Pin compose example to v0.1.10

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_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)_ | Working directory for `COMFY_CMD` |
+| `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
+Desktop app kills its server when you close it)? gpu-turnstile can supervise
-standalone launch command and gpu-turnstile supervises it: the first
+it: the first request starts it, it stops again after `COMFY_IDLE_TIMEOUT`
-request starts it, it stops again after `COMFY_IDLE_TIMEOUT` (default 5m)
+(default 5m) without work, freeing the GPU for games or the LLM.
-without work, freeing the GPU for games or the LLM. Example for a Desktop
+
-install (run it once manually to confirm it works):
+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_URL=http://127.0.0.1:8189
-COMFY_CMD="C:\ComfyUI\.venv\Scripts\python.exe ComfyUI\main.py --port 8188"
+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
 ```
 
@@ -130,7 +140,7 @@ 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
@@ -159,7 +164,7 @@ process instead of expecting an always-on server:
 
 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 +216,14 @@ 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_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` | `` | working directory for `COMFY_CMD` |
+| `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 +242,7 @@ 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"
@@ -172,6 +173,7 @@ 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 +190,27 @@ 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()
@@ -412,7 +435,26 @@ 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 +480,7 @@ 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 +514,20 @@ 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.
+			python, script := supervise.ComfyLayout(runtime.GOOS, cfg.ComfyDir)
+			for _, p := range []string{python, script} {
+				if _, err := os.Stat(p); err != nil {
+					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
 		}

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:v0.1.10
     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 =
+	// ComfyCmd spawns and supervises a ComfyUI server on demand. When
-	// unmanaged, the current behavior). ComfyDir is its working directory.
+	// ComfyCmd is empty but ComfyDir is set, management is enabled with the
-	// The managed server is stopped after ComfyIdleTimeout without
+	// standard venv layout under ComfyDir (.venv + main.py or
-	// requests, freeing its VRAM; ComfyStartTimeout bounds how long a
+	// ComfyUI/main.py; --port from the COMFY_URL port) — ComfyCmd is the
-	// request waits for it to come up.
+	// 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 {
+	if cfg.GamePollInterval != 15*time.Second {
-		t.Fatalf("GamePollInterval = %v, want 5s default", cfg.GamePollInterval)
+		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_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`, "Working directory for COMFY_CMD (default: empty = inherit)", 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/supervise/supervise.go

@@ -9,13 +9,54 @@ import (
 	"fmt"
 	"io"
 	"log/slog"
+	"net/url"
+	"os"
 	"os/exec"
+	"path/filepath"
 	"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.
+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()
+	}
+	return cmd
+}
+
 // Process is one managed child process.
 type Process struct {
 	name         string

internal/supervise/supervise_test.go

@@ -7,6 +7,8 @@ import (
 	"net/http"
 	"net/http/httptest"
 	"os"
+	"path/filepath"
+	"strings"
 	"testing"
 	"time"
 )
@@ -190,3 +192,50 @@ 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)
+	}
+}