Behavision/agent/cmd/behavision-setup/main.go

// Command behavision-setup prepares a shop PC to run the recognition engine.
//
// It exists because the engine is Python and the rest of the product is Go.
// The Go halves cross-compile to Windows from any machine; the engine, frozen
// with PyInstaller, does not - PyInstaller bundles the interpreter and native
// wheels of the machine it runs on, so a frozen engine can only be built on
// Windows. That single fact was the whole reason a release could not be cut.
//
// So this installs the engine from source instead of shipping it frozen: find
// a Python, build a private virtual environment beside the database, install
// the engine into it, fetch the models, and record how to start it. Everything
// in the release can then be built anywhere.
//
// The trade, stated plainly because whoever runs this is standing in a shop:
// it needs Python and a working internet connection at install time, and it
// takes minutes rather than seconds. A frozen build needs neither. What it
// buys is a release that exists.
package main

import (
	"bufio"
	"context"
	"errors"
	"fmt"
	"io"
	"net/http"
	"os"
	"os/exec"
	"path/filepath"
	"runtime"
	"strconv"
	"strings"
	"time"

	"bytes"
	"encoding/json"

	"github.com/loyaly/behavision-agent/pkg/config"
	"github.com/loyaly/behavision-agent/pkg/demo"
	"github.com/loyaly/behavision-agent/pkg/engine"
	"github.com/loyaly/behavision-agent/pkg/enrol"
	"github.com/loyaly/behavision-agent/pkg/paths"
)

// The engine needs 3.10; nothing here works below it and the failure would
// otherwise arrive as a syntax error deep inside a dependency.
const minMinor = 10

func main() {
	if err := run(); err != nil {
		fmt.Fprintf(os.Stderr, "\n  Setup did not finish: %v\n\n", err)
		pause()
		os.Exit(1)
	}
	pause()
}

func run() error {
	fmt.Println()
	fmt.Println("  Behavision setup")
	fmt.Println("  ----------------")
	fmt.Println()

	state := paths.StateRoot()
	src, err := engineSource()
	if err != nil {
		return err
	}
	fmt.Printf("  engine source   %s\n", src)
	fmt.Printf("  install into    %s\n", state)
	fmt.Println()

	if err := paths.EnsureState(); err != nil {
		return fmt.Errorf("could not create %s: %w", state, err)
	}

	// A demo release ships its cameras sealed. Ask for the code NOW, before
	// the ten-minute download, so a mistyped one costs seconds; the cameras
	// are actually added at the end, through the running engine.
	bundle, err := unlockDemo(src)
	if err != nil {
		return err
	}
	var demoCams []demo.Camera
	if bundle != nil {
		demoCams = bundle.Cameras
		switch {
		case bundle.EnrolCode != "":
			step("Demo", "unlocked - this PC will join a shop at head office")
		default:
			step("Demo cameras", fmt.Sprintf("%d unlocked", len(demoCams)))
		}
	}

	if running := behavisionRunning(); running != "" {
		// lint:ignore ST1005 — this is not a wrapped error, it is the whole
		// message an operator reads at a shop counter. ST1005 forbids
		// trailing punctuation because errors get concatenated mid-sentence;
		// nothing wraps this one, and stripping the full stops would make
		// three sentences run together.
		//lint:ignore ST1005 operator-facing prose, never wrapped
		return fmt.Errorf("%s is running. Quit Behavision from the tray icon first, then run setup again.\n\n"+
			"Setting up underneath a running copy starts a second engine on the same port and, in a demo,\n"+
			"re-claims the shop while the open app still holds the old credentials.", running)
	}

	py, ver, err := findPython()
	if err != nil {
		return err
	}
	step("Python", fmt.Sprintf("%s  (%s)", ver, py))

	venv := filepath.Join(state, "runtime")
	if err := makeVenv(py, venv); err != nil {
		return err
	}
	vpy := venvPython(venv)
	step("Virtual environment", venv)

	// The engine reads its settings from <state>/config/default.yaml and will
	// seed that from beside its own code on first run - which works when its
	// code is a checkout or a frozen folder and not when it is a package in
	// site-packages, where there is no config beside it. Seeded here, from the
	// copy the release ships. Never overwritten: an upgrade must not revert an
	// operator's thresholds.
	if err := seedConfig(src, state); err != nil {
		return err
	}
	step("Settings", filepath.Join(state, "config", "default.yaml"))

	// --upgrade so re-running after a new release replaces the engine rather
	// than leaving the old one in place and reporting success.
	if err := pipInstall(vpy, src); err != nil {
		return err
	}
	step("Engine and dependencies", "installed")

	if err := runEngine(vpy, "setup-models"); err != nil {
		return fmt.Errorf("downloading the recognition models: %w", err)
	}
	step("Recognition models", "downloaded")

	if err := writeConfig(vpy); err != nil {
		return err
	}
	step("Startup settings", filepath.Join(state, "agent.json"))

	// Proving it starts is the point. An installer that reports success and
	// leaves a shop with an engine that will not run has done worse than
	// failing: the failure surfaces later, to someone who did not install it.
	// Joining a shop: head office supplies the cameras, so any left on this PC
	// from an earlier install go first. Otherwise the reconciler offers them UP
	// to head office - without their passwords, which the engine never returns
	// - and the shop ends up with the same lens listed twice, one copy of which
	// can never be pushed to another PC. Measured on the first claimed demo.
	if bundle != nil && bundle.EnrolCode != "" {
		if err := os.Remove(paths.CamerasFile()); err == nil {
			step("Earlier cameras", "removed - head office supplies them now")
		}
	}
	if err := smokeTest(vpy, demoCams); err != nil {
		return fmt.Errorf("the engine installed but would not start: %w", err)
	}
	step("Engine starts and answers", "verified")
	if len(demoCams) > 0 {
		step("Demo cameras", "added to the engine")
	}
	switch {
	case bundle != nil && bundle.EnrolCode != "":
		// The demo that IS the product: this PC claims a real shop, exactly
		// as a customer install does, and its cameras arrive from head office
		// on the first sync. The app then opens on Login.
		siteName, err := claimShop(bundle.EnrolCode, bundle.CloudBase)
		if err != nil {
			return fmt.Errorf("could not join the shop at head office: %w", err)
		}
		step("Head office", "linked to "+siteName)
	case bundle != nil:
		// No head office in this demo. Without this the app opens on "type an
		// installation code" and sits there; with it, it opens on Live.
		if err := markStandalone(); err != nil {
			return err
		}
		step("Head office", "none - running on this PC only")
	}

	fmt.Println()
	fmt.Println("  Done. Start Behavision from the Start menu or the desktop icon.")
	fmt.Println("  It appears in the system tray; right-click there to stop it.")
	fmt.Println()
	return nil
}

func step(label, detail string) {
	fmt.Printf("  [ok] %-24s %s\n", label, detail)
}

// engineSource finds the Python source shipped beside this executable. Beside,
// not downloaded: the engine and the app must be the same release, and a
// version skew between them is the class of bug nobody can reproduce.
func engineSource() (string, error) {
	candidates := []string{
		filepath.Join(paths.InstallRoot(), "engine-src"),
		filepath.Join(paths.InstallRoot(), "..", "engine-src"),
	}
	if wd, err := os.Getwd(); err == nil {
		candidates = append(candidates, filepath.Join(wd, "engine-src"), wd)
	}
	for _, c := range candidates {
		if _, err := os.Stat(filepath.Join(c, "pyproject.toml")); err == nil {
			abs, _ := filepath.Abs(c)
			return abs, nil
		}
	}
	return "", errors.New("could not find the engine source (expected an " +
		"engine-src folder with pyproject.toml beside this program). " +
		"Unzip the whole release together rather than moving this file out of it")
}

// findPython returns the first interpreter that is new enough.
//
// `py -3` first on Windows: the launcher is what the official installer puts
// on PATH, and `python` there is often the Microsoft Store stub that prints an
// advert and exits 9009 instead of running anything.
// behavisionRunning names a Behavision process if one is up. Windows only -
// that is the platform setup ships on - and by image name via tasklist, which
// needs no extra privilege.
func behavisionRunning() string {
	if runtime.GOOS != "windows" {
		return ""
	}
	for _, name := range []string{"Behavision.exe", "behavision-agent.exe"} {
		out, err := exec.Command("tasklist", "/FI", "IMAGENAME eq "+name, "/NH").Output()
		if err == nil && strings.Contains(strings.ToLower(string(out)), strings.ToLower(name)) {
			return name
		}
	}
	return ""
}

func findPython() (string, string, error) {
	type cand struct {
		exe  string
		args []string
	}
	var cands []cand
	if runtime.GOOS == "windows" {
		cands = append(cands, cand{"py", []string{"-3"}})
	}
	cands = append(cands, cand{"python3", nil}, cand{"python", nil})

	var tried []string
	for _, c := range cands {
		exe, err := exec.LookPath(c.exe)
		if err != nil {
			continue
		}
		args := append(append([]string{}, c.args...), "-c",
			"import sys;print('%d.%d'%sys.version_info[:2])")
		out, err := exec.Command(exe, args...).Output()
		if err != nil {
			continue
		}
		ver := strings.TrimSpace(string(out))
		tried = append(tried, c.exe+" "+ver)
		if major, minor, ok := parseVer(ver); ok && (major > 3 || (major == 3 && minor >= minMinor)) {
			full := exe
			if len(c.args) > 0 {
				full = exe + " " + strings.Join(c.args, " ")
			}
			return full, "Python " + ver, nil
		}
	}

	// The advice has to match the machine. Telling a Mac user to tick "Add
	// python.exe to PATH" on a Windows installer page reads as software that
	// does not know where it is running, which is exactly the moment somebody
	// stops trusting the rest of what it says.
	msg := "no Python 3.10 or newer was found on this computer.\n\n"
	if runtime.GOOS == "windows" {
		msg += "    Install it from https://www.python.org/downloads/windows/\n" +
			"    and tick \"Add python.exe to PATH\" on the first screen,\n" +
			"    then run this again."
	} else {
		msg += "    Install it with `brew install python@3.12`, or from\n" +
			"    https://www.python.org/downloads/macos/, then run this again."
	}
	if len(tried) > 0 {
		msg += "\n\n    Found, but too old: " + strings.Join(tried, ", ")
	}
	return "", "", errors.New(msg)
}

func parseVer(s string) (int, int, bool) {
	parts := strings.Split(s, ".")
	if len(parts) < 2 {
		return 0, 0, false
	}
	major, err1 := strconv.Atoi(parts[0])
	minor, err2 := strconv.Atoi(parts[1])
	return major, minor, err1 == nil && err2 == nil
}

// splitLauncher turns `py -3` back into a command and its arguments.
func splitLauncher(s string) (string, []string) {
	f := strings.Fields(s)
	if len(f) == 0 {
		return s, nil
	}
	return f[0], f[1:]
}

func venvPython(venv string) string {
	if runtime.GOOS == "windows" {
		return filepath.Join(venv, "Scripts", "python.exe")
	}
	return filepath.Join(venv, "bin", "python")
}

// makeVenv builds the engine's own interpreter under the writable state root.
//
// A virtual environment rather than the system Python: a shop PC may have
// Python there for something else, and pinning numpy below 2.0 - which the
// engine requires - inside a shared interpreter is how you break the other
// thing months later, silently.
func makeVenv(py, venv string) error {
	if _, err := os.Stat(venvPython(venv)); err == nil {
		return nil // already built; pip below brings it up to date
	}
	exe, args := splitLauncher(py)
	args = append(args, "-m", "venv", venv)
	return stream(exec.Command(exe, args...), "creating the virtual environment")
}

func pipInstall(vpy, src string) error {
	fmt.Println("  Installing the engine and its libraries. This downloads a few")
	fmt.Println("  hundred megabytes and takes a while on a slow connection.")
	fmt.Println()
	if err := stream(exec.Command(vpy, "-m", "pip", "install", "--upgrade",
		"pip", "setuptools", "wheel"), "updating pip"); err != nil {
		return err
	}

	// A wheel if the release ships one - nothing to build on the shop PC, and
	// pip never has to touch the folder the release was unzipped into.
	//
	// That matters more than it sounds: `pip install <folder>` makes setuptools
	// write behavision.egg-info INTO that folder, and the folder is read-only
	// whenever the release was unzipped somewhere sensible - Program Files, or
	// the shared drive INSTALL.txt says is fine. Found by running this in a
	// container with the source mounted read-only: "could not create
	// 'behavision.egg-info': Read-only file system". Falling back to source
	// copies it somewhere writable first, for the same reason.
	if wheels, _ := filepath.Glob(filepath.Join(src, "behavision-*.whl")); len(wheels) > 0 {
		return stream(exec.Command(vpy, "-m", "pip", "install", "--upgrade", wheels[0]),
			"installing the engine")
	}
	tmp, err := os.MkdirTemp("", "behavision-src-")
	if err != nil {
		return err
	}
	defer os.RemoveAll(tmp)
	if err := copyTree(src, tmp); err != nil {
		return fmt.Errorf("staging the engine source: %w", err)
	}
	return stream(exec.Command(vpy, "-m", "pip", "install", "--upgrade", tmp),
		"installing the engine")
}

// seedConfig puts the shipped default.yaml where the engine will look for it,
// and leaves an existing one alone.
func seedConfig(src, state string) error {
	dst := filepath.Join(state, "config", "default.yaml")
	if _, err := os.Stat(dst); err == nil {
		return nil
	}
	from := filepath.Join(src, "config", "default.yaml")
	b, err := os.ReadFile(from)
	if err != nil {
		return fmt.Errorf("the release is missing config/default.yaml: %w", err)
	}
	if err := os.MkdirAll(filepath.Dir(dst), 0o755); err != nil {
		return err
	}
	return os.WriteFile(dst, b, 0o644)
}

// copyTree copies a source tree, skipping the caches a checkout accumulates.
func copyTree(from, to string) error {
	return filepath.WalkDir(from, func(path string, d os.DirEntry, err error) error {
		if err != nil {
			return err
		}
		rel, _ := filepath.Rel(from, path)
		if d.IsDir() {
			if d.Name() == "__pycache__" || strings.HasSuffix(d.Name(), ".egg-info") {
				return filepath.SkipDir
			}
			return os.MkdirAll(filepath.Join(to, rel), 0o755)
		}
		b, err := os.ReadFile(path)
		if err != nil {
			return err
		}
		return os.WriteFile(filepath.Join(to, rel), b, 0o644)
	})
}

// runEngine runs the engine exactly as the app will later: same interpreter,
// same environment. In particular ChildEnv sets BEHAVISION_DATA_DIR, without
// which a pip-installed engine decides its state lives in site-packages and
// downloads the models to a place the app never looks.
func runEngine(vpy string, args ...string) error {
	full := append([]string{"-m", "behavision"}, args...)
	cmd := exec.Command(vpy, full...)
	cmd.Env = engine.ChildEnv("")
	return stream(cmd, "running the engine")
}

// writeConfig records how to start the engine, in the same file and through
// the same type the app reads, so the two cannot disagree about it.
func writeConfig(vpy string) error {
	path := paths.AgentConfig()
	cfg, err := config.Load(path)
	if err != nil {
		return fmt.Errorf("reading %s: %w", path, err)
	}
	// An absolute path: the app resolves a relative EngineExe against its own
	// install root under Program Files, and the interpreter is not there.
	cfg.EngineExe = vpy
	cfg.EngineArgs = []string{"-m", "behavision", "run"}
	if cfg.APIBase == "" {
		cfg.APIBase = "http://127.0.0.1:8010"
	}
	return cfg.Save(path)
}

// smokeTest starts the engine exactly as the app will and waits for its API to
// answer. Any reply counts, including 401: the engine invents its own
// credential when none is configured, and a refusal proves it is serving.
func smokeTest(vpy string, demoCams []demo.Camera) error {
	ctx, cancel := context.WithTimeout(context.Background(), 120*time.Second)
	defer cancel()

	cmd := exec.CommandContext(ctx, vpy, "-m", "behavision", "run")
	cmd.Env = engine.ChildEnv("")
	var log strings.Builder
	cmd.Stdout, cmd.Stderr = &log, &log
	if err := cmd.Start(); err != nil {
		return err
	}
	defer func() {
		_ = cmd.Process.Kill()
		_, _ = cmd.Process.Wait()
	}()

	client := &http.Client{Timeout: 3 * time.Second}
	deadline := time.Now().Add(75 * time.Second)
	for time.Now().Before(deadline) {
		resp, err := client.Get("http://127.0.0.1:8010/api/health")
		if err == nil {
			_, _ = io.Copy(io.Discard, resp.Body)
			resp.Body.Close()
			if demoCams == nil {
				return nil
			}
			// Through the engine's own Add Camera, not written to its file:
			// the store is what applies DPAPI to the password on Windows, so
			// this is how the credential ends up encrypted on disk rather
			// than sitting in cameras.json for anyone who can read
			// ProgramData.
			return addCameras(demoCams)
		}
		if cmd.ProcessState != nil && cmd.ProcessState.Exited() {
			break
		}
		time.Sleep(2 * time.Second)
	}
	return fmt.Errorf("it did not answer within 75 seconds.\n\n%s",
		tail(log.String(), 15))
}

func tail(s string, n int) string {
	lines := strings.Split(strings.TrimRight(s, "\n"), "\n")
	if len(lines) > n {
		lines = lines[len(lines)-n:]
	}
	return "    " + strings.Join(lines, "\n    ")
}

// stream runs a command and shows its output. Shown, not swallowed: pip failing
// on a missing build tool prints exactly what is wrong, and hiding that leaves
// the operator with "setup failed" and nothing to act on.
func stream(cmd *exec.Cmd, what string) error {
	cmd.Stdout, cmd.Stderr = os.Stdout, os.Stderr
	if err := cmd.Run(); err != nil {
		return fmt.Errorf("%s failed: %w", what, err)
	}
	return nil
}

// pause keeps the window open. Double-clicked from Explorer, a console program
// that finishes closes instantly and the operator sees nothing at all -
// success and failure look identical.
func pause() {
	if runtime.GOOS != "windows" {
		return
	}
	fmt.Print("  Press Enter to close. ")
	_, _ = bufio.NewReader(os.Stdin).ReadString('\n')
}

// unlockDemo returns the sealed cameras a demo release ships, or nil when this
// is not a demo release. Asks for the unlock code on the console; three tries,
// because a code is read down a phone and typed by hand.
func unlockDemo(src string) (*demo.Payload, error) {
	sealed, err := os.ReadFile(filepath.Join(src, "demo-cameras.enc"))
	if err != nil {
		return nil, nil // not a demo release
	}
	fmt.Println()
	fmt.Println("  This is a demo release with the cameras already set up.")
	fmt.Println("  It needs the unlock code you were given.")
	fmt.Println()
	in := bufio.NewReader(os.Stdin)
	for attempt := 1; attempt <= 3; attempt++ {
		fmt.Print("  Unlock code: ")
		line, _ := in.ReadString('\n')
		plain, err := demo.Open(line, sealed)
		if err == nil {
			payload, err := demo.Decode(plain)
			if err != nil {
				return nil, fmt.Errorf("the bundle unlocked but did not parse: %w", err)
			}
			fmt.Println()
			return &payload, nil
		}
		fmt.Printf("  %v\n", err)
	}
	return nil, errors.New("no valid unlock code after three tries. Check it " +
		"with whoever gave you this release and run setup again")
}

// claimShop redeems the installation code sealed in the bundle: the same call
// the app's Setup screen and `behavision-agent claim` make, so the PC ends up
// in exactly the state a customer's would - broker login, API token, the
// broker's CA on disk - and head office pushes its cameras down on the first
// sync.
func claimShop(code, base string) (string, error) {
	if base == "" {
		base = "https://mcp.loyaly.ai"
	}
	ctx, cancel := context.WithTimeout(context.Background(), 30*time.Second)
	defer cancel()
	b, err := enrol.Claim(ctx, base, code)
	if err != nil {
		return "", err
	}
	path := paths.AgentConfig()
	cfg, err := config.Load(path)
	if err != nil {
		return "", err
	}
	cfg.ClientID = b.ClientSlug
	cfg.SiteID = b.SiteSlug
	cfg.SiteName = b.SiteName
	cfg.BrokerURL = b.MQTTURL
	cfg.BrokerUsername = b.MQTTUser
	cfg.BrokerPassword = b.MQTTPass
	cfg.AgentToken = b.AgentToken
	cfg.CloudBase = base
	cfg.Standalone = false
	cfg.SessionToken, cfg.SessionRefresh, cfg.SessionEmail = "", "", ""
	caPath, err := enrol.SaveCA(b.CACert, paths.BrokerCA())
	if err != nil {
		return "", err
	}
	cfg.BrokerCAFile = caPath
	if err := cfg.Save(path); err != nil {
		return "", err
	}
	return b.SiteName, nil
}

// addCameras posts each demo camera to the running engine, with the credential
// the engine generated for itself on first start.
func addCameras(cams []demo.Camera) error {
	user, pass, err := engineCredential()
	if err != nil {
		return err
	}
	client := &http.Client{Timeout: 30 * time.Second}
	for _, c := range cams {
		if c.Port == 0 {
			c.Port = 554
		}
		body, _ := json.Marshal(c)
		req, _ := http.NewRequest(http.MethodPost, "http://127.0.0.1:8010/api/cameras",
			bytes.NewReader(body))
		req.Header.Set("Content-Type", "application/json")
		if user != "" {
			req.SetBasicAuth(user, pass)
		}
		resp, err := client.Do(req)
		if err != nil {
			return fmt.Errorf("adding camera %s: %w", c.ID, err)
		}
		msg, _ := io.ReadAll(io.LimitReader(resp.Body, 4096))
		resp.Body.Close()
		// 409 is "already there" - a re-run of setup, which is allowed.
		if resp.StatusCode >= 300 && resp.StatusCode != http.StatusConflict {
			return fmt.Errorf("adding camera %s: %s: %s", c.ID, resp.Status,
				strings.TrimSpace(string(msg)))
		}
	}
	return nil
}

// engineCredential reads the Basic credential the engine wrote on its first
// start. Empty when the engine is configured without one.
func engineCredential() (string, string, error) {
	b, err := os.ReadFile(paths.APICredentials())
	if err != nil {
		if os.IsNotExist(err) {
			return "", "", nil
		}
		return "", "", err
	}
	var user, pass string
	for _, line := range strings.Split(string(b), "\n") {
		if v, ok := strings.CutPrefix(line, "username="); ok {
			user = strings.TrimSpace(v)
		}
		if v, ok := strings.CutPrefix(line, "password="); ok {
			pass = strings.TrimSpace(v)
		}
	}
	return user, pass, nil
}

// markStandalone records that this PC runs on its own, through the same
// config type the app reads.
func markStandalone() error {
	path := paths.AgentConfig()
	cfg, err := config.Load(path)
	if err != nil {
		return err
	}
	cfg.Standalone = true
	return cfg.Save(path)
}