proxy: fix metrics capture for v1/responses (#586)

properly parse anthropic compatible usage data from streaming responses.

closes: #577

.github/workflows/containers.yml

@@ -29,7 +29,7 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        platform: [intel, cuda, vulkan, cpu, musa, rocm]
+        platform: [intel, cuda, cuda13, vulkan, cpu, musa, rocm]
       fail-fast: false
     steps:
       - name: Checkout code

config-schema.json

@@ -48,6 +48,12 @@
             "default": 120,
             "description": "Number of seconds to wait for a model to be ready to serve requests."
         },
+        "globalTTL": {
+            "type": "integer",
+            "minimum": 0,
+            "default": 0,
+            "description": "Default TTL for all models in seconds, 0 means no TTL and models will never be automatically unloaded"
+        },
         "logLevel": {
             "type": "string",
             "enum": [
@@ -177,9 +183,9 @@
                     },
                     "ttl": {
                         "type": "integer",
-                        "minimum": 0,
-                        "default": 0,
-                        "description": "Automatically unload the model after ttl seconds. 0 disables unloading. Must be >0 to enable."
+                        "minimum": -1,
+                        "default": -1,
+                        "description": "Automatically unload the model after ttl seconds. -1 uses the global TTL value, 0 disables unloading. Must be >0 to enable."
                     },
                     "useModelName": {
                         "type": "string",
@@ -368,4 +374,4 @@
             "description": "A dictionary of remote peers and models they provide. Peers can be another llama-swap or any server that provides the /v1/ generative API endpoints supported by llama-swap."
         }
     }
-}
+}

config.example.yaml

@@ -75,6 +75,11 @@ sendLoadingState: true
 #   all fields except for Id so chat UIs can use the alias equivalent to the original.
 includeAliasesInList: false
 
+# globalTTL: the default TTL in seconds before unloading a model
+# - optional, default: 0 (never automatically unload)
+# - must be >= 0
+globalTTL: 0
+
 # macros: a dictionary of string substitutions
 # - optional, default: empty dictionary
 # - macros are reusable snippets
@@ -180,8 +185,10 @@ models:
     checkEndpoint: /custom-endpoint
 
     # ttl: automatically unload the model after ttl seconds
-    # - optional, default: 0
-    # - ttl values must be a value greater than 0
+    # - optional, default: -1 (use global default)
+    # - ttl values must be a value greater than or equal to 0
+    # - a ttl of -1 will use the global TTL value as the default
+    # - a ttl of 0 will mean never unload
     # - a value of 0 disables automatic unloading of the model
     ttl: 60
 

docker/build-container.sh

@@ -27,7 +27,7 @@ ARCH=$1
 PUSH_IMAGES=${2:-false}
 
 # List of allowed architectures
-ALLOWED_ARCHS=("intel" "vulkan" "musa" "cuda" "cpu" "rocm")
+ALLOWED_ARCHS=("intel" "vulkan" "musa" "cuda" "cuda13" "cpu" "rocm")
 
 # Check if ARCH is in the allowed list
 if [[ ! " ${ALLOWED_ARCHS[@]} " =~ " ${ARCH} " ]]; then

proxy/config/config.go

@@ -124,6 +124,7 @@ type Config struct {
 	LogToStdout        string                 `yaml:"logToStdout"`
 	MetricsMaxInMemory int                    `yaml:"metricsMaxInMemory"`
 	CaptureBuffer      int                    `yaml:"captureBuffer"`
+	GlobalTTL          int                    `yaml:"globalTTL"`
 	Models             map[string]ModelConfig `yaml:"models"` /* key is model ID */
 	Profiles           map[string][]string    `yaml:"profiles"`
 	Groups             map[string]GroupConfig `yaml:"groups"` /* key is group ID */
@@ -203,6 +204,7 @@ func LoadConfigFromReader(r io.Reader) (Config, error) {
 		LogToStdout:        LogToStdoutProxy,
 		MetricsMaxInMemory: 1000,
 		CaptureBuffer:      5,
+		GlobalTTL:          0,
 	}
 	if err = yaml.Unmarshal([]byte(yamlStr), &config); err != nil {
 		return Config{}, err
@@ -216,6 +218,10 @@ func LoadConfigFromReader(r io.Reader) (Config, error) {
 		return Config{}, fmt.Errorf("startPort must be greater than 1")
 	}
 
+	if config.GlobalTTL < 0 {
+		return Config{}, fmt.Errorf("globalTTL must be >= 0")
+	}
+
 	switch config.LogToStdout {
 	case LogToStdoutProxy, LogToStdoutUpstream, LogToStdoutBoth, LogToStdoutNone:
 	default:
@@ -255,6 +261,15 @@ func LoadConfigFromReader(r io.Reader) (Config, error) {
 		modelConfig.Cmd = StripComments(modelConfig.Cmd)
 		modelConfig.CmdStop = StripComments(modelConfig.CmdStop)
 
+		// set model TTL to globalTTL it is the default value
+		if modelConfig.UnloadAfter == MODEL_CONFIG_DEFAULT_TTL {
+			modelConfig.UnloadAfter = config.GlobalTTL
+		}
+
+		if modelConfig.UnloadAfter < 0 {
+			return Config{}, fmt.Errorf("model %s: invalid TTL value %d", modelId, modelConfig.UnloadAfter)
+		}
+
 		// Validate model macros
 		for _, macro := range modelConfig.Macros {
 			if err = validateMacro(macro.Name, macro.Value); err != nil {
@@ -293,6 +308,8 @@ func LoadConfigFromReader(r io.Reader) (Config, error) {
 			modelConfig.Proxy = strings.ReplaceAll(modelConfig.Proxy, macroSlug, macroStr)
 			modelConfig.CheckEndpoint = strings.ReplaceAll(modelConfig.CheckEndpoint, macroSlug, macroStr)
 			modelConfig.Filters.StripParams = strings.ReplaceAll(modelConfig.Filters.StripParams, macroSlug, macroStr)
+			modelConfig.Name = strings.ReplaceAll(modelConfig.Name, macroSlug, macroStr)
+			modelConfig.Description = strings.ReplaceAll(modelConfig.Description, macroSlug, macroStr)
 
 			// Substitute macros in SetParamsByID keys and values
 			if len(modelConfig.Filters.SetParamsByID) > 0 {
@@ -336,6 +353,8 @@ func LoadConfigFromReader(r io.Reader) (Config, error) {
 			modelConfig.Cmd = strings.ReplaceAll(modelConfig.Cmd, macroSlug, macroStr)
 			modelConfig.CmdStop = strings.ReplaceAll(modelConfig.CmdStop, macroSlug, macroStr)
 			modelConfig.Proxy = strings.ReplaceAll(modelConfig.Proxy, macroSlug, macroStr)
+			modelConfig.Name = strings.ReplaceAll(modelConfig.Name, macroSlug, macroStr)
+			modelConfig.Description = strings.ReplaceAll(modelConfig.Description, macroSlug, macroStr)
 
 			if len(modelConfig.Metadata) > 0 {
 				result, err := substituteMacroInValue(modelConfig.Metadata, "PORT", nextPort)
@@ -355,6 +374,8 @@ func LoadConfigFromReader(r io.Reader) (Config, error) {
 			"proxy":               modelConfig.Proxy,
 			"checkEndpoint":       modelConfig.CheckEndpoint,
 			"filters.stripParams": modelConfig.Filters.StripParams,
+			"name":                modelConfig.Name,
+			"description":         modelConfig.Description,
 		}
 
 		for fieldName, fieldValue := range fieldMap {

proxy/config/config_test.go

@@ -848,6 +848,71 @@ func TestConfig_APIKeys_EnvMacros(t *testing.T) {
 	})
 }
 
+func TestConfig_GlobalTTL(t *testing.T) {
+	t.Run("globalTTL sets default for models", func(t *testing.T) {
+		content := `
+globalTTL: 300
+models:
+  model1:
+    cmd: server --port ${PORT}
+`
+		config, err := LoadConfigFromReader(strings.NewReader(content))
+		assert.NoError(t, err)
+		assert.Equal(t, 300, config.GlobalTTL)
+		assert.Equal(t, 300, config.Models["model1"].UnloadAfter)
+	})
+
+	t.Run("model ttl=0 overrides globalTTL", func(t *testing.T) {
+		content := `
+globalTTL: 300
+models:
+  model1:
+    cmd: server --port ${PORT}
+    ttl: 0
+`
+		config, err := LoadConfigFromReader(strings.NewReader(content))
+		assert.NoError(t, err)
+		assert.Equal(t, 0, config.Models["model1"].UnloadAfter)
+	})
+
+	t.Run("model explicit ttl overrides globalTTL", func(t *testing.T) {
+		content := `
+globalTTL: 300
+models:
+  model1:
+    cmd: server --port ${PORT}
+    ttl: 600
+`
+		config, err := LoadConfigFromReader(strings.NewReader(content))
+		assert.NoError(t, err)
+		assert.Equal(t, 600, config.Models["model1"].UnloadAfter)
+	})
+
+	t.Run("globalTTL defaults to 0", func(t *testing.T) {
+		content := `
+models:
+  model1:
+    cmd: server --port ${PORT}
+`
+		config, err := LoadConfigFromReader(strings.NewReader(content))
+		assert.NoError(t, err)
+		assert.Equal(t, 0, config.GlobalTTL)
+		assert.Equal(t, 0, config.Models["model1"].UnloadAfter)
+	})
+
+	t.Run("negative globalTTL rejected", func(t *testing.T) {
+		content := `
+globalTTL: -1
+models:
+  model1:
+    cmd: server --port ${PORT}
+`
+		_, err := LoadConfigFromReader(strings.NewReader(content))
+		assert.Error(t, err)
+		assert.Contains(t, err.Error(), "globalTTL must be >= 0")
+	})
+}
+
 func TestConfig_EnvMacros(t *testing.T) {
 	t.Run("basic env substitution in cmd", func(t *testing.T) {
 		t.Setenv("TEST_MODEL_PATH", "/opt/models")

proxy/config/macro_in_macro_test.go

@@ -104,6 +104,62 @@ models:
 	assert.Contains(t, err.Error(), "self-reference")
 }
 
+// Test macro substitution in name and description fields
+func TestConfig_MacroInNameAndDescription(t *testing.T) {
+	content := `
+startPort: 10000
+macros:
+  "VARIANT": "Q4_K_M"
+  "FAMILY": "llama"
+
+models:
+  my-model:
+    cmd: echo ok
+    proxy: http://localhost:8080
+    name: "${FAMILY} ${VARIANT}"
+    description: "A ${FAMILY} model in ${VARIANT} format"
+`
+
+	config, err := LoadConfigFromReader(strings.NewReader(content))
+	assert.NoError(t, err)
+	assert.Equal(t, "llama Q4_K_M", config.Models["my-model"].Name)
+	assert.Equal(t, "A llama model in Q4_K_M format", config.Models["my-model"].Description)
+}
+
+// Test MODEL_ID macro in name and description fields
+func TestConfig_ModelIDInNameAndDescription(t *testing.T) {
+	content := `
+startPort: 10000
+models:
+  llama-3b:
+    cmd: echo ok
+    proxy: http://localhost:8080
+    name: "Model: ${MODEL_ID}"
+    description: "Running ${MODEL_ID}"
+`
+
+	config, err := LoadConfigFromReader(strings.NewReader(content))
+	assert.NoError(t, err)
+	assert.Equal(t, "Model: llama-3b", config.Models["llama-3b"].Name)
+	assert.Equal(t, "Running llama-3b", config.Models["llama-3b"].Description)
+}
+
+// Test unknown macro in name or description returns an error
+func TestConfig_UnknownMacroInNameDescription(t *testing.T) {
+	content := `
+startPort: 10000
+models:
+  test:
+    cmd: echo ok
+    proxy: http://localhost:8080
+    name: "Model ${UNDEFINED}"
+`
+
+	_, err := LoadConfigFromReader(strings.NewReader(content))
+	assert.Error(t, err)
+	assert.Contains(t, err.Error(), "UNDEFINED")
+}
+
 // Test undefined macro reference error
 func TestConfig_UndefinedMacroReference(t *testing.T) {
 	content := `

proxy/config/model_config.go

@@ -5,6 +5,10 @@ import (
 	"runtime"
 )
 
+const (
+	MODEL_CONFIG_DEFAULT_TTL = -1
+)
+
 type ModelConfig struct {
 	Cmd           string   `yaml:"cmd"`
 	CmdStop       string   `yaml:"cmdStop"`
@@ -47,7 +51,7 @@ func (m *ModelConfig) UnmarshalYAML(unmarshal func(interface{}) error) error {
 		Aliases:          []string{},
 		Env:              []string{},
 		CheckEndpoint:    "/health",
-		UnloadAfter:      0,
+		UnloadAfter:      MODEL_CONFIG_DEFAULT_TTL, // use GlobalTTL
 		Unlisted:         false,
 		UseModelName:     "",
 		ConcurrencyLimit: 0,

proxy/metrics_monitor.go

@@ -350,6 +350,11 @@ func processStreamingResponse(modelID string, start time.Time, body []byte) (Tok
 			usage := parsed.Get("usage")
 			timings := parsed.Get("timings")
 
+			// v1/responses format nests usage under response.usage
+			if !usage.Exists() {
+				usage = parsed.Get("response.usage")
+			}
+
 			if usage.Exists() || timings.Exists() {
 				return parseMetrics(modelID, start, usage, timings)
 			}
@@ -503,9 +508,9 @@ func filterAcceptEncoding(acceptEncoding string) string {
 	supported := map[string]bool{"gzip": true, "deflate": true}
 	var filtered []string
 
-	for _, part := range strings.Split(acceptEncoding, ",") {
+	for part := range strings.SplitSeq(acceptEncoding, ",") {
 		// Parse encoding and optional quality value (e.g., "gzip;q=1.0")
-		encoding := strings.TrimSpace(strings.Split(part, ";")[0])
+		encoding, _, _ := strings.Cut(strings.TrimSpace(part), ";")
 		if supported[strings.ToLower(encoding)] {
 			filtered = append(filtered, strings.TrimSpace(part))
 		}

proxy/metrics_monitor_test.go

@@ -709,6 +709,35 @@ data: [DONE]
 		assert.Equal(t, 0, metrics[0].OutputTokens)
 	})
 
+	t.Run("v1/responses format with nested response.usage", func(t *testing.T) {
+		mm := newMetricsMonitor(testLogger, 10, 0)
+
+		// v1/responses SSE format: usage is nested under response.usage
+		responseBody := "event: response.completed\n" +
+			`data: {"type":"response.completed","response":{"id":"resp_abc","object":"response","created_at":1773416985,"status":"completed","model":"test-model","output":[],"usage":{"input_tokens":17,"output_tokens":23,"total_tokens":40}}}` +
+			"\n\n"
+
+		nextHandler := func(modelID string, w http.ResponseWriter, r *http.Request) error {
+			w.Header().Set("Content-Type", "text/event-stream")
+			w.WriteHeader(http.StatusOK)
+			w.Write([]byte(responseBody))
+			return nil
+		}
+
+		req := httptest.NewRequest("POST", "/v1/responses", nil)
+		rec := httptest.NewRecorder()
+		ginCtx, _ := gin.CreateTestContext(rec)
+
+		err := mm.wrapHandler("test-model", ginCtx.Writer, req, nextHandler)
+		assert.NoError(t, err)
+
+		metrics := mm.getMetrics()
+		assert.Equal(t, 1, len(metrics))
+		assert.Equal(t, "test-model", metrics[0].Model)
+		assert.Equal(t, 17, metrics[0].InputTokens)
+		assert.Equal(t, 23, metrics[0].OutputTokens)
+	})
+
 	t.Run("handles empty streaming response records minimal metrics", func(t *testing.T) {
 		mm := newMetricsMonitor(testLogger, 10, 0)
 

proxy/process_test.go

@@ -117,12 +117,12 @@ func TestProcess_UnloadAfterTTL(t *testing.T) {
 	}
 
 	expectedMessage := "I_sense_imminent_danger"
-	config := getTestSimpleResponderConfig(expectedMessage)
-	assert.Equal(t, 0, config.UnloadAfter)
-	config.UnloadAfter = 3 // seconds
-	assert.Equal(t, 3, config.UnloadAfter)
+	conf := getTestSimpleResponderConfig(expectedMessage)
+	assert.Equal(t, config.MODEL_CONFIG_DEFAULT_TTL, conf.UnloadAfter)
+	conf.UnloadAfter = 3 // seconds
+	assert.Equal(t, 3, conf.UnloadAfter)
 
-	process := NewProcess("ttl_test", 2, config, debugLogger, debugLogger)
+	process := NewProcess("ttl_test", 2, conf, debugLogger, debugLogger)
 	defer process.Stop()
 
 	// this should take 4 seconds
@@ -159,12 +159,12 @@ func TestProcess_LowTTLValue(t *testing.T) {
 		t.Skip("skipping test, edit process_test.go to run it ")
 	}
 
-	config := getTestSimpleResponderConfig("fast_ttl")
-	assert.Equal(t, 0, config.UnloadAfter)
-	config.UnloadAfter = 1 // second
-	assert.Equal(t, 1, config.UnloadAfter)
+	conf := getTestSimpleResponderConfig("fast_ttl")
+	assert.Equal(t, config.MODEL_CONFIG_DEFAULT_TTL, conf.UnloadAfter)
+	conf.UnloadAfter = 1 // second
+	assert.Equal(t, 1, conf.UnloadAfter)
 
-	process := NewProcess("ttl", 2, config, debugLogger, debugLogger)
+	process := NewProcess("ttl", 2, conf, debugLogger, debugLogger)
 	defer process.Stop()
 
 	for i := 0; i < 100; i++ {

proxy/proxymanager_test.go

@@ -730,7 +730,7 @@ func TestProxyManager_RunningEndpoint(t *testing.T) {
 		// Verify extended fields are present
 		assert.NotEmpty(t, response.Running[0].Cmd, "cmd should be populated")
 		assert.NotEmpty(t, response.Running[0].Proxy, "proxy should be populated")
-		assert.Equal(t, 0, response.Running[0].TTL, "ttl should default to 0")
+		assert.Equal(t, -1, response.Running[0].TTL, "ttl should default to -1 (use globalTTL)")
 	})
 }
 

ui-svelte/.npmrc

@@ -0,0 +1 @@
+legacy-peer-deps=true

ui-svelte/package.json

@@ -12,18 +12,18 @@
     "test:watch": "vitest"
   },
   "devDependencies": {
-    "@sveltejs/vite-plugin-svelte": "^5.0.3",
+    "@sveltejs/vite-plugin-svelte": "^7.0.0",
     "@tailwindcss/vite": "^4.1.8",
     "@tsconfig/svelte": "^5.0.4",
     "@types/hast": "^3.0.4",
     "@types/node": "^25.1.0",
-    "svelte": "^5.19.0",
+    "svelte": "^5.46.4",
     "svelte-check": "^4.1.4",
     "tailwindcss": "^4.1.8",
     "typescript": "~5.8.3",
-    "vite": "^6.3.5",
-    "vite-plugin-compression2": "^2.4.0",
-    "vitest": "^4.0.18"
+    "vite": "^8.0.0",
+    "vite-plugin-compression2": "^2.5.1",
+    "vitest": "^4.1.0"
   },
   "dependencies": {
     "highlight.js": "^11.11.1",

ui-svelte/src/components/playground/ChatMessage.svelte

@@ -116,6 +116,47 @@
       cancelEdit();
     }
   }
+
+  const COPY_SVG = `<svg xmlns="http://www.w3.org/2000/svg" width="14" height="14" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round"><rect width="14" height="14" x="8" y="8" rx="2" ry="2"/><path d="M4 16c-1.1 0-2-.9-2-2V4c0-1.1.9-2 2-2h10c1.1 0 2 .9 2 2"/></svg>`;
+  const CHECK_SVG = `<svg xmlns="http://www.w3.org/2000/svg" width="14" height="14" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round"><path d="M20 6 9 17l-5-5"/></svg>`;
+
+  function codeBlockCopy(node: HTMLElement) {
+    function attachButtons() {
+      node.querySelectorAll<HTMLPreElement>('pre:not([data-copy-btn])').forEach(pre => {
+        pre.setAttribute('data-copy-btn', 'true');
+        const btn = document.createElement('button');
+        btn.className = 'code-copy-btn';
+        btn.title = 'Copy code';
+        btn.innerHTML = COPY_SVG;
+        btn.addEventListener('click', async () => {
+          const text = pre.querySelector('code')?.textContent ?? pre.textContent ?? '';
+          try {
+            if (navigator.clipboard && window.isSecureContext) {
+              await navigator.clipboard.writeText(text);
+            } else {
+              const ta = document.createElement('textarea');
+              ta.value = text;
+              ta.style.cssText = 'position:fixed;left:-9999px';
+              document.body.appendChild(ta);
+              ta.select();
+              document.execCommand('copy');
+              document.body.removeChild(ta);
+            }
+            btn.innerHTML = CHECK_SVG;
+            btn.classList.add('copied');
+            setTimeout(() => { btn.innerHTML = COPY_SVG; btn.classList.remove('copied'); }, 2000);
+          } catch (e) {
+            console.error('copy failed', e);
+          }
+        });
+        pre.appendChild(btn);
+      });
+    }
+    attachButtons();
+    const mo = new MutationObserver(attachButtons);
+    mo.observe(node, { childList: true, subtree: true });
+    return { destroy: () => mo.disconnect() };
+  }
 </script>
 
 <div class="flex {role === 'user' ? 'justify-end' : 'justify-start'} mb-4">
@@ -174,7 +215,7 @@
       {#if showRaw}
         <div class="whitespace-pre-wrap font-mono text-sm">{textContent}</div>
       {:else}
-        <div class="prose prose-sm dark:prose-invert max-w-none">
+        <div class="prose prose-sm dark:prose-invert max-w-none" use:codeBlockCopy>
           {#each renderedParts.blocks as block (block.id)}
             {@html block.html}
           {/each}
@@ -299,14 +340,42 @@
 
 <style>
   .prose :global(pre) {
+    position: relative;
     background-color: var(--color-surface);
     border: 1px solid var(--color-border, rgba(128, 128, 128, 0.2));
     border-radius: 0.375rem;
     padding: 0.75rem;
+    padding-right: 2.5rem;
     overflow-x: auto;
     margin: 0.5rem 0;
   }
 
+  .prose :global(.code-copy-btn) {
+    position: absolute;
+    top: 0.375rem;
+    right: 0.375rem;
+    display: flex;
+    align-items: center;
+    justify-content: center;
+    padding: 0.25rem;
+    border-radius: 0.25rem;
+    border: 1px solid var(--color-border);
+    background: var(--color-surface);
+    color: var(--color-txtsecondary);
+    cursor: pointer;
+    transition: background-color 0.15s;
+    line-height: 0;
+  }
+
+  .prose :global(.code-copy-btn:hover) {
+    background: var(--color-secondary);
+  }
+
+  .prose :global(.code-copy-btn.copied) {
+    color: var(--color-success);
+    opacity: 1;
+  }
+
   .prose :global(code) {
     font-family: ui-monospace, SFMono-Regular, Menlo, Monaco, Consolas, monospace;
     font-size: 0.875em;

ui-svelte/src/stores/api.ts

@@ -62,7 +62,7 @@ export function enableAPIEvents(enabled: boolean): void {
             const newModels = JSON.parse(message.data) as Model[];
             // Sort models by name and id
             newModels.sort((a, b) => {
-              return (a.name + a.id).localeCompare(b.name + b.id);
+              return (a.name + a.id).localeCompare(b.name + b.id, undefined, { numeric : true} );
             });
             models.set(newModels);
             break;