C

handlers.go

@@ -55,7 +55,10 @@ func (b *Bot) handleVoiceMessage(ctx context.Context, message *models.Message, u
 
 	chatMemory := b.getOrCreateChatMemory(chatID)
 	contextMessages := b.prepareContextMessages(chatMemory)
-	segments, err := b.getAnthropicResponse(ctx, contextMessages, isNewChat, isOwner, false, username, firstName, lastName, isPremium, languageCode, messageTime)
+	// Voice path passes nil for onSegment: tool-call narration across multiple
+	// TTS clips would be jarring, so we accumulate everything and synthesize one
+	// audio clip from the joined text.
+	response, err := b.getAnthropicResponse(ctx, contextMessages, isNewChat, isOwner, false, username, firstName, lastName, isPremium, languageCode, messageTime, nil)
 	if err != nil {
 		ErrorLogger.Printf("Error getting Anthropic response for voice: %v", err)
 		if err := b.sendResponse(ctx, chatID, b.anthropicErrorResponse(err, userID), businessConnectionID); err != nil {
@@ -64,10 +67,6 @@ func (b *Bot) handleVoiceMessage(ctx context.Context, message *models.Message, u
 		return
 	}
 
-	// Voice replies always synthesize as one audio clip — tool-call narration
-	// across multiple TTS clips would be jarring, so we join here.
-	response := strings.Join(segments, "\n\n")
-
 	audioReader, err := b.generateSpeech(ctx, response)
 	if err != nil {
 		// TTS failed — fall back to text so the user still gets a reply.
@@ -365,22 +364,31 @@ func (b *Bot) handleUpdate(ctx context.Context, tgBot *bot.Bot, update *models.U
 	// Determine if the text contains only emojis
 	isEmojiOnly := isOnlyEmojis(text)
 
-	// Get response from Anthropic
-	segments, err := b.getAnthropicResponse(ctx, contextMessages, isNewChatFlag, isOwner, isEmojiOnly, username, firstName, lastName, isPremium, languageCode, messageTime)
+	// Stream Anthropic's reply, sending each completed text block to Telegram
+	// as it arrives — gives the conversational rhythm Claude uses around tool
+	// calls (text → pause for tool → text → pause → text), rather than a long
+	// upfront wait followed by all bubbles at once.
+	joined, err := b.getAnthropicResponse(
+		ctx, contextMessages, isNewChatFlag, isOwner, isEmojiOnly,
+		username, firstName, lastName, isPremium, languageCode, messageTime,
+		func(seg string) error {
+			return b.sendOneSegment(ctx, chatID, seg, businessConnectionID)
+		},
+	)
 	if err != nil {
 		ErrorLogger.Printf("Error getting Anthropic response: %v", err)
 		// Errors go out as a single message — no need to fan out a one-line error.
-		if err := b.sendResponse(ctx, chatID, b.anthropicErrorResponse(err, userID), businessConnectionID); err != nil {
-			ErrorLogger.Printf("Error sending response: %v", err)
+		if sendErr := b.sendResponse(ctx, chatID, b.anthropicErrorResponse(err, userID), businessConnectionID); sendErr != nil {
+			ErrorLogger.Printf("Error sending response: %v", sendErr)
 		}
 		return
 	}
 
-	// Successful LLM reply: deliver each text block as its own Telegram bubble,
-	// matching the conversational rhythm Claude uses around tool calls.
-	if err := b.sendMultiResponse(ctx, chatID, segments, businessConnectionID); err != nil {
-		ErrorLogger.Printf("Error sending response: %v", err)
-		return
+	// Record the full turn once, at end-of-stream. Same 1-reply-per-prompt
+	// invariant as the non-streaming path: one DB row, one answered_on stamp,
+	// one chat-memory entry containing the joined segments.
+	if _, storeErr := b.screenOutgoingMessage(chatID, joined); storeErr != nil {
+		ErrorLogger.Printf("Error recording assistant turn: %v", storeErr)
 	}
 }
 
@@ -419,13 +427,13 @@ func (b *Bot) generateStickerResponse(ctx context.Context, message Message, cont
 	// "Sent a sticker: <emoji>"), so the full conversation history is preserved.
 	if message.StickerFileID != "" {
 		messageTime := int(message.Timestamp.Unix())
-		segments, err := b.getAnthropicResponse(ctx, contextMessages, false, false, true, message.Username, "", "", false, "", messageTime)
+		// Sticker reactions are casual chit-chat; tool use is unusual here, so
+		// pass nil for onSegment and return the joined text for a single bubble.
+		response, err := b.getAnthropicResponse(ctx, contextMessages, false, false, true, message.Username, "", "", false, "", messageTime, nil)
 		if err != nil {
 			return "", err
 		}
-		// Sticker reactions are casual chit-chat; tool use is unusual here, so
-		// join into one message rather than fanning out as multiple bubbles.
-		return strings.Join(segments, "\n\n"), nil
+		return response, nil
 	}
 
 	return "Hmm, that's interesting!", nil