picoclaw/pkg/channels/telegram.go

package channels

import (
	"context"
	"fmt"
	"io"
	"log"
	"net/http"
	"os"
	"path/filepath"
	"regexp"
	"strings"
	"sync"
	"time"

	"github.com/mymmrac/telego"
	tu "github.com/mymmrac/telego/telegoutil"

	"github.com/sipeed/picoclaw/pkg/bus"
	"github.com/sipeed/picoclaw/pkg/config"
	"github.com/sipeed/picoclaw/pkg/voice"
)

type TelegramChannel struct {
	*BaseChannel
	bot          *telego.Bot
	config       config.TelegramConfig
	chatIDs      map[string]int64
	transcriber  *voice.GroqTranscriber
	placeholders sync.Map // chatID -> messageID
	stopThinking sync.Map // chatID -> chan struct{}
}

func NewTelegramChannel(cfg config.TelegramConfig, bus *bus.MessageBus) (*TelegramChannel, error) {
	bot, err := telego.NewBot(cfg.Token)
	if err != nil {
		return nil, fmt.Errorf("failed to create telegram bot: %w", err)
	}

	base := NewBaseChannel("telegram", cfg, bus, cfg.AllowFrom)

	return &TelegramChannel{
		BaseChannel:  base,
		bot:          bot,
		config:       cfg,
		chatIDs:      make(map[string]int64),
		transcriber:  nil,
		placeholders: sync.Map{},
		stopThinking: sync.Map{},
	}, nil
}

func (c *TelegramChannel) SetTranscriber(transcriber *voice.GroqTranscriber) {
	c.transcriber = transcriber
}

func (c *TelegramChannel) Start(ctx context.Context) error {
	log.Printf("Starting Telegram bot (polling mode)...")

	updates, err := c.bot.UpdatesViaLongPolling(ctx, &telego.GetUpdatesParams{
		Timeout: 30,
	})
	if err != nil {
		return fmt.Errorf("failed to start long polling: %w", err)
	}

	c.setRunning(true)
	log.Printf("Telegram bot @%s connected", c.bot.Username())

	go func() {
		for {
			select {
			case <-ctx.Done():
				return
			case update, ok := <-updates:
				if !ok {
					log.Printf("Updates channel closed, reconnecting...")
					return
				}
				if update.Message != nil {
					c.handleMessage(ctx, update)
				}
			}
		}
	}()

	return nil
}

func (c *TelegramChannel) Stop(ctx context.Context) error {
	log.Println("Stopping Telegram bot...")
	c.setRunning(false)
	return nil
}

func (c *TelegramChannel) Send(ctx context.Context, msg bus.OutboundMessage) error {
	if !c.IsRunning() {
		return fmt.Errorf("telegram bot not running")
	}

	chatID, err := parseChatID(msg.ChatID)
	if err != nil {
		return fmt.Errorf("invalid chat ID: %w", err)
	}

	// Stop thinking animation
	if stop, ok := c.stopThinking.Load(msg.ChatID); ok {
		close(stop.(chan struct{}))
		c.stopThinking.Delete(msg.ChatID)
	}

	htmlContent := markdownToTelegramHTML(msg.Content)

	// Try to edit placeholder
	if pID, ok := c.placeholders.Load(msg.ChatID); ok {
		c.placeholders.Delete(msg.ChatID)
		editMsg := tu.EditMessageText(tu.ID(chatID), pID.(int), htmlContent)
		editMsg.ParseMode = telego.ModeHTML

		if _, err = c.bot.EditMessageText(ctx, editMsg); err == nil {
			return nil
		}
		// Fallback to new message if edit fails
	}

	tgMsg := tu.Message(tu.ID(chatID), htmlContent)
	tgMsg.ParseMode = telego.ModeHTML

	if _, err = c.bot.SendMessage(ctx, tgMsg); err != nil {
		log.Printf("HTML parse failed, falling back to plain text: %v", err)
		tgMsg.ParseMode = ""
		_, err = c.bot.SendMessage(ctx, tgMsg)
		return err
	}

	return nil
}

func (c *TelegramChannel) handleMessage(ctx context.Context, update telego.Update) {
	message := update.Message
	if message == nil {
		return
	}

	user := message.From
	if user == nil {
		return
	}

	senderID := fmt.Sprintf("%d", user.ID)
	if user.Username != "" {
		senderID = fmt.Sprintf("%d|%s", user.ID, user.Username)
	}

	chatID := message.Chat.ID
	c.chatIDs[senderID] = chatID

	content := ""
	mediaPaths := []string{}

	if message.Text != "" {
		content += message.Text
	}

	if message.Caption != "" {
		if content != "" {
			content += "\n"
		}
		content += message.Caption
	}

	if message.Photo != nil && len(message.Photo) > 0 {
		photo := message.Photo[len(message.Photo)-1]
		photoPath := c.downloadPhoto(ctx, photo.FileID)
		if photoPath != "" {
			mediaPaths = append(mediaPaths, photoPath)
			if content != "" {
				content += "\n"
			}
			content += fmt.Sprintf("[image: %s]", photoPath)
		}
	}

	if message.Voice != nil {
		voicePath := c.downloadFile(ctx, message.Voice.FileID, ".ogg")
		if voicePath != "" {
			mediaPaths = append(mediaPaths, voicePath)

			transcribedText := ""
			if c.transcriber != nil && c.transcriber.IsAvailable() {
				ctx, cancel := context.WithTimeout(context.Background(), 30*time.Second)
				defer cancel()

				result, err := c.transcriber.Transcribe(ctx, voicePath)
				if err != nil {
					log.Printf("Voice transcription failed: %v", err)
					transcribedText = fmt.Sprintf("[voice: %s (transcription failed)]", voicePath)
				} else {
					transcribedText = fmt.Sprintf("[voice transcription: %s]", result.Text)
					log.Printf("Voice transcribed successfully: %s", result.Text)
				}
			} else {
				transcribedText = fmt.Sprintf("[voice: %s]", voicePath)
			}

			if content != "" {
				content += "\n"
			}
			content += transcribedText
		}
	}

	if message.Audio != nil {
		audioPath := c.downloadFile(ctx, message.Audio.FileID, ".mp3")
		if audioPath != "" {
			mediaPaths = append(mediaPaths, audioPath)
			if content != "" {
				content += "\n"
			}
			content += fmt.Sprintf("[audio: %s]", audioPath)
		}
	}

	if message.Document != nil {
		docPath := c.downloadFile(ctx, message.Document.FileID, "")
		if docPath != "" {
			mediaPaths = append(mediaPaths, docPath)
			if content != "" {
				content += "\n"
			}
			content += fmt.Sprintf("[file: %s]", docPath)
		}
	}

	if content == "" {
		content = "[empty message]"
	}

	log.Printf("Telegram message from %s: %s...", senderID, truncateString(content, 50))

	// Thinking indicator
	err := c.bot.SendChatAction(ctx, tu.ChatAction(tu.ID(chatID), telego.ChatActionTyping))
	if err != nil {
		log.Printf("Failed to send chat action: %v", err)
	}

	stopChan := make(chan struct{})
	c.stopThinking.Store(fmt.Sprintf("%d", chatID), stopChan)

	pMsg, err := c.bot.SendMessage(ctx, tu.Message(tu.ID(chatID), "Thinking... 💭"))
	if err == nil {
		pID := pMsg.MessageID
		c.placeholders.Store(fmt.Sprintf("%d", chatID), pID)

		go func(cid int64, mid int, stop <-chan struct{}) {
			dots := []string{".", "..", "..."}
			emotes := []string{"💭", "🤔", "☁️"}
			i := 0
			ticker := time.NewTicker(2000 * time.Millisecond)
			defer ticker.Stop()
			for {
				select {
				case <-stop:
					return
				case <-ticker.C:
					i++
					text := fmt.Sprintf("Thinking%s %s", dots[i%len(dots)], emotes[i%len(emotes)])
					_, editErr := c.bot.EditMessageText(ctx, tu.EditMessageText(tu.ID(chatID), mid, text))
					if editErr != nil {
						log.Printf("Failed to edit thinking message: %v", editErr)
					}
				}
			}
		}(chatID, pID, stopChan)
	}

	metadata := map[string]string{
		"message_id": fmt.Sprintf("%d", message.MessageID),
		"user_id":    fmt.Sprintf("%d", user.ID),
		"username":   user.Username,
		"first_name": user.FirstName,
		"is_group":   fmt.Sprintf("%t", message.Chat.Type != "private"),
	}

	c.HandleMessage(senderID, fmt.Sprintf("%d", chatID), content, mediaPaths, metadata)
}

func (c *TelegramChannel) downloadPhoto(ctx context.Context, fileID string) string {
	file, err := c.bot.GetFile(ctx, &telego.GetFileParams{FileID: fileID})
	if err != nil {
		log.Printf("Failed to get photo file: %v", err)
		return ""
	}

	return c.downloadFileWithInfo(file, ".jpg")
}

func (c *TelegramChannel) downloadFileWithInfo(file *telego.File, ext string) string {
	if file.FilePath == "" {
		return ""
	}

	url := c.bot.FileDownloadURL(file.FilePath)
	log.Printf("File URL: %s", url)

	mediaDir := filepath.Join(os.TempDir(), "picoclaw_media")
	if err := os.MkdirAll(mediaDir, 0755); err != nil {
		log.Printf("Failed to create media directory: %v", err)
		return ""
	}

	localPath := filepath.Join(mediaDir, file.FilePath[:min(16, len(file.FilePath))]+ext)

	if err := c.downloadFromURL(url, localPath); err != nil {
		log.Printf("Failed to download file: %v", err)
		return ""
	}

	return localPath
}

func (c *TelegramChannel) downloadFromURL(url, localPath string) error {
	resp, err := http.Get(url)
	if err != nil {
		return fmt.Errorf("failed to download: %w", err)
	}
	defer resp.Body.Close()

	if resp.StatusCode != http.StatusOK {
		return fmt.Errorf("download failed with status: %d", resp.StatusCode)
	}

	out, err := os.Create(localPath)
	if err != nil {
		return fmt.Errorf("failed to create file: %w", err)
	}
	defer out.Close()

	_, err = io.Copy(out, resp.Body)
	if err != nil {
		return fmt.Errorf("failed to write file: %w", err)
	}

	log.Printf("File downloaded successfully to: %s", localPath)
	return nil
}

func (c *TelegramChannel) downloadFile(ctx context.Context, fileID, ext string) string {
	file, err := c.bot.GetFile(ctx, &telego.GetFileParams{FileID: fileID})
	if err != nil {
		log.Printf("Failed to get file: %v", err)
		return ""
	}

	if file.FilePath == "" {
		return ""
	}

	url := c.bot.FileDownloadURL(file.FilePath)
	log.Printf("File URL: %s", url)

	mediaDir := filepath.Join(os.TempDir(), "picoclaw_media")
	if err = os.MkdirAll(mediaDir, 0755); err != nil {
		log.Printf("Failed to create media directory: %v", err)
		return ""
	}

	localPath := filepath.Join(mediaDir, fileID[:16]+ext)

	if err = c.downloadFromURL(url, localPath); err != nil {
		log.Printf("Failed to download file: %v", err)
		return ""
	}

	return localPath
}

func parseChatID(chatIDStr string) (int64, error) {
	var id int64
	_, err := fmt.Sscanf(chatIDStr, "%d", &id)
	return id, err
}

func truncateString(s string, maxLen int) string {
	if len(s) <= maxLen {
		return s
	}
	return s[:maxLen]
}

func markdownToTelegramHTML(text string) string {
	if text == "" {
		return ""
	}

	codeBlocks := extractCodeBlocks(text)
	text = codeBlocks.text

	inlineCodes := extractInlineCodes(text)
	text = inlineCodes.text

	text = regexp.MustCompile(`^#{1,6}\s+(.+)$`).ReplaceAllString(text, "$1")

	text = regexp.MustCompile(`^>\s*(.*)$`).ReplaceAllString(text, "$1")

	text = escapeHTML(text)

	text = regexp.MustCompile(`\[([^\]]+)\]\(([^)]+)\)`).ReplaceAllString(text, `<a href="$2">$1</a>`)

	text = regexp.MustCompile(`\*\*(.+?)\*\*`).ReplaceAllString(text, "<b>$1</b>")

	text = regexp.MustCompile(`__(.+?)__`).ReplaceAllString(text, "<b>$1</b>")

	reItalic := regexp.MustCompile(`_([^_]+)_`)
	text = reItalic.ReplaceAllStringFunc(text, func(s string) string {
		match := reItalic.FindStringSubmatch(s)
		if len(match) < 2 {
			return s
		}
		return "<i>" + match[1] + "</i>"
	})

	text = regexp.MustCompile(`~~(.+?)~~`).ReplaceAllString(text, "<s>$1</s>")

	text = regexp.MustCompile(`^[-*]\s+`).ReplaceAllString(text, "• ")

	for i, code := range inlineCodes.codes {
		escaped := escapeHTML(code)
		text = strings.ReplaceAll(text, fmt.Sprintf("\x00IC%d\x00", i), fmt.Sprintf("<code>%s</code>", escaped))
	}

	for i, code := range codeBlocks.codes {
		escaped := escapeHTML(code)
		text = strings.ReplaceAll(text, fmt.Sprintf("\x00CB%d\x00", i), fmt.Sprintf("<pre><code>%s</code></pre>", escaped))
	}

	return text
}

type codeBlockMatch struct {
	text  string
	codes []string
}

func extractCodeBlocks(text string) codeBlockMatch {
	re := regexp.MustCompile("```[\\w]*\\n?([\\s\\S]*?)```")
	matches := re.FindAllStringSubmatch(text, -1)

	codes := make([]string, 0, len(matches))
	for _, match := range matches {
		codes = append(codes, match[1])
	}

	text = re.ReplaceAllStringFunc(text, func(m string) string {
		return fmt.Sprintf("\x00CB%d\x00", len(codes)-1)
	})

	return codeBlockMatch{text: text, codes: codes}
}

type inlineCodeMatch struct {
	text  string
	codes []string
}

func extractInlineCodes(text string) inlineCodeMatch {
	re := regexp.MustCompile("`([^`]+)`")
	matches := re.FindAllStringSubmatch(text, -1)

	codes := make([]string, 0, len(matches))
	for _, match := range matches {
		codes = append(codes, match[1])
	}

	text = re.ReplaceAllStringFunc(text, func(m string) string {
		return fmt.Sprintf("\x00IC%d\x00", len(codes)-1)
	})

	return inlineCodeMatch{text: text, codes: codes}
}

func escapeHTML(text string) string {
	text = strings.ReplaceAll(text, "&", "&amp;")
	text = strings.ReplaceAll(text, "<", "&lt;")
	text = strings.ReplaceAll(text, ">", "&gt;")
	return text
}