byre/internal/agents/hands.go

package agents

import (
	"context"
	"encoding/json"
	"fmt"
	"os"
	"os/exec"
	"path/filepath"
	"strings"
	"time"

	"g.fc.run/ai/byre/internal/api"
	"g.fc.run/ai/byre/internal/mcp"
)

const screenshotGuidance = "\n- When a turn changes something you can see, you can show it in your final message: save screenshots with the Playwright tools (pages you serve on this task's ports) or hands' capture with save (apps on this Mac), and embed each as a Markdown image, ![what it shows](<path>), with the path the tool returned. They go to the task's media folder, outside the worktree, so they are never committed, and are deleted when the task closes. Leave out a screenshot that adds nothing to the text."

func MediaDir(worktreePath string) string {
	return worktreePath + "-media"
}

func (m *Manager) handsDir(sessionID string) string {
	return filepath.Join(m.handsRoot, sessionID)
}

// replayd keys ScreenCaptureKit clients by executable path, so two hands
// processes run from one path keep cancelling each other's connection.
func (m *Manager) handsMCP(sessionID, mediaDir string) (mcp.Stdio, error) {
	dir := m.handsDir(sessionID)
	err := os.RemoveAll(dir)
	if err != nil {
		return mcp.Stdio{}, err
	}
	err = os.MkdirAll(dir, 0o755)
	if err != nil {
		return mcp.Stdio{}, err
	}
	bin, err := copyHands(dir)
	if err != nil {
		return mcp.Stdio{}, err
	}
	return mcp.Stdio{Name: "hands", Command: bin, Args: []string{"--media-dir", mediaDir}}, nil
}

func copyHands(dir string) (string, error) {
	src, err := exec.LookPath("byre-hands")
	if err != nil {
		return "", err
	}
	data, err := os.ReadFile(src)
	if err != nil {
		return "", err
	}
	bin := filepath.Join(dir, "byre-hands")
	return bin, os.WriteFile(bin, data, 0o755)
}

func (m *Manager) CheckPermissions(ctx context.Context) ([]api.Permission, error) {
	err := os.MkdirAll(m.handsRoot, 0o755)
	if err != nil {
		return nil, err
	}
	dir, err := os.MkdirTemp(m.handsRoot, "check-")
	if err != nil {
		return nil, err
	}
	defer os.RemoveAll(dir)
	bin, err := copyHands(dir)
	if err != nil {
		return nil, err
	}
	ctx, cancel := context.WithTimeout(ctx, 50*time.Second)
	defer cancel()
	cmd := exec.CommandContext(ctx, bin, "check")
	stderr := strings.Builder{}
	cmd.Stderr = &stderr
	out, err := cmd.Output()
	if ctx.Err() == context.DeadlineExceeded {
		return nil, fmt.Errorf("byre-hands check didn't finish within 50s; answer macOS's prompt on the server's Mac and check again")
	}
	if err != nil {
		return nil, fmt.Errorf("byre-hands check: %w: %s", err, strings.TrimSpace(stderr.String()))
	}
	perms := []api.Permission{}
	err = json.Unmarshal(out, &perms)
	if err != nil {
		return nil, fmt.Errorf("parse byre-hands check: %w", err)
	}
	return perms, nil
}