Pin compose example to v0.2.2

README.md

@@ -58,14 +58,14 @@ override file values. Invalid values fail at startup.
 | `LLM_BUSY_STATUS` | `503` | HTTP status for rejected LLM requests in reject mode (400–599, e.g. 429) |
 | `BUSY_RETRY_AFTER` | `30` | Seconds sent as `Retry-After` on busy responses (both modes) |
 | `WARM_MODEL` | _(empty)_ | Model to reload after an image job (off by default) |
-| `COMFY_CMD` | _(empty = unmanaged)_ | Supervise ComfyUI: start on demand, stop when idle to free VRAM. Requires `COMFY_URL` |
-| `COMFY_DIR` | _(empty)_ | Working directory for `COMFY_CMD` |
+| `COMFY_CMD` | _(derived from `COMFY_DIR`; both empty = unmanaged)_ | Supervise ComfyUI: start on demand, stop when idle to free VRAM. Requires `COMFY_URL` |
+| `COMFY_DIR` | _(empty)_ | Standard venv install root: set alone to supervise ComfyUI with the derived command (`.venv` + `main.py`); also the working directory for `COMFY_CMD` |
 | `COMFY_IDLE_TIMEOUT` | `5m` | Stop the managed ComfyUI after this long idle |
 | `COMFY_START_TIMEOUT` | `2m` | Max wait for the managed ComfyUI to come up |
 | `GAME_PROCS` | _(empty = disabled)_ | Process names (comma-separated); while any runs, the GPU counts as held: requests wait, Ollama unloads, managed ComfyUI stops |
 | `GPU_FOREIGN_VRAM_MB` | `0` (disabled) | Also treat the GPU as held when a non-ignored process uses more VRAM than this (needs nvidia-smi) |
 | `GPU_IGNORE_PROCS` | `ollama,ollama app,ollama_llama_server,python,pythonw` | Process names never counted as foreign GPU users |
-| `GAME_POLL_INTERVAL` | `5s` | How often game/VRAM detection runs |
+| `GAME_POLL_INTERVAL` | `15s` | How often game/VRAM detection runs (don't go below ~10s — nvidia-smi polls keep the GPU awake) |
 | `LOGLEVEL` | `warn` | `info` logs every request (colored arrows in text mode), `debug` adds lock transitions. `LOG_LEVEL` works as an alias |
 | `LOG_FORMAT` | `text` | `json` for structured JSON logs |
 | `LOG_FILE` | _(empty)_ | Append logs to this file instead of stderr |
@@ -99,18 +99,28 @@ override file values. Invalid values fail at startup.
   class) in text mode, which renders in `docker compose logs` on Windows
   Terminal. Set `NO_COLOR` to disable colors.
 
-## Managed ComfyUI (`COMFY_CMD`)
+## Managed ComfyUI (`COMFY_CMD` / `COMFY_DIR`)
 
 Don't want ComfyUI running 24/7 (it holds VRAM even when idle — and the
-Desktop app kills its server when you close it)? Point `COMFY_CMD` at a
-standalone launch command and gpu-turnstile supervises it: the first
-request starts it, it stops again after `COMFY_IDLE_TIMEOUT` (default 5m)
-without work, freeing the GPU for games or the LLM. Example for a Desktop
-install (run it once manually to confirm it works):
+Desktop app kills its server when you close it)? gpu-turnstile can supervise
+it: the first request starts it, it stops again after `COMFY_IDLE_TIMEOUT`
+(default 5m) without work, freeing the GPU for games or the LLM.
+
+The easy way — point `COMFY_DIR` at a standard venv install (a folder with
+`.venv` and `main.py`, or `.venv` and `ComfyUI\main.py`) and the launch
+command is derived from it, including `--port` from `COMFY_URL`:
 
 ```
-COMFY_URL=http://127.0.0.1:8188
-COMFY_CMD="C:\ComfyUI\.venv\Scripts\python.exe ComfyUI\main.py --port 8188"
+COMFY_URL=http://127.0.0.1:8189
+COMFY_DIR=C:\ComfyUI
+```
+
+For other layouts, spell the command out yourself (run it once manually to
+confirm it works):
+
+```
+COMFY_URL=http://127.0.0.1:8189
+COMFY_CMD="C:\ComfyUI\.venv\Scripts\python.exe" main.py --port 8189
 COMFY_DIR=C:\ComfyUI
 ```
 
@@ -124,13 +134,22 @@ answers on the port, gpu-turnstile just uses it instead of spawning
 instance already holds the port when you open the desktop app, the
 desktop's server is the one that fails to bind.
 
+One catch when gpu-turnstile runs as a service: the sandboxed service
+account may not enter your user profile, so a ComfyUI install under
+`C:\Users\...` (or `/home/...`) fails with "Access is denied".
+`--install-service` fixes that automatically — it grants
+`NT SERVICE\gpu-turnstile` recursive access to `COMFY_DIR` on Windows and
+adds a `BindPaths=` to the systemd unit on Linux. Re-run it after changing
+`COMFY_DIR`; or grant by hand from an admin shell:
+`icacls "<COMFY_DIR>" /grant "NT SERVICE\gpu-turnstile:(OI)(CI)M" /T`.
+
 ## Game detection
 
 Want to game on the same GPU without Ollama/ComfyUI squatting on the VRAM?
 gpu-turnstile can watch for foreign GPU holders and, while one is active,
 make LLM/image requests wait (or 503, per `LLM_BUSY_MODE`), unload Ollama's
 models and stop the managed ComfyUI so the game gets the memory. Two
-detection paths, each optional, polled every `GAME_POLL_INTERVAL` (5s):
+detection paths, each optional, polled every `GAME_POLL_INTERVAL` (15s):
 
 ```
 GAME_PROCS=cyberpunk2077.exe,bg3.exe     # the reliable way on Windows

SPEC.md

@@ -128,10 +128,15 @@ state is `idle`, send `POST /api/generate {"model":WARM_MODEL,"keep_alive":-1}`
 with empty prompt to reload the chat model so the next chat doesn't pay the
 load time. Off by default.
 
-### Managed ComfyUI (`COMFY_CMD`)
+### Managed ComfyUI (`COMFY_CMD` / `COMFY_DIR`)
 
 When `COMFY_CMD` is set, gpu-turnstile runs ComfyUI as a supervised child
-process instead of expecting an always-on server:
+process instead of expecting an always-on server. Setting only `COMFY_DIR`
+enables the same management with the launch command derived from the
+standard venv layout under it (`.venv\Scripts\python.exe` on Windows,
+`.venv/bin/python` on Linux; `ComfyUI\main.py`, or a flat `main.py` when
+that is what exists; `--port` from the `COMFY_URL` port). Missing layout
+files are flagged in the startup log.
 
 - **Start on demand**: any ComfyUI request spawns it (double quotes in the
   command line group arguments with spaces; `COMFY_DIR` sets the working
@@ -154,12 +159,20 @@ process instead of expecting an always-on server:
 - Its stdout/stderr is forwarded to the log at INFO. The health check
   skips the intentionally-stopped/starting states; a failed probe while
   the process is alive and was previously ready is logged as DOWN.
+- **Permissions**: the service account is sandboxed (Windows virtual
+  account, systemd `DynamicUser`), so a ComfyUI install inside a user
+  profile is off-limits by default. `--install-service` opens it up —
+  a recursive ACL grant for `NT SERVICE\gpu-turnstile` on Windows, a
+  `BindPaths=` in the unit on Linux — reading `COMFY_DIR` from the config
+  it installs. Re-run `--install-service` after changing `COMFY_DIR`, or
+  grant by hand (admin shell):
+  `icacls "<COMFY_DIR>" /grant "NT SERVICE\gpu-turnstile:(OI)(CI)M" /T`.
 
 ## Game detection (foreign GPU holders)
 
 Games and other foreign GPU users sit outside the URL-based consumer model —
 nothing proxies through gpu-turnstile for them. Two independent detection
-paths, polled every `GAME_POLL_INTERVAL` (default 5 s); either one being
+paths, polled every `GAME_POLL_INTERVAL` (default 15 s); either one being
 configured enables the feature:
 
 - **Process watch list** (`GAME_PROCS`, comma-separated, case-insensitive,
@@ -211,14 +224,14 @@ override file values. A missing file is fine; a malformed one is fatal.
 | `LLM_BUSY_STATUS` | `503` | HTTP status for rejected LLM requests in reject mode (400–599, e.g. 429) |
 | `BUSY_RETRY_AFTER` | `30` | seconds sent as `Retry-After` on busy responses (both modes) |
 | `WARM_MODEL` | `` | optional model to reload after an image job |
-| `COMFY_CMD` | _(empty = unmanaged)_ | spawn and supervise ComfyUI on demand: first request starts it, idle stop after `COMFY_IDLE_TIMEOUT` frees its VRAM. Requires `COMFY_URL` |
-| `COMFY_DIR` | `` | working directory for `COMFY_CMD` |
+| `COMFY_CMD` | _(derived from `COMFY_DIR`; both empty = unmanaged)_ | spawn and supervise ComfyUI on demand: first request starts it, idle stop after `COMFY_IDLE_TIMEOUT` frees its VRAM. Requires `COMFY_URL` |
+| `COMFY_DIR` | `` | standard venv install root: set alone to supervise ComfyUI with the derived launch command (`.venv` + `main.py`, `--port` from `COMFY_URL`); also the working directory for `COMFY_CMD` |
 | `COMFY_IDLE_TIMEOUT` | `5m` | stop the managed ComfyUI after this long without requests or jobs |
 | `COMFY_START_TIMEOUT` | `2m` | how long a request waits for the managed ComfyUI to come up |
 | `GAME_PROCS` | _(empty = disabled)_ | comma-separated process names (case-insensitive, `.exe` optional); while any runs, the GPU counts as held by it: requests wait, Ollama unloads, the managed ComfyUI stops |
 | `GPU_FOREIGN_VRAM_MB` | `0` (disabled) | also treat the GPU as held when a process not in `GPU_IGNORE_PROCS` uses more VRAM than this; needs nvidia-smi |
 | `GPU_IGNORE_PROCS` | `ollama,ollama app,ollama_llama_server,python,pythonw` | process names never counted as foreign GPU users |
-| `GAME_POLL_INTERVAL` | `5s` | how often game/VRAM detection runs |
+| `GAME_POLL_INTERVAL` | `15s` | how often game/VRAM detection runs (nvidia-smi polls keep the GPU awake; don't go below ~10s) |
 | `LOGLEVEL` | `warn` | `info` logs every request (colored arrows in text mode), `debug` adds lock transitions. `LOG_LEVEL` is accepted as an alias |
 | `LOG_FORMAT` | `text` | `json` for structured JSON logs |
 | `LOG_FILE` | `` | append logs to this file instead of stderr (useful as a service) |
@@ -237,7 +250,7 @@ override file values. A missing file is fine; a malformed one is fatal.
 | `UPDATE_REPO` | `https://git.rambossek.at/PUBLIC/gpu-turnstile` | repository to check for releases |
 | `UPDATE_ASSET` | `gpu-turnstile.exe` | release asset to download |
 | `APP_VER` | `stable` | version to run: `dev` disables updates, `stable` tracks the latest release, or an exact `vX.Y.Z` pin (up- or downgraded to) |
-| `CFG_VER` | _(installer-managed)_ | config format reference written by `--install-service` (always a concrete `vX.Y.Z`; a dev build stamps `v0.0.0`); missing = the file is replaced with a fresh sample (backup `.bak`) |
+| `CFG_VER` | _(installer-managed)_ | config format reference written by `--install-service` (always a concrete `vX.Y.Z`; a dev build stamps `v0.0.0`); missing = the file is replaced with a fresh sample (backup `.bak`). New settings are appended (commented out) at install and at every startup after an update changed the version |
 
 Startup fails fast on unparsable values and when neither consumer URL is
 set. Enabled upstreams are probed once at start (`/api/version`,

cmd/gpu-turnstile/main.go

@@ -15,6 +15,7 @@ import (
 	"os"
 	"os/signal"
 	"path/filepath"
+	"runtime"
 	"strings"
 	"syscall"
 	"time"
@@ -38,6 +39,11 @@ var version = "dev"
 // process: a signed update has been staged and the GPU lock is idle.
 const exitCodeUpdate = 3
 
+// exitCodeStaged is returned by an elevated --force-update child when it
+// staged a new binary, so the non-elevated parent can tell "updated" from
+// "up to date" (it cannot see the child's console).
+const exitCodeStaged = 4
+
 // stdoutIsTerminal reports whether stdout is a console (char device), as
 // opposed to a pipe or file — which is what Docker containers and services
 // see.
@@ -172,6 +178,7 @@ func main() {
 	}
 	log, logOut, logCloser := newLogger(cfg)
 	defer logCloser.Close()
+	syncEnvFile(resolveConfigPath(configPath), cfg.LogFile, log)
 
 	if service.IsService() {
 		if err := service.Run(func(ctx context.Context) error { return run(ctx, cfg, log, logOut, true) }); err != nil {
@@ -188,6 +195,27 @@ func main() {
 	}
 }
 
+// syncEnvFile upgrades an installer-written config file after an update:
+// settings added since its CFG_VER are appended (commented out) and CFG_VER
+// is bumped. Files not written by the installer (no CFG_VER), up-to-date
+// files and dev builds are left untouched; a write failure is logged, not
+// fatal.
+func syncEnvFile(path, logFile string, log *slog.Logger) {
+	data, err := os.ReadFile(path)
+	if err != nil {
+		return // no config file; nothing to upgrade
+	}
+	synced, changed := config.SyncSample(string(data), version, logFile)
+	if !changed {
+		return
+	}
+	if err := os.WriteFile(path, []byte(synced), 0o644); err != nil {
+		log.Warn("could not append new settings to the config file", "path", path, "err", err)
+		return
+	}
+	log.Warn("config file updated: new settings appended", "path", path, "version", version)
+}
+
 // defaultConfigPath returns gpu-turnstile.env next to the executable.
 func defaultConfigPath() string {
 	exe, err := os.Executable()
@@ -325,11 +353,12 @@ func forceUpdateCommand(configPath string, elevatedChild bool) int {
 	// instead of hanging in a TCP connect for minutes.
 	ctx, cancel := context.WithTimeout(context.Background(), 30*time.Second)
 	defer cancel()
-	staged, err := u.Check(ctx, exePath)
+	staged, to, err := u.Check(ctx, exePath)
 	if err != nil && isPermission(err) && !service.Elevated() {
 		code, _ := elevateAndMirror("--force-update")
-		if code == 0 {
-			fmt.Println("update applied (elevated)")
+		reportElevatedUpdate(code, to)
+		if code == 0 || code == exitCodeStaged {
+			return 0
 		}
 		return code
 	}
@@ -341,12 +370,13 @@ func forceUpdateCommand(configPath string, elevatedChild bool) int {
 		fmt.Printf("%s is up to date\n", versionLine())
 		return 0
 	}
-	fmt.Printf("%s: update staged\n", versionLine())
+	fmt.Printf("gpu-turnstile: updated from %s to %s\n", version, to)
 	restarted, err := service.RestartIfRunning()
 	if err != nil && isPermission(err) && !service.Elevated() {
 		code, _ := elevateAndMirror("--force-update")
-		if code == 0 {
-			fmt.Println("update applied (elevated)")
+		reportElevatedUpdate(code, to)
+		if code == 0 || code == exitCodeStaged {
+			return 0
 		}
 		return code
 	}
@@ -355,13 +385,35 @@ func forceUpdateCommand(configPath string, elevatedChild bool) int {
 		return 1
 	}
 	if restarted {
-		fmt.Println("service restarted on the new version")
+		fmt.Println("service restarted on " + to)
 	} else {
-		fmt.Println("no running service; the new version applies on next start")
+		fmt.Println("no running service; " + to + " applies on the next start")
+	}
+	if elevatedChild {
+		// Tell the non-elevated parent (which cannot see this console)
+		// whether anything was staged, so its mirror message is honest.
+		return exitCodeStaged
 	}
 	return 0
 }
 
+// reportElevatedUpdate prints the parent's summary of an elevated
+// --force-update child: exitCodeStaged means the child staged a new binary,
+// 0 means it found nothing to do. to is the tag the parent's own check
+// resolved before it hit the permission wall ("" when it never got that
+// far).
+func reportElevatedUpdate(code int, to string) {
+	switch {
+	case code == exitCodeStaged && to != "":
+		fmt.Printf("gpu-turnstile: updated from %s to %s (elevated)\n", version, to)
+	case code == exitCodeStaged:
+		fmt.Println("update applied (elevated)")
+	case code == 0:
+		fmt.Printf("%s is up to date\n", versionLine())
+	}
+	// Non-zero, non-staged codes: elevateAndMirror already printed the failure.
+}
+
 // serviceCommand installs (copyBin = register the canonical-layout copy)
 // or removes the service and reports the result. On Windows, when the
 // shell is not elevated, the command relaunches itself through a UAC
@@ -412,7 +464,26 @@ func orDisabled(url string) string {
 	return url
 }
 
+// managedComfyCommand resolves how ComfyUI is launched when it is managed:
+// COMFY_CMD verbatim, or the standard venv layout under COMFY_DIR. Empty
+// when neither is set (unmanaged).
+func managedComfyCommand(cfg config.Config) string {
+	if cfg.ComfyCmd != "" {
+		return cfg.ComfyCmd
+	}
+	if cfg.ComfyDir != "" {
+		return supervise.DefaultComfyCommand(runtime.GOOS, cfg.ComfyDir, cfg.ComfyURL)
+	}
+	return ""
+}
+
 func run(ctx context.Context, cfg config.Config, log *slog.Logger, logOut io.Writer, isService bool) error {
+	// ComfyUI can run as a managed child — COMFY_CMD verbatim, or the
+	// standard venv layout derived from COMFY_DIR alone: started on demand
+	// by the proxy, stopped after COMFY_IDLE_TIMEOUT idle (and on shutdown)
+	// so its VRAM is freed.
+	comfyCmdLine := managedComfyCommand(cfg)
+
 	// The startup line carries the version and every setting and is emitted
 	// at WARN so it is visible even with the default (quiet) log level.
 	log.Log(ctx, slog.LevelWarn, "starting gpu-turnstile",
@@ -438,7 +509,7 @@ func run(ctx context.Context, cfg config.Config, log *slog.Logger, logOut io.Wri
 		"backoff_max", cfg.BackoffMax,
 		"prompt_capture_limit", cfg.PromptCaptureLimit,
 		"warm_model", cfg.WarmModel,
-		"comfy_cmd", cfg.ComfyCmd,
+		"comfy_cmd", orDisabled(comfyCmdLine),
 		"comfy_dir", cfg.ComfyDir,
 		"comfy_idle_timeout", cfg.ComfyIdleTimeout,
 		"comfy_start_timeout", cfg.ComfyStartTimeout,
@@ -472,13 +543,27 @@ func run(ctx context.Context, cfg config.Config, log *slog.Logger, logOut io.Wri
 		}
 	}
 
-	// With COMFY_CMD set, ComfyUI runs as a managed child: started on
-	// demand by the proxy, stopped after COMFY_IDLE_TIMEOUT idle (and on
-	// shutdown) so its VRAM is freed.
 	var comfySup *supervise.Process
-	if cfg.ComfyCmd != "" {
+	if comfyCmdLine != "" {
+		if cfg.ComfyCmd == "" {
+			// Derived from COMFY_DIR: flag a wrong-looking layout early,
+			// while the operator is still watching the startup log. Inside
+			// a profile the service account may not enter, os.Stat fails
+			// with EACCES — that reads as "not found" but means "grant
+			// access", so say so.
+			python, script := supervise.ComfyLayout(runtime.GOOS, cfg.ComfyDir)
+			for _, p := range []string{python, script} {
+				if _, err := os.Stat(p); err != nil {
+					if isPermission(err) {
+						log.Warn("COMFY_DIR: not accessible to the service account; grant access or re-run --install-service", "path", p)
+					} else {
+						log.Warn("COMFY_DIR: file not found; ComfyUI requests will fail until it exists", "path", p)
+					}
+				}
+			}
+		}
 		var err error
-		comfySup, err = supervise.New("comfy", cfg.ComfyCmd, cfg.ComfyDir, comfyClient.Probe, cfg.ComfyStartTimeout, log)
+		comfySup, err = supervise.New("comfy", comfyCmdLine, cfg.ComfyDir, comfyClient.Probe, cfg.ComfyStartTimeout, log)
 		if err != nil {
 			return err
 		}
@@ -757,16 +842,16 @@ func updateLoop(ctx context.Context, cfg config.Config, log *slog.Logger, lk *lo
 	}
 	u := &update.Updater{Repo: cfg.UpdateRepo, Asset: cfg.UpdateAsset, Version: version, Desired: cfg.AppVersion, Log: log}
 	for {
-		staged, err := u.Check(ctx, exePath)
+		staged, to, err := u.Check(ctx, exePath)
 		if err != nil && ctx.Err() == nil {
 			log.Warn("auto-update check failed", "err", err)
 		}
 		if staged {
 			if !isService {
-				log.Warn("auto-update: new binary staged; restart gpu-turnstile to apply")
+				log.Warn("auto-update: new binary staged; restart gpu-turnstile to apply", "version", to)
 				return
 			}
-			log.Warn("auto-update: staged; restarting once the GPU is idle")
+			log.Warn("auto-update: staged; restarting once the GPU is idle", "version", to)
 			if waitForIdle(ctx, lk, 24*time.Hour) {
 				log.Warn("auto-update: restarting to apply update")
 				os.Exit(exitCodeUpdate)

compose.yaml.example

@@ -6,7 +6,7 @@
 # ComfyUI --listen 0.0.0.0 --port 8189).
 services:
   gpu-turnstile:
-    image: git.rambossek.at/public/gpu-turnstile:v0.1.8
+    image: git.rambossek.at/public/gpu-turnstile:v0.2.2
     restart: unless-stopped
     environment:
       # Each consumer is enabled by setting its URL; leave one unset to

internal/config/config.go

@@ -51,11 +51,14 @@ type Config struct {
 	LLMBusyStatus  int
 	BusyRetryAfter int
 
-	// ComfyCmd spawns and supervises a ComfyUI server on demand (empty =
-	// unmanaged, the current behavior). ComfyDir is its working directory.
-	// The managed server is stopped after ComfyIdleTimeout without
-	// requests, freeing its VRAM; ComfyStartTimeout bounds how long a
-	// request waits for it to come up.
+	// ComfyCmd spawns and supervises a ComfyUI server on demand. When
+	// ComfyCmd is empty but ComfyDir is set, management is enabled with the
+	// standard venv layout under ComfyDir (.venv + main.py or
+	// ComfyUI/main.py; --port from the COMFY_URL port) — ComfyCmd is the
+	// override for other layouts and doubles as the working directory when
+	// set explicitly. The managed server is stopped after ComfyIdleTimeout
+	// without requests, freeing its VRAM; ComfyStartTimeout bounds how long
+	// a request waits for it to come up.
 	ComfyCmd          string
 	ComfyDir          string
 	ComfyIdleTimeout  time.Duration
@@ -116,7 +119,7 @@ func Defaults() Config {
 		// ComfyUI runs under python; excluding it (and Ollama) by name keeps
 		// our own consumers from tripping the foreign-VRAM check.
 		GPUIgnoreProcs:   []string{"ollama", "ollama app", "ollama_llama_server", "python", "pythonw"},
-		GamePollInterval: 5 * time.Second,
+		GamePollInterval: 15 * time.Second,
 
 		LogLevel: slog.LevelWarn,
 	}
@@ -305,6 +308,9 @@ func Load(getenv func(string) string) (Config, error) {
 	if cfg.ComfyCmd != "" && cfg.ComfyURL == "" {
 		return cfg, fmt.Errorf("COMFY_CMD requires COMFY_URL to be set (the proxy needs somewhere to forward)")
 	}
+	if cfg.ComfyCmd == "" && cfg.ComfyDir != "" && cfg.ComfyURL == "" {
+		return cfg, fmt.Errorf("COMFY_DIR without COMFY_CMD requires COMFY_URL to be set (it enables the managed ComfyUI)")
+	}
 	if cfg.OllamaURL == "" && cfg.ComfyURL == "" {
 		return cfg, ErrNoConsumer
 	}

internal/config/config_test.go

@@ -201,8 +201,8 @@ func TestGameDetectionSettings(t *testing.T) {
 	if len(cfg.GPUIgnoreProcs) != 2 || cfg.GPUIgnoreProcs[1] != "my-trainer" {
 		t.Fatalf("GPUIgnoreProcs = %v", cfg.GPUIgnoreProcs)
 	}
-	if cfg.GamePollInterval != 5*time.Second {
-		t.Fatalf("GamePollInterval = %v, want 5s default", cfg.GamePollInterval)
+	if cfg.GamePollInterval != 15*time.Second {
+		t.Fatalf("GamePollInterval = %v, want 15s default", cfg.GamePollInterval)
 	}
 
 	// Defaults: both detection paths off, ignore list covers our consumers.
@@ -222,3 +222,28 @@ func TestGameDetectionSettings(t *testing.T) {
 		t.Fatal("GPUIgnoreProcs default must not be empty")
 	}
 }
+
+func TestComfyDirOnlyEnablesManaged(t *testing.T) {
+	// COMFY_DIR without COMFY_CMD and without COMFY_URL is a mistake.
+	_, err := Load(func(k string) string {
+		if k == "COMFY_DIR" {
+			return `C:\ComfyUI`
+		}
+		return ""
+	})
+	if err == nil || !strings.Contains(err.Error(), "COMFY_DIR") {
+		t.Fatalf("err = %v, want COMFY_DIR/COMFY_URL validation error", err)
+	}
+	// With COMFY_URL it loads — the launch command is derived from the dir.
+	if _, err := Load(func(k string) string {
+		switch k {
+		case "COMFY_DIR":
+			return `C:\ComfyUI`
+		case "COMFY_URL":
+			return "http://127.0.0.1:8189"
+		}
+		return ""
+	}); err != nil {
+		t.Fatalf("COMFY_DIR with COMFY_URL must load: %v", err)
+	}
+}

internal/config/sample.go

@@ -28,14 +28,14 @@ func sampleEntries(logFile string) []sampleEntry {
 		{"OLLAMA_URL", "http://127.0.0.1:11434", "Ollama upstream URL; setting it enables the Ollama consumer (default: empty = disabled)", false},
 		{"COMFY_URL", "http://127.0.0.1:8188", "ComfyUI upstream URL; setting it enables the ComfyUI consumer (default: empty = disabled)", false},
 		{"WARM_MODEL", "", "Optional model to reload after an image job (default: empty = none)", false},
-		{"COMFY_CMD", `"C:\ComfyUI\.venv\Scripts\python.exe" ComfyUI\main.py --port 8188`, "Spawn and supervise ComfyUI on demand: the first request starts it, it stops after COMFY_IDLE_TIMEOUT to free VRAM (default: empty = unmanaged)", false},
-		{"COMFY_DIR", `C:\ComfyUI`, "Working directory for COMFY_CMD (default: empty = inherit)", false},
+		{"COMFY_CMD", `"C:\ComfyUI\.venv\Scripts\python.exe" ComfyUI\main.py --port 8188`, "Spawn and supervise ComfyUI on demand: the first request starts it, it stops after COMFY_IDLE_TIMEOUT to free VRAM (default: derived from COMFY_DIR; both empty = unmanaged)", false},
+		{"COMFY_DIR", `C:\ComfyUI`, "Root of a standard ComfyUI venv install (.venv + main.py): setting it alone supervises ComfyUI with the derived launch command; also the working directory for COMFY_CMD", false},
 		{"COMFY_IDLE_TIMEOUT", "5m", "Stop the managed ComfyUI after this long without requests or jobs (frees VRAM)", false},
 		{"COMFY_START_TIMEOUT", "2m", "How long a request waits for the managed ComfyUI to come up", false},
 		{"GAME_PROCS", "cyberpunk2077.exe,hl2.exe", "While a listed process runs, the GPU counts as held by it: requests wait, Ollama unloads, managed ComfyUI stops (default: empty = disabled)", false},
 		{"GPU_FOREIGN_VRAM_MB", "1024", "Also treat the GPU as held when a process not in GPU_IGNORE_PROCS uses more VRAM than this (needs nvidia-smi; 0/empty = disabled)", false},
 		{"GPU_IGNORE_PROCS", "ollama,ollama app,ollama_llama_server,python,pythonw", "Process names never counted as foreign GPU users (ComfyUI runs under python)", false},
-		{"GAME_POLL_INTERVAL", "5s", "How often game/VRAM detection runs", false},
+		{"GAME_POLL_INTERVAL", "15s", "How often game/VRAM detection runs (nvidia-smi polls keep the GPU awake; don't go below ~10s)", false},
 		{"UNLOAD_TIMEOUT", "60s", "How long to wait for Ollama to unload a model", false},
 		{"JOB_TIMEOUT", "15m", "Maximum time to wait for a ComfyUI job", false},
 		{"LLM_WAIT_TIMEOUT", "10m", "Max time an LLM request waits for the GPU before being answered 503 (wait mode)", false},
@@ -66,7 +66,8 @@ func sampleEntries(logFile string) []sampleEntry {
 // comment line. Everything is commented out — so all defaults apply —
 // except the CFG_VER/APP_VER header and LOG_FILE when logFile is non-empty
 // (a Windows service has no console). CFG_VER records the version that
-// wrote the file so later installs can upgrade it.
+// wrote the file so installs — and startups after an update — can upgrade
+// it.
 func SampleEnv(version, logFile string) string {
 	// CFG_VER is always a concrete vX.Y.Z — never "dev". A dev build
 	// stamps v0.0.0, which sorts older than any release, so the next

internal/service/envfile.go

@@ -45,3 +45,19 @@ func writeEnvFile(path, content string) error {
 	}
 	return nil
 }
+
+// configuredValue reads one key from the env file the service will load, so
+// the installers can adapt the sandbox to it (ACL grants, unit directives).
+// "" when unset or unreadable.
+func configuredValue(configPath, key string) string {
+	f, err := os.Open(configPath)
+	if err != nil {
+		return ""
+	}
+	defer f.Close()
+	values, err := config.ParseEnvFile(f)
+	if err != nil {
+		return ""
+	}
+	return values[key]
+}

internal/service/service_linux.go

@@ -15,6 +15,8 @@ import (
 	"os/signal"
 	"path/filepath"
 	"syscall"
+
+	"gpu-turnstile/internal/supervise"
 )
 
 // Name matches the Windows service name; the systemd unit is Name + ".service".
@@ -62,8 +64,23 @@ func Run(run func(ctx context.Context) error) error {
 // filesystem is read-only except StateDirectory (the install dir, so
 // self-updates can rewrite the binary), and the usual no-privilege-escalation
 // directives apply. The proxy needs nothing but outbound TCP/UDP and the
-// notify socket, so it loses nothing.
-func renderUnit(exePath, configPath string) string {
+// notify socket, so it loses nothing. A managed ComfyUI (comfyDir) gets a
+// BindPaths hole through ProtectHome/ProtectSystem: it reads its venv and
+// writes output/temp/user data under COMFY_DIR. A venv whose base
+// interpreter (pyvenv.cfg home) lives outside COMFY_DIR gets an additional
+// read-only bind, and a Comfy-Desktop shared data dir (models, input,
+// output) a read-write one.
+func renderUnit(exePath, configPath, comfyDir string) string {
+	bind := ""
+	if comfyDir != "" {
+		bind = "BindPaths=" + comfyDir + "\n"
+		if home := comfyVenvHome(comfyDir); home != "" {
+			bind += "BindReadOnlyPaths=" + home + "\n"
+		}
+		if shared := supervise.DesktopSharedDir(comfyDir); shared != "" {
+			bind += "BindPaths=" + shared + "\n"
+		}
+	}
 	return fmt.Sprintf(`[Unit]
 Description=gpu-turnstile GPU arbitration proxy for Ollama and ComfyUI
 After=network-online.target
@@ -78,7 +95,7 @@ RestartSec=5s
 
 DynamicUser=yes
 StateDirectory=%s
-ProtectSystem=strict
+%sProtectSystem=strict
 ProtectHome=yes
 PrivateTmp=yes
 NoNewPrivileges=yes
@@ -100,7 +117,7 @@ SystemCallErrorNumber=EPERM
 
 [Install]
 WantedBy=multi-user.target
-`, exePath, configPath, Name)
+`, exePath, configPath, Name, bind)
 }
 
 // copyFile copies src to dst, creating dst with the given mode.
@@ -125,7 +142,9 @@ func copyFile(src, dst string, mode os.FileMode) error {
 // sure /etc/gpu-turnstile.env exists (copied from the given config file if
 // provided), writes the hardened unit, then enables and starts it. With
 // copyBin=false the current executable location and config path are
-// registered as-is instead. Needs root.
+// registered as-is instead. When the config sets COMFY_DIR, the unit gets a
+// BindPaths= for it so the sandboxed service can reach the managed ComfyUI
+// even under /home. Needs root.
 //
 // Re-running install converges an existing unit instead of failing: it is
 // stopped first if active, the installed binary is replaced only when the
@@ -186,7 +205,7 @@ func Install(configPath string, copyBin bool, version string) error {
 			cfg = abs
 		}
 	}
-	rendered := renderUnit(exe, cfg)
+	rendered := renderUnit(exe, cfg, configuredValue(cfg, "COMFY_DIR"))
 	if old, _ := os.ReadFile(unitPath); string(old) != rendered {
 		if err := os.WriteFile(unitPath, []byte(rendered), 0o644); err != nil {
 			return fmt.Errorf("write %s (run as root): %w", unitPath, err)

internal/service/service_linux_test.go

@@ -8,7 +8,7 @@ import (
 )
 
 func TestRenderUnit(t *testing.T) {
-	unit := renderUnit("/var/lib/gpu-turnstile/gpu-turnstile", "/etc/gpu-turnstile.env")
+	unit := renderUnit("/var/lib/gpu-turnstile/gpu-turnstile", "/etc/gpu-turnstile.env", "")
 	for _, want := range []string{
 		"Type=notify",
 		"WatchdogSec=30s",
@@ -26,4 +26,12 @@ func TestRenderUnit(t *testing.T) {
 			t.Fatalf("unit missing %q:\n%s", want, unit)
 		}
 	}
+	if strings.Contains(unit, "BindPaths") {
+		t.Fatalf("unit without COMFY_DIR must not bind anything:\n%s", unit)
+	}
+
+	unit = renderUnit("/var/lib/gpu-turnstile/gpu-turnstile", "/etc/gpu-turnstile.env", "/home/gpu/ComfyUI")
+	if !strings.Contains(unit, "BindPaths=/home/gpu/ComfyUI\n") {
+		t.Fatalf("unit with COMFY_DIR must bind it:\n%s", unit)
+	}
 }

internal/service/service_windows.go

@@ -25,7 +25,7 @@ import (
 	"golang.org/x/sys/windows/svc"
 	"golang.org/x/sys/windows/svc/mgr"
 
-	"gpu-turnstile/internal/config"
+	"gpu-turnstile/internal/supervise"
 )
 
 // Name is the Windows service name.
@@ -106,10 +106,12 @@ func (h *handler) Execute(_ []string, requests <-chan svc.ChangeRequest, status
 // the service after 5s on failure — this is also what brings up a staged
 // update after the updater exits with a non-zero code. After registering,
 // the virtual account is granted modify access to the install and data
-// directories (self-updates rewrite the exe), and read access to the
-// config file if it lives elsewhere. The grants must come after
-// CreateService: the virtual account's SID only exists once the service is
-// registered.
+// directories (self-updates rewrite the exe), read access to the
+// config file if it lives elsewhere, and — when the config sets COMFY_DIR —
+// recursive modify access to the managed ComfyUI's install tree, which may
+// live inside a user profile the account otherwise cannot enter. The grants
+// must come after CreateService: the virtual account's SID only exists once
+// the service is registered.
 //
 // Re-running install on an existing service converges instead of failing:
 // the service is stopped first if running (so the binary can be replaced),
@@ -146,6 +148,7 @@ func Install(configPath string, copyBin bool, version string) error {
 		if st, qErr := s.Query(); qErr == nil &&
 			(st.State == svc.Running || st.State == svc.StartPending) {
 			wasRunning = true
+			fmt.Println("stopping the running gpu-turnstile service")
 			if err := stopAndWait(s); err != nil {
 				return err
 			}
@@ -161,6 +164,7 @@ func Install(configPath string, copyBin bool, version string) error {
 			}
 			installedExe := filepath.Join(installDir, "gpu-turnstile.exe")
 			if same, _ := sameFileContent(exe, installedExe); !same {
+				fmt.Printf("installing %s\n", installedExe)
 				if err := copyFile(exe, installedExe); err != nil {
 					return fmt.Errorf("copy binary to %s: %w", installedExe, err)
 				}
@@ -208,6 +212,7 @@ func Install(configPath string, copyBin bool, version string) error {
 		// Best effort: start now instead of waiting for the next boot. A
 		// missing config (no consumer URLs) fails the start; the service stays
 		// registered and can be started once the config exists.
+		fmt.Println("starting the gpu-turnstile service")
 		s.Start()
 		return nil
 	}
@@ -243,6 +248,7 @@ func Install(configPath string, copyBin bool, version string) error {
 		return err
 	}
 	if wasRunning {
+		fmt.Println("starting the gpu-turnstile service")
 		if err := s.Start(); err != nil {
 			return fmt.Errorf("start service: %w", err)
 		}
@@ -354,7 +360,7 @@ func grantAll(exe, configPath string) error {
 			return err
 		}
 	}
-	if logFile := configuredLogFile(configPath); logFile != "" {
+	if logFile := configuredValue(configPath, "LOG_FILE"); logFile != "" {
 		dir := filepath.Dir(logFile)
 		if err := os.MkdirAll(dir, 0o755); err == nil {
 			if err := grantAccess(dir, "(OI)(CI)(M)"); err != nil {
@@ -362,6 +368,31 @@ func grantAll(exe, configPath string) error {
 			}
 		}
 	}
+	// A managed ComfyUI whose install lives somewhere the virtual account
+	// may not go (a user profile) needs an explicit grant — recursively,
+	// since ComfyUI also writes output/temp/user data next to its code. A
+	// missing directory is skipped: the startup warning covers it.
+	if comfyDir := configuredValue(configPath, "COMFY_DIR"); comfyDir != "" {
+		if _, err := os.Stat(comfyDir); err == nil {
+			if err := grantAccessTree(comfyDir, "(OI)(CI)(M)"); err != nil {
+				return err
+			}
+			// uv venvs (Comfy-Desktop) redirect to a base interpreter that
+			// can live outside COMFY_DIR; read+execute suffices for it.
+			if home := comfyVenvHome(comfyDir); home != "" {
+				if err := grantAccessTree(home, "(OI)(CI)(RX)"); err != nil {
+					return err
+				}
+			}
+			// Comfy-Desktop keeps models/input/output in a shared dir next
+			// to the install; the managed instance writes output there.
+			if shared := supervise.DesktopSharedDir(comfyDir); shared != "" {
+				if err := grantAccessTree(shared, "(OI)(CI)(M)"); err != nil {
+					return err
+				}
+			}
+		}
+	}
 	return nil
 }
 
@@ -466,28 +497,35 @@ func RelaunchElevated(args []string) (int, error) {
 // grantAccess gives the virtual account the icacls permission set (e.g.
 // "(OI)(CI)(M)") on path.
 func grantAccess(path, perms string) error {
-	out, err := exec.Command("icacls", path, "/grant", virtualAccount+":"+perms).CombinedOutput()
+	return runIcacls(path, perms, false)
+}
+
+// grantAccessTree is grantAccess with /T: the ACE is applied to the
+// existing tree, not just inherited by children created later. Needed when
+// the tree already exists, e.g. a ComfyUI install in a user profile. On a
+// large tree (a venv has tens of thousands of files) this takes minutes,
+// so it says what it is doing instead of looking hung.
+func grantAccessTree(path, perms string) error {
+	return runIcacls(path, perms, true)
+}
+
+func runIcacls(path, perms string, recursive bool) error {
+	args := []string{path, "/grant", virtualAccount + ":" + perms}
+	if recursive {
+		fmt.Printf("granting %s %s access to %s (large trees can take minutes)\n", virtualAccount, perms, path)
+		args = append(args, "/T")
+	}
+	start := time.Now()
+	out, err := exec.Command("icacls", args...).CombinedOutput()
 	if err != nil {
 		return fmt.Errorf("grant %s access to %s: %w (%s)", virtualAccount, path, err, strings.TrimSpace(string(out)))
 	}
+	if recursive {
+		fmt.Printf("access granted in %s\n", time.Since(start).Round(time.Second))
+	}
 	return nil
 }
 
-// configuredLogFile reads LOG_FILE from the config file so the installer
-// can pre-create and ACL the log directory. "" when unset or unreadable.
-func configuredLogFile(configPath string) string {
-	f, err := os.Open(configPath)
-	if err != nil {
-		return ""
-	}
-	defer f.Close()
-	values, err := config.ParseEnvFile(f)
-	if err != nil {
-		return ""
-	}
-	return values["LOG_FILE"]
-}
-
 // RestartIfRunning restarts the service when it is installed and running
 // (used after a forced update staged a new binary). Reports whether a
 // restart happened. A service that is not installed or not running is not

internal/service/venv.go

@@ -0,0 +1,38 @@
+package service
+
+import (
+	"os"
+	"path/filepath"
+	"strings"
+)
+
+// comfyVenvHome returns the base interpreter directory of the Python venv at
+// <comfyDir>/.venv when that directory lives outside comfyDir, "" otherwise.
+// uv-created venvs (Comfy-Desktop) ship a redirector python.exe whose real
+// interpreter is the pyvenv.cfg "home" tree — typically a sibling of
+// COMFY_DIR, which a sandbox/ACL covering COMFY_DIR alone does not reach.
+func comfyVenvHome(comfyDir string) string {
+	data, err := os.ReadFile(filepath.Join(comfyDir, ".venv", "pyvenv.cfg"))
+	if err != nil {
+		return ""
+	}
+	for _, line := range strings.Split(string(data), "\n") {
+		k, v, ok := strings.Cut(line, "=")
+		if !ok || strings.TrimSpace(k) != "home" {
+			continue
+		}
+		home := strings.TrimSpace(v)
+		if home == "" {
+			return ""
+		}
+		if st, err := os.Stat(home); err != nil || !st.IsDir() {
+			return ""
+		}
+		rel, err := filepath.Rel(comfyDir, home)
+		if err != nil || rel == ".." || strings.HasPrefix(rel, ".."+string(filepath.Separator)) {
+			return home
+		}
+		return "" // inside comfyDir: already covered by the COMFY_DIR grant
+	}
+	return ""
+}

internal/service/venv_test.go

@@ -0,0 +1,45 @@
+package service
+
+import (
+	"os"
+	"path/filepath"
+	"testing"
+)
+
+func TestComfyVenvHome(t *testing.T) {
+	root := t.TempDir()
+	comfy := filepath.Join(root, "ComfyUI")
+	outside := filepath.Join(root, "standalone-env")
+	inside := filepath.Join(comfy, "runtime")
+	for _, d := range []string{filepath.Join(comfy, ".venv"), outside, inside} {
+		if err := os.MkdirAll(d, 0o755); err != nil {
+			t.Fatal(err)
+		}
+	}
+	cfg := filepath.Join(comfy, ".venv", "pyvenv.cfg")
+
+	write := func(home string) {
+		if err := os.WriteFile(cfg, []byte("home = "+home+"\nversion_info = 3.13.0\n"), 0o644); err != nil {
+			t.Fatal(err)
+		}
+	}
+
+	write(outside)
+	if got := comfyVenvHome(comfy); got != outside {
+		t.Fatalf("outside home: got %q, want %q", got, outside)
+	}
+
+	write(inside)
+	if got := comfyVenvHome(comfy); got != "" {
+		t.Fatalf("inside home: got %q, want empty", got)
+	}
+
+	write(filepath.Join(root, "does-not-exist"))
+	if got := comfyVenvHome(comfy); got != "" {
+		t.Fatalf("missing home: got %q, want empty", got)
+	}
+
+	if got := comfyVenvHome(filepath.Join(root, "no-venv")); got != "" {
+		t.Fatalf("no pyvenv.cfg: got %q, want empty", got)
+	}
+}

internal/supervise/supervise.go

@@ -9,13 +9,82 @@ import (
 	"fmt"
 	"io"
 	"log/slog"
+	"net/url"
+	"os"
 	"os/exec"
+	"path/filepath"
+	"regexp"
 	"runtime"
 	"strings"
 	"sync"
 	"time"
 )
 
+// ComfyLayout returns the interpreter and script path of a standard ComfyUI
+// venv install rooted at dir for the given GOOS: .venv\Scripts\python.exe
+// on Windows, .venv/bin/python elsewhere. The script is main.py — either in
+// a ComfyUI subdirectory or directly under dir, whichever exists (the
+// subdirectory form wins ties and is the default when neither exists yet,
+// so the caller's missing-file warning points at the documented layout).
+func ComfyLayout(goos, dir string) (python, script string) {
+	if goos == "windows" {
+		python = filepath.Join(dir, ".venv", "Scripts", "python.exe")
+	} else {
+		python = filepath.Join(dir, ".venv", "bin", "python")
+	}
+	script = filepath.Join(dir, "ComfyUI", "main.py")
+	if _, err := os.Stat(script); err != nil {
+		if _, err := os.Stat(filepath.Join(dir, "main.py")); err == nil {
+			script = filepath.Join(dir, "main.py")
+		}
+	}
+	return python, script
+}
+
+// DefaultComfyCommand builds the launch command for the standard venv
+// layout (see ComfyLayout): the script is passed relative to dir so dir
+// stays the working directory, and --port is taken from comfyURL when the
+// URL carries one. On a Comfy-Desktop standalone install the shared data
+// directory (models, input, output) is added as --*-directory flags so the
+// managed instance sees the desktop app's models.
+func DefaultComfyCommand(goos, dir, comfyURL string) string {
+	python, script := ComfyLayout(goos, dir)
+	rel, err := filepath.Rel(dir, script)
+	if err != nil {
+		rel = script
+	}
+	cmd := `"` + python + `" ` + rel
+	if u, err := url.Parse(comfyURL); err == nil && u.Port() != "" {
+		cmd += " --port " + u.Port()
+	}
+	if shared := DesktopSharedDir(dir); shared != "" {
+		for _, sub := range []string{"models", "input", "output"} {
+			p := filepath.Join(shared, sub)
+			if st, err := os.Stat(p); err == nil && st.IsDir() {
+				cmd += ` --` + sub + `-directory "` + p + `"`
+			}
+		}
+	}
+	return cmd
+}
+
+// DesktopSharedDir returns the Comfy-Desktop shared data directory
+// (<root>/ComfyUI-Shared) when dir looks like a desktop standalone install
+// (<root>/ComfyUI-Installs/<name>/ComfyUI) and the shared models directory
+// exists; "" otherwise. The desktop app keeps models, input and output
+// there rather than inside the ComfyUI tree.
+func DesktopSharedDir(dir string) string {
+	installs := filepath.Dir(filepath.Dir(dir))
+	if filepath.Base(installs) != "ComfyUI-Installs" {
+		return ""
+	}
+	shared := filepath.Join(filepath.Dir(installs), "ComfyUI-Shared")
+	if st, err := os.Stat(filepath.Join(shared, "models")); err == nil && st.IsDir() {
+		return shared
+	}
+	return ""
+}
+
 // Process is one managed child process.
 type Process struct {
 	name         string
@@ -144,6 +213,9 @@ func (p *Process) EnsureRunning() error {
 	p.external = false
 	cmd := exec.Command(p.argv[0], p.argv[1:]...)
 	cmd.Dir = p.dir
+	// Ask the child not to colorize (ComfyUI ignores this and colors
+	// anyway, so pipeLog also strips escape sequences).
+	cmd.Env = append(os.Environ(), "NO_COLOR=1", "TERM=dumb")
 	stdout, err := cmd.StdoutPipe()
 	if err != nil {
 		return err
@@ -237,7 +309,9 @@ func (p *Process) WatchIdle(ctx context.Context, idleTimeout time.Duration, gpuI
 }
 
 // pipeLog forwards one child output stream to the log at INFO, line by
-// line, prefixed with the process name.
+// line, prefixed with the process name. ANSI escape sequences are
+// stripped: ComfyUI colorizes unconditionally, and the escapes only
+// render as garbage in a log file.
 func (p *Process) pipeLog(r io.Reader) {
 	buf := make([]byte, 4096)
 	var line string
@@ -249,18 +323,25 @@ func (p *Process) pipeLog(r io.Reader) {
 			if i < 0 {
 				break
 			}
-			p.log.Info(p.name + ": " + strings.TrimRight(line[:i], "\r"))
+			p.log.Info(p.name + ": " + stripANSI(strings.TrimRight(line[:i], "\r")))
 			line = line[i+1:]
 		}
 		if err != nil {
 			if strings.TrimSpace(line) != "" {
-				p.log.Info(p.name + ": " + line)
+				p.log.Info(p.name + ": " + stripANSI(line))
 			}
 			return
 		}
 	}
 }
 
+// ansiPattern matches CSI escape sequences (colors, cursor moves, …).
+var ansiPattern = regexp.MustCompile("\x1b\\[[0-9;?]*[a-zA-Z]")
+
+func stripANSI(s string) string {
+	return ansiPattern.ReplaceAllString(s, "")
+}
+
 // stopTree kills cmd's process, including its children on Windows (python
 // launchers tend to spawn some). The Wait goroutine reaps it.
 func stopTree(cmd *exec.Cmd) {

internal/supervise/supervise_test.go

@@ -7,6 +7,8 @@ import (
 	"net/http"
 	"net/http/httptest"
 	"os"
+	"path/filepath"
+	"strings"
 	"testing"
 	"time"
 )
@@ -190,3 +192,85 @@ func TestWatchIdleRespectsBusyGPU(t *testing.T) {
 		t.Fatal("process was stopped while the GPU was busy")
 	}
 }
+
+func TestComfyLayoutAndDefaultCommand(t *testing.T) {
+	// Nested layout (ComfyUI/main.py under dir) wins.
+	dir := t.TempDir()
+	nested := filepath.Join(dir, "ComfyUI", "main.py")
+	if err := os.MkdirAll(filepath.Dir(nested), 0o755); err != nil {
+		t.Fatal(err)
+	}
+	if err := os.WriteFile(nested, []byte("x"), 0o644); err != nil {
+		t.Fatal(err)
+	}
+	python, script := ComfyLayout("windows", dir)
+	if want := filepath.Join(dir, ".venv", "Scripts", "python.exe"); python != want {
+		t.Errorf("python = %s, want %s", python, want)
+	}
+	if script != nested {
+		t.Errorf("script = %s, want %s", script, nested)
+	}
+	cmd := DefaultComfyCommand("windows", dir, "http://127.0.0.1:8189")
+	want := `"` + filepath.Join(dir, ".venv", "Scripts", "python.exe") + `" ` + filepath.Join("ComfyUI", "main.py") + " --port 8189"
+	if cmd != want {
+		t.Errorf("cmd = %q, want %q", cmd, want)
+	}
+
+	// Flat layout (main.py directly under dir) is found too.
+	flat := t.TempDir()
+	if err := os.WriteFile(filepath.Join(flat, "main.py"), []byte("x"), 0o644); err != nil {
+		t.Fatal(err)
+	}
+	if _, script := ComfyLayout("linux", flat); script != filepath.Join(flat, "main.py") {
+		t.Errorf("flat script = %s", script)
+	}
+	cmd = DefaultComfyCommand("linux", flat, "http://comfy.internal")
+	if strings.Contains(cmd, "--port") {
+		t.Errorf("cmd = %q, want no --port for a port-less URL", cmd)
+	}
+	if !strings.HasSuffix(cmd, `" main.py`) {
+		t.Errorf("cmd = %q, want quoted python + relative main.py", cmd)
+	}
+
+	// Neither exists yet: default to the documented nested form so the
+	// startup warning points there.
+	empty := t.TempDir()
+	if _, script := ComfyLayout("windows", empty); script != filepath.Join(empty, "ComfyUI", "main.py") {
+		t.Errorf("missing-layout script = %s", script)
+	}
+}
+
+func TestStripANSI(t *testing.T) {
+	cases := map[string]string{
+		"\x1b[32m[INFO]\x1b[0m Starting server":   "[INFO] Starting server",
+		"\x1b[1m\x1b[31m[ERROR]\x1b[0m boom":      "[ERROR] boom",
+		"plain line":                              "plain line",
+		"\x1b[33mWARN\x1b[0m: \x1b[1mbold\x1b[0m": "WARN: bold",
+	}
+	for in, want := range cases {
+		if got := stripANSI(in); got != want {
+			t.Errorf("stripANSI(%q) = %q, want %q", in, got, want)
+		}
+	}
+}
+
+func TestDesktopSharedDir(t *testing.T) {
+	root := t.TempDir()
+	comfy := filepath.Join(root, "ComfyUI-Installs", "rtx5080", "ComfyUI")
+	if err := os.MkdirAll(comfy, 0o755); err != nil {
+		t.Fatal(err)
+	}
+	if got := DesktopSharedDir(comfy); got != "" {
+		t.Fatalf("no shared dir yet: got %q, want empty", got)
+	}
+	shared := filepath.Join(root, "ComfyUI-Shared")
+	if err := os.MkdirAll(filepath.Join(shared, "models"), 0o755); err != nil {
+		t.Fatal(err)
+	}
+	if got := DesktopSharedDir(comfy); got != shared {
+		t.Fatalf("got %q, want %q", got, shared)
+	}
+	if got := DesktopSharedDir(filepath.Join(root, "plain", "ComfyUI")); got != "" {
+		t.Fatalf("non-desktop layout: got %q, want empty", got)
+	}
+}

internal/update/update.go

@@ -173,11 +173,13 @@ func CleanupOld(exePath string) {
 
 // Check performs a single update check. staged is true when a
 // signature-verified binary has been swapped into place at exePath; the
-// caller should then restart the process. A nil error with staged=false
-// means "no action" (up to date, APP_VER=dev, or no embedded public key);
-// a non-nil error means the check failed and the running binary is
-// untouched.
-func (u *Updater) Check(ctx context.Context, exePath string) (staged bool, err error) {
+// caller should then restart the process. to is the release tag the check
+// resolved (the latest release or the pinned tag), set once the release
+// fetch succeeded — even when staging afterwards fails. A nil error with
+// staged=false means "no action" (up to date, APP_VER=dev, or no embedded
+// public key); a non-nil error means the check failed and the running
+// binary is untouched.
+func (u *Updater) Check(ctx context.Context, exePath string) (staged bool, to string, err error) {
 	log := u.logger()
 	desired := u.Desired
 	if desired == "" {
@@ -185,15 +187,15 @@ func (u *Updater) Check(ctx context.Context, exePath string) (staged bool, err e
 	}
 	if desired == "dev" {
 		log.Debug("auto-update: APP_VER=dev, skipping")
-		return false, nil
+		return false, "", nil
 	}
 	if publicKeyPEM == "" {
 		log.Debug("auto-update: no public key embedded, skipping")
-		return false, nil
+		return false, "", nil
 	}
 	api, err := u.apiURL()
 	if err != nil {
-		return false, err
+		return false, "", err
 	}
 
 	pinned := desired != "stable"
@@ -203,29 +205,30 @@ func (u *Updater) Check(ctx context.Context, exePath string) (staged bool, err e
 	}
 	body, err := u.get(ctx, endpoint)
 	if err != nil {
-		return false, fmt.Errorf("fetch release: %w", err)
+		return false, "", fmt.Errorf("fetch release: %w", err)
 	}
 	var rel release
 	if err := json.Unmarshal(body, &rel); err != nil {
-		return false, fmt.Errorf("parse release: %w", err)
+		return false, "", fmt.Errorf("parse release: %w", err)
 	}
+	to = rel.TagName
 	if pinned {
 		// Pin mode: any difference from the target tag means stage it —
 		// including downgrades and replacing a dev binary.
 		if u.Version == rel.TagName {
 			log.Debug("auto-update: already on pinned version", "version", u.Version)
-			return false, nil
+			return false, to, nil
 		}
 	} else if u.Version != "" && u.Version != "dev" {
 		// Stable mode: only strictly newer releases count; a dev binary
 		// cannot be compared and is always replaced by the latest release.
 		newer, err := newerVersion(u.Version, rel.TagName)
 		if err != nil {
-			return false, err
+			return false, to, err
 		}
 		if !newer {
 			log.Debug("auto-update: up to date", "version", u.Version, "latest", rel.TagName)
-			return false, nil
+			return false, to, nil
 		}
 	}
 
@@ -235,42 +238,42 @@ func (u *Updater) Check(ctx context.Context, exePath string) (staged bool, err e
 	}
 	assetURL, ok := urls[u.Asset]
 	if !ok {
-		return false, fmt.Errorf("release %s has no asset %q", rel.TagName, u.Asset)
+		return false, to, fmt.Errorf("release %s has no asset %q", rel.TagName, u.Asset)
 	}
 	sigURL, ok := urls[u.Asset+".sig"]
 	if !ok {
-		return false, fmt.Errorf("release %s has no signature asset %q", rel.TagName, u.Asset+".sig")
+		return false, to, fmt.Errorf("release %s has no signature asset %q", rel.TagName, u.Asset+".sig")
 	}
 
 	data, err := u.get(ctx, assetURL)
 	if err != nil {
-		return false, fmt.Errorf("download %s: %w", u.Asset, err)
+		return false, to, fmt.Errorf("download %s: %w", u.Asset, err)
 	}
 	sig, err := u.get(ctx, sigURL)
 	if err != nil {
-		return false, fmt.Errorf("download signature: %w", err)
+		return false, to, fmt.Errorf("download signature: %w", err)
 	}
 
 	if sumURL, ok := urls[u.Asset+".sha256"]; ok {
 		sumText, err := u.get(ctx, sumURL)
 		if err != nil {
-			return false, fmt.Errorf("download checksum: %w", err)
+			return false, to, fmt.Errorf("download checksum: %w", err)
 		}
 		want := strings.Fields(string(sumText))[0]
 		got := hex.EncodeToString(sha256Bytes(data))
 		if !strings.EqualFold(want, got) {
-			return false, fmt.Errorf("sha256 mismatch: got %s, want %s", got, want)
+			return false, to, fmt.Errorf("sha256 mismatch: got %s, want %s", got, want)
 		}
 	}
 	if err := verifySignature(publicKeyPEM, data, sig); err != nil {
-		return false, err
+		return false, to, err
 	}
 
 	if err := stage(exePath, data); err != nil {
-		return false, fmt.Errorf("stage update: %w", err)
+		return false, to, fmt.Errorf("stage update: %w", err)
 	}
 	log.Info("auto-update: new version staged", "from", u.Version, "to", rel.TagName)
-	return true, nil
+	return true, to, nil
 }
 
 func sha256Bytes(data []byte) []byte {

internal/update/update_test.go

@@ -102,13 +102,16 @@ func TestCheckStagesUpdate(t *testing.T) {
 	withPublicKey(t, f.pubPEM)
 	exe := fakeExe(t)
 
-	staged, err := f.updater("v0.1.2").Check(context.Background(), exe)
+	staged, to, err := f.updater("v0.1.2").Check(context.Background(), exe)
 	if err != nil {
 		t.Fatal(err)
 	}
 	if !staged {
 		t.Fatal("expected staged update")
 	}
+	if to != "v9.9.9" {
+		t.Fatalf("to = %q, want v9.9.9", to)
+	}
 	content, _ := os.ReadFile(exe)
 	if string(content) != "new-binary" {
 		t.Fatalf("exe content = %q", content)
@@ -125,7 +128,7 @@ func TestCheckRejectsTamperedSignature(t *testing.T) {
 	withPublicKey(t, f.pubPEM)
 	exe := fakeExe(t)
 
-	staged, err := f.updater("v0.1.2").Check(context.Background(), exe)
+	staged, _, err := f.updater("v0.1.2").Check(context.Background(), exe)
 	if err == nil {
 		t.Fatal("expected signature error")
 	}
@@ -142,7 +145,7 @@ func TestCheckSkipsOlderOrEqual(t *testing.T) {
 	for _, tag := range []string{"v0.1.2", "v0.1.1", "v0.0.9"} {
 		f := newFakeGitea(t, tag, []byte("new-binary"))
 		withPublicKey(t, f.pubPEM)
-		staged, err := f.updater("v0.1.2").Check(context.Background(), fakeExe(t))
+		staged, _, err := f.updater("v0.1.2").Check(context.Background(), fakeExe(t))
 		if err != nil {
 			t.Fatal(err)
 		}
@@ -155,7 +158,7 @@ func TestCheckSkipsOlderOrEqual(t *testing.T) {
 func TestCheckSkipsWithoutPublicKey(t *testing.T) {
 	f := newFakeGitea(t, "v9.9.9", []byte("new-binary"))
 	withPublicKey(t, "")
-	staged, err := f.updater("v0.1.2").Check(context.Background(), fakeExe(t))
+	staged, _, err := f.updater("v0.1.2").Check(context.Background(), fakeExe(t))
 	if err != nil || staged {
 		t.Fatalf("staged=%v err=%v, want no action without key", staged, err)
 	}
@@ -167,7 +170,7 @@ func TestCheckDevBuildGetsStable(t *testing.T) {
 	f := newFakeGitea(t, "v9.9.9", []byte("new-binary"))
 	withPublicKey(t, f.pubPEM)
 	exe := fakeExe(t)
-	staged, err := f.updater("dev").Check(context.Background(), exe)
+	staged, _, err := f.updater("dev").Check(context.Background(), exe)
 	if err != nil {
 		t.Fatal(err)
 	}
@@ -184,7 +187,7 @@ func TestCheckDesiredDevDisables(t *testing.T) {
 	f := newFakeGitea(t, "v9.9.9", []byte("new-binary"))
 	withPublicKey(t, f.pubPEM)
 	for _, version := range []string{"dev", "v0.1.2"} {
-		staged, err := f.updaterDesired(version, "dev").Check(context.Background(), fakeExe(t))
+		staged, _, err := f.updaterDesired(version, "dev").Check(context.Background(), fakeExe(t))
 		if err != nil || staged {
 			t.Fatalf("version %s: staged=%v err=%v, want no action with APP_VER=dev", version, staged, err)
 		}
@@ -198,13 +201,16 @@ func TestCheckPinned(t *testing.T) {
 		f := newFakeGitea(t, "v0.5.0", []byte("pinned-binary"))
 		withPublicKey(t, f.pubPEM)
 		exe := fakeExe(t)
-		staged, err := f.updaterDesired(version, "v0.5.0").Check(context.Background(), exe)
+		staged, to, err := f.updaterDesired(version, "v0.5.0").Check(context.Background(), exe)
 		if err != nil {
 			t.Fatalf("version %s: %v", version, err)
 		}
 		if !staged {
 			t.Fatalf("version %s: expected pinned v0.5.0 to be staged", version)
 		}
+		if to != "v0.5.0" {
+			t.Fatalf("version %s: to = %q, want v0.5.0", version, to)
+		}
 		content, _ := os.ReadFile(exe)
 		if string(content) != "pinned-binary" {
 			t.Fatalf("version %s: exe content = %q", version, content)
@@ -213,7 +219,7 @@ func TestCheckPinned(t *testing.T) {
 
 	f := newFakeGitea(t, "v0.5.0", []byte("pinned-binary"))
 	withPublicKey(t, f.pubPEM)
-	staged, err := f.updaterDesired("v0.5.0", "v0.5.0").Check(context.Background(), fakeExe(t))
+	staged, _, err := f.updaterDesired("v0.5.0", "v0.5.0").Check(context.Background(), fakeExe(t))
 	if err != nil || staged {
 		t.Fatalf("staged=%v err=%v, want no action when already on the pinned version", staged, err)
 	}