diff --git a/pkg/agent/context.go b/pkg/agent/context.go
index 6fccbaf53..8a35d4457 100644
--- a/pkg/agent/context.go
+++ b/pkg/agent/context.go
@@ -466,10 +466,14 @@ func (cb *ContextBuilder) BuildMessages(
 
 	// Add current user message
 	if strings.TrimSpace(currentMessage) != "" {
-		messages = append(messages, providers.Message{
+		msg := providers.Message{
 			Role:    "user",
 			Content: currentMessage,
-		})
+		}
+		if len(media) > 0 {
+			msg.Media = media
+		}
+		messages = append(messages, msg)
 	}
 
 	return messages
diff --git a/pkg/agent/loop.go b/pkg/agent/loop.go
index ac9b449a2..b803187b1 100644
--- a/pkg/agent/loop.go
+++ b/pkg/agent/loop.go
@@ -47,14 +47,15 @@ type AgentLoop struct {
 
 // processOptions configures how a message is processed
 type processOptions struct {
-	SessionKey      string // Session identifier for history/context
-	Channel         string // Target channel for tool execution
-	ChatID          string // Target chat ID for tool execution
-	UserMessage     string // User message content (may include prefix)
-	DefaultResponse string // Response when LLM returns empty
-	EnableSummary   bool   // Whether to trigger summarization
-	SendResponse    bool   // Whether to send response via bus
-	NoHistory       bool   // If true, don't load session history (for heartbeat)
+	SessionKey      string   // Session identifier for history/context
+	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:// refs from inbound message
+	DefaultResponse string   // Response when LLM returns empty
+	EnableSummary   bool     // Whether to trigger summarization
+	SendResponse    bool     // Whether to send response via bus
+	NoHistory       bool     // If true, don't load session history (for heartbeat)
 }
 
 const defaultResponse = "I've completed processing but have no response to give. Increase `max_tool_iterations` in config.json."
@@ -497,6 +498,7 @@ func (al *AgentLoop) processMessage(ctx context.Context, msg bus.InboundMessage)
 		Channel:         msg.Channel,
 		ChatID:          msg.ChatID,
 		UserMessage:     msg.Content,
+		Media:           msg.Media,
 		DefaultResponse: defaultResponse,
 		EnableSummary:   true,
 		SendResponse:    false,
@@ -603,11 +605,15 @@ func (al *AgentLoop) runAgentLoop(
 		history,
 		summary,
 		opts.UserMessage,
-		nil,
+		opts.Media,
 		opts.Channel,
 		opts.ChatID,
 	)
 
+	// Resolve media:// refs to base64 data URLs (streaming)
+	maxMediaSize := al.cfg.Agents.Defaults.GetMaxMediaSize()
+	messages = resolveMediaRefs(messages, al.mediaStore, maxMediaSize)
+
 	// 3. Save user message to session
 	agent.Sessions.AddMessage(opts.SessionKey, "user", opts.UserMessage)