Support for images

bot.go

@@ -27,6 +27,11 @@ type Bot struct {
 	userLimitersMu  sync.RWMutex
 	clock           Clock
 	botID           uint // Reference to BotModel.ID
+	// albumBuffers holds Telegram media_group items as they arrive, keyed by
+	// MediaGroupID. Each pending album has a 1s flush timer (see album_buffer.go)
+	// that triggers a single coalesced photo turn once arrivals stop.
+	albumBuffers   map[string]*pendingAlbum
+	albumBuffersMu sync.Mutex
 }
 
 // Helper function to determine message type
@@ -94,6 +99,7 @@ func NewBot(db *gorm.DB, config BotConfig, clock Clock, tgClient TelegramClient)
 		clock:           clock,
 		botID:           botEntry.ID, // Ensure BotModel has ID field
 		tgBot:           tgClient,
+		albumBuffers:    make(map[string]*pendingAlbum),
 	}
 
 	if tgClient == nil {
@@ -251,6 +257,32 @@ func (b *Bot) getOrCreateChatMemory(chatID int64) *ChatMemory {
 	return chatMemory
 }
 
+// stripDeadFileIDFromMemory removes a single file_id from every message in the
+// chat's in-memory ChatMemory. Called by the runtime self-heal in
+// getAnthropicResponse after Anthropic 404s for that file_id, so the immediate
+// retry (and any subsequent turn replay) won't reference it. The corresponding
+// DB rows are stamped separately via markFilesPendingCleanup.
+func (b *Bot) stripDeadFileIDFromMemory(chatID int64, deadFileID string) {
+	b.chatMemoriesMu.Lock()
+	defer b.chatMemoriesMu.Unlock()
+	cm, exists := b.chatMemories[chatID]
+	if !exists {
+		return
+	}
+	for i := range cm.Messages {
+		if len(cm.Messages[i].ImageFileIDs) == 0 {
+			continue
+		}
+		survivors := make([]string, 0, len(cm.Messages[i].ImageFileIDs))
+		for _, fid := range cm.Messages[i].ImageFileIDs {
+			if fid != deadFileID {
+				survivors = append(survivors, fid)
+			}
+		}
+		cm.Messages[i].ImageFileIDs = survivors
+	}
+}
+
 // addMessageToChatMemory adds a new message to the chat memory, ensuring the memory size is maintained.
 func (b *Bot) addMessageToChatMemory(chatMemory *ChatMemory, message Message) {
 	b.chatMemoriesMu.Lock()
@@ -272,7 +304,7 @@ func (b *Bot) prepareContextMessages(chatMemory *ChatMemory) []anthropic.BetaMes
 	// Debug logging
 	InfoLogger.Printf("Chat memory contains %d messages", len(chatMemory.Messages))
 	for i, msg := range chatMemory.Messages {
-		InfoLogger.Printf("Message %d: IsUser=%v, Text=%q", i, msg.IsUser, msg.Text)
+		InfoLogger.Printf("Message %d: IsUser=%v, Text=%q Images=%d", i, msg.IsUser, msg.Text, len(msg.ImageFileIDs))
 	}
 
 	// Note: consecutive messages with the same role are permitted.
@@ -282,20 +314,18 @@ func (b *Bot) prepareContextMessages(chatMemory *ChatMemory) []anthropic.BetaMes
 	// See: https://platform.claude.com/docs/en/api/messages
 	var contextMessages []anthropic.BetaMessageParam
 	for _, msg := range chatMemory.Messages {
-		textContent := strings.TrimSpace(msg.Text)
-		if textContent == "" {
-			// Skip empty messages
+		blocks := contentBlocksForMessage(msg)
+		if len(blocks) == 0 {
+			// Skip turns that carry neither text nor images.
 			continue
 		}
-
-		block := anthropic.NewBetaTextBlock(textContent)
 		var param anthropic.BetaMessageParam
 		if msg.IsUser {
-			param = anthropic.NewBetaUserMessage(block)
+			param = anthropic.NewBetaUserMessage(blocks...)
 		} else {
 			param = anthropic.BetaMessageParam{
 				Role:    anthropic.BetaMessageParamRoleAssistant,
-				Content: []anthropic.BetaContentBlockParamUnion{block},
+				Content: blocks,
 			}
 		}
 		contextMessages = append(contextMessages, param)
@@ -303,6 +333,28 @@ func (b *Bot) prepareContextMessages(chatMemory *ChatMemory) []anthropic.BetaMes
 	return contextMessages
 }
 
+// contentBlocksForMessage assembles the Anthropic content blocks representing
+// one stored Message. Image blocks are emitted before the text block (Anthropic
+// docs: "Claude works best when images come before text"). Multi-image user
+// turns prepend each image with an "Image N:" label, as the docs explicitly
+// recommend for multi-image prompts. Assistant turns carry text only.
+func contentBlocksForMessage(msg Message) []anthropic.BetaContentBlockParamUnion {
+	var blocks []anthropic.BetaContentBlockParamUnion
+	if msg.IsUser && len(msg.ImageFileIDs) > 0 {
+		multi := len(msg.ImageFileIDs) > 1
+		for i, fileID := range msg.ImageFileIDs {
+			if multi {
+				blocks = append(blocks, anthropic.NewBetaTextBlock(fmt.Sprintf("Image %d:", i+1)))
+			}
+			blocks = append(blocks, anthropic.NewBetaImageBlock(anthropic.BetaFileImageSourceParam{FileID: fileID}))
+		}
+	}
+	if textContent := strings.TrimSpace(msg.Text); textContent != "" {
+		blocks = append(blocks, anthropic.NewBetaTextBlock(textContent))
+	}
+	return blocks
+}
+
 func (b *Bot) isNewChat(chatID int64) bool {
 	var count int64
 	b.db.Model(&Message{}).Where("chat_id = ? AND bot_id = ?", chatID, b.botID).Count(&count)
@@ -449,6 +501,27 @@ func (b *Bot) sendResponse(ctx context.Context, chatID int64, text string, busin
 	return nil
 }
 
+// sendOneSegment delivers a single Telegram message without touching storage
+// or chat memory. Used by the streaming response path: each completed text
+// block fires this helper as it arrives, and the full turn is recorded once
+// at end-of-stream via screenOutgoingMessage. Keeps the 1-reply-per-prompt
+// storage invariant while letting the user see segments with natural rhythm.
+func (b *Bot) sendOneSegment(ctx context.Context, chatID int64, text, businessConnectionID string) error {
+	params := &bot.SendMessageParams{
+		ChatID: chatID,
+		Text:   text,
+	}
+	if businessConnectionID != "" {
+		params.BusinessConnectionID = businessConnectionID
+	}
+	if _, err := b.tgBot.SendMessage(ctx, params); err != nil {
+		ErrorLogger.Printf("[%s] Error sending segment to chat %d with BusinessConnectionID %s: %v",
+			b.config.ID, chatID, businessConnectionID, err)
+		return err
+	}
+	return nil
+}
+
 // sendStats sends the bot statistics to the specified chat.
 func (b *Bot) sendStats(ctx context.Context, chatID int64, userID int64, targetUserID int64, businessConnectionID string) {
 	// If targetUserID is 0, show global stats