditional):**
-    * If the event is identified as *new* AND a *location description* was extracted.
-        * Call the getEventLocationId tool, providing the extracted location description. **Generate only the getEventLocationId tool call structure.**
-
-**Create Event:**
-    * If the event was identified as *new*:
-        * Prepare the parameters for the createEvent tool using the extracted details (Name, Start Date/Time, End Date/Time).
-	* If you identify the event as *duplicate*, meaning you think an event in listEvents is the same as the event on this image.
-		* Call the updateEvent tool so this image is also linked to that event. If you find any new information you can update it using this tool too.
-
-**Handling Multiple Events:**
-    * If the image contains multiple distinct events, ideally process them one by one.
-	* Do this until there are no more events on this image
-
-**Task Completion / No Action Needed:**
-    * Call the finish tool **only** when one of the following conditions is met:
-        * No identifiable event information was found in the initial image analysis.
-        * The listEvents check confirmed the identified event already exists.
-        * You have successfully called createEvent for a new event.
-
-**Available Tools:**
-
-* **listEvents**: Retrieves the user's existing events. **Must** be called first if potential event details are found in the image, to enable duplicate checking.
-* **getEventLocationId**: Takes a location description (text) and retrieves a unique ID (locationId) for it. Use this *before* createEvent *only* if a new event has a specific location mentioned.
-* **createEvent**: Adds a *new*, non-duplicate event to the user's calendar/list. Only call *after* listEvents confirms the event is new. Requires name. Include startDateTime, endDateTime, and locationId (if available and retrieved).
-* **stopAgent**: Signals that processing for the current image is complete (either action was taken, no action was needed because the event already existed, or no event was found). Call this as the final step.
+**Tools:**
+* think: Internal reasoning/planning step.
+* listEvents: Check for duplicates (mandatory first step for found events).
+* getEventLocationId: Get ID for location text.
+* createEvent: Add new event (Name req.). Terminal action for new events.
+* stopAgent: Signal completion (no event/duplicate found). Terminal action.
 `
 
 const eventTools = `
 [
+	{
+			"type": "function",
+			"function": {
+				"name": "think",
+				"description": "Use this tool to think through the image, evaluating the event and whether or not it exists in the users listEvents.",
+				"parameters": {
+					"type": "object",
+					"properties": {
+						"thought": {
+							"type": "string",
+							"description": "A singular thought about the image"
+						}
+					},
+					"required": ["thought"]
+				}
+			}
+	  },
     {
         "type": "function",
         "function": {
@@ -168,6 +165,10 @@ func NewEventAgent(log *log.Logger, eventsModel models.EventModel, locationModel
 	locationQuery := "Can you get me the ID of the location present in this image?"
 	locationAgent.Options.Query = &locationQuery
 
+	agentClient.ToolHandler.AddTool("think", func(info client.ToolHandlerInfo, args string, call client.ToolCall) (any, error) {
+		return "Thought", nil
+	})
+
 	agentClient.ToolHandler.AddTool("listEvents", func(info client.ToolHandlerInfo, args string, call client.ToolCall) (any, error) {
 		return eventsModel.List(context.Background(), info.UserId)
 	})
@@ -183,6 +184,8 @@ func NewEventAgent(log *log.Logger, eventsModel models.EventModel, locationModel
 
 		layout := "2006-01-02T15:04:05Z"
 
+		// TODO: check for nil pointers.
+
 		startTime, err := time.Parse(layout, *args.StartDateTime)
 		if err != nil {
 			return model.Events{}, err

backend/agents/location_agent.go

@@ -39,12 +39,11 @@ Action loop:
 		* Do not use this tool if this location already exists.
 	* If the input contains a location that already exists, you should use createExistingLocation.
 		* If there is a similar location in listLocation, you should use this tool. It doesnt have to be an exact match.
+	* Lastly, if the user asked a specific question about a location. You must do all the actions but also always use the reply tool to answer the user.
+		* This is the only way you can communicate with the user if they asked a query.
 
 You should repeat the action loop until all locations on the image are done.
 Once you are done, use stopAgent.
-
-**Reply to user querys**
-	* If the user asks you a specific question, you should use the reply tool to reply to them.
 `
 
 const replyTool = `
@@ -72,7 +71,7 @@ const locationTools = `
         "type": "function",
         "function": {
             "name": "think",
-            "description": "Use this tool to think through the image, evaluating the location and whether or not it exists in the users listLocations.",
+            "description": "Use this tool to think through the image, evaluating the location and whether or not it exists in the users listLocations. You should also ask yourself if the user has asked a query, and if you've used the correct tool to reply to them.",
             "parameters": {
                 "type": "object",
                 "properties": {

backend/agents/orchestrator.go

@@ -157,7 +157,7 @@ func NewOrchestratorAgent(log *log.Logger, noteAgent NoteAgent, contactAgent cli
 	})
 
 	agent.ToolHandler.AddTool("eventAgent", func(info client.ToolHandlerInfo, args string, call client.ToolCall) (any, error) {
-		// go eventAgent.RunAgent(info.UserId, info.ImageId, imageName, imageData)
+		go eventAgent.RunAgent(info.UserId, info.ImageId, imageName, imageData)
 
 		return "eventAgent called successfully", nil
 	})