Update github actions for notifying homebrew build (#212)

Combine homebrew-llama-swap event with the release action

.github/workflows/release.yml

@@ -7,6 +7,10 @@ on:
 
   # Allows manual triggering of the workflow
   workflow_dispatch:
+    inputs:
+      tag:
+        description: 'Tag version to release (e.g. v144)'
+        required: true
 
 permissions:
   contents: write
@@ -20,15 +24,15 @@ jobs:
         uses: actions/checkout@v4
         with:
           fetch-depth: 0
+          ref: ${{ github.event.inputs.tag || github.ref }}
       -
         name: Set up Go
         uses: actions/setup-go@v5
-
       -
         name: Set up Node.js
         uses: actions/setup-node@v4
         with:
-          node-version: '23'  # or your preferred version
+          node-version: '23'
       -
         name: Install dependencies and build UI
         run: |
@@ -46,4 +50,30 @@ jobs:
           version: '~> v2'
           args: release --clean
         env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+
+  trigger-tap-update:
+    runs-on: ubuntu-latest
+    needs: goreleaser
+    steps:
+      - name: "Resolve tag to dispatch"
+        id: tag
+        run: |
+          if [[ "${{ github.event_name }}" == "workflow_dispatch" ]]; then
+            echo "tag=${{ github.event.inputs.tag }}" >> "$GITHUB_OUTPUT"
+          else
+            echo "tag=${{ github.ref_name }}" >> "$GITHUB_OUTPUT"
+          fi
+
+      - name: "Trigger tap repository update"
+        uses: peter-evans/repository-dispatch@v2
+        with:
+          token: ${{ secrets.TAP_REPO_PAT }}
+          repository: mostlygeek/homebrew-llama-swap
+          event-type: new-release
+          client-payload: |
+            {
+              "release": {
+                "tag_name": "${{ steps.tag.outputs.tag }}"
+              }
+            }

README.md

@@ -18,7 +18,7 @@ Written in golang, it is very easy to install (single binary with no dependencie
   - `v1/completions`
   - `v1/chat/completions`
   - `v1/embeddings`
-  - `v1/rerank`
+  - `v1/rerank`, `v1/reranking`, `rerank`
   - `v1/audio/speech` ([#36](https://github.com/mostlygeek/llama-swap/issues/36))
   - `v1/audio/transcriptions` ([docs](https://github.com/mostlygeek/llama-swap/issues/41#issuecomment-2722637867))
 - ✅ llama-swap custom API endpoints
@@ -70,9 +70,10 @@ See the [configuration documentation](https://github.com/mostlygeek/llama-swap/w
 
 ## Web UI
 
-llama-swap ships with a web based interface to make it easier to monitor logs and check the status of models. 
+llama-swap ships with a real time web interface to monitor logs and status of models:
+
+<img width="1786" height="1334" alt="image" src="https://github.com/user-attachments/assets/d6258cb9-1dad-40db-828f-2be860aec8fe" />
 
-<img width="1758" alt="image" src="https://github.com/user-attachments/assets/31ae5bcd-5efd-46b0-b64b-6db9e60196d3" />
 
 ## Docker Install ([download images](https://github.com/mostlygeek/llama-swap/pkgs/container/llama-swap))
 
@@ -121,6 +122,20 @@ $ docker run -it --rm --runtime nvidia -p 9292:8080 \
 
 </details>
 
+## Homebrew Install (macOS/Linux)
+
+For macOS & Linux users, `llama-swap` can be installed via [Homebrew](https://brew.sh):
+
+```shell
+# Set up tap and install formula 
+brew tap mostlygeek/llama-swap
+brew install llama-swap
+# Run llama-swap
+llama-swap --config path/to/config.yaml --listen localhost:8080
+```
+
+This will install the `llama-swap` binary and make it available in your path. See the [configuration documentation](https://github.com/mostlygeek/llama-swap/wiki/Configuration)
+
 ## Bare metal Install ([download](https://github.com/mostlygeek/llama-swap/releases))
 
 Pre-built binaries are available for Linux, Mac, Windows and FreeBSD. These are automatically published and are likely a few hours ahead of the docker releases. The baremetal install works with any OpenAI compatible server, not just llama-server.
@@ -173,6 +188,13 @@ Any OpenAI compatible server would work. llama-swap was originally designed for
 
 For Python based inference servers like vllm or tabbyAPI it is recommended to run them via podman or docker. This provides clean environment isolation as well as responding correctly to `SIGTERM` signals to shutdown.
 
+## Contributors 
+<a href="https://github.com/mostlygeek/llama-swap/graphs/contributors">
+  <img src="https://contrib.rocks/image?repo=mostlygeek/llama-swap" />
+</a>
+
+Made with [contrib.rocks](https://contrib.rocks).
+
 ## Star History
 
 [![Star History Chart](https://api.star-history.com/svg?repos=mostlygeek/llama-swap&type=Date)](https://www.star-history.com/#mostlygeek/llama-swap&Date)

config.example.yaml

@@ -15,6 +15,12 @@ healthCheckTimeout: 500
 # - Valid log levels: debug, info, warn, error
 logLevel: info
 
+# metricsMaxInMemory: maximum number of metrics to keep in memory
+# - optional, default: 1000
+# - controls how many metrics are stored in memory before older ones are discarded
+# - useful for limiting memory usage when processing large volumes of metrics
+metricsMaxInMemory: 1000
+
 # startPort: sets the starting port number for the automatic ${PORT} macro.
 # - optional, default: 5800
 # - the ${PORT} macro can be used in model.cmd and model.proxy settings
@@ -200,4 +206,4 @@ groups:
     members:
       - "forever-modelA"
       - "forever-modelB"
-      - "forever-modelc"
+      - "forever-modelc"

docker/config.example.yaml

@@ -1,5 +1,6 @@
 healthCheckTimeout: 300
 logRequests: true
+metricsMaxInMemory: 1000
 
 models:
   "qwen2.5":

misc/simple-responder/simple-responder.go

@@ -35,20 +35,90 @@ func main() {
 
 	// Set up the handler function using the provided response message
 	r.POST("/v1/chat/completions", func(c *gin.Context) {
-		c.Header("Content-Type", "application/json")
-
-		// add a wait to simulate a slow query
-		if wait, err := time.ParseDuration(c.Query("wait")); err == nil {
-			time.Sleep(wait)
-		}
-
 		bodyBytes, _ := io.ReadAll(c.Request.Body)
 
-		c.JSON(http.StatusOK, gin.H{
-			"responseMessage":  *responseMessage,
-			"h_content_length": c.Request.Header.Get("Content-Length"),
-			"request_body":     string(bodyBytes),
-		})
+		// Check if streaming is requested
+		// Query is checked instead of JSON body since that event stream conflicts with other tests
+		isStreaming := c.Query("stream") == "true"
+
+		if isStreaming {
+			// Set headers for streaming
+			c.Header("Content-Type", "text/event-stream")
+			c.Header("Cache-Control", "no-cache")
+			c.Header("Connection", "keep-alive")
+			c.Header("Transfer-Encoding", "chunked")
+
+			// add a wait to simulate a slow query
+			if wait, err := time.ParseDuration(c.Query("wait")); err == nil {
+				time.Sleep(wait)
+			}
+
+			// Send 10 "asdf" tokens
+			for i := 0; i < 10; i++ {
+				data := gin.H{
+					"created": time.Now().Unix(),
+					"choices": []gin.H{
+						{
+							"index": 0,
+							"delta": gin.H{
+								"content": "asdf",
+							},
+							"finish_reason": nil,
+						},
+					},
+				}
+				c.SSEvent("message", data)
+				c.Writer.Flush()
+			}
+
+			// Send final data with usage info
+			finalData := gin.H{
+				"usage": gin.H{
+					"completion_tokens": 10,
+					"prompt_tokens":     25,
+					"total_tokens":      35,
+				},
+				// add timings to simulate llama.cpp
+				"timings": gin.H{
+					"prompt_n":             25,
+					"prompt_ms":            13,
+					"predicted_n":          10,
+					"predicted_ms":         17,
+					"predicted_per_second": 10,
+				},
+			}
+			c.SSEvent("message", finalData)
+			c.Writer.Flush()
+
+			// Send [DONE]
+			c.SSEvent("message", "[DONE]")
+			c.Writer.Flush()
+		} else {
+			c.Header("Content-Type", "application/json")
+
+			// add a wait to simulate a slow query
+			if wait, err := time.ParseDuration(c.Query("wait")); err == nil {
+				time.Sleep(wait)
+			}
+
+			c.JSON(http.StatusOK, gin.H{
+				"responseMessage":  *responseMessage,
+				"h_content_length": c.Request.Header.Get("Content-Length"),
+				"request_body":     string(bodyBytes),
+				"usage": gin.H{
+					"completion_tokens": 10,
+					"prompt_tokens":     25,
+					"total_tokens":      35,
+				},
+				"timings": gin.H{
+					"prompt_n":             25,
+					"prompt_ms":            13,
+					"predicted_n":          10,
+					"predicted_ms":         17,
+					"predicted_per_second": 10,
+				},
+			})
+		}
 	})
 
 	// for issue #62 to check model name strips profile slug
@@ -74,6 +144,11 @@ func main() {
 		c.Header("Content-Type", "application/json")
 		c.JSON(http.StatusOK, gin.H{
 			"responseMessage": *responseMessage,
+			"usage": gin.H{
+				"completion_tokens": 10,
+				"prompt_tokens":     25,
+				"total_tokens":      35,
+			},
 		})
 
 	})

proxy/config.go

@@ -142,6 +142,7 @@ type Config struct {
 	HealthCheckTimeout int                    `yaml:"healthCheckTimeout"`
 	LogRequests        bool                   `yaml:"logRequests"`
 	LogLevel           string                 `yaml:"logLevel"`
+	MetricsMaxInMemory int                    `yaml:"metricsMaxInMemory"`
 	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 */
@@ -194,6 +195,7 @@ func LoadConfigFromReader(r io.Reader) (Config, error) {
 		HealthCheckTimeout: 120,
 		StartPort:          5800,
 		LogLevel:           "info",
+		MetricsMaxInMemory: 1000,
 	}
 	err = yaml.Unmarshal(data, &config)
 	if err != nil {

proxy/config_posix_test.go

@@ -196,6 +196,7 @@ groups:
 			},
 		},
 		HealthCheckTimeout: 15,
+		MetricsMaxInMemory: 1000,
 		Profiles: map[string][]string{
 			"test": {"model1", "model2"},
 		},

proxy/config_windows_test.go

@@ -193,6 +193,7 @@ groups:
 			},
 		},
 		HealthCheckTimeout: 15,
+		MetricsMaxInMemory: 1000,
 		Profiles: map[string][]string{
 			"test": {"model1", "model2"},
 		},

proxy/events.go

@@ -6,6 +6,7 @@ const ProcessStateChangeEventID = 0x01
 const ChatCompletionStatsEventID = 0x02
 const ConfigFileChangedEventID = 0x03
 const LogDataEventID = 0x04
+const TokenMetricsEventID = 0x05
 
 type ProcessStateChangeEvent struct {
 	ProcessName string

proxy/metrics_middleware.go

@@ -0,0 +1,170 @@
+package proxy
+
+import (
+	"bytes"
+	"fmt"
+	"io"
+	"net/http"
+	"time"
+
+	"github.com/gin-gonic/gin"
+	"github.com/tidwall/gjson"
+)
+
+// MetricsMiddleware sets up the MetricsResponseWriter for capturing upstream requests
+func MetricsMiddleware(pm *ProxyManager) gin.HandlerFunc {
+	return func(c *gin.Context) {
+		bodyBytes, err := io.ReadAll(c.Request.Body)
+		if err != nil {
+			pm.sendErrorResponse(c, http.StatusBadRequest, "could not ready request body")
+			c.Abort()
+			return
+		}
+		c.Request.Body = io.NopCloser(bytes.NewBuffer(bodyBytes))
+
+		requestedModel := gjson.GetBytes(bodyBytes, "model").String()
+		if requestedModel == "" {
+			pm.sendErrorResponse(c, http.StatusBadRequest, "missing or invalid 'model' key")
+			c.Abort()
+			return
+		}
+
+		realModelName, found := pm.config.RealModelName(requestedModel)
+		if !found {
+			pm.sendErrorResponse(c, http.StatusBadRequest, fmt.Sprintf("could not find real modelID for %s", requestedModel))
+			c.Abort()
+			return
+		}
+
+		writer := &MetricsResponseWriter{
+			ResponseWriter: c.Writer,
+			metricsRecorder: &MetricsRecorder{
+				metricsMonitor: pm.metricsMonitor,
+				realModelName:  realModelName,
+				isStreaming:    gjson.GetBytes(bodyBytes, "stream").Bool(),
+				startTime:      time.Now(),
+			},
+		}
+		c.Writer = writer
+		c.Next()
+
+		rec := writer.metricsRecorder
+		rec.processBody(writer.body)
+	}
+}
+
+type MetricsRecorder struct {
+	metricsMonitor *MetricsMonitor
+	realModelName  string
+	isStreaming    bool
+	startTime      time.Time
+}
+
+// processBody handles response processing after request completes
+func (rec *MetricsRecorder) processBody(body []byte) {
+	if rec.isStreaming {
+		rec.processStreamingResponse(body)
+	} else {
+		rec.processNonStreamingResponse(body)
+	}
+}
+
+func (rec *MetricsRecorder) parseAndRecordMetrics(jsonData gjson.Result) bool {
+	usage := jsonData.Get("usage")
+	if !usage.Exists() {
+		return false
+	}
+
+	// default values
+	outputTokens := int(jsonData.Get("usage.completion_tokens").Int())
+	inputTokens := int(jsonData.Get("usage.prompt_tokens").Int())
+	tokensPerSecond := -1.0
+	durationMs := int(time.Since(rec.startTime).Milliseconds())
+
+	// use llama-server's timing data for tok/sec and duration as it is more accurate
+	if timings := jsonData.Get("timings"); timings.Exists() {
+		tokensPerSecond = jsonData.Get("timings.predicted_per_second").Float()
+		durationMs = int(jsonData.Get("timings.prompt_ms").Float() + jsonData.Get("timings.predicted_ms").Float())
+	}
+
+	rec.metricsMonitor.addMetrics(TokenMetrics{
+		Timestamp:       time.Now(),
+		Model:           rec.realModelName,
+		InputTokens:     inputTokens,
+		OutputTokens:    outputTokens,
+		TokensPerSecond: tokensPerSecond,
+		DurationMs:      durationMs,
+	})
+
+	return true
+}
+
+func (rec *MetricsRecorder) processStreamingResponse(body []byte) {
+	// Iterate **backwards** through the lines looking for the data payload with
+	// usage data
+	lines := bytes.Split(body, []byte("\n"))
+
+	for i := len(lines) - 1; i >= 0; i-- {
+		line := bytes.TrimSpace(lines[i])
+		if len(line) == 0 {
+			continue
+		}
+
+		// SSE payload always follows "data:"
+		prefix := []byte("data:")
+		if !bytes.HasPrefix(line, prefix) {
+			continue
+		}
+		data := bytes.TrimSpace(line[len(prefix):])
+
+		if len(data) == 0 {
+			continue
+		}
+
+		if bytes.Equal(data, []byte("[DONE]")) {
+			// [DONE] line itself contains nothing of interest.
+			continue
+		}
+
+		if gjson.ValidBytes(data) {
+			if rec.parseAndRecordMetrics(gjson.ParseBytes(data)) {
+				return // short circuit if a metric was recorded
+			}
+		}
+	}
+}
+
+func (rec *MetricsRecorder) processNonStreamingResponse(body []byte) {
+	if len(body) == 0 {
+		return
+	}
+
+	// Parse JSON to extract usage information
+	if gjson.ValidBytes(body) {
+		rec.parseAndRecordMetrics(gjson.ParseBytes(body))
+	}
+}
+
+// MetricsResponseWriter captures the entire response for non-streaming
+type MetricsResponseWriter struct {
+	gin.ResponseWriter
+	body            []byte
+	metricsRecorder *MetricsRecorder
+}
+
+func (w *MetricsResponseWriter) Write(b []byte) (int, error) {
+	n, err := w.ResponseWriter.Write(b)
+	if err != nil {
+		return n, err
+	}
+	w.body = append(w.body, b...)
+	return n, nil
+}
+
+func (w *MetricsResponseWriter) WriteHeader(statusCode int) {
+	w.ResponseWriter.WriteHeader(statusCode)
+}
+
+func (w *MetricsResponseWriter) Header() http.Header {
+	return w.ResponseWriter.Header()
+}

proxy/metrics_monitor.go

@@ -0,0 +1,82 @@
+package proxy
+
+import (
+	"encoding/json"
+	"sync"
+	"time"
+
+	"github.com/mostlygeek/llama-swap/event"
+)
+
+// TokenMetrics represents parsed token statistics from llama-server logs
+type TokenMetrics struct {
+	ID              int       `json:"id"`
+	Timestamp       time.Time `json:"timestamp"`
+	Model           string    `json:"model"`
+	InputTokens     int       `json:"input_tokens"`
+	OutputTokens    int       `json:"output_tokens"`
+	TokensPerSecond float64   `json:"tokens_per_second"`
+	DurationMs      int       `json:"duration_ms"`
+}
+
+// TokenMetricsEvent represents a token metrics event
+type TokenMetricsEvent struct {
+	Metrics TokenMetrics
+}
+
+func (e TokenMetricsEvent) Type() uint32 {
+	return TokenMetricsEventID // defined in events.go
+}
+
+// MetricsMonitor parses llama-server output for token statistics
+type MetricsMonitor struct {
+	mu         sync.RWMutex
+	metrics    []TokenMetrics
+	maxMetrics int
+	nextID     int
+}
+
+func NewMetricsMonitor(config *Config) *MetricsMonitor {
+	maxMetrics := config.MetricsMaxInMemory
+	if maxMetrics <= 0 {
+		maxMetrics = 1000 // Default fallback
+	}
+
+	mp := &MetricsMonitor{
+		maxMetrics: maxMetrics,
+	}
+
+	return mp
+}
+
+// addMetrics adds a new metric to the collection and publishes an event
+func (mp *MetricsMonitor) addMetrics(metric TokenMetrics) {
+	mp.mu.Lock()
+	defer mp.mu.Unlock()
+
+	metric.ID = mp.nextID
+	mp.nextID++
+	mp.metrics = append(mp.metrics, metric)
+	if len(mp.metrics) > mp.maxMetrics {
+		mp.metrics = mp.metrics[len(mp.metrics)-mp.maxMetrics:]
+	}
+
+	event.Emit(TokenMetricsEvent{Metrics: metric})
+}
+
+// GetMetrics returns a copy of the current metrics
+func (mp *MetricsMonitor) GetMetrics() []TokenMetrics {
+	mp.mu.RLock()
+	defer mp.mu.RUnlock()
+
+	result := make([]TokenMetrics, len(mp.metrics))
+	copy(result, mp.metrics)
+	return result
+}
+
+// GetMetricsJSON returns metrics as JSON
+func (mp *MetricsMonitor) GetMetricsJSON() ([]byte, error) {
+	mp.mu.RLock()
+	defer mp.mu.RUnlock()
+	return json.Marshal(mp.metrics)
+}

proxy/proxymanager.go

@@ -33,6 +33,8 @@ type ProxyManager struct {
 	upstreamLogger *LogMonitor
 	muxLogger      *LogMonitor
 
+	metricsMonitor *MetricsMonitor
+
 	processGroups map[string]*ProcessGroup
 
 	// shutdown signaling
@@ -78,6 +80,8 @@ func New(config Config) *ProxyManager {
 		muxLogger:      stdoutLogger,
 		upstreamLogger: upstreamLogger,
 
+		metricsMonitor: NewMetricsMonitor(&config),
+
 		processGroups: make(map[string]*ProcessGroup),
 
 		shutdownCtx:    shutdownCtx,
@@ -149,14 +153,18 @@ func (pm *ProxyManager) setupGinEngine() {
 		c.Next()
 	})
 
+	mm := MetricsMiddleware(pm)
+
 	// Set up routes using the Gin engine
-	pm.ginEngine.POST("/v1/chat/completions", pm.proxyOAIHandler)
+	pm.ginEngine.POST("/v1/chat/completions", mm, pm.proxyOAIHandler)
 	// Support legacy /v1/completions api, see issue #12
-	pm.ginEngine.POST("/v1/completions", pm.proxyOAIHandler)
+	pm.ginEngine.POST("/v1/completions", mm, pm.proxyOAIHandler)
 
 	// Support embeddings
-	pm.ginEngine.POST("/v1/embeddings", pm.proxyOAIHandler)
-	pm.ginEngine.POST("/v1/rerank", pm.proxyOAIHandler)
+	pm.ginEngine.POST("/v1/embeddings", mm, pm.proxyOAIHandler)
+	pm.ginEngine.POST("/v1/rerank", mm, pm.proxyOAIHandler)
+	pm.ginEngine.POST("/v1/reranking", mm, pm.proxyOAIHandler)
+	pm.ginEngine.POST("/rerank", mm, pm.proxyOAIHandler)
 
 	// Support audio/speech endpoint
 	pm.ginEngine.POST("/v1/audio/speech", pm.proxyOAIHandler)
@@ -183,6 +191,9 @@ func (pm *ProxyManager) setupGinEngine() {
 
 	pm.ginEngine.GET("/unload", pm.unloadAllModelsHandler)
 	pm.ginEngine.GET("/running", pm.listRunningProcessesHandler)
+	pm.ginEngine.GET("/health", func(c *gin.Context) {
+		c.String(http.StatusOK, "OK")
+	})
 
 	pm.ginEngine.GET("/favicon.ico", func(c *gin.Context) {
 		if data, err := reactStaticFS.ReadFile("ui_dist/favicon.ico"); err == nil {
@@ -366,7 +377,13 @@ func (pm *ProxyManager) proxyOAIHandler(c *gin.Context) {
 		return
 	}
 
-	processGroup, realModelName, err := pm.swapProcessGroup(requestedModel)
+	realModelName, found := pm.config.RealModelName(requestedModel)
+	if !found {
+		pm.sendErrorResponse(c, http.StatusBadRequest, fmt.Sprintf("could not find real modelID for %s", requestedModel))
+		return
+	}
+
+	processGroup, _, err := pm.swapProcessGroup(realModelName)
 	if err != nil {
 		pm.sendErrorResponse(c, http.StatusInternalServerError, fmt.Sprintf("error swapping process group: %s", err.Error()))
 		return

proxy/proxymanager_api.go

@@ -24,6 +24,7 @@ func addApiHandlers(pm *ProxyManager) {
 	{
 		apiGroup.POST("/models/unload", pm.apiUnloadAllModels)
 		apiGroup.GET("/events", pm.apiSendEvents)
+		apiGroup.GET("/metrics", pm.apiGetMetrics)
 	}
 }
 
@@ -85,6 +86,7 @@ type messageType string
 const (
 	msgTypeModelStatus messageType = "modelStatus"
 	msgTypeLogData     messageType = "logData"
+	msgTypeMetrics     messageType = "metrics"
 )
 
 type messageEnvelope struct {
@@ -130,6 +132,18 @@ func (pm *ProxyManager) apiSendEvents(c *gin.Context) {
 		}
 	}
 
+	sendMetrics := func(metrics TokenMetrics) {
+		jsonData, err := json.Marshal(metrics)
+		if err == nil {
+			select {
+			case sendBuffer <- messageEnvelope{Type: msgTypeMetrics, Data: string(jsonData)}:
+			case <-ctx.Done():
+				return
+			default:
+			}
+		}
+	}
+
 	/**
 	 * Send updated models list
 	 */
@@ -150,10 +164,20 @@ func (pm *ProxyManager) apiSendEvents(c *gin.Context) {
 		sendLogData("upstream", data)
 	})()
 
+	/**
+	 * Send Metrics data
+	 */
+	defer event.On(func(e TokenMetricsEvent) {
+		sendMetrics(e.Metrics)
+	})()
+
 	// send initial batch of data
 	sendLogData("proxy", pm.proxyLogger.GetHistory())
 	sendLogData("upstream", pm.upstreamLogger.GetHistory())
 	sendModels()
+	for _, metrics := range pm.metricsMonitor.GetMetrics() {
+		sendMetrics(metrics)
+	}
 
 	for {
 		select {
@@ -169,3 +193,12 @@ func (pm *ProxyManager) apiSendEvents(c *gin.Context) {
 		}
 	}
 }
+
+func (pm *ProxyManager) apiGetMetrics(c *gin.Context) {
+	jsonData, err := pm.metricsMonitor.GetMetricsJSON()
+	if err != nil {
+		c.JSON(http.StatusInternalServerError, gin.H{"error": "failed to get metrics"})
+		return
+	}
+	c.Data(http.StatusOK, "application/json", jsonData)
+}

proxy/proxymanager_test.go

@@ -165,9 +165,11 @@ func TestProxyManager_SwapMultiProcessParallelRequests(t *testing.T) {
 			}
 
 			mu.Lock()
-			var response map[string]string
+			var response map[string]interface{}
 			assert.NoError(t, json.Unmarshal(w.Body.Bytes(), &response))
-			results[key] = response["responseMessage"]
+			result, ok := response["responseMessage"].(string)
+			assert.Equal(t, ok, true)
+			results[key] = result
 			mu.Unlock()
 		}(key)
 
@@ -644,7 +646,7 @@ func TestProxyManager_ChatContentLength(t *testing.T) {
 
 	proxy.ServeHTTP(w, req)
 	assert.Equal(t, http.StatusOK, w.Code)
-	var response map[string]string
+	var response map[string]interface{}
 	assert.NoError(t, json.Unmarshal(w.Body.Bytes(), &response))
 	assert.Equal(t, "81", response["h_content_length"])
 	assert.Equal(t, "model1", response["responseMessage"])
@@ -672,7 +674,7 @@ func TestProxyManager_FiltersStripParams(t *testing.T) {
 
 	proxy.ServeHTTP(w, req)
 	assert.Equal(t, http.StatusOK, w.Code)
-	var response map[string]string
+	var response map[string]interface{}
 	assert.NoError(t, json.Unmarshal(w.Body.Bytes(), &response))
 
 	// `temperature` and `stream` are gone but model remains
@@ -683,3 +685,91 @@ func TestProxyManager_FiltersStripParams(t *testing.T) {
 	// assert.Equal(t, "abc", response["y_param"])
 	// t.Logf("%v", response)
 }
+
+func TestProxyManager_MiddlewareWritesMetrics_NonStreaming(t *testing.T) {
+	config := AddDefaultGroupToConfig(Config{
+		HealthCheckTimeout: 15,
+		Models: map[string]ModelConfig{
+			"model1": getTestSimpleResponderConfig("model1"),
+		},
+		LogLevel: "error",
+	})
+
+	proxy := New(config)
+	defer proxy.StopProcesses(StopWaitForInflightRequest)
+
+	// Make a non-streaming request
+	reqBody := `{"model":"model1", "stream": false}`
+	req := httptest.NewRequest("POST", "/v1/chat/completions", bytes.NewBufferString(reqBody))
+	w := httptest.NewRecorder()
+
+	proxy.ServeHTTP(w, req)
+	assert.Equal(t, http.StatusOK, w.Code)
+
+	// Check that metrics were recorded
+	metrics := proxy.metricsMonitor.GetMetrics()
+	if !assert.NotEmpty(t, metrics, "metrics should be recorded for non-streaming request") {
+		return
+	}
+
+	// Verify the last metric has the correct model
+	lastMetric := metrics[len(metrics)-1]
+	assert.Equal(t, "model1", lastMetric.Model)
+	assert.Equal(t, 25, lastMetric.InputTokens, "input tokens should be 25")
+	assert.Equal(t, 10, lastMetric.OutputTokens, "output tokens should be 10")
+	assert.Greater(t, lastMetric.TokensPerSecond, 0.0, "tokens per second should be greater than 0")
+	assert.Greater(t, lastMetric.DurationMs, 0, "duration should be greater than 0")
+}
+
+func TestProxyManager_MiddlewareWritesMetrics_Streaming(t *testing.T) {
+	config := AddDefaultGroupToConfig(Config{
+		HealthCheckTimeout: 15,
+		Models: map[string]ModelConfig{
+			"model1": getTestSimpleResponderConfig("model1"),
+		},
+		LogLevel: "error",
+	})
+
+	proxy := New(config)
+	defer proxy.StopProcesses(StopWaitForInflightRequest)
+
+	// Make a streaming request
+	reqBody := `{"model":"model1", "stream": true}`
+	req := httptest.NewRequest("POST", "/v1/chat/completions?stream=true", bytes.NewBufferString(reqBody))
+	w := httptest.NewRecorder()
+
+	proxy.ServeHTTP(w, req)
+	assert.Equal(t, http.StatusOK, w.Code)
+
+	// Check that metrics were recorded
+	metrics := proxy.metricsMonitor.GetMetrics()
+	if !assert.NotEmpty(t, metrics, "metrics should be recorded for streaming request") {
+		return
+	}
+
+	// Verify the last metric has the correct model
+	lastMetric := metrics[len(metrics)-1]
+	assert.Equal(t, "model1", lastMetric.Model)
+	assert.Equal(t, 25, lastMetric.InputTokens, "input tokens should be 25")
+	assert.Equal(t, 10, lastMetric.OutputTokens, "output tokens should be 10")
+	assert.Greater(t, lastMetric.TokensPerSecond, 0.0, "tokens per second should be greater than 0")
+	assert.Greater(t, lastMetric.DurationMs, 0, "duration should be greater than 0")
+}
+
+func TestProxyManager_HealthEndpoint(t *testing.T) {
+	config := AddDefaultGroupToConfig(Config{
+		HealthCheckTimeout: 15,
+		Models: map[string]ModelConfig{
+			"model1": getTestSimpleResponderConfig("model1"),
+		},
+		LogLevel: "error",
+	})
+
+	proxy := New(config)
+	defer proxy.StopProcesses(StopWaitForInflightRequest)
+	req := httptest.NewRequest("GET", "/health", nil)
+	rec := httptest.NewRecorder()
+	proxy.ServeHTTP(rec, req)
+	assert.Equal(t, http.StatusOK, rec.Code)
+	assert.Equal(t, "OK", rec.Body.String())
+}

ui/src/App.tsx

@@ -3,6 +3,7 @@ import { useTheme } from "./contexts/ThemeProvider";
 import { APIProvider } from "./contexts/APIProvider";
 import LogViewerPage from "./pages/LogViewer";
 import ModelPage from "./pages/Models";
+import ActivityPage from "./pages/Activity";
 
 function App() {
   const theme = useTheme();
@@ -21,6 +22,10 @@ function App() {
                 <NavLink to="/models" className={({ isActive }) => (isActive ? "navlink active" : "navlink")}>
                   Models
                 </NavLink>
+
+                <NavLink to="/activity" className={({ isActive }) => (isActive ? "navlink active" : "navlink")}>
+                  Activity
+                </NavLink>
                 <button className="btn btn--sm" onClick={theme.toggleTheme}>
                   {theme.isDarkMode ? "🌙" : "☀️"}
                 </button>
@@ -32,6 +37,7 @@ function App() {
             <Routes>
               <Route path="/" element={<LogViewerPage />} />
               <Route path="/models" element={<ModelPage />} />
+              <Route path="/activity" element={<ActivityPage />} />
               <Route path="*" element={<Navigate to="/" replace />} />
             </Routes>
           </main>

ui/src/contexts/APIProvider.tsx

@@ -19,30 +19,41 @@ interface APIProviderType {
   enableAPIEvents: (enabled: boolean) => void;
   proxyLogs: string;
   upstreamLogs: string;
+  metrics: Metrics[];
 }
+
+interface Metrics {
+  id: number;
+  timestamp: string;
+  model: string;
+  input_tokens: number;
+  output_tokens: number;
+  tokens_per_second: number;
+  duration_ms: number;
+}
+
 interface LogData {
   source: "upstream" | "proxy";
   data: string;
 }
 interface APIEventEnvelope {
-  type: "modelStatus" | "logData";
+  type: "modelStatus" | "logData" | "metrics";
   data: string;
 }
 
 const APIContext = createContext<APIProviderType | undefined>(undefined);
 type APIProviderProps = {
   children: ReactNode;
+  autoStartAPIEvents?: boolean;
 };
 
-export function APIProvider({ children }: APIProviderProps) {
+export function APIProvider({ children, autoStartAPIEvents = true }: APIProviderProps) {
   const [proxyLogs, setProxyLogs] = useState("");
   const [upstreamLogs, setUpstreamLogs] = useState("");
-  const proxyEventSource = useRef<EventSource | null>(null);
-  const upstreamEventSource = useRef<EventSource | null>(null);
+  const [metrics, setMetrics] = useState<Metrics[]>([]);
   const apiEventSource = useRef<EventSource | null>(null);
 
   const [models, setModels] = useState<Model[]>([]);
-  const modelStatusEventSource = useRef<EventSource | null>(null);
 
   const appendLog = useCallback((newData: string, setter: React.Dispatch<React.SetStateAction<string>>) => {
     setter((prev) => {
@@ -55,6 +66,7 @@ export function APIProvider({ children }: APIProviderProps) {
     if (!enabled) {
       apiEventSource.current?.close();
       apiEventSource.current = null;
+      setMetrics([]);
       return;
     }
 
@@ -75,7 +87,7 @@ export function APIProvider({ children }: APIProviderProps) {
               }
               break;
 
-            case "logData": {
+            case "logData":
               const logData = JSON.parse(message.data) as LogData;
               switch (logData.source) {
                 case "proxy":
@@ -85,7 +97,16 @@ export function APIProvider({ children }: APIProviderProps) {
                   appendLog(logData.data, setUpstreamLogs);
                   break;
               }
-            }
+              break;
+
+            case "metrics":
+              {
+                const newMetric = JSON.parse(message.data) as Metrics;
+                setMetrics((prevMetrics) => {
+                  return [newMetric, ...prevMetrics];
+                });
+              }
+              break;
           }
         } catch (err) {
           console.error(e.data, err);
@@ -105,12 +126,14 @@ export function APIProvider({ children }: APIProviderProps) {
   }, []);
 
   useEffect(() => {
+    if (autoStartAPIEvents) {
+      enableAPIEvents(true);
+    }
+
     return () => {
-      proxyEventSource.current?.close();
-      upstreamEventSource.current?.close();
-      modelStatusEventSource.current?.close();
+      enableAPIEvents(false);
     };
-  }, []);
+  }, [enableAPIEvents, autoStartAPIEvents]);
 
   const listModels = useCallback(async (): Promise<Model[]> => {
     try {
@@ -163,8 +186,9 @@ export function APIProvider({ children }: APIProviderProps) {
       enableAPIEvents,
       proxyLogs,
       upstreamLogs,
+      metrics,
     }),
-    [models, listModels, unloadAllModels, loadModel, enableAPIEvents, proxyLogs, upstreamLogs]
+    [models, listModels, unloadAllModels, loadModel, enableAPIEvents, proxyLogs, upstreamLogs, metrics]
   );
 
   return <APIContext.Provider value={value}>{children}</APIContext.Provider>;

ui/src/lib/Utils.ts

@@ -1,18 +0,0 @@
-export function processEvalTimes(text: string) {
-  const lines = text.match(/^ *eval time.*$/gm) || [];
-
-  let totalTokens = 0;
-  let totalTime = 0;
-
-  lines.forEach((line) => {
-    const tokensMatch = line.match(/\/\s*(\d+)\s*tokens/);
-    const timeMatch = line.match(/=\s*(\d+\.\d+)\s*ms/);
-
-    if (tokensMatch) totalTokens += parseFloat(tokensMatch[1]);
-    if (timeMatch) totalTime += parseFloat(timeMatch[1]);
-  });
-
-  const avgTokensPerSecond = totalTime > 0 ? totalTokens / (totalTime / 1000) : 0;
-
-  return [lines.length, totalTokens, Math.round(avgTokensPerSecond * 100) / 100];
-}

ui/src/pages/Activity.tsx

@@ -0,0 +1,77 @@
+import { useState, useEffect } from "react";
+import { useAPI } from "../contexts/APIProvider";
+
+const formatTimestamp = (timestamp: string): string => {
+  return new Date(timestamp).toLocaleString();
+};
+
+const formatSpeed = (speed: number): string => {
+  return speed < 0 ? "unknown" : speed.toFixed(2) + " t/s";
+};
+
+const formatDuration = (ms: number): string => {
+  return (ms / 1000).toFixed(2) + "s";
+};
+
+const ActivityPage = () => {
+  const { metrics } = useAPI();
+  const [error, setError] = useState<string | null>(null);
+
+  useEffect(() => {
+    if (metrics.length > 0) {
+      setError(null);
+    }
+  }, [metrics]);
+
+  if (error) {
+    return (
+      <div className="p-6">
+        <h1 className="text-2xl font-bold mb-4">Activity</h1>
+        <div className="bg-red-50 border border-red-200 rounded-md p-4">
+          <p className="text-red-800">{error}</p>
+        </div>
+      </div>
+    );
+  }
+
+  return (
+    <div className="p-6">
+      <h1 className="text-2xl font-bold mb-4">Activity</h1>
+
+      {metrics.length === 0 ? (
+        <div className="text-center py-8">
+          <p className="text-gray-600">No metrics data available</p>
+        </div>
+      ) : (
+        <div className="overflow-x-auto">
+          <table className="min-w-full divide-y">
+            <thead>
+              <tr>
+                <th className="px-6 py-3 text-left text-xs font-medium uppercase tracking-wider">Timestamp</th>
+                <th className="px-6 py-3 text-left text-xs font-medium uppercase tracking-wider">Model</th>
+                <th className="px-6 py-3 text-left text-xs font-medium uppercase tracking-wider">Input Tokens</th>
+                <th className="px-6 py-3 text-left text-xs font-medium uppercase tracking-wider">Output Tokens</th>
+                <th className="px-6 py-3 text-left text-xs font-medium uppercase tracking-wider">Generation Speed</th>
+                <th className="px-6 py-3 text-left text-xs font-medium uppercase tracking-wider">Duration</th>
+              </tr>
+            </thead>
+            <tbody className="divide-y">
+              {metrics.map((metric, index) => (
+                <tr key={`${metric.id}-${index}`}>
+                  <td className="px-6 py-4 whitespace-nowrap text-sm">{formatTimestamp(metric.timestamp)}</td>
+                  <td className="px-6 py-4 whitespace-nowrap text-sm">{metric.model}</td>
+                  <td className="px-6 py-4 whitespace-nowrap text-sm">{metric.input_tokens.toLocaleString()}</td>
+                  <td className="px-6 py-4 whitespace-nowrap text-sm">{metric.output_tokens.toLocaleString()}</td>
+                  <td className="px-6 py-4 whitespace-nowrap text-sm">{formatSpeed(metric.tokens_per_second)}</td>
+                  <td className="px-6 py-4 whitespace-nowrap text-sm">{formatDuration(metric.duration_ms)}</td>
+                </tr>
+              ))}
+            </tbody>
+          </table>
+        </div>
+      )}
+    </div>
+  );
+};
+
+export default ActivityPage;

ui/src/pages/LogViewer.tsx

@@ -3,14 +3,7 @@ import { useAPI } from "../contexts/APIProvider";
 import { usePersistentState } from "../hooks/usePersistentState";
 
 const LogViewer = () => {
-  const { proxyLogs, upstreamLogs, enableAPIEvents } = useAPI();
-
-  useEffect(() => {
-    enableAPIEvents(true);
-    return () => {
-      enableAPIEvents(false);
-    };
-  }, []);
+  const { proxyLogs, upstreamLogs } = useAPI();
 
   return (
     <div className="flex flex-col gap-5" style={{ height: "calc(100vh - 125px)" }}>

ui/src/pages/Models.tsx

@@ -1,11 +1,10 @@
-import { useState, useEffect, useCallback, useMemo } from "react";
+import { useState, useCallback, useMemo } from "react";
 import { useAPI } from "../contexts/APIProvider";
 import { LogPanel } from "./LogViewer";
-import { processEvalTimes } from "../lib/Utils";
 import { usePersistentState } from "../hooks/usePersistentState";
 
 export default function ModelsPage() {
-  const { models, unloadAllModels, loadModel, upstreamLogs, enableAPIEvents } = useAPI();
+  const { models, unloadAllModels, loadModel, upstreamLogs, metrics } = useAPI();
   const [isUnloading, setIsUnloading] = useState(false);
   const [showUnlisted, setShowUnlisted] = usePersistentState("showUnlisted", true);
 
@@ -13,13 +12,6 @@ export default function ModelsPage() {
     return models.filter((model) => showUnlisted || !model.unlisted);
   }, [models, showUnlisted]);
 
-  useEffect(() => {
-    enableAPIEvents(true);
-    return () => {
-      enableAPIEvents(false);
-    };
-  }, []);
-
   const handleUnloadAllModels = useCallback(async () => {
     setIsUnloading(true);
     try {
@@ -34,9 +26,15 @@ export default function ModelsPage() {
     }
   }, []);
 
-  const [totalLines, totalTokens, avgTokensPerSecond] = useMemo(() => {
-    return processEvalTimes(upstreamLogs);
-  }, [upstreamLogs]);
+  const [totalRequests, totalTokens, avgTokensPerSecond] = useMemo(() => {
+    const totalRequests = metrics.length;
+    if (totalRequests === 0) {
+      return [0, 0, 0];
+    }
+    const totalTokens = metrics.reduce((sum, m) => sum + m.output_tokens, 0);
+    const avgTokensPerSecond = (metrics.reduce((sum, m) => sum + m.tokens_per_second, 0) / totalRequests).toFixed(2);
+    return [totalRequests, totalTokens, avgTokensPerSecond];
+  }, [metrics]);
 
   return (
     <div>
@@ -96,14 +94,13 @@ export default function ModelsPage() {
 
         {/* Right Column */}
         <div className="w-full md:w-1/2 flex flex-col" style={{ height: "calc(100vh - 125px)" }}>
-          <div className="card mb-4 min-h-[250px]">
-            <h2>Log Stats</h2>
-            <p className="italic my-2">note: eval logs from llama-server</p>
+          <div className="card mb-4 min-h-[225px]">
+            <h2>Chat Activity</h2>
             <table className="w-full border border-gray-200">
               <tbody>
                 <tr className="border-b border-gray-200">
                   <td className="py-2 px-4 font-medium border-r border-gray-200">Requests</td>
-                  <td className="py-2 px-4 text-right">{totalLines}</td>
+                  <td className="py-2 px-4 text-right">{totalRequests}</td>
                 </tr>
                 <tr className="border-b border-gray-200">
                   <td className="py-2 px-4 font-medium border-r border-gray-200">Total Tokens Generated</td>