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

properly parse anthropic compatible usage data from streaming responses.

closes: #577

proxy/config/config.go

@@ -308,6 +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 {
@@ -351,6 +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)
@@ -370,6 +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/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/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)
 

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": "^8.0.0",
-    "vite-plugin-compression2": "^2.4.0",
+    "vite-plugin-compression2": "^2.5.1",
-    "vitest": "^4.0.18"
+    "vitest": "^4.1.0"
   },
   "dependencies": {
     "highlight.js": "^11.11.1",

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;