X-Git-Url: https://git.giacomolli.uk/onechat/blobdiff_plain/8fb85e5647f82e029956d81be29b3a5ac3490636..b2fc2d6a737dd5bab25e57ba822dd07258de93e6:/telegram.go?ds=sidebyside

diff --git a/telegram.go b/telegram.go
index f2c687a..a595b68 100644
--- a/telegram.go
+++ b/telegram.go
@@ -133,13 +133,13 @@ func (c TelegramConfig) validate() error {
 }
 
 // TelegramBot connects the private chat of the owner with the agent. It polls
-// the Bot API for new messages and sends each text message of the owner to the
-// agent. It ignores every other update. Its sender sends the replies, the
-// errors, the notices of the bot, and the user messages of the other clients to
-// the chat, and shows the typing action while a turn runs. Only the replies
-// have a format: their Markdown goes as rich messages, which Telegram renders
-// itself, and as message entities only when Telegram refuses a rich message.
-// The rest is plain text. Tool calls do not go to the chat.
+// the Bot API for new messages and sends owner text and images to the agent. It
+// ignores every other update. Its sender sends the replies, the errors, the
+// notices of the bot, and the user messages of the other clients to the chat,
+// and shows the typing action while a turn runs. Only the replies have a
+// format: their Markdown goes as rich messages, which Telegram renders itself,
+// and as message entities only when Telegram refuses a rich message. The rest
+// is plain text. Tool calls do not go to the chat.
 //
 // The offset file holds the ID of the next update. It moves past an update
 // only after the message of the update is durable in the log, so a restart
@@ -193,8 +193,8 @@ func (b *TelegramBot) Notify(event Event) {
 }
 
 // Run polls for the messages of the owner and sends the queued events to the
-// chat until ctx ends. It returns an error only when a message or the offset
-// cannot be written, because then the bot would lose or repeat messages.
+// chat until ctx ends. It returns an error only when a message or the offset or
+// image cannot be written, because then the bot would lose or repeat messages.
 func (b *TelegramBot) Run(ctx context.Context, l *TurnLoop, whatsapp *WhatsApp) error {
 	ctx, cancel := context.WithCancel(ctx)
 	defer cancel()
@@ -258,9 +258,9 @@ func (b *TelegramBot) send(ctx context.Context) {
 	}
 }
 
-// poll gets the updates from the stored offset on and handles each one, until
-// ctx ends. Each update is handled to its end also when ctx ends during it, so
-// a stop does not repeat its message.
+// poll gets updates from the stored offset and handles them until ctx ends. A
+// failed image download retries from the same offset. A submitted message is
+// flushed even if ctx ends, and only then can the offset advance.
 func (b *TelegramBot) poll(ctx context.Context, l *TurnLoop, whatsapp *WhatsApp) error {
 	offset, err := telegramLoadOffset(b.offsetPath)
 	if err != nil {
@@ -273,7 +273,16 @@ func (b *TelegramBot) poll(ctx context.Context, l *TurnLoop, whatsapp *WhatsApp)
 		back:   "receive back",
 	}
 
+	imageOutage := &TelegramOutage{
+		logger: b.logger,
+		loss:   "image receive failed",
+		back:   "image receive back",
+	}
+
+	imageWait := b.minWait
 	wait := b.minWait
+
+poll:
 	for ctx.Err() == nil {
 		updates, err := b.api.GetUpdates(ctx, offset)
 		if ctx.Err() != nil {
@@ -290,16 +299,27 @@ func (b *TelegramBot) poll(ctx context.Context, l *TurnLoop, whatsapp *WhatsApp)
 		outage.End()
 
 		wait = b.minWait
+
 		for _, update := range updates {
 			if ctx.Err() != nil {
 				return nil
 			}
 
-			err = b.handle(context.WithoutCancel(ctx), l, whatsapp, update)
+			err = b.handle(ctx, l, whatsapp, update)
 			if err != nil {
+				retry, asked := telegramRetryable(err)
+				if retry {
+					imageWait = b.pause(ctx, imageOutage, err, imageWait, asked)
+					continue poll
+				}
+
 				return err
 			}
 
+			imageOutage.End()
+
+			imageWait = b.minWait
+
 			offset = update.UpdateID + 1
 			err = telegramSaveOffset(b.offsetPath, offset)
 			if err != nil {
@@ -373,9 +393,9 @@ func (b *TelegramBot) pause(ctx context.Context, outage *TelegramOutage, err err
 // to the agent, and handle returns when it is durable in the log. The line
 // /stop interrupts the turn, the line /stop NAME stops the subagent NAME, and a
 // line that starts with /whatsapp runs a WhatsApp command on whatsapp, whose
-// answers go to the chat only. Any other message of the owner gets the answer
-// that only text is supported. Every other update is ignored, and its content
-// is not logged.
+// answers go to the chat only. Photos and image documents enter the shared
+// image store with their caption. Other media keep the text-only answer. Every
+// other update is ignored, and its content is not logged.
 func (b *TelegramBot) handle(ctx context.Context, l *TurnLoop, whatsapp *WhatsApp, update TelegramUpdate) error {
 	message := update.Message
 	if message == nil || message.Chat.Type != "private" || message.Chat.ID != b.owner || message.From == nil || message.From.ID != b.owner {
@@ -387,6 +407,41 @@ func (b *TelegramBot) handle(ctx context.Context, l *TurnLoop, whatsapp *WhatsAp
 	name, stop := stopSubagentName(message.Text)
 	args, isWhatsApp := whatsappCommandArgs(message.Text)
 	switch {
+	case len(message.Photo) > 0 || message.Document != nil:
+		text, err := telegramImageText(ctx, b.api, l.agent.Images(), message)
+		if err != nil {
+			retry, _ := telegramRetryable(err)
+			if retry {
+				return fmt.Errorf("receive image: %w", err)
+			}
+
+			switch {
+			case errors.Is(err, errTelegramOtherMedia):
+				b.notice(telegramTextOnly)
+			case errors.Is(err, errImageSize), errors.Is(err, errImageFormat), errors.Is(err, errTelegramPhotoSize):
+				b.notice(err.Error())
+			default:
+				var answer *TelegramError
+
+				if !errors.As(err, &answer) {
+					return fmt.Errorf("receive Telegram image: %w", err)
+				}
+
+				b.notice("Cannot download image.")
+			}
+
+			return nil
+		}
+
+		_, err = l.Submit(telegramSource, text)
+		if err != nil {
+			return fmt.Errorf("submit Telegram image: %w", err)
+		}
+
+		err = l.Flush(context.WithoutCancel(ctx))
+		if err != nil {
+			return fmt.Errorf("flush Telegram image: %w", err)
+		}
 	case message.Text == "":
 		b.notice(telegramTextOnly)
 	case strings.TrimSpace(message.Text) == stopCommand:
@@ -410,7 +465,7 @@ func (b *TelegramBot) handle(ctx context.Context, l *TurnLoop, whatsapp *WhatsAp
 			return err
 		}
 
-		err = l.Flush(ctx)
+		err = l.Flush(context.WithoutCancel(ctx))
 		if err != nil {
 			return fmt.Errorf("flush the message from Telegram: %w", err)
 		}