MCP error logging

handlers.go

@@ -10,9 +10,10 @@ import (
 	"github.com/anthropics/anthropic-sdk-go"
 	"github.com/go-telegram/bot"
 	"github.com/go-telegram/bot/models"
+	"golang.org/x/sync/errgroup"
 )
 
-func (b *Bot) handleVoiceMessage(ctx context.Context, message *models.Message, userMsg Message, chatID, userID int64, username, firstName, lastName string, isPremium bool, languageCode string, messageTime int, isNewChat, isOwner bool, businessConnectionID string) {
+func (b *Bot) handleVoiceMessage(ctx context.Context, message *models.Message, userMsg Message, chatID, userID int64, username, firstName, lastName string, isPremium bool, languageCode string, messageTime int, businessConnectionID string) {
 	// If ElevenLabs is not configured, respond with text — consistent with all other error paths.
 	if b.config.ElevenLabsAPIKey == "" {
 		if err := b.sendResponse(ctx, chatID, "I don't understand voice messages.", businessConnectionID); err != nil {
@@ -55,7 +56,10 @@ func (b *Bot) handleVoiceMessage(ctx context.Context, message *models.Message, u
 
 	chatMemory := b.getOrCreateChatMemory(chatID)
 	contextMessages := b.prepareContextMessages(chatMemory)
-	response, 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, chatID, contextMessages, 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 {
@@ -91,17 +95,163 @@ func (b *Bot) handleVoiceMessage(ctx context.Context, message *models.Message, u
 	}
 }
 
+// uploadPhotoFromItem downloads the largest PhotoSize from a Telegram message
+// item and uploads it to the Anthropic Files API tagged with the bot's filename
+// convention. Telegram serves photos as JPEG regardless of the user's original
+// format, so the content-type is fixed.
+func (b *Bot) uploadPhotoFromItem(ctx context.Context, item *models.Message, chatID int64) (string, error) {
+	photo := largestPhotoSize(item.Photo)
+	data, err := b.downloadTelegramFile(ctx, photo.FileID)
+	if err != nil {
+		return "", fmt.Errorf("download %s: %w", photo.FileID, err)
+	}
+	filename := formatUploadFilename(b.botID, chatID, item.ID, "jpg")
+	return b.uploadImageToAnthropic(ctx, data, filename, "image/jpeg")
+}
+
+// handlePhotoMessage processes a user turn that contains one or more photos —
+// either a single photo or a Telegram media_group (album) coalesced upstream.
+// For albums the caller passes the items sorted by message_id. Each item's
+// largest PhotoSize is downloaded and uploaded to the Anthropic Files API; the
+// resulting file_ids are persisted on a single Message row representing the
+// whole user turn. On any upload failure, compensating deletes fire against
+// already-uploaded file_ids and the DB row is not written — orphans on
+// Anthropic are preferred over poisoned DB references.
+func (b *Bot) handlePhotoMessage(
+	ctx context.Context,
+	items []*models.Message,
+	chatID, userID int64,
+	username, firstName, lastName string,
+	isPremium bool,
+	languageCode string,
+	messageTime int,
+	businessConnectionID string,
+) {
+	if len(items) == 0 {
+		return
+	}
+
+	// Phase 1: download + upload each photo in parallel. Album latency collapses
+	// from N*RTT to ~max(t_i) — relevant for the multi-screenshot use case.
+	// Caption capture happens in the sequential loop (one item carries it; order
+	// is preserved upstream via flushAlbum's sort by message_id). uploaded[i]
+	// matches items[i] so file_ids stay in user-intended order; non-photo items
+	// leave their slot empty and are compacted out before commit.
+	uploaded := make([]string, len(items))
+	caption := ""
+	g, gctx := errgroup.WithContext(ctx)
+	for i, item := range items {
+		if item.Caption != "" {
+			caption = item.Caption
+		}
+		if len(item.Photo) == 0 {
+			continue
+		}
+		i, item := i, item
+		g.Go(func() error {
+			fileID, err := b.uploadPhotoFromItem(gctx, item, chatID)
+			if err != nil {
+				return err
+			}
+			uploaded[i] = fileID
+			return nil
+		})
+	}
+	if err := g.Wait(); err != nil {
+		ErrorLogger.Printf("[%s] photo upload failed: %v", b.config.ID, err)
+		var successful []string
+		for _, fid := range uploaded {
+			if fid != "" {
+				successful = append(successful, fid)
+			}
+		}
+		b.compensatingDelete(ctx, successful)
+		if sendErr := b.sendResponse(ctx, chatID, "Sorry, I couldn't process one of your images.", businessConnectionID); sendErr != nil {
+			ErrorLogger.Printf("Error sending photo failure message: %v", sendErr)
+		}
+		return
+	}
+	finalUploaded := make([]string, 0, len(uploaded))
+	for _, fid := range uploaded {
+		if fid != "" {
+			finalUploaded = append(finalUploaded, fid)
+		}
+	}
+	if len(finalUploaded) == 0 {
+		return
+	}
+
+	// Phase 2: commit Message row. getOrCreateChatMemory MUST run before
+	// storeMessage — on a cold cache, the get-or-create hydrates from DB, and
+	// hydrating after the insert would re-load the just-stored row, causing
+	// addMessageToChatMemory below to produce a duplicate user turn. Mirrors
+	// the ordering used by screenIncomingMessage for the same reason.
+	chatMemory := b.getOrCreateChatMemory(chatID)
+	userMessage := b.createMessage(chatID, userID, username, "user", caption, true)
+	userMessage.ImageFileIDs = finalUploaded
+	if err := b.storeMessage(&userMessage); err != nil {
+		b.compensatingDelete(ctx, finalUploaded)
+		ErrorLogger.Printf("[%s] store photo message failed: %v", b.config.ID, err)
+		if sendErr := b.sendResponse(ctx, chatID, "Sorry, I had trouble saving your message.", businessConnectionID); sendErr != nil {
+			ErrorLogger.Printf("Error sending store failure message: %v", sendErr)
+		}
+		return
+	}
+	b.addMessageToChatMemory(chatMemory, userMessage)
+
+	// Phase 3: stream Anthropic's reply, same shape as the text path.
+	contextMessages := b.prepareContextMessages(chatMemory)
+	joined, err := b.getAnthropicResponse(
+		ctx, chatID, contextMessages, false,
+		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 for photo: %v", err)
+		if sendErr := b.sendResponse(ctx, chatID, b.anthropicErrorResponse(err, userID), businessConnectionID); sendErr != nil {
+			ErrorLogger.Printf("Error sending anthropic error response: %v", sendErr)
+		}
+		return
+	}
+	if _, storeErr := b.screenOutgoingMessage(chatID, joined); storeErr != nil {
+		ErrorLogger.Printf("Error recording assistant turn: %v", storeErr)
+	}
+}
+
 // anthropicErrorResponse returns the message to send back to the user when getAnthropicResponse
-// fails. Admins and owners receive an actionable hint when the model is deprecated; regular users
-// always get the generic fallback to avoid leaking internal details.
+// fails. Admins and owners (anyone with model:set scope) receive the underlying API error so they
+// can act on it — actionable hint for model-deprecation, raw status+body+request-id for everything
+// else. Regular users always get the generic fallback to avoid leaking internal details.
 func (b *Bot) anthropicErrorResponse(err error, userID int64) string {
-	if errors.Is(err, ErrModelNotFound) && b.hasScope(userID, ScopeModelSet) {
+	isElevated := b.hasScope(userID, ScopeModelSet)
+
+	if errors.Is(err, ErrModelNotFound) && isElevated {
 		return fmt.Sprintf(
 			"⚠️ Model `%s` is no longer available (deprecated or removed by Anthropic).\n"+
 				"Use /set_model <model-id> to switch. Current models: https://platform.claude.com/docs/en/about-claude/models/overview",
 			b.config.Model,
 		)
 	}
+
+	if isElevated {
+		var apiErr *anthropic.Error
+		if errors.As(err, &apiErr) {
+			body := apiErr.RawJSON()
+			if len(body) > 800 {
+				body = body[:800] + "...(truncated)"
+			}
+			out := fmt.Sprintf("⚠️ Anthropic API error %d:\n%s", apiErr.StatusCode, body)
+			if apiErr.RequestID != "" {
+				out += fmt.Sprintf("\nRequest-ID: %s", apiErr.RequestID)
+			}
+			return out
+		}
+		// Non-API errors (network, context cancel, etc.) — show the Go error text.
+		return fmt.Sprintf("⚠️ Anthropic call failed: %v", err)
+	}
+
 	return "I'm sorry, I'm having trouble processing your request right now."
 }
 
@@ -141,17 +291,8 @@ func (b *Bot) handleUpdate(ctx context.Context, tgBot *bot.Bot, update *models.U
 	messageTime := message.Date
 	text := message.Text
 
-	// Check if it's a new chat (before storing the message so the flag is accurate).
-	isNewChatFlag := b.isNewChat(chatID)
-
-	// Screen incoming message (store to DB + add to chat memory)
-	userMsg, err := b.screenIncomingMessage(message)
-	if err != nil {
-		ErrorLogger.Printf("Error storing user message: %v", err)
-		return
-	}
-
-	// Determine if the user is the owner
+	// Determine if the user is the owner — needed up-front so the album buffer
+	// can capture it alongside other per-turn metadata.
 	var isOwner bool
 	if b.db.Where("telegram_id = ? AND bot_id = ? AND is_owner = ?", userID, b.botID, true).First(&User{}).Error == nil {
 		isOwner = true
@@ -172,6 +313,34 @@ func (b *Bot) handleUpdate(ctx context.Context, tgBot *bot.Bot, update *models.U
 		}
 	}
 
+	// Photo routing bypasses screenIncomingMessage entirely: handlePhotoMessage
+	// owns its own DB-row creation (one row per coalesced user turn, holding
+	// all uploaded file_ids). Album items go through the 1s buffer first; only
+	// the flush dispatches to handlePhotoMessage.
+	if message.MediaGroupID != "" && len(message.Photo) > 0 {
+		b.bufferAlbumItem(ctx, message, chatID, userID, username, firstName, lastName,
+			isPremium, languageCode, messageTime, businessConnectionID)
+		return
+	}
+	if len(message.Photo) > 0 {
+		if !b.checkRateLimits(userID) {
+			b.sendRateLimitExceededMessage(ctx, chatID, businessConnectionID)
+			return
+		}
+		b.handlePhotoMessage(ctx, []*models.Message{message},
+			chatID, userID, username, firstName, lastName,
+			isPremium, languageCode, messageTime,
+			businessConnectionID)
+		return
+	}
+
+	// Screen incoming message (store to DB + add to chat memory) — text/voice/sticker only.
+	userMsg, err := b.screenIncomingMessage(message)
+	if err != nil {
+		ErrorLogger.Printf("Error storing user message: %v", err)
+		return
+	}
+
 	// Check if the message is a command — applies on every message, including the very first.
 	if message.Entities != nil {
 		for _, entity := range message.Entities {
@@ -317,7 +486,7 @@ func (b *Bot) handleUpdate(ctx context.Context, tgBot *bot.Bot, update *models.U
 	// Check if the message contains a voice note (context is built inside the handler
 	// after the transcript replaces the placeholder, so it must not be built here).
 	if message.Voice != nil {
-		b.handleVoiceMessage(ctx, message, userMsg, chatID, userID, username, firstName, lastName, isPremium, languageCode, messageTime, isNewChatFlag, isOwner, businessConnectionID)
+		b.handleVoiceMessage(ctx, message, userMsg, chatID, userID, username, firstName, lastName, isPremium, languageCode, messageTime, businessConnectionID)
 		return
 	}
 
@@ -340,17 +509,31 @@ 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
-	response, 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, chatID, contextMessages, 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)
-		response = b.anthropicErrorResponse(err, userID)
+		// Errors go out as a single message — no need to fan out a one-line error.
+		if sendErr := b.sendResponse(ctx, chatID, b.anthropicErrorResponse(err, userID), businessConnectionID); sendErr != nil {
+			ErrorLogger.Printf("Error sending response: %v", sendErr)
+		}
+		return
 	}
 
-	// Send the response
-	if err := b.sendResponse(ctx, chatID, response, 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)
 	}
 }
 
@@ -389,7 +572,9 @@ 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())
-		response, 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, message.ChatID, contextMessages, true, message.Username, "", "", false, "", messageTime, nil)
 		if err != nil {
 			return "", err
 		}
@@ -443,23 +628,27 @@ func (b *Bot) clearChatHistory(ctx context.Context, chatID int64, currentUserID
 	// useful for group moderation ("/clear <userID> <chatID>").
 	var err error
 	if hardDelete {
-		// Permanently delete messages
+		// Hard delete routes through hardDeleteScope, which orchestrates the
+		// soft-delete → Anthropic Files.Delete → Unscoped().Delete dance. Rows
+		// whose Anthropic-side file cleanup fails stay soft-deleted for the
+		// reconciliation job to retry.
 		if targetUserID == currentUserID {
 			// Own history — delete ALL messages (user + assistant) in the current chat.
-			err = b.db.Unscoped().Where("chat_id = ? AND bot_id = ?", chatID, b.botID).Delete(&Message{}).Error
+			err = b.hardDeleteScope(ctx, "chat_id = ? AND bot_id = ?", chatID, b.botID)
 			InfoLogger.Printf("User %d permanently deleted their own chat history in chat %d", currentUserID, chatID)
 		} else {
 			if targetChatID != 0 {
 				// Chat-scoped: delete ALL messages (user + assistant) in the specified chat.
-				err = b.db.Unscoped().Where("chat_id = ? AND bot_id = ?", targetChatID, b.botID).Delete(&Message{}).Error
+				err = b.hardDeleteScope(ctx, "chat_id = ? AND bot_id = ?", targetChatID, b.botID)
 				InfoLogger.Printf("Admin/owner %d permanently deleted chat history for user %d in chat %d", currentUserID, targetUserID, targetChatID)
 			} else {
-				// Bot-wide: delete all of the user's own messages across every chat, then delete
-				// assistant messages from their DM chat (where chat_id == user_id by Telegram convention).
-				err = b.db.Unscoped().Where("bot_id = ? AND user_id = ?", b.botID, targetUserID).Delete(&Message{}).Error
-				if err == nil {
-					err = b.db.Unscoped().Where("chat_id = ? AND bot_id = ? AND is_user = ?", targetUserID, b.botID, false).Delete(&Message{}).Error
-				}
+				// Bot-wide: user's own messages across every chat plus assistant
+				// responses in their DM chat (where chat_id == user_id by Telegram
+				// convention). The two clauses are collapsed into one OR-WHERE so
+				// the helper's three-step pattern covers both in a single pass.
+				err = b.hardDeleteScope(ctx,
+					"bot_id = ? AND (user_id = ? OR (chat_id = ? AND is_user = ?))",
+					b.botID, targetUserID, targetUserID, false)
 				InfoLogger.Printf("Admin/owner %d permanently deleted all chat history for user %d", currentUserID, targetUserID)
 			}
 		}