Send terminal images by local path

[onechat] / telegram.go

diff --git a/telegram.go b/telegram.go
index 2a9345a3a4b6823c0a17039c207dcf437f12d640..a595b68fd0d1756efc0b520e4c15d17781386c6a 100644 (file)
--- a/telegram.go
+++ b/telegram.go
@@ -7,7 +7,7 @@ import (
        "errors"
        "fmt"
        "io"
        "errors"
        "fmt"
        "io"

-       "log"
+       "log/slog"

        "net/http"
        "os"
        "path/filepath"
        "net/http"
        "os"
        "path/filepath"


@@ -97,7 +97,7 @@ func loadTelegramConfig(dir string) (TelegramConfig, bool, error) {
 // newTelegramBot returns the bot of owner on api. The offset file is at
 // offsetPath, and logger gets the failures. No log line holds the text of a
 // message.
 // newTelegramBot returns the bot of owner on api. The offset file is at
 // offsetPath, and logger gets the failures. No log line holds the text of a
 // message.

-func newTelegramBot(api *TelegramAPI, owner int64, offsetPath string, logger *log.Logger) *TelegramBot {
+func newTelegramBot(api *TelegramAPI, owner int64, offsetPath string, logger *slog.Logger) *TelegramBot {

        return &TelegramBot{
                api:        api,
                owner:      owner,
        return &TelegramBot{
                api:        api,
                owner:      owner,


@@ -133,13 +133,13 @@ func (c TelegramConfig) validate() error {
 }
 
 // TelegramBot connects the private chat of the owner with the agent. It polls
 }
 
 // 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
 //
 // 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


@@ -154,7 +154,7 @@ type TelegramBot struct {
        api        *TelegramAPI
        owner      int64
        offsetPath string
        api        *TelegramAPI
        owner      int64
        offsetPath string

-       logger     *log.Logger
+       logger     *slog.Logger

        minWait    time.Duration
        maxWait    time.Duration
 
        minWait    time.Duration
        maxWait    time.Duration
 


@@ -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
 }
 
 // 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()
 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 {
 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",
        }
 
                back:   "receive back",
        }
 

+       imageOutage := &TelegramOutage{
+               logger: b.logger,
+               loss:   "image receive failed",
+               back:   "image receive back",
+       }
+
+       imageWait := b.minWait

        wait := b.minWait
        wait := b.minWait

+
+poll:

        for ctx.Err() == nil {
                updates, err := b.api.GetUpdates(ctx, offset)
                if ctx.Err() != nil {
        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
                outage.End()
 
                wait = b.minWait

+

                for _, update := range updates {
                        if ctx.Err() != nil {
                                return nil
                        }
 
                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 {
                        if err != nil {

+                               retry, asked := telegramRetryable(err)
+                               if retry {
+                                       imageWait = b.pause(ctx, imageOutage, err, imageWait, asked)
+                                       continue poll
+                               }
+

                                return err
                        }
 
                                return err
                        }
 

+                       imageOutage.End()
+
+                       imageWait = b.minWait
+

                        offset = update.UpdateID + 1
                        err = telegramSaveOffset(b.offsetPath, offset)
                        if err != nil {
                        offset = update.UpdateID + 1
                        err = telegramSaveOffset(b.offsetPath, offset)
                        if err != nil {


@@ -373,13 +393,13 @@ 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
 // 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 {
 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 {

-               b.logger.Print("message ignored: not from the owner")
+               b.logger.Info("message ignored: not from the owner")

 
                return nil
        }
 
                return nil
        }


@@ -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 {
        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:
        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
                }
 
                        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)
                }
                if err != nil {
                        return fmt.Errorf("flush the message from Telegram: %w", err)
                }


@@ -440,7 +495,7 @@ func (b *TelegramBot) deliver(ctx context.Context, part TelegramPart) {
                var answer *TelegramError
 
                if len(part.entities) > 0 && errors.As(err, &answer) && answer.Status == http.StatusBadRequest {
                var answer *TelegramError
 
                if len(part.entities) > 0 && errors.As(err, &answer) && answer.Status == http.StatusBadRequest {

-                       b.logger.Printf("reply sent as plain text: %v", err)
+                       b.logger.Warn("reply sent as plain text", "err", err)

 
                        part.entities = nil
 
 
                        part.entities = nil
 


@@ -448,7 +503,7 @@ func (b *TelegramBot) deliver(ctx context.Context, part TelegramPart) {
                }
 
                if !retry {
                }
 
                if !retry {

-                       b.logger.Printf("reply lost: %v", err)
+                       b.logger.Error("reply lost", "err", err)

 
                        return
                }
 
                        return
                }


@@ -479,7 +534,7 @@ func (b *TelegramBot) deliverRich(ctx context.Context, markdown string) {
                }
 
                if telegramRejected(err) {
                }
 
                if telegramRejected(err) {

-                       b.logger.Printf("reply sent with simple formatting: %v", err)
+                       b.logger.Warn("reply sent with simple formatting", "err", err)

 
                        for _, part := range telegramReplyParts(telegramUnescapeTags(markdown)) {
                                b.deliver(ctx, part)
 
                        for _, part := range telegramReplyParts(telegramUnescapeTags(markdown)) {
                                b.deliver(ctx, part)


@@ -489,7 +544,7 @@ func (b *TelegramBot) deliverRich(ctx context.Context, markdown string) {
                }
 
                if !retry {
                }
 
                if !retry {

-                       b.logger.Printf("reply lost: %v", err)
+                       b.logger.Error("reply lost", "err", err)

 
                        return
                }
 
                        return
                }


@@ -520,7 +575,7 @@ func (b *TelegramBot) notice(text string) {
 // nothing. The next answer of Telegram logs back and the length of the outage.
 // loss and back say what the user loses and gets again.
 type TelegramOutage struct {
 // nothing. The next answer of Telegram logs back and the length of the outage.
 // loss and back say what the user loses and gets again.
 type TelegramOutage struct {

-       logger *log.Logger
+       logger *slog.Logger

        loss   string
        back   string
        start  time.Time
        loss   string
        back   string
        start  time.Time


@@ -533,7 +588,7 @@ func (o *TelegramOutage) Fail(err error, delay time.Duration) {
        }
 
        o.start = time.Now()
        }
 
        o.start = time.Now()

-       o.logger.Printf("%s: %v (retry in %s)", o.loss, err, durationText(delay))
+       o.logger.Warn(o.loss, "err", err, "retry", delay)

 }
 
 // End logs the end of the outage that runs, with its length.
 }
 
 // End logs the end of the outage that runs, with its length.


@@ -542,7 +597,7 @@ func (o *TelegramOutage) End() {
                return
        }
 
                return
        }
 

-       o.logger.Printf("%s after %s", o.back, durationText(time.Since(o.start)))
+       o.logger.Info(o.back, "after", time.Since(o.start))

 
        o.start = time.Time{}
 }
 
        o.start = time.Time{}
 }


@@ -721,10 +776,10 @@ func telegramRichCut(markdown string, limit int) (int, string, string) {
 
                end += start + 1
                text := strings.TrimRight(markdown[start:end], "\r\n")
 
                end += start + 1
                text := strings.TrimRight(markdown[start:end], "\r\n")

-               _, opens := telegramCodeFence(text)
+               _, opens := markdownCodeFence(text)

                switch {
                case fence != "":
                switch {
                case fence != "":

-                       if telegramClosesFence(text, fence) {
+                       if markdownClosesFence(text, fence) {

                                fence = ""
                        } else if end > len(opening)+1 && end+len(fence)+1 <= limit {
                                code, inFence, inOpening = end, fence, opening
                                fence = ""
                        } else if end > len(opening)+1 && end+len(fence)+1 <= limit {
                                code, inFence, inOpening = end, fence, opening