X-Git-Url: https://git.giacomolli.uk/onechat/blobdiff_plain/48d7bce28b18ecef4c52c98821675605464cecb9..f5c601f1801aaa276f8c335fcb51c373edc0b50c:/telegram.go

diff --git a/telegram.go b/telegram.go
index f3b3bb2..4ed0861 100644
--- a/telegram.go
+++ b/telegram.go
@@ -108,6 +108,7 @@ func loadTelegramConfig(dir string) (TelegramConfig, bool, error) {
 func newTelegramBot(api *TelegramAPI, owner int64, offsetPath string, logger *slog.Logger) *TelegramBot {
 	return &TelegramBot{
 		api:        api,
+		voice:      &VoiceTranscriber{},
 		owner:      owner,
 		offsetPath: offsetPath,
 		logger:     logger,
@@ -139,13 +140,13 @@ 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 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 Bot API for new messages and sends owner text, images, and voice notes 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
@@ -158,6 +159,7 @@ func (c TelegramConfig) validate() error {
 // and the retries between them log nothing.
 type TelegramBot struct {
 	api        *TelegramAPI
+	voice      *VoiceTranscriber
 	owner      int64
 	offsetPath string
 	logger     *slog.Logger
@@ -399,8 +401,9 @@ func (b *TelegramBot) pause(ctx context.Context, outage *TelegramOutage, err err
 // /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. 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.
+// image store with their caption. Voice notes keep their audio and local
+// transcript. 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 {
@@ -412,6 +415,17 @@ func (b *TelegramBot) handle(ctx context.Context, l *TurnLoop, whatsapp *WhatsAp
 	name, stop := stopSubagentName(message.Text)
 	args, isWhatsApp := whatsappCommandArgs(message.Text)
 	switch {
+	case message.Voice != nil:
+		text := telegramVoiceText(ctx, b.api, l.agent.Voices(), b.voice, message)
+		_, err := l.Submit(telegramSource, text)
+		if err != nil {
+			return fmt.Errorf("submit Telegram voice: %w", err)
+		}
+
+		err = l.Flush(context.WithoutCancel(ctx))
+		if err != nil {
+			return fmt.Errorf("flush Telegram voice: %w", err)
+		}
 	case len(message.Photo) > 0 || message.Document != nil:
 		text, err := telegramImageText(ctx, b.api, l.agent.Images(), message)
 		if err != nil {