remove unnecessary field and helper

Author: ilopezluna

cmd/cli/commands/compose.go

@@ -177,7 +177,7 @@ func downloadModelsOnlyIfNotFound(desktopClient *desktop.Client, models []string
 			printer := desktop.NewSimplePrinter(func(s string) {
 				_ = sendInfo(s)
 			})
-			_, _, err = desktopClient.Pull(model, false, printer)
+			_, _, err = desktopClient.Pull(model, printer)
 			if err != nil {
 				_ = sendErrorf("Failed to pull model: %v", err)
 				return fmt.Errorf("Failed to pull model: %w\n", err)

cmd/cli/commands/pull.go

@@ -10,8 +10,6 @@ import (
 )
 
 func newPullCmd() *cobra.Command {
-	var ignoreRuntimeMemoryCheck bool
-
 	c := &cobra.Command{
 		Use:   "pull MODEL",
 		Short: "Pull a model from Docker Hub or HuggingFace to your local environment",
@@ -20,19 +18,17 @@ func newPullCmd() *cobra.Command {
 			if _, err := ensureStandaloneRunnerAvailable(cmd.Context(), asPrinter(cmd), false); err != nil {
 				return fmt.Errorf("unable to initialize standalone model runner: %w", err)
 			}
-			return pullModel(cmd, desktopClient, args[0], ignoreRuntimeMemoryCheck)
+			return pullModel(cmd, desktopClient, args[0])
 		},
 		ValidArgsFunction: completion.NoComplete,
 	}
 
-	c.Flags().BoolVar(&ignoreRuntimeMemoryCheck, "ignore-runtime-memory-check", false, "Do not block pull if estimated runtime memory for model exceeds system resources.")
-
 	return c
 }
 
-func pullModel(cmd *cobra.Command, desktopClient *desktop.Client, model string, ignoreRuntimeMemoryCheck bool) error {
+func pullModel(cmd *cobra.Command, desktopClient *desktop.Client, model string) error {
 	printer := asPrinter(cmd)
-	response, _, err := desktopClient.Pull(model, ignoreRuntimeMemoryCheck, printer)
+	response, _, err := desktopClient.Pull(model, printer)
 
 	if err != nil {
 		return handleClientError(err, "Failed to pull model")

cmd/cli/commands/run.go

@@ -570,7 +570,6 @@ func chatWithMarkdownContext(ctx context.Context, cmd *cobra.Command, client *de
 
 func newRunCmd() *cobra.Command {
 	var debug bool
-	var ignoreRuntimeMemoryCheck bool
 	var colorMode string
 	var detach bool
 
@@ -686,7 +685,7 @@ func newRunCmd() *cobra.Command {
 					return handleClientError(err, "Failed to inspect model")
 				}
 				cmd.Println("Unable to find model '" + model + "' locally. Pulling from the server.")
-				if err := pullModel(cmd, desktopClient, model, ignoreRuntimeMemoryCheck); err != nil {
+				if err := pullModel(cmd, desktopClient, model); err != nil {
 					return err
 				}
 			}
@@ -733,7 +732,6 @@ func newRunCmd() *cobra.Command {
 	c.Args = requireMinArgs(1, "run", cmdArgs)
 
 	c.Flags().BoolVar(&debug, "debug", false, "Enable debug logging")
-	c.Flags().BoolVar(&ignoreRuntimeMemoryCheck, "ignore-runtime-memory-check", false, "Do not block pull if estimated runtime memory for model exceeds system resources.")
 	c.Flags().StringVar(&colorMode, "color", "no", "Use colored output (auto|yes|no)")
 	c.Flags().BoolVarP(&detach, "detach", "d", false, "Load the model in the background without interaction")
 

cmd/cli/desktop/desktop.go

@@ -105,7 +105,7 @@ func (c *Client) Status() Status {
 	}
 }
 
-func (c *Client) Pull(model string, ignoreRuntimeMemoryCheck bool, printer standalone.StatusPrinter) (string, bool, error) {
+func (c *Client) Pull(model string, printer standalone.StatusPrinter) (string, bool, error) {
 	model = normalizeHuggingFaceModelName(model)
 
 	// Check if this is a Hugging Face model and if HF_TOKEN is set
@@ -116,9 +116,8 @@ func (c *Client) Pull(model string, ignoreRuntimeMemoryCheck bool, printer stand
 
 	return c.withRetries("download", 3, printer, func(attempt int) (string, bool, error, bool) {
 		jsonData, err := json.Marshal(dmrm.ModelCreateRequest{
-			From:                     model,
-			IgnoreRuntimeMemoryCheck: ignoreRuntimeMemoryCheck,
-			BearerToken:              hfToken,
+			From:        model,
+			BearerToken: hfToken,
 		})
 		if err != nil {
 			// Marshaling errors are not retryable

cmd/cli/desktop/desktop_test.go

@@ -39,7 +39,7 @@ func TestPullHuggingFaceModel(t *testing.T) {
 	}, nil)
 
 	printer := NewSimplePrinter(func(s string) {})
-	_, _, err := client.Pull(modelName, false, printer)
+	_, _, err := client.Pull(modelName, printer)
 	assert.NoError(t, err)
 }
 
@@ -126,7 +126,7 @@ func TestNonHuggingFaceModel(t *testing.T) {
 	}, nil)
 
 	printer := NewSimplePrinter(func(s string) {})
-	_, _, err := client.Pull(modelName, false, printer)
+	_, _, err := client.Pull(modelName, printer)
 	assert.NoError(t, err)
 }
 
@@ -250,7 +250,7 @@ func TestPullRetryOnNetworkError(t *testing.T) {
 	)
 
 	printer := NewSimplePrinter(func(s string) {})
-	_, _, err := client.Pull(modelName, false, printer)
+	_, _, err := client.Pull(modelName, printer)
 	assert.NoError(t, err)
 }
 
@@ -270,7 +270,7 @@ func TestPullNoRetryOn4xxError(t *testing.T) {
 	}, nil).Times(1)
 
 	printer := NewSimplePrinter(func(s string) {})
-	_, _, err := client.Pull(modelName, false, printer)
+	_, _, err := client.Pull(modelName, printer)
 	assert.Error(t, err)
 	assert.Contains(t, err.Error(), "Model not found")
 }
@@ -297,7 +297,7 @@ func TestPullRetryOn5xxError(t *testing.T) {
 	)
 
 	printer := NewSimplePrinter(func(s string) {})
-	_, _, err := client.Pull(modelName, false, printer)
+	_, _, err := client.Pull(modelName, printer)
 	assert.NoError(t, err)
 }
 
@@ -324,7 +324,7 @@ func TestPullRetryOnServiceUnavailable(t *testing.T) {
 	)
 
 	printer := NewSimplePrinter(func(s string) {})
-	_, _, err := client.Pull(modelName, false, printer)
+	_, _, err := client.Pull(modelName, printer)
 	assert.NoError(t, err)
 }
 
@@ -341,7 +341,7 @@ func TestPullMaxRetriesExhausted(t *testing.T) {
 	mockClient.EXPECT().Do(gomock.Any()).Return(nil, io.EOF).Times(4)
 
 	printer := NewSimplePrinter(func(s string) {})
-	_, _, err := client.Pull(modelName, false, printer)
+	_, _, err := client.Pull(modelName, printer)
 	assert.Error(t, err)
 	assert.Contains(t, err.Error(), "failed to download after 3 retries")
 }

cmd/cli/docs/reference/model_pull.md

@@ -3,12 +3,6 @@
 <!---MARKER_GEN_START-->
 Pull a model from Docker Hub or HuggingFace to your local environment
 
-### Options
-
-| Name                            | Type   | Default | Description                                                                       |
-|:--------------------------------|:-------|:--------|:----------------------------------------------------------------------------------|
-| `--ignore-runtime-memory-check` | `bool` |         | Do not block pull if estimated runtime memory for model exceeds system resources. |
-
 
 <!---MARKER_GEN_END-->
 

cmd/cli/docs/reference/model_run.md

@@ -5,12 +5,11 @@ Run a model and interact with it using a submitted prompt or chat mode
 
 ### Options
 
-| Name                            | Type     | Default | Description                                                                       |
-|:--------------------------------|:---------|:--------|:----------------------------------------------------------------------------------|
-| `--color`                       | `string` | `no`    | Use colored output (auto\|yes\|no)                                                |
-| `--debug`                       | `bool`   |         | Enable debug logging                                                              |
-| `-d`, `--detach`                | `bool`   |         | Load the model in the background without interaction                              |
-| `--ignore-runtime-memory-check` | `bool`   |         | Do not block pull if estimated runtime memory for model exceeds system resources. |
+| Name             | Type     | Default | Description                                          |
+|:-----------------|:---------|:--------|:-----------------------------------------------------|
+| `--color`        | `string` | `no`    | Use colored output (auto\|yes\|no)                   |
+| `--debug`        | `bool`   |         | Enable debug logging                                 |
+| `-d`, `--detach` | `bool`   |         | Load the model in the background without interaction |
 
 
 <!---MARKER_GEN_END-->

pkg/inference/models/api.go

@@ -14,9 +14,6 @@ import (
 type ModelCreateRequest struct {
 	// From is the name of the model to pull.
 	From string `json:"from"`
-	// IgnoreRuntimeMemoryCheck indicates whether the server should check if it has sufficient
-	// memory to run the given model (assuming default configuration).
-	IgnoreRuntimeMemoryCheck bool `json:"ignore-runtime-memory-check,omitempty"`
 	// BearerToken is an optional bearer token for authentication.
 	BearerToken string `json:"bearer-token,omitempty"`
 }

pkg/inference/scheduling/loader.go

@@ -194,15 +194,6 @@ func (l *loader) broadcast() {
 	}
 }
 
-// formatMemorySize formats a memory size in bytes as a string.
-// Values of 0 or 1 are treated as sentinel values for "unknown" memory size.
-func formatMemorySize(bytes uint64) string {
-	if bytes <= 1 {
-		return "unknown"
-	}
-	return fmt.Sprintf("%d MB", bytes/1024/1024)
-}
-
 // freeRunnerSlot frees a runner slot.
 // The caller must hold the loader lock.
 func (l *loader) freeRunnerSlot(slot int, key runnerKey) {

pkg/inference/scheduling/loader_test.go

@@ -125,65 +125,6 @@ func createAliveTerminableMockRunner(log *logrus.Entry, backend inference.Backen
 	}
 }
 
-// TestFormatMemorySize tests the formatMemorySize helper function
-func TestFormatMemorySize(t *testing.T) {
-	tests := []struct {
-		name     string
-		bytes    uint64
-		expected string
-	}{
-		{
-			name:     "sentinel value 0 is unknown",
-			bytes:    0,
-			expected: "unknown",
-		},
-		{
-			name:     "sentinel value 1 is unknown",
-			bytes:    1,
-			expected: "unknown",
-		},
-		{
-			name:     "2 bytes is still unknown (edge case)",
-			bytes:    2,
-			expected: "0 MB",
-		},
-		{
-			name:     "1 MB",
-			bytes:    1024 * 1024,
-			expected: "1 MB",
-		},
-		{
-			name:     "512 MB",
-			bytes:    512 * 1024 * 1024,
-			expected: "512 MB",
-		},
-		{
-			name:     "1 GB",
-			bytes:    1024 * 1024 * 1024,
-			expected: "1024 MB",
-		},
-		{
-			name:     "8 GB",
-			bytes:    8 * 1024 * 1024 * 1024,
-			expected: "8192 MB",
-		},
-		{
-			name:     "fractional MB rounds down",
-			bytes:    1024*1024 + 512*1024, // 1.5 MB
-			expected: "1 MB",
-		},
-	}
-
-	for _, tt := range tests {
-		t.Run(tt.name, func(t *testing.T) {
-			result := formatMemorySize(tt.bytes)
-			if result != tt.expected {
-				t.Errorf("formatMemorySize(%d) = %q, want %q", tt.bytes, result, tt.expected)
-			}
-		})
-	}
-}
-
 // TestMakeRunnerKey tests that runner keys are created correctly
 func TestMakeRunnerKey(t *testing.T) {
 	tests := []struct {