X-Git-Url: https://git.giacomolli.uk/onechat/blobdiff_plain/723f6e18adc6482ed913e1618c8a76e981720c2b..b1be0ee8530df5db8973bfe355f2f6d3149383a0:/tools.go?ds=sidebyside

diff --git a/tools.go b/tools.go
index a75514f..621cd84 100644
--- a/tools.go
+++ b/tools.go
@@ -27,9 +27,9 @@ const (
 	// output, enough for toolClipCharacters/2 characters of 4 bytes.
 	toolClipBytes = 4 * toolClipCharacters / 2
 
-	// toolShellWaitDelay is how long a command can keep its output open
+	// toolShellOutputTimeout is how long a command can keep its output open
 	// after it ends or after its kill.
-	toolShellWaitDelay = 2 * time.Second
+	toolShellOutputTimeout = 2 * time.Second
 )
 
 // ToolLog is the log that the tools write their calls and results to.
@@ -54,8 +54,8 @@ type ToolChat interface {
 // spawn and tell, the WhatsApp link for the WhatsApp tools, and the schedules
 // for the schedule tools. Each permanent agent has the parent-child queue. Only
 // the root has child creation and source routes. A child has neither of them
-// nor a WhatsApp link. The toolbox of a subagent has none of them, so these are
-// unknown tools there.
+// nor a WhatsApp link. Only the root can show images to the user. The toolbox
+// of a subagent has none of them, so these are unknown tools there.
 type Toolbox struct {
 	log       ToolLog
 	chat      ToolChat
@@ -68,13 +68,16 @@ type Toolbox struct {
 	messages  *DaemonMessages
 	children  *DaemonChildren
 	routes    *Routes
+	images    *ImageStore
+	imageShow *ImageShow
 }
 
 // Call logs the call of the tool name with its JSON arguments, makes the log
-// durable, runs the tool, and logs its clipped output, which it returns. A
-// failed tool gives its error as the output. An error of Call itself is an
-// error of the log. When ctx ends before the flush, the tool does not run.
-func (b *Toolbox) Call(ctx context.Context, name, arguments string) (string, error) {
+// durable, runs the tool, and logs its clipped text. It returns that text or
+// the text and image parts of a single-message zoom. Pixels never enter the
+// log. A failed tool gives its error as the output. An error of Call itself is
+// an error of the log. When ctx ends before the flush, the tool does not run.
+func (b *Toolbox) Call(ctx context.Context, name, arguments string) (any, error) {
 	_, err := b.log.Append("tool", toolCallText(name, arguments))
 	if err != nil {
 		return "", fmt.Errorf("append tool call: %w", err)
@@ -90,12 +93,26 @@ func (b *Toolbox) Call(ctx context.Context, name, arguments string) (string, err
 		output = toolClip(b.run(ctx, name, arguments))
 	}
 
+	var (
+		result    any = output
+		resultErr error
+	)
+
+	if err == nil {
+		result, resultErr = imageToolOutput(b, name, arguments, output)
+	}
+
+	if resultErr != nil {
+		output = "error: " + resultErr.Error()
+		result = output
+	}
+
 	_, err = b.log.Append("echo", output)
 	if err != nil {
 		return "", fmt.Errorf("append tool result: %w", err)
 	}
 
-	return output, nil
+	return result, nil
 }
 
 // run runs one tool and returns its output, or its error as text.
@@ -215,6 +232,16 @@ func (b *Toolbox) run(ctx context.Context, name, arguments string) string {
 		case err == nil:
 			output, err = b.runs.Tell(ctx, args.Name, args.Message)
 		}
+	case "image_show":
+		var args ToolImageShowArguments
+
+		err = toolDecodeArguments(arguments, &args)
+		switch {
+		case b.imageShow == nil:
+			err = fmt.Errorf("unknown tool %q", name)
+		case err == nil:
+			output, err = b.imageShow.Show(ctx, args.Image, args.Caption)
+		}
 	case "whatsapp_find":
 		var args ToolWhatsAppFindArguments
 
@@ -233,7 +260,7 @@ func (b *Toolbox) run(ctx context.Context, name, arguments string) string {
 		case b.whatsapp == nil:
 			err = fmt.Errorf("unknown tool %q", name)
 		case err == nil:
-			output, err = b.whatsapp.Send(ctx, args.ID, args.Chat, args.Text)
+			output, err = b.whatsapp.Send(ctx, args.ID, args.Chat, args.Text, args.Image)
 		}
 	case "schedule_set":
 		var args ToolScheduleSetArguments
@@ -363,7 +390,7 @@ func (b *Toolbox) shell(ctx context.Context, command string) string {
 	cmd.Cancel = func() error {
 		return syscall.Kill(-cmd.Process.Pid, syscall.SIGKILL)
 	}
-	cmd.WaitDelay = toolShellWaitDelay
+	cmd.WaitDelay = toolShellOutputTimeout
 
 	output := &ToolHeadTail{}
 	cmd.Stdout = output
@@ -533,6 +560,12 @@ type ToolTellArguments struct {
 	Message string `json:"message"`
 }
 
+// ToolImageShowArguments are the arguments of image_show.
+type ToolImageShowArguments struct {
+	Image   string `json:"image"`
+	Caption string `json:"caption"`
+}
+
 // ToolWhatsAppFindArguments are the arguments of whatsapp_find.
 type ToolWhatsAppFindArguments struct {
 	Name string `json:"name"`
@@ -540,9 +573,10 @@ type ToolWhatsAppFindArguments struct {
 
 // ToolWhatsAppSendArguments are the arguments of whatsapp_send.
 type ToolWhatsAppSendArguments struct {
-	ID   string `json:"id"`
-	Chat string `json:"chat"`
-	Text string `json:"text"`
+	ID    string `json:"id"`
+	Chat  string `json:"chat"`
+	Text  string `json:"text"`
+	Image string `json:"image"`
 }
 
 // ToolScheduleSetArguments are the arguments of schedule_set. Exactly one of At