feat: wire Media through agent pipeline to enable vision model support

- Add Media field to processOptions struct
- Pass msg.Media from InboundMessage to processOptions in processMessage
- Update BuildMessages to attach media to user message
- Pass opts.Media to BuildMessages instead of nil in runAgentLoop
- Enables vision-capable models (Gemini 2.0 Flash, etc.) to receive image_url content parts

pkg/agent/context.go

@@ -198,10 +198,11 @@ func (cb *ContextBuilder) BuildMessages(history []providers.Message, summary str
 
 	messages = append(messages, history...)
 
-	if strings.TrimSpace(currentMessage) != "" {
+	if strings.TrimSpace(currentMessage) != "" || len(media) > 0 {
 		messages = append(messages, providers.Message{
 			Role:    "user",
 			Content: currentMessage,
+			Media:   media,
 		})
 	}
 

pkg/agent/loop.go

@@ -46,6 +46,7 @@ type processOptions struct {
 	Channel         string   // Target channel for tool execution
 	ChatID          string   // Target chat ID for tool execution
 	UserMessage     string   // User message content (may include prefix)
+	Media           []string // Media URLs attached to the user message
 	DefaultResponse string   // Response when LLM returns empty
 	EnableSummary   bool     // Whether to trigger summarization
 	SendResponse    bool     // Whether to send response via bus
@@ -313,6 +314,7 @@ func (al *AgentLoop) processMessage(ctx context.Context, msg bus.InboundMessage)
 		Channel:         msg.Channel,
 		ChatID:          msg.ChatID,
 		UserMessage:     msg.Content,
+		Media:           msg.Media,
 		DefaultResponse: "I've completed processing but have no response to give.",
 		EnableSummary:   true,
 		SendResponse:    false,
@@ -402,7 +404,7 @@ func (al *AgentLoop) runAgentLoop(ctx context.Context, agent *AgentInstance, opt
 		history,
 		summary,
 		opts.UserMessage,
-		nil,
+		opts.Media,
 		opts.Channel,
 		opts.ChatID,
 	)